 |
|
|
|
|
Golems Publications
Filter
Journal
Neil T. Dantam and Mike Stilman
The Motion Grammar: Analysis of a Linguistic Method for Robot Control
IEEE/RAS Transactions on Robotics.
no. 3. 2013.
We present the Motion Grammar: an approach to represent and verify
robot control policies based on Context-Free Grammars. The
production rules of the grammar represent a top-down task
decomposition of robot behavior. The terminal symbols of this
language represent sensor readings that are parsed in real-time.
Efficient algorithms for context-free parsing guarantee that online
parsing is computationally tractable. We analyze verification
properties and language constraints of this linguistic modeling
approach, show a linguistic basis that unifies several existing
methods, and demonstrate effectiveness through experiments on a
14-DOF manipulator interacting with 32 objects (chess pieces) and an
unpredictable human adversary. We provide many of the algorithms
discussed as Open Source, permissively licensed software.
@article{dantam2013motion,
title = {The Motion Grammar: Analysis of a Linguistic Method for Robot Control},
number = {3},
volume = {29},
pages = {704--718},
journal = {IEEE/RAS Transactions on Robotics},
author = {Neil T. Dantam and Mike Stilman},
year = {2013}
}
Mike Stilman
Global Manipulation Planing in Robot Joint Space with Task Constraints
IEEE/RAS Transactions on Robotics.
no. 3. 2010.
We explore global randomized joint space path planning for articulated
robots that are subject to task space constraints. This paper
describes a representation of constrained motion for joint space
planners and develops two simple and efficient methods for constrained
sampling of joint configurations: Tangent Space Sampling (TS) and
First-Order Retraction (FR). FR is formally proven to provide global
sampling for linear task space transformations. Constrained joint
space planning is important for many real world problems involving
redundant manipulators. On the one hand, tasks are designated in work
space coordinates: rotating doors about selected axes, sliding
drawers along selected trajectories or holding objects level during
transport. On the other, joint space planning gives alternative paths
that use redundant degrees of freedom to avoid obstacles or satisfy
additional goals while performing a task. We demonstrate that our
methods are faster and more invariant to parameter choices than
existing techniques
@article{stilman2010global,
title = {Global Manipulation Planing in Robot Joint Space with Task Constraints},
number = {3},
volume = {26},
pages = {576--584},
journal = {IEEE/RAS Transactions on Robotics},
author = {Mike Stilman},
year = {2010}
}
Mike Stilman and James Kuffner
Planning Among Movable Obstacles with Artificial Constraints
International Journal of Robotics Research.
no. 12. 2008.
This paper presents artificial constraints as a method for guiding
heuristic search in the computationally challenging domain of motion
planning among movable obstacles. The robot is permitted to manipulate
unspecified obstacles in order to create space for a path. A plan
is an ordered sequence of paths for robot motion and object
manipulation. We show that under monotone assumptions, anticipating
future manipulation paths results in constraints on both the choice of
objects and their placements at earlier stages in the plan. We present
an algorithm that uses this observation to incrementally reduce the
search space and quickly find solutions to previously unsolved classes
of movable obstacle problems. Our planner is developed for arbitrary
robot geometry and kinematics. It is presented with an implementation
for the domain of navigation among movable obstacles
@article{stilman2008planning,
title = {Planning Among Movable Obstacles with Artificial Constraints},
number = {12},
volume = {27},
pages = {1295--1307},
journal = {International Journal of Robotics Research},
author = {Mike Stilman and James Kuffner},
year = {2008}
}
Satoshi Kagami, Koichi Nishiwaki, James Kuffner, Simon Thompson, Joel Chestnutt, Mike Stilman, and Philipp Michel
Humanoid HRP2-DHRC for Autonomous and Interactive Behavior
Robotics Research.
2007.
Recently, research on humanoid-type robots has become increasingly active,
and a broad array of fundamental issues are under investigation. However,
in order to achieve a humanoid robot which can operate in human environ-
ments, not only the fundamental components themselves, but also the suc-
cessful integration of these components will be required. At present, almost
all humanoid robots that have been developed have been designed for bipedal
locomotion experiments. In order to satisfy the functional demands of loco-
motion as well as high-level behaviors, humanoid robots require good me-
chanical design, hardware, and software which can support the integration of
tactile sensing, visual perception, and motor control. Autonomous behaviors
are currently still very primitive for humanoid-type robots. It is difficult to
conduct research on high-level autonomy and intelligence in humanoids due
to the development and maintenance costs of the hardware. We believe low-
level autonomous functions will be required in order to conduct research on
higher-level autonomous behaviors for humanoids.
@article{kagami2007hrp2,
title = {Humanoid HRP2-DHRC for Autonomous and Interactive Behavior},
volume = {28},
pages = {103--117},
journal = {Robotics Research},
author = {Satoshi Kagami and Nishiwaki, Koichi and James Kuffner and Thompson, Simon and Chestnutt, Joel and Mike Stilman and Michel, Philipp},
year = {2007}
}
Mike Stilman, Koichi Nishiwaki, Satoshi Kagami, and James Kuffner
Planning and Executing Navigation Among Movable Obstacles
Springer Journal of Advanced Robotics.
no. 14. 2007.
This paper explores autonomous locomotion, reaching, grasping and
manipulation for the domain of Navigation Among Movable Obstacles
(NAMO). The robot perceives and constructs a model of an environment
filled with various fixed and movable obstacles, and automatically plans
a navigation strategy to reach a desired goal location. The planned
strategy consists of a sequence of walking and compliant manipulation
operations. It is executed by the robot with online feedback. We give
an overview of our NAMO system, as well as provide details of the
autonomous planning, online grasping and compliant hand positioning
during dynamically-stable walking. Finally, we present results of a
successful implementation running on the Humanoid Robot HRP-2.
@article{stilman2007planning,
title = {Planning and Executing Navigation Among Movable Obstacles},
number = {14},
volume = {21},
pages = {1617--1634},
journal = {Springer Journal of Advanced Robotics},
author = {Mike Stilman and Nishiwaki, Koichi and Satoshi Kagami and James Kuffner},
year = {2007}
}
Mike Stilman and James Kuffner
Navigation Among Movable Obstacles: Real-Time Reasoning in Complex Environments
International Journal on Humanoid Robotics.
no. 4. 2005.
In this paper, we address the problem of Navigation Among Movable
Obstacles (NAMO): a practical extension to navigation for humanoids
and other dexterous mobile robots. The robot is permitted to
reconfgure the environment by moving obstacles and clearing free space
for a path. This paper presents a resolution complete planner for a
subclass of NAMO problems. Our planner takes advantage of the
navigational structure through state-space decomposition and heuristic
search. The planning complexity is reduced to the difficulty of the
specified navigation task, rather than the dimensionality of the
multiobject domain. We demonstrate real-time results for spaces that
contain large numbers of movable obstacles. We also present a
practical framework for single-agent search that can be used in
algorithmic reasoning about this domain.
@article{stilman2005navigation,
title = {Navigation Among Movable Obstacles: Real-Time Reasoning in Complex Environments},
number = {4},
volume = {2},
pages = {479--504},
month = {December},
journal = {International Journal on Humanoid Robotics},
author = {Mike Stilman and James Kuffner},
year = {2005}
}
Books and Chapters
Mike Stilman
Autonomous Manipulation of Movable Obstacles
Ch. 8. Ed. Kensuke Harada, Eiichi Yoshida, and Kazuhito Yokoi. University of Chicago Press. 2010.
In this chapter we describe recent progress towards autonomous manipulation
of environment objects. Many tasks, such as nursing home assistance, construction
or search and rescue, require the robot to not only avoid obstacles but also move
them out if its way to make space for reaching the goal. We present algorithms that
decide which objects should be moved, where to move them and how to move them.
Finally, we introduce a complete system that takes into account humanoid balance,
joint limits and fullbody constraints to accomplish environment interaction.
@inbook{stilman2010mphr,
title = {Autonomous Manipulation of Movable Obstacles},
publisher = {University of Chicago Press},
chapter = {8},
edition = {13},
editor = {Kensuke Harada and Eiichi Yoshida and Kazuhito Yokoi},
author = {Mike Stilman},
year = {2010}
}
Conference
- 2014
Martin Levihn, Koichi Nishiwaki, Satoshi Kagami, and Mike Stilman
Autonomous Environment Manipulation to Assist Humanoid Locomotion
IEEE International Conference on Robotics and Automation.
2014.
Legged robots have unique capabilities to traverse complex environments by stepping over and onto objects. Many footstep planners have been developed to take advantage of these capabilities. However, legged robots also have inherent constraints such as a maximum step height and distance. These constraints typically limit their reachable space, independent of footstep planning. Thus, we propose that robots such as humanoid robots that have manipulation capabilities should use them. A robot should autonomously modify its environment if necessary. We present a system that enabled a real robot to use a box to create itself a stair step or place a board on the ground to cross a gap, allowing it to reach its otherwise unreachable goal configuration.
@inproceedings{levihn2014ICRA,
title = {Autonomous Environment Manipulation to Assist Humanoid Locomotion},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Martin Levihn and Nishiwaki, Koichi and Kagami, Satoshi and Mike Stilman},
year = {2014}
}
- 2013
Martin Levihn, Leslie Pack Kaelbling, Tomas Lozano-Perez, and Mike Stilman
Foresight and Reconsideration in Hierarchical Planning and Execution
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2013.
Legged robots have unique capabilities to traverse complex environments by stepping over and onto objects. Many footstep planners have been developed to take advantage of these capabilities. However, legged robots also have inherent constraints such as a maximum step height and distance. These constraints typically limit their reachable space, independent of footstep planning. Thus, we propose that robots such as humanoid robots that have manipulation capabilities should use them. A robot should autonomously modify its environment if necessary. We present a system that enabled a real robot to use a box to create itself a stair step or place a board on the ground to cross a gap, allowing it to reach its otherwise unreachable goal configuration.
@inproceedings{levihn2013IROS,
title = {Foresight and Reconsideration in Hierarchical Planning and Execution},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Martin Levihn and Kaelbling, Leslie Pack and Lozano-Perez, Tomas and Mike Stilman},
year = {2013}
}
Jonathan Scholz, Martin Levihn, and Charles L. Isbell
What Does Physics Bias: A Comparison of Model Priors for Robot Manipulation
1st Multidisciplinary Conference on Reinforcement Learning and Decision Making.
2013.
We explore robot object manipulation as a Bayesian model-based reinforcement learning problem under a collection
of different model priors. Our main contribution is to highlight the limitations of classical non-parametric regression
approaches in the context of online learning, and to introduce an alternative approach based on monolithic physical
inference. The primary motivation for this line of research is to incorporate physical system identification into the RL
model, where it can be integrated with modern approaches to Bayesian structure learning. Overall, our results support
the idea that modern physical simulation tools provide a model space with an appropriate inductive bias for manipulation
problems in natural environments.
@inproceedings{scholz2013RLDM,
title = {What Does Physics Bias: A Comparison of Model Priors for Robot Manipulation},
booktitle = {1st Multidisciplinary Conference on Reinforcement Learning and Decision Making},
author = {Jonathan Scholz and Martin Levihn and Isbell, Charles L.},
year = {2013}
}
Martin Levihn, Matthew Dutton, Alexander Trevor, and Mike Stilman
Detecting Partially Occluded Objects via Segmentation and Validation
IEEE Workshop on Robot Vision (WoRV).
2013.
This paper presents a novel algorithm: Verfied
Partial Object Detector (VPOD) for accurate detection of
partially occluded objects such as furniture in 3D point clouds.
VPOD is implemented and validated on real sensor data
obtained by our robot. It extends Viewpoint Feature Histograms
(VFH) which classify unoccluded objects to also classifying
partially occluded objects such as furniture that might be seen
in typical office environments. To achieve this result, VPOD
employs two strategies. First, object models are segmented
and the object database is extended to include partial models.
Second, once a matching partial object is detected, the complete
object model is aligned back into the scene and verified for
consistency with the point cloud data. Overall, our approach
increases the number of objects found and substantially reduces
false positives due to the verification process.
@inproceedings{levihn2013worv,
title = {Detecting Partially Occluded Objects via Segmentation and Validation},
booktitle = {IEEE Workshop on Robot Vision (WoRV)},
author = {Martin Levihn and Dutton, Matthew and Trevor, Alexander and Mike Stilman},
year = {2013}
}
Can Erdogan and Mike Stilman
Planning in Constraint Space: Automated Design of Functional Structures
IEEE/RSJ International Conference on Robotics and Automation.
2013.
On the path to full autonomy, robotic agents have to
learn how to manipulate their environments for their benefit. In
particular, the ability to design structures that are functional in
overcoming challenges is imperative. The problem of automated
design of functional structures (ADFS) addresses the question
of whether the objects in the environment can be placed in a
useful configuration. In this work, we first make the observation
that the ADFS problem represents a class of problems in
high dimensional, continuous spaces that can be broken down
into simpler subproblems with semantically meaningful actions.
Next, we propose a framework where discrete actions that
induce constraints can partition the solution space effectively.
Subsequently, we solve the original class of problems by searching
over the available actions, where the evaluation criteria for the
search is the feasibility test of the accumulated constraints.
We prove that with a sound feasibility test, our algorithm is
complete. Additionally, we argue that a convexity requirement
on the constraints leads to significant efficiency gains. Finally,
we present successful results to the ADFS problem.
@inproceedings{erdogan2013ADFS,
title = {Planning in Constraint Space: Automated Design of Functional Structures},
pages = {1799-1804},
month = {May},
booktitle = {IEEE/RSJ International Conference on Robotics and Automation},
author = {Can Erdogan and Mike Stilman},
year = {2013}
}
Kyel Ok, Sameer Ansari, Billy Gallagher, William Sica, Frank Dellaert, and Mike Stilman
Path Planning with Uncertainty: Voronoi Uncertainty Fields
IEEE/RSJ International Conference on Robotics and Automation.
2013.
In this paper, a two-level path planning algorithm
that deals with map uncertainty is proposed. The higher
level planner uses modi?ed generalized Voronoi diagrams to
guarantee ?nding a connected path from the start to the goal
if a collision-free path exists. The lower level planner considers
uncertainty of the observed obstacles in the environment and
assigns repulsive forces based on their distance to the robot
and their positional uncertainty. The attractive forces from the
Voronoi nodes and the repulsive forces from the uncertaintybiased potential
fields form a hybrid planner we call Voronoi
Uncertainty Fields (VUF). The proposed planner has two
strong properties: (1) bias against uncertain obstacles, and (2)
completeness. We analytically prove the properties and run
simulations to validate our method in a forest-like environment.
@inproceedings{ok2013voronoi,
title = {Path Planning with Uncertainty: Voronoi Uncertainty Fields},
pages = {4581-4586},
month = {May},
booktitle = {IEEE/RSJ International Conference on Robotics and Automation},
author = {Ok, Kyel and Ansari, Sameer and Gallagher, Billy and Sica, William and Dellaert, Frank and Mike Stilman},
year = {2013}
}
Martin Levihn, Jonathan Scholz, and Mike Stilman
Planning with Movable Obstacles in Continuous Environments with Uncertain Dynamics
IEEE International Conference on Robotics and Automation.
2013.
In this paper we present a decision theoretic
planner for the problem of Navigation Among Movable Obstacles
(NAMO) operating under conditions faced by real
robotic systems. While planners for the NAMO domain exist,
they typically assume a deterministic environment or rely on
discretization of the configuration and action spaces, preventing
their use in practice. In contrast, we propose a planner that
operates in real-world conditions such as uncertainty about the
parameters of workspace objects and continuous configuration
and action (control) spaces.
To achieve robust NAMO planning despite these conditions,
we introduce a novel integration of Monte Carlo simulation
with an abstract MDP construction. We present theoretical and
empirical arguments for time complexity linear in the number
of obstacles as well as a detailed implementation and examples
from a dynamic simulation environment.
@inproceedings{levihn2013MDP,
title = {Planning with Movable Obstacles in Continuous Environments with Uncertain Dynamics},
pages = {3817-3823},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Martin Levihn and Jonathan Scholz and Mike Stilman},
year = {2013}
}
Rowland O'Flaherty, Pete Vieira, M.X. Grey, Paul Oh, Aaron Bobick, Magnus Egerstedt, and Mike Stilman
Humanoid Robot Teleoperation for Tasks with Power Tools
IEEE International Conference on Technologies for Practical Robot Applications.
2013.
This paper presents the implementation of inverse kinematics
to achieve teleoperation of a physical humanoid robot platform.
The humanoid platform will be used to compete in the DARPA
Robot Challenge, which requires autonomous execution of various
search and rescue tasks, such as cutting through walls, which is
a very practical application to robotics. Using a closed-form
kinematic solution and a basic feedback controller, our objective
of executing simple tasks is realized via teleoperation. Joint
limits and singularities are accounted for using the different
cases in the kinematic solution; and a decision method is
implemented to determine how to position the end-effector when
the goal is outside the feasible workspace.
@inproceedings{oflaherty2013teleop,
title = {Humanoid Robot Teleoperation for Tasks with Power Tools},
pages = {119-124},
booktitle = {IEEE International Conference on Technologies for Practical Robot Applications},
author = {Rowland O'Flaherty and Pete Vieira and M.X. Grey and Oh, Paul and Bobick, Aaron and Magnus Egerstedt and Mike Stilman},
year = {2013}
}
M.X. Grey, Neil T. Dantam, Dan M. Lofaro, Paul Oh, Aaron Bobick, Magnus Egerstedt, and Mike Stilman
Multi-Process Control Software for Humanoid Robots
IEEE International Conference on Technologies for Practical Robot Applications.
2013.
Humanoid robots require greater software reliability than traditional
mechantronic systems if they are to perform useful tasks in typical human-oriented
environments. This paper covers a software architecture which distributes the
load of computation and control tasks over multiple processes, enabling fail-safes
within the software. These fail-safes ensure that unexpected crashes or latency
do not produce damaging behavior in the robot. The distribution also
offers benefits for future software development by making the architecture
modular and extensible. Utilizing a low-latency inter-process
communication protocol (Ach), processes are able to communicate with high control frequencies.
The key motivation of this software architecture is to provide a practical framework
for safe and reliable humanoid robot software development. The authors test and
verify this framework on a HUBO2 Plus humanoid robot.
@inproceedings{grey2013architecture,
title = {Multi-Process Control Software for Humanoid Robots},
pages = {190-195},
booktitle = {IEEE International Conference on Technologies for Practical Robot Applications},
author = {M.X. Grey and Neil T. Dantam and Lofaro, Dan M. and Oh, Paul and Bobick, Aaron and Magnus Egerstedt and Mike Stilman},
year = {2013}
}
- 2012
Ana Huamán Quispe and Mike Stilman
Deterministic Motion Planning for Redundant Robots along End-Effector Paths
International Conference on Humanoid Robots (Humanoids).
2012.
In this paper we propose a deterministic approach to solve the Motion
Planning along End-Effector Paths problem (MPEP) for redundant
manipulators. Most of the existing approaches are based on local
optimization techniques, hence they do not offer global guarantees of
finding a path if it exists. Our proposed method is resolution
complete. This feature is achieved by discretizing the Jacobian
nullspace at each waypoint and selecting the next configuration
according to a given heuristic function. To escape from possible local
minima, our algorithm implements a backtracking strategy that allows
our planner to recover from erroneous previous configuration choices
by performing a breadth-first backwards search procedure. We present
the results of simulated experiments performed with diverse
manipulators and a humanoid robot.
@inproceedings{huaman2012nns,
title = {Deterministic Motion Planning for Redundant Robots along End-Effector Paths},
booktitle = {International Conference on Humanoid Robots (Humanoids)},
author = {Ana Huamán Quispe and Mike Stilman},
year = {2012}
}
Neil T. Dantam and Mike Stilman
Robust and Efficient Communication for Real-Time Multi-Process Robot Software
International Conference on Humanoid Robots (Humanoids).
2012.
We present a new Interprocess Communication (IPC) mechanism and
library. Ach is uniquely suited for coordinating drivers, controllers,
and algorithms in complex robotic systems such as humanoid robots.
Ach eliminates the Head-of-Line Blocking problem for applications that
always require access to the newest message. Ach is efficient,
robust, and formally verified. It has been tested and demonstrated on
a variety of physical robotic systems, and we discuss the
implementation on our humanoid robot Golem Krang. Finally, the source
code for Ach is available under an Open Source permissive license.
@inproceedings{dantam2012robust,
title = {Robust and Efficient Communication for Real-Time Multi-Process Robot Software},
booktitle = {International Conference on Humanoid Robots (Humanoids)},
author = {Neil T. Dantam and Mike Stilman},
year = {2012}
}
Neil T. Dantam, Irfan Essa, and Mike Stilman
Linguistic Transfer of Human Assembly Tasks to Robots
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2012.
We demonstrate the automatic transfer of an assembly task from human
to robot. This work extends efforts showing the utility of linguistic
models in verifiable robot control policies by now performing real
visual analysis of human demonstrations to automatically extract a
policy for the task. This method tokenizes each human demonstration
into a sequence of object connection symbols, then transforms the set
of sequences from all demonstrations into an automaton, which
represents the task-language for assembling a desired object.
Finally, we combine this assembly automaton with a kinematic model of
a robot arm to reproduce the demonstrated task.
@inproceedings{dantam2012mgassem,
title = {Linguistic Transfer of Human Assembly Tasks to Robots},
pages = {237--242},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Neil T. Dantam and Irfan Essa and Mike Stilman},
year = {2012}
}
Tobias Kunz and Mike Stilman
Manipulation Planning with Soft Task Constraints
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2012.
We present a randomized configuration space planner that enforces soft workspace task constraints. A soft task constraint allows an interval of feasible values while favoring a given exact value. Previous work only allows for enforcing an exact value or an interval without a specific preference. Soft task constraints are a useful concept in everyday life. For example when carrying a container of liquid we want to keep it as close to the upright position as possible but want to be able to tilt it slightly in order to avoid obstacles. This paper introduces the necessary algorithms for handling such constraints, including projection methods and useful representations of everyday constraints. Our algorithms are evaluated on a series of simulated benchmark problems and shown to yield significant improvement in constraint satisfaction.
@inproceedings{kunz2012soft,
title = {Manipulation Planning with Soft Task Constraints},
pages = {1937--1942},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Tobias Kunz and Mike Stilman},
year = {2012}
}
Neil T. Dantam and Mike Stilman
The Motion Grammar Calculus for Context-Free Hybrid Systems
American Control Conference.
2012.
Best Presentation in Session
This paper provides a method for deriving provably correct controllers
for Hybrid Dynamical Systems with Context-Free discrete dynamics,
nonlinear continuous dynamics, and nonlinear state partitioning. The
proposed method models the system using a Context-Free Motion Grammar
and specifies correct performance using a Regular language
representation such as Linear Temporal Logic. The initial model is
progressively rewritten via a calculus of symbolic transformation
rules until it satisfies the desired specification.
@inproceedings{dantam2012mgcalc,
title = {The Motion Grammar Calculus for Context-Free Hybrid Systems},
pages = {5294--5301},
month = {June},
booktitle = {American Control Conference},
author = {Neil T. Dantam and Mike Stilman},
year = {2012}
}
Neil T. Dantam, Carlos Nieto-Granda, Henrik Christensen, and Mike Stilman
Linguistic Composition of Semantic Maps and Hybrid Controllers
International Symposium on Experimental Robotics.
2012.
This work combines semantic maps with hybrid control models,
generating a direct link between action and environment models to
produce a control policy for mobile manipulation in unstructured
environments. First, we generate a semantic map for our environment
and design a base model of robot action. Then, we combine this map
and action model using the Motion Grammar Calculus to produce a
combined robot-environment model. Using this combined model, we apply
supervisory control to produce a policy for the manipulation task. We
demonstrate this approach on a Segway RMP-200 mobile platform.
@inproceedings{dantam2012composition,
title = {Linguistic Composition of Semantic Maps and Hybrid Controllers},
pages = {17--21},
month = {June},
booktitle = {International Symposium on Experimental Robotics},
author = {Neil T. Dantam and Carlos Nieto-Granda and Henrik Christensen and Mike Stilman},
year = {2012}
}
Scott Koziol, P. Hasler, and Mike Stilman
Robot Path Planning Using Field Programmable Analog Arrays
IEEE International Conference on Robotics and Automation.
2012.
We present the successful application of reconfgurable
Analog-Very-Large-Scale-Integrated(AVLSI) circuits to motion planning
for the AmigoBot robot. Previous research has shown that custom
application-specifc-integrated-circuits (ASICs) can be used for robot
path planning. However, ASICs are typically fixed circuit designs that
require long fabrication times on the order of months. In contrast,
our reconfgurable analog circuits called Field Programmable Analog
Arrays (FPAAs) implement a variety of AVLSI circuits in minutes. We
present experimental results of online robot path planning using FPAA
circuitry, validating our assertion that FPAA-based AVLSI design is a
feasible approach to computing complete motion plans using analog
foating-gate resistive grids. We demonstrate the integration of FPAA
hardware and software with a real robot platform and hardware in the
loop simulations, present the trajectories developed by our planner
and provide analysis of the time and space complexity of our proposed
approach. The paper concludes by formulating metrics that identify
domains where analog solutions to planning may be faster and more
effcient than traditional, digital robot planning techniques.
@inproceedings{koziol2012robot,
title = {Robot Path Planning Using Field Programmable Analog Arrays},
pages = {1747--1752},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Koziol, Scott and P. Hasler and Mike Stilman},
year = {2012}
}
Tobias Kunz and Mike Stilman
Time-Optimal Trajectory Generation for Path Following with Bounded Acceleration and Velocity
Robotics: Science and Systems.
2012.
This paper presents a novel method to generate the time-optimal
trajectory that exactly follows a given differentiable joint-space
path within given bounds on joint accelerations and velocities. We
also present a path preprocessing method to make nondifferentiable
paths differentiable by adding circular blends. We introduce
improvements to existing work that make the algorithm more robust in
the presence of numerical inaccuracies. Furthermore we validate our
methods on hundreds of randomly generated test cases on simulated and
real 7-DOF robot arms. Finally, we provide open source software that
implements our algorithms.
@inproceedings{kunz2012time,
title = {Time-Optimal Trajectory Generation for Path Following with Bounded Acceleration and Velocity},
pages = {09--13},
month = {July},
booktitle = {Robotics: Science and Systems},
author = {Tobias Kunz and Mike Stilman},
year = {2012}
}
Martin Levihn, Takeo Igarashi, and Mike Stilman
Multi-Robot Multi-Object Rearrangement in Assignment Space
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2012.
We present Assignment Space Planning, a new effi- cient robot
multi-agent coordination algorithm for the PSPACE- hard problem of
multi-robot multi-object push rearrangement. In both simulated and
real robot experiments, we demonstrate that our method produces
optimal solutions for simple problems and exhibits novel emergent
behaviors for complex scenarios. Assignment Space takes advantage of
the domain structure by splitting the planning up into three stages,
effectively reducing the search space size and enabling the planner to
produce optimized plans in seconds. Our algorithm finds solutions of
comparable quality to complete configuration space search while
reducing the computing time to seconds, which allows our approach to
be applied in practical scenarios in real-time.
@inproceedings{levihn2012multi,
title = {Multi-Robot Multi-Object Rearrangement in Assignment Space},
pages = {5255--5261},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Martin Levihn and Takeo Igarashi and Mike Stilman},
year = {2012}
}
Martin Levihn, Jonathan Scholz, and Mike Stilman
Hierarchical Decision Theoretic Planning for Navigation Among Movable Obstacles
Workshop on the Algorithmic Foundations of Robotics.
2012.
In this paper we present the first decision theoretic planner for the
problem of Navigation Among Movable Obstacles (NAMO). While efficient
planners for NAMO exist, they are challenging to implement in practice
due to the inherent uncertainty in both perception and control of real
robots. Generalizing existing NAMO planners to nondeterministic
domains is particularly difficult due to the sensitivity of MDP
methods to task dimensionality. Our work addresses this challenge by
combining ideas from Hierarchical Reinforcement Learning with Monte
Carlo Tree Search, and results in an algorithm that can be used for
fast online planning in uncertain environments. We evaluate our
algorithm in simulation, and provide a theoretical argument for our
results which suggest linear time complexity in the number of
obstacles for typical environments.
@inproceedings{levihn2012hierarchical,
title = {Hierarchical Decision Theoretic Planning for Navigation Among Movable Obstacles},
pages = {19--35},
month = {June},
booktitle = {Workshop on the Algorithmic Foundations of Robotics},
author = {Martin Levihn and Jonathan Scholz and Mike Stilman},
year = {2012}
}
Jiuguang Wang, Eric Whitman, and Mike Stilman
Whole-Body Trajectory Optimization for Humanoid Falling
American Control Conference.
2012.
Best Presentation in Session
We present an optimization-based control strategy for generating
whole-body trajectories for humanoid robots in order to minimize
damage in falling. In this work, the falling problem is formulated
using optimal control where we seek to minimize the impulse on impact
with the ground, subject to the full-body dynamics and constraints of
the robot in joint space. We extend previous work in this domain by
numerically solving the resulting optimal control problem, generating
open-loop trajectories by solving an equivalent nonlinear programming
(NLP) problem. These results are illustrated in simulation using the
models of dynamically balancing humanoid robots in both wheeled and
legged forms. Through the comparison of falling trajectories for the
two systems, we demonstrate the advantages of the proposed strategy
over previous work in this domain for the effective reduction of the
impulse at impact.
@inproceedings{wang2012wholebody,
title = {Whole-Body Trajectory Optimization for Humanoid Falling},
pages = {4837--4842},
month = {June},
booktitle = {American Control Conference},
author = {Jiuguang Wang and Whitman, Eric and Mike Stilman},
year = {2012}
}
- 2011
Baris Akgun and Mike Stilman
Sampling Heuristics for Optimal Motion Planning in High Dimension
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2011.
We present a sampling-based motion planner that improves the
performance of the probabilistically optimal RRT* planning
algorithm. Experiments demonstrate that our planner finds a fast
initial path and decreases the cost of this path iteratively. We
identify and address the limitations of RRT* in high-dimensional
configuration spaces. We introduce a sampling bias to facilitate and
accelerate cost decrease in these spaces and a simple node-rejection
criteria to increase efficiency. Finally, we incorporate an existing
bi-directional approach to search which decreases the time to find an
initial path. We analyze our planner on a simple 2D navigation problem
in detail to show its properties and test it on a difficult 7D
manipulation problem to show its effectiveness. Our results
consistently demonstrate improved performance over RRT*
@inproceedings{akgun2011sampling,
title = {Sampling Heuristics for Optimal Motion Planning in High Dimension},
pages = {2640--2645},
month = {September},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Baris Akgun and Mike Stilman},
year = {2011}
}
Akansel Cosgun, Tucker Hermans, Victor Emeli, and Mike Stilman
Push Planning for Object Placement on Cluttered Table Surfaces
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2011.
We present a novel planning algorithm for the problem of placing
objects on a cluttered surface such as a table, counter or floor. The
planner (1) selects a placement for the target object and (2)
constructs a sequence of manipulation actions that create space for
the object. When no continuous space is large enough for direct
placement, the planner leverages means-end analysis and dynamic
simulation to find a sequence of linear pushes that clears the
necessary space. Our heuristic for determining candidate placement
poses for the target object is used to guide the manipulation
search. We show successful results for our algorithm in simulation
@inproceedings{cosgun2011push,
title = {Push Planning for Object Placement on Cluttered Table Surfaces},
pages = {4627--4632},
month = {September},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Cosgun, Akansel and Tucker Hermans and Emeli, Victor and Mike Stilman},
year = {2011}
}
Neil T. Dantam, Pushkar Kolhe, and Mike Stilman
The Motion Grammar for Physical Human-Robot Games
IEEE International Conference on Robotics and Automation.
2011.
SAIC/Georgia Tech Achievement Award
We introduce the Motion Grammar, a powerful new representation for
robot decision making, and validate its properties through the
successful implementation of a physical human-robot game. The Motion
Grammar is a formal tool for task decomposition and hybrid control in
the presence of significant online uncertainty. In this paper, we
describe the Motion Grammar, introduce some of the formal guarantees
it can provide, and represent the entire game of human-robot chess
through a single formal language. This language includes game-play,
safe handling of human motion, uncertainty in piece positions,
misplaced and collapsed pieces. We demonstrate the simple and
effective language formulation through experiments on a 14-DOF
manipulator interacting with 32 objects (chess pieces) and an
unpredictable human adversary.
@inproceedings{dantam2011chess,
title = {The Motion Grammar for Physical Human-Robot Games},
pages = {5463--5469},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Neil T. Dantam and Pushkar Kolhe and Mike Stilman},
year = {2011}
}
Neil T. Dantam and Mike Stilman
The Motion Grammar: Linguistic Perception, Planning, and Control
Robotics: Science and Systems.
2011.
We present and analyze the Motion Grammar: a novel unified
representation for task decomposition, perception, planning, and
control that provides both fast online control of robots in uncertain
environments and the ability to guarantee completeness and
correctness. The grammar represents a policy for the task which is
parsed in real-time based on perceptual input. Branches of the syntax
tree form the levels of a hierarchical decomposition, and the
individual robot sensor readings are given by tokens. We implement
this approach in the interactive game of Yamakuzushi on a physical
robot resulting in a system that repeatably competes with a human
opponent in sustained gameplay for the roughly six minute duration of
each match.
@inproceedings{dantam2011yama,
title = {The Motion Grammar: Linguistic Perception, Planning, and Control},
pages = {49--56},
month = {June},
booktitle = {Robotics: Science and Systems},
author = {Neil T. Dantam and Mike Stilman},
year = {2011}
}
Tobias Kunz, Peter Kingston, Mike Stilman, and Magnus Egerstedt
Dynamic Chess: Strategic Planning for Robot Motion
IEEE International Conference on Robotics and Automation.
2011.
We introduce and experimentally validate a novel algorithmic model for
physical human-robot interaction with hybrid dynamics. Our
computational solutions are complementary to passive and compliant
hardware. We focus on the case where human motion can be predicted. In
these cases, the robot can select optimal motions in response to human
actions and maximize safety. By representing the domain as a Markov
Game, we enable the robot to not only react to the human but also to
construct an infinite horizon optimal policy of actions and
responses. Experimentally, we apply our model to simulated robot sword
defense. Our approach enables a simulated 7-DOF robot arm to block
known attacks in any sequence. We generate optimized blocks and apply
game theoretic tools to choose the best action for the defender in the
presence of an intelligent adversary.
@inproceedings{kunz2011dynamic,
title = {Dynamic Chess: Strategic Planning for Robot Motion},
pages = {3796--3803},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Tobias Kunz and Kingston, Peter and Mike Stilman and Magnus Egerstedt},
year = {2011}
}
- 2010
Takeo Igarashi and Mike Stilman
Homotopic Path Planning on Manifolds for Cabled Mobile Robots
Workshop on the Algorithmic Foundations of Robotics.
2010.
We present two path planning algorithms for mobile robots that are connected
by cable to a fixed base. Our algorithms efficiently compute the
shortest path and control strategy that lead the robot to the target location
considering cable length and obstacle interactions. First, we focus on
cable-obstacle collisions. We introduce and formally analyze algorithms that
build and search an overlapped configuration space manifold. Next, we
present an extension that considers cable-robot collisions. All algorithms are
experimentally validated using a real robot.
@inproceedings{Igarashi2010homotopic,
title = {Homotopic Path Planning on Manifolds for Cabled Mobile Robots},
pages = {1--18},
month = {December},
booktitle = {Workshop on the Algorithmic Foundations of Robotics},
author = {Takeo Igarashi and Mike Stilman},
year = {2010}
}
Pushkar Kolhe, Neil T. Dantam, and Mike Stilman
Dynamic Pushing Strategies for Dynamically Stable Mobile Manipulators
IEEE International Conference on Robotics and Automation.
2010.
This paper presents three effective manipulation strategies for
wheeled, dynamically balancing robots with articulated links. By
comparing these strategies through analysis, simulation and robot
experiments, we show that contact placement and body posture have a
significant impact on the robot's ability to accelerate and displace
environment objects. Given object geometry and friction parameters we
determine the most effective methods for utilizing wheel torque to
perform non-prehensile manipulation.
@inproceedings{kolhe2010dynamic,
title = {Dynamic Pushing Strategies for Dynamically Stable Mobile Manipulators},
pages = {3745--3750},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Pushkar Kolhe and Neil T. Dantam and Mike Stilman},
year = {2010}
}
Tobias Kunz, Ulrich Reiser, Mike Stilman, and Alexander Verl
Real-Time Path Planning for a Robot Arm in Changing Environments
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2010.
We present a practical strategy for real-time path planning for
articulated robot arms in changing environments by integrating PRM for
Changing Environments with 3D sensor data. Our implementation on
Care-O-Bot 3 identifies bottlenecks in the algorithm and introduces
new methods that solve the overall task of detecting obstacles and
planning a path around them in under 100 ms. A fast planner is
necessary to enable the robot to react to quickly changing human
environments. We have tested our implementation in real-world
experiments where a human subject enters the manipulation area, is
detected and safely avoided by the robot. This capability is critical
for future applications in automation and service robotics where
humans will work closely with robots to jointly perform tasks
@inproceedings{kunz2010real,
title = {Real-Time Path Planning for a Robot Arm in Changing Environments},
pages = {5906--5911},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Tobias Kunz and Reiser, Ulrich and Mike Stilman and Verl, Alexander},
year = {2010}
}
Jonathan Scholz and Mike Stilman
Combining Motion Planning and Optimization for Flexible Robot Manipulation
IEEE/RAS International Conference on Humanoid Robotics.
2010.
Best Paper Award
Robots that operate in natural human environments must be capable of
handling uncertain dynamics and underspecified goals. Current solutions
for robot motion planning are split between graph-search methods, such
as RRT and PRM which offer solutions to high-dimensional problems, and
Reinforcement Learning methods, which relieve the need to specify
explicit goals and action dynamics. This paper addresses the gap
between these methods by presenting a task-space probabilistic planner
which solves general manipulation tasks posed as optimization
criteria. Our approach is validated in simulation and on a 7-DOF robot
arm that executes several tabletop manipulation tasks. First, this
paper formalizes the problem of planning in underspecified domains. It
then describes the algorithms necessary for applying this approach to
planar manipulation tasks. Finally it validates the algorithms on a
series of sample tasks that have distinct objectives, multiple objects
with different shapes/dynamics, and even obstacles that interfere with
object motion.
@inproceedings{scholz2010combining,
title = {Combining Motion Planning and Optimization for Flexible Robot Manipulation},
pages = {80--85},
month = {December},
booktitle = {IEEE/RAS International Conference on Humanoid Robotics},
author = {Jonathan Scholz and Mike Stilman},
year = {2010}
}
Martin Schuster, Richard Bormann, Daniela Steidl, Saul Reynolds-Haertle, and Mike Stilman
Stable Stacking for the Distributor's Pallet Packing Problem
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2010.
We present a novel algorithm that solves the distributor's pallet
packing problem. In contrast to existing algorithms, our method
optimizes stack stability in addition to stack volume. Furthermore,
our algorithm explicitly handles cases where the construction of
homogeneous layers of packages with equal height is impossible due to
differences in package heights and quantities. The algorithm is a
nested beam search that separately optimizes local and global
evaluation criteria. We show successful results on both real world
and synthetic data sets, compare our performance to an existing
algorithm and demonstrate experimental applications in simulation and
on a real palletizing robo
@inproceedings{schuster2010stable,
title = {Stable Stacking for the Distributor's Pallet Packing Problem},
pages = {3646--3651},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Schuster, Martin and Bormann, Richard and Steidl, Daniela and Saul Reynolds-Haertle and Mike Stilman},
year = {2010}
}
Mike Stilman, Jon Olson, and William Gloss
Golem Krang: Dynamically Stable Humanoid Robot for Mobile Manipulation
IEEE International Conference on Robotics and Automation.
2010.
What would humans be like if nature had invented the wheel? Golem
Krang is a novel humanoid torso designed at Georgia Tech. The robot
dynamically transforms from a .5 m static to a 1.5 m dynamic
configuration. Our robot development has led to two advances in the
design of platforms for mobility and manipulation: (1) A 2-DOF robot
base that autonomously stands from horizontal rest; (2) A 4-DOF
humanoid torso that adds a waist roll joint to replicate human torso
folding and a yaw joint for spine rotation. The mobile torso also
achieves autonomous standing in a constrained space while lifting a 40
kg payload. Golem validates our assertions by consistently achieving
static-dynamic transformations. This paper describes the design of our
mobile torso. It considers a number of factors including its
suitability for human environments, mechanical simplicity and the
ability to store potential and kinetic energy for handling heavy human
and even super-human tasks
@inproceedings{stilman2010golem,
title = {Golem Krang: Dynamically Stable Humanoid Robot for Mobile Manipulation},
pages = {3304--3309},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Mike Stilman and Olson, Jon and Gloss, William},
year = {2010}
}
Hai-Ning Wu, Martin Levihn, and Mike Stilman
Navigation Among Movable Obstacles in Unknown Environments
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2010.
This paper explores the Navigation Among Movable Obstacles (NAMO)
problem in an unknown environment. We consider the realistic scenario
in which the robot has to navigate to a goal position in an unknown
environment consisting of static and movable objects. The robot may
move objects if the goal can not be reached otherwise or if moving the
object may significantly shorten the path to the goal. We consider
real situations in which the robot only has limited sensing
information and where the action selection can therefore only be based
on partial knowledge learned from the environment at that point. This
paper introduces an algorithm that significantly reduces the necessary
calculations to accomplish this task compared to a direct approach. We
present an efficient implementation for the case of planar,
axis-aligned environments and report experimental results on
challenging scenarios with more than 50 objects
@inproceedings{wu2010navigation,
title = {Navigation Among Movable Obstacles in Unknown Environments},
pages = {1433--1438},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Wu, Hai-Ning and Martin Levihn and Mike Stilman},
year = {2010}
}
Kasemsit Teeyapan, Jiuguang Wang, Tobias Kunz, and Mike Stilman
Robot Limbo: Optimized Planning and Control for Dynamically Stable Robots Under Vertical Obstacles
IEEE International Conference on Robotics and Automation.
2010.
We present successful control strategies for dynamically stable robots
that avoid low ceilings and other vertical obstacles in a manner
similar to limbo dances. Given the parameters of the mission,
including the goal and obstacle dimensions, our method uses a
sequential composition of IOlinearized controllers and applies
stochastic optimization to automatically compute the best controller
gains and references, as well as the times for switching between the
different controllers. We demonstrate this system through numerical
simulations, validation in a physics-based simulation environment, as
well as on a novel two-wheeled platform. The results show that the
generated control strategies are successful in mission planning for
this challenging problem domain and offer significant advantages over
hand-tuned alternative
@inproceedings{teeyapan2010limbo,
title = {Robot Limbo: Optimized Planning and Control for Dynamically Stable Robots Under Vertical Obstacles},
pages = {4519--4524},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Teeyapan, Kasemsit and Jiuguang Wang and Tobias Kunz and Mike Stilman},
year = {2010}
}
- 2009
Jiuguang Wang, Philip Rogers, Lonnie Parker, Douglas Brooks, and Mike Stilman
Robot Jenga: Autonomous and Strategic Block Extraction
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2009.
This paper describes our successful implementation of a robot that
autonomously and strategically removes multiple blocks from an
unstable Jenga tower. We present an integrated strategy for
perception, planning and control that achieves repeatable performance
in this challenging physical domain. In contrast to previous
implementations, we rely only on low-cost, readily available system
components and use strategic algorithms to resolve system
uncertainty. We present a three-stage planner for block extraction
which considers block selection, extraction order, and physics-based
simulation that evaluates removability. Existing vision techniques are
combined in a novel sequence for the identification and tracking of
blocks within the tower. Discussion of our approach is presented
following experimental results on a 5-DOF robot manipulator
@inproceedings{wang2009jenga,
title = {Robot Jenga: Autonomous and Strategic Block Extraction},
pages = {5248--5253},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Jiuguang Wang and Rogers, Philip and Parker, Lonnie and Brooks, Douglas and Mike Stilman},
year = {2009}
}
Mike Stilman, Jiuguang Wang, Kasemsit Teeyapan, and Ray Marceau
Optimized Control Strategies for Wheeled Humanoids and Mobile Manipulators
IEEE/RAS International Conference on Humanoid Robotics.
2009.
Best Paper Finalist
Optimizing the control of articulated mobile robots leads to emergent
behaviors that improve the effectiveness, efficiency and stability of
wheeled humanoids and dynamically stable mobile manipulators. Our
simulated results show that optimization over the target pose, height
and control parameters results in effective strategies for standing,
acceleration and deceleration. These strategies improve system
performance by orders of magnitude over existing controllers. This
paper presents a simple controller for robot motion and an
optimization method for choosing its parameters. By using whole-body
articulation, we achieve new skills such as standing and unprecedented
levels of performance for acceleration and deceleration of the robot
base. We describe a new control architecture, present a method for
optimization, and illustrate its functionality through two distinct
methods of simulation
@inproceedings{stilman2009optimized,
title = {Optimized Control Strategies for Wheeled Humanoids and Mobile Manipulators},
pages = {568--573},
month = {December},
booktitle = {IEEE/RAS International Conference on Humanoid Robotics},
author = {Mike Stilman and Jiuguang Wang and Teeyapan, Kasemsit and Marceau, Ray},
year = {2009}
}
- 2008
Mike Stilman, Koichi Nishiwaki, and Satoshi Kagami
Humanoid Teleoperation For Whole Body Manipulation
IEEE International Conference on Robotics and Automation.
2008.
We present results of successful telemanipulation of large, heavy
objects by a humanoid robot. Using a single joystick the operator
controls walking and whole body manipulation along arbitrary paths for
up to ten minutes of continuous execution. The robot grasps, walks,
pushes, pulls, turns and re-grasps a 55kg range of loads on
casters. Our telemanipulation framework changes reference frames
online to let the operator steer the robot in free walking, its hands
in grasping and the object during mobile manipulation. In the case of
manipulation, our system computes a robot motion that satisfies the
commanded object path as well as the kinematic and dynamic constraints
of the robot. Furthermore, we achieve increased robot stability by
learning dynamic friction models of manipulated objects
@inproceedings{stilman2008humanoid,
title = {Humanoid Teleoperation For Whole Body Manipulation},
pages = {3175--3180},
month = {May},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Mike Stilman and Nishiwaki, Koichi and Satoshi Kagami},
year = {2008}
}
Jur van den Berg, Mike Stilman, James Kuffner, Ming Lin, and Dinesh Manocha
Path Planning Among Movable Obstacles: A Probabilistically Complete Approach
Workshop on the Algorithmic Foundation of Robotics.
2008.
In this paper we study the problem of path planning among movable
obstacles, in which a robot is allowed to move the obstacles if they
block the robot's way from a start to a goal position. We make the
observation that we can decouple the computations of the robot motions
and the obstacle movements, and present a probabilistically complete
algorithm, something which to date has not been achieved for this
problem. Our algorithm maintains an explicit representation of the
robot's configuration space. We present an eficient implementation for
the case of planar, axis-aligned environments and report experimental
results on challenging scenarios
@inproceedings{vandenberg2008path,
title = {Path Planning Among Movable Obstacles: A Probabilistically Complete Approach},
pages = {599--614},
month = {December},
booktitle = {Workshop on the Algorithmic Foundation of Robotics},
author = {Jur van den Berg and Mike Stilman and James Kuffner and Lin, Ming and Manocha, Dinesh},
year = {2008}
}
- 2007
Mike Stilman, Koichi Nishiwaki, and Satoshi Kagami
Learning Object Models for Humanoid Manipulation
IEEE/RAS International Conference on Humanoid Robotics.
2007.
We present a successful implementation of rigid grasp manipulation for
large objects moved along specified trajectories by a humanoid
robot. HRP-2 manipulates tables on casters with a range of loads up to
its own mass. The robot maintains dynamic balance by controlling its
center of gravity to compensate for refiected forces. To achieve high
performance for large objects with unspecified dynamics the robot
learns a friction model for each object and applies it to torso
trajectory generation. We empirically compare this method to a purely
reactive strategy and show a significant increase in predictive power
and stability.
@inproceedings{stilman2007learning,
title = {Learning Object Models for Humanoid Manipulation},
pages = {174--179},
month = {November},
booktitle = {IEEE/RAS International Conference on Humanoid Robotics},
author = {Mike Stilman and Nishiwaki, Koichi and Satoshi Kagami},
year = {2007}
}
Mike Stilman, Jan-Ullrich Schamburek, James Kuffner, and Tamim Asfour
Manipulation planning among movable obstacles
IEEE International Conference on Robotics and Automation.
2007.
This paper presents the ResolveSpatialConstraints (RSC) algorithm for
manipulation planning in a domain with movable obstacles. Empirically
we show that our algorithm quickly generates plans for simulated
articulated robots in a highly nonlinear search space of exponential
dimension. RSC is a reverse-time search that samples future robot
actions and constrains the space of prior object displacements. To
optimize the efficiency of RSC, we identify methods for sampling object
surfaces and generating connecting paths between grasps and
placements. In addition to experimental analysis of RSC, this paper
looks into object placements and task-space motion constraints among
other unique features of the three dimensional manipulation planning
domain.
@inproceedings{stilman2007manipulation,
title = {Manipulation planning among movable obstacles},
pages = {3327--3332},
month = {April},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Mike Stilman and Schamburek, Jan-Ullrich and James Kuffner and Tamim Asfour},
year = {2007}
}
Mike Stilman
Task Constrained Motion Planning in Robot Joint Space
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2007.
We explore global randomized joint space path planning for articulated
robots that are subject to task space constraints. This paper
describes a representation of constrained motion for joint space
planners and develops two simple and efficient methods for constrained
sampling of joint configurations: Tangent Space Sampling (TS) and
First-Order Retraction (FR). Constrained joint space planning is
important for many real world problems involving redundant
manipulators. On the one hand, tasks are designated in work space
coordinates: rotating doors about fixed axes, sliding drawers along
fixed trajectories or holding objects level during transport. On the
other, joint space planning gives alternative paths that use redundant
degrees of freedom to avoid obstacles or satisfy additional goals
while performing a task. In simulation, we demonstrate that our
methods are faster and significantly more invariant to
problem/algorithm parameters than existing techniques
@inproceedings{stilman2007task,
title = {Task Constrained Motion Planning in Robot Joint Space},
pages = {3074--3081},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Mike Stilman},
year = {2007}
}
Satoshi Kagami, Koichi Nishiwaki, James Kuffner, Simon Thompson, Joel Chestnutt, Mike Stilman, and Philipp Michel
Humanoid HRP2-DHRC Autonomous and Interactive Behavior
Robotics Research: Results of the 12th International Symposium ISRR.
Ch. 11. Ed. Thrun, S., Brooks, R.A., and Durrant-Whyte, H.F.. Springer Verlag. 2007.
Recently, research on humanoid-type robots has become increasingly active,
and a broad array of fundamental issues are under investigation. However,
in order to achieve a humanoid robot which can operate in human environ-
ments, not only the fundamental components themselves, but also the suc-
cessful integration of these components will be required. At present, almost
all humanoid robots that have been developed have been designed for bipedal
locomotion experiments. In order to satisfy the functional demands of loco-
motion as well as high-level behaviors, humanoid robots require good me-
chanical design, hardware, and software which can support the integration of
tactile sensing, visual perception, and motor control. Autonomous behaviors
are currently still very primitive for humanoid-type robots. It is difficult to
conduct research on high-level autonomy and intelligence in humanoids due
to the development and maintenance costs of the hardware. We believe low-
level autonomous functions will be required in order to conduct research on
higher-level autonomous behaviors for humanoids.
@inproceedings{kagami2007humanoid,
title = {Humanoid HRP2-DHRC Autonomous and Interactive Behavior},
pages = {103--117},
publisher = {Springer Verlag},
chapter = {11},
editor = {Thrun, S. and Brooks, R.A. and Durrant-Whyte, H.F.},
booktitle = {Robotics Research: Results of the 12th International Symposium ISRR},
author = {Satoshi Kagami and Nishiwaki, Koichi and James Kuffner and Thompson, Simon and Chestnutt, Joel and Mike Stilman and Michel, Philipp},
year = {2007}
}
- 2006
Mike Stilman, Koichi Nishiwaki, Satoshi Kagami, and James Kuffner
Planning and Executing Navigation Among Movable Obstacles
IEEE/RSJ International Conference on Intelligent Robots and Systems.
2006.
This paper explores autonomous locomotion, reaching, grasping and
manipulation for the domain of Navigation Among Movable Obstacles
(NAMO). The robot perceives and constructs a model of an environment
filled with various fixed and movable obstacles, and automatically plans
a navigation strategy to reach a desired goal location. The planned
strategy consists of a sequence of walking and compliant manipulation
operations. It is executed by the robot with online feedback. We give
an overview of our NAMO system, as well as provide details of the
autonomous planning, online grasping and compliant hand positioning
during dynamically-stable walking. Finally, we present results of a
successful implementation running on the Humanoid Robot HRP-2
@inproceedings{stlman2006planning,
title = {Planning and Executing Navigation Among Movable Obstacles},
pages = {1617--1634},
month = {October},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
author = {Mike Stilman and Nishiwaki, Koichi and Satoshi Kagami and James Kuffner},
year = {2006}
}
Mike Stilman and James Kuffner
Planning Among Movable Obstacles with Artificial Constraints
Workshop on the Algorithmic Foundations of Robotics.
2006.
This paper presents artiificial constraints as a method for guiding
heuristic search in the computationally challenging domain of motion
planning among movable obstacles. The robot is permitted to manipulate
unspecifieed obstacles in order to create space for a path. A plan is an
ordered sequence of paths for robot motion and object manipulation. We
show that under monotone assumptions, anticipating future manipulation
paths results in constraints on both the choice of objects and their
placements at earlier stages in the plan. We present an algorithm that
uses this observation to incrementally reduce the search space and
quickly find solutions to previously unsolved classes of movable
obstacle problems. Our planner is developed for arbitrary robot
geometry and kinematics. It is presented with an implementation for
the domain of navigation among movable obstacles.
@inproceedings{stilman2006planningamong,
title = {Planning Among Movable Obstacles with Artificial Constraints},
pages = {1295--1307},
month = {July},
booktitle = {Workshop on the Algorithmic Foundations of Robotics},
author = {Mike Stilman and James Kuffner},
year = {2006}
}
- 2005
Mike Stilman, Chris Atkeson, James Kuffner, and Garth Zeglin
Dynamic Programming in Reduced Dimensional Spaces: Dynamic Planning For Robust Biped Locomotion
IEEE International Conference on Robotics and Automation.
2005.
We explore the use of computational optimal control techniques for
automated construction of policies in complex dynamic
environments. Our implementation of dynamic programming is performed
in a reduced dimensional subspace of a simulated four-DOF biped robot
with point feet. We show that a computed solution to this problem can
be generated and yield empirically stable walking that can handle
various types of disturbances.
@inproceedings{stilman2005dynamic,
title = {Dynamic Programming in Reduced Dimensional Spaces: Dynamic Planning For Robust Biped Locomotion},
pages = {2399--2404},
month = {April},
booktitle = {IEEE International Conference on Robotics and Automation},
author = {Mike Stilman and Chris Atkeson and James Kuffner and Zeglin, Garth},
year = {2005}
}
- 2004
Mike Stilman and James Kuffner
Navigation Among Movable Obstacles: Real-time Reasoning in Complex Environments
IEEE/RAS International Conference on Humanoid Robotics.
2004.
In this paper, we address the problem of Navigation Among Movable
Obstacles (NAMO): a practical extension to navigation for humanoids
and other dexterous mobile robots. The robot is permitted to
reconfigure the environment by moving obstacles and clearing free
space for a path. This paper presents a resolution complete planner
for a subclass of NAMO problems. Our planner takes advantage of the
navigational structure through state-space decomposition and heuristic
search. The planning complexity is reduced to the difficulty of the
specific navigation task, rather than the dimensionality of the
multiobject domain. We demonstrate real-time results for spaces that
contain large numbers of movable obstacles. We also present a
practical framework for single-agent search that can be used in
algorithmic reasoning about this domain.
@inproceedings{stilman2004navigation,
title = {Navigation Among Movable Obstacles: Real-time Reasoning in Complex Environments},
pages = {322--341},
month = {November},
booktitle = {IEEE/RAS International Conference on Humanoid Robotics},
author = {Mike Stilman and James Kuffner},
year = {2004}
}
Workshop
Arash Rouhani, Neil T. Dantam, and Mike Stilman
Software-Synthesis via LL(*) for Context-Free Robot Programs
4th Workshop on Formal Methods for Robotics and Automation, RSS.
2013.
Producing reliable software for robotic systems requires formal
techniques to ensure correctness. Some popular approaches model the
discrete dynamics and computation of the robot using finite state
automata or linear temporal logic. We can represent more complicated
systems and tasks, and still retain key guarantees on verifiability
and runtime performance, by modeling the system instead with a
context-free grammar. The challenge with a context-free model is the
need for a more advanced software synthesis algorithm. We address
this challenge by adapting the LL(*) parser generation algorithm,
originally developed for program translation, to the domain of online
robot control. We demonstrate this LL(*) parser generation
implementation in the Motion Grammar Kit, permitting synthesis for
robot control software for complex, hierarchical, and recursive tasks.
@inproceedings{rouhani2013software,
title = {Software-Synthesis via LL(*) for Context-Free Robot Programs},
month = {June},
booktitle = {4th Workshop on Formal Methods for Robotics and Automation, RSS},
author = {Rouhani, Arash and Neil T. Dantam and Mike Stilman},
year = {2013}
}
Neil T. Dantam, Magnus Egerstedt, and Mike Stilman
Make Your Robot Talk Correctly: Deriving Models of Hybrid System
RSS Workshop on Grounding Human-Robot Dialog for Spatial Tasks.
2011.
Using both formal language and differential equations to model a
robotic system, we introduce a calculus of transformation rules for
the symbolic derivation of hybrid controllers. With a Context-Free
Motion Grammar, we show how to test reachability between different
regions of state-space and give several symbolic transformations to
modify the set of event strings the system may generate. This
approach lets one modify the language of the hybrid system, providing
a way to change system behavior so that it satisfies linguistic
constraints on correct operation.
@inproceedings{dantam2011talk,
title = {Make Your Robot Talk Correctly: Deriving Models of Hybrid System},
month = {June},
booktitle = {RSS Workshop on Grounding Human-Robot Dialog for Spatial Tasks},
author = {Neil T. Dantam and Magnus Egerstedt and Mike Stilman},
year = {2011}
}
Victor Emeli, Charlie Kemp, and Mike Stilman
Push Planning for Object Placement in Clutter Using the PR-2.
The PR2 Workshop, IEEE Int. Conf. on Intelligent Robots and Systems.
2011.
The goal of this project is to investigate the implementation of a
planning algorithm for the problem of placing objects on a cluttered
surface with a PR-2 mobile manipulator. The original push planning
algorithm was initially developed as a simulation. We modified the
simulator for execution in real-world cluttered environments. This
paper discusses the challenges of implementation and presents
empirical results that determine how well the simulator models the
real world as clutter is pushed and collides with other objects
@inproceedings{emeli2011push,
title = {Push Planning for Object Placement in Clutter Using the PR-2.},
month = {September},
booktitle = {The PR2 Workshop, IEEE Int. Conf. on Intelligent Robots and Systems},
author = {Emeli, Victor and Charlie Kemp and Mike Stilman},
year = {2011}
}
Technical Reports
Rowland O'Flaherty, Pete Vieira, M.X. Grey, Paul Oh, Aaron Bobick, Magnus Egerstedt, and Mike Stilman
Kinematics and Inverse Kinematics for the Humanoid Robot HUBO2+
no. GT-GOLEM-2013-001. Georgia Institute of Technology, Atlanta, GA. 2013.
This paper derives the forward and inverse kinematics of a humanoid
robot. The specific humanoid that the derivation is for is a robot
with 27 degrees of freedom but the procedure can be easily applied
to other similar humanoid platforms. First, the forward and inverse
kinematics are derived for the arms and legs. Then, the kinematics
for the torso and the head are solved. Finally, the forward and
inverse kinematic solutions for the whole body are derived using
the kinematics of arms, legs, torso, and head.
@techreport{oflaherty2013hubokinematics,
title = {Kinematics and Inverse Kinematics for the Humanoid Robot HUBO2+},
number = {GT-GOLEM-2013-001},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Rowland O'Flaherty and Pete Vieira and M.X. Grey and Oh, Paul and Bobick, Aaron and Magnus Egerstedt and Mike Stilman},
year = {2013}
}
Martin Levihn, Matthew Dutton, Alexander Trevor, and Mike Stilman
Detecting Partially Occluded Objects via Segmentation and Validation
no. GT-GOLEM-2012-001. Georgia Institute of Technology, Atlanta, GA. 2012.
This paper presents a novel algorithm: Verfied Partial Object Detector
(VPOD) for accurate detection of partially occluded objects such as
furniture in 3D point clouds. VPOD is implemented and validated on
real sensor data obtained by our robot. It extends Viewpoint Feature
Histograms (VFH) which classify unoccluded objects to also classifying
partially occluded objects such as furniture that might be seen in
typical office environments. To achieve this result, VPOD employs two
strategies. First, object models are segmented and the object database
is extended to include partial models. Second, once a matching
partial object is detected, the full object model is aligned back into
the scene and verified for consistency with the point cloud
data. Overall, our approach increases the number of objects found and
substantially reduces false positives due to the verification process.
@techreport{levihn2012detecting,
title = {Detecting Partially Occluded Objects via Segmentation and Validation},
number = {GT-GOLEM-2012-001},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Martin Levihn and Dutton, Matthew and Alexander Trevor and Mike Stilman},
year = {2012}
}
Neil T. Dantam, Irfan Essa, and Mike Stilman
Algorithms for Linguistic Robot Policy Inference from Demonstration of Assembly Tasks
no. GT-GOLEM-2012-002. Georgia Institute of Technology, Atlanta, GA. 2012.
We describe several algorithms used for the inference of linguistic
robot policies from human demonstration. First, tracking and match
objects using the Hungarian Algorithm. Then, we convert Regular
Expressions to Nondeterministic Finite Automata (NFA) using the
McNaughton-Yamada-Thompson Algorithm. Next, we use Subset
Construction to convert to a Deterministic Finite Automaton. Finally,
we minimize finite automata using either Hopcroft's Algorithm or
Brzozowski's Algorithm.
@techreport{dantam2012algorithms,
title = {Algorithms for Linguistic Robot Policy Inference from Demonstration of Assembly Tasks},
number = {GT-GOLEM-2012-002},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Neil T. Dantam and Irfan Essa and Mike Stilman},
year = {2012}
}
Tobias Kunz and Mike Stilman
Turning Paths Into Trajectories Using Parabolic Blends
no. GT-GOLEM-2011-004. Georgia Institute of Technology, Atlanta, GA. 2011.
We present an approach for converting a path of multiple continuous
linear segments into a trajectory that satisfies velocity and
acceleration constraints and closely follows the given path without
coming to a complete stop at every waypoint. Our method applies
parabolic blends around waypoints to improve speed. In contrast to
established methods that smooth trajectories with parabolic blends,
our method does not require the timing of waypoints or durations of
blend phases. This makes our approach particularly useful for robots
that must follow kinematic paths that are not explicitly parametrized
by time. Our method chooses timing automatically to achieve high
performance while satisfying the velocity and acceleration constraints
of a given robot.
@techreport{kunz2011turning,
title = {Turning Paths Into Trajectories Using Parabolic Blends},
number = {GT-GOLEM-2011-004},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Tobias Kunz and Mike Stilman},
year = {2011}
}
Tobias Kunz and Mike Stilman
Time-Optimal Path Following with Bounded Joint Accelerations and Velocities
no. GT-GOLEM-2011-005. Georgia Institute of Technology, Atlanta, GA. 2011.
This paper presents a method to generate the time-optimal trajectroy
that exactly follows a given differentiable joint-space path within
given bounds on joint accelerations and velocities. We also present a
path preprocessing method to make nondifferentiable paths
differentiable by adding circular blends.
@techreport{kunz2011time,
title = {Time-Optimal Path Following with Bounded Joint Accelerations and Velocities},
number = {GT-GOLEM-2011-005},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Tobias Kunz and Mike Stilman},
year = {2011}
}
Martin Levihn and Mike Stilman
Efficient Opening Detection
no. GT-GOLEM-2011-002. Georgia Institute of Technology. 2011.
We present an efficient and powerful algorithm for detecting openings.
Openings indicate the existence of a new path for the robot. The reliable
detection of new openings is of great relevance for the domain of moving
objects as a robot typically needs to detect openings for itself to navigate
through. It is also especially relevant to the domain of Navigation Among
Movable Obstacles in known as well as unknown environments. In these domains
a robot has to plan for object manipulations that help it to navigate to the
goal. Tremendous speed-ups for algorithms in these domains can be achieved by
limiting the considerations of obstacle manipulations to cases where
manipulations create new openings. The presented algorithm can detect openings
for obstacles of arbitrary shapes being displaced or moving by themselves, in
arbitrarily directions in changing environments. To the knowledge of the
authors, this is the first algorithm to achieve efficient opening detection
for arbitrary shaped obstacles.
@techreport{levihn2011efficient,
title = {Efficient Opening Detection},
number = {GT-GOLEM-2011-002},
institution = {Georgia Institute of Technology},
author = {Martin Levihn and Mike Stilman},
year = {2011}
}
Neil T. Dantam and Mike Stilman
Ach: IPC for Real-Time Robot Control
no. GT-GOLEM-2011-001. Georgia Institute of Technology, Atlanta, GA. 2011.
We present a new Inter-Process Communication (IPC) mechanism and
library. Ach is uniquely suited for coordinating perception, control
drivers, and algorithms in real-time systems that sample data from
physical processes. Ach eliminates the Head-of-Line Blocking problem
for applications that always require access to the newest message.
Ach is efficient, robust, and formally verified. It has been tested
and demonstrated on a variety of physical robotic systems. Finally,
the source code for Ach is available under an Open Source BSD-style
license.
@techreport{dantam2011achtech,
title = {Ach: IPC for Real-Time Robot Control},
number = {GT-GOLEM-2011-001},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Neil T. Dantam and Mike Stilman},
year = {2011}
}
Saul Reynolds-Haertle and Mike Stilman
Design and Development of a Dynamically-Balancing Holonomic Robot
no. GT-GOLEM-2011-003. Georgia Institute of Technology, Atlanta, GA. 2011.
This paper describes the design, control, and construction of Golem
Wing, the first vehicle which both balances dynamically and has
entirely holonomic ground movement. A nonstandard linear arrangement
of mecanum wheels gives it the load-lifting, performance, and
manipulation benefits of a dynamically-balancing platform without the
maneuvering difficulties exhibited by previous balancing platforms. We
show that the arrangement is capable of holonomic motion, describe a
controller that maintains dynamic balance during holonomic motion, and
show an implementation of the system in hardware that validate our
assertions.
@techreport{reynolds2011design,
title = {Design and Development of a Dynamically-Balancing Holonomic Robot},
number = {GT-GOLEM-2011-003},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Saul Reynolds-Haertle and Mike Stilman},
year = {2011}
}
Neil T. Dantam and Mike Stilman
The Motion Grammar: Linguistic Perception, Planning, and Control
no. GT-GOLEM-2010-001. Georgia Institute of Technology, Atlanta, GA. 2010.
We present the Motion Grammar: a novel unified representation for task
decomposition, perception, planning, and hybrid control that provides
a computationally tractable way to control robots in uncertain
environments with guarantees on completeness and correctness. The
grammar represents a policy for the task which is parsed in real-time
based on perceptual input. Branches of the syntax tree form the levels
of a hierarchical decomposition, and the individual robot sensor
readings are given by tokens. We implement this approach in the
interactive game of Yamakuzushi on a physical robot resulting in a
system that repeatably competes with a human opponent in sustained
game-play for matches up to six minutes.
@techreport{dantam2010mgtech,
title = {The Motion Grammar: Linguistic Perception, Planning, and Control},
number = {GT-GOLEM-2010-001},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Neil T. Dantam and Mike Stilman},
year = {2010}
}
Neil T. Dantam, Pushkar Kolhe, and Mike Stilman
Equations of Motion for Dynamically Stable Mobile Manipulators
no. GT-GOLEM-2010-002. Georgia Institute of Technology, Atlanta, GA. 2010.
Equations of motion for dynamically stable mobile manipulation
@techreport{dantam2010equations,
title = {Equations of Motion for Dynamically Stable Mobile Manipulators},
number = {GT-GOLEM-2010-002},
institution = {Georgia Institute of Technology, Atlanta, GA},
author = {Neil T. Dantam and Pushkar Kolhe and Mike Stilman},
year = {2010}
}
Mike Stilman, Philipp Michel, Joel Chestnutt, Koichi Nishiwaki, Satoshi Kagami, and James Kuffner
Augmented Reality for Robot Development and Experimentation
no. CMU-RI-TR-05-55. Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. 2005.
The successful development of autonomous robotic systems requires
careful fusion of complex subsystems for perception, planning, and
control. Often these subsystems are designed in a modular fashion and
tested individually. However, when ultimately combined with other
components to form a complete system, unexpected interactions between
subsystems can occur that make it difficult to isolate the source of
problems. This paper presents a novel paradigm for robot
experimentation that enables unified testing of individual subsystems
while acting as part of a complete whole made up of both virtual and
real components. We exploit the recent advances in speed and accuracy
of optical motion capture to localize the robot, track environment
objects, and extract extrinsic parameters for moving cameras in
real-time. We construct a world model representation that serves as
ground truth for both visual and tactile sensors in the
environment. From this data, we build spatial and temporal
correspondences between virtual elements, such as motion plans, and
real artifacts in the scene. The system enables safe, decoupled
testing of component algorithms for vision, motion planning and
control that would normally have to be tested simultaneously on actual
hardware. We show results of successful online applications in the
development of an autonomous humanoid robot.
@techreport{stilman2005augmented,
title = {Augmented Reality for Robot Development and Experimentation},
number = {CMU-RI-TR-05-55},
institution = {Robotics Institute, Carnegie Mellon University, Pittsburgh, PA},
author = {Mike Stilman and Michel, Philipp and Chestnutt, Joel and Nishiwaki, Koichi and Satoshi Kagami and James Kuffner},
year = {2005}
}
|
|
|
|
|
|
 |
|