Navigation Among Movable Obstacles (NAMO) |
|
Robots would be far more useful if they could autonomously move obstacles out of the way. Future rescue robots that save humans from disasters such as floods and earthquakes will be required to solve Navigation Among Movable Obstacles (NAMO). Traditional motion planning algorithms search for collision-free paths from the start to the goal. This is not sufficient when the flood waters have caused furniture to float and collapse, leaving no open path to the victims. Instead, the robot must quickly decide which obstacles can be moved to clear a path to the goal. It must choose where to move objects and compute valid motion plans that integrate navigation and manipulation. Our recent work develops practical planning algorithms that take advantage of these options while simultaneously constructing more accurate models of the environment. Project Members:Mike Stilman, Martin Levihn, Ana Huaman, Hai-Ning Wu |
|
Recent Publications:
H. Wu, M. Levihn, M. Stilman Navigation Among Movable Obstacles in Unknown Environments. Int. Conf. on Intelligent Robots and Systems (IROS'10), 2010.
Earlier Results:
- M. Stilman and J. Kuffner. Planning Among Movable Obstacles with Artificial Constraints. International Journal of Robotics Research, 27(12):1295-1307, November 2008.
- M. Stilman, K. Nishiwaki, S. Kagami, and J. Kuffner. Planning and Executing Navigation Among Movable Obstacles. Advanced Robotics, 2007.
- M. Stilman, J. Kuffner. Navigation Among Movable Obstacles: Real-Time Reasoning in Complex Environments. Int. J. of Humanoid Roboitcs, Vol. 2, No. 4, December, 2005 pp. 479-504.
- J. van den Berg, M. Stilman, J. Kuffner, M. Lin, D. Manocha. Path Planning Among Movable Obstacles: A Probabilistically Complete Approach. In. Proc. Workshop on Algorithmic Foundation of Robotics (WAFR'08), 2008.
- M. Stilman and J.J. Kuffner. Navigation Among Movable Obstacles: Real-time Reasoning in Complex Environments. In Proc. IEEE Int. Conf. on Humanoid Robotics (Humanoids'04), 2004.
