An objective-based stochastic framework for manipulation planning

We consider the problem of determining robot manipulation plans when sensing and control uncertainties are specified as conditional probability densities. Traditional approaches are usually based on worst-case error analysis in a methodology known as preimage backchaining. We have developed a general framework for determining sensor-based robot plans by blending ideas from stochastic optimal control and dynamic game theory with traditional preimage backchaining concepts. We argue that the consideration of a precise loss (or performance) functional is crucial to determining and evaluating manipulation plans in a probabilistic setting. We consequently introduce a stochastic, performance preimage that generalizes previous preimage notions. We also present some optimal strategies for planar manipulation tasks that were computed by a dynamic programming-based algorithm.<<ETX>>

[1]  Michael Erdmann,et al.  Randomization in Robot Tasks , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[2]  Steven M. LaValle,et al.  Game theory as a unifying structure for a variety of robot tasks , 1993, Proceedings of 8th IEEE International Symposium on Intelligent Control.

[3]  Jean-Claude Latombe,et al.  A Monte-Carlo algorithm for path planning with many degrees of freedom , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[4]  Russell H. Taylor,et al.  Sensor-based manipulation planning as a game with nature , 1988 .

[5]  Daniel E. Whitney,et al.  Force Feedback Control of Manipulator Fine Motions , 1977 .

[6]  Alan D. Christiansen,et al.  Probabilistic analysis of manipulation tasks: a research agenda , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[7]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[8]  Steven M. LaValle,et al.  Path selection and coordination for multiple robots via Nash equilibria , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[9]  Jean-Claude Latombe,et al.  Robot Motion Planning with Uncertainty in Control and Sensing , 1991, Artif. Intell..

[10]  Russell H. Taylor,et al.  Automatic Synthesis of Fine-Motion Strategies for Robots , 1984 .

[11]  R. Bertram,et al.  Stochastic Systems , 2008, Control Theory for Physicists.

[12]  Michael A. Erdmann,et al.  On Motion Planning with Uncertainty , 1984 .

[13]  Bruce Randall Donald,et al.  Sensor interpretation and task-directed planning using perceptual equivalence classes , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[14]  Ken Goldberg,et al.  Stochastic plans for robotic manipulation , 1991 .