Affiliation:
1. Robotics Laboratory Department of Computer Science Stanford University Stanford, California 94305
Abstract
We propose a new approach to robot path planning that consists of building and searching a graph connecting the local minima of a potential function defined over the robot's configuration space. A planner based on this approach has been implemented. This planner is consider ably faster than previous path planners and solves prob lems for robots with many more degrees of freedom (DOFs). The power of the planner derives both from the "good" properties of the potential function and from the efficiency of the techniques used to escape the local min ima of this function. The most powerful of these tech niques is a Monte Carlo technique that escapes local min ima by executing Brownian motions. The overall approach is made possible by the systematic use of distributed rep resentations (bitmaps) for the robot's work space and configuration space. We have experimented with the plan ner using several computer-simulated robots, including rigid objects with 3 DOFs (in 2D work space) and 6 DOFs (in 3D work space) and manipulator arms with 8, 10, and 31 DOFs (in 2D and 3D work spaces). Some of the most significant experiments are reported in this article.
Subject
Applied Mathematics,Artificial Intelligence,Electrical and Electronic Engineering,Mechanical Engineering,Modelling and Simulation,Software
Reference45 articles.
1. Alami, R., Siméon, T., and Laumond, J.P. 1989. A geometrical approach to planning manipulation tasks—the case of discrete placements and grasps. In Miura, H., and Arimoto, S. (eds.): Robotics Research 5. Cambridge, MA: MIT Press, pp. 453-463.
2. Small Random perturbation of dynamical systems with reflecting boundary
Cited by
609 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献