作者: B. Baginski
DOI: 10.1109/ROBOT.1996.509216
关键词: Robot 、 Solid modeling 、 Geometry 、 Robot kinematics 、 Path (graph theory) 、 Mathematical optimization 、 Measure (physics) 、 Mathematics 、 Computational geometry 、 Motion planning 、 Maxima and minima
摘要: A new approach to motion planning for manipulators is presented. collision-free path initially obtained by shrinking the robot's geometry model, and this modified remain while robot re-inflated. For purpose, a measure based on factor needed shrink model in certain configuration get it free of collisions defined. This serves as potential used modify whole trajectories. The information evaluated locally, no preprocessing or global diffusion required. To overcome local minima, planner embedded random exploration algorithm. Simulation results demonstrate power approach.