3-D Path Planning using Neural Networks for a Robot Manipulator
It is complex to find a good path when the robot is in a complex dynamic change condition, we are developing a trajectory prediction system is to reliably predict the moving obstacles. Algorithms for the device to perform path planning and trajectory prediction are described. We used neural network whose retraining is automatically triggered if major changes in the target behavior pattern are detected. The path planner uses super quadratic potential fields and incorporates a height change mechanism that is triggered where necessary and in order to get over short massif or pass by the taller obstacle.
trajectory prediction system height change mechanism path planning
Wang Wei Wei Shimin
The Instrment Department Institute of Disaster Prevention Science and Technology Beijing 101601, Chi Automation School Beijing University of Post and Telecommunications Beijing 100876, China
国际会议
长沙
英文
3-6
2010-05-11（万方平台首次上网日期，不代表论文的发表时间）