Robot Path Planning Algorithm Based on Improved RRT
The RRT algorithm based on random sampling is widely used in non-holonomic constrained pro-gramming problems.However,the RRT method has problems such as slow convergence speed,strong ran-domness,a large number of redundant nodes,and difficulty in quickly finding path.In response to the above issues,proposed an improved RRT algorithm.This method first adopts a strategy of directly expanding to the target,and then randomly expanding or expanding to the target based on the expansion results.At the same time,nodes that failed to expand due to collisions are randomly rotated to enable them to successfully expand.Finally,a bi-directional growth strategy is adopted to accelerate convergence speed.The simulation verification results show that the convergence speed of the proposed method is better than that of the RRT method,with a calculation time reduction of 18.1%～88.1%,and a 24.0%～90.6%reduction in tree nodes.
NETL
NSTL
万方数据
