The Rapidly-exploring Random Tree(rrt)is a classical algorithm of motionplanning based on incremental sampling,which is widely used to solve the planning problem of mobile *** it,due to the meandering path,the inaccu...
详细信息
The Rapidly-exploring Random Tree(rrt)is a classical algorithm of motionplanning based on incremental sampling,which is widely used to solve the planning problem of mobile *** it,due to the meandering path,the inaccurate terminal state and the slow exploration,is often inefficient in many applications such as autonomousroad *** address these issues and considering the realistic context of autonomousroadvehicles,this paper proposes a fastrrtalgorithm that introduces an off-line template set based on the traffic scenes and an aggressive extension strategy of search *** improvements can lead to a faster and more accurate rrt towards the ***,our approach combines the closed-loop prediction approach using the model of vehicle,which can smooth the portion of off-line template and the portion of on-line tree generated,while a trajectory and control sequence for the vehicle would be *** results illustrate that our method is fast and efficient in solving planning queries of autonomousroad vehicle in urban environments.
暂无评论