Towards High Efficient Long-horizon Planning with Expert-guided Motion-encoding Tree Search

作     者：Zhou, Tong Lyu, Erli Wang, Jiaole Cen, Guangdu Zha, Ziqi Qi, Senmao Meng, Max Q.-H. 

作者机构：Department of Electronic Engineering The Chinese University of Hong Kong Shatin Hong Kong Faculty of Applied Science Macao Polytechnic University China  Shenzhen518055 China The Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Shenzhen Research Institute of The Chinese University of Hong Kong Shenzhen518057 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Efficiency 

摘      要：Autonomous driving holds promise for increased safety, optimized traffic management, and a new level of convenience in transportation. While model-based reinforcement learning approaches such as MuZero enables long-term planning, the exponentially increase of the number of search nodes as the tree goes deeper significantly effect the searching efficiency. To deal with this problem, in this paper we proposed the expert-guided motion-encoding tree search (EMTS) algorithm. EMTS extends the MuZero algorithm by representing possible motions with a comprehensive motion primitives latent space and incorporating expert policies to improve the searching efficiency. The comprehensive motion primitives latent space enables EMTS to sample arbitrary trajectories instead of raw action to reduce the depth of the search tree. And the incorporation of expert policies guided the search and training phases the EMTS algorithm to enable early convergence. In the experiment section, the EMTS algorithm is compared with other four algorithms in three challenging scenarios. The experiment result verifies the effectiveness and the searching efficiency of the proposed EMTS *** Codes 68T40 Copyright © 2023, The Authors. All rights reserved.