Generative Adversarial Network Based Heuristics for Sampling-Based Path Planning

作     者：Tianyi Zhang Jiankun Wang Max Q.-H.Meng Tianyi Zhang;Jiankun Wang;Max Q.-H.Meng

作者机构：Department of Electronic and Electrical EngineeringSouthern University of Science and TechnologyShenzhen 518055China 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2022年第9卷第1期

页      面：64-74页

核心收录：

学科分类：0711[理学-系统科学] 08[工学] 080202[工学-机械电子工程] 081104[工学-模式识别与智能系统] 0802[工学-机械工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was partially supported by National Key R&D Program of China(2019YFB1312400) Shenzhen Key Laboratory of Robotics Perception and Intelligence(ZDSYS20200810171800001) Hong Kong RGC GRF(14200618) Hong Kong RGC CRF(C4063-18G). 

主　　题：Generative adversarial network(GAN) optimal path planning robot path planning sampling-based path planning 

摘      要：Sampling-based path planning is a popular methodology for robot path planning.With a uniform sampling strategy to explore the state space,a feasible path can be found without the complex geometric modeling of the configuration space.However,the quality of the initial solution is not guaranteed,and the convergence speed to the optimal solution is slow.In this paper,we present a novel image-based path planning algorithm to overcome these limitations.Specifically,a generative adversarial network(GAN)is designed to take the environment map(denoted as RGB image)as the input without other preprocessing works.The output is also an RGB image where the promising region(where a feasible path probably exists)is segmented.This promising region is utilized as a heuristic to achieve non-uniform sampling for the path planner.We conduct a number of simulation experiments to validate the effectiveness of the proposed method,and the results demonstrate that our method performs much better in terms of the quality of the initial solution and the convergence speed to the optimal solution.Furthermore,apart from the environments similar to the training set,our method also works well on the environments which are very different from the training set.