Gaussian process motion planning for robots based on random restarts

doi:10.16731/j.cnki.1671-3133.2024.12.007

Abstract

Abstract: In complex obstacle environments,mobile robots using the Gaussian Path Motion Planning (GPMP2) algorithm suffer from the problems of falling into local optimums and poor obstacle avoidance performance,a method based on stochastic restart and obstacle avoidance improvement was proposed Gaussian Process Motion Planning with Stochastic Restart and Obstacle Avoidance Improvement (GPMP2-SROAI). Firstly,the random restart mechanism in the Covariant Hamiltonian Optimisation for Motion Planning (CHOMP) was introduced to apply perturbations to the trajectory to jump out of the local optimum and improve the efficiency and robustness of the trajectory optimization. Then,a Model Predictive Control with Control Barrier Function (MPC-CBF) approach based on the barrier function was introduced to avoid collisions by predicting the range of motion of the robot during the optimisation process. Simulation results show that, the improved algorithm achieves a success rate of 92.6 % in path planning,which is 24.9 % higher than that of GPMP2,12.5 % higher than the path shortest probability,and 4.8 % higher than the average smoothing degree,and also achieves a better quality of trajectory planning compared with the mainstream algorithms,with smoother trajectories and better obstacle avoidance effects.

Key words: path planning, random restart, robot obstacle avoidance, factor graph optimisation

CLC Number:

TP391.41

YUAN Xuqing, WEI Yuanyuan, WANG Yaoli, CHANG Qing, FU Shimo. Gaussian process motion planning for robots based on random restarts[J]. Modern Manufacturing Engineering, 2024, 531(12): 54-60.

References

[1] 张琰,蔡静.复杂环境下移动机器人自动路径规划研究[J].电脑编程技巧与维护,2022(10):122-124.
[2] 何成刚,朱润智,黄挺博,等.工业机器人轨迹规划与优化研究进展[J].现代制造工程,2023(7):150-159.
[3] LEU J,WANG M,TOMIZUKA M.Long-horizon motion planning via sampling and segmented trajectory optimization[C]//2022 European Control Conference (ECC).[S.l.]:IEEE,2022:538-545.
[4] 黄云志,徐玉全,韩亮,等.基于改进高斯采样PRM算法和狭窄通道识别的路径规划方法:CN202210730956.1[P].2024-02-05.
[5] 成怡,王赟,修春波.一种改进RRT算法在路径规划中的应用研究[J].控制工程,2020,27(3):5.
[6] KALAKRISHNAN M,CHITTA S,THEODOROU E,et al.STOMP:Stochastic Trajectory Optimization for Motion Planning[C]//2011 IEEE International Conference on Robotics and Automation.[S.l.]:IEEE,2011:4569-4574.
[7] MUKADAM M,YAN X,BOOTS B.Gaussian process motion planning[C]//2016 IEEE international conference on robotics and automation (ICRA).[S.l.]:IEEE,2016:9-15.
[8] DONG J,MUKADAM M,DELLAERT F,et al.Motion planning as probabilistic inference using Gaussian processes and factor graphs[J]. RSS,2016,10:15607.
[9] RATLIFF N,ZUCKER M,BAGNELL J A,et al.CHOMP:Gradient optimization techniques for efficient motion planning[C]//2009 IEEE International Conference on Robotics and Automation.[S.l.]:IEEE,2009:489-494.
[10] GUO S,LIU B,ZHANG S,et al.Continuous-time Gaussian process trajectory generation for multi-robot formation via probabilistic inference[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).[S.l.]:IEEE,2021:9247-9253.
[11] WU X,LI P,LI Q,et al.Two-Dimensional-Simultaneous Localisation and Mapping Study Based on Factor Graph Elimination Optimisation[J].Sustainability,2023,15(2):1172.
[12] 陈亚瑞,杨巨成,史艳翠,等.概率生成模型变分推理方法综述[J].计算机研究与发展,2022,59(3):617-632.
[13] WAINWRIGHT M J,JORDAN M I.Graphical models,exponential families,and variational inference[J].Foundations and Trends© in Machine Learning,2008,1(1/2):1-305.
[14] ROBERT C P,CASELLA G,CASELLA G.Introducing monte carlo methods with[M].New York:Springer,2010.
[15] YESHMUKHAMETOV A,KALIMOLDAYEV M,MAMYRBAYEV O,et al.Design and kinematics of serial/parallel hybrid robot[C]//2017 3rd International Conference on Control,Automation and Robotics (ICCAR).[S.l.]:IEEE,2017:162-165.
[16] 方佳艳,刘峤.具有同步化特征选择的迭代紧凑非平行支持向量聚类算法[J].电子学报,2020,48(1):15.
[17] 孙小倩,辛绍杰.基于改进型A^*算法的移动机器人路径规划[J].组合机床与自动化加工技术,2023(3):5-8.
[18] HIROSE O.Acceleration of non-rigid point set registration with downsampling and Gaussian process regression[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(8):2858-2865.