融合GMM和PSO的储罐超声检测机器人避障研究  

Research on Obstacle Avoidance of Storage Tank Ultrasonic Inspection Robot Integratingg GMM and PSO

作　　者：吴以童 李斌[1,2] 刘春[1,2] 王聪 WU Yi-tong;LI Bin;LIU Chun;WANG Cong(State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang Liaoning 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang Liaoning 110169,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院沈阳自动化研究所机器人学国家重点实验室,辽宁沈阳110016 [2]中国科学院机器人与智能制造创新研究院,辽宁沈阳110169 [3]中国科学院大学,北京100049

出　　处：《计算机仿真》2023年第11期408-414,共7页Computer Simulation

基　　金：国家重点研发计划(2019YFB1310702)。

摘　　要：为实现储油罐内机器人自主检测技术,需要克服机器人自主应对复杂储罐底部环境的难点,提出基于融合改进的高斯混合模型和粒子群算法的移动机器人障碍位置记忆和局部避障算法FGMM-PSO,使机器人具有环境自适应能力、泛化障碍记录能力和自主避障能力。通过webots机器人仿真环境平台建立环境参数与机构关联模型,模拟了机器人在油罐内的避障移动,结果表明,FGMM-PSO算法能够使机器人完成油罐内自主障碍记忆和避障任务,进而令机器人克服复杂储罐底部环境进行检测成为可能。In order to realize the autonomous detection technology of robots in oil storage tanks,it is necessary to overcome the difficulties of robots dealing with the complex environment at the bottom of storage tanks autonomously.In this paper,based on improved Gaussian mixture model and particle swarm optimization algorithm,a mobile robot obstacle location memory and local obstacle avoidance algorithm FCMM-PSO is proposed.The robot has the abilities of environment adaptation,generalization obstacle recording and autonomous obstacle avoidance.In this paper,webots robot simulation environment platform was used to establish an association model between environmental parameters and mechanism,and to simulate the robot's obstacle avoidance movement in oil tank.The results show that FGMM-PSO algorithm can enable the robot to complete autonomous obstacle memory and obstacle avoidance tasks in oil tank,and thus make it possible for the robot to overcome the complex environment at the bottom of the tank for detec-tion.

关 键 词：储油罐 超声检测 避障算法 仿真 高斯混合模型 粒子群 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]