基于变分稀疏高斯过程的多机器人协同感知与围捕  

Multi-robot Collaborative Perception and Capture Based on Variational Sparse Gaussian Process

作　　者：曹凯[1,2] 陈阳泉 魏云博 刘志 陈超波 高嵩[1] CAO Kai;CHEN Yang-Quan;WEI Yun-Bo;LIU Zhi;CHEN Chao-Bo;GAO Song(School of Electronic Information Engineering,Xi'an Technological University,Xi'an 710021,China;The MESA Laboratory,School of Engineering,University of California,Merced 95343,USA)

机构地区：[1]西安工业大学电子信息工程学院,西安710021 [2]加州大学默塞德分校工程学院MESA实验室,美国默塞德95343

出　　处：《自动化学报》2025年第4期778-791,共14页Acta Automatica Sinica

基　　金：国家重点研发计划项目(2022YFE0123400);陕西省科技厅重点项目(2023-ZDLNY-61,2022QFY01-16);国家自然科学基金(62303368);教育部重点实验室基金(202312-IFTKFKT-007)资助。

摘　　要：针对未知环境下的多机器人环境感知和围捕问题,提出一种基于变分稀疏高斯过程回归的分布式感知与围捕算法.考虑到传统高斯过程回归不适合处理大量数据的问题,在这项工作中,首先考虑障碍物的影响,以引入分离超平面的质心维诺划分算法为机器人动态规划任务区域;其次,利用多机器人在任务区域中的移动探索获取环境信息,并通过变分自由方法来近似模型的后验分布,完成对未知环境的感知;最后,基于粒子群优算法为围捕机器人动态分配围捕点,实现多机器人的全方位均匀围捕.通过仿真实验证明,该算法能够适用于单源、多源以及动态源的围捕,且能够在保证多机器人编队安全性的同时,实现较高的迭代速度,最终成功实现均匀围捕.To solve the problem of multi-robot environmental perception and capture in unknown environments.Proposing a distributed perception and capture algorithm based on variational sparse Gaussian process regression.Considering the issue that traditional Gaussian process regression is not suitable for handling large amounts of data,in this paper,the influence of obstacles is first taken into account to introduce the centroidal Voronoi tessinations algorithm with separating hyperplanes for dynamic planning of the task area for robots;Secondly,the movement exploration of multi-robot in the task area is used to obtain environmental information,and the variational free energy method is used to approximate the posterior distribution of the model to complete the perception of the unknown environment;Finally,the particleswarm optimization algorithm is used to dynamically assign capture points for the capturing robots,achieving all-round uniform capture of multi-robot.Simulation experiments prove that this algorithm is applicable to single-source,multi-source and dynamic source environments,and can achieve high iteration speed while ensuring the safety of the multi-robot formation,ultimately successfully achieving uniform capture.

关 键 词：多机器人 质心维诺划分 变分稀疏高斯过程回归 围捕 协同感知 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]