Distributed field mapping for mobile sensor teams using a derivative‐free optimisation algorithm  

作　　者：Tony X.Lin Jia Guo Said Al-Abri Fumin Zhang 

机构地区：[1]School of Electrical&Computer Engineering,Georgia Institute of Technology,Atlanta,Georgia,USA [2]College of Engineering,Sultan Qaboos University,Muscat,Oman [3]Department of Electronic&Computer Engineering,Hong Kong University of Science and Technology,Hong Kong,China

出　　处：《IET Cyber-Systems and Robotics》2024年第2期20-34,共15页智能系统与机器人（英文）

摘　　要：The authors propose a distributed field mapping algorithm that drives a team of robots to explore and learn an unknown scalar field using a Gaussian Process(GP).The authors’strategy arises by balancing exploration objectives between areas of high error and high variance.As computing high error regions is impossible since the scalar field is unknown,a bio-inspired approach known as Speeding-Up and Slowing-Down is leveraged to track the gradient of the GP error.This approach achieves global field-learning convergence and is shown to be resistant to poor hyperparameter tuning of the GP.This approach is validated in simulations and experiments using 2D wheeled robots and 2D flying mini-ature autonomous blimps.

关 键 词：environment SENSING MULTI-ROBOT systems 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]