Multi-Robot Area Coverage and Environment Estimation Based on the Mixture of Gaussian Processes

Author(s):  
Yixian Zhao ◽  
Jiashuai Chen ◽  
Jinming Xu ◽  
Shuai Liu
2013 ◽  
Author(s):  
Mian Huang ◽  
Runze Li ◽  
Hansheng Wang ◽  
Weixin Yao

2019 ◽  
pp. 1192-1219
Author(s):  
Prithviraj Dasgupta ◽  
Taylor Whipple ◽  
Ke Cheng

This paper examines the problem of distributed coverage of an initially unknown environment using a multi-robot system. Specifically, focus is on a coverage technique for coordinating teams of multiple mobile robots that are deployed and maintained in a certain formation while covering the environment. The technique is analyzed theoretically and experimentally to verify its operation and performance within the Webots robot simulator, as well as on physical robots. Experimental results show that the described coverage technique with robot teams moving in formation can perform comparably with a technique where the robots move individually while covering the environment. The authors also quantify the effect of various parameters of the system, such as the size of the robot teams, the presence of localization, and wheel slip noise, as well as environment related features like the size of the environment and the presence of obstacles and walls on the performance of the area coverage operation.


2011 ◽  
Vol 2 (1) ◽  
pp. 44-69 ◽  
Author(s):  
Prithviraj Dasgupta ◽  
Taylor Whipple ◽  
Ke Cheng
Keyword(s):  

2013 ◽  
Vol 34 (4) ◽  
pp. 251-276 ◽  
Author(s):  
Pooyan Fazli ◽  
Alireza Davoodi ◽  
Alan K. Mackworth
Keyword(s):  

Author(s):  
Qikun Xiang ◽  
Jie Zhang ◽  
Ido Nevat ◽  
Pengfei Zhang

Data trustworthiness is a crucial issue in real-world participatory sensing applications. Without considering this issue, different types of worker misbehavior, especially the challenging collusion attacks, can result in biased and inaccurate estimation and decision making. We propose a novel trust-based mixture of Gaussian processes (GP) model for spatial regression to jointly detect such misbehavior and accurately estimate the spatial field. We develop a Markov chain Monte Carlo (MCMC)-based algorithm to efficiently perform Bayesian inference of the model. Experiments using two real-world datasets show the superior robustness of our model compared with existing approaches.


Sign in / Sign up

Export Citation Format

Share Document