GP-Frontier for Local Mapless Navigation

Autor:	Ali, Mahmoud, Liu, Lantao
Rok vydání:	2023
Předmět:	Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	We propose a new frontier concept called the Gaussian Process Frontier (GP-Frontier) that can be used to locally navigate a robot towards a goal without building a map. The GP-Frontier is built on the uncertainty assessment of an efficient variant of sparse Gaussian Process. Based only on local ranging sensing measurement, the GP-Frontier can be used for navigation in both known and unknown environments. The proposed method is validated through intensive evaluations, and the results show that the GP-Frontier can navigate the robot in a safe and persistent way, i.e., the robot moves in the most open space (thus reducing the risk of collision) without relying on a map or a path planner. Comment: 7 pages, 7 figures, accepted at the 2023 IEEE International Conference on Robotics and Automation ICRA2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.11717 Zobrazit plný text záznamu View this record from Arxiv