Title: Map matching navigation method based on scene information fusion

Authors: Yanqing Wang; Yongquan Li; Chuang Xu; Chaoxia Shi

Addresses: School of Information Engineering, Nanjing Xiaozhuang University, Nanjing 211171, China ' School of Information Engineering, Nanjing Xiaozhuang University, Nanjing 211171, China ' School of Information Engineering, Nanjing Xiaozhuang University, Nanjing 211171, China ' School of Information Engineering, Nanjing Xiaozhuang University, Nanjing 211171, China

Abstract: In the process of large topological map creation, the odometer track reckoning can meet the calculation requirements in the system with limited computing ability, but the error of the odometer will lead to the cumulative error in the process of map creation. This paper proposes multi-robot cooperative exploration based on geometric-topological scene map and proposes a new representation method of topological map, which adds the scene information. This method uses the SuperPoint network structure to extract the local feature point information in the image and uses this information for scene matching and node localisation to provide more reliable support for map creation. Considering the spatial relationship between a single node and different nodes, we use the hidden Markov model (HMM) to locate nodes accurately and use the geometrical-topological feature scene matching method to perform map fusion. Finally, the effectiveness and feasibility of the proposed algorithm are verified by experiments.

Keywords: market approach; geometric-feature scene matching; loop-back detection.

DOI: 10.1504/IJMIC.2022.127105

International Journal of Modelling, Identification and Control, 2022 Vol.41 No.1/2, pp.110 - 119

Received: 07 Jul 2021
Accepted: 14 Nov 2021

Published online: 22 Nov 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article