Abstract
This paper describes a graph search-based exploration method. Segmented frontier nodes and their relative transformations constitute a frontier-graph structure. Frontier detection and segmentation are performed using local grid maps of adjacent nodes. The proposed frontier-graph structure can systematically manage local information according to the exploration state and overcome the problem caused by updating a single global grid map. The robot selects the next target using breadth-first search (BFS) exploration of the frontier-graph. The BFS exploration is improved to generate an efficient loop-closing sequence between adjacent nodes. We verify that our BFS-based exploration method can gradually extend the frontier-graph structure and efficiently map the entire environment, regardless of the starting position.
Highlights
Mapping is one of the most critical prerequisites for mobile robots performing various high-level tasks
We assume that the Simultaneous localization and mapping (SLAM) algorithm gives the robot’s state in the global reference frame at every decision step in all simulations, because we focus on the exploration method itself in this paper
This paper describes a graph search-based exploration method using frontier detection and segmentation
Summary
Mapping is one of the most critical prerequisites for mobile robots performing various high-level tasks. The purpose of frontier-based exploration methods is full coverage of the environment, rather than accuracy of the mapping and localization states. Integrated exploration, known as active SLAM, plans a path to improve localization accuracy and increase mapping coverage in an unknown environment [9]. The basic SLAM framework of integrated exploration constructs a feature map or a pose graph for state estimation, a grid map is produced whenever the robot needs to detect frontiers [12,13]. This paper presents an integrated exploration method that constructs a frontier-graph structure using a local grid map and selects the exploration target based on this frontier-graph.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
