Abstract
Abstract. In the field of autonomous navigation for robotics, one of the most challenging issues is to locate the Next-Best-View and to guide robotics through a previously unknown environment. Existing methods based on generalized Voronoi graphs (GVGs) have presented feasible solutions but require excessive computation to construct GVGs from metric maps, and the GVGs are usually redundant. This paper proposes a reduced approximated GVG (RAGVG), which provides a topological representation of the explored space with a smaller graph. To be specific, a fast and practical algorithm for constructing RAGVGs from metric maps is presented, and a RAGVG-based autonomous robotic exploration framework is designed and implemented. The proposed method for constructing RAGVGs is validated with two known common maps, while the RAGVG-based autonomous exploration framework is tested on two simulation and one real-world museum. The experimental results show that the proposed algorithm is efficient in constructing RAGVGs, and indicate that the mobile robot controlled by the RAGVG-based autonomous exploration framework, compared with famous frontiers-based method, reduced the total time by approximately 20% for the given tasks.
Highlights
One of the most challenging issues in mobile robotics is the ability to autonomously explore previously unknown spaces (Burgard, Moors, Stachniss, et al, 2005)
Due to the complexity of metric maps, frontierbased methods suffer from low efficiency in evaluating candidate points (CPs) (Tsardoulias, Iliakopoulou, Kargakos et al, 2017) and planning global paths (Thrun, 1998)
This paper presents a novel autonomous exploration system based on an reduced approximated generalized Voronoi graph (GVG) (RAGVG), and the discovered improvements are as follows: -- A fast, robust and parallel algorithm was proposed for constructing an RAGVG from an occupancy grid map (OGM); -- The efficiency of selecting the NBV was markedly improved by generating more competitive CPs and by using fast graphbased path planning; -- The number of local obstacles that must be avoided was reduced by means of a collision-free global path that is rapidly generated from an RAGVG
Summary
One of the most challenging issues in mobile robotics is the ability to autonomously explore previously unknown spaces (Burgard, Moors, Stachniss, et al, 2005). With the help of an exploration strategy, mobile robots can autonomously decide where to go and build an environment map of a previously unknown space to accomplish a given task, such as map building (Stachniss, Burgard, 2003), search and rescue (Calisi, Farinelli, Iocchi et al, 2005), and 3D model building (Low, Lastra, 2006; Quintana, Prieto, Adán et al, 2016). The generalized Voronoi graph (GVG) is a kind of topological map, and it performs well as a basis for sensor-based path planning in an unknown static environment (Choset, 1995). It remains difficult because the existing algorithms for constructing GVGs are usually complex and unstable (Nagatani, Choset, 1999; Choset, 2000)
Sign-in/Register to view highlights & summary 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 callMore From: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: 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.
