2020/10/31 by Lukas Schmid, Victor Reijgwart, Lionel Ott +4
Computer Science · Engineering · #Artificial intelligence #Computer science #Computer vision #Distributed Control Multi-Agent Systems #Geography #Global Map #Mobile robot #Motion planning #Odometry #Real-time computing #Robot #Robotic Path Planning Algorithms #Robotics and Sensor-Based Localization #Scale (ratio) #Visual odometry #cs.RO
paper · pdf · doi:10.1109/lra.2021.3068954
published as IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4504-4511, July 2021 · 8 pages, 9 figures, accepted for IEEE RA-L, code is open source: https://github.com/ethz-asl/glocal_exploration
arxiv created 2021/03/05 · openalex publication_date 2021/03/25 · arxiv updated 2021/04/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Exploration is a fundamental problem in robot autonomy. A major limitation, however, is that during exploration robots oftentimes have to rely on on-board systems alone for state estimation, accumulating significant drift over time in large environments. Drift can be detrimental to robot safety and exploration performance. In this work, a submap-based, multi-layer approach for both mapping and planning is proposed to enable safe and efficient volumetric exploration of large scale environments despite odometry drift. The central idea of our approach combines local (temporally and spatially) and global mapping to guarantee safety and efficiency. Similarly, our planning approach leverages the presented map to compute global volumetric frontiers in a changing global map and utilizes the nature of exploration dealing with partial information for efficient local and global planning. The presented system is thoroughly evaluated and shown to outperform state of the art methods even under drift-free conditions. Our system, termed GLocal, is made available open source.