TY - GEN

T1 - Have I been here before?

T2 - 2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics

AU - Habich, Tim-Lukas

AU - Stuede, Marvin

AU - Labbé, Mathieu

AU - Spindeldreier, Svenja

N1 - Accepted at AIM Conference 2021

PY - 2021/3/11

Y1 - 2021/3/11

N2 - This work presents an extension of graph-based SLAM methods to exploit the potential of 3D laser scans for loop detection. Every high-dimensional point cloud is replaced by a compact global descriptor, whereby a trained detector decides whether a loop exists. Searching for loops is performed locally in a variable space to consider the odometry drift. Since closing a wrong loop has fatal consequences, an extensive verification is performed before acceptance. The proposed algorithm is implemented as an extension of the widely used state-of-the-art library RTAB-Map, and several experiments show the improvement: During SLAM with a mobile service robot in changing indoor and outdoor campus environments, our approach improves RTAB-Map regarding total number of closed loops. Especially in the presence of significant environmental changes, which typically lead to failure, localization becomes possible by our extension. Experiments with a car in traffic (KITTI benchmark) show the general applicability of our approach. These results are comparable to the state-of-the-art LiDAR method LOAM. The developed ROS package is freely available.

AB - This work presents an extension of graph-based SLAM methods to exploit the potential of 3D laser scans for loop detection. Every high-dimensional point cloud is replaced by a compact global descriptor, whereby a trained detector decides whether a loop exists. Searching for loops is performed locally in a variable space to consider the odometry drift. Since closing a wrong loop has fatal consequences, an extensive verification is performed before acceptance. The proposed algorithm is implemented as an extension of the widely used state-of-the-art library RTAB-Map, and several experiments show the improvement: During SLAM with a mobile service robot in changing indoor and outdoor campus environments, our approach improves RTAB-Map regarding total number of closed loops. Especially in the presence of significant environmental changes, which typically lead to failure, localization becomes possible by our extension. Experiments with a car in traffic (KITTI benchmark) show the general applicability of our approach. These results are comparable to the state-of-the-art LiDAR method LOAM. The developed ROS package is freely available.

KW - cs.RO

UR - http://www.scopus.com/inward/record.url?scp=85112759656&partnerID=8YFLogxK

U2 - 10.1109/AIM46487.2021.9517565

DO - 10.1109/AIM46487.2021.9517565

M3 - Conference contribution

SP - 504

EP - 510

BT - Proceedings of the 2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

Y2 - 12 July 2021 through 16 July 2021

ER -