Abstract
In this paper, we present a novel end-to-end learning-based LiDAR sensor relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input. Compared to visual sensor-based relocalization, LiDAR sensors can provide rich and robust geometric information about a scene. However, point clouds of LiDAR sensors are unordered and unstructured making it difficult to apply traditional deep learning regression models for this task. We address this issue by proposing a novel PointNet-style architecture with self-attention to efficiently estimate 6-DoF poses from 360° LiDAR sensor frames. Extensive experiments on recently released challenging Oxford Radar RobotCar dataset and real-world robot experiments demonstrate that the proposed method can achieve accurate relocalization performance.
Highlights
L iDAR sensor-based localization methods have achieved impressive accuracy [1], [2]
The PointLoc improves the LiDAR point cloud retrievalbased approach PointNetVLAD by 46.47% in translation and 70.45% in rotation, which proves the effectiveness of our proposed method
The PointLoc improves the Deep Closest Point (DCP) with PointNet by 29.46% in translation and 37.80% in rotation, which reveals that the proposed embedding neural network can effectively learn meaningful features for relocalization
Summary
L iDAR sensor-based localization methods have achieved impressive accuracy [1], [2]. A typical LiDAR sensor localization system usually includes a feature extraction module, a feature matching algorithm, an outlier rejection step, a matching cost function, a spatial searching or optimization method and a temporal optimization or filtering mechanism [3]. These geometric localization methods achieve high accuracy in some scenarios, they require significant hand-engineering efforts to tune the huge amount of hyper-parameters, and depend heavily on the running environments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
