Deep LiDAR localization using optical flow sensor-map correspondences
Paper in proceeding, 2020

In this paper we propose a method for accurate localization of a multi-layer LiDAR sensor in a pre-recorded map, given a coarse initialization pose. The foundation of the algorithm is the usage of neural network optical flow predictions. We train a network to encode representations of the sensor measurement and the map, and then regress flow vectors at each spatial position in the sensor feature map. The flow regression network is straight-forward to train, and the resulting flow field can be used with standard techniques for computing sensor pose from sensor-to-map correspondences. Additionally, the network can regress flow at different spatial scales, which means that it is able to handle both position recovery and high accuracy localization. We demonstrate average localization accuracy of <0.04m position and <0.1◦ heading angle for a vehicle driving application with simulated LiDAR measurements, which is similar to point-to-point iterative closest point (ICP). The algorithm typically manages to recover position with prior error of more than 20m and is significantly more robust to scenes with non-salient or repetitive structure than the baselines used for comparison.

Author

Anders Sunegård

Volvo Group

Lennart Svensson

Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering

Torsten Sattler

Czech Technical University in Prague

Proceedings - 2020 International Conference on 3D Vision, 3DV 2020

838-847 9320401

International Virtual Conference on 3D Vision - 3DV 2020
Online, Japan,

Probabilistic models and deep learning - bridging the gap

Wallenberg AI, Autonomous Systems and Software Program, -- .

Highly Automated Freight Transports EUTS (AutoFreight)

VINNOVA (2016-05415), 2017-04-01 -- 2020-02-29.

Areas of Advance

Transport

Subject Categories

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/3DV50981.2020.00094

More information

Latest update

4/21/2023