[論文レビュー] Learning to Localize Using a LiDAR Intensity Map

Ioan Andrei Bârsan, Shenlong Wang+2 more|arXiv (Cornell University)|Dec 20, 2020

Robotics and Sensor-Based Localization被引用数 64

ひとこと要約

本論文は、オンライン LiDAR スイープと aLiDAR 強度マップを共有深空間に埋め込み、効率的な畳み込みマッチングで局在化する、リアルタイムかつ較正非依存の局在システムを提案し、センサー間でセンチメートルレベルの精度を15 Hzで実現します。

ABSTRACT

In this paper we propose a real-time, calibration-agnostic and effective localization system for self-driving cars. Our method learns to embed the online LiDAR sweeps and intensity map into a joint deep embedding space. Localization is then conducted through an efficient convolutional matching between the embeddings. Our full system can operate in real-time at 15Hz while achieving centimeter level accuracy across different LiDAR sensors and environments. Our experiments illustrate the performance of the proposed approach over a large-scale dataset consisting of over 4000km of driving.

研究の動機と目的

• Motivate centimeter-level vehicle localization for HD-map-based perception and planning in autonomous driving.
• Propose a calibration-agnostic localization framework that operates across different LiDAR sensors.
• Develop a deep embedding approach for online LiDAR sweeps and pre-built LiDAR intensity maps.
• Enable real-time localization through efficient frequency-domain convolutional matching.

提案手法

• Embed online LiDAR BEV intensity images and pre-built intensity maps into a common neural embedding space.
• Compute LiDAR pose likelihoods by cross-correlating rotated online embedding with the map embedding in the Fourier domain.
• Model localization as a deep recursive Bayesian update combining LiDAR, GPS, and motion priors.
• Use a histogram-filter-like discrete search over a 3-DoF pose (x, y, theta) centered at the dead-reckoning pose.
• Train the system end-to-end with a cross-entropy loss on the resulting pose score map.
• Adopt a soft argmax for smoother pose estimates and robustness to observation noise.

実験結果

リサーチクエスチョン

• RQ1 Can a learned embedding space enable calibration-free LiDAR-based localization across different sensors?
• RQ2 What is the accuracy and robustness of the proposed embedding-based localization under real-time constraints?
• RQ3 How well does the system generalize from one LiDAR modality to another and across urban/highway environments?
• RQ4 What is the impact of using velocity/motion priors and probabilistic inference on localization robustness?

主な発見

Method	Motion	Prob	Lat	Lon	Total	<=100 m	<=500 m	<= End
Dynamics	Yes	No	439.21	863.68	1216.01	0.46	98.14	100.00
Raw LiDAR	Yes	No	1245.13	590.43	1514.42	1.84	81.02	92.49
ICP	Yes	No	1.52	5.04	5.44	3.50	5.03	7.14
Ours (LinkNet)	No	No	3.87	4.99	7.76	0.35	0.35	0.72
Ours (LinkNet)	Yes	No	3.81	4.53	7.18	1.06	1.06	1.44
Ours (LinkNet)	Yes	Yes	3.00	4.33	6.47	0.00	0.00	0.00

• Achieves real-time localization at 15 Hz with centimeter-level accuracy on diverse highway and urban scenes.
• Outperforms ICP and raw LiDAR matching baselines in median error and especially in worst-case (failure rate) scenarios.
• Demonstrates cross-sensor/generalization capability, maintaining accuracy when transferring between LiDAR A and LiDAR B datasets.
• FFT-based convolution dramatically speeds up matching, enabling efficient search over rotation and translation in a 3-DoF space.
• Incorporating motion priors and probabilistic inference improves robustness and reduces failure rates.
• Single-channel embeddings with LinkNet backbones provide a favorable balance of accuracy and runtime.