Learning to Localize Using a LiDAR Intensity Map
arXiv:2012.10902
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.
12 pages, 7 figures, 5 tables; Presented at the 2nd Conference on Robot Learning (CoRL), 2018
Cited by in corpus (20)
- A Survey of Deep Learning Techniques for Autonomous Driving
- OverlapNet: Loop Closing for LiDAR-based SLAM
- Range Image-based LiDAR Localization for Autonomous Vehicles
- A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
- Semantics for Robotic Mapping, Perception and Interaction: A Survey
- RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model
- Any Way You Look At It: Semantic Crossview Localization and Mapping with LiDAR
- Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information
- Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
- Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
- PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
- Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks
- DiSCO: Differentiable Scan Context with Orientation
- DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving
- Local Descriptor for Robust Place Recognition using LiDAR Intensity
- Robust Place Recognition using an Imaging Lidar
- Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation
- Learning to Localize Through Compressed Binary Maps
- Convolutional Recurrent Network for Road Boundary Extraction
- DAGMapper: Learning to Map by Discovering Lane Topology