Robust Localization for Autonomous Vehicles in Highway Scenes
Daqian Cheng, Xuchu Ding, Yujia Wu, Xiang Zhang, Lei Wang
AI summary
Problem
State-of-the-art urban localization methods degrade on highways due to environmental homogeneity, heavy occlusion, degraded GNSS, and high-speed dynamics, leaving a gap for robust, production-ready highway navigation.
Approach
The system decouples 3D geometry and 2D road-texture cues into a dual-likelihood LiDAR front end, fuses them via an Error State Kalman Filter, and applies a Control EKF using steering and acceleration commands to reduce lag and improve tracking.
Key results
- Dual-likelihood LiDAR front end handles environmental changes and heavy occlusion
- Control EKF reduces localization lag and prevents oscillatory behavior at high speeds
- Automated offline mapping pipeline maintains high-cadence, fresh HD maps
- Public dataset of 163 km of challenging highway and urban clips released with standardized benchmarks
Why it matters
Provides a validated, production-ready localization framework and benchmark for high-speed autonomous trucking and highway navigation, bridging the gap between urban and highway autonomy.
Abstract
Localization for autonomous vehicles on highways remains under-explored compared to urban roads, and state-of- the-art methods for urban scenes degrade when directly applied to highways. We identify key challenges including environment changes under information homogeneity, heavy occlusion, de- graded GNSS signals, and stringent downstream requirements on accuracy and latency. We propose a robust localization sys- tem to address highway challenges, which uses a dual-likelihood LiDAR front end that decouples 3D geometric structures and 2D road-texture cues to handle environment changes; a Control- EKF further leverages steering and acceleration commands to reduce lag and improve closed-loop behavior. An automated offline mapping and ground-truth pipeline keep maps fresh at high cadence for optimal localization performance. To catalyze progress, we release a public dataset covering both urban roads and highways while focusing on representative challenging highway clips, totaling 163 km; benchmarking is standardized using product-oriented accuracy metrics and certified ground truth. Compared to Apollo and Autoware, our system performs similarly on urban roads but shows superior robustness on challenging highway scenarios. The system has been validated by more than one million kilometers of road testing.