FAR-LIO: Enabling High-Speed Autonomy through Fast, Accurate, and Robust LiDAR-Inertial Odometry

2026-06-24

AI Summary

This work addresses the challenge of achieving low-latency, high-accuracy, and robust pose estimation in high-speed, highly dynamic, and unstructured environments—such as autonomous racing—where sensor noise is significant. We propose FAR-LIO, a CUDA-accelerated LiDAR-inertial odometry framework that innovatively integrates voxel hashing, sparsity-aware generalized ICP, and adaptive density management to enable efficient parallel nearest-neighbor search and map updates. The backend employs a tightly coupled extended Kalman filter (EKF) with latency compensation to fuse high-frequency IMU measurements. Evaluated across four sensor configurations and real-world vehicle tests at speeds up to 250 km/h, FAR-LIO reduces position error by 6.9% and runtime by 38.4% on average compared to state-of-the-art methods, substantially improving both accuracy and computational efficiency.

Abstract

Robust and accurate odometry estimation is essential in modern robotics. In environments characterized by highly dynamic motion and sensor noise, odometry estimation becomes increasingly challenging. Autonomous racing combines both factors in an unstructured setting, where minimizing odometry latency is essential for stable closed-loop control. This paper introduces FAR-LIO, a highly optimized CUDA-accelerated LiDAR-inertial odometry framework developed for Fast, Accurate, and Robust performance. Our system leverages a novel CUDA-based voxel hashmap to enable parallelized nearest-neighbor search and efficient map updates. We employ a sparsity-aware Generalized Iterative Closest Point algorithm with adaptive thresholding on top of the CUDA-based voxel hashmap with adaptive density to achieve low-latency without compromising accuracy. An Extended Kalman Filter serves as a robust backend. It utilizes an upsampling and delay compensation strategy to fuse the LiDAR odometry with high-frequency IMU data, thereby ensuring a robust and smooth odometry output. We evaluate FAR-LIO across four different sensor setups, using both public datasets and data from two autonomous racecars driving at speeds of up to 250 km/h. FAR-LIO achieves an average 6.9% reduction in the positional error and 38.4% lower runtime compared to state-of-the-art baselines on target hardware using a single parameter set. This demonstrates its computational efficiency and broad applicability. To build upon our work, our code is available open-source on https://github.com/TUMFTM/FAR-LIO.

Problem

• LiDAR-inertial odometry
• high-speed autonomy
• low-latency odometry
• sensor noise
• dynamic environments

Innovation

• CUDA-accelerated
• voxel hashmap
• sparsity-aware GICP
• LiDAR-inertial odometry
• low-latency