Traj-LIO: A Resilient Multi-LiDAR Multi-IMU State Estimator Through Sparse Gaussian Process

TL;DR

This paper presents Traj-LIO, a resilient multi-LiDAR multi-IMU state estimator using Gaussian Processes to predict continuous trajectories, capable of handling sensor failures and asynchronous data for improved robustness.

Contribution

It introduces a novel GP-based continuous-time trajectory estimation method that integrates multiple LiDARs and IMUs, enhancing resilience and real-time performance in sensor fusion.

Findings

Demonstrates robustness to sensor failures in experiments.

Achieves real-time performance with combined SO(3) and vector space representation.

Validates versatility across public datasets.

Abstract

Nowadays, sensor suits have been equipped with redundant LiDARs and IMUs to mitigate the risks associated with sensor failure. It is challenging for the previous discrete-time and IMU-driven kinematic systems to incorporate multiple asynchronized sensors, which are susceptible to abnormal IMU data. To address these limitations, we introduce a multi-LiDAR multi-IMU state estimator by taking advantage of Gaussian Process (GP) that predicts a non-parametric continuous-time trajectory to capture sensors' spatial-temporal movement with limited control states. Since the kinematic model driven by three types of linear time-invariant stochastic differential equations are independent of external sensor measurements, our proposed approach is capable of handling different sensor configurations and resilient to sensor failures. Moreover, we replace the conventional $\mathrm{SE}(3)$ state representation with the combination of $\mathrm{SO}(3)$ and vector space, which enables GP-based LiDAR-inertial system to fulfill the real-time requirement. Extensive experiments on the public datasets demonstrate the versatility and resilience of our proposed multi-LiDAR multi-IMU state estimator. To contribute to the community, we will make our source code publicly available.