Tightly-Coupled LiDAR-IMU-Wheel Odometry with an Online Neural Kinematic Model Learning via Factor Graph Optimization

2024-07-12

arXiv.org

AI Summary

In feature-deprived environments (e.g., tunnels, long straight corridors), both LiDAR-based and wheel-odometry-based localization suffer severe degeneracy—LiDAR matching fails due to insufficient geometric structure, while wheel odometry accumulates substantial errors under wheel slip or lateral motion. To address this, we propose a tightly coupled multi-sensor odometry framework integrating LiDAR, IMU, and wheel encoders within a factor graph for joint optimization. Crucially, we introduce a lightweight neural network embedded directly into the factor graph, enabling online co-optimization of both network parameters and robot states. This allows real-time, adaptive modeling of terrain-induced variations and large-scale kinematic errors caused by slippage. Experiments across diverse degenerate scenarios demonstrate significant suppression of point-cloud degeneracy and trajectory drift. Our method achieves a 42% improvement in absolute pose accuracy over state-of-the-art baselines, delivering both high precision and robust performance under challenging conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Environments lacking geometric features (e.g., tunnels and long straight corridors) are challenging for LiDAR-based odometry algorithms because LiDAR point clouds degenerate in such environments. For wheeled robots, a wheel kinematic model (i.e., wheel odometry) can improve the reliability of the odometry estimation. However, the kinematic model suffers from complex motions (e.g., wheel slippage, lateral movement) in the case of skid-steering robots particularly because this robot model rotates by skidding its wheels. Furthermore, these errors change nonlinearly when the wheel slippage is large (e.g., drifting) and are subject to terrain-dependent parameters. To simultaneously tackle point cloud degeneration and the kinematic model errors, we developed a LiDAR-IMU-wheel odometry algorithm incorporating online training of a neural network that learns the kinematic model of wheeled robots with nonlinearity. We propose to train the neural network online on a factor graph along with robot states, allowing the learning-based kinematic model to adapt to the current terrain condition. The proposed method jointly solves online training of the neural network and LiDARIMUwheel odometry on a unified factor graph to retain the consistency of all those constraints. Through experiments, we first verified that the proposed network adapted to a changing environment, resulting in an accurate odometry estimation across different environments.We then confirmed that the proposed odometry estimation algorithm was robust against point cloud degeneration and nonlinearity (e.g., large wheel slippage by drifting) of the kinematic model.

Problem

• Lidar-based odometry
• Wheel odometry accuracy
• Slip and sideways motion

Innovation

• Fusion Algorithm
• Neural Network Learning
• Adaptive Environment