Do We Still Need to Work on Odometry for Autonomous Driving?

2025-05-07

AI Summary

This work challenges the necessity of high-complexity odometry in autonomous driving and proposes a minimalist wheel encoder–gyroscope (OG) odometry method. The approach fuses only integrated wheel encoder measurements with gyroscope-derived yaw angular velocity, eliminating reliance on LiDAR, vision, or tightly coupled multi-sensor optimization. Evaluated on the Boreas benchmark, OG odometry achieves a state-of-the-art 0.20% relative translational error—outperforming advanced LiDAR-inertial SE(2) methods (0.26%)—while reducing computational cost by three orders of magnitude. Crucially, it maintains robust pose estimation under extreme snowy conditions with substantial wheel slip, degrading gracefully only upon severe slippage. These results demonstrate that, across most practical operating conditions, the lightweight and robust OG paradigm can effectively replace complex multi-source fusion odometry, offering a new design principle for low-cost, high-reliability perception in autonomous driving systems.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Over the past decades, a tremendous amount of work has addressed the topic of ego-motion estimation of moving platforms based on various proprioceptive and exteroceptive sensors. At the cost of ever-increasing computational load and sensor complexity, odometry algorithms have reached impressive levels of accuracy with minimal drift in various conditions. In this paper, we question the need for more research on odometry for autonomous driving by assessing the accuracy of one of the simplest algorithms: the direct integration of wheel encoder data and yaw rate measurements from a gyroscope. We denote this algorithm as Odometer-Gyroscope (OG) odometry. This work shows that OG odometry can outperform current state-of-the-art radar-inertial SE(2) odometry for a fraction of the computational cost in most scenarios. For example, the OG odometry is on top of the Boreas leaderboard with a relative translation error of 0.20%, while the second-best method displays an error of 0.26%. Lidar-inertial approaches can provide more accurate estimates, but the computational load is three orders of magnitude higher than the OG odometry. To further the analysis, we have pushed the limits of the OG odometry by purposely violating its fundamental no-slip assumption using data collected during a heavy snowstorm with different driving behaviours. Our conclusion shows that a significant amount of slippage is required to result in non-satisfactory pose estimates from the OG odometry.

Problem

• Assessing need for advanced odometry in autonomous driving
• Evaluating accuracy of simple Odometer-Gyroscope (OG) odometry
• Testing OG odometry limits under extreme slippage conditions

Innovation

• Simple OG odometry using wheel encoders and gyroscope
• OG odometry outperforms radar-inertial SE(2) methods
• OG odometry has low computational cost