Planar Velocity Estimation for Fast-Moving Mobile Robots Using Event-Based Optical Flow

TL;DR

This paper presents a novel velocity estimation method for fast-moving mobile robots using event-based optical flow, which is robust to motion blur and does not rely on slip assumptions, showing promising results in real-world tests.

Contribution

The authors introduce a ground-plane optical flow approach that decouples velocity estimation from wheel traction assumptions, leveraging event cameras for improved robustness and accuracy.

Findings

Achieves performance comparable to state-of-the-art Event-VIO.

Demonstrates a 38.3% reduction in lateral error.

Effective at highway speeds up to 32 m/s.

Abstract

Accurate velocity estimation is critical in mobile robotics, particularly for driver assistance systems and autonomous driving. Wheel odometry fused with Inertial Measurement Unit (IMU) data is a widely used method for velocity estimation; however, it typically requires strong assumptions, such as non-slip steering, or complex vehicle dynamics models that do not hold under varying environmental conditions like slippery surfaces. We introduce an approach to velocity estimation that is decoupled from wheel-to-surface traction assumptions by leveraging planar kinematics in combination with optical flow from event cameras pointed perpendicularly at the ground. The asynchronous micro-second latency and high dynamic range of event cameras make them highly robust to motion blur, a common challenge in vision-based perception techniques for autonomous driving. The proposed method is evaluated through in-field experiments on a 1:10 scale autonomous racing platform and compared to precise motion capture data, demonstrating not only performance on par with the state-of-the-art Event-VIO method but also a 38.3 % improvement in lateral error. Qualitative experiments at highway speeds of up to 32 m/s further confirm the effectiveness of our approach, indicating significant potential for real-world deployment.