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

2025-05-16

AI Summary

Planar velocity estimation for mobile robots—especially high-speed autonomous vehicles—commonly relies on the wheel-ground no-slip assumption, resulting in poor robustness under low-traction conditions. Method: This paper proposes a traction-assumption-free real-time velocity estimation algorithm. It pioneers the integration of microsecond-resolution asynchronous optical flow from a downward-facing event camera with a planar rigid-body kinematic model, augmented by multi-sensor temporal synchronization and an embedded real-time estimation framework. Contribution/Results: Evaluated on a 1:10 autonomous racing platform operating up to 32 m/s, the method reduces lateral velocity estimation error by 38.3% compared to Event-VIO, achieves state-of-the-art accuracy, and demonstrates practical deployability on resource-constrained embedded hardware.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Estimating velocity for fast-moving robots without wheel-slip assumptions
• Overcoming motion blur in vision-based autonomous driving systems
• Improving lateral velocity accuracy using event-based optical flow

Innovation

• Event cameras for robust optical flow
• Planar kinematics decoupled from traction
• High-speed validation up to 32 m/s