RadarTrack: Enhancing Ego-Vehicle Speed Estimation with Single-chip mmWave Radar

2025-04-20

AI Summary

To address the limitations of Doppler-shift-based velocity estimation in single-chip millimeter-wave radar—namely, its reliance on static-scene assumptions and inability to meet low-latency requirements for embedded systems—this paper proposes RadarTrack, a signal-processing-only real-time velocity estimation algorithm. RadarTrack introduces a novel paradigm that directly computes ego-velocity from inter-frame phase differences, eliminating dependence on Doppler spectrum analysis and the static-environment assumption. The algorithm is lightweight and computationally efficient, enabling deployment on resource-constrained embedded platforms with end-to-end latency under 10 ms. Evaluated on real-world automotive datasets, it achieves a mean absolute velocity estimation error of <0.15 m/s—outperforming state-of-the-art deep learning–based and multi-modal fusion approaches. This work establishes a new single-sensor velocity perception paradigm that is high-accuracy, low-power, and robust—enabling applications in micro-robotics, AR navigation, and cost-effective autonomous driving systems.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In this work, we introduce RadarTrack, an innovative ego-speed estimation framework utilizing a single-chip millimeter-wave (mmWave) radar to deliver robust speed estimation for mobile platforms. Unlike previous methods that depend on cross-modal learning and computationally intensive Deep Neural Networks (DNNs), RadarTrack utilizes a novel phase-based speed estimation approach. This method effectively overcomes the limitations of conventional ego-speed estimation approaches which rely on doppler measurements and static surrondings. RadarTrack is designed for low-latency operation on embedded platforms, making it suitable for real-time applications where speed and efficiency are critical. Our key contributions include the introduction of a novel phase-based speed estimation technique solely based on signal processing and the implementation of a real-time prototype validated through extensive real-world evaluations. By providing a reliable and lightweight solution for ego-speed estimation, RadarTrack holds significant potential for a wide range of applications, including micro-robotics, augmented reality, and autonomous navigation.

Problem

• Enhancing ego-vehicle speed estimation using single-chip mmWave radar
• Overcoming limitations of Doppler-based methods with phase-based approach
• Enabling low-latency real-time speed estimation for embedded platforms

Innovation

• Single-chip mmWave radar for speed estimation
• Novel phase-based speed estimation technique
• Low-latency embedded platform implementation