RadarEye: Robust Liquid Level Tracking Using mmWave Radar in Robotic Pouring

2026-02-11

AI Summary

This study addresses the challenge of unreliable visual perception in robotic pouring tasks involving transparent liquids, where reflections, refractions, and varying illumination hinder accurate liquid-level estimation. To overcome this limitation, the work introduces millimeter-wave radar into this domain for the first time and proposes a real-time signal processing pipeline that integrates high-resolution range-angle beamforming with a physics-informed mid-course tracker. This approach effectively suppresses multipath interference and enables robust liquid surface tracking even under strong clutter. Experimental results demonstrate that the method achieves a median absolute height error of 0.35 cm during real-world water-pouring tasks, with each update requiring only 0.62 ms—significantly outperforming baseline approaches based on vision or ultrasound.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Transparent liquid manipulation in robotic pouring remains challenging for perception systems: specular/refraction effects and lighting variability degrade visual cues, undermining reliable level estimation. To address this challenge, we introduce RadarEye, a real-time mmWave radar signal processing pipeline for robust liquid level estimation and tracking during the whole pouring process. RadarEye integrates (i) a high-resolution range-angle beamforming module for liquid level sensing and (ii) a physics-informed mid-pour tracker that suppresses multipath to maintain lock on the liquid surface despite stream-induced clutter and source container reflections. The pipeline delivers sub-millisecond latency. In real-robot water-pouring experiments, RadarEye achieves a 0.35 cm median absolute height error at 0.62 ms per update, substantially outperforming vision and ultrasound baselines.

Problem

• liquid level tracking
• robotic pouring
• transparent liquid manipulation
• perception challenge
• specular/refraction effects

Innovation

• mmWave radar
• liquid level tracking
• beamforming
• multipath suppression
• robotic pouring