RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehicles

2025-07-01

AI Summary

To address the challenges of weak perception under visual occlusion, sparse and noisy radar point clouds, high computational overhead, and prohibitive hardware costs associated with traditional SLAM systems on low-cost indoor mobile robots, this paper proposes a lightweight Graph Neural Network (GNN)-based point cloud enhancement framework tailored for millimeter-wave radar. It is the first work to deploy GNNs on resource-constrained edge devices for radar point cloud denoising, completion, and structural optimization. Leveraging sparse graph modeling and inference acceleration techniques, the framework achieves a single-frame inference latency of 7.3 ms on a Raspberry Pi 5—without requiring additional compute resources. The method significantly improves localization accuracy, SLAM robustness, and navigation reliability. Extensive evaluation across three representative indoor dynamic scenarios demonstrates strong generalization capability and cross-platform deployability.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Low-cost indoor mobile robots have gained popularity with the increasing adoption of automation in homes and commercial spaces. However, existing lidar and camera-based solutions have limitations such as poor performance in visually obscured environments, high computational overhead for data processing, and high costs for lidars. In contrast, mmWave radar sensors offer a cost-effective and lightweight alternative, providing accurate ranging regardless of visibility. However, existing radar-based localization suffers from sparse point cloud generation, noise, and false detections. Thus, in this work, we introduce RaGNNarok, a real-time, lightweight, and generalizable graph neural network (GNN)-based framework to enhance radar point clouds, even in complex and dynamic environments. With an inference time of just 7.3 ms on the low-cost Raspberry Pi 5, RaGNNarok runs efficiently even on such resource-constrained devices, requiring no additional computational resources. We evaluate its performance across key tasks, including localization, SLAM, and autonomous navigation, in three different environments. Our results demonstrate strong reliability and generalizability, making RaGNNarok a robust solution for low-cost indoor mobile robots.

Problem

• Enhancing sparse radar point clouds for indoor robots
• Reducing noise and false detections in radar data
• Enabling real-time processing on resource-constrained devices

Innovation

• Lightweight GNN for radar point cloud enhancement
• Real-time processing on resource-constrained devices
• Generalizable across diverse environments and tasks