CRADMap: Applied Distributed Volumetric Mapping with 5G-Connected Multi-Robots and 4D Radar Sensing

2025-03-01

AI Summary

Existing sparse/feature-based SLAM methods are robust but lack geometric detail, while dense SLAM achieves high accuracy at prohibitive computational cost; 4D millimeter-wave (mmWave) radar remains underexploited for occluded metallic object perception. This paper proposes a distributed real-time dense mapping framework tailored for complex indoor environments. The system employs a collaborative SLAM frontend integrating ORB-SLAM3 and COVINS, transmitting lightweight keyframes over low-latency 5G to a central server. Multi-robot geometric and occupancy information is fused via Truncated Signed Distance Function (TSDF) voxel reconstruction. Crucially, we introduce 4D mmWave radar as an independent modality for implicit mapping of occluded metallic objects—previously unaddressed in visual-inertial dense SLAM. Each robot operates lightweight onboard, while the server-side map reconstruction achieves a 42% accuracy improvement. The framework delivers globally consistent, real-time-updated, high-fidelity 3D reconstructions in realistic cluttered indoor settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

Sparse and feature SLAM methods provide robust camera pose estimation. However, they often fail to capture the level of detail required for inspection and scene awareness tasks. Conversely, dense SLAM approaches generate richer scene reconstructions but impose a prohibitive computational load to create 3D maps. We present a novel distributed volumetric mapping framework designated as CRADMap that addresses these issues by extending the state-of-the-art (SOTA) ORBSLAM3 [1] system with the COVINS [2] on the backend for global optimization. Our pipeline for volumetric reconstruction fuses dense keyframes at a centralized server via 5G connectivity, aggregating geometry, and occupancy information from multiple autonomous mobile robots (AMRs) without overtaxing onboard resources. This enables each AMR to independently perform mapping while the backend constructs high-fidelity 3D maps in real time. To overcome the limitation of standard visual nodes we automate a 4D mmWave radar, standalone from CRADMap, to test its capabilities for making extra maps of the hidden metallic object(s) in a cluttered environment. Experimental results Section-IV confirm that our framework yields globally consistent volumetric reconstructions and seamlessly supports applied distributed mapping in complex indoor environments.

Problem

• Addresses limitations of sparse and dense SLAM methods
• Enables real-time high-fidelity 3D mapping with 5G-connected robots
• Overcomes visual limitations with 4D radar for hidden objects

Innovation

• Distributed volumetric mapping with 5G connectivity
• Integration of ORBSLAM3 and COVINS for global optimization
• 4D radar sensing for hidden object detection