Enhancing Indoor Mobility with Connected Sensor Nodes: A Real-Time, Delay-Aware Cooperative Perception Approach

TL;DR

Problem: indoor mobility in crowded, dynamic spaces where single-node perception struggles with occlusions and delays. Approach: a real-time, delay-aware cooperative perception system with local sensor-node processing and a central delay-aware fusion module, including adaptive clustering and ground-contact LiDAR-camera fusion. Contributions: (1) adaptive hierarchical clustering that accounts for scanning patterns, (2) ground-contact feature-based LiDAR-camera fusion, (3) delay-aware global perception that compensates network latency, and (4) a new Indoor Pedestrian Tracking dataset for dynamic indoor scenarios. Findings: experiments show improved detection precision and robustness to delays compared with baselines, validating practical utility for intelligent hospital mobility. Significance: enables safer and more reliable autonomous hospital beds and delivery robots in healthcare facilities.

Abstract

This paper presents a novel real-time, delay-aware cooperative perception system designed for intelligent mobility platforms operating in dynamic indoor environments. The system contains a network of multi-modal sensor nodes and a central node that collectively provide perception services to mobility platforms. The proposed Hierarchical Clustering Considering the Scanning Pattern and Ground Contacting Feature based Lidar Camera Fusion improve intra-node perception for crowded environment. The system also features delay-aware global perception to synchronize and aggregate data across nodes. To validate our approach, we introduced the Indoor Pedestrian Tracking dataset, compiled from data captured by two indoor sensor nodes. Our experiments, compared to baselines, demonstrate significant improvements in detection accuracy and robustness against delays. The dataset is available in the repository: https://github.com/NingMingHao/MVSLab-IndoorCooperativePerception

Figures (6)

• Figure 1: Overview of the proposed cooperative perception system
• Figure 2: The proposed delay-aware cooperative perception framework.
• Figure 3: The time synchronization process.Master clock. ensure uniform trigger signals for simultaneous data capture. Sensor Node soft triggers ensures temporal alignment of multi-modal data. Center Node aggregation and processing of synchronized data from all nodes.
• Figure 4: Clustering Example.Image and the projected points.Over-Segmentation-$\epsilon=0.25m$.Under-Segmentation-$\epsilon=0.5m$.Proposed Hierarchical Clustering.Different clusters are shown in different colors.
• Figure 5: Computation Time Comparison.