Vision-based Perception System for Automated Delivery Robot-Pedestrians Interactions
This work addresses the challenge of socially acceptable robot-pedestrian interactions for urban delivery robots, but it is incremental as it builds on existing datasets and methods.
The paper tackled the problem of safe and efficient navigation for Automated Delivery Robots in pedestrian-heavy urban spaces by developing a vision-based perception system, resulting in up to a 10% increase in identity preservation, a 7% improvement in multiobject tracking accuracy, and detection precision exceeding 85%.
The integration of Automated Delivery Robots (ADRs) into pedestrian-heavy urban spaces introduces unique challenges in terms of safe, efficient, and socially acceptable navigation. We develop the complete pipeline for a single vision sensor based multi-pedestrian detection and tracking, pose estimation, and monocular depth perception. Leveraging the real-world MOT17 dataset sequences, this study demonstrates how integrating human-pose estimation and depth cues enhances pedestrian trajectory prediction and identity maintenance, even under occlusions and dense crowds. Results show measurable improvements, including up to a 10% increase in identity preservation (IDF1), a 7% improvement in multiobject tracking accuracy (MOTA), and consistently high detection precision exceeding 85%, even in challenging scenarios. Notably, the system identifies vulnerable pedestrian groups supporting more socially aware and inclusive robot behaviour.