UMCP: A Unified Multi-Task Collaborative Perception Network for Luggage Trolley Pose Estimation

2026-07-20

AI Summary

This work addresses the challenges of high inference latency and substantial deployment costs associated with cascaded models for real-time, high-precision pose estimation of luggage carts in complex dynamic scenes. To this end, we propose an end-to-end unified multi-task collaborative perception network built upon the YOLOv12 architecture, which simultaneously performs object detection, keypoint localization, and orientation estimation. We introduce an Orientation Feature Enhancement Module (OFEM) and model orientation as a circular probability distribution using KL divergence to enhance angular accuracy. Experimental results demonstrate that the proposed method achieves competitive overall performance while significantly reducing model complexity and computational overhead, outperforming existing approaches.

Abstract

In robotic autonomous luggage trolley collection, robots must continuously localize scattered luggage trolleys in cluttered and dynamic environments. This requires the vision system to achieve both high accuracy and real-time performance. However, existing visual perception approaches for luggage trolleys often rely on cascaded multi-model inference, leading to increased inference latency and high deployment costs. To address these limitations, this article presents a unified multi-task collaborative perception network (UMCP) that simultaneously performs luggage trolley detection, keypoint detection and orientation estimation. Based on the YOLOv12 architecture, keypoint features are fused with orientation features and then fed into an orientation feature enhancement module (OFEM), thereby improving orientation estimation accuracy. In addition, circular probability distribution modeling with a Kullback-Leibler (KL) divergence loss is adopted to enhance orientation estimation accuracy further. Experimental results demonstrate that the proposed method achieves competitive overall accuracy while substantially reducing model complexity and computational cost compared with existing methods. A website about this work is available at https://sites.google.com/view/robot-umcp.

Problem

• luggage trolley pose estimation
• multi-task perception
• real-time performance
• model complexity
• inference latency

Innovation

• Unified Multi-Task Learning
• Orientation Estimation
• Keypoint Detection
• Circular Probability Distribution
• YOLOv12