UMCP: A Unified Multi-Task Collaborative Perception Network for Luggage Trolley Pose Estimation
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors designed a new vision system for robots that collect luggage trolleys to help them find and recognize trolleys more quickly and accurately in busy places. Instead of using several separate models, their approach combines multiple tasks—detecting trolleys, finding key points on them, and figuring out their direction—into one efficient system. They improved the system's ability to estimate direction by mixing key point and orientation information and using a special math technique called KL divergence. Their tests showed that this combined method works well while saving computing power and time compared to older methods.
robotic perceptionluggage trolley detectionmulti-task learningkeypoint detectionorientation estimationYOLOv12orientation feature enhancement modulecircular probability distributionKullback-Leibler divergencemodel complexity
Authors
Zhirui Sun, Zhihao Jiang, Yao Wang, Jianwei Peng, Jiankun Wang
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.