A Unified Multi-Task Deep Learning Framework for Robotic Bin-Picking of Planar Objects

Abstract

Automating random bin-picking in industrial robotics, where robots handle diverse and cluttered objects, remains challenging due to the complexity of object detection and pose estimation. While many solutions focus on free-form objects, systems specifically designed for planar objects are lacking. Planar objects pose unique challenges, as the commonly used point pair feature approach for free-form objects is ineffective due to their lack of distinctive geometric features. In this study, the proposed framework was implemented and evaluated using USB packs as a representative planar object case study. An innovative approach is introduced for the random bin-picking of planar objects by developing a multi-task model for instance segmentation and keypoint detection in 2D images. Geometric approach is then employed to estimate the 6D object pose for robotic grasping. Furthermore, a grasp candidate selection strategy is proposed to enable reliable grasping in cluttered industrial environments. Experimental results show that the proposed method achieved mAP50 values of 0.954, 0.800, and 0.926 for bounding box detection, instance segmentation, and keypoint detection, respectively, with a processing time of 2.7 ms. Future work will focus on integrating the framework into a digital twin system to support real-time monitoring, simulation, and optimization of automated manufacturing processes.