Picking Bins Empty: A Hierarchical Hybrid Approach with Online Self-Learning of Grasp Points for Reliable Industrial Bin-Picking
Robotics
Summary
The authors address the problem of robot bin-picking, where a robot must pick up many parts without needing human help. They combine two common methods: a precise model-based system and a flexible model-free system. Their hybrid approach uses the model-based method for normal picking and the model-free part to handle tricky cases where the model-based system fails. They also add an automatic learning step to improve the robot's grasp choices over time. Tests on car parts showed their method cleared bins completely and worked better than using either method alone.
bin-pickingmodel-based methodsmodel-free algorithmsgrasp pointsrobotic manipulationhierarchical hybrid approachself-learningWilson score intervalsautonomous operation
Authors
Florian Töper, Samarth Kishor Yelvande, Jan Niklas Ewertz, Rudolph Triebel, Peter Ohlhausen
Abstract
Bin-picking is a cornerstone of modern manufacturing, yet achieving complete bin clearance without manual intervention remains a critical challenge. While model-based methods provide high precision, they frequently suffer from deadlocks when predefined grasps are occluded or perception fails. Labor-intensive fine-tuning of grasp points is commonly required to reach a satisfactory performance for new parts. Model-free algorithms offer a more flexible alternative with "out-of-the-box" versatility but lack the reliability and repeatability required for production. Unlike existing work, which treats the two techniques in isolation, we propose a fourtiered hierarchical hybrid approach to combine the best of both worlds. A model-based pipeline serves as a robust backbone, while a model-free "exploration agent" resolves deadlock situations and discovers new grasp points. This is supported by an online self-learning mechanism that uses gripper-stroke feedback and Wilson score intervals to autonomously rank grasp candidates, reducing manual commissioning effort. Validation on three automotive parts demonstrates that our method significantly outperforms a model-free baseline in grasp success rate while improving the bin clearance rate of the model-based baseline from 50.9% to 100% across all experiments. This transition to full bin clearance marks a significant step towards truly autonomous, intervention-free industrial operation.