A Topological Solution of Entanglement for Complex-shaped Parts in Robotic Bin-picking

TL;DR

This paper introduces a topology-based method using an entanglement map to identify non-tangle grasp points in complex-shaped, heavily entangled objects for robotic bin-picking, outperforming learning-based approaches.

Contribution

The proposed method offers a model-free, efficient approach to detect grasp points in complex scenes, avoiding time-consuming training and enhancing success rates.

Findings

Outperforms previous learning-based methods in success rates.

Does not require object models or training, enabling easy adaptation.

Provides a comprehensive view of entanglement in complex bin-picking scenes.

Abstract

This paper addresses the problem of picking up only one object at a time avoiding any entanglement in bin-picking. To cope with a difficult case where the complex-shaped objects are heavily entangled together, we propose a topology-based method that can generate non-tangle grasp positions on a single depth image. The core technique is entanglement map, which is a feature map to measure the entanglement possibilities obtained from the input image. We use the entanglement map to select probable regions containing graspable objects. The optimum grasping pose is detected from the selected regions considering the collision between robot hand and objects. Experimental results show that our analytic method provides a more comprehensive and intuitive observation of entanglement and exceeds previous learning-based work in success rates. Especially, our topology-based method does not rely on any object models or time-consuming training process, so that it can be easily adapted to more complex bin-picking scenes.