Learning Based Industrial Bin-picking Trained with Approximate Physics Simulator
This addresses the challenge of low success rates in industrial bin-picking due to complex physical contacts, though it is incremental as it builds on existing learning and simulation methods.
The paper tackles the problem of robotic bin-picking from randomly stacked piles by using a learning-based approach with CNN to determine grasping postures, and shows that using exact 3D models for depth images mitigates the effects of approximations in a physics simulator.
In this research, we tackle the problem of picking an object from randomly stacked pile. Since complex physical phenomena of contact among objects and fingers makes it difficult to perform the bin-picking with high success rate, we consider introducing a learning based approach. For the purpose of collecting enough number of training data within a reasonable period of time, we introduce a physics simulator where approximation is used for collision checking. In this paper, we first formulate the learning based robotic bin-picking by using CNN (Convolutional Neural Network). We also obtain the optimum grasping posture of parallel jaw gripper by using CNN. Finally, we show that the effect of approximation introduced in collision checking is relaxed if we use exact 3D model to generate the depth image of the pile as an input to CNN.