Interpreting Contact Interactions to Overcome Failure in Robot Assembly Tasks
This work provides a method for robots to autonomously perform assembly tasks with unknown parts and positions, which is an incremental improvement for robotic manipulation.
This paper addresses the challenge of multi-part assembly under uncertainty by enabling a robot to learn part types and positions through physical interaction. The proposed probabilistic approach uses differentiable filters to interpret tactile sensorimotor traces from failed attempts, allowing the robot to update its belief about part position and type and overcome assembly failures. Experiments show improved precision in estimation and faster task completion compared to baselines.
A key challenge towards the goal of multi-part assembly tasks is finding robust sensorimotor control methods in the presence of uncertainty. In contrast to previous works that rely on a priori knowledge on whether two parts match, we aim to learn this through physical interaction. We propose a hierarchical approach that enables a robot to autonomously assemble parts while being uncertain about part types and positions. In particular, our probabilistic approach learns a set of differentiable filters that leverage the tactile sensorimotor trace from failed assembly attempts to update its belief about part position and type. This enables a robot to overcome assembly failure. We demonstrate the effectiveness of our approach on a set of object fitting tasks. The experimental results indicate that our proposed approach achieves higher precision in object position and type estimation, and accomplishes object fitting tasks faster than baselines.