Leveraging Contact Forces for Learning to Grasp

TL;DR

This paper introduces a model-free deep reinforcement learning approach that leverages contact feedback to improve robotic grasping robustness under uncertainty, especially for complex object shapes and pose variations.

Contribution

It demonstrates that incorporating contact sensing into reinforcement learning policies significantly enhances grasping robustness compared to visual feedback alone.

Findings

Contact feedback improves grasp success rates under pose uncertainty.

Robust grasping achieved with complex finger coordination.

Contact sensing outperforms visual-only approaches in experiments.

Abstract

Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.