Bayesian optimization for robust robotic grasping using a sensorized compliant hand

TL;DR

This paper introduces a Bayesian optimization approach for robotic grasping with tactile sensors, enabling safe and efficient adaptation to unknown objects amidst real-world noise and uncertainty.

Contribution

It applies Bayesian optimization to tactile-based robotic grasping, providing a novel framework for safe, adaptive, and efficient grasping in uncertain environments.

Findings

Effective grasping of unknown objects demonstrated

Robustness to noise and environmental uncertainties shown

Improved grasp success rate over baseline methods

Abstract

One of the first tasks we learn as children is to grasp objects based on our tactile perception. Incorporating such skill in robots will enable multiple applications, such as increasing flexibility in industrial processes or providing assistance to people with physical disabilities. However, the difficulty lies in adapting the grasping strategies to a large variety of tasks and objects, which can often be unknown. The brute-force solution is to learn new grasps by trial and error, which is inefficient and ineffective. In contrast, Bayesian optimization applies active learning by adding information to the approximation of an optimal grasp. This paper proposes the use of Bayesian optimization techniques to safely perform robotic grasping. We analyze different grasp metrics to provide realistic grasp optimization in a real system including tactile sensors. An experimental evaluation in the robotic system shows the usefulness of the method for performing unknown object grasping even in the presence of noise and uncertainty inherent to a real-world environment.