Integrating High-Resolution Tactile Sensing into Grasp Stability Prediction

TL;DR

This paper explores combining high-resolution tactile sensors with vision and depth data to enhance grasp stability prediction in robotics, using simulation and neural networks, highlighting benefits and limitations in generalizing to new objects.

Contribution

It demonstrates the integration of tactile sensing with vision and depth for grasp prediction and evaluates neural network performance with expanded object sets and ablation studies.

Findings

Multimodal sensing improves grasp prediction for known objects.

Neural networks struggle to generalize to unknown objects.

Simulation addresses tactile sensing challenges in robotics.

Abstract

We investigate how high-resolution tactile sensors can be utilized in combination with vision and depth sensing, to improve grasp stability prediction. Recent advances in simulating high-resolution tactile sensing, in particular the TACTO simulator, enabled us to evaluate how neural networks can be trained with a combination of sensing modalities. With the large amounts of data needed to train large neural networks, robotic simulators provide a fast way to automate the data collection process. We expand on the existing work through an ablation study and an increased set of objects taken from the YCB benchmark set. Our results indicate that while the combination of vision, depth, and tactile sensing provides the best prediction results on known objects, the network fails to generalize to unknown objects. Our work also addresses existing issues with robotic grasping in tactile simulation and how to overcome them.