SpikeATac: A Multimodal Tactile Finger with Taxelized Dynamic Sensing for Dexterous Manipulation

TL;DR

SpikeATac is a novel multimodal tactile finger combining dynamic PVDF sensing and static capacitive sensing, enabling dexterous manipulation of fragile objects through advanced learning-based control.

Contribution

Introduces SpikeATac, a multimodal tactile sensor with high-speed dynamic response and static sensing, and demonstrates its application in dexterous in-hand manipulation using reinforcement learning.

Findings

Fast, sensitive dynamic signals at contact onset and breakage

Ability to delicately grasp fragile, deformable objects

Successful in-hand manipulation of fragile objects with learned policies

Abstract

In this work, we introduce SpikeATac, a multimodal tactile finger combining a taxelized and highly sensitive dynamic response (PVDF) with a static transduction method (capacitive) for multimodal touch sensing. Named for its `spiky' response, SpikeATac's 16-taxel PVDF film sampled at 4 kHz provides fast, sensitive dynamic signals to the very onset and breaking of contact. We characterize the sensitivity of the different modalities, and show that SpikeATac provides the ability to stop quickly and delicately when grasping fragile, deformable objects. Beyond parallel grasping, we show that SpikeATac can be used in a learning-based framework to achieve new capabilities on a dexterous multifingered robot hand. We use a learning recipe that combines reinforcement learning from human feedback with tactile-based rewards to fine-tune the behavior of a policy to modulate force. Our hardware platform and learning pipeline together enable a difficult dexterous and contact-rich task that has not previously been achieved: in-hand manipulation of fragile objects. Videos are available at https://roamlab.github.io/spikeatac/ .