TacO: Benchmarking Tactile Sensors for Object Manipulation

TL;DR

This paper systematically evaluates different tactile sensors for robot manipulation tasks, providing empirical guidance on sensor selection based on task-specific performance and sensor properties.

Contribution

It introduces a framework for selecting tactile sensors tailored to manipulation tasks and compares four sensor modalities across multiple tasks.

Findings

Sensor usefulness varies with modality and task.

Performance depends on sensor resolution, shear sensing, and material friction.

All code, data, and hardware details will be publicly available.

Abstract

Vision-based learning from demonstrations has achieved remarkable success in enabling robots to perform manipulation tasks and high-level semantic reasoning, yet it remains insufficient for complex, contact-rich manipulation. While there is broad agreement that tactile sensing improves manipulation, there is no empirical guidance on which tactile sensors are best suited for which manipulation tasks. In this paper, we provide a systematic, task-driven evaluation of tactile sensors for robot manipulation and propose a framework for selecting and evaluating sensors based on manipulation policy performance. Separate manipulation policies are trained for tactile sensors of four distinct modalities: visual, acoustic, magnetic, and resistive, across three tasks: pick-and-place with unknown mass, object reorientation, and plug insertion. For each task, an analysis of how sensor properties such as spatial resolution, shear sensing, and tactile representation, and the inherent material friction affect task performances is done. Rather than tactile sensing being universally beneficial in the same way, our results show that the usefulness of tactile information depends strongly on sensor modality, material properties, and the specific manipulation tasks. All of the tactile sensors, code, data, and hardware setup will be publicly available on the project website.