TacO: Benchmarking Tactile Sensors for Object Manipulation

2026-05-21

AI Summary

This study addresses the lack of systematic evaluation and selection guidelines for tactile sensors tailored to specific manipulation tasks. It presents the first task-oriented benchmarking framework for tactile sensing, comprehensively evaluating visual, acoustic, magnetic, and resistive sensors across three contact-intensive manipulation tasks. By integrating learning-based manipulation policies, multimodal perception, spatial resolution analysis, and shear force characterization, the work uncovers intricate couplings among sensor modality, object material properties, and task performance. The findings demonstrate that the efficacy of tactile information is highly dependent on the interplay between sensor type, material characteristics, and task requirements. To support reproducibility and future research, the authors publicly release all datasets, code, and hardware configurations, providing an empirical foundation for informed tactile sensor selection in robotic manipulation.

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.

Problem

• tactile sensors
• object manipulation
• sensor evaluation
• manipulation tasks
• task-driven benchmarking

Innovation

• tactile sensing
• manipulation policy
• sensor modality
• task-driven evaluation
• contact-rich manipulation