TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

2026-06-23

AI Summary

This work addresses the challenge of enabling robots to autonomously explore and identify objects within confined spaces using only tactile sensing in the absence of vision. The authors propose a purely tactile-driven, end-to-end reinforcement learning framework that, for the first time, achieves a fully vision-free exploration policy trained entirely on real hardware. By integrating tactile perception from a multi-fingered dexterous hand, tactile-based 3D reconstruction, and a dynamic reward scheduling mechanism, the approach unifies global exploration with local fine-grained perception. Experimental results demonstrate that the system attains a 77% task success rate in real-world environments with an average reconstruction error of 0.015 meters, significantly outperforming existing baseline methods.

Abstract

Humans effortlessly locate and identify objects by touch alone, even without vision. In contrast, robotic systems rely heavily on vision and struggle with autonomous tactile exploration and object identification. We present TACTFUL, a vision-free tactile exploration framework that enables a multi-fingered robot to autonomously explore confined workspaces, discover objects through contact, and identify them via tactile reconstruction. Trained entirely on real hardware without simulation, our system learns a single policy that balances global workspace exploration with local surface refinement through a dynamic reward schedule. Our results demonstrate that tactile sensing, when paired with structured learning, can serve as an effective primary modality for object-level reasoning, achieving 77% success with 0.015 m average reconstruction error and outperforming baseline approaches on real-world objects.

Problem

• tactile exploration
• object localization
• object identification
• vision-free robotics
• confined environments

Innovation

• tactile-driven exploration
• vision-free robotics
• tactile reconstruction
• real-world policy learning
• object identification