Research Analyzer
← Back ICRA 2026

TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation

Yinghao Wu, Shuhong Hou, Haowen Zheng, Yichen Li, Weiyi Lu, Xun Zhou, Yitian Shao

PDF

AI summary

Key figure (auto-extracted from paper)
A low-cost IMU-based tactile sensing framework enables robots to perform high-precision insertion tasks by detecting micrometer-scale deformations.
tactile sensing robotic manipulation diffusion policy IMU contact-rich tasks

Problem

Visual perception is often insufficient or obstructed during fine robotic insertion tasks, and existing touch sensors are either insensitive to subtle changes or produce excessive data.

Approach

Integrates a 6-axis IMU into elastomeric gripper tips and uses transformer encoders with a diffusion policy to fuse transient tactile cues with visual data for 6-DoF control.

Key results

  • 79% average success rate on grasping and insertion tasks, outperforming vision-only and force/torque sensing policies
  • 88% average success rate in tactile-only insertion tasks with initial misalignments of 1 to 3 mm
  • Nearly 70% success rate when generalizing from a single prism-slot pair to unseen objects like USB plugs and metal keys
  • High data efficiency (42 KB/s) and low hardware cost ($5)

Why it matters

Provides an affordable, high-bandwidth sensing solution for delicate robotic manipulation tasks where vision is insufficient.

Abstract

Robotic manipulation tasks such as inserting a key into a lock or plugging a USB device into a port can fail when visual perception is insufficient to detect misalignment. In these situations, touch sensing is crucial for the robot to monitor the task’s states and make precise, timely adjustments. Current touch sensing solutions are either insensitive to detect subtle changes or demand excessive sensor data. Here, we introduce TranTac, a data-efficient and low-cost tactile sensing and control framework that integrates a single contact-sensitive 6-axis inertial measurement unit within the elastomeric tips of a robotic gripper for completing fine insertion tasks. Our customized sensing system can detect dynamic translational and torsional deformations at the micrometer scale, enabling the tracking of visually imperceptible pose changes of the grasped object. By leveraging transformer-based encoders and diffusion policy, TranTac can imitate human insertion behaviors using transient tactile cues detected at the gripper’s tip during insertion processes. These cues enable the robot to dynamically control and correct the 6-DoF pose of the grasped object. When combined with vision, TranTac achieves an average success rate of 79% on object grasping and insertion tasks, outperforming both vision-only policy and the one augmented with end-effector 6D force/torque sensing. Additionally, TranTac’s contact local- ization performance is validated through tactile-only insertion tasks, where the inserted object and slot are initially misaligned by 1 to 3 mm, achieving an average success rate of 88%. We assess the generalizability by training TranTac on a single prism-slot pair and testing it on unseen data, including a USB plug and a metal key, and find that the insertion tasks can still be completed with an average success rate of nearly 70%. The proposed framework may inspire new robotic tactile sensing systems for delicate manipulation tasks. Project page: https://wusdream.github.io/TranTac/

Index terms

Force and Tactile Sensing Assembly Bioinspired Robot Learning

Related papers