TranTac: Leveraging Transient Tactile Signals for Contact-Rich Robotic Manipulation
🤖 AI Summary
To address failure in fine insertion tasks—such as key insertion or USB plugging—caused by visually imperceptible micrometer-scale misalignments, this paper proposes TranTac, the first framework to leverage transient, micrometer-resolution tactile signals alongside vision–tactile fusion for dynamic control. Methodologically, it integrates a low-power, high-sensitivity 6-axis IMU within an elastic fingertip for tactile sensing, employs a Transformer encoder to model temporal tactile dynamics, and utilizes a diffusion-based policy model for real-time 6-DoF pose adjustment. Compared with state-of-the-art approaches, TranTac significantly improves robustness and generalization: achieving 79% average success rate in grasp-and-insert tasks, 88% alignment accuracy under vision-free conditions, and near 70% cross-object generalization success. Its core contribution is establishing a lightweight, dynamic, and generalizable tactile-driven manipulation paradigm tailored to high-contact-complexity scenarios.
Application Category
📝 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. Contact localization performance is also validated through tactile-only misaligned insertion tasks, 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.
Problem
Research questions and friction points this paper is trying to address.
Robotic manipulation fails when vision cannot detect subtle misalignments
Current tactile sensors lack sensitivity or require excessive data
Fine insertion tasks need precise pose tracking using transient tactile cues
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses transient tactile signals for manipulation
Integrates IMU sensors in gripper tips
Employs transformer encoders with diffusion policy
🔎 Similar Papers
No similar papers found.
