# Built Different: Tactile Perception to Overcome Cross-Embodiment Capability Differences in Collaborative Manipulation

arXiv: https://arxiv.org/abs/2409.14896 · HTML: https://mlsanity.com/paper/2409.14896/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1907.13098/) (2019)
- [Learning Visuotactile Skills with Two Multifingered Hands](https://mlsanity.com/paper/2404.16823/) (2024)
- [Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry](https://mlsanity.com/paper/2104.01167/) (2021)
- [GelSlim3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Finger](https://mlsanity.com/paper/2103.12269/) (2021)
- [Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting](https://mlsanity.com/paper/2402.19249/) (2024)
- [Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertion](https://mlsanity.com/paper/2110.03555/) (2021)
- [Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment](https://mlsanity.com/paper/2406.01968/) (2024)
- [A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents](https://mlsanity.com/paper/2402.04580/) (2024)
- [VIRDO++: Real-World, Visuo-tactile Dynamics and Perception of Deformable Objects](https://mlsanity.com/paper/2210.03701/) (2022)
- [DelTact: A Vision-based Tactile Sensor Using Dense Color Pattern](https://mlsanity.com/paper/2202.02179/) (2022)
- [FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network](https://mlsanity.com/paper/1810.02653/) (2018)
- [Tactile-Driven Non-Prehensile Object Manipulation via Extrinsic Contact Mode Control](https://mlsanity.com/paper/2405.18214/) (2024)
- [Integrated Object Deformation and Contact Patch Estimation from Visuo-Tactile Feedback](https://mlsanity.com/paper/2305.14470/) (2023)
- [Effective Estimation of Contact Force and Torque for Vision-based Tactile Sensor with Helmholtz-Hodge Decomposition](https://mlsanity.com/paper/1906.09460/) (2019)
- [GelFlow: Self-supervised Learning of Optical Flow for Vision-Based Tactile Sensor Displacement Measurement](https://mlsanity.com/paper/2309.06735/) (2023)
- [Optical Tactile Sensing for Aerial Multi-Contact Interaction: Design, Integration, and Evaluation](https://mlsanity.com/paper/2401.17149/) (2024)

## Built on by (most cited first, 6 of 6)

- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models](https://mlsanity.com/paper/2509.07962/) (2025)
- [Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation](https://mlsanity.com/paper/2606.29941/) (2026)
- [CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation](https://mlsanity.com/paper/2606.26423/) (2026)
- [TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models](https://mlsanity.com/paper/2606.29089/) (2026)
- [The Embodiment Gap in Robot Foundation Models](https://mlsanity.com/paper/2608.18433/) (2026)

## Abstract (arXiv)

Tactile sensing is a widely-studied means of implicit communication between robot and human. In this paper, we investigate how tactile sensing can help bridge differences between robotic embodiments in the context of collaborative manipulation. For a robot, learning and executing force-rich collaboration require compliance to human interaction. While compliance is often achieved with admittance control, many commercial robots lack the joint torque monitoring needed for such control. To address this challenge, we present an approach that uses tactile sensors and behavior cloning to transfer policies from robots with these capabilities to those without. We train a single policy that demonstrates positive transfer across embodiments, including robots without torque sensing. We demonstrate this positive transfer on four different tactile-enabled embodiments using the same policy trained on force-controlled robot data. Across multiple proposed metrics, the best performance came from a decomposed tactile shear-field representation combined with a pre-trained encoder, which improved success rates over alternative representations.