Learning Heterogeneous Tactile Representation for General Dexterous Manipulation
Paper · https://arxiv.org/abs/2611.12806
Tactile sensing is an indispensable modality for contact-rich dexterous manipulation, a capability that hints at the ultimate frontiers of embodied intelligence. However, commercially available tactile sensors are still at a relatively early stage of development, with each type of sensor offering irreplaceable strengths alongside its own drawbacks. A key challenge is thus to free tactile understanding from sensor-specific physics, so that embodied models can effectively leverage heterogeneous tactile data. To this end, we develop LingBot-Touch, a tactile foundation model characterized by the following properties. (i) Our model yields a unified representation across different tactile sensors (i.e., piezoresistive, magnetic, and visuotactile sensors), and is easily extensible to new sensor types. (ii) The resulting tactile tokens are plug-and-play: they can be seamlessly integrated into policy models across paradigms, from diffusion policy to vision-language-action (VLA) models such as π_{0.5} and LingBot-VLA, consistently enhancing manipulation dexterity. (iii) Extensive experiments, spanning simulation and real-robot deployments across multiple hardware platforms, demonstrate that our tactile representation substantially benefits complex manipulation tasks while maintaining strong computational efficiency. We believe the findings in this work demonstrate the potential of leveraging cross-sensor data to scale tactile learning, and offer encouraging insights for the design of future hardware and embodied models.
First seen by Oriel on .
AI summary
The paper introduces LingBot-Touch, a tactile foundation model that learns a unified representation across sensor types and improves dexterous manipulation when integrated into policy models.
- LingBot-Touch supports piezoresistive, magnetic, and visuotactile sensors, with an architecture described as extensible to new sensor types.
- Its tactile tokens can be integrated into diffusion policy and vision-language-action models, including $\pi_{0.5}$ and LingBot-VLA.
- Experiments in simulation and on real robots across multiple hardware platforms report improvements on complex manipulation tasks.
- The authors report strong computational efficiency but provide no numerical performance results in the abstract.
#tactile sensing #robot manipulation #foundation models #embodied ai
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hugging Face Papers: 105, latest observation ; +13 over observed period since
Comments
Comment count reported by the source.
- Hugging Face Papers: 2, latest observation ; +1 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Papers | 2611.12806 | https://arxiv.org/abs/2611.12806 Read discussion |