Robotics · 2026-10-15
Tactile-Guided Robot Learning: From Representation Learning to Foundation Models
Kiyanoush Nazari, Luchen Li, Haoshu Fang, Nima Fazeli, Zhibin Li, Fumiya Iida, Thomas George Thuruthel
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
This paper is a learning-centric review of tactile-guided robot learning for dexterous manipulation. It organizes research by touch’s functional role across representation learning, tactile-conditioned policies, tactile foundation/world models, predictive/adaptive tactile control, and generalization (objects, tasks, sensors, embodiments, and sim-to-real). It argues touch is shifting from task-specific feedback to a core modality for general-purpose embodied intelligence.
Why it matters
The authors report that tactile-guided manipulation is fragmented and that existing surveys often emphasize hardware/perception and predate foundation-model/VLA systems. By structuring how touch contributes across the learning and control pipeline, the review highlights design principles and remaining challenges for learning transferable physical representations and for scaling tactile learning across heterogeneous data and hardware.
Method
- Review structured by functional role of tactile information across learning/control: representation, tactile-conditioned policies, tactile foundation/world models, predictive/adaptive control, and generalization/sim-to-real.
- Synthesizes design principles and remaining challenges for learning transferable physical representations, integrating semantic reasoning with contact-level control, and scaling tactile learning across heterogeneous data and hardware.
- Frames emerging directions toward tactile foundation and world models that can predict, reason about, and adapt physical interactions.
Limitation
As a review, the paper does not report new experimental results; its focus is on synthesizing prior work and identifying remaining challenges and research directions.
Abstract (from arXiv)
Tactile sensing is becoming central to robust, adaptive, and dexterous robotic manipulation. Beyond its traditional role in contact detection and reactive control, touch is increasingly used to learn transferable representations, condition manipulation policies, and support embodied physical reasoning. Yet existing surveys largely emphasize tactile hardware and perception, leaving the rapid shift toward learning-based tactile manipulation insufficiently synthesized. This paper reviews tactile-guided skill learning from a learning-centric perspective, organized by the functional role of touch across the learning and control pipeline. We examine tactile representation and policy learning, tactile foundation models, predictive and adaptive control, and generalization across objects, tasks, sensors, embodiments, and simulation-to-real transfer. Across these directions, we identify common design principles and remaining challenges in learning transferable physical representations, integrating semantic reasoning with contact-level control, and scaling tactile learning across heterogeneous data and hardware. Finally, we outline emerging directions toward tactile foundation and world models that can predict, reason about, and adapt physical interactions. Together, this review characterizes the transition of touch from a task-specific feedback signal toward a core modality for general-purpose embodied intelligence. An accompanying database of the reviewed literature and associated resources is available at https://sites.google.com/view/touch-in-robot-learning-review.
Related papers
- TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Model
- Physical Canvas: A Vision Tactile World Model For Robot Policy Evaluation And Learning
- ACTS: Learning Visuo-Tactile World Models from Human Physical Interaction
- Dexterous Tactile World Model
- Touch-JEPA: Tactile Representation Learning from Hand-Object Video with Limited Tactile Supervision
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-10-14 · Indexed by Pub-AI: 2026-10-15 UTC
Tactile-Guided Robot Learning: From Representation Learning to Foundation Models
Preprint posted: 2026-10-14 · Original record ↗
- arxiv
- 2610.20134
Explicit source versions (1)
- v1 · 2026-10-14
- Preprint available
Source date: 2026-10-14 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Tactile sensing is becoming central to robust, adaptive, and dexterous robotic manipulation. Beyond its traditional role in contact detection and reactive control, touch is increasingly used to learn transferable representations, condition manipulation policies, and support embodied physical reasoning. Yet existing surveys largely emphasize tactile hardware and perception, leaving the rapid shift toward learning-based tactile manipulation insufficiently synthesized. This paper reviews tactile-guided skill learning from a learning-centric perspective, organized by the functional role of touch across the learning and control pipeline. We examine tactile representation and policy learning, tactile foundation models, predictive and adaptive control, and generalization across objects, tasks, sensors, embodiments, and simulation-to-real transfer. Across these directions, we identify common design principles and remaining challenges in learning transferable physical representations, integrating semantic reasoning with contact-level control, and scaling tactile learning across heterogeneous data and hardware. Finally, we outline emerging directions toward tactile foundation and world models that can predict, reason about, and adapt physical interactions. Together, this review characterizes the transition of touch from a task-specific feedback signal toward a core modality for general-purpose embodied intelligence. An accompanying database of the reviewed literature and associated resources is available at https://sites.google.com/view/touch-in-robot-learning-review.