Tactile Curiosity Drives Robot Interaction
cs.RO, cs.AI
Submitted: 2026-09-30
Updated: 2026-10-13
Comments: 16 pages, 6 figures, 1 table. Preprint, under review
License: http://creativecommons.org/licenses/by/4.0/
The gist: Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient.
Terminology
Abstract
Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge. Existing intrinsic motivation methods based on model disagreement or epistemic uncertainty improve on isotropic noise, but they can also reward uncertainty in functionally irrelevant transitions, such as erratic motions in free space. In this work, we argue that tactile feedback provides a natural signal for exploration, and introduce TacEx, a framework that incorporates touch into epistemic uncertainty-driven exploration by decomposing model uncertainty across sensory modalities and directing curiosity toward the tactile channel. By anchoring curiosity to the sense of touch, TacEx drives the robot to discover complex contact dynamics, learning to manipulate and grasp objects without task rewards or expert demonstrations during exploration. The interaction-dense dataset collected through this tactile-driven curiosity supports offline learning of downstream pick-and-place policies without additional environment interaction. We further use tactile-driven exploration to post-train vision-language-action (VLA) models. Although the VLAs are initially pre-trained without tactile feedback, post-training with TacEx substantially improves downstream performance while remaining highly sample-efficient.
Sources
- Playing Atari with Deep Reinforcement Learning
- Soft Actor-Critic Algorithms and Applications
- Optimistic Online LQR via Intrinsic Rewards
- Rotating without Seeing: Towards In-hand Dexterity through Touch
- Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning
- DeepMind Control Suite
- Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Diffusion Policy Policy Optimization
- Manipulation by Feel: Touch-Based Control with Deep Predictive Models
- DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexterity
- Tactile-based Object Retrieval From Granular Media
- Exploration by Random Network Distillation
- Learning Soft Robotic Dynamics with Active Exploration
- Sample-efficient and Scalable Exploration in Continuous-Time RL
- Model-Based Reinforcement Learning for Control under Time-Varying Dynamics
- Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies