# TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance

arXiv: https://arxiv.org/abs/2601.20239 · HTML: https://mlsanity.com/paper/2601.20239/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2026.

## Built on by (most cited first, 12 of 12)

- [Tactile Modality Fusion for Vision-Language-Action Models](https://mlsanity.com/paper/2603.14604/) (2026)
- [TacCoRL: Integrating Tactile Feedback into VLA via Simulation](https://mlsanity.com/paper/2606.11743/) (2026)
- [Inference-time Policy Steering via Vision and Touch](https://mlsanity.com/paper/2606.14981/) (2026)
- [Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation](https://mlsanity.com/paper/2606.29941/) (2026)
- [N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2607.23783/) (2026)
- [τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision](https://mlsanity.com/paper/2607.24485/) (2026)
- [Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion](https://mlsanity.com/paper/2607.17257/) (2026)
- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)
- [Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation](https://mlsanity.com/paper/2604.05544/) (2026)
- [Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation](https://mlsanity.com/paper/2608.09410/) (2026)
- [N0-Foundation: Towards the Age of Tactile Intelligence](https://mlsanity.com/paper/2608.29601/) (2026)
- [Robot Learning with Visual Predicted Force](https://mlsanity.com/paper/2610.04741/) (2026)

## Abstract (arXiv)

Fine-grained and contact-rich manipulation remain challenging for robots, largely due to the underutilization of tactile feedback. To address this, we introduce TouchGuide, a novel cross-policy visuo-tactile fusion paradigm that fuses modalities within a low-dimensional action space. Specifically, TouchGuide operates in two stages to guide a pre-trained diffusion or flow-matching visuomotor policy at inference time. First, the policy produces a coarse, visually-plausible action using only visual inputs during early sampling. Second, a task-specific Contact Physical Model (CPM) provides tactile guidance to steer and refine the action, ensuring it aligns with realistic physical contact conditions. Trained through contrastive learning on limited expert demonstrations, the CPM provides a tactile-informed feasibility score to steer the sampling process toward refined actions that satisfy physical contact constraints. Furthermore, to facilitate TouchGuide training with high-quality and cost-effective data, we introduce TacUMI, a data collection system. TacUMI achieves a favorable trade-off between precision and affordability; by leveraging rigid fingertips, it obtains direct tactile feedback, thereby enabling the collection of reliable tactile data. Extensive experiments on five challenging contact-rich tasks, such as shoe lacing and chip handover, show that TouchGuide consistently and significantly outperforms state-of-the-art visuo-tactile policies.