# Learning tactile perception from high-bandwidth single-point sensing

arXiv: https://arxiv.org/abs/2609.24621 · HTML: https://mlsanity.com/paper/2609.24621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation](https://mlsanity.com/paper/2005.14679/) (2020)
- [See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation](https://mlsanity.com/paper/2212.03858/) (2022)
- [ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data](https://mlsanity.com/paper/2406.19464/) (2024)
- [AnySkin: Plug-and-play Skin Sensing for Robotic Touch](https://mlsanity.com/paper/2409.08276/) (2024)
- [Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning](https://mlsanity.com/paper/2205.14850/) (2022)
- [TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation](https://mlsanity.com/paper/2603.12665/) (2026)
- [Hearing Touch: Audio-Visual Pretraining for Contact-Rich Manipulation](https://mlsanity.com/paper/2405.08576/) (2024)
- [PolyTouch: A Robust Multi-Modal Tactile Sensor for Contact-rich Manipulation Using Tactile-Diffusion Policies](https://mlsanity.com/paper/2504.19341/) (2025)
- [Touch begins where vision ends: Generalizable policies for contact-rich manipulation](https://mlsanity.com/paper/2506.13762/) (2025)
- [Learning Precise, Contact-Rich Manipulation through Uncalibrated Tactile Skins](https://mlsanity.com/paper/2410.17246/) (2024)
- [FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems](https://mlsanity.com/paper/2604.28156/) (2026)
- [eFlesh: Highly customizable Magnetic Touch Sensing using Cut-Cell Microstructures](https://mlsanity.com/paper/2506.09994/) (2025)
- [TacO: Benchmarking Tactile Sensors for Object Manipulation](https://mlsanity.com/paper/2605.21976/) (2026)
- [Tactile-Driven Gentle Grasping for Human-Robot Collaborative Tasks](https://mlsanity.com/paper/2303.09346/) (2023)
- [Tactile Genesis: Exploring Tactile Sensors at Scale for Learning Dexterous Tasks](https://mlsanity.com/paper/2606.22332/) (2026)
- [VibeAct: Vibration to Actions for Contact-Rich Reactive Robot Dexterity](https://mlsanity.com/paper/2606.27344/) (2026)

## Abstract (arXiv)

Tactile sensing is increasingly being incorporated into learning-based robotic manipulation, yet many existing approaches rely on spatially distributed sensors. Here we introduce {SpectRobot}, a framework that transforms single-point tactile signals into compact time-frequency spectrograms. These spectrograms encode high-bandwidth tactile histories as fixed-size image-like representations. They can be processed by standard vision encoders and integrated into learning pipelines originally developed for vision, while preserving temporal and frequency information unavailable to conventional cameras. Rather than increasing spatial density through arrays of tactile elements, SpectRobot exploits the rich dynamics contained in sparse, high-bandwidth single-point measurements. In our implementation, the sensors are mounted away from the contact surface while remaining mechanically coupled to it, reducing direct exposure to wear and potentially improving robustness in harsh environments and for long-term deployment on dexterous robots. Our experiments demonstrate that: (1) a robot can exploit single-point vibration signals to solve a visually occluded manipulation task; (2) temporal history strongly influences policy performance, while sensing bandwidth controls the spectral information available, with measurements extending to 100~kHz; and (3) the same representation can be used across different tactile sensing technologies mediated by acceleration, force, or strain. We further show that capabilities previously associated with research-grade instrumentation can be accessed using readily available, off-the-shelf hardware. We believe that broader access to high-bandwidth tactile sensing could facilitate the integration of contact dynamics into embodied learning systems and, for some tasks, offer an alternative or complement to increasing the spatial density of tactile sensing.