UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation

• URL: http://arxiv.org/abs/2606.31451v1
• Date: Tue, 30 Jun 2026 10:25:46 GMT
• Title: UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation
• Abstract summary: We propose UniTac, the first UMM designed for tactile understanding and generation.<n>UniTac models the tactile process as a transition from non-contact to contact, capturing the physical interaction between sensors and objects through a dual-level representation.<n>For tactile understanding, UniTac introduces two tasks, object property description and sensor identification, to enhance reasoning over physical and cross-sensor information.<n>For tactile generation, we design a two-stage training paradigm consisting of reconstruction and alignment, together with a sensor-prior-based sampling strategy that simulates realistic tactile contact.
• Score: 31.729644010916576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unified multimodal models (UMMs) have shown great promise in integrating understanding and generation across diverse modalities. However, existing research rarely extends this paradigm to the tactile domain, where both object-level semantics and sensor-level configurations jointly determine the meaning of touch. To address this gap, we propose UniTac, the first UMM designed for tactile understanding and generation. UniTac models the tactile process as a transition from non-contact to contact, capturing the physical interaction between sensors and objects through a dual-level representation that encodes both sensor and object attributes. For tactile understanding, UniTac introduces two tasks, object property description and sensor identification, to enhance reasoning over physical and cross-sensor information. For tactile generation, we design a two-stage training paradigm consisting of reconstruction and alignment, together with a sensor-prior-based sampling strategy that simulates realistic tactile contact. Trained on large-scale multi-sensor datasets, UniTac achieves state-of-the-art performance in tactile understanding and generates realistic tactile signals across sensors.

Related papers

• VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios [7.9567869558684094]
  VQ-Touch is a tactile generation framework that supports both cross-sensor and multi-scenario applications.<n>To efficiently extract complex deformation and texture features from the data, we propose DM-VQGAN.<n>We introduce a discrete diffusion decoder with a unified conditioning interface, supporting multimodal generation tasks such as images and labels.
  arXiv  Detail & Related papers  (2026-07-16T08:53:41Z)
• Heterogeneous Tactile Transformer [12.676986440348543]
  Heterogeneous Tactile Transformer (HTT) is a framework that learns shared tactile representations across heterogeneous sensors.<n>Pretraining uses our novel Heterogeneous Paired Tactile dataset, containing 1.6M synchronized frames across four vision- and array-based tactile sensors.<n> HTT is shown to learn transferable representations that adapt to new tasks and previously unseen sensors.
  arXiv  Detail & Related papers  (2026-06-29T08:24:38Z)
• Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms [70.51538670020267]
  We propose a hierarchical taxonomy that organizes the field into two primary dimensions: multimodal datasets and multimodal methods.<n>On the data side, we categorize resources ranging from Tactile-Vision datasets, Tactile-Language datasets, Tactile-Vision-Language datasets, and Tactile-Vision-Other datasets.<n>On the method side, we structure prior work into three core pillars: (1) Multimodal Perception and Recognition, (2) Cross-Modal Generation, focusing on bidirectional translation between tactile, vision, and text, and (3) Multimodal Interaction, emphasizing feedback control and language-guided manipulation.
  arXiv  Detail & Related papers  (2026-05-17T09:09:30Z)
• Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation [82.63833405368159]
  Generalizing tool manipulation requires both semantic planning and precise physical control.<n>We propose Semantic-Contact Fields (SCFields), a unified 3D representation fusing visual semantics with dense contact estimates.<n> Experiments on scraping, crayon drawing, and peeling demonstrate robust category-level generalization.
  arXiv  Detail & Related papers  (2026-02-14T16:05:08Z)
• UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors [51.88112610411651]
  We propose a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors.<n>UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image)<n>To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions.
  arXiv  Detail & Related papers  (2026-02-01T11:03:01Z)
• Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities [19.45726946555448]
  Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties.<n>Existing methods fail to fully integrate the intermediate communication among tactile, language, and vision modalities.<n>We propose TLV-CoRe, a CLIP-based Tactile-Language-Vision Collaborative Representation learning method.
  arXiv  Detail & Related papers  (2025-11-14T17:34:20Z)
• AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors [11.506370451126378]
  Visuo-tactile sensors aim to emulate human tactile perception, enabling robots to understand and manipulate objects.<n>We introduce TacQuad, an aligned multi-modal tactile multi-sensor dataset from four different visuo-tactile sensors.<n>We propose AnyTouch, a unified static-dynamic multi-sensor representation learning framework with a multi-level structure.
  arXiv  Detail & Related papers  (2025-02-15T08:33:25Z)
• Elastic Tactile Simulation Towards Tactile-Visual Perception [58.44106915440858]
  We propose Elastic Interaction of Particles (EIP) for tactile simulation. EIP models the tactile sensor as a group of coordinated particles, and the elastic property is applied to regulate the deformation of particles during contact. We further propose a tactile-visual perception network that enables information fusion between tactile data and visual images.
  arXiv  Detail & Related papers  (2021-08-11T03:49:59Z)
• Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition [131.6328804788164]
  We propose a framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) The SAKDN uses multiple wearable-sensors as teacher modalities and uses RGB videos as student modality.
  arXiv  Detail & Related papers  (2020-09-01T03:38:31Z)
• OmniTact: A Multi-Directional High Resolution Touch Sensor [109.28703530853542]
  Existing tactile sensors are either flat, have small sensitive fields or only provide low-resolution signals. We introduce OmniTact, a multi-directional high-resolution tactile sensor. We evaluate the capabilities of OmniTact on a challenging robotic control task.
  arXiv  Detail & Related papers  (2020-03-16T01:31:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.