TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction

• URL: http://arxiv.org/abs/2607.28391v1
• Date: Thu, 30 Jul 2026 15:47:01 GMT
• Title: TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction
• Abstract summary: World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures.<n>We present TacWAM, a mechanics-aware tactile WAM that addresses this challenge in three steps.<n>We evaluate TacWAM on four real-world contact-rich manipulation tasks covering fragile grasping, sustained surface contact, and dynamic in-hand manipulation.
• Score: 15.274487606802124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual prediction captures scene structure and object motion, yet provides limited supervision for force, deformation, shear, and slip during contact-rich manipulation. This creates two design requirements: tactile futures should carry meaningful physical information, and they should not become privileged cues for action generation. We present TacWAM, a mechanics-aware tactile WAM that addresses this challenge in three steps. First, a Spatially Aligned Fusion (SAF) Tactile Encoder maps tactile appearance, dense force fields, and deformation flow into a shared latent prediction space, with bilateral force and torque reconstruction preserving global contact information. Second, a tactile history encoder provides temporal context so future tactile prediction reflects how force and deformation change beyond the current tactile observation. Third, Anchor-Guided Tri-Modal (AGT) Attention separates current visual and tactile anchors, future prediction tokens, and action tokens, allowing future tactile states to supervise training without being directly read by the action branch. We evaluate TacWAM on four real-world contact-rich manipulation tasks covering fragile grasping, sustained surface contact, and dynamic in-hand manipulation. TacWAM achieves an average success rate of 75.0%, exceeding the strongest evaluated baseline by 37.5 percentage points. Staged ablations show consistent degradation when tactile history is removed and access to future prediction targets is relaxed. These results indicate that future tactile supervision can improve contact-aware action learning when combined with informative tactile representations and deployment-consistent information constraints.

Related papers

• Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models [4.240284950848863]
  Oracle Visuo-Tactile Foresight (OVTF) supplies paired RGB and tactile futures from successful trajectories verified in simulation.<n>Within OVTF, we propose Asymmetric Phase-Local Future Memory (AFM), in which visual memory reads future vision.<n>We compare AFM with Modality-Isolated Future Memory (IFM), which removes visual-to-tactile access and processes each future modality independently.
  arXiv  Detail & Related papers  (2026-08-01T09:04:43Z)
• τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision [43.426795127841075]
  We present, a touch-augmented Vision-Language-Action (VLA) framework that learns an action-conditioned tactile representation from future visual supervision.<n>We also introduce TacAura, a dataset of synchronized vision, proprioception, and vision-based tactile signals across four representative contact-rich manipulation tasks.
  arXiv  Detail & Related papers  (2026-07-27T14:25:15Z)
• VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation [22.0330577788623]
  Contact-rich manipulation requires policies to react to local deformation, pressure, slip, and friction.<n>Existing visual-tactile policies usually feed tactile observations directly into action prediction.<n>We introduce VT-WAM, a Visual-Tactile World Action Model that jointly learns future visual prediction, tactile deformation prediction, and action prediction.
  arXiv  Detail & Related papers  (2026-07-02T17:58:36Z)
• UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models [32.87879913150572]
  We propose a unified tactile learning framework for contact-rich manipulation.<n>We show that our method improves success rate, manipulation accuracy, and contact robustness over existing methods.
  arXiv  Detail & Related papers  (2026-06-30T14:24:00Z)
• Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention [53.84395207661823]
  We propose Tactile-WAM, a touch-aware WAM with a Tactile Asymmetric Attention Mechanism (TAAM)<n>On ManiFeel, Tactile-WAM improves the mean success rate by 38.9% overall and by 86% on contact-rich tasks.
  arXiv  Detail & Related papers  (2026-06-25T06:54:56Z)
• TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation [50.608989079323784]
  We propose TouchThinker, a tactile-language framework that scales tactile commonsense reasoning to the open world from both data and representation perspectives.<n>First, we construct TouchThinker-1M, a million-scale, multi-source tactile reasoning dataset covering textbf415 objects, textbf8 scenarios, and textbf7 sensor types.<n>Then, we propose action-aware modeling mechanism to improve tactile representation efficiency and enable efficient reasoning.
  arXiv  Detail & Related papers  (2026-06-10T03:58:32Z)
• TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation [46.82050380051203]
  Contact-rich manipulation requires robots to continuously regulate and regulate physical dynamic contact transitions or complex surface geometries.<n>Recent imitation learning methods improve contact-aware control by incorporating tactile or force feedback, but they rarely model the asymmetric roles of global force and local tactile sensing.<n>We propose TacForeSight, a lightweight force foresight framework for real-time manipulation.
  arXiv  Detail & Related papers  (2026-06-09T17:59:03Z)
• LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning [51.969318585152116]
  LatentPilot exploits future observations during training as a valuable data source to learn action-conditioned visual dynamics.<n>We propose a flywheel-style training mechanism that iteratively collects on-policy trajectories and retrains the model to better match the agent's behavior distribution.<n> Experiments on R2R-CE, RxR-CE, and R2R-PE benchmarks achieve new SOTA results, and real-robot tests across diverse environments demonstrate LatentPilot's superior understanding of environment-action dynamics in scene.
  arXiv  Detail & Related papers  (2026-03-31T02:21:59Z)
• OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation [57.133721026727706]
  We present textbfOmniViTac, a large-scale visuo-tactile-action dataset comprising $21,000+$ trajectories across $86$ tasks and $100+$ objects.<n>We propose textbf OmniVTA, a world-model-based visuo-tactile manipulation framework that integrates four tightly coupled modules.
  arXiv  Detail & Related papers  (2026-03-19T17:52:42Z)
• TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance [53.35296919674763]
  TouchGuide is a novel cross-policy visuo-tactile fusion paradigm that fuses modalities within a low-dimensional action space.<n>touchGuide operates in two stages to guide a pre-trained diffusion or flow-matching visuomotor policy.<n>To facilitate TouchGuide training with high-quality and cost-effective data, we introduce TacUMI, a data collection system.
  arXiv  Detail & Related papers  (2026-01-28T04:22:47Z)

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.