ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching

• URL: http://arxiv.org/abs/2605.11048v1
• Date: Mon, 11 May 2026 13:27:00 GMT
• Title: ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
• Abstract summary: ForceFlow is a force-aware reactive framework built upon flow matching.<n>We show that ForceFlow achieves a 37% success rate improvement over the strong baseline ForceVLA.<n>It also exhibits accurate force signal prediction and superior performance in contact force self-regulation.
• Score: 53.30290192030814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision force feedback and control. Although recent efforts have attempted to integrate force/torque sensing into policies, how to build a simple yet effective framework that achieves robust generalization under multimodal observations remains an open question. In this paper, we propose ForceFlow, a force-aware reactive framework built upon flow matching. For contact-stage policy design, we investigate force signal fusion mechanisms and adopt an asymmetric multimodal fusion architecture that treats force as a global regulatory signal, combined with a joint prediction paradigm that enhances the policy's understanding of instantaneous force and historical information, thereby achieving deep coupling between force and motion. For task-level hierarchical decomposition, we divide manipulation into a vision-dominant approach stage (VLM-based pointing for target localization) and a touch-dominant interaction stage (force-driven contact execution), with a Vision-to-Force (V2F) handover mechanism that explicitly decouples spatial generalization from contact regulation. Experimental results across six real-world contact-rich tasks demonstrate that ForceFlow achieves a 37% success rate improvement over the strong baseline ForceVLA while maintaining significantly lower cost. Moreover, ForceFlow exhibits accurate force signal prediction and demonstrates superior performance in contact force self-regulation and zero-shot out-of-distribution (OOD) generalization.

Related papers

• Beyond Implicit Force: Evaluating Explicit Force-Torque Proxies in Action Chunking with Transformers [27.33711271960601]
  Action Chunking with Transformers (ACT) has shown strong performance in fine-grained manipulation.<n>Many deployments collect demonstrations through leader-follower teleoperation.<n>This paper examines whether ACT's apparent force-awareness depends on this hidden interaction cue.
  arXiv  Detail & Related papers  (2026-07-16T05:16:05Z)
• ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation [75.39847750457626]
  ForceVLA2, an end-to-end vision-language-action framework, equips robots with hybrid force-position control and explicit force awareness.<n>To support learning and evaluation, we construct ForceVLA2-Dataset, containing 1,000 trajectories over 5 contact-rich tasks.<n>Experiments show that ForceVLA2 substantially improves success rates and reliability in contact-rich manipulation.
  arXiv  Detail & Related papers  (2026-03-16T12:03:58Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• Force Policy: Learning Hybrid Force-Position Control Policy under Interaction Frame for Contact-Rich Manipulation [55.969741720077565]
  Contact-rich manipulation demands human-like integration of perception and force feedback.<n>Existing learning-based policies often entangle these roles in a monolithic network.<n>We propose a global-local vision-force policy in which a global policy guides free-space actions using vision, and upon contact, a high-frequency local policy with force feedback estimates the interaction frame and executes hybrid force-position control for stable interaction.
  arXiv  Detail & Related papers  (2026-02-25T16:35:24Z)
• FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation [8.726448573057725]
  We present Force-Distilled VLA, a novel framework that integrates force awareness into contact-rich manipulation.<n>The core of our approach is a Force Distillation Module (FDM), which distills force by mapping a learnable query token.<n>During inference, this distilled force token is injected into the pretrained VLM, enabling force-aware reasoning.
  arXiv  Detail & Related papers  (2026-02-02T14:19:46Z)
• ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning [52.86018040861575]
  We propose a unified end-to-end visual-force diffusion policy that integrates visual planning and reactive force control within a single network.<n>We introduce Structural Slow-Fast Learning, a mechanism utilizing causal attention to simultaneously process asynchronous visual and force tokens.<n>Experiments on contact-rich tasks demonstrate that ImplicitRDP significantly outperforms both vision-only and hierarchical baselines.
  arXiv  Detail & Related papers  (2025-12-11T18:59:46Z)
• ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation [62.58034332427291]
  ForceVLA is a novel end-to-end manipulation framework.<n>It treats external force sensing as a first-class modality within VLA systems.
  arXiv  Detail & Related papers  (2025-05-28T09:24:25Z)
• ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation [0.10995326465245926]
  We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions.<n>We employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization.<n>Our evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-11T05:39:07Z)

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.