ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation

• URL: http://arxiv.org/abs/2609.16586v1
• Date: Tue, 15 Sep 2026 03:31:55 GMT
• Title: ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation
• Abstract summary: ProxiDex is a dynamics-guided proximity policy framework for dexterous manipulation.<n>It reconstructs interaction point clouds and converts geometric distances into proximity cues, forming a hardware-agnostic contact representation.<n>ProxiDex adaptively reweights proximity tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference.
• Score: 9.170854062817556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and existing policies rarely model how these cues evolve under actions, making them brittle under contact uncertainty. To address these, we present ProxiDex, a dynamics-guided proximity policy framework that treats hand-object proximity as an interaction state for dexterous manipulation. ProxiDex reconstructs interaction point clouds and converts geometric distances into proximity cues, forming a hardware-agnostic contact representation that provides immersive feedback during VR teleoperation. Built on this representation, ProxiDex learns action-conditioned proximity dynamics with a coupled forward-inverse design: future observation latents are predicted from actions, while proximity variations are decoded from latent changes. Leveraging these dynamics, ProxiDex adaptively reweights proximity tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference, stabilizing action generation under unreliable visual feedback. Simulation and real-world experiments demonstrate improved success rates and robustness over representative baselines across standard, unseen objects, and perturbation scenarios. Additional visualizations are available at https://proxidex.github.io/.

Related papers

• Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands [99.00248904465089]
  Dexterous hands differ in finger structure, contact surfaces, and sensor layouts.<n>We present Bench2Dex, a simulation benchmark for visuo-tactile bimanual manipulation across 12 dexterous hands.
  arXiv  Detail & Related papers  (2026-09-14T15:22:59Z)
• C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video [47.458936125974226]
  C2Dex is a video-to-dexterous-manipulation framework built around a shared interaction.<n> stable object-side contacts recovered by noisy frame-wise observations in the canonical object space.<n>C2Dex achieves end-to-end trajectory success rates of 57.78% and 26.67%.
  arXiv  Detail & Related papers  (2026-08-07T09:54:00Z)
• AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion [60.79507611737292]
  Humans achieve stable and adaptive grasps by seamlessly integrating visual perception and tactile feedback.<n>Existing robotic grasping approaches rely on visual inputs and lack mechanisms for tactile-guided adaptation after contact.<n>We propose a unified visuo-tactile-fusion grasping framework that integrates grasp generation, feasibility prediction, and adaptive refinement.
  arXiv  Detail & Related papers  (2026-08-06T16:29:11Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance [49.69016078147708]
  Accurately reconstructing human behavior in close-interaction scenarios is crucial for enabling realistic virtual interactions in augmented reality.<n>We propose SocialMirror, a diffusion-based framework that integrates semantic and geometric cues to effectively address these issues.<n>SocialMirror achieves state-of-the-art performance in reconstructing interactive human meshes, demonstrating strong generalization across unseen datasets and in-the-wild scenarios.
  arXiv  Detail & Related papers  (2026-04-15T07:41:52Z)
• Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning [27.1809716948267]
  We introduce a framework that can facilitate policy learning with a learned representation of contact-induced object dynamics in cluttered environments.<n>Our method outperforms prehensile manipulation, human teleoperation, and prior representation-based policies by over 25% in success rate.
  arXiv  Detail & Related papers  (2026-03-10T16:40:30Z)
• Toward Operationalizing Rasmussen: Drift Observability on the Simplex for Evolving Systems [0.0]
  Monitoring drift into failure is hindered by Euclidean anomaly detection.<n>Rasmussen's dynamic safety model motivates drift under competing pressures.<n>We propose a vision for drift observability on the simplex.
  arXiv  Detail & Related papers  (2026-02-05T09:41:49Z)
• Precise Action-to-Video Generation Through Visual Action Prompts [62.951609704196485]
  Action-driven video generation faces a precision-generality trade-off.<n>Agent-centric action signals provide precision at the cost of cross-domain transferability.<n>We "render" actions into precise visual prompts as domain-agnostic representations.
  arXiv  Detail & Related papers  (2025-08-18T17:12:28Z)
• Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper [7.618517580705364]
  We present a portable, lightweight gripper with integrated tactile sensors.<n>We propose a cross-modal representation learning framework that integrates visual and tactile signals.<n>We validate our approach on fine-grained tasks such as test tube insertion and pipette-based fluid transfer.
  arXiv  Detail & Related papers  (2025-07-20T17:53:59Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)

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.