Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning

• URL: http://arxiv.org/abs/2603.09882v1
• Date: Tue, 10 Mar 2026 16:40:30 GMT
• Title: Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning
• Abstract summary: 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.
• Score: 27.1809716948267
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Extrinsic dexterity leverages environmental contact to overcome the limitations of prehensile manipulation. However, achieving such dexterity in cluttered scenes remains challenging and underexplored, as it requires selectively exploiting contact among multiple interacting objects with inherently coupled dynamics. Existing approaches lack explicit modeling of such complex dynamics and therefore fall short in non-prehensile manipulation in cluttered environments, which in turn limits their practical applicability in real-world environments. In this paper, we introduce a Dynamics-Aware Policy Learning (DAPL) framework that can facilitate policy learning with a learned representation of contact-induced object dynamics in cluttered environments. This representation is learned through explicit world modeling and used to condition reinforcement learning, enabling extrinsic dexterity to emerge without hand-crafted contact heuristics or complex reward shaping. We evaluate our approach in both simulation and the real world. Our method outperforms prehensile manipulation, human teleoperation, and prior representation-based policies by over 25% in success rate on unseen simulated cluttered scenes with varying densities. The real-world success rate reaches around 50% across 10 cluttered scenes, while a practical grocery deployment further demonstrates robust sim-to-real transfer and applicability.

Related papers

• GIRAF: Towards Generalizable Human Interactions with Articulated Objects [50.52795413484619]
  We present a text-conditioned diffusion model that addresses the challenge of Synthesizing realistic full-body human interactions with articulated objects.<n>Our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-08T19:30:44Z)
• 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)
• PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System [67.2851799763138]
  PhysHSI comprises a simulation training pipeline and a real-world deployment system.<n>In simulation, we adopt adversarial motion prior-based policy learning to imitate natural humanoid-scene interaction data.<n>For real-world deployment, we introduce a coarse-to-fine object localization module that combines LiDAR and camera inputs.
  arXiv  Detail & Related papers  (2025-10-13T07:11:37Z)
• Deformable Cluster Manipulation via Whole-Arm Policy Learning [27.54191389134963]
  We propose a novel framework for learning model-free policies integrating two modalities: 3D point clouds and proprioceptive touch indicators.<n>Our reinforcement learning framework leverages a distributional state representation, aided by kernel mean embeddings, to achieve improved training efficiency and real-time inference.<n>We deploy the framework in a power line clearance scenario and observe that the agent generates creative strategies leveraging multiple arm links for de-occlusion.
  arXiv  Detail & Related papers  (2025-07-22T23:58:30Z)
• Robust Visual Localization via Semantic-Guided Multi-Scale Transformer [3.3106947066548167]
  We propose a framework that combines multi-scale feature learning with semantic scene understanding.<n>Our approach employs a hierarchical Transformer with cross-scale attention to fuse geometric details and contextual cues, preserving spatial precision while adapting to environmental changes.
  arXiv  Detail & Related papers  (2025-06-10T07:44:53Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• Zero-Shot Visual Generalization in Robot Manipulation [0.13280779791485384]
  Current approaches often sidestep the problem by relying on invariant representations such as point clouds and depth.<n>Disentangled representation learning has recently shown promise in enabling vision-based reinforcement learning policies to be robust to visual distribution shifts.<n>We demonstrate zero-shot adaptability to visual perturbations in both simulation and on real hardware.
  arXiv  Detail & Related papers  (2025-05-16T22:01:46Z)
• Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids [56.892520712892804]
  We introduce a practical sim-to-real RL recipe that trains a humanoid robot to perform three dexterous manipulation tasks.<n>We demonstrate high success rates on unseen objects and robust, adaptive policy behaviors.
  arXiv  Detail & Related papers  (2025-02-27T18:59:52Z)
• Twisting Lids Off with Two Hands [82.21668778600414]
  We show how policies trained in simulation can be effectively and efficiently transferred to the real world. Specifically, we consider the problem of twisting lids of various bottle-like objects with two hands. This is the first sim-to-real RL system that enables such capabilities on bimanual multi-fingered hands.
  arXiv  Detail & Related papers  (2024-03-04T18:59:30Z)
• Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments [66.83839051693695]
  Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. We propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially life-long dynamic scenes with photo-realistic appearance. A novel element of this paper is that scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives.
  arXiv  Detail & Related papers  (2021-09-16T10:37:21Z)
• Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models [7.653542219337937]
  We present a framework for learning composite dynamical behaviors from expert demonstrations. We learn a switching linear dynamical model with contacts encoded in switching conditions as a close approximation of our system dynamics. We then use discrete-time LQR as the differentiable policy class for data-efficient learning of control to develop a control strategy.
  arXiv  Detail & Related papers  (2021-03-26T04:40:24Z)
• ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations [4.8986598953553555]
  Our method learns parameterizations of inter-body signed distance and contact-frame Jacobians. Our method can predict realistic impact, non-penetration, and stiction when trained on 60 seconds of real-world data.
  arXiv  Detail & Related papers  (2020-09-23T14:51:08Z)

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.