EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow

• URL: http://arxiv.org/abs/2602.22461v1
• Date: Wed, 25 Feb 2026 22:50:51 GMT
• Title: EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
• Abstract summary: EgoAVFlow learns manipulation and active vision from egocentric videos through a shared 3D flow representation.<n>We show that EgoAVFlow consistently outperforms prior human-demo-based baselines.
• Score: 17.993528705818008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visibility, which human viewpoint imitation often fails to provide due to human-specific priors. We propose EgoAVFlow, which learns manipulation and active vision from egocentric videos through a shared 3D flow representation that supports geometric visibility reasoning and transfers without robot demonstrations. EgoAVFlow uses diffusion models to predict robot actions, future 3D flow, and camera trajectories, and refines viewpoints at test time with reward-maximizing denoising under a visibility-aware reward computed from predicted motion and scene geometry. Real-world experiments under actively changing viewpoints show that EgoAVFlow consistently outperforms prior human-demo-based baselines, demonstrating effective visibility maintenance and robust manipulation without robot demonstrations.

Related papers

• Contrastive Action-Image Pre-training for Visuomotor Control [91.5630572541332]
  We introduce CAIP, a vision encoder that treats human hand poses from large-scale egocentric video as a proxy for end-effector actions.<n>Leveraging 32,041 hours of egocentric human video and only 88 hours of robotic manipulation data, CAIP outperforms state-of-the-art vision encoders.
  arXiv  Detail & Related papers  (2026-06-15T20:00:20Z)
• ActiveMimic: Egocentric Video Pretraining with Active Perception [84.2999803878421]
  Egocentric human video offers a scalable alternative to robot data for pretraining.<n>We present ActiveMimic, a pretraining framework that recovers synchronized camera and wrist trajectories from a single body-worn RGB camera.<n>We show that ActiveMimic consistently surpasses baselines pretrained on human video and matches state-of-the-art models pretrained on robot data.
  arXiv  Detail & Related papers  (2026-06-04T14:01:01Z)
• HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model [13.153130497047043]
  Learning generalizable vision-language-action models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies.<n>We propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos.<n>Experiments on feature visualization, simulation, and realworld manipulation show improved human-robot alignment and downstream policy performance.
  arXiv  Detail & Related papers  (2026-05-29T12:36:30Z)
• Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation [57.28703268044067]
  We propose Cortical Policy, a novel dual-stream view transformer for robotic manipulation.<n>Our framework offers a fresh perspective for robotic manipulation and holds potential for broader application in vision-based robot control.
  arXiv  Detail & Related papers  (2026-03-22T04:18:54Z)
• OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer [84.22494391514066]
  OCRA is a framework for video-based human-to-Robot Action transfer.<n>It learns directly from human demonstration videos to enable robust manipulation.
  arXiv  Detail & Related papers  (2026-03-15T14:31:03Z)
• Mitty: Diffusion-based Human-to-Robot Video Generation [57.494785199352975]
  We present Mitty, a Diffusion Transformer that enables video In-Context Learning for end-to-end Human2Robot video generation.<n>Built on a pretrained video diffusion model, Mitty leverages strong visual-temporal priors to translate human demonstrations into robot-execution videos without action labels or intermediate abstractions.<n> Experiments on Human2Robot and EPIC-Kitchens show that Mitty delivers state-of-the-art results, strong generalization to unseen environments, and new insights for scalable robot learning from human observations.
  arXiv  Detail & Related papers  (2025-12-19T05:52:15Z)
• MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training [40.45924128424013]
  We propose MimicDreamer, a framework that turns low-cost human demonstrations into robot-usable supervision.<n>For visual alignment, we propose H2R Aligner, a video diffusion model that generates high-fidelity robot demonstration videos.<n>For viewpoint stabilization, EgoStabilizer is proposed, which canonicalizes egocentric videos via homography.<n>For action alignment, we map human hand trajectories to the robot frame and apply a constrained inverse kinematics solver.
  arXiv  Detail & Related papers  (2025-09-26T11:05:10Z)
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos [49.820119587446655]
  In this paper, we explore training Vision-Language-Action (VLA) models using egocentric human videos.<n>With a VLA trained on human video that predicts human wrist and hand actions, we can perform Inverse Kinematics and convert the human actions to robot actions.<n>We propose a simulation benchmark called Ego Humanoid Manipulation Benchmark, where we design diverse bimanual manipulation tasks with demonstrations.
  arXiv  Detail & Related papers  (2025-07-16T17:27:44Z)
• Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations [19.28925489415787]
  RIGVid enables robots to perform complex manipulation tasks by imitating AI-generated videos.<n>A video diffusion model generates potential demonstration videos, and a vision-language model automatically filters out results that do not follow the command.<n>A 6D pose tracker then extracts object trajectories from the video, and the trajectories are retargeted to the robot in an embodiment-agnostic fashion.
  arXiv  Detail & Related papers  (2025-07-01T17:39:59Z)
• ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flow [4.2766838326810355]
  We present ViSA-Flow, a framework that learns pre-labeled representation from unsupervised large-scale video data.<n>First, a generative-trained semantic action flow is automatically extracted from large-scale human-object interaction video data.<n>Second, this prior is efficiently adapted to a target robot by fine-tuning on a small set of robot demonstrations processed through the same semantic abstraction pipeline.
  arXiv  Detail & Related papers  (2025-05-02T14:03:06Z)
• VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
  VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos.<n> VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
  arXiv  Detail & Related papers  (2025-03-10T10:04:58Z)

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.