HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

• URL: http://arxiv.org/abs/2603.03243v1
• Date: Tue, 03 Mar 2026 18:36:49 GMT
• Title: HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
• Abstract summary: Whole-Body Mobile Manipulation Interface (HoMMI) learns whole-body mobile manipulation directly from robot-free human demonstrations.<n>We augment UMI interfaces with egocentric sensing to capture the global context required for mobile manipulation.<n>We explicitly bridge this gap with a cross-embodiment hand-eye policy design.
• Score: 15.551927664158695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulation directly from robot-free human demonstrations. We augment UMI interfaces with egocentric sensing to capture the global context required for mobile manipulation, enabling portable, robot-free, and scalable data collection. However, naively incorporating egocentric sensing introduces a larger human-to-robot embodiment gap in both observation and action spaces, making policy transfer difficult. We explicitly bridge this gap with a cross-embodiment hand-eye policy design, including an embodiment agnostic visual representation; a relaxed head action representation; and a whole-body controller that realizes hand-eye trajectories through coordinated whole-body motion under robot-specific physical constraints. Together, these enable long-horizon mobile manipulation tasks requiring bimanual and whole-body coordination, navigation, and active perception. Results are best viewed on: https://hommi-robot.github.io

Related papers

• AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning [25.241504281004243]
  We present AdvDex, a framework for learning dexterous manipulation from human and robot demonstrations.<n>First, we introduce OmniShare, a large-scale multimodal dataset of human manipulation demonstrations.<n>Second, we propose the Joint-Aligned Action Space (JAAS), a canonical action representation comprising an $mathrmSE(3)$ wrist pose and 15 finger joints.<n>Third, we use domain-adversarial learning to reduce embodiment-specific information in the learned visual representation.
  arXiv  Detail & Related papers  (2026-08-14T07:19:06Z)
• HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation [6.733928872257592]
  We propose HumanoidUMI, a portable and robot-free framework for humanoid whole-body data collection.<n>We use lightweight VR devices and UMI-inspired grippers to collect sparse human keypoint trajectories, wrist-view observations, and gripper actions.<n>Experiments in five real-world scenarios demonstrate the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2026-06-25T16:23:56Z)
• ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration [51.69384671495837]
  ActiveGlasses is a system for learning robot manipulation from ego-centric human demonstrations with active vision.<n>A stereo camera mounted on smart glasses serves as the sole perception device for both data collection and policy inference.<n>To enable zero-transfer, we extract object trajectories from demonstrations and use an object-centric point-cloud policy to jointly predict manipulation and head movement.
  arXiv  Detail & Related papers  (2026-04-09T17:59:08Z)
• ZeroWBC: Learning Natural Visuomotor Humanoid Control Directly from Human Egocentric Video [52.78703020909145]
  We introduce ZeroWBC, a novel framework that learns a natural humanoid visuomotor control policy directly from human egocentric videos.<n>Our approach first fine-tunes a Vision-Language Model (VLM) to predict future whole-body human motions based on text instructions and egocentric visual context.<n>Experiments on the Unitree G1 humanoid robot demonstrate that our method outperforms baseline approaches in motion naturalness and versatility.
  arXiv  Detail & Related papers  (2026-03-10T04:19:43Z)
• EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration [67.13034606664333]
  EgoHumanoid is the first framework to co-train a vision-language-action policy using egocentric human demonstrations.<n>A portable system for scalable human data collection is developed.
  arXiv  Detail & Related papers  (2026-02-10T18:59:03Z)
• Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations [25.15848825594207]
  We present the Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse whole-body manipulation tasks.<n>HuMI enables robot-free data collection by capturing rich whole-body motion using portable hardware.<n>HuMI achieves a 3x increase in data collection efficiency compared to teleoperation and attains a 70% success rate in unseen environments.
  arXiv  Detail & Related papers  (2026-02-06T12:10:47Z)
• Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations [52.29884993824894]
  Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community.<n>AINA enables learning multi-fingered policies from data collected by anyone, anywhere, and in any environment using Aria Gen 2 glasses.
  arXiv  Detail & Related papers  (2025-11-20T18:59:02Z)
• TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System [79.48781507497769]
  Existing humanoid teleoperation systems either use decoupled control or depend on expensive motion capture setups.<n>We introduce TWIST2, a portable, mocap-free humanoid teleoperation and data collection system.<n>We demonstrate long-horizon dexterous and mobile humanoid skills and we can collect 100 demonstrations in 15 minutes with an almost 100% success rate.
  arXiv  Detail & Related papers  (2025-11-04T18:58:35Z)
• TWIST: Teleoperated Whole-Body Imitation System [28.597388162969057]
  We present the Teleoperated Whole-Body Imitation System (TWIST), a system for humanoid teleoperation through whole-body motion imitation.<n>We develop a robust, adaptive, and responsive whole-body controller using a combination of reinforcement learning and behavior cloning.<n>TWIST enables real-world humanoid robots to achieve unprecedented, versatile, and coordinated whole-body motor skills.
  arXiv  Detail & Related papers  (2025-05-05T17:59:03Z)
• Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost [8.71539730969424]
  MoMa-Teleop is a novel teleoperation method that infers end-effector motions from existing interfaces.<n>We demonstrate that our approach results in a significant reduction in task completion time across a variety of robots and tasks.
  arXiv  Detail & Related papers  (2024-09-23T15:09:45Z)
• Visual Whole-Body Control for Legged Loco-Manipulation [22.50054654508986]
  We study the problem of mobile manipulation using legged robots equipped with an arm. We propose a framework that can conduct the whole-body control autonomously with visual observations.
  arXiv  Detail & Related papers  (2024-03-25T17:26:08Z)
• Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations [66.47064743686953]
  Eye-in-hand cameras have shown promise in enabling greater sample efficiency and generalization in vision-based robotic manipulation. Videos of humans performing tasks, on the other hand, are much cheaper to collect since they eliminate the need for expertise in robotic teleoperation. In this work, we augment narrow robotic imitation datasets with broad unlabeled human video demonstrations to greatly enhance the generalization of eye-in-hand visuomotor policies.
  arXiv  Detail & Related papers  (2023-07-12T07:04:53Z)
• Open-World Object Manipulation using Pre-trained Vision-Language Models [72.87306011500084]
  For robots to follow instructions from people, they must be able to connect the rich semantic information in human vocabulary. We develop a simple approach, which leverages a pre-trained vision-language model to extract object-identifying information. In a variety of experiments on a real mobile manipulator, we find that MOO generalizes zero-shot to a wide range of novel object categories and environments.
  arXiv  Detail & Related papers  (2023-03-02T01:55:10Z)

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.