Coordinated Humanoid Manipulation with Choice Policies

• URL: http://arxiv.org/abs/2512.25072v1
• Date: Wed, 31 Dec 2025 18:59:53 GMT
• Title: Coordinated Humanoid Manipulation with Choice Policies
• Abstract summary: We present a system that combines a modular teleoperation interface with a scalable learning framework.<n>Choice Policy is an imitation learning approach that generates multiple candidate actions and learns to score them.<n>We validate our approach on two real-world tasks: loading dishwasher and whole-body loco-manipulation for whiteboard wiping.
• Score: 43.635012621027904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humanoid robots hold great promise for operating in human-centric environments, yet achieving robust whole-body coordination across the head, hands, and legs remains a major challenge. We present a system that combines a modular teleoperation interface with a scalable learning framework to address this problem. Our teleoperation design decomposes humanoid control into intuitive submodules, which include hand-eye coordination, grasp primitives, arm end-effector tracking, and locomotion. This modularity allows us to collect high-quality demonstrations efficiently. Building on this, we introduce Choice Policy, an imitation learning approach that generates multiple candidate actions and learns to score them. This architecture enables both fast inference and effective modeling of multimodal behaviors. We validate our approach on two real-world tasks: dishwasher loading and whole-body loco-manipulation for whiteboard wiping. Experiments show that Choice Policy significantly outperforms diffusion policies and standard behavior cloning. Furthermore, our results indicate that hand-eye coordination is critical for success in long-horizon tasks. Our work demonstrates a practical path toward scalable data collection and learning for coordinated humanoid manipulation in unstructured environments.

Related papers

• HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning [52.022681285103126]
  We present HumanoidMimicGen, a method for generating humanoid legged loco-manipulation data.<n>Our method adapts contact-rich whole-body skills from a handful of source demonstrations to new states.<n>We show that whole-body visuomotor policies co-trained with data generated by HumanoidMimicGen outperform those trained only on real-world data by 20%.
  arXiv  Detail & Related papers  (2026-05-26T21:57:11Z)
• Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warping [44.348686148716894]
  We introduce Tether, a method for autonomous functional play involving structured, task-directed interactions.<n>First, we design a novel open-loop policy that warps actions from a small set of source demonstrations.<n>Second, we deploy this policy for autonomous functional play in the real world via a continuous cycle of task selection, execution, evaluation, and improvement.
  arXiv  Detail & Related papers  (2026-03-03T18:59:07Z)
• Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration [58.4036440289082]
  Hand-object motion-capture (MoCap) offer large-scale, contact-rich demonstrations and hold promise for dexterous robotic scopes.<n>We introduce Dexplore, a unified single-loop optimization that performs repositories and tracking to learn robot control policies directly from MoCap at scale.
  arXiv  Detail & Related papers  (2025-09-11T17:59:07Z)
• Towards Human-level Intelligence via Human-like Whole-Body Manipulation [10.199110135230674]
  We present Astribot Suite, a robot learning suite for whole-body manipulation aimed at general daily tasks across diverse environments.<n>Our results show that Astribot's cohesive integration of embodiment, teleoperation interface, and learning pipeline marks a significant step towards real-world, general-purpose whole-body robotic manipulation.
  arXiv  Detail & Related papers  (2025-07-23T02:23:41Z)
• SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending [79.83865372778273]
  We introduce SkillBlender, a novel hierarchical reinforcement learning framework for versatile humanoid loco-manipulation.<n>SkillBlender first pretrains goal-conditioned task-agnostic primitive skills, and then dynamically blends these skills to accomplish complex loco-manipulation tasks.<n>We also introduce SkillBench, a parallel, cross-embodiment, and diverse simulated benchmark containing three embodiments, four primitive skills, and eight challenging loco-manipulation tasks.
  arXiv  Detail & Related papers  (2025-06-11T03:24:26Z)
• Dexterous Manipulation through Imitation Learning: A Survey [32.47862766672596]
  Imitation learning (IL) offers an alternative by allowing robots to acquire dexterous manipulation skills directly from expert demonstrations.<n>IL captures fine-grained coordination and contact dynamics while bypassing the need for explicit modeling and large-scale trial-and-error.<n>Our goal is to offer researchers and practitioners a comprehensive introduction to this rapidly evolving domain.
  arXiv  Detail & Related papers  (2025-04-04T15:14:38Z)
• Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models [22.826115023573205]
  We infuse the predictive nature of human manipulation strategies into robot imitation learning.<n>We train a diffusion model to predict future states and compute robot actions that achieve the predicted states.<n>Our framework consistently outperforms state-of-the-art state-to-action mapping policies.
  arXiv  Detail & Related papers  (2025-03-30T01:25:35Z)
• Dreamitate: Real-World Visuomotor Policy Learning via Video Generation [49.03287909942888]
  We propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. We generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot.
  arXiv  Detail & Related papers  (2024-06-24T17:59:45Z)
• Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance [71.36749876465618]
  We describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples. experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world.
  arXiv  Detail & Related papers  (2022-12-19T22:50:40Z)
• Learning Multi-Arm Manipulation Through Collaborative Teleoperation [63.35924708783826]
  Imitation Learning (IL) is a powerful paradigm to teach robots to perform manipulation tasks. Many real-world tasks require multiple arms, such as lifting a heavy object or assembling a desk. We present Multi-Arm RoboTurk (MART), a multi-user data collection platform that allows multiple remote users to simultaneously teleoperate a set of robotic arms.
  arXiv  Detail & Related papers  (2020-12-12T05:43:43Z)
• Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning [14.315501760755609]
  Training agents to autonomously learn how to use anthropomorphic robotic hands has the potential to lead to systems capable of performing a multitude of complex manipulation tasks. We first introduce a suite of challenging simulated manipulation tasks that current reinforcement learning and trajectory optimisation techniques find difficult. We then introduce a simple trajectory optimisation that performs significantly better than existing methods on these environments.
  arXiv  Detail & Related papers  (2020-09-09T13:49:52Z)

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.