HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers

• URL: http://arxiv.org/abs/2606.06493v3
• Date: Tue, 09 Jun 2026 07:34:32 GMT
• Title: HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
• Abstract summary: HANDOFF is a humanoid whole-body controller that is intuitive, general, modular, and expressive for diverse loco-manipulation skills.<n>On the Unitree G1, HANDOFF matches state-of-the-art velocity tracking and offers one of the largest robust workspaces manipulation.
• Score: 6.1409946459609275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For a humanoid robot to be deployed in the real world, the choice of command space (i.e., the interface between task planning and whole-body control) is crucial. Existing whole-body controllers typically demand dense kinematic or spatial references that planners struggle to synthesize from task semantics. We instead propose a compact, explicit interface that is intuitive, general, modular, and expressive enough for diverse loco-manipulation skills. To this end, we introduce HANDOFF, a single humanoid whole-body controller that follows this interface and is distilled via multi-teacher KL distillation under a context-conditioned gating scheme into a mixture-of-experts student from three complementary specialists: whole-body motion tracking with safety-filtered data, locomotion, and fall-recovery. On the Unitree G1, HANDOFF matches state-of-the-art velocity tracking and offers one of the largest robust manipulation workspaces. We further demonstrate hardware feasibility through multiple natural-language-driven task roll-outs, powered by a VLM-driven agentic planner with no task-specific data or controller fine-tuning.

Related papers

• Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks [5.936743269468451]
  HYPER-GNC is a multi-task reinforcement learning framework for autonomous free-flying robots.<n>It maps physics-informed task embeddings to the weights of a shared actor-critic policy.<n>Experiments demonstrate that HYPER-GNC achieves sample efficiency comparable to single-task specialists.
  arXiv  Detail & Related papers  (2026-07-27T11:39:22Z)
• VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands [56.029505206531155]
  Vision Guided Agile Interaction Control (VAIC) is a unified framework that bridges the gap between current controllers and humanoid robots.<n>First, a privileged teacher policy masters diverse interaction skills using precise object kinematics and exact environmental states.<n>Second, a deployable student policy distills these capabilities by replacing full body tracking with velocity targets across multiple axes.
  arXiv  Detail & Related papers  (2026-06-08T09:52:55Z)
• CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation [11.545606851036787]
  We propose a compliant end-effector-root (EE-root) control abstraction for modular humanoid loco-manipulation.<n>EE-root provides a practical abstraction for humanoid loco-manipulation, enabling modular and scalable integration of diverse skills.
  arXiv  Detail & Related papers  (2026-05-19T15:23:40Z)
• CLAW: Composable Language-Annotated Whole-body Motion Generation [55.99805728566105]
  We present CLAW, a pipeline for scalable generation of language-annotated whole-body motion data.<n>CLAW composes motion primitives from a kinematic planner, parameterized by movement, heading, speed, pelvis height, and duration.<n>A low-level controller tracks these references in MuJoCo simulation, yielding physically grounded trajectories.
  arXiv  Detail & Related papers  (2026-04-13T10:02:04Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• PILOT: A Perceptive Integrated Low-level Controller for Loco-manipulation over Unstructured Scenes [18.916978556216097]
  PILOT is a single-stage reinforcement learning framework tailored for perceptive loco-manipulation.<n>It synergizes perceptive locomotion and expansive whole-body control within a single policy.<n> PILOT demonstrates superior stability, command tracking precision, and terrain traversability compared to existing baselines.
  arXiv  Detail & Related papers  (2026-01-24T12:25:20Z)
• CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation [70.5382178207975]
  hIsight Perturbation (CHIP) is a plug-and-play module that enables controllable end-effector stiffness.<n>CHIP is easy to implement and requires neither data augmentation nor additional reward tuning.<n>We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-16T18:56:04Z)
• HumanoidVerse: A Versatile Humanoid for Vision-Language Guided Multi-Object Rearrangement [51.16740261131198]
  We introduce HumanoidVerse, a novel framework for vision-language guided humanoid control.<n>HumanoidVerse supports consecutive manipulation of multiple objects, guided only by natural language instructions and egocentric camera RGB observations.<n>Our work represents a key step toward robust, general-purpose humanoid agents capable of executing complex, sequential tasks under real-world sensory constraints.
  arXiv  Detail & Related papers  (2025-08-23T08:23:14Z)
• HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception [57.37135310143126]
  HO SIG is a novel framework for synthesizing full-body interactions through hierarchical scene perception.<n>Our framework supports unlimited motion length through autoregressive generation and requires minimal manual intervention.<n>This work bridges the critical gap between scene-aware navigation and dexterous object manipulation.
  arXiv  Detail & Related papers  (2025-06-02T12:08:08Z)
• 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)
• DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control [53.80518003412016]
  Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research. We study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls.
  arXiv  Detail & Related papers  (2024-07-20T05:39:28Z)

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.