GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction

• URL: http://arxiv.org/abs/2608.18234v2
• Date: Sun, 23 Aug 2026 09:07:15 GMT
• Title: GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction
• Abstract summary: We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control.<n>Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command.<n>An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets.
• Score: 68.67772166423812
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent, while the low-level policy keeps the robot balanced and physically feasible. Existing trackers deliver this interface only on flat ground: trained in empty scenes, they never learn how contact with terrain and objects reshapes their dynamics, and they attempt to teach the policy to balance under any command by continually enlarging the reference-motion corpus, which stops working once feasible behaviors become environment-dependent. We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control. Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command, so the network that acts also models how the environment shapes what it can do next. An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets. The predicted distribution is reused at deployment to detect implausible commands online and retract them onto learned behaviors, so the robot attempts tasks in a "best-effort" manner. The result is a unified policy that takes real-time command, interacts with environment, and stays robust to implausible commands, falls, and disturbances. GigaBrain-WBC-0.5 achieves the highest success rate across all four regimes among three large-scale tracker baselines: 81.3% on terrain interaction (4.3x the strongest baseline), 83.1% under implausible commands, and 99.3% fall recovery (16.8x the strongest baseline). Hardware trials show robust interaction under missing supports and disturbances; the Unitree G1 checkpoint transfers to the Maker L01 robot with simple fine-tuning.

Related papers

• WLA$^3$: World Latent Action Modeling for Semantics, Dynamics, and Kinematics [33.75014442121971]
  We introduce WLA$3$ (World Latent Action Modeling for Semantics, Dynamics, and Kinematics), a unified generalist policy model framework.<n> WLA$3$ reuses representations learned by a World Latent Action Model (WLAM) across semantics, dynamics, and kinematics.<n>On LARYBench, the final 32D latent action reaches 67.89% average classification accuracy.
  arXiv  Detail & Related papers  (2026-09-14T16:59:00Z)
• Morphology-Aware Human Motion Retargeting for Wheeled-Humanoid Loco-Manipulation [3.1041072702135213]
  We present a pipeline that converts multi-dataset motion into executable loco-manipulation behavior for the Galaxea R1 wheeled humanoid.<n>The robot has a planar three-wheel base, a serial torso, and two arms but no leg joints.<n>A reference-twist-driven planning layer then decodes planar base motion into continuous three-wheel steering and rolling commands.
  arXiv  Detail & Related papers  (2026-09-10T10:40:31Z)
• Hydra-0: Action Flow for Generalist World Modeling and Control [64.88849745875753]
  Hydra-0 is a world model conditioned on action flow, which represents robot actions as pixel motion.<n>Our best configuration achieves 90.4% lower robot-motion error and 60.2% lower object-motion error.<n>A trained action head maps the resulting latent features to executable actions without requiring task-specific expert robot demonstrations.
  arXiv  Detail & Related papers  (2026-08-18T17:59:30Z)
• Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report [25.18747802029395]
  We present ABot-C0, a generalist motion-control system for quadruped robots.<n>We construct a data pyramid through conditional video-generation, annotated motion capture, and human design, producing 16,074 physically feasible motion clips.<n>We then go a step further toward robust all-terrain locomotion by adopting a three-stage privileged-to-perceptive framework.
  arXiv  Detail & Related papers  (2026-07-08T13:04:07Z)
• Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors [51.096845970243855]
  Whole-body Humanoid-Object Interaction (HOI) is bottlenecked by the scarcity of high-fidelity 3D data.<n>We propose Imagine2Real, a zero-shot HOI framework for flexible, geometry-free interaction.
  arXiv  Detail & Related papers  (2026-05-21T10:15:39Z)
• ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control [8.983091538704645]
  We present ECHO, an edge-hosted framework for language-driven whole-body control of humanoid robots.<n>A cloud-native diffusion-based text-to-motion generator synthesizes motion references from natural language instructions.<n>An edge-deployed reinforcement-learning tracker executes them in closed loop on the robot.
  arXiv  Detail & Related papers  (2026-03-17T07:16:18Z)
• HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model [56.4392302336014]
  We present HAIC, a framework for robust interaction across diverse object dynamics without external state estimation.<n>Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history.<n> Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks.
  arXiv  Detail & Related papers  (2026-02-12T09:34:35Z)
• Learning Humanoid Standing-up Control across Diverse Postures [27.79222176982376]
  Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems.<n>We present HoST (Humanoid Standing-up Control), a reinforcement learning framework that learns standing-up control from scratch.<n>Our experimental results demonstrate that the controllers achieve smooth, stable, and robust standing-up motions across a wide range of laboratory and outdoor environments.
  arXiv  Detail & Related papers  (2025-02-12T13:10:09Z)
• NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning [67.53972459080437]
  Navigating a nonholonomic robot in a cluttered, unknown environment requires accurate perception and precise motion for real-time collision avoidance.<n>This paper presents NeuPAN: a real-time, highly accurate, map-free, easy-to-deploy, and environment-invariant robot motion planner.
  arXiv  Detail & Related papers  (2024-03-11T15:44:38Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)

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.