A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
hub
Homie: Humanoid loco-manipulation with isomorphic exoskeleton cockpit
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
abstract
Generalizable humanoid loco-manipulation poses significant challenges, requiring coordinated whole-body control and precise, contact-rich object manipulation. To address this, this paper introduces HOMIE, a semi-autonomous teleoperation system that combines a reinforcement learning policy for body control mapped to a pedal, an isomorphic exoskeleton arm for arm control, and motion-sensing gloves for hand control, forming a unified cockpit to freely operate humanoids and establish a data flywheel. The policy incorporates novel designs, including an upper-body pose curriculum, a height-tracking reward, and symmetry utilization. These features enable the system to perform walking and squatting to specific heights while seamlessly adapting to arbitrary upper-body poses. The exoskeleton, by eliminating the reliance on inverse dynamics, delivers faster and more precise arm control. The gloves utilize Hall sensors instead of servos, allowing even compact devices to achieve 15 or more degrees of freedom and freely adapt to any model of dexterous hands. Compared to previous teleoperation systems, HOMIE stands out for its exceptional efficiency, completing tasks in half the time; its expanded working range, allowing users to freely reach high and low areas as well as interact with any objects; and its affordability, with a price of just $500. The system is fully open-source, demos and code can be found in our https://homietele.github.io/.
hub tools
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 25roles
background 1polarities
background 1representative citing papers
A force-aware humanoid benchmark pairs synchronized human motion-force data with simulation-based force replay to evaluate whole-body control policies under realistic physical disturbances.
CWI decouples MoCap data for upper-body manipulation and lower-body locomotion, using dual discriminators and multi-critic training plus distillation to produce a policy that works from hand poses and velocity commands alone.
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
CoorDex distills privileged body and hand motion teachers into proprioceptive latent priors and composes them via shared-context residual RL heads to enable continuous high-DoF dexterous loco-manipulation.
OpenHLM is an empirical recipe yielding a whole-body humanoid VLA model that outperforms GR00T N1.6 and Ψ0 baselines on long-horizon tasks using less than half the demonstration time.
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.
MPC-based retargeting framework enables cross-morphology whole-body teleoperation from a single XR device via dynamic feasibility optimization, state synchronization, and SLAM feedback, with reported gains in simulation and real-world tests.
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple rewards for mocap deployment.
VOFA combines a depth-image visuomotor policy with a force-adaptive whole-body controller to push objects of unknown mass to arbitrary goals on a humanoid.
A weightlessness mechanism enables humanoid robots to dynamically relax joints for stable, contact-rich motions across diverse environments without task-specific tuning.
HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.
Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.
Scaling motion tracking models along size, data volume, and compute produces a foundation model for natural, robust humanoid whole-body control with downstream uses in kinematic planning and vision-language-action models.
WARP is an offline retargeting method using a SEW geometric solver to produce consistent whole-body robot trajectories from human demonstrations for zero-shot mobile manipulation.
HALOMI extends UMI with egocentric sensing and a manifold-constrained controller plus alignment adaptations to learn loco-manipulation on humanoids from human demos, reporting 85% average success on three real-world tasks.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
GRAIL creates over 20,000 synthetic loco-manipulation sequences from known 3D configurations and video priors, then trains policies that achieve 84% pick-up and 90% stair-climbing success on a real Unitree G1 humanoid using only the generated data.
HumanoidMimicGen automatically generates large loco-manipulation datasets from few source demonstrations using whole-body planning, enabling visuomotor policies that outperform real-data-only training by 20% on a new nine-task benchmark.
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
A multi-agent large-model framework (Active Spatial Brain + Generalizable Action Cerebellum) enables spatial-aware humanoid whole-body manipulation without task-specific real-robot data.
HTD, a multimodal transformer policy trained with behavioral cloning and touch dreaming to predict future tactile latents, achieves a 90.9% relative success rate improvement over baselines on five real-world contact-rich humanoid loco-manipulation tasks.
citing papers explorer
-
ContactMimic: Humanoid Object Interaction via Contact Control
A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
-
ThorArena: Benchmarking Humanoid Physical Interaction with Human Motion-Force Demonstrations
A force-aware humanoid benchmark pairs synchronized human motion-force data with simulation-based force replay to evaluate whole-body control policies under realistic physical disturbances.
-
CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation
CWI decouples MoCap data for upper-body manipulation and lower-body locomotion, using dual discriminators and multi-critic training plus distillation to produce a policy that works from hand poses and velocity commands alone.
-
OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
-
CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation
CoorDex distills privileged body and hand motion teachers into proprioceptive latent priors and composes them via shared-context residual RL heads to enable continuous high-DoF dexterous loco-manipulation.
-
OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation
OpenHLM is an empirical recipe yielding a whole-body humanoid VLA model that outperforms GR00T N1.6 and Ψ0 baselines on long-horizon tasks using less than half the demonstration time.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation
MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.
-
X-OP: Cross-Morphology Whole-Body Teleoperation via MPC Retargeting
MPC-based retargeting framework enables cross-morphology whole-body teleoperation from a single XR device via dynamic feasibility optimization, state synchronization, and SLAM feedback, with reported gains in simulation and real-world tests.
-
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
-
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple rewards for mocap deployment.
-
VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids
VOFA combines a depth-image visuomotor policy with a force-adaptive whole-body controller to push objects of unknown mass to arbitrary goals on a humanoid.
-
Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot
A weightlessness mechanism enables humanoid robots to dynamically relax joints for stable, contact-rich motions across diverse environments without task-specific tuning.
-
HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control
HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.
-
Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.
-
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
Scaling motion tracking models along size, data volume, and compute produces a foundation model for natural, robust humanoid whole-body control with downstream uses in kinematic planning and vision-language-action models.
-
WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations
WARP is an offline retargeting method using a SEW geometric solver to produce consistent whole-body robot trajectories from human demonstrations for zero-shot mobile manipulation.
-
HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations
HALOMI extends UMI with egocentric sensing and a manifold-constrained controller plus alignment adaptations to learn loco-manipulation on humanoids from human demos, reporting 85% average success on three real-world tasks.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
GRAIL creates over 20,000 synthetic loco-manipulation sequences from known 3D configurations and video priors, then trains policies that achieve 84% pick-up and 90% stair-climbing success on a real Unitree G1 humanoid using only the generated data.
-
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
HumanoidMimicGen automatically generates large loco-manipulation datasets from few source demonstrations using whole-body planning, enabling visuomotor policies that outperform real-data-only training by 20% on a new nine-task benchmark.
-
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
-
Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum
A multi-agent large-model framework (Active Spatial Brain + Generalizable Action Cerebellum) enables spatial-aware humanoid whole-body manipulation without task-specific real-robot data.
-
Learning Versatile Humanoid Manipulation with Touch Dreaming
HTD, a multimodal transformer policy trained with behavioral cloning and touch dreaming to predict future tactile latents, achieves a 90.9% relative success rate improvement over baselines on five real-world contact-rich humanoid loco-manipulation tasks.
-
RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting
RPG trains a unified humanoid robot policy using motion and temporal randomization to achieve smooth, stable transitions between fighting skills and locomotion.