MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
hub
Omniretarget: Interaction-preserving data gen- eration for humanoid whole-body loco-manipulation and scene interaction
34 Pith papers cite this work. Polarity classification is still indexing.
34
Pith papers citing it
abstract
A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive locomotion and loco-manipulation. To address this, we introduce OmniRetarget, an interaction-preserving data generation engine based on an interaction mesh that explicitly models and preserves the crucial spatial and contact relationships between an agent, the terrain, and manipulated objects. By minimizing the Laplacian deformation between the human and robot meshes while enforcing kinematic constraints, OmniRetarget generates kinematically feasible trajectories. Moreover, preserving task-relevant interactions enables efficient data augmentation, from a single demonstration to different robot embodiments, terrains, and object configurations. We comprehensively evaluate OmniRetarget by retargeting motions from OMOMO, LAFAN1, and our in-house MoCap datasets, generating over 8-hour trajectories that achieve better kinematic constraint satisfaction and contact preservation than widely used baselines. Such high-quality data enables proprioceptive RL policies to successfully execute long-horizon (up to 30 seconds) parkour and loco-manipulation skills on a Unitree G1 humanoid, trained with only 5 reward terms and simple domain randomization shared by all tasks, without any learning curriculum.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 34representative citing papers
ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.
A DRL policy learns racing controls from depth spectral distributions using a non-geometric physics-informed reward, achieving 12% better performance than humans on out-of-distribution tracks with under 1% of baseline computation.
Rhythm transfers interactive whole-body behaviors from simulation to real dual Unitree G1 humanoids via interaction-aware retargeting and graph-reward RL.
A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
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.
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
PressMimic fuses RGB and pressure for pose estimation via FRAPPE++ and uses pressure signals in RL policy PSP, backed by the MotionPRO dataset, to achieve physically consistent humanoid motion imitation.
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
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.
PhysDrift generates executable humanoid co-speech motions directly from speech via robot-native data curated by IK-EER, claiming better alignment and plausibility than human-centric retargeting.
A humanoid robot can carry out diverse manipulation tasks in a zero-shot way by imitating one AI-generated video, using contact-aware trajectory optimization instead of task-specific policy training.
Video2Sim2Real turns a single human video into a deployable robot manipulation skill by reconstructing a digital twin, anchoring motions to object-centric simulator configurations, and bridging sim-to-real gaps with imitation learning and residual RL.
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
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.
CEER proposes a compliant end-effector and root control interface that unifies loco-manipulation for humanoids via a distilled low-level policy and hierarchical planners.
SynAgent enables generalizable cooperative humanoid manipulation by transferring skills from solo human-object interactions to multi-agent scenarios via interaction-preserving retargeting, single-agent pretraining with multi-agent PPO, and a conditional VAE generative policy.
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
A modular system uses motion matching to compose long-horizon human skill chains, trains RL experts, and distills them into a depth-based policy that lets a Unitree G1 humanoid autonomously climb, vault, and roll over obstacles up to 1.25 m tall.
HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive 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.
TopoRetarget uses a sparse interaction graph and distance-weighted Laplacian deformation optimization with kinematic and penetration constraints to retarget human demonstrations to dexterous hands while preserving task-relevant contacts.
citing papers explorer
-
MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
-
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.
-
Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing
A DRL policy learns racing controls from depth spectral distributions using a non-geometric physics-informed reward, achieving 12% better performance than humans on out-of-distribution tracks with under 1% of baseline computation.
-
Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids
Rhythm transfers interactive whole-body behaviors from simulation to real dual Unitree G1 humanoids via interaction-aware retargeting and graph-reward RL.
-
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.
-
SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
-
PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation
PressMimic fuses RGB and pressure for pose estimation via FRAPPE++ and uses pressure signals in RL policy PSP, backed by the MotionPRO dataset, to achieve physically consistent humanoid motion imitation.
-
TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
-
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.
-
PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation
PhysDrift generates executable humanoid co-speech motions directly from speech via robot-native data curated by IK-EER, claiming better alignment and plausibility than human-centric retargeting.
-
GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training
A humanoid robot can carry out diverse manipulation tasks in a zero-shot way by imitating one AI-generated video, using contact-aware trajectory optimization instead of task-specific policy training.
-
Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video
Video2Sim2Real turns a single human video into a deployable robot manipulation skill by reconstructing a digital twin, anchoring motions to object-centric simulator configurations, and bridging sim-to-real gaps with imitation learning and residual RL.
-
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
-
LIMMT: Less is More for Motion Tracking
A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.
-
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
-
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.
-
CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation
CEER proposes a compliant end-effector and root control interface that unifies loco-manipulation for humanoids via a distilled low-level policy and hierarchical planners.
-
SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy
SynAgent enables generalizable cooperative humanoid manipulation by transferring skills from solo human-object interactions to multi-agent scenarios via interaction-preserving retargeting, single-agent pretraining with multi-agent PPO, and a conditional VAE generative policy.
-
Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.
-
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
A modular system uses motion matching to compose long-horizon human skill chains, trains RL experts, and distills them into a depth-based policy that lets a Unitree G1 humanoid autonomously climb, vault, and roll over obstacles up to 1.25 m tall.
-
HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model
HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.
-
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.
-
TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation
TopoRetarget uses a sparse interaction graph and distance-weighted Laplacian deformation optimization with kinematic and penetration constraints to retarget human demonstrations to dexterous hands while preserving task-relevant contacts.
-
OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
OMG is a diffusion model for omni-modal whole-body humanoid motion generation that uses language, audio, and reference motions after large-scale data curation to achieve state-of-the-art performance and adaptation.
-
VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands
VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.
-
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
-
LadderMan: Learning Humanoid Perceptive Ladder Climbing
A hybrid motion-tracking and imitation-reinforcement pipeline produces a depth-based visuomotor policy that lets humanoids climb varied ladders zero-shot on hardware and perform teleoperated manipulation while climbing.
-
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
Humanoid-GPT is a causal Transformer pre-trained on a unified billion-scale motion dataset that tracks dynamic behaviors with zero-shot generalization to unseen motions and tasks.
-
Constrained Whole-Body Tracking for Humanoid Robots
ConstrainedMimic integrates operational space control and control barrier functions into RL tracking policies to enforce arbitrary runtime constraints on humanoid kinematics and dynamics while preserving contact modes and tracking goals.
-
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.
-
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.
-
SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation
SplitAdapter factorizes adaptation into load-aware and dynamics-aware encoders using split world-model objectives, GRL regularization, and hierarchical FiLM, reporting higher full-task success than baselines across 2-6 kg masses and 0-60 cm heights.
- Learning Versatile Humanoid Manipulation with Touch Dreaming