Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
Hover: Humanoid versatile controller for general-purpose tasks
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
Humanoid whole-body control requires adapting to diverse tasks such as navigation, loco-manipulation, and tabletop manipulation, each demanding a different mode of control. For example, navigation relies on root velocity tracking, while tabletop manipulation prioritizes upper-body joint angle tracking. Existing approaches typically train individual policies tailored to a specific command space, limiting their transferability across modes. We present the key insight that full-body kinematic motion imitation can serve as a common abstraction for all these tasks and provide general-purpose motor skills for learning multiple modes of whole-body control. Building on this, we propose HOVER (Humanoid Versatile Controller), a multi-mode policy distillation framework that consolidates diverse control modes into a unified policy. HOVER enables seamless transitions between control modes while preserving the distinct advantages of each, offering a robust and scalable solution for humanoid control across a wide range of modes. By eliminating the need for policy retraining for each control mode, our approach improves efficiency and flexibility for future humanoid applications.
fields
cs.RO 14representative citing papers
A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
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.
EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods and transferable to humanoid controllers.
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.
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.
A weightlessness mechanism enables humanoid robots to dynamically relax joints for stable, contact-rich motions across diverse environments without task-specific tuning.
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
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 single causal-transformer policy with latent recovery modes and contact-affordance prediction enables humanoid robots to recover from 100-300 N pushes with 100% success in simulation, generalizing zero-shot across wall distances, mass, friction, and latency changes.
A single goal-conditioned RL policy trained on contact plans performs multiple gaits and bimanual manipulation tasks on quadruped and humanoid robots.
In a confounded single-seed comparison, a dual-critic design reached targets 3.5x faster than a unified critic, but the causal role of critic architecture was not isolated.
citing papers explorer
-
Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
-
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.
-
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
-
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.
-
EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control
EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods and transferable to humanoid controllers.
-
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.
-
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.
-
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.
-
DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
-
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.
-
RecoverFormer: End-to-End Contact-Aware Recovery for Humanoid Robots
A single causal-transformer policy with latent recovery modes and contact-affordance prediction enables humanoid robots to recover from 100-300 N pushes with 100% success in simulation, generalizing zero-shot across wall distances, mass, friction, and latency changes.
-
Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning
A single goal-conditioned RL policy trained on contact plans performs multiple gaits and bimanual manipulation tasks on quadruped and humanoid robots.
-
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
In a confounded single-seed comparison, a dual-critic design reached targets 3.5x faster than a unified critic, but the causal role of critic architecture was not isolated.