Pith. sign in

REVIEW 12 cited by

Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.07773 v2 pith:ZYXDVU5L submitted 2024-12-10 cs.RO cs.AIcs.LG

classification cs.ROcs.AIcs.LG
keywords locomotionmanipulationcontrolmotionpreciseupper-bodyrobusthumanoid
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Humanoid robots require both robust lower-body locomotion and precise upper-body manipulation. While recent Reinforcement Learning (RL) approaches provide whole-body loco-manipulation policies, they lack precise manipulation with high DoF arms. In this paper, we propose decoupling upper-body control from locomotion, using inverse kinematics (IK) and motion retargeting for precise manipulation, while RL focuses on robust lower-body locomotion. We introduce PMP (Predictive Motion Priors), trained with Conditional Variational Autoencoder (CVAE) to effectively represent upper-body motions. The locomotion policy is trained conditioned on this upper-body motion representation, ensuring that the system remains robust with both manipulation and locomotion. We show that CVAE features are crucial for stability and robustness, and significantly outperforms RL-based whole-body control in precise manipulation. With precise upper-body motion and robust lower-body locomotion control, operators can remotely control the humanoid to walk around and explore different environments, while performing diverse manipulation tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation

    cs.RO 2025-10 conditional novelty 6.0 of 10

    A 10,300-demonstration, 260-task multimodal humanoid manipulation dataset with baseline policy evaluations and a cloud evaluation platform.

  2. TOP: Time Optimization Policy for Stable and Accurate Standing Manipulation with Humanoid Robots

    cs.RO 2025-08 conditional novelty 6.0 of 10

    A reinforcement-learned time optimization policy that adaptively slows upper-body motion clips improves stability and precision of humanoid standing manipulation at a modest time cost.

  3. Robot Drummer: Learning Rhythmic Skills for Humanoid Drumming

    cs.RO 2025-07 conditional novelty 6.0 of 10

    A simulated Unitree G1 humanoid learns to drum dozens of popular songs from MIDI with high F1 scores using a Rhythmic Contact Chain and temporal decomposition.

  4. GMT: General Motion Tracking for Humanoid Whole-Body Control

    cs.RO 2025-06 conditional novelty 6.0 of 10

    GMT trains a single unified humanoid policy using adaptive sampling and mixture-of-experts, achieving lower tracking errors than a re-implemented ExBody2 across diverse whole-body motions.

  5. Versatile Loco-Manipulation through Flexible Interlimb Coordination

    cs.RO 2025-06 conditional novelty 6.0 of 10

    ReLIC lets a robot dog dynamically reassign its legs between walking and manipulating, achieving 78.9% average success across 12 real-world loco-manipulation tasks.

  6. Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A slow-fast two-agent reinforcement learning architecture with separate upper- and lower-body policies reduces end-effector shaking during humanoid locomotion.

  7. Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A VR-teleoperated, reinforcement-learning-balanced control stack lets a miniature ROBOTIS OP3 humanoid walk and manipulate objects simultaneously.

  8. REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

    cs.RO 2026-03 conditional novelty 5.0 of 10

    Jointly fine-tuning a diffusion-policy high-level planner and an RL low-level controller raises humanoid loco-manipulation success rates from ~50-70% to >90% in simulation.

  9. Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots

    cs.RO 2025-07 conditional novelty 5.0 of 10

    A humanoid-specific multimodal occupancy perception system with a new dataset, sensor layout, and a fusion network that claims state-of-the-art results on its own benchmark.

  10. EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation

    cs.RO 2025-07 conditional novelty 5.0 of 10

    A state-conditioned executable motion prior network modifies upper-body motion targets so a humanoid can imitate human gestures while maintaining balance.

  11. AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

    cs.RO 2025-07 conditional novelty 5.0 of 10

    AC-DiT adds mobility-to-body conditioning and perception-aware 2D/3D weighting to a diffusion transformer, improving success rates on simulated and real-world mobile manipulation tasks.

  12. SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control

    cs.RO 2025-05 conditional novelty 5.0 of 10

    SMAP uses a vector-quantized periodic autoencoder to adapt human motion into physically plausible humanoid motion, then distills an RL teacher policy into a student policy for whole-body control.

Pith tools