What Matters in Humanoid General Motion Tracking? An Empirical Study

• URL: http://arxiv.org/abs/2607.19903v1
• Date: Wed, 22 Jul 2026 08:37:19 GMT
• Title: What Matters in Humanoid General Motion Tracking? An Empirical Study
• Abstract summary: We develop YAHMP, an open-source framework for training, evaluating, and deploying whole-body motion tracking policies on the Unitree G1.<n>We evaluate the resulting policies on a test set of retargeted human motions and compare the nominal policy with TWIST2 as an external baseline trained on the same motion set.
• Score: 2.728639503114606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humanoid general motion tracking requires policies that can follow diverse whole-body references while maintaining balance. Building such policies involves many practical design choices, and their individual effects are often hard to assess. We address this issue with an empirical study of common modeling and training factors used in recent humanoid motion-imitation pipelines. To make the study controlled and reproducible, we developed YAHMP, an open-source modular framework for training, evaluating, and deploying whole-body motion tracking policies on the Unitree G1. Within YAHMP, we define a nominal configuration and compare variants that differ in motion-command representation, observation history, action representation, actuation profile, hand-force randomization during training, and training approach. We evaluate the resulting policies on a test set of retargeted human motions and compare the nominal policy with TWIST2 as an external baseline trained on the same motion set. The results distinguish choices with clear tracking effects from choices that mainly change actuation effort, training complexity, or physical interaction capability. Finally, we deploy YAHMP policies zero-shot on the real Unitree G1, demonstrating diverse whole-body motion tracking, balance under external perturbations, and forceful interaction.

Related papers

• Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot [56.377161933570335]
  Humans naturally exploit a "weightless" state during non-self-stabilizing (NSS) motions.<n>Inspired by this biological mechanism, we propose a weightlessness-state auto-labeling strategy for dataset annotation.<n>Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.
  arXiv  Detail & Related papers  (2026-04-23T07:10:05Z)
• PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning [50.63196995993855]
  We propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC)<n>Our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors.
  arXiv  Detail & Related papers  (2026-03-25T07:55:37Z)
• ICPRL: Acquiring Physical Intuition from Interactive Control [38.098959182766144]
  We introduce ICPRL (In-Context Physical Reinforcement Learning), a framework that empowers VLMs to acquire physical intuition and adapt their policies in-context.<n>Our approach trains a vision-grounded policy model via multi-turn Group Relative Policy Optimization (GRPO) over diverse multi-episode interaction histories.<n>This enables the agent to adapt strategies by conditioning on past trial-and-error sequences, without requiring any weight updates.
  arXiv  Detail & Related papers  (2026-03-01T15:17:18Z)
• EGM: Efficiently Learning General Motion Tracking Policy for High Dynamic Humanoid Whole-Body Control [26.475304854903516]
  EGM is a framework that enables efficient learning of a general motion tracking policy.<n>We develop a three-stage curriculum training flow to progressively enhance the policy's robustness against disturbances.<n>Despite training on only 4.08 hours of data, EGM generalized robustly across 49.25 hours of test motions, outperforming baselines on both routine and highly dynamic tasks.
  arXiv  Detail & Related papers  (2025-12-22T05:25:24Z)
• Evaluating Gemini Robotics Policies in a Veo World Simulator [69.23071832313246]
  We introduce a generative evaluation system built upon a frontier video foundation model (Veo)<n>The system is optimized to support robot action conditioning and multi-view consistency.<n>We validate these capabilities through 1600+ real-world evaluations of eight Gemini Robotics policy checkpoints and five tasks for a bimanual manipulator.
  arXiv  Detail & Related papers  (2025-12-11T14:22:14Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control [14.36344580057985]
  Policies Diffusion (DPs) have shown impressive results in robotic manipulation. This paper investigates how dataset diversity and size affect the performance of DPs for humanoid whole-body control.
  arXiv  Detail & Related papers  (2024-11-02T19:33:28Z)
• Adaptive Tracking of a Single-Rigid-Body Character in Various Environments [2.048226951354646]
  We propose a deep reinforcement learning method based on the simulation of a single-rigid-body character. Using the centroidal dynamics model (CDM) to express the full-body character as a single rigid body (SRB) and training a policy to track a reference motion, we can obtain a policy capable of adapting to various unobserved environmental changes. We demonstrate that our policy, efficiently trained within 30 minutes on an ultraportable laptop, has the ability to cope with environments that have not been experienced during learning.
  arXiv  Detail & Related papers  (2023-08-14T22:58:54Z)
• 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)
• A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control [2.2082422928825136]
  We present a simple and intuitive approach for interactive control of physically simulated characters. Our work builds upon generative adversarial networks (GAN) and reinforcement learning. We highlight the applicability of our approach in a range of imitation and interactive control tasks.
  arXiv  Detail & Related papers  (2021-05-21T00:03:29Z)
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [77.59069361196404]
  TRiPOD is a novel method for predicting body dynamics based on graph attentional networks. To incorporate a real-world challenge, we learn an indicator representing whether an estimated body joint is visible/invisible at each frame. Our evaluation shows that TRiPOD outperforms all prior work and state-of-the-art specifically designed for each of the trajectory and pose forecasting tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:01:00Z)

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.