Adversarial Motion Prior

Also known as AMP

Follow this topic Ask about this topic

Latest papers

10 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Push the Limit: Learning High-Speed Sprinting and Aggressive Cornering on a Full-Scale Humanoid
Oct 10, 2026Huaxing Huang, Ruidong Li, Jinchao Han +2Adversarial Motion Prior Compliant Legged Locomotion
Noetix Robotics · Tsinghua University
DAMP: Humanoid Locomotion via Denoised Belief Learning and Adversarial Motion Priors
Oct 8, 2026Puying Shen, Wenhao Cui, Huaxing Huang +4Adversarial Motion Prior Humanoid Robot Locomotion
School of Control Science and Engineering, Shandong University. · Shandong Key Laboratory of Humanoid Robotics.
Flow-Matched Motion Priors: Online Optimal-Transport Rewards for Imitation Learning
Sep 14, 2026Yilin Zou, Chenghua Liu, Chenglong Wu +1Imitation Learning RL for Legged Locomotion
School of Aerospace Engineering, Tsinghua University, Beijing 100084, China · Institute of Software, Chinese Academy of Sciences, Beijing, China
Learning Roller-Skating Motions of Humanoid Robots Based on Adversarial Motion Priors
Jul 12, 2026Yunkang Cheng, Yutong Wu, Menghan Li +2Humanoid Robot Locomotion Adversarial Motion Prior
Department of Automation, Tsinghua University, Beijing, China · Beijing Key Laboratory of Embodied Intelligence Systems, Beijing, China · Institute for Embodied Intelligence and Robotics, Tsinghua University, Beijing, China
Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies
Jun 26, 2026Penghui Chen, Tinglong Zheng, Yufeng Zhang +1Humanoid Robot Locomotion Robot Skill Learning
Department of Automation, Tsinghua University, Beijing, China · Booster Robotics Technology Co., Ltd, Beijing, China · School of Mechanical and Electronic Control Engineering, Beijing Jiaotong University, Beijing, China
T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion
Jun 5, 2026Junhong Guo, Hao Hu, Chen Chen +6Humanoid Robot Locomotion Adversarial Motion Prior
Harbin Institute of Technology · Leju Robotics
Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors
May 18, 2026Yidan Lu, Yichao Zhong, Liu Zhao +2Humanoid Robot Locomotion Robot Failure Recovery
The University of Hong Kong, Hong Kong SAR, China.
Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior
Apr 21, 2026Yuanye Wu, Keyi Wang, Linqi Ye +1Humanoid Robot Locomotion Adversarial Motion Prior
School of Future Technology, Shanghai University, Shanghai, 200444, China · National and Local Co-Built Humanoid Robotics Innovation Center, 201203 Shanghai, China
Partial Motion Imitation for Learning Cart Pushing with Legged Manipulators
Mar 27, 2026Mili Das, Morgan Byrd, Donghoon Baek +1Adversarial Motion Prior Legged Robotics
Georgia Institute of Technology, Atlanta, GA, 30308, USA
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes
Aug 23, 2025Haozhuo Zhang, Jingkai Sun, Michele Caprio +5Human Motion Generation Adversarial Motion Prior
The University of Manchester, Manchester, UK · X-Humanoid, Beijing, China · University of Hong Kong, Hong Kong, China +1

Oct 10, 2026J/K move · Enter open · S save

Push the Limit: Learning High-Speed Sprinting and Aggressive Cornering on a Full-Scale Humanoid

Huaxing Huang, Ruidong Li, Jinchao Han, Ziyang Dong+1

Noetix Robotics · Tsinghua University

Adversarial Motion Prior Compliant Legged Locomotion Humanoid Robot Locomotion Legged Robotics RL for Legged Locomotion

Open paper AskPDF arXiv

We present a learning-based framework that enables a full-scale bipedal humanoid to sprint at over 7 m/s with motion-prior-guided gait and perform aggressive cornering at high speed with a pronounced trunk lean of up to

25^\circ

. Achieving this combination is challenging: above approximately 4 m/s, periodic foot impacts induce severe, high-frequency yaw-rate oscillations intrinsic to high-speed gaits. This high-frequency temporal structure corrupts the history of proprioceptive feedback that flat-MLP policies rely on, while rendering conventional yaw-rate tracking rewards counterproductive, as they fight against the robot's natural oscillatory dynamics. Moreover, a single style prior shared across skills cannot tell which skill is commanded and inherently compromises the low-speed skill fidelity. To overcome these limitations, we adopt a causal multi-head attention (MHA) module to explicitly model the high-frequency temporal feedback. In place of the oscillatory yaw rate, we design a heading-direction reward that supervises only the low-frequency velocity direction, allowing agile turning at high speed without suppressing natural gait oscillations. We further introduce skill-conditioned multi-adversarial-motion-prior (MAMP) discriminators that condition the style reward on the commanded skill. Ablation experiments confirm that each mechanism is essential: replacing structured temporal encoding with a flat-history MLP caps the top speed; reverting to yaw-rate tracking prevents high-speed turning; and a single shared discriminator makes in-place turning collapse into a quasi-static stance. Our framework bridges the gap between raw sprinting speed and reference-motion fidelity, demonstrating stable high-speed sprinting and aggressive cornering in both simulation and real-robot deployment.