[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86051-en":3,"doc-seo-86051-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86051,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Learning Roller-Skating Motions of Humanoid Robots Based on Adversarial Motion Priors","Humanoid roller-skating requires coordinated whole-body balance, rolling-contact handling, and velocity-dependent posture regulation. The work introduces an adversarial motion prior (AMP) reinforcement learning framework to learn two humanoid roller-skating gaits: Pump Glide and Push Glide. Two gait datasets are independently collected via motion capture, retargeted to the robot, smoothed and resampled into AMP reference states, and trained with separate AMP pipelines, reward architectures, and policies. Simulation experiments assess gait quality, velocity tracking, turning, and reward ablation effects.","arXiv :2607 . 10815v1 [ cs .RO] 12 Jul 2026  \nLearning Roller-Skating Motions of Humanoid Robots Based on Adversarial Motion Priors  \nYunkang Cheng 1†, Yutong Wu 1†, Menghan Li 1 , Shihe Zhou 1 , and Mingguo  \nZhao 1 ,2 ,3⋆  \n1 Department of Automation, Tsinghua University, Beijing, China  \n2 Beijing Key Laboratory of Embodied Intelligence Systems, Beijing, China  \n3 Institute for Embodied Intelligence and Robotics, Tsinghua University, Beijing, China  \nCorresponding author: Mingguo Zhao Project website: [https://cyk579.github.io/Roller-Skating/](https://cyk579.github.io/Roller-Skating/)  \nAbstract. Humanoid roller-skating is difficult because the robot must coordinate whole-body balance, rolling contacts, and velocity-dependent posture regulation. This paper presents an adversarial motion prior based reinforcement learning framework for two humanoid roller-skating gaits:  \nPump Glide skating and Push Glide skating. The two gait datasets are collected independently through motion capture and retargeted to the humanoid robot separately. The retargeted data are then smoothed andresampled into reference motion states for AMP training. The two gaits are learned by independent AMP training pipelines with separate reference datasets, separate policies, and independent reward architectures.  \nSimulation experiments are designed to evaluate gait quality, velocity tracking, turning, and gait-specific reward ablations.  \nKeywords: humanoid robot, roller-skating, reinforcement learning, adversarial motion prior  \n1 Introduction  \nThis work is built around the experimental system shown in Fig. 1: a Booster T1 humanoid retrofitted with passive roller skates and controlled by an AMP-PPO policy. The robot has 23 actuated body DoFs, while four unactuated skate wheels under each foot introduce 8 passive wheel DoFs. Operator velocity commandsand robot state feedback are assembled into observation histories; the policy runs in a 50 Hz loop and outputs joint motor commands. Training and evaluation are conducted in Isaac Lab [23] with the passive-wheel contact model described below.  \nRoller-skating provides a locomotion mode between bipedal walking and  \nwheeled mobility: the robot preserves human-like leg motion while obtaining continuous gliding through skates. Wheeled-legged locomotion can be divided † These authors contributed equally.  \n⋆ Corresponding author.  \n2 Y. Cheng et al.  \nFig. 1. T1 humanoid skating platform, passive wheel modification, and system overview.  \ninto actuated-wheel and passive-wheel systems; this paper focuses on the latter, where propulsion is generated by leg motion and wheel-ground friction rather than wheel motors. The goal is to realize humanoid roller-skating motions on this passive-wheel system, not only in simulation but also in real-robot trials.  \nThis goal makes skate-wheel simulation a central technical challenge. Flatfoot support is replaced by rolling contact, and the passive wheels introduce underactuated dynamics, anisotropic friction, velocity-dependent posture regulation, and gait-specific propulsion. Therefore, the fidelity and stability of the wheel model directly affect sim-to-real feasibility and evaluation accuracy. Although AMP has become a mature route for legged locomotion and character control, applying it to roller skating is still nontrivial because the learned style must remain compatible with rolling contact, weight transfer, and passive-wheel constraints.  \nAccordingly, this paper makes three contributions:  \n1. A passive skate-wheel simulation method for humanoid roller skating, including a sliced-cylinder collision model and geometric analysis of wheel-contact fidelity.  \n2. An AMP-based learning–simulation–deployment pipeline that converts human skating demonstrations into gait-specific motion priors and trains separate policies for Pump Glide and Push Glide.  \n3. Simulation and real-robot validation of two passive-wheel humanoid skating gaits, with analysis of velocity response, gai","cbCaiqntBHUrIU2Z","https://ap.wps.com/l/cbCaiqntBHUrIU2Z","pdf",6791823,1,12,"English","en",105,"# Introduction\n## System overview\n## Key challenges and contributions\n# Related Work\n## Humanoid dynamic motion control\n## Wheeled-legged and skating robots","[{\"question\":\"What makes humanoid roller-skating difficult for robots?\",\"answer\":\"The robot must coordinate whole-body balance, rolling contacts, and velocity-dependent posture regulation while satisfying constraints from passive skate wheels and gait-specific propulsion.\"},{\"question\":\"Which two roller-skating gaits does the AMP framework learn?\",\"answer\":\"The framework learns Pump Glide skating and Push Glide skating as two separate gait behaviors trained via independent AMP training pipelines.\"},{\"question\":\"How are the training motion priors obtained for AMP?\",\"answer\":\"Motion capture datasets are independently collected for each gait, retargeted to the humanoid robot, then smoothed and resampled into reference motion states used for AMP training.\"}]",1784208083,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"learning-roller-skating-motions-of-humanoid-robots-based-on-adversarial-motion-priors","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/learning-roller-skating-motions-of-humanoid-robots-based-on-adversarial-motion-priors/86051/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What makes humanoid roller-skating difficult for robots?","Question",{"text":75,"@type":76},"The robot must coordinate whole-body balance, rolling contacts, and velocity-dependent posture regulation while satisfying constraints from passive skate wheels and gait-specific propulsion.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which two roller-skating gaits does the AMP framework learn?",{"text":80,"@type":76},"The framework learns Pump Glide skating and Push Glide skating as two separate gait behaviors trained via independent AMP training pipelines.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the training motion priors obtained for AMP?",{"text":84,"@type":76},"Motion capture datasets are independently collected for each gait, retargeted to the humanoid robot, then smoothed and resampled into reference motion states used for AMP training.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]