[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84409-en":3,"doc-seo-84409-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},84409,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","CONTACTMIMIC: Humanoid Object Interaction via Contact Control","Keypoint tracking alone fails to drive meaningful physical interaction in humanoid manipulation tasks such as sitting on a chair, wiping a board, or pushing furniture, where success depends on which body parts contact which objects and when. CONTACTMIMIC introduces a learning framework that combines explicit part-level binary contact commands with keypoint trajectories. It uses contact-following rewards and trajectory augmentation to break keypoint–contact correlations, decoupling contact behavior from keypoint geometry while enabling precise contact and controllability. Experiments on 10 motions validate task completion without task-specific rewards and outperform keypoint-only trackers; ablations and sim2real results on 5 motions confirm the augmentation’s necessity.","arXiv :2607 .08742v 1 [ cs .RO] 9 Jul 2026  \nCONTACTMIMIC:  \nHumanoid Object Interaction via Contact Control  \nXinyao Li∗ Xialin He∗ Runpei Dong Saurabh Gupta  \nUniversity of Illinois Urbana-Champaign  \nFigure 1: CONTACTMIMIC enables explicit contact control on a real humanoid across diverse interaction tasks. For each task, a same policy is commanded to either make the task-relevant contact (contact ✔) or to suppress it (contact ✘), by toggling a per-part contact label.  \nAbstract: Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object. We present CONTACTMIMIC, a learning framework that tracks explicit partlevel binary contact commands alongside keypoint trajectories. CONTACTMIMIC is made possible through the use of contact-following rewards and a trajectory augmentation scheme aimed at breaking the correlations between keypoint trajectories and contact labels. The resulting policy successfully decouples contact behavior from keypoint geometry, and achieves precise physical contact as well as contact-controllability (produce or suppress contact during deployment as desired) . Simulation experiments across 10 diverse human-object interaction motions confirm that CONTACTMIMIC exhibits contact controllability that en-  \n∗Equal contribution.  \nables it to complete manipulation tasks without task-specific rewards, while also outperforming keypoint-only trackers on contact-relevant tasks. Ablations confirm the necessity of the proposed trajectory augmentation scheme and sim2real deployment validates contact controllability in the real world across 5 different motions. Video results are available on [https://lixinyao11.github.io/](https://lixinyao11.github.io/)[ ](https://lixinyao11.github.io/)contactmimic-page/ .  \nKeywords: Humanoid Loco-manipulation, Motion Tracking, Contact Modeling  \n1 Introduction  \nMost useful whole-body loco-manipulation tasks with a humanoid require making contacts with the environment in important ways. Consider a humanoid wiping a whiteboard, or pushing chairs to tidy a room, or picking up boxes. Success is determined not by the robot’s keypoint trajectory, but rather by what body part contacts what objects, and when. For wiping a whiteboard, it is precisely the contacts at the hands that differentiate between waving the hand very close to a whiteboard and actually wiping it. Thus, just keypoint trajectories is an incomplete specification and many useful loco-manipulation tasks can’t be expressed just with keypoint trajectories. Yet, current humanoid trackers [1–6] aren’t aware of the contacts they should make along the way, and are only trained to track keypoint trajectories. As a result, while they may reproduce the shape of a motion, they miss the contacts that make the motion useful for a task. Thus, even universal keypoint trackers aren’t directly useful and require finetuning with task-specific rewards for success [1, 6, 7] .  \nConsider instead contact-conditioned keypoint trackers, where rather than just conditioning trackers on keypoint trajectories, we also provide the desired per time-step body-link contact labels as additional input to the policy. The additional contact information disambiguates tasks (e.g. wiping vs. waving, sitting vs. squatting) . Furthermore, it can provide more fine-grained control over the motion, e.g. sit in the chair but without leaning on the back. And finally, it may be possible to train task-specific policies without requiring task-specific rewards, but simply by training for the objective of matching keypoint and contact trajectories.  \nSo, how do we train a contact-conditioned keypoint tracker? There are two key considerations: a) how do we source trajectory data with associated contact labels for training, and b) how to design and train contact conditioned policies. For the first quest","cbCaitRYNyW0NbC1","https://ap.wps.com/l/cbCaitRYNyW0NbC1","pdf",37603146,1,17,"English","en",105,"# Introduction\n## Contact-conditioned keypoint tracking\n## Training data and augmentation\n## Contact-based policy objectives\n## Simulation and real-world validation","[{\"question\":\"Why is keypoint tracking insufficient for humanoid object interaction tasks?\",\"answer\":\"Because task success depends on explicit physical contacts between specific body parts and objects at particular times, not only on matching keypoint trajectories.\"},{\"question\":\"What is CONTACTMIMIC and what signals does it use?\",\"answer\":\"CONTACTMIMIC is a learning framework that tracks keypoint trajectories together with explicit part-level binary contact commands to either make or suppress task-relevant contact.\"},{\"question\":\"How does CONTACTMIMIC enable controllable contact during deployment?\",\"answer\":\"It decouples contact behavior from keypoint geometry using contact-following rewards and a trajectory augmentation scheme that breaks correlations between keypoint trajectories and contact labels, so changing contact commands changes robot behavior.\"}]",1784195404,43,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"contactmimic-humanoid-object-interaction-via-contact-control","",{"@graph":35,"@context":84},[36,53,67],{"@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/contactmimic-humanoid-object-interaction-via-contact-control/84409/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is keypoint tracking insufficient for humanoid object interaction tasks?","Question",{"text":74,"@type":75},"Because task success depends on explicit physical contacts between specific body parts and objects at particular times, not only on matching keypoint trajectories.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What is CONTACTMIMIC and what signals does it use?",{"text":79,"@type":75},"CONTACTMIMIC is a learning framework that tracks keypoint trajectories together with explicit part-level binary contact commands to either make or suppress task-relevant contact.",{"name":81,"@type":72,"acceptedAnswer":82},"How does CONTACTMIMIC enable controllable contact during deployment?",{"text":83,"@type":75},"It decouples contact behavior from keypoint geometry using contact-following rewards and a trajectory augmentation scheme that breaks correlations between keypoint trajectories and contact labels, so changing contact commands changes robot behavior.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":105,"slug":137},19,"General","general"]