{"id":7428,"date":"2023-08-08T05:50:03","date_gmt":"2023-08-08T05:50:03","guid":{"rendered":"https:\/\/apagom.com\/2023\/?page_id=7428"},"modified":"2023-08-12T23:58:19","modified_gmt":"2023-08-12T23:58:19","slug":"ai-collision","status":"publish","type":"page","link":"https:\/\/apagom.com\/2023\/ai-collision\/","title":{"rendered":"AI COLLISION"},"content":{"rendered":"\n<p class=\"has-large-font-size\"><strong><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">Real-time Collision using AI<\/mark><\/strong><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p class=\"has-black-color has-text-color\">Each object is represented as a quadric decomposition &#8211; a collection of parts, where each one is an intersection of quadric inequalities. Collision detection, consisting of deepest point estimation and a prediction of an intersection polygon, is formulated as a semi-definite programming problem and solved using Recurrent neural networks. The method can be applied to rigid, elastic, articulated, or deformable bodies, modeled by both convex or non-convex quadrics. The model was trained on 100 million contact points with the expected relative prediction error 10<sup>-6<\/sup> and 99.8<sup>th<\/sup> percentile below 10<sup>-5<\/sup>. The model does not need to be retrained for new scenes.<\/p>\n\n\n\n<p class=\"has-black-color has-text-color\"><br><strong>Videos <\/strong><\/p>\n\n\n\n<p> <\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-4-3 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<div class='embed-container'><iframe loading=\"lazy\" title=\"[SIGGRAPH 2023 Real-Time Live!] Real-Time Collision using AI\" width=\"1920\" height=\"1080\" src=\"https:\/\/www.youtube.com\/embed\/7snCXBe2RMA?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen><\/iframe><\/div>\n<\/div><figcaption class=\"wp-element-caption\">[SIGGRAPH 2023 Real-Time Live!] Real-Time Collision using AI<\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Real-time Collision using AI Each object is represented as a quadric decomposition &#8211; a collection of parts, where each one is an intersection of quadric inequalities. Collision detection, consisting of deepest point estimation and a prediction of an intersection polygon, is formulated as a semi-definite programming problem and solved using Recurrent neural networks. The method&hellip; <br \/> <a class=\"read-more\" href=\"https:\/\/apagom.com\/2023\/ai-collision\/\">Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"__cvm_playback_settings":[],"__cvm_video_id":"","footnotes":""},"class_list":["post-7428","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/pages\/7428","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/comments?post=7428"}],"version-history":[{"count":32,"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/pages\/7428\/revisions"}],"predecessor-version":[{"id":7622,"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/pages\/7428\/revisions\/7622"}],"wp:attachment":[{"href":"https:\/\/apagom.com\/2023\/wp-json\/wp\/v2\/media?parent=7428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}