{"id":537436,"date":"2026-07-07T12:23:08","date_gmt":"2026-07-07T12:23:08","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/537436\/"},"modified":"2026-07-07T12:23:08","modified_gmt":"2026-07-07T12:23:08","slug":"glass-crashes-slashed-ant-group-embodied-ai-unit-claims-breakthrough-in-robot-sensing","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/537436\/","title":{"rendered":"Glass crashes slashed? Ant Group embodied AI unit claims breakthrough in robot sensing"},"content":{"rendered":"<p>Robbyant, the embodied <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/artificial-intelligence?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">artificial intelligence<\/a> arm of Chinese fintech giant Ant Group, launched a new vision model that it claims can help robots overcome a long-standing challenge: accurately perceiving glass, mirrors and transparent objects.The unit of Hangzhou-based <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/ant-group?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">Ant Group<\/a> on Tuesday unveiled its next-generation spatial perception model, LingBot-Depth 2.0, alongside a new foundational visual model called LingBot-Vision, as AI labs race to equip machines with the \u201cbrains\u201d required to navigate complex physical spaces.Together, the technologies aimed to solve a critical bottleneck in <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/robotics?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">robotics<\/a> by ensuring machines could \u201caccurately and stably\u201d see in unpredictable, real-world environments, according to the Robbyant, which is also known as Ant Lingbo Technology.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">It was the first model of its kind trained specifically to recognise the edges of objects, the firm said. This allowed the AI to pinpoint boundaries with high precision \u2013 down to a fraction of a single pixel \u2013 giving robots a sharper understanding of the 3D spaces around them, it added.<\/p>\n<p>LingBot-Vision enters an arena dominated by <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/meta-platforms?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">Meta Platforms<\/a>\u2019 open-source vision model, DINOv3. But where that model relies on massive computational scale, LingBot-Vision aims to outrun rivals through structural efficiency.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">According to a research paper published by the Robbyant team, LingBot-Vision surpassed the 7-billion-parameter DINOv3 across multiple metrics on the NYUv2 depth-estimation benchmark. It achieved this using one-seventh as many parameters and less than a third of the training data, according to the benchmark.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">The new vision model serves as the critical engine driving LingBot-Depth 2.0.<\/p>\n","protected":false},"excerpt":{"rendered":"Robbyant, the embodied artificial intelligence arm of Chinese fintech giant Ant Group, launched a new vision model that&hellip;\n","protected":false},"author":2,"featured_media":537437,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[5682,23495,229,228427,138490,6159,61,60,228424,228383,2393,228426,228381,5698,10178,80,228425],"class_list":["post-537436","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-alibaba-group-holding","tag-ant-group","tag-chinese","tag-dinov3","tag-embodied-ai","tag-hangzhou","tag-ie","tag-ireland","tag-lingbot-depth","tag-lingbot-vision","tag-meta-platforms","tag-nyuv2","tag-robbyant","tag-shanghai","tag-south-china-morning-post","tag-technology","tag-transparent-objects"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/537436","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=537436"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/537436\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/537437"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=537436"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=537436"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=537436"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}