{"id":12083,"date":"2026-09-10T19:16:31","date_gmt":"2026-09-10T11:16:31","guid":{"rendered":"https:\/\/infernews.com\/blog\/tango\/"},"modified":"2026-09-10T19:16:51","modified_gmt":"2026-09-10T11:16:51","slug":"tango","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/tango\/","title":{"rendered":"TANGO\uff1a\u4eba\u5f62\u6a5f\u5668\u4eba\u7a7f\u8d8a\u51cc\u4e82\u623f\u9593\uff0c\u5168\u9760\u8a9e\u8a00\u6307\u4ee4"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/09\/pasted-c89f7de84d3e.jpg\" alt=\"TANGO architecture and data-generation pipeline.\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u5982\u679c\u53eb\u4e00\u90e8\u4eba\u5f62\u6a5f\u68b0\u4eba\u5f9e\u5ba2\u5ef3\u8d70\u5230\u5eda\u623f\uff0c\u4f46\u9014\u4e2d\u5806\u6eff\u7d19\u7bb1\u3001\u96dc\u7269\u3001\u7a84\u7e2b\uff0c\u4e00\u822c\u5c0e\u822a\u6f14\u7b97\u6cd5\u53ea\u61c2\u300c\u898f\u5283\u8def\u5f91\u300d\uff0c\u5c0d\u5b83\u4f86\u8aaa\u5e7e\u4e4e\u7b49\u65bc\u5ee2\u6b66\u529f\uff0c\u56e0\u70ba\u96d9\u8173\u3001\u96d9\u624b\u3001\u8170\u90e8\u5176\u5be6\u8981\u908a\u884c\u908a\u914d\u5408\u5730\u5f62\u90c1\u52d5\u3002TANGO\uff08whole-body Vision-Language-Action model\uff09\u6b63\u6b63\u70ba\u9019\u7a2e\u5834\u666f\u800c\u8a2d\u8a08\uff1a\u6536\u5230\u4e00\u53e5\u81ea\u7136\u8a9e\u8a00\u6307\u4ee4\uff0c\u52a0\u4e0a\u524d\u7f6e\u8207\u5411\u4e0b\u671b\u7684 RGB \u5f71\u50cf\u5f8c\uff0c\u6a21\u578b\u76f4\u63a5\u8f38\u51fa 29 \u500b\u81ea\u7531\u5ea6\uff0829-DoF\uff09\u7684\u5168\u8eab\u95dc\u7bc0\u89d2\u5ea6\uff0c\u914d\u5408 6D \u5e95\u76e4\u65cb\u8f49\u8868\u793a\uff0c\u4ee4\u6a5f\u68b0\u4eba\u80fd\u5920\u4e00\u908a\u884c\u3001\u4e00\u908a\u64fa\u624b\u6536\u8179\u907f\u958b\u969c\u7919\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u8a13\u7df4\u6578\u64da\u5168\u90e8\u4f86\u81ea\u6a21\u64ec\u5668\uff0c\u80cc\u5f8c\u6709\u4e00\u5957\u540d\u70ba Plan-Edit-Track \u7684\u6d41\u6c34\u7dda\uff1a\u5148\u7528\u5168\u5c40\u8def\u5f91\u898f\u5283\uff0c\u518d\u505a\u5168\u8eab\u9006\u5411\u904b\u52d5\u5b78\uff08Kinematics\uff09\u52d5\u4f5c\u751f\u6210\uff0c\u63a5\u4f4f\u7528\u969c\u7919\u611f\u77e5\u7de8\u8f2f\u907f\u958b\u64fa\u4f4d\uff0c\u6700\u5f8c\u7528\u5f37\u5316\u5b78\u7fd2\u8ffd\u8e64\u78ba\u4fdd\u52d5\u4f5c\u771f\u5be6\u505a\u5f97\u51fa\u569f\u3002\u8a13\u7df4\u96c6\u57fa\u65bc VLNVerse \u8207 SAGE-3D \u5834\u666f\uff0c\u518d\u52a0\u5165\u5074\u5411\u3001\u8cbc\u5730\u3001\u9802\u90e8\u7b49\u591a\u985e\u969c\u7919\uff0c\u52d9\u6c42\u8cbc\u8fd1\u771f\u5be6\u5bb6\u5c45\u4e82\u6cc1\u3002<\/p>\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"TANGO\ud83d\udc83\ud83c\udffb Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_67a-jjJpXKE\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F67a-jjJpXKE%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/67a-jjJpXKE\" \/><meta itemprop=\"duration\" content=\"PT2M59S\" \/><meta itemprop=\"uploadDate\" content=\"2026-09-09T05:20:17Z\" \/><\/div><div id=\"lyte_67a-jjJpXKE\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F67a-jjJpXKE%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">TANGO\ud83d\udc83\ud83c\udffb Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model<\/div><\/div><button tabindex=\"0\" class=\"play\"><\/button><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/67a-jjJpXKE\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F67a-jjJpXKE%2F0.jpg\" alt=\"TANGO\ud83d\udc83\ud83c\udffb Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional navigation methods that operate over simplified navigation abstractions, humanoid traversal in cluttered environments requires continuous geometry-aware whole-body adaptation, including coordinated arm placement, torso adjustment, and gait modulation for collision-free movement through complex 3D spaces. We introduce TANGO, a whole-body vision-language navigation framework for language-conditioned humanoid traversal in cluttered environments. Given a natural-language instruction and egocentric RGB observations, TANGO predicts 29-DoF joint-space actions for whole-body humanoid control. TANGO is trained entirely in simulation by synthesizing diverse collision-free traversal behaviors through global path planning, kinematic whole-body motion generation, obstacle-aware motion editing, and reinforcement-learning-based tracking. In simulation and real-world experiments, TANGO improves language-guided navigation and transfers zero-shot to a Unitree G1 humanoid without real-world training data.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n\n\n<p class=\"wp-block-paragraph\">\u6a21\u578b\u7d50\u69cb\u672c\u8eab\u4ea6\u5e7e\u8b1b\u7a76\uff1a\u5e95\u5c64\u4fc2\u4e00\u500b 70 \u5104\u53c3\u6578\uff087B\uff09\u7684\u8996\u89ba\u8a9e\u8a00\u9aa8\u5e79\uff0c\u914d\u642d\u4e00\u500b\u7528 flow-matching\uff08\u6d41\u5339\u914d\uff09\u8a13\u7df4\u5605 MM-DiT\uff08Multi-Modal Diffusion Transformer\uff0c\u591a\u6a21\u614b\u64f4\u6563 Transformer\uff09\u52d5\u4f5c\u5c08\u5bb6\uff0c\u518d\u52a0\u4e00\u500b\u4f4e\u968e\u5168\u8eab\u8ffd\u8e64\u5668\u8ca0\u8cac\u5373\u6642\u57f7\u884c\u3002\u90e8\u7f72\u6642 VLA\uff08Vision-Language-Action\uff0c\u8996\u89ba\u8a9e\u8a00\u52d5\u4f5c\uff09\u6a21\u578b\u55ba\u4f3a\u670d\u5668\u4f4e\u983b\u904b\u884c\uff0c\u8ffd\u8e64\u5668\u55ba\u6a5f\u68b0\u4eba onboard \u9ad8\u983b\u904b\u884c\uff0c\u505a\u5230\u5be6\u6642\u53cd\u61c9\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5be6\u9a57\u7d50\u679c\u65b9\u9762\uff0cTANGO \u55ba\u6a21\u64ec\u8207\u771f\u6a5f\u6e2c\u8a66\u90fd\u63d0\u5347\u5497\u8a9e\u8a00\u5c0e\u822a\u8868\u73fe\uff0c\u6700\u91cd\u8981\u4fc2\u96f6\u6a23\u672c\u9077\u79fb\uff08zero-shot transfer\uff09\u76f4\u63a5\u843d Unitree G1\uff08\u5b87\u6a39 G1\uff09\u4eba\u5f62\u6a5f\u68b0\u4eba\uff0c\u5514\u4f7f\u984d\u5916\u771f\u5be6\u6578\u64da\u518d\u8a13\u7df4\u3002\u5c0d\u7814\u7a76 VLA\u3001\u6a5f\u5668\u4eba\u5c0e\u822a\u6216\u4eba\u5f62\u6a5f\u68b0\u4eba\u90e8\u7f72\u5605\u5718\u968a\u569f\u8b1b\uff0c\u5462\u5957 pipeline \u9023\u6578\u64da\u751f\u6210\u5230\u6a21\u578b\u7d50\u69cb\u90fd\u5e7e\u503c\u5f97\u62c6\u89e3\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u91cd\u9ede\u6458\u8981\uff1a<br>\n&#8211; \u8a9e\u8a00\u6307\u4ee4\u76f4\u63a5\u5c0d\u61c9\u5168\u8eab 29-DoF \u52d5\u4f5c\uff0c\u6db5\u84cb\u624b\u3001\u8ec0\u5e79\u3001\u6b65\u614b\u5354\u8abf<br>\n&#8211; Plan-Edit-Track \u6d41\u6c34\u7dda\u5168\u6a21\u64ec\u8a13\u7df4\uff0c\u914d\u5408 VLNVerse \u8207 SAGE-3D \u5834\u666f\u751f\u6210<br>\n&#8211; \u63a1\u7528 7B \u8996\u89ba\u8a9e\u8a00\u9aa8\u5e79 + flow-matching MM-DiT \u52d5\u4f5c\u5c08\u5bb6\u96d9\u6a21\u7d44\u8a2d\u8a08<br>\n&#8211; \u4f3a\u670d\u5668\u8dd1 VLA\u3001\u6a5f\u68b0\u4eba onboard \u8dd1\u8ffd\u8e64\u5668\uff0c\u652f\u63f4\u5be6\u6642\u63a7\u5236<br>\n&#8211; \u96f6\u6a23\u672c\u9077\u79fb\u81f3 Unitree G1\uff0c\u7121\u9700\u771f\u5be6\u8a13\u7df4\u6578\u64da<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/tango-vla.github.io\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>TANGO \u662f\u4e00\u500b\u8b93\u4eba\u5f62\u6a5f\u5668\u4eba\u807d\u5230\u81ea\u7136\u8a9e\u8a00\u6307\u4ee4\u5f8c\uff0c\u81ea\u52d5\u8abf\u6574\u624b\u8173\u3001\u8ec0\u5e79\u8207\u6b65\u614b\u907f\u958b\u96dc\u7269\u7684\u5168\u8eab\u63a7\u5236\u6846\u67b6\uff0c\u53ef\u4ee5\u7406\u89e3\u6210\u628a\u6a5f\u68b0\u4eba\u5c0e\u822a\u5f9e\u300c\u6703\u8d70\u300d\u5347\u7d1a\u6210\u300c\u6703\u7a7f\u904e\u6c99\u767c\u5e95\u4e0b\u300d\u3002<\/p>\n","protected":false},"author":8,"featured_media":12082,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","footnotes":""},"categories":[169,76,149,119,127,31,204,184,197,199],"tags":[],"class_list":["post-12083","post","type-post","status-publish","format-standard","hentry","category-169","category-76","category-149","category-119","category-127","category-video","category-visionlanguageaction","category-robotic","category-framework","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/12083","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=12083"}],"version-history":[{"count":1,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/12083\/revisions"}],"predecessor-version":[{"id":12085,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/12083\/revisions\/12085"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/12082"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=12083"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=12083"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=12083"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}