{"id":34980,"date":"2024-12-16T08:58:49","date_gmt":"2024-12-16T00:58:49","guid":{"rendered":"https:\/\/17aitech.com\/?p=34980"},"modified":"2024-12-16T08:58:49","modified_gmt":"2024-12-16T00:58:49","slug":"%e6%9d%8e%e9%a3%9e%e9%a3%9e%e3%80%8c%e7%a9%ba%e9%97%b4%e6%99%ba%e8%83%bd%e3%80%8d%e4%b9%8b%e5%90%8e%ef%bc%8c%e4%b8%8a%e4%ba%a4%e3%80%81%e6%99%ba%e6%ba%90%e3%80%81%e5%8c%97%e5%a4%a7%e7%ad%89%e6%8f%90","status":"publish","type":"post","link":"https:\/\/17aitech.com\/?p=34980","title":{"rendered":"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot"},"content":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-08-07-2\" target=\"_blank\">\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot<\/a><\/p>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png\"><\/a><\/section>\n<blockquote data-author-name=\"\" data-content-utf8-length=\"166\" data-source-title=\"\" data-type=\"2\" data-url=\"\">\n<section>\n<section>AIxiv\u4e13\u680f\u662f<mark data-type=\"institutions\" data-id=\"9e96434f-5827-41e3-9b3c-36d39bc0d446\">\u673a\u5668\u4e4b\u5fc3<\/mark>\u53d1\u5e03\u5b66\u672f\u3001\u6280\u672f\u5185\u5bb9\u7684\u680f\u76ee\u3002\u8fc7\u53bb\u6570\u5e74\uff0c<mark data-type=\"institutions\" data-id=\"9e96434f-5827-41e3-9b3c-36d39bc0d446\">\u673a\u5668\u4e4b\u5fc3<\/mark>AIxiv\u4e13\u680f\u63a5\u6536\u62a5\u9053\u4e862000\u591a\u7bc7\u5185\u5bb9\uff0c\u8986\u76d6\u5168\u7403\u5404\u5927\u9ad8\u6821\u4e0e\u4f01\u4e1a\u7684\u9876\u7ea7\u5b9e\u9a8c\u5ba4\uff0c\u6709\u6548\u4fc3\u8fdb\u4e86\u5b66\u672f\u4ea4\u6d41\u4e0e\u4f20\u64ad\u3002\u5982\u679c\u60a8\u6709\u4f18\u79c0\u7684\u5de5\u4f5c\u60f3\u8981\u5206\u4eab\uff0c\u6b22\u8fce\u6295\u7a3f\u6216\u8005\u8054\u7cfb\u62a5\u9053\u3002\u6295\u7a3f\u90ae\u7bb1\uff1aliyazhou@jiqizhixin.com\uff1bzhaoyunfeng@jiqizhixin.com<\/section>\n<\/section>\n<\/blockquote>\n<section><\/section>\n<section><strong>\u672c\u6587\u7b2c\u4e00\u4f5c\u8005\u4e3a\u65af\u5766\u798f\u5927\u5b66\u7814\u7a76\u751f\u8521\u95fb\u9a81\uff0c\u6b64\u524d\uff0c\u4ed6\u4ee5\u7ee9\u70b9\u7b2c\u4e00\u540d\u7684\u6210\u7ee9\u5728<mark data-type=\"institutions\" data-id=\"58854454-7c46-469e-a4e0-1205db4e1a5f\">\u4e1c\u5357\u5927\u5b66<\/mark>\u53d6\u5f97\u5b66\u58eb\u5b66\u4f4d\u3002\u4ed6\u7684\u7814\u7a76\u5174\u8da3\u4e3a\u591a\u6a21\u6001\u5927\u6a21\u578b\u3001\u5177\u8eab\u667a\u80fd\u3002\u6b64\u5de5\u4f5c\u4e3a\u5176\u5728\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\u8bbf\u95ee\u548c\u5317\u4eac\u667a\u6e90<mark data-type=\"concepts\" data-id=\"2d28aa9c-942d-471d-bd96-8bfefb7144e0\">\u4eba\u5de5\u667a\u80fd<\/mark>\u7814\u7a76\u9662\u5b9e\u4e60\u671f\u95f4\u5b8c\u6210\uff0c\u5bfc\u5e08\u4e3a\u672c\u6587\u901a\u8baf\u4f5c\u8005\u8d75\u6ce2\u6559\u6388\u3002<\/strong><\/section>\n<section><\/section>\n<section>\u6b64\u524d\uff0c<mark data-type=\"experts\" data-id=\"8d5c1902-53f9-4a03-9c4c-1369cb30f400\">\u674e\u98de\u98de<\/mark>\u8001\u5e08\u63d0\u51fa\u4e86\u7a7a\u95f4\u667a\u80fd (Spatial Intelligence) \u8fd9\u4e00\u6982\u5ff5\uff0c\u4f5c\u4e3a\u56de\u5e94\uff0c\u6765\u81ea\u4e0a\u4ea4\u3001\u65af\u5766\u798f\u3001\u667a\u6e90\u3001\u5317\u5927\u3001\u725b\u6d25\u3001\u4e1c\u5927\u7684\u7814\u7a76\u8005\u63d0\u51fa\u4e86\u7a7a\u95f4\u5927\u6a21\u578b SpatialBot\uff0c\u5e76\u63d0\u51fa\u4e86\u8bad\u7ec3\u6570\u636e SpatialQA \u548c\u6d4b\u8bd5\u699c\u5355 SpatialBench\uff0c \u5c1d\u8bd5\u8ba9\u591a\u6a21\u6001\u5927\u6a21\u578b\u5728\u901a\u7528\u573a\u666f\u548c\u5177\u8eab\u573a\u666f\u4e0b\u7406\u89e3\u6df1\u5ea6\u3001\u7406\u89e3\u7a7a\u95f4\u3002<\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-9b3f39ccd40dccca8cfda81ef7b4aa25.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-9b3f39ccd40dccca8cfda81ef7b4aa25.png\"><\/a><\/p>\n<ul>\n<li>\n<section>\u8bba\u6587\u6807\u9898: SpatialBot: Precise Depth Understanding with Vision Language Models<\/section>\n<\/li>\n<li>\n<section>\u8bba\u6587\u94fe\u63a5: https:\/\/arxiv.org\/abs\/2406.13642<\/section>\n<\/li>\n<li>\n<section>\u9879\u76ee\u4e3b\u9875: https:\/\/github.com\/BAAI-DCAI\/SpatialBot<\/section>\n<\/li>\n<\/ul>\n<section><\/section>\n<section>\u5728\u5177\u8eab\u667a\u80fd\u7684 pick and place \u4efb\u52a1\u4e2d\uff0c\u9700\u8981\u5224\u65ad\u673a\u68b0\u722a\u662f\u5426\u78b0\u5230\u4e86\u76ee\u6807\u7269\u4f53\u3002\u5982\u679c\u78b0\u5230\uff0c\u5219\u53ef\u4ee5\u5408\u4e0a\u722a\u5b50\u6293\u53d6\u3002\u7136\u800c\uff0c\u5728\u8fd9\u4e2a Berkerly UR5 Demonstration Dataset \u573a\u666f\u4e2d\uff0c\u5373\u4f7f\u662f GPT-4o \u6216\u4eba\u7c7b\uff0c\u90fd\u65e0\u6cd5\u4ece\u5355\u5f20 RGB \u56fe\u50cf\u4e2d\u5224\u65ad\u673a\u68b0\u722a\u662f\u5426\u78b0\u5230\u4e86\u76ee\u6807\u7269\u4f53\uff0c\u6bd4\u5982\u501f\u52a9\u6df1\u5ea6\u4fe1\u606f\uff0c\u5c06\u6df1\u5ea6\u56fe\u76f4\u63a5\u7ed9 GPT-4o \u770b\u7684\u8bdd\uff0c\u4e5f\u65e0\u6cd5\u5224\u65ad\uff0c\u56e0\u4e3a\u5b83\u4e0d\u80fd\u7406\u89e3\u6df1\u5ea6\u56fe\u3002<\/section>\n<section><\/section>\n<section>SpatialBot \u901a\u8fc7\u5bf9 RGB-Depth \u7684\u7406\u89e3\uff0c\u53ef\u4ee5\u51c6\u786e\u83b7\u5f97\u673a\u68b0\u722a\u548c\u76ee\u6807\u7269\u4f53\u7684\u6df1\u5ea6\u503c\uff0c\u4ece\u800c\u4ea7\u751f\u5bf9\u7a7a\u95f4\u6982\u5ff5\u7684\u7406\u89e3\u3002<\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-a71af0167b8a05385a2213f2480b1f22.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-a71af0167b8a05385a2213f2480b1f22.png\"><\/a><\/p>\n<section><strong>\u5177\u8eab\u573a\u666f\u7684 SpatialBot Demo\uff1a<\/strong><\/section>\n<section><\/section>\n<section>1. \u4ee5\u4eba (\u76f8\u673a) \u7684\u89c6\u89d2\uff0c\u6293\u53d6\u53f3\u4fa7\u7684\u8336\u676f<a href=\"https:\/\/mp.weixin.qq.com\/s\/X1iqkkEMsop9DGCY08AfCw\"><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-6b8775c9648f4b9ab7dc0326b1f7cc21.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-6b8775c9648f4b9ab7dc0326b1f7cc21.png\"><\/a><\/a>2. \u6293\u53d6\u6700\u4e2d\u95f4\u7684\u8336\u676f\u00a0<a href=\"https:\/\/mp.weixin.qq.com\/s\/X1iqkkEMsop9DGCY08AfCw\"><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-08e0d7a11d04e500a1f0a05a98a73226.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-08e0d7a11d04e500a1f0a05a98a73226.png\"><\/a><\/a><\/section>\n<section><strong>\u4f5c\u4e3a\u8d70\u5411\u5177\u8eab\u667a\u80fd\u7684\u5fc5\u8981\u8def\u5f84\uff0c\u5982\u4f55\u8ba9\u5927\u6a21\u578b\u7406\u89e3\u7a7a\u95f4\uff1f<\/strong><\/section>\n<section><\/section>\n<section>\u70b9\u4e91\u6bd4\u8f83\u8d35\uff0c\u53cc\u76ee\u76f8\u673a\u5728\u4f7f\u7528\u4e2d\u9700\u8981\u7ecf\u5e38\u6821\u51c6\u3002\u76f8\u6bd4\u4e4b\u4e0b\uff0c\u6df1\u5ea6\u76f8\u673a\u4ef7\u683c\u53ef\u4ee5\u63a5\u53d7\u3001\u4f7f\u7528\u8303\u56f4\u5e7f\u3002\u5728\u901a\u7528\u573a\u666f\u4e2d\uff0c\u5373\u4f7f\u6ca1\u6709\u8fd9\u6837\u7684\u786c\u4ef6\u8bbe\u5907\uff0c\u5927\u89c4\u6a21\u65e0\u76d1\u7763\u8bad\u7ec3\u8fc7\u7684\u6df1\u5ea6\u4f30\u8ba1\u6a21\u578b\u5df2\u7ecf\u53ef\u4ee5\u63d0\u4f9b\u8f83\u4e3a\u51c6\u786e\u7684\u6df1\u5ea6\u4fe1\u606f\u3002\u56e0\u6b64\uff0c\u4f5c\u8005\u63d0\u51fa\uff0c\u4f7f\u7528 RGBD \u4f5c\u4e3a\u7a7a\u95f4\u5927\u6a21\u578b\u7684\u8f93\u5165\u3002<\/section>\n<section><\/section>\n<section><strong>\u76ee\u524d\u7684\u6280\u672f\u8def\u7ebf\u5b58\u5728\u4ec0\u4e48\u95ee\u9898\uff1f<\/strong><\/section>\n<section><\/section>\n<ol>\n<li>\n<section>\u73b0\u6709\u6a21\u578b\u65e0\u6cd5\u76f4\u63a5\u7406\u89e3\u6df1\u5ea6\u56fe\u8f93\u5165\u3002\u6bd4\u5982\uff0c\u56fe\u50cf\u7f16\u7801\u5668 CLIP\/SigLIP \u5728 RGB \u56fe\u50cf\u4e0a\u8bad\u7ec3\uff0c\u6ca1\u6709\u89c1\u8fc7\u6df1\u5ea6\u56fe\u3002<\/section>\n<\/li>\n<li>\n<section>\u73b0\u6709\u5927\u6a21\u578b\u6570\u636e\u96c6\uff0c\u5927\u591a\u4ec5\u7528 RGB \u5c31\u53ef\u4ee5\u5206\u6790\u3001\u56de\u7b54\u3002\u56e0\u6b64\uff0c\u5982\u679c\u4ec5\u4ec5\u7b80\u5355\u7684\u5c06\u73b0\u6709\u6570\u636e\u6539\u4e3a RGBD \u8f93\u5165\uff0c\u6a21\u578b\u4e0d\u4f1a\u4e3b\u52a8\u5230\u6df1\u5ea6\u56fe\u4e2d\u7d22\u5f15\u77e5\u8bc6\u3002\u9700\u8981\u4e13\u95e8\u8bbe\u8ba1\u4efb\u52a1\u548c QA\uff0c\u5f15\u5bfc\u6a21\u578b\u7406\u89e3\u6df1\u5ea6\u56fe\u3001\u4f7f\u7528\u6df1\u5ea6\u4fe1\u606f\u3002<\/section>\n<\/li>\n<\/ol>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-cb4eb034822444501e0525cc0c3722c1.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-cb4eb034822444501e0525cc0c3722c1.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u4e09\u4e2a\u5c42\u6b21\u7684 SpatialQA\uff0c\u9010\u6b65\u5f15\u5bfc\u6a21\u578b\u7406\u89e3\u6df1\u5ea6\u56fe\u3001\u4f7f\u7528\u6df1\u5ea6\u4fe1\u606f<\/sup><\/em><\/section>\n<section>\u00a0<\/section>\n<section><strong>\u5982\u4f55\u5f15\u5bfc\u6a21\u578b\u7406\u89e3\u548c\u4f7f\u7528\u6df1\u5ea6\u4fe1\u606f\uff0c\u7406\u89e3\u7a7a\u95f4\uff1f<\/strong><\/section>\n<section><\/section>\n<section>\u4f5c\u8005\u63d0\u51fa\u5177\u6709\u4e09\u4e2a\u5c42\u6b21\u7684 SpatialQA \u6570\u636e\u96c6\u3002<\/section>\n<section><\/section>\n<ol>\n<li>\n<section>\u5728 low level \u5f15\u5bfc\u6a21\u578b\u7406\u89e3\u6df1\u5ea6\u56fe\uff0c\u5f15\u5bfc\u4ece\u6df1\u5ea6\u56fe\u76f4\u63a5\u83b7\u53d6\u4fe1\u606f\uff1b<\/section>\n<\/li>\n<li>\n<section>\u5728 middle level \u8ba9\u6a21\u578b\u5c06 depth \u4e0e RGB \u5bf9\u9f50\uff1b<\/section>\n<\/li>\n<li>\n<section>\u5728 high level \u8bbe\u8ba1\u591a\u4e2a\u6df1\u5ea6\u76f8\u5173\u4efb\u52a1\uff0c\u6807\u6ce8\u4e86 50k \u7684\u6570\u636e\uff0c\u8ba9\u6a21\u578b\u5728\u7406\u89e3\u6df1\u5ea6\u56fe\u7684\u57fa\u7840\u4e0a\uff0c\u4f7f\u7528\u6df1\u5ea6\u4fe1\u606f\u5b8c\u6210\u4efb\u52a1\u3002\u4efb\u52a1\u5305\u62ec\uff1a\u7a7a\u95f4\u4f4d\u7f6e\u5173\u7cfb\uff0c\u7269\u4f53\u5927\u5c0f\uff0c\u7269\u4f53\u63a5\u89e6\u4e0e\u5426\uff0c\u673a\u5668\u4eba\u573a\u666f\u7406\u89e3\u7b49\u3002<\/section>\n<\/li>\n<\/ol>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-48b334d834497c395db43d07b8e672a1.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-48b334d834497c395db43d07b8e672a1.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0\u793a\u4f8b\u5bf9\u8bdd<\/sup><\/em><\/section>\n<section><\/section>\n<section><strong>SpatialBot \u5305\u542b\u4ec0\u4e48\uff1f<\/strong><\/section>\n<section><\/section>\n<section>1. \u501f\u9274 agent \u4e2d\u7684\u601d\u60f3\uff0cSpatialBot \u5728\u9700\u8981\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7 API \u83b7\u53d6\u51c6\u786e\u7684\u6df1\u5ea6\u4fe1\u606f\u3002\u5728\u6df1\u5ea6\u4fe1\u606f\u83b7\u53d6\u3001\u8fdc\u8fd1\u5173\u7cfb\u6bd4\u8f83\u7684\u4efb\u52a1\u4e0a\uff0c\u53ef\u4ee5\u8fbe\u5230 99%+ \u7684<mark data-type=\"concepts\" data-id=\"8be77eae-12da-4e9e-9a88-b7f5bae98c2e\">\u51c6\u786e\u7387<\/mark>\u3002<\/section>\n<section>2. \u9488\u5bf9\u7a7a\u95f4\u7406\u89e3\u4efb\u52a1\uff0c\u4f5c\u8005\u516c\u5e03\u4e86 SpatialBench \u699c\u5355\u3002\u901a\u8fc7\u7cbe\u5fc3\u8bbe\u8ba1\u548c\u6807\u6ce8 QA\uff0c\u6d4b\u8bd5\u6a21\u578b\u6df1\u5ea6\u7406\u89e3\u80fd\u529b\u3002SpatialBot \u5728\u699c\u5355\u4e0a\u5c55\u793a\u4e86\u548c GPT-4o \u63a5\u8fd1\u7684\u80fd\u529b\u3002<\/section>\n<section><\/section>\n<section><strong>\u6a21\u578b\u5982\u4f55\u7406\u89e3\u6df1\u5ea6\u56fe\uff1f<\/strong><\/section>\n<section><\/section>\n<section>1. \u8f93\u5165\u6a21\u578b\u7684\u6df1\u5ea6\u56fe\uff1a\u4e3a\u4e86\u517c\u987e\u5ba4\u5185\u5ba4\u5916\u4efb\u52a1\uff0c\u9700\u8981\u7edf\u4e00\u7684\u6df1\u5ea6\u56fe\u7f16\u7801\u65b9\u5f0f\u3002\u5ba4\u5185\u7684\u6293\u53d6\u3001\u5bfc\u822a\u4efb\u52a1\u53ef\u80fd\u9700\u8981\u6beb\u7c73\u7ea7\u7684\u7cbe\u786e\u5ea6\uff0c\u5ba4\u5916\u7684\u573a\u666f\u4e0d\u9700\u8981\u8fd9\u4e48\u7cbe\u51c6\uff0c\u5374\u53ef\u80fd\u9700\u8981 100 \u7c73\u4ee5\u4e0a\u7684\u6df1\u5ea6\u503c\u8303\u56f4\u3002\u4f20\u7edf\u89c6\u89c9\u4efb\u52a1\u4e2d\u4f1a\u7528 Ordinal Encoding \u6765\u7f16\u7801\uff0c\u4f46\u662f ordinal \u7684\u503c\u65e0\u6cd5\u8fdb\u884c\u52a0\u51cf\u8fd0\u7b97\u3002\u4e3a\u4e86\u5c3d\u53ef\u80fd\u4fdd\u7559\u6240\u6709\u6df1\u5ea6\u4fe1\u606f\uff0cSpatialBot \u76f4\u63a5\u4f7f\u7528\u4ee5\u6beb\u7c73\u4e3a\u5355\u4f4d\u7684 metric depth\uff0c\u8303\u56f4\u4e3a 1mm\uff5e131m\uff0c\u4f7f\u7528 uint24 \u6216\u4e09\u901a\u9053\u7684 uint8 \u6765\u4fdd\u7559\u8fd9\u4e9b\u503c\u3002<\/section>\n<section>2. \u4e3a\u4e86\u7cbe\u51c6\u7684\u83b7\u53d6\u6df1\u5ea6\u4fe1\u606f\uff0c\u501f\u9274 agents \u4e2d\u7684\u601d\u60f3\uff0cSpatialBot \u5728\u8ba4\u4e3a\u6709\u5fc5\u8981\u7684\u65f6\u5019\uff0c\u4f1a\u4ee5\u70b9\u7684\u5f62\u5f0f\u8c03\u7528 DepthAPI\uff0c\u83b7\u53d6\u51c6\u786e\u7684\u6df1\u5ea6\u503c\u3002\u82e5\u60f3\u83b7\u53d6\u7269\u4f53\u7684\u6df1\u5ea6\uff0cSpatialBot \u4f1a\u5148\u601d\u8003\u7269\u4f53\u7684 bounding box \u662f\u4ec0\u4e48\uff0c\u7136\u540e\u7528 bounding box \u7684\u4e2d\u5fc3\u70b9\u8c03\u7528 API\u3002<\/section>\n<section>3. SpatialBot \u4f7f\u7528\u7269\u4f53\u7684\u4e2d\u5fc3\u70b9\u3001\u6df1\u5ea6\u5e73\u5747\u3001\u6700\u5927\u548c\u6700\u5c0f\u56db\u4e2a\u503c\u6765\u63cf\u8ff0\u6df1\u5ea6\u3002<\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-4b80f7a094dc46bdec8a7a7708cbba50.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-4b80f7a094dc46bdec8a7a7708cbba50.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 SpatialBot \u548c DepthAPI \u67b6\u6784<\/sup><\/em><\/section>\n<section><\/section>\n<section><strong>SpatialBot \u5728\u901a\u7528\u573a\u666f\u548c\u5177\u8eab\u573a\u666f\u6548\u679c\u5982\u4f55\uff1f<\/strong><\/section>\n<section><\/section>\n<section>1. SpatialBot \u57fa\u4e8e 3B \u5230 8B \u7684\u591a\u4e2a base LLM\u3002\u901a\u8fc7\u5728 SpatialQA \u4e2d\u5b66\u4e60\u7a7a\u95f4\u77e5\u8bc6\uff0cSpatialBot \u5728\u5e38\u7528 MLLM \u6570\u636e\u96c6 (MME\u3001MMBench \u7b49) \u4e0a\u540c\u6837\u5c55\u793a\u4e86\u663e\u8457\u7684\u6548\u679c\u63d0\u5347\u3002<\/section>\n<section>2. \u5728 Open X-Embodiment\u3001\u4f5c\u8005\u6536\u96c6\u7684\u673a\u5668\u4eba\u6293\u53d6\u6570\u636e\u7b49\u5177\u8eab\u4efb\u52a1\u4e0a\uff0cSpatialBot \u540c\u6837\u5c55\u793a\u4e86\u60ca\u4eba\u6548\u679c\u3002<\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-617d108063a482bfc436709c627f6b7a.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-617d108063a482bfc436709c627f6b7a.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 SpatialBot \u901a\u7528\u573a\u666f\u5bf9\u6bd4\u5b9e\u9a8c<\/sup><\/em><\/section>\n<section><\/section>\n<section><strong>\u6570\u636e\u5982\u4f55\u6807\u6ce8\uff1f<\/strong><\/section>\n<section><\/section>\n<section>\u7cbe\u5fc3\u8bbe\u8ba1\u4e86\u5173\u4e8e\u7a7a\u95f4\u7406\u89e3\u7684\u95ee\u9898\uff0c\u6bd4\u5982\u6df1\u5ea6\u3001\u8fdc\u8fd1\u5173\u7cfb\u3001\u4e0a\u4e0b\u5de6\u53f3\u524d\u540e\u4f4d\u7f6e\u5173\u7cfb\u3001\u5927\u5c0f\u5173\u7cfb\uff0c\u5e76\u4e14\u5305\u542b\u4e86\u5177\u8eab\u4e2d\u7684\u91cd\u8981\u95ee\u9898\uff0c\u6bd4\u5982\u4e24\u4e2a\u7269\u4f53\u662f\u5426\u63a5\u89e6\u3002<\/section>\n<section><\/section>\n<section>\u5728\u6d4b\u8bd5\u96c6 SpatialBench \u4e2d\uff0c\u9996\u5148\u4eba\u5de5\u601d\u8003\u95ee\u9898\u3001\u9009\u9879\u548c\u7b54\u6848\u3002\u4e3a\u4e86\u6269\u5927\u6d4b\u8bd5\u96c6\u5927\u5c0f\uff0c\u4e5f\u4f7f\u7528 GPT \u4ee5\u540c\u6837\u7684\u6d41\u7a0b\u6807\u6ce8\u3002<\/section>\n<section><\/section>\n<section>\u8bad\u7ec3\u96c6 SpatialQA \u5305\u542b\u4e09\u65b9\u9762\uff1a\u00a0<\/section>\n<section><\/section>\n<ol>\n<li>\n<section>\u76f4\u63a5\u7406\u89e3\u6df1\u5ea6\u56fe\uff0c\u8ba9\u6a21\u578b\u770b\u6df1\u5ea6\u56fe\uff0c\u5206\u6790\u6df1\u5ea6\u7684\u5206\u5e03\uff0c\u731c\u6d4b\u5176\u4e2d\u53ef\u80fd\u5305\u542b\u7684\u7269\u4f53\uff1b\u00a0<\/section>\n<\/li>\n<li>\n<section>\u7a7a\u95f4\u5173\u7cfb\u7406\u89e3\u548c\u63a8\u7406\uff1b<\/section>\n<\/li>\n<li>\n<section>\u673a\u5668\u4eba\u573a\u666f\u7406\u89e3\uff1a\u63cf\u8ff0 Open X-Embodiment \u548c\u672c\u6587\u6536\u96c6\u7684\u673a\u5668\u4eba\u6570\u636e\u4e2d\u7684\u573a\u666f\u3001\u5305\u542b\u7684\u7269\u4f53\u3001\u53ef\u80fd\u7684\u4efb\u52a1\uff0c\u5e76\u4eba\u5de5\u6807\u6ce8\u7269\u4f53\u3001\u673a\u5668\u4eba\u7684 bounding box\u3002<\/section>\n<\/li>\n<\/ol>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-c39af959e2252f0fa7ac3694a2ea1f47.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-c39af959e2252f0fa7ac3694a2ea1f47.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0\u7a7a\u95f4\u5173\u7cfb\u7406\u89e3<\/sup><\/em><\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-8125a0c01818f962668d9477c6025b77.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-8125a0c01818f962668d9477c6025b77.png\"><\/a><\/p>\n<section><em><sup>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0Open X-Embodiment \u673a\u5668\u4eba\u573a\u666f\u7406\u89e3<\/sup><\/em><\/section>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-197304272e818c1c9fa8b6a620c7f6ef.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-197304272e818c1c9fa8b6a620c7f6ef.png\"><\/a><\/p>\n<section><em><sup>\u6df1\u5ea6\u56fe\u7406\u89e3\u3002\u5728\u4f7f\u7528 GPT \u6807\u6ce8\u8fd9\u90e8\u5206\u6570\u636e\u65f6\uff0cGPT \u4f1a\u5148\u770b\u5230\u6df1\u5ea6\u56fe\uff0c\u63cf\u8ff0\u6df1\u5ea6\u56fe\u3001\u63a8\u7406\u5176\u4e2d\u53ef\u80fd\u5305\u542b\u7684\u573a\u666f\u548c\u7269\u4f53\uff0c\u7136\u540e\u770b\u5230 RGB \u56fe\uff0c\u7b5b\u9009\u51fa\u6b63\u786e\u7684\u63cf\u8ff0\u548c\u63a8\u7406\u3002<\/sup><\/em><\/section>\n<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-08-07-2\" target=\"_blank\">\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[27],"tags":[70,73,68],"class_list":["post-34980","post","type-post","status-publish","format-standard","hentry","category-news","tag-agent","tag-73","tag-68"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot - \u4e00\u8d77AI\u6280\u672f<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/17aitech.com\/?p=34980\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/17aitech.com\/?p=34980\",\"url\":\"https:\/\/17aitech.com\/?p=34980\",\"name\":\"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot - \u4e00\u8d77AI\u6280\u672f\",\"isPartOf\":{\"@id\":\"https:\/\/17aitech.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/17aitech.com\/?p=34980#primaryimage\"},\"image\":{\"@id\":\"https:\/\/17aitech.com\/?p=34980#primaryimage\"},\"thumbnailUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png\",\"datePublished\":\"2024-12-16T00:58:49+00:00\",\"author\":{\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d\"},\"breadcrumb\":{\"@id\":\"https:\/\/17aitech.com\/?p=34980#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/17aitech.com\/?p=34980\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/?p=34980#primaryimage\",\"url\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png\",\"contentUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/17aitech.com\/?p=34980#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/17aitech.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/17aitech.com\/#website\",\"url\":\"https:\/\/17aitech.com\/\",\"name\":\"\u4e00\u8d77AI\u6280\u672f\",\"description\":\"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca\",\"alternateName\":\"\u4e00\u8d77AI\u6280\u672f\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/17aitech.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d\",\"name\":\"AI\u5c0f\u52a9\u624b\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/image\/\",\"url\":\"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png\",\"contentUrl\":\"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png\",\"caption\":\"AI\u5c0f\u52a9\u624b\"},\"description\":\"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e\",\"url\":\"https:\/\/17aitech.com\/?page_id=33738&user=3\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot - \u4e00\u8d77AI\u6280\u672f","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/17aitech.com\/?p=34980","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/17aitech.com\/?p=34980","url":"https:\/\/17aitech.com\/?p=34980","name":"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot - \u4e00\u8d77AI\u6280\u672f","isPartOf":{"@id":"https:\/\/17aitech.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/17aitech.com\/?p=34980#primaryimage"},"image":{"@id":"https:\/\/17aitech.com\/?p=34980#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png","datePublished":"2024-12-16T00:58:49+00:00","author":{"@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d"},"breadcrumb":{"@id":"https:\/\/17aitech.com\/?p=34980#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/17aitech.com\/?p=34980"]}]},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/?p=34980#primaryimage","url":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png","contentUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/08\/frc-7dbe163334a1157f948b090c6398e5b4.png"},{"@type":"BreadcrumbList","@id":"https:\/\/17aitech.com\/?p=34980#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/17aitech.com\/"},{"@type":"ListItem","position":2,"name":"\u674e\u98de\u98de\u300c\u7a7a\u95f4\u667a\u80fd\u300d\u4e4b\u540e\uff0c\u4e0a\u4ea4\u3001\u667a\u6e90\u3001\u5317\u5927\u7b49\u63d0\u51fa\u7a7a\u95f4\u5927\u6a21\u578bSpatialBot"}]},{"@type":"WebSite","@id":"https:\/\/17aitech.com\/#website","url":"https:\/\/17aitech.com\/","name":"\u4e00\u8d77AI\u6280\u672f","description":"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca","alternateName":"\u4e00\u8d77AI\u6280\u672f","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/17aitech.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d","name":"AI\u5c0f\u52a9\u624b","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/#\/schema\/person\/image\/","url":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","contentUrl":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","caption":"AI\u5c0f\u52a9\u624b"},"description":"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e","url":"https:\/\/17aitech.com\/?page_id=33738&user=3"}]}},"_links":{"self":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/34980","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=34980"}],"version-history":[{"count":0,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/34980\/revisions"}],"wp:attachment":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=34980"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=34980"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=34980"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}