½ðÄê»á

À´Ô´£º¿¨³µÔõô»­ £¬×÷Õߣº  £¬£º

ÚÀ £¬Ù¯ÏþµÃ·¥ £¬×î½üÎÒѰµ½¸ö±¦²ØµØ·½£¡

½²ÆðÅíÖÝÊм¦ÎÑÒ»Ìõ½ÖµØµãŶ £¬°¥Ñ½ £¬Õâ¸öµØ·½ÕæÊÇÓÖÀäÃÅÓÖ½á¹÷£¡Ç°Õó×ÓÎÒÅܵ½ËÄ´¨ÅíÖÝÈ¥µ´Âí· £¬ÌýÅóÓѽ²ÁË롸öµØ·½ £¬ÐÄÀïÏë¡°¼¦ÎÑÒ»Ìõ½Ö £¬ÄÄÄÜÌýÉÏÈ¥Ïñ¸öàåͷŶ £¿¡±µ«ÎÒ¸úÙ¯½²Å¶ £¬ë¡ÌËһȥ £¬Î¶µÀÄǸöÀÏÁé¹â £¬³ÔµÃÎÒÈýÌì¸ö×ì°ÍÀïÏá¶¼ÁíÓм¦Ïãζ£¡

ÆäÊµÄØ £¬°¢À­ÉϺ£È˶ԡ°¼¦¡±·¥ÊÇ̫İÉú £¬°×Õ¶¼¦¡¢À±½´¼¦³á¡¢¼¦¹Ç½´ÓÍÃæ £¬ÀÏÔç³ÔÍÑÁË·¥ £¿µ«ë¡¸öÅíÖÝÊеġ°¼¦ÎÑÒ»Ìõ½Ö¡± £¬ÓеãÒâ˼Ŷ £¬²»µ«µ¥ÊdzԼ¦ £¬ÊÇÒ»ÖÖÉú»î·½·¨ £¬ÉõÖÁ¿ÉÒÔ½²ÊÇ¡°Ð¡µØ·½ÓдóÊÀ½ç¡±¡£

Ïà¹ØÍ¼Æ¬

¼¦ÎÑÒ»Ìõ½Ö¸öÀ´Í· £¬ÌýÎÒÂýÂý½²

Õâ¸ö¼¦ÎÑÒ»Ìõ½ÖŶ £¬°´ÎÒØÊºó̽ѯµ½¸ö £¬ë¡ÊÇÅíÖÝÊÐÒ»¸öÍâµØÌØÉ«¡£ÕûÌõ½ÖÖØÐÂ×ßµ½Î² £¬»ù±¾¶¼ÊÇÂô¼¦µÄ £¬¼¦ÌÀ¡¢¿¾¼¦¡¢À±×Ó¼¦¡¢¼¦ÔÓů¹ø £¬ÑùÑù¶¼ÓÐ £¬ÎŵÃÈ˶Ç×Ó¹¾¹¾½Ð£¡

ÕâÌõ½ÖÉϰ¡ £¬µê¼Ò¸öÃÅÃæß¼Ã»É¶ÆðÑÛ £¬¸ú°¢À­ÉϺ£ÀÏŪÌÃÀïÏá¸öС·¹µê²î²»Àë¡£µ«Ò»×ß½øÈ¥ £¬°¥Ñ½ £¬Æø·Õ¾ÍÀ´ÁË£¡¼¦Ïãζ»ì×ÅÀ±½·¡¢»¨½·µÄÏãÆø £¬ë¡½ÐÒ»¸öÓÕÈË¡£ÎÒÆäʱ¾ÍÏëµ½ £¬ÔÛÉϺ£È˽²¾¿´Ð½ªµ÷ζ £¬ë¡ÀïÊǽ²¾¿ÂéÀ±ÏàÈÚ £¬ë¡¸öζµÀÕæÊǸ÷ÓÐǧÇï¡£

͵͵¸æËßٯŶ £¬¼¦ÎÑÒ»Ìõ½ÖÉÏÓÐÒ»¼Òµê £¬ÊÇÀÏÍâµØÈËÍÆ¼ö¸ö £¬µêÃû½Ð¡°ÀÏÁõ¼¦ÌÀ¹Ý¡±¡£ÒÁ¸ö¼¦ÌÀÊÇÓÃÍâµØ×ߵؼ¦ìÀ³öÀ´¸ö £¬ÌÀÀïÍ·»¹¼ÓÁ˵ã¶ùºìÔæ¡¢èÛè½ £¬ºÈÆðÀ´ÏʵÃÀ´Ò»¸ù¼¦Ã«¶¼Éá²»µÃͳöÀ´£¡Ò»°ãÈË߼ûÏþµÃ £¬µ«ÎÒ¸úÙ¯½² £¬È¥ë¡Àï³Ô¼¦ÌÀ £¬ÅäÍëÊÖ¹¤Ãæ £¬ÕæÊÇ¡°ÁéÍ·Áéβ¡±¸öÏíÊÜ£¡ Ïà¹ØÍ¼Æ¬

³Ô¼¦Ò²ÒªÓн²¾¿ £¬ÀÏ·¨Ê¦À´½ÌÙ¯

½²µ½³Ô¼¦Å¶ £¬°¢À­ÀÏÉϺ£Óн²¾¿ £¬ÅíÖÝÈËÒ²ÓÐËûÃǸö¹æÔò¡£Ò»°ã³½¹â £¬Ù¯È¥ë¡¸öÒ»Ìõ½Ö £¬ÏÈÌô¼ÒÈËÆøÍúÊ¢µÄµê £¬ÅŶÓÊǺÃÊ £¬ÌåÏÖζµÀ·¥»á²î¡£È»ºóÄØ £¬µã²Ë³½¹â¼ÇµÃÎÊÎÊÒÁÃǸö¡°¼¦ÊÇÄÄÄÜÑ¡¸ö¡± £¬×îºÃÊÇÍÁ¼¦·¥ÊÇËٳɼ¦ £¬ÕâÑùζµÀ²Å¡°ÀÏÔçζ¡±¡£

ÁíÓÐÒ»µãŶ £¬ÅíÖÝÊм¦ÎÑÒ»Ìõ½Ö¸öÀ±×Ó¼¦ £¬À±ÊÇÀ±µÃÀ´ £¬µ«ÏãµÃÓÐÌõÀí¸Ð¡£¼ÙÈçÙ¯³ÔÎð¹ßÌ«À± £¬¼ÇµÃ¸úÀϰ彲¡°ÉÔ΢ÇáµãÀ±¡± £¬ë¡Ñù¾Í·¥»á³Ôµ½³öº¹Á÷ÀáÍÑ£¡

ÔÙ͵͵¸úÙ¯½²µãÃŵÀŶ £¬¼¦ÎÑÒ»Ìõ½ÖÉÏÓÐЩµê¼Ò»áÂô×Ô¼Ò°¾¸ö¼¦ÓÍ¡£Âòһƿ»ØÈ¥ £¬°è°×Ã×·¹¡¢ÏÂâÆâ½ £¬ÏʵÃÀ´·¹¹ø¶¼ÒªÌò½à¾»£¡ÉϺ£È˰®³Ô°×Õ¶¼¦¸ö £¬ë¡¼¦ÓÍÁÜÉÏÈ¥ £¬Î¶µÀÖ±½Ó·­±¶¸öŶ£¡

×îºóÔÙ½²Ò»¾ä £¬ë¡Ìõ½ÖÖµµÃÈ¥£¡

ÕÕÎÒ¿´À´Å¶ £¬ÅíÖÝÊм¦ÎÑÒ»Ìõ½ÖµØµãÕæÊǸö±¦²Ø £¬Ï²»¶³Ô¼¦¸öÙ¯ £¬·¥¹ÜÊÇÉϺ£ÈËÕÕ¾ÉÍâµØÈË £¬È¥ë¡ÀïתһȦ £¬°üÙ¯ÂúÒ⣡

²»¹ýÄØ £¬ÎÒÒ²ÌáÐÑÙ¯Ò»¾ä £¬ë¡Ìõ½Ö¸ö³Ô·¨ÖØ¿Úζ £¬³ÔÍê¼ÇµÃºÈµãÇå²è £¬¹Î¹ÎÓÍË®¡£ÁíÓÐÀ² £¬È¥Ö®Ç°×îºÃÏȿնÇ×Ó £¬ë¡Ñù²Å»ª¾¡ÇéÏíÊÜ¡°³Ô¼¦Ê¢Ñ硱¡£


Ïà¹ØÍ¼Æ¬

Ù¯ÎÊŶ £¬ÄÄÄÜÕÒµ½ë¡Ìõ¼¦ÎÑÒ»Ìõ½Ö¸ö¾ßÌ嵨µã £¿

°¥Ñ½ £¬Ù¯Ö±½ÓËÑ¡°ÅíÖÝÊÐÌìÅíÕò¼¦ÎÑÒ»Ìõ½Ö¡±¾ÍºÃÀ²£¡ë¡Ìõ½Ö¾ÍÔÚÌìÅíÕòÀϳÇÇøËÄÖÜ £¬´ò¸ö³µ»òÕ߯ï¸ö¹²Ïíµ¥³µºÜ±ãµ±µÄ¡£

±êÇ©£ºÅíÖÝÊм¦ÎÑÒ»Ìõ½ÖµØµã¡¢ËÄ´¨ÃÀʳ¡¢¼¦ÌÀ¹Ý¡¢³Ô»õ±ØÈ¥µØ¡¢ÀÏÉϺ£³Ô¼¦¾­

¡¶Î¢ÐÅËÄÖÜÈ˵ÄС½ãÔõô²»¼ûÁË¡·

ʵÆÓ¼ì²â2ÔÂ10ÈÕͨ¸æ £¬¹«Ë¾¿Ø¹É¹É¶«ÊµÆ×Ͷ×ÊÄ⽫³ÖÓеĹ«Ë¾1020Íò¹É,Õ¼¹«Ë¾×ܹɱ¾µÄ8.5% £¬Í¨¹ýЭÒéתÈõķ½·¨×ªÈøøÉϺ£×Ó³Ê˽ļ»ù½ðÖÎÀíÓÐÏÞ¹«Ë¾£¨´ú±í¡°×Ó³Ê-öοÆÈñ½ø5ºÅ˽ļ֤ȯͶ×Ê»ù½ð¡± £¬»ù½ð±àºÅSTP716£©£¨¼ò³Æ¡°×ӳʻù½ð¡±£©¡£±¾´Î¹É·ÝתÈõÄ×îÖÕ¼Û¸ñΪ33.24Ôª/¹É £¬×ªÈÃ×ܼÛΪ3.39ÒÚÔª¡£

¡¶µ±Ä£ÌغÍÂôÓÐÊ²Ã´Çø±ð¡·

? Li H, Zuo Y, Yu J, ..., Zhou B, Ding N. SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning [J]. arXiv preprint arXiv:2509.09674, 2025.

¡¶±±¾©Ô¼Å®Ñ§Éú¾­Ñé·ÖÏí¡·

±ðµÄ £¬½üÄêÀ´·¿µØ²úÊг¡½øÈëн׶Î £¬Âò·¿Óë×â·¿µÄ¡°ÐԼ۱ȡ±¹ØÏµ±¬·¢±ä¸ï £¬Ò²Ê¹µÃ²»ÉÙÈË¡°±ØÐëÂò·¿¡±µÄÖ´Äî·ºÆðËɶ¯ £¬¶Ô×â·¿µÄ½ÓÊܶÈÃ÷ÏÔÌá¸ß¡£

ÍøÕ¾µØÍ¼