Traditional tokenization methods for robotic actions struggle with high-frequency, dexterous tasks…
@TheHumanoidHub11万 位关注者
26,198 次观看
7 条评论
评论来自 X (Twitter) 上的原帖

@TheHumanoidHub
More details in this thread:
17 个赞

@SeketAanru
Unveiling the Future of Prompt Engineering for Better AI Interactions #tech
1,508 个赞

@navuud
How does one build a laundry robot like this at home 😁
2 个赞

@BrianBellia
So, does this mean the end of teleoperation as a means of training humanoids? I hope it spells the end of teleoperation, period. At this stage, it should be autonomous or nothing - except in rare cases like Optimus catching a ball.
2 个赞

@TheHumanoidHub
The DROID dataset they using for training is generated with teleop
1 个赞

@PageLyndon
Give'm some practice. They will get better.
1 个赞

@rethynkai
Really like the way it put the 2nd on the top of the first. After intellectual capital, machines are getting better understanding of physical environment.
1 个赞