Introduce HumanPlus - Autonomous Skills part
@zipengfu13K followers
158,373 views
10 Comments
Comments from the original post on X (Twitter)

@zipengfu
We build our customized 33-DoF humanoid, and a data collection pipeline through real-time shadowing in the real world.
24 likes

@zipengfu
Using the data collected through shadowing, we then perform supervised behavior cloning to train skill policies using egocentric vision. We introduce Humanoid Imitation Transformer. Based on ACT, HIT adds forward dynamics prediction on image feature space as a regularization.
16 likes

@zipengfu
Compared to baselines, HIT uses - binocular vision, thus having implicit stereos for depth information - visual feedback better, avoiding overfitting to proprioception given small-sized demos
8 likes

@zipengfu
Besides vision-based whole-body manipulation skills, our humanoid has strong locomotion skills: - outperforming H1 default standing controller under strong perturbation forces - enabling more whole-body skills like squatting and jumping
6 likes

@zipengfu
This project is not possible without our team of experts, covering from computer graphics to robot learning to robot hardware: - co-leads: @qingqing_zhao_ @Qi_Wu577 - advisors: @chelseabfinn @GordonWetzstein project website: hardware: code:
31 likes

@hausman_k
Congrats @zipengfu !! 🎉
2 likes

@Yang_ML_Estate
Pretty cool!

@SirSloppyJoe
@DrDisrespect robodoc?

@botbot_ai
Wow! Incredible, is the demo unit the Unitree H1?

@LatentsExplored
@heyjchu