Users are praising ETH researchers' humanoid robot locomotion work for rough terrain parkour because it highlights impressive student growth and technical achievements.
This work came from a fruitful collaboration between @SFU and @leggedrobotics @ETH_en, supported by Michael Xu @mxu_cg, Junzhe He @JayHe748646, Chenhao Li @breadli428, Takahiro Miki @ki_ki_ki1, Clemens Schwarke, Chong Zhang @ChongZzZhang, Xue Bin Peng @xbpeng4, Marco Hutter.
Watching my students Zewei @ctki49 and Kehan @KehanWen170077 grow into independent researchers and experts in humanoid locomotion has been the most rewarding part of this project — every bit as gratifying as the technical results. Couldn't be prouder of them. 👏
@breadli428 @SFU @leggedrobotics @ETH_en @mxu_cg @JayHe748646 @ki_ki_ki1 @ChongZzZhang @xbpeng4 Nice work as always!
@breadli428 🆒 ☑️
@breadli428 Reminds me of this paper on getting robot dogs to do parkour. Went from dogs to humanoids real quick! https://sites.google.com/leggedrobotics.com/agile-navigation
@breadli428 The slight leaning backwards is intentional to maintain CG?
@jack_polloway The techniques are quite different tho. The dog operated on a fixed set of skills while the humanoid needs adaptive references to be generated on the fly.
@DevRajyagu18621 Nope, that’s the bias from the initial reference dataset