PHC
PHC copied to clipboard
Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars
I found that the results trained in H2O suffer from joint jitter, while this issue does not appear in PHC. Is it possible to distill the training results from PHC...
Thank you for your work. I have encountered some issues during the reproduction process. How to correctly convert the AMASS dataset into G1 data. The conversion process is stuck at...
Thank you for your work! But there is something confusing me that In the python file `video_to_pose_server.py`, you create global variable `pose_mat` but never update it. For `pose_getter`, you send...
I install this resiposity follow the README.md and download all file, but run every example has the error of "from uhc.smpllib.smpl_local_robot import SMPL_Robot ModuleNotFoundError: No module named 'uhc'" and i...
Hi, the filter_ints for the self_collision is currently hard-coded as below: As I need to change from the PHC-provided unitree G1 urdf to the official urdf, this filter ints list...
Thank you for your excellent work on Perpetual Humanoid Control (PHC) and for continuously updating it. It’s impressive to see that PHC now supports Unitree H1 and G1 robots, along...
Hi!Very good work.!I would like to ask how the model HumanoidIm/phc_kp_pnn_iccv/Humanoid.pth used for language control is trained? I used the provided command line but got the wrong number of mlp...
A kind reminder: there is an op in phc/env/tasks/humanoid.py line 1179: self.p_gains, self.d_gains = to_torch(self.p_gains), to_torch(self.d_gains) this op changes the device to "cuda:0", which could cause a bug when "cuda:0"...