PHC
PHC copied to clipboard
Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars
Hi! Thanks for the great work. I was trying to test the isaaclab evaluation in your provided code, but found out that there is no `data/action_offset_smpl.pkl` file for now. Can...
Hi, I would like to know how to adjust if I want to achieve real-time tracking on other humanoid robots.
我没梯子,访问不了https://drive.google.com,请问有其他地址可以下载到测试文件sample_data/amass_isaac_standing_upright_slim.pkl么?
Hello,I want to use my own pkl or upload a video to get the motion, but when I use the video_demo and upload my video I only get the first...
Hi ZhengyiLuo, First, thanks for releasing the code. I trained and evaluated H1 with the following commands: the train command: ``` python phc/run_hydra.py \ project_name=Robot_IM \ robot=unitree_h1 \ env=env_im_h1_phc env.motion_file=sample_data/sample_dance_h1.pkl...
I found the pred_pos , but translation data is missing, is there any way to get it? 
In `load_motion_with_skeleton`, when `target_heading` is provided, the motion's global orientation becomes incorrect. ```python if not target_heading is None: start_root_rot = sRot.from_rotvec(pose_aa[0, 0]) heading_inv_rot = sRot.from_quat(torch_utils.calc_heading_quat_inv(torch.from_numpy(start_root_rot.as_quat()[None, ]))) heading_delta = sRot.from_quat(target_heading) *...
Hi, this is a great work! May I ask how I can save the simulation results as a video? My remote server doesn’t have a GUI. Thanks.