Skip to content

Official Implementation of "KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills", tartgeted at g1 robot with SINGLE joint on WAIST as 'waist yaw joint'

active 2025-06-162026-07-02 (UTC)

Partial coverage11,254 / 11,982 hourly files (94%) · 2 absent upstream · 726 failed, retryable2025-03-292026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
636
Pushes
14
Pull requests
4
Issues
71
Stars
412
Forks
58

Activity over time

Daily event counts in the loaded window

Line chart, 382 days from 2025-06-16 to 2026-07-02. Pushes: 14 total, peak 3 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 71 total, peak 9 in a day. Comments: 75 total, peak 7 in a day. Stars: 412 total, peak 49 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue#80zhuangzx72026-05-21 06:12
    General Policy Training with LAFAN Dataset
  • Issue#75bwrooney822026-01-21 06:47
    Questions about reward curves
  • Issue comment#75bwrooney822026-01-21 06:47
    Questions about reward curves
  • Issue#76bwrooney822026-01-21 06:46
    Sim2real中遇到的报错
  • Issue#74kevinlhw11112026-01-16 07:14
    MotionTracking Training训练后到sim2sim遇到问题
  • Issue comment#74bwrooney822026-01-16 04:53
    MotionTracking Training训练后到sim2sim遇到问题
  • Issue comment#37bwrooney822025-12-17 11:34
    Fix motion load bug
  • Issue#73amn7652025-12-11 08:45
    lack of module "smpl_sim"
  • Issue#73amn7652025-12-11 08:39
    lack of module "smpl_sim"
  • Issue comment#70Shi-Soul2025-12-06 16:15
    训练不收敛
  • Issue#71rotaku-12025-11-30 06:46
    PBHC交流群
  • Issue#70LPZliu2025-11-23 13:10
    训练不收敛
  • Issue comment#64Shi-Soul2025-11-15 14:49
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue comment#64Shi-Soul2025-11-14 23:09
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue comment#64lucasjinreal2025-11-14 09:54
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue comment#64lucasjinreal2025-11-14 08:23
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue comment#64lucasjinreal2025-11-13 01:06
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue#63Shi-Soul2025-11-12 18:45
    how to export jit.pt , not only onnx,
  • Issue comment#64Shi-Soul2025-11-12 18:33
    Deploy code cost 90ms while onnx infer only 0.1ms
  • Issue comment#67Shi-Soul2025-11-12 18:31
    Is it suitable for go2?
  • Issue comment#68bwrooney822025-11-06 15:30
    Bug: matrix_from_quat called with default w_last=False but input is w_last=True
  • Issue#65chenlockyer2025-11-05 09:19
    How to train policies for the G1 23dof ?我只有23自由度版本的G1,要怎么做才能适配
  • Issue#60learning-github-zgy2025-10-29 01:01
    Question about the released general controller and motion data format
  • Issue#60learning-github-zgy2025-10-28 09:42
    Question about the released general controller and motion data format
  • Issue#25Shi-Soul2025-10-28 08:47
    When playing the SMPL data in blender, the poses data is not processed correctly

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 412 stars here means stars gained during the window, not the repo's star count.