人形机器人全身运动规划相关资料与文章

1.HumanPlus: Humanoid Shadowing and Imitation from Humans

文章地址:[2406.10454] HumanPlus: Humanoid Shadowing and Imitation from Humans

代码地址:MarkFzp/humanplus: [CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans

其他相关参考资料: 斯坦福ALOHA机器人团队最新论文-HumanPlus: 从人类学习的人形机器人动作模仿和自主操作-优快云博客

 HumanPlus(斯坦福人形机器人)的代码解读与复现关键:从HST到HIT、HardWare-优快云博客

2.Visual Whole-Body Control for Legged Loco-Manipulation

文章地址:[2403.16967] Visual Whole-Body Control for Legged Loco-Manipulation

代码地址: Ericonaldo/visual_wholebody: Train a loco-manipulation dog with RL

其他参考资料:读《Visual Whole-Body for Loco-Manipulation》①low_visual whole-body control for legged loco-manipula-优快云博客

 这个工程很好部署,CPU直接就可以运行:

python train.py  --exptid SOME_YOUR_DESCRIPTION --proj_name b1z1-low --task b1z1 --sim_device=cpu  --rl_device=cpu  --observe_gait_commands

GPU运行:

python train.py  --exptid SOME_YOUR_DESCRIPTION --proj_name b1z1-low --task b1z1 --sim_device cuda:0 --rl_device cuda:0 --observe_gait_commands

具体输入参数设置:

⚙️ Parameter Description
  • --task: Required parameter; values can be (go2, g1, h1, h1_2).
  • --headless: Defaults to starting with a graphical interface; set to true for headless mode (higher efficiency).
  • --resume: Resume training from a checkpoint in the logs.
  • --experiment_name: Name of the experiment to run/load.
  • --run_name: Name of the run to execute/load.
  • --load_run: Name of the run to load; defaults to the latest run.
  • --checkpoint: Checkpoint number to load; defaults to the latest file.
  • --num_envs: Number of environments for parallel training.
  • --seed: Random seed.
  • --max_iterations: Maximum number of training iterations.
  • --sim_device: Simulation computation device; specify CPU as --sim_device=cpu.
  • --rl_device: Reinforcement learning computation device; specify CPU as --rl_device=cpu.

Default Training Result Directorylogs/<experiment_name>/<date_time>_<run_name>/model_<iteration>.pt

3. 宇树人形机器人isaac_gym仿真工程地址:unitreerobotics/unitree_rl_gym

4.傅里叶机器人:lufhttps://github.com/FFTAI/Wiki-GRx-Gazeboicon-default.png?t=O83Ahttps://github.com/FFTAI/Wiki-GRx-Gazebo

参考资料:

https://www.zhihu.com/question/652648522/answer/3588978808icon-default.png?t=O83Ahttps://www.zhihu.com/question/652648522/answer/3588978808

5.智元机器人: https://github.com/AgibotTech/agibot_x1_train

参考资料:https://zhuanlan.zhihu.com/p/6967843177

6.Alexbotmini/3_Walk and trot/humanoid-gym at main · Alexhuge1/Alexbotmini

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值