weqwoueu / Isaac-Legged-LocomotionView on GitHub
本项目基于 **NVIDIA Omniverse / Isaac Lab** 大规模并行张量仿真框架,针对目前工业界最前沿的足式平台(**Unitree G1/H1 人形机器人, Unitree Go1 / ANYmal-C 机器狗**)进行了强化学习 (PPO) 步态策略的从零训练。项目深度介入了**域随机化 (Domain Randomization)** 与 **面向硬件的奖励塑形 (Hardware-Aware Reward Shaping)**,成功实现了机器人无需视觉输入、仅靠本体感觉(Proprioception)即可在崎岖地形(Rough Terrain)与极限冰面下保持动态平衡的鲁棒控制。
19Mar 4, 2026Updated 4 months ago

Alternatives and similar repositories for Isaac-Legged-Locomotion

Users that are interested in Isaac-Legged-Locomotion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?