Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots
-
Updated
Oct 23, 2026 - Python
Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots
Agent native framework for robot learning with multi-physics
Codebase for Kinova Gen3 training in Isaac Lab, sim2real transfer and ROS deployment.
IsaacLab to Mujoco GO2 deploy, IsaacLab to Real world GO2 deploy
Deploying a quadruped robot policy(DreamWaQ, walk-these-ways, HIMLoco) trained in Isaacgym to ROS2 Gazebo for Sim-to-Sim
Automatic Domain Randomization (ADR) proposed in "Solving Rubik's Cube with a Robot Hand"
DDC (Deployable Dynamic-CoM): a unified policy and method-agnostic sim2sim benchmark for humanoid single-leg stance; deploys on a real Unitree G1. arXiv:2608.00500
Quadruped RL training: A1 with legged_gym (standing + velocity tracking) and custom robot integration with mjlab (12-DOF)
Deep Reinforcement Learning and Imitation Learning with sim2sim exploration and behavior cloning
Lightweight repo for getting started with learning to control the Unitree G1 humanoid robot with sim2sim (mujoco & isaac lab) and sim2real policy validation.
Repository created using https://github.com/google-deepmind/mujoco_playground as base in order to add the Go2 walking and handstand policies. It contains the code to train and simulate the policy.
Velocity tracking and sim-to-sim transfer for Unitree H1 humanoid locomotion using reinforcement learning.
find why a humanoid locomotion policy fails between simulators: contract, physics, or task. MuJoCo, CPU.
Human mocap retargeting and whole-body motion tracking for humanoids (Unitree G1, IGRIS-C) in Isaac Lab and MuJoCo. Simulation only.
NaVILA VLM navigation on the Booster K1: MuJoCo with my trained PPO walker, plus a relay used live on the real robot
Navegación autónoma basada en Redes Neuronales
DM-Dog-RL is a reinforcement-learning locomotion project for a Damiao-motor quadruped robot. It contains both the training stack and the real-robot ROS deployment workspace.
Sim2Sim RL for humanoid-robot: train locomotion policies with PPO (RSL-RL) in NVIDIA Isaac Sim / Isaac Lab, export them to ONNX, and validate the same policy in MuJoCo via an observation, joint-mapping and PD-control adapter. Demonstrated on the Unitree G1 29-DoF humanoid.
To associate your repository with the sim2sim topic, visit your repo's landing page and select "manage topics."