cagataydev2026cc-by-4.0-generated-with-nvidia-isaac
Unitree Go2 quadruped rough-terrain locomotion (Isaac Lab, recorded with strands-robots)
A PPO policy trained in NVIDIA Isaac Lab controls a 12-DoF Unitree Go2 quadruped walking over procedurally generated rough terrain while tracking commanded base velocity. The policy rollouts were recorded as a LeRobot v3 dataset containing 12 episodes at 50 fps.
Downloads79
Episodes12
Hours0.0333
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- Unitree Go2
- Action Space
- 12-DoF: joint_pos.FL_hip_joint, joint_pos.FR_hip_joint, joint_pos.RL_hip_joint, joint_pos.RR_hip_joint, joint_pos.FL_thigh_joint, joint_pos.FR_thigh_joint, joint_pos.RL_thigh_joint, joint_pos.RR_thigh_joint, joint_pos.FL_calf_joint, joint_pos.FR_calf_joint, joint_pos.RL_calf_joint, joint_pos.RR_calf_joint
- Environment
- simulation
- Task Types
- locomotionterrain_navigation
- Episodes
- 12
- Total Hours
- 0.0333
- Data Format
- LeRobot
- License
- cc-by-4.0-generated-with-nvidia-isaac
Access
Need custom rgb data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack