Downloads · 30 days
0
unitree-g1-stepdown-safety
arushbisht12/unitree-g1-stepdown-safety
unitree-g1-stepdown-safety is a reinforcement learning model from arushbisht12. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This model is a high-performance safety-first neural locomotion policy for the Unitree G1 Humanoid Robot, trained end-to-end with a 4-level terrain curriculum.
Access
Public
Updated Aug 30, 2026
Repo size
46.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.stl50.7 MB · 99%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- fd97d9ac
Model card
From the Hugging Face model README
End-to-End Safety Locomotion Policy for Unitree G1 Humanoid
This model is a high-performance safety-first neural locomotion policy for the Unitree G1 Humanoid Robot, trained end-to-end with a 4-level terrain curriculum.
Key Capabilities
- Dynamic Bipedal Walking: Learns natural stepping limit cycles via
feet_air_timerewards. - Rear-Leg CoM Anchoring: Stabilizes center of mass on the rear stance leg during edge traversal.
- Adaptive Step vs. Retraction:
- Drops $\le 12\text{ cm}$: Safely descends with compliant force loading onto the lower platform.
- Drops $> 12\text{ cm}$: Detects unsafe drop, halts forward momentum, pulls lead leg back, and maintains upright standing posture.
Deployment with sim.py / view_stepdown.py
# 1. Interactive 3D Viewer on Step-Down
mjpython view_stepdown.py --drop 0.08 --policy safety_motion.pt
# 2. Interactive 3D Viewer on Cliff (Retract & Hold)
mjpython view_stepdown.py --drop 0.20 --policy safety_motion.pt
# 3. Standard Simulation
python sim.py --policy safety_motion.pt
- Task
- Reinforcement Learning
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026