s1ddh-rth/HumanoidClimb-RL

This project explores the application of reinforcement learning (RL) to train humanoid robots for dynamic rock climbing movements, focusing on achieving the challenging "dyno" maneuver. Using the Proximal Policy Optimization (PPO) algorithm, the simulation integrates physics-based environments to model realistic climbing scenarios.

12
/ 100
Experimental

This project helps robotics researchers and engineers train humanoid robots to perform complex rock climbing movements, specifically dynamic transfers known as 'dynos.' You input simulation parameters for a climbing environment, and it outputs trained models that dictate how a virtual humanoid robot moves its limbs to climb. This is for researchers developing advanced robotic control systems for bipedal or multi-limbed robots.

No commits in the last 6 months.

Use this if you are a robotics researcher aiming to develop and evaluate reinforcement learning algorithms for dynamic, multi-limb robotic locomotion in complex environments.

Not ideal if you need a plug-and-play solution for real-world robot deployment or if your focus is on static stability rather than dynamic movement.

robotics reinforcement-learning-research motion-planning humanoid-control climbing-robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Last pushed

Oct 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/s1ddh-rth/HumanoidClimb-RL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.