Parkour

Visit Tool

Parkour is an open-source project focused on robot parkour learning, providing resources and code for training robots. It includes an Isaac Gym environment and configuration files for simulation and hardware deployment.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is parkour?

Parkour is an open-source project that facilitates robot parkour learning, offering comprehensive resources and code for training robots. Developed by Ziwen Zhuang and others, it was presented at CoRL 2023 and received a Best Systems Paper Award Finalist recognition. The repository structure includes `legged_gym` for the Isaac Gym environment and config files, and `rsl_rl` for network modules and algorithm implementation. It supports training in simulation for robots like A1 and Go2, and provides instructions for hardware deployment on Unitree Go1 and Go2 robots. The project is valuable for researchers and developers in robotics and AI interested in advanced robot locomotion and reinforcement learning.

Best used for

Ideal for developers who need to research and implement advanced robot locomotion, simulate complex parkour behaviors, and deploy trained models onto physical robots like Unitree Go1 and Go2. Especially valuable for academic research and development in robotics and AI.

Common actions

train robot locomotion

simulate robot behavior

deploy robot policies

develop reinforcement learning models

face swappinggithub copilotdeepfake"AI Agents"collaborationopen-sourcelow-code/no-codeautomated workflowworkflows

Capabilities

Key features

Isaac Gym environment
Robot training configurations
Network module implementation
Algorithm implementation
Hardware deployment guides
Terrain generation code

Target Audience

developer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What robots are supported by the Parkour project?

The Parkour project explicitly supports training and deployment for Unitree Go1 and Go2 robots. It also mentions A1 training configurations, making it versatile for various quadrupedal robots in research and development.

What is the primary purpose of the `legged_gym` and `rsl_rl` folders?

The `legged_gym` folder contains the Isaac Gym environment and configuration files necessary for simulation and training. The `rsl_rl` folder houses the network module and algorithm implementations, which can be directly copied for robot deployment.

How can I deploy trained models on hardware?

The project provides specific instructions for hardware deployment. For Unitree Go1, refer to `Deploy-Go1.md`, and for Unitree Go2, follow the instructions in `Deploy-Go2.md`. These guides detail the steps required to transfer and run your trained policies.

Trending

Subcategories trending in Coding & Development

Open Source & Models Code Assistants No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce