Giter VIP home page Giter VIP logo

ian-chuang / homestri-ur5e-rl Goto Github PK

View Code? Open in Web Editor NEW
13.0 1.0 1.0 9.31 MB

A Mujoco Gymnasium Environment for manipulating flexible objects with a UR5e robot arm and Robotiq 2F-85 gripper. Experiment with joint effort, velocity, position, and operational space controllers. Teleoperate in task space and visualize in GUI. Note: Experimental, not actively maintained.

Python 100.00%
gymnasium mujoco robotiq-2f-85-gripper teleoperation ur5e joint-effort-controller joint-position-controller joint-velocity-controller operational-space-controller

homestri-ur5e-rl's Introduction

homestri-ur5e-rl

Welcome to the homestri-ur5e-rl repository! This repository provides a Mujoco Gymnasium Environment designed for manipulating flexible objects using a UR5e robot arm and a Robotiq 2F-85 gripper.

Robot Manipulation

Overview

The key features of this repository are:

  • Mujoco Simulation: The repository contains an example Mujoco XML configuration featuring a UR5e robot arm with an attached Robotiq 2F-85 gripper. This setup allows the robot to interact with a flexible cable in a simulated environment.

  • Gymnasium Integration: The environment is seamlessly integrated into the Gymnasium framework and comes with a graphical user interface (GUI) that visualizes the Mujoco simulation. This GUI provides an interactive way to observe the robot's actions and interactions.

  • Controller Variety: The UR5e robot arm offers multiple controller options, enabling various modes of control, including:

    • Joint effort controller
    • Joint velocity controller
    • Joint position controller
    • Operational space controller
  • Teleoperation: For manual control, keyboard input is supported, allowing teleoperation of the robot in task space. This can be particularly useful for specific tasks that require direct human intervention.

Repository Information

Please note the following details about this repository:

Installation

Follow these steps to set up the environment:

  1. Clone the repository:

    git clone https://github.com/ian-chuang/homestri-ur5e-rl.git
    
  2. Navigate to the repository directory:

    cd homestri-ur5e-rl
    
  3. Install the required packages using pip:

    pip install -e .
    

Testing the Environment

To test the environment, you can execute the following command:

python scripts/test_base_robot_env.py

Feel free to explore and experiment with the capabilities of the homestri-ur5e-rl environment. Keep in mind that this repository is an experimental project and might not receive regular updates. If you encounter issues or have questions, refer to the repository or seek support from the developer community.

homestri-ur5e-rl's People

Contributors

ian-chuang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

bit-xlj

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.