Skip to content

Koumudi02/ml-robotics-workshop

 
 

Repository files navigation

Machine Learning for Robotics Workshop

Welcome to the Machine Learning for Robotics workshop! This self-paced program will guide you through 10 exciting levels where you will learn to apply machine learning techniques to robotics. Complete all levels and a mini-project to earn your certificate.


Workshop Overview

What You Will Learn

  • Foundational concepts of robotics and machine learning (ML).
  • Hands-on experience with tools like Python, OpenCV, TensorFlow, and ROS.
  • Practical applications like computer vision, reinforcement learning, and SLAM.
  • Building an end-to-end robot simulation integrating ML techniques.

How It Works

  • The workshop is divided into 10 levels, each hosted on its own GitHub folder.
  • Each level contains:
    • A README.md with objectives, resources, and tasks.
    • Code templates and datasets (if applicable).
  • Participants must complete the tasks and submit their solutions on GitHub.

Eligibility for Certification

To earn your certificate:

  1. Complete all 10 levels.
  2. Submit a mini-project that integrates the skills learned.
  3. Pass all submissions reviewed by mentors.

Getting Started

Step 1: Make sure that you are part of ML Robotics workshop channel.

  • All discussions, announcements, and Q&A will take place on our Discord server.
  • Make sure to:
    • Check the #announcements channel for updates.
    • Use level-specific channels (e.g., #level-1, #level-2) for queries.

Step 2: Fork and Clone the Repository

  1. Fork this repository to your GitHub account.
  2. Clone the repository to your local machine:
    git clone https://github.com/<your-username>/ml-robotics-workshop.git
  3. Navigate to the folder for your current level:
    cd ml-robotics-workshop/level-1

Step 3: Complete Each Level

  1. Read the objectives and tasks in the README.md file for the level.
  2. Follow the provided resources to complete the tasks.
  3. Submit your solutions as instructed in the level folder.

Step 4: Submit Your Work

  • Push your changes to your forked repository:
    git add .
    git commit -m "Completed Level X"
    git push origin main
  • Share the link to your repository in the #submissions channel on Discord.
  • Mentors will review your work and provide feedback.

Workshop Levels

Level Topic Key Skills
Level 1 Introduction to Robotics and ML Basics of ML and robotics
Level 2 Python Basics and Simulation Setup Python scripting, robot simulation setup
Level 3 Linear Algebra and Probability Mathematical foundations for robotics
Level 4 Computer Vision Basics Object detection and tracking
Level 5 Supervised Learning for Robotics Regression models, performance evaluation
Level 6 Reinforcement Learning Basics Q-learning, policy optimization
Level 7 Deep Learning Applications CNNs, object classification
Level 8 Path Planning and SLAM Navigation, mapping, A* algorithm
Level 9 Integrating NLP Voice-controlled robotics
Level 10 Mini-Project Full integration of concepts learned

Mini-Project Guidelines

  • Objective: Build a robot simulation that integrates navigation, object recognition, and voice commands.
  • Requirements:
    • Use a robot simulation platform like Gazebo or Webots.
    • Apply at least 3 concepts learned during the workshop.
    • Document your project with a README.md (overview, setup instructions, and demonstration).
  • Submission:
    • Upload your project to GitHub.
    • Share the repository link in the #mini-project-submissions channel on Discord.

Resources


Support and Queries

  • Join the discussion in the #discussion or level-specific channels on Discord.
  • Use the #help channel for technical questions.
  • Tag mentors or moderators for urgent assistance.

Let’s Get Started!

Dive into the exciting world of machine learning and robotics. We’re thrilled to have you on this journey. Good luck, and don’t hesitate to reach out for help!

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%