Course Community

In this Tutorial we will learn how to make a Niryo Robot able to recognize objects it has never seen
before. To perform that, we will create an AI model based on the open source pre trained YOLO
model. We will therefore train our own model from this base with a custom dataset. Then we will
deploy this model to the Niryo Robot.

The project uses ROS Noetic to orchestrate communication between Turtlebot 3, NED 2 by Niryo, and a host PC. It incorporates:

• ArUco marker-based localization

• Color-based lane detection with OpenCV

• Visual servoing with NED 2

• Coordinated pick-and-place and navigation

This project aims to develop an industrial automation system leveraging artificial intelligence (AI) and robotic arms to enhance efficiency in vertical logistics and storage in an industrial application. The primary goal is to implement through AI robots with real-time decision-making capabilities, optimizing handling, sorting, and storage operations. The proposed solution is meant to increase productivity, reduce errors, and optimize the utilization of available space.

The available materials include Siemens ET200SP PLC, Siemens TP700 Comfort Human-Machine Interface (HMI), Niryo NED 2 robotic arm, a conveyor system, Jetson Nano with a camera, and a small-scale model for vertical storage

Ce projet a pour but de concevoir un bras robotique automatisé à 6 axes, capable de trier des déchets en temps réel grâce à l’intelligence artificielle. Il répond à des problématiques écologiques et industrielles en combinant robotique, vision par ordinateur et automatisation intelligente.

This project enables the Niryo robot Ned2 to play a game of chess against a human player. It explains the process of making the board and pieces needed for the robot to play. Then the environment setup will be explained as well as how the code runs.

The full project with all the codes and files is available here.

A modular pick-and-place sorting system for the Niryo Ned2 robot that can sort objects by colour (red, green, blue) into separate zones.

• Modular Design: Easy to add or remove functionalities
• Color-based Sorting: Sorts red, green, and blue objects into separate zones
• Multiple Sorting Modes:
  • Continuous sorting
  • Batch sorting with target counts
  • Single object sorting
• Comprehensive Statistics: Track sorting performance
• Error Handling: Robust error handling and recovery
• Safety Features: Automatic calibration and safe shutdown

You can find more about the project here.

Projet de tri automatisé Industrie 4.0 : un système de pick & place trie les pièces par couleur dans des zones de dépose imprimées en 3D, met au rebut les pièces carrées et assure le suivi via base de données et tableau de bord interactif.

A showcase of undergraduate robotics projects featuring the Ned2, from gesture-controlled manipulation to digital twins, chess-playing robots, and multi-robot production lines.

We will use Python programming to send commands to the robotic arm. > In this exercise, the Ned2 robotic arm will perform a pick-and-place operation using text recognition.