STEM Project via Robot Dog with Agentic AI

About

This initiative integrates Agentic AI with a quadruped robot dog to create a hands-on STEM learning experience, allowing students to apply abstract concepts in a physical environment. The solution integrates Agentic AI for autonomous decision-making using  LLM-based planning. It utilises quadruped hardware ( Unitree Go2 Edu) equipped with sensors and controllers. The software stack includes Python and ROS for simulation and deployment, processing sensor data for navigation and obstacle avoidance.

Features

  • Hands-On Robotics: Facilitates STEM learning through direct interaction with robotic hardware.

  • Practical Application: Encourages the application of theoretical concepts in real-world scenarios.

  • Voice & AI Control: Features multi-level AI integration, including voice control and autonomous navigation.

Video

Latest Exemplars & Use Cases

Assessment: Cloze Test Generation

Assessment: Cloze Test Generation

, ,

This system utilises multi-agent collaboration to automatically source and check content from the web and generate cloze (fill-in-the-blank) tests, publishing them with learning management systems (LMS). It employs a multi-agent workflow in which one agent handles...

read more
Chinese Composition Assessment

Chinese Composition Assessment

, ,

This solution analyses photos of handwritten Chinese compositions to provide scores and feedback based on teacher-configurable rubrics. The technical core combines Optical Character Recognition (OCR) with LLMs for text extraction. A multi-agent system separates...

read more