Embodied intelligence represents a rapidly emerging paradigm in robotics where intelligent behaviour arises through the integration of perception, decision-making, action, and interaction within a physical agent operating in the real world. Advances in autonomous robotics, computer vision, sensor fusion, and human-robot interaction have enabled mobile robotic systems to perform increasingly sophisticated tasks in dynamic environments. Quadruped robots, in particular, offer superior mobility and adaptability compared to traditional wheeled platforms, making them well-suited for navigating complex indoor and outdoor environments.

This project investigates the development of an embodied intelligent campus assistant using a quadruped robotic platform. The robot will be capable of perceiving its surroundings, understanding environmental context, navigating autonomously, and interacting naturally with users within a university campus environment. The project will explore the integration of perception, mapping, localization, navigation, and human-robot interaction capabilities to create an autonomous robotic assistant capable of supporting campus visitors, students, and staff.

Using the Unitree Go2 quadruped robot as the experimental platform, students will design and evaluate autonomous behaviours that enable the robot to perform assistance tasks such as campus guidance, user engagement, environmental monitoring, and information delivery. The project will involve real-world deployment and evaluation within campus environments, providing valuable insights into the practical challenges and opportunities of embodied intelligence systems.