Course Code: AOT511
Synopsis
This course explores the intersection of computer vision and robotics, focusing on how machines perceive, interpret, and interact with their environment. Students will learn key concepts in image processing, object detection, sensor fusion, robotic perception, and autonomous navigation. Topics also include 3D reconstruction, human-robot collaboration, and the ethical implications of deploying intelligent systems. Practical applications are emphasised through case studies and hands-on exercises using real-world robotics and vision tools.
Level: 5
Credit Units: 5
Presentation Pattern: EVERY JAN
Topics
- Introduction to Computer Vision and Robotics
- Image Processing and Feature Extraction
- Camera Models and Calibration
- Object Detection and Classification
- Object Tracking and Motion Estimation
- Sensor Fusion for Robotic Perception
- Simultaneous Localisation and Mapping (SLAM)
- Path Planning and Vision-Based Navigation
- 3D Reconstruction and Scene Understanding
- Human-Robot Interaction (HRI)
- Augmented Reality (AR) and Mixed Reality Interfaces
- Ethics, Privacy, and Societal Impacts of Vision-Enabled Robotics
Learning Outcome
- Assess ethical, societal, and privacy implications of deploying vision-enabled robotic systems in public and industrial domains.
- Evaluate object detection, tracking, and scene understanding algorithms for their effectiveness in real-time robotic applications.
- Create multi-sensor data using advanced fusion techniques to enable robust perception and navigation in uncertain environments.
- Design integrated computer vision and robotic systems capable of perceiving, interpreting, and acting in dynamic environments.
- Formulate vision-based control strategies for autonomous navigation and human-robot collaboration in safety-critical contexts.
- Propose innovative solutions by applying 3D reconstruction, SLAM, and AR/VR interfaces to real-world problems in robotics and automation