Aims and Objectives

Project Aim

The aim of this project is to design, implement, and evaluate a sensor-driven digital twin for collision prevention, with a particular focus on assessing whether multi-sensor fusion offers a more reliable and robust safety strategy than computer vision alone. The project uses simulation and scaled hardware experiments to enable safe, repeatable testing of perception and decision-making behaviour in autonomous systems.

Project Objectives

To achieve this aim, the project is structured around the following objectives:

• Design a sensor-driven digital twin capable of representing the perception state of a vehicle using both simulated and real sensor inputs.

• Implement a camera-based perception module using a YOLO object detection model to identify dynamic obstacles in real time.

• Integrate LiDAR sensing to provide accurate, metric distance measurements to detected objects.

• Incorporate mmWave radar data to estimate relative object velocity and improve collision-risk assessment.

• Fuse camera, LiDAR, and radar data to compute Time-To-Collision (TTC) as a physically meaningful safety metric.

• Apply collision-prevention decisions, such as braking or avoidance, within a simulated environment to observe realistic vehicle responses.

• Compare the performance of vision-only and sensor-fusion-based approaches under identical test scenarios using the digital twin.

• Evaluate system performance in terms of detection reliability, responsiveness, and overall safety behaviour.

• Demonstrate scalability by transitioning from simulation-only validation to experiments on a scaled hardware platform.