Candidate: Oleksandra Nahorna
Date: December 6, 2024
Time: 10:00am
Location: Microsoft Teams Meeting
Supervisors: Seyed Majid Zahedi and Yash Vardhan Pant
All are welcome!
Abstract:
When we hear autonomous or ego vehicles, we imagine a safe, self-driving device. However, this designation is unsuitable for describing a self-driving car because the car's automation is still being refined, and safety is being studied and constantly improved. However, we can also participate in improving the algorithms for the car with small means, namely, by studying the behaviour of an autonomous car in virtual reality. This work challenges realism, namely, it compares the likelihood of emergencies in generated car accidents to real-life cases. To do this, as in any other area, we study historical data on road accidents. These situations are compared with selectively generated instances, and a successful comparison is recorded and described by creating a narrative for the generated situation. Thereby smoothing the boundary between virtual and real accidents on the road. Using the Reinforcement Learning technique, a single-agent or multi-agent attacker vehicle is trained to reproduce collisions in a virtual environment. Generated cases can be different, both simple and difficult to reproduce in the real world. However, their presence can prepare ego-vehicle for any situations that may arise on the road. Thus, improving the safety of the self-driving car. It is important to note that reproducing and preparing an autonomous car in a virtual environment can be an economical approach. After all, to train the model, only time is needed depending on the number of generated episodes, thereby reducing the cost of testing or pre-testing. And it will also help to recreate scenarios that are problematic for recreation in real, physical space. Testing cars using different algorithms can help to identify a pattern or algorithm suitable for a specific environment, type of road, and number of actors on the road. This diploma work is dedicated to the above-mentioned studies and seeks to publicize and recommend using a virtual environment to improve the automotive industry.