Research Project Title:
An Interlock for Self Driving Cars
abstract:Self driving cars are likely to be safer, on average, than human-driven cars; but they may fail in new and catastrophic ways that a human driver could have prevented. In this project, we aim to develop a new architecture that would bring human-like flexibility to self-driving cars and make them more dependable. I will first create models of self-driving cars and relevant traffic conditions to simulate situations in which self-driving cars operate unreliably, then design multiple control systems that target at different catastrophic situations and use black-box testing to test and improve the effectiveness of system.
I am excited about SuperUROP because it will allow me to gain a year-long experience in academic research. I’ve always been interested in self-driving cars, especially how their software systems are developed. Having worked as a software engineer, I really look forward to utilizing my engineering skills in this project and investigating into how to make self-driving cars safer.