Explorations and Lessons Learned in Building an Autonomous Formula SAE Car from Simulations
This work addresses the challenge of autonomous driving in student competitions, but it is incremental as it applies existing simulation-to-real methods to a specific domain.
The paper tackled the problem of developing a self-driving algorithm for a Formula SAE car by training a deep neural network in simulation and deploying it on a real vehicle, achieving real-time steering angle inference from a single camera input.
This paper describes the exploration and learnings during the process of developing a self-driving algorithm in simulation, followed by deployment on a real car. We specifically concentrate on the Formula Student Driverless competition. In such competitions, a formula race car, designed and built by students, is challenged to drive through previously unseen tracks that are marked by traffic cones. We explore and highlight the challenges associated with training a deep neural network that uses a single camera as input for inferring car steering angles in real-time. The paper explores in-depth creation of simulation, usage of simulations to train and validate the software stack and then finally the engineering challenges associated with the deployment of the system in real-world.