Date of Submission
Academic Programs and Concentrations
Project Advisor 1
This project explores the use of deep convolutional neural networks in autonomous cars. Successful implementation of autonomous vehicles has many societal benefits. One of the main benefits is its potential to significantly reduce traffic accidents. In the United States, the National Highway Traffic Safety Administration states that human error is at fault for 93% of automotive crashes. Robust driverless vehicles can prevent many of these collisions. The main challenge in developing autonomous vehicles today is how to create a system that is able to accurately perceive and process the world around it. In 2016, NVIDIA successfully trained a deep convolutional neural network to map raw images from a single front-facing camera into steering commands. Today, automotive companies such as Google’s Waymo, and Tesla’s Autopilot, utilize deep convolutional neural networks to control their autonomous vehicles. The goal of this project is to evaluate how well a recurrent neural network and categorical output perform when combined with NVIDIA’s platform. These models’ performances are then evaluated on a scaled self driving car and compared to a human driver. NVIDIA’s model combined with a RNN is able to keep the car within 6.1 cm of a human driver’s path.
Open Access Agreement
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Chang, Jason Zisheng, "Training Neural Networks to Pilot Autonomous Vehicles: Scaled Self-Driving Car" (2018). Senior Projects Spring 2018. 402.
This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.
Automotive Engineering Commons, Computer and Systems Architecture Commons, Electrical and Computer Engineering Commons, Hardware Systems Commons