George Hotz, Eder Santana - 2016
Publications: arXiv Add/Edit
Comma.ai's approach to Artificial Intelligence for self-driving cars is based on an agent that learns to clone driver behaviors and plans maneuvers by simulating future events in the road. This paper illustrates one of our research approaches for driving simulation. One where we learn to simulate. Here we investigate variational autoencoders with classical and learned cost functions using generative adversarial networks for embedding road frames. Afterwards, we learn a transition model in the embedded space using action conditioned Recurrent Neural Networks. We show that our approach can keep predicting realistic looking video for several frames despite the transition model being optimized without a cost function in the pixel space.
This is a compilation of resources, tutorials, side projects, and other useful materials that I am learning and covering as I get ready for Udacity's Self-Driving Car Engineer Nanodegree program