Energy-Based Models for End-to-End Autonomous Driving
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Tartu Ülikool
Abstract
Energy-based models (EBMs), a promising class of machine learning models, have shown
impressive results in several domains, from natural language generation to computer
vision. Learning to imitate expert demonstrations using an EBM has recently achieved
state-of-the-art results in robotics, made possible by EBMs’ better ability to handle
multimodal probability distributions and learn behavior with abrupt command changes.
In this work, EBMs are tested for the first time in the end-to-end autonomous driving
domain on a real car. As a result, it is discovered that a simple EBM variant performs
slightly better and is more stable than a baseline conventional neural network architecture.
At the same time, EBMs turn out to exhibit a higher variability of predictions over time,
or whiteness. As a solution to this problem, this work introduces a regularization
technique that makes the predictions more smooth over time. In addition, an energybased
uncertainty metric is proposed, but its usefulness could not be assessed with
sufficient reliability due to an insufficient number of real car evaluations. The thesis
suggests several ideas for future work, such as using a different sampling method and
comparing against mixture density networks.
Description
Keywords
end-to-end, autonomous driving, neural networks, behavioral cloning, energy-based models, real car