Application of Neuroevolution in Autonomous Cars

TL;DR

This paper presents a neuroevolution-based approach to train autonomous cars in simulation without relying on large datasets, demonstrating self-optimization and potential for improved generalization in driving tasks.

Contribution

The authors introduce a novel neuroevolution method for training self-driving cars that eliminates the need for extensive data collection and dataset evaluation.

Findings

Successfully trained autonomous cars using neuroevolution in simulation.

Demonstrated the ability of genetic algorithms to generalize driving attributes.

Showed that evolution can reach optimal solutions without data dependency.

Abstract

With the onset of Electric vehicles, and them becoming more and more popular, autonomous cars are the future in the travel/driving experience. The barrier to reaching level 5 autonomy is the difficulty in the collection of data that incorporates good driving habits and the lack thereof. The problem with current implementations of self-driving cars is the need for massively large datasets and the need to evaluate the driving in the dataset. We propose a system that requires no data for its training. An evolutionary model would have the capability to optimize itself towards the fitness function. We have implemented Neuroevolution, a form of genetic algorithm, to train/evolve self-driving cars in a simulated virtual environment with the help of Unreal Engine 4, which utilizes Nvidia's PhysX Physics Engine to portray real-world vehicle dynamics accurately. We were able to observe the serendipitous nature of evolution and have exploited it to reach our optimal solution. We also demonstrate the ease in generalizing attributes brought about by genetic algorithms and how they may be used as a boilerplate upon which other machine learning techniques may be used to improve the overall driving experience.