# GridSim: A Vehicle Kinematics Engine for Deep Neuroevolutionary Control in Autonomous Driving

## TL;DR

This paper introduces GridSim, a new autonomous driving simulator that enables testing deep reinforcement learning and genetic algorithm-based behavioral learning in diverse simulated driving scenarios.

## Contribution

The paper presents GridSim, a novel simulation engine for autonomous driving that supports evaluating deep reinforcement learning and genetic algorithms for vehicle control.

## Key findings

- Deep reinforcement learning achieved effective driving behaviors in simulations.
- Genetic algorithms successfully optimized driving policies for various scenarios.
- GridSim provides a versatile platform for testing autonomous driving algorithms.

## Abstract

Current state of the art solutions in the control of an autonomous vehicle mainly use supervised end-to-end learning, or decoupled perception, planning and action pipelines. Another possible solution is deep reinforcement learning, but such a method requires that the agent interacts with its surroundings in a simulated environment. In this paper we introduce GridSim, which is an autonomous driving simulator engine running a car-like robot architecture to generate occupancy grids from simulated sensors. We use GridSim to study the performance of two deep learning approaches, deep reinforcement learning and driving behavioral learning through genetic algorithms. The deep network encodes the desired behavior in a two elements fitness function describing a maximum travel distance and a maximum forward speed, bounded to a specific interval. The algorithms are evaluated on simulated highways, curved roads and inner-city scenarios, all including different driving limitations.