Road Detection as a part of the Reward System for Reinforcement Learning-based Autonomous Cars
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 Human drivers are subject to numerous flaws. It is common that the driversget tired and lose control of the vehicle, and some even get drunk or high, whichresults in dangerous situations for themselves and others.Autonomous driving is a field of study which has gained notoriety lately, as itattempts to get more reliable than humans at driving; Though there is still muchresearch to be done in the field. We are far away from replacing human driverswith safe AI-equivalents.In this thesis, we aim to validate a road detection algorithm as a part of thereward system of the autonomous vehicle1. We introduce…
Development of a Simulator for Prototyping Reinforcement Learning-Based Autonomous Cars
Autonomous driving is a research field that has received attention in recent years, with increasing applications of reinforcement learning (RL) algorithms. It is impractical to train an autonomous vehicle thoroughly in the physical space, i.e., the so-called ’real world’; therefore, simulators are used in almost all training of autonomous driving algorithms. There are numerous autonomous driving simulators, very few of which are specifically targeted at RL. RL-based cars are challenging due to the variety of reward functions available. There is a lack of simulators addressing many central RL research tasks within autonomous driving, such as scene understanding, localization and mapping, pla…
Road Detection for Reinforcement Learning Based Autonomous Car
Human mistakes in traffic often have terrible consequences. The long-awaited introduction of self-driving vehicles may solve many of the problems with traffic, but much research is still needed before cars are fully autonomous.In this paper, we propose a new Road Detection algorithm using online supervised learning based on a Neural Network architecture. This algorithm is designed to support a Reinforcement Learning algorithm (for example, the standard Proximal Policy Optimization or PPO) by detecting when the car is in an adverse condition. Specifically, the PPO gets a penalty whenever the virtual automobile gets stuck or drives off the road with any of its four wheels.Initial experiments …