Driverless Car: Autonomous Driving Using Deep Reinforcement Learning in Urban Environment

Deep Reinforcement Learning has led us to newer possibilities in solving complex control and navigation related tasks. The paper presents Deep Reinforcement Learning autonomous navigation and obstacle avoidance of self-driving cars, applied with Deep Q Network to a simulated car an urban environment...

Full description

Saved in:
Bibliographic Details
Published in2018 15th International Conference on Ubiquitous Robots (UR) pp. 896 - 901
Main Authors Fayjie, Abdur R., Hossain, Sabir, Oualid, Doukhi, Lee, Deok-Jin
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Automobiles
Autonomous automobiles
Cameras
Neural networks
Prototypes
Real-time systems
Training
Online AccessGet full text
DOI10.1109/URAI.2018.8441797

Cover

More Information
Summary:Deep Reinforcement Learning has led us to newer possibilities in solving complex control and navigation related tasks. The paper presents Deep Reinforcement Learning autonomous navigation and obstacle avoidance of self-driving cars, applied with Deep Q Network to a simulated car an urban environment. The approach uses two types of sensor data as input: camera sensor and laser sensor in front of the car. It also designs a cost-efficient high-speed car prototype capable of running the same algorithm in real-time. The design uses a camera and a Hokuyo Lidar sensor in the car front. It uses embedded GPU (Nvidia-TX2) for running deep-learning algorithms based on sensor inputs.
DOI:10.1109/URAI.2018.8441797