AIDec 12, 2017

Simulated Autonomous Driving on Realistic Road Networks using Deep Reinforcement Learning

arXiv:1712.04363v21 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the need for more usual driving environments in simulated autonomous driving research, though it appears incremental as it focuses on software validation and a specific task.

The paper tackles the problem of validating Deep Reinforcement Learning algorithms for autonomous driving in realistic road networks, presenting Driving School for Autonomous Agents (DSA^2) software and demonstrating its application for velocity regulation on a straight road with different speed limits.

Using Deep Reinforcement Learning (DRL) can be a promising approach to handle various tasks in the field of (simulated) autonomous driving. However, recent publications mainly consider learning in unusual driving environments. This paper presents Driving School for Autonomous Agents (DSA^2), a software for validating DRL algorithms in more usual driving environments based on artificial and realistic road networks. We also present the results of applying DSA^2 for handling the task of driving on a straight road while regulating the velocity of one vehicle according to different speed limits.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes