Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles
Preprint
Abstract
In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, this work proposes the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. Driving scenarios where the road is occupied both by autonomous and manual driving vehicles are considered. To the best of our knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments. The derived reinforcement learning policy, firstly, is compared against an optimal policy derived via dynamic programming, and, secondly, its efficiency is evaluated under realistic scenarios generated by the established SUMO microscopic traffic flow simulator. Finally, some initial results regarding the effect of autonomous vehicles' behavior on the overall traffic flow are presented.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Navigating Occluded Intersections with Autonomous Vehicles Using Deep Reinforcement Learning2018
- Combining neural networks and tree search for task and motion planning in challenging environments2017
- Brain-Inspired Cognitive Model With Attention for Self-Driving CarsIEEE Transactions on Cognitive and Developmental Systems, 2017
- The Driving Safety Field Based on Driver–Vehicle–Road InteractionsIEEE Transactions on Intelligent Transportation Systems, 2015
- A tube-based robust nonlinear predictive control approach to semiautonomous ground vehiclesVehicle System Dynamics, 2014
- Evaluation of Different Vehicle Following Models Under Mixed Traffic ConditionsProcedia - Social and Behavioral Sciences, 2013
- Recent exact algorithms for solving the vehicle routing problem under capacity and time window constraintsEuropean Journal of Operational Research, 2012
- A Survey of Motion Planning Algorithms from the Perspective of Autonomous UAV GuidanceJournal of Intelligent & Robotic Systems, 2009
- The MIT–Cornell collision and why it happenedJournal of Field Robotics, 2008
- A Conceptual Framework for Active Safety in Road TrafficVehicle System Dynamics, 1999