Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning

Abstract

This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.

References in corpus (3)

• Deep Learning in Neural Networks: An Overview
• Congested Traffic States in Empirical Observations and Microscopic Simulations
• Deep Reinforcement Learning framework for Autonomous Driving

Cited by in corpus (12)

• Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving
• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS
• A Learning-based Discretionary Lane-Change Decision-Making Model with Driving Style Awareness
• Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving
• Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF
• Resilient Branching MPC for Multi-Vehicle Traffic Scenarios Using Adversarial Disturbance Sequences
• Deep Q-learning: a robust control approach
• SLAS: Speed and Lane Advisory System for Highway Navigation
• Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions
• Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization
• Development of A Stochastic Traffic Environment with Generative Time-Series Models for Improving Generalization Capabilities of Autonomous Driving Agents