TY - CHAP
T1 - High-level decision making for safe and reasonable autonomous lane changing using reinforcement learning
AU - Mirchevska, Branka
AU - Pek, Christian
AU - Werling, Moritz
AU - Althoff, Matthias
AU - Boedecker, Joschka
PY - 2018
Y1 - 2018
N2 - Machine learning techniques have been shown to outperform many rule-based systems for the decision-making of autonomous vehicles. However, applying machine learning is challenging due to the possibility of executing unsafe actions and slow learning rates. We address these issues by presenting a reinforcement learning-based approach, which is combined with formal safety verification to ensure that only safe actions are chosen at any time. We let a deep reinforcement learning (RL) agent learn to drive as close as possible to a desired velocity by executing reasonable lane changes on simulated highways with an arbitrary number of lanes. By making use of a minimal state representation, consisting of only 13 continuous features, and a Deep Q-Network (DQN), we are able to achieve fast learning rates. Our RL agent is able to learn the desired task without causing collisions and outperforms a complex, rule-based agent that we use for benchmarking.
AB - Machine learning techniques have been shown to outperform many rule-based systems for the decision-making of autonomous vehicles. However, applying machine learning is challenging due to the possibility of executing unsafe actions and slow learning rates. We address these issues by presenting a reinforcement learning-based approach, which is combined with formal safety verification to ensure that only safe actions are chosen at any time. We let a deep reinforcement learning (RL) agent learn to drive as close as possible to a desired velocity by executing reasonable lane changes on simulated highways with an arbitrary number of lanes. By making use of a minimal state representation, consisting of only 13 continuous features, and a Deep Q-Network (DQN), we are able to achieve fast learning rates. Our RL agent is able to learn the desired task without causing collisions and outperforms a complex, rule-based agent that we use for benchmarking.
U2 - 10.1109/ITSC.2018.8569448
DO - 10.1109/ITSC.2018.8569448
M3 - Chapter
BT - International Conference on Intelligent Transportation Systems (ITSC)
ER -