A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers

By Pin Wang, Ching-yao Chan, Arnaud de La Fortelle. 2018

270 citations recorded by the source corpus.

Lane change is a crucial vehicle maneuver which needs coordination with surrounding vehicles. Automated lane changing functions built on rule-based models may perform well under pre-defined operating conditions, but they may be prone to failure when unexpected situations are encountered. In our study, we proposed a Reinforcement Learning based approach to train the vehicle agent to learn an automated lane change behavior such that it can intelligently make a lane change under diverse and even unforeseen scenarios. Particularly, we treated both state space and action space as continuous, and designed a Q-function approximator that has a closed-form greedy policy, which contributes to the computation efficiency of our deep Q-learning algorithm. Extensive simulations are conducted for training the algorithm, and the results illustrate that the Reinforcement Learning based vehicle agent is capable of learning a smooth and efficient driving policy for lane change maneuvers.

Subfields: Artificial Intelligence, Automotive Engineering, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Control and Systems Engineering

Citations in the corpus

Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, methodology): “Authors [88] use Q-learning, whereas traditional approaches consist in deﬁning ﬁxed way points, velocity proﬁles and curvature of path to be followed by the ego vehicle.”
Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning (2019, methodology): “Learning algorithms can be used to solve the tasks in an integrated/end-to-end fashion [13] [14] or in an isolated approach for each driving task like intersectiondriving [15] [16] and lane-changing [17].”
A Survey of Deep Learning Applications to Autonomous Vehicle Control (2019, methodology): “[96] used reinforcement learning to train an agent to execute lane change manoeuvrers using a Deep Q-Network (DQN).”
A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, background): “However, the driver’s behavior is always complicated such that manually specifying the weight of the reward function is inappropriate [166], [167].”
Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles (2020, methodology): “The most used quantitative measures are the longitudinal acceleration [47], lateral acceleration [48], [49] and jerk [50], [10].”
A Review of Motion Planning for Highway Autonomous Driving (2020, methodology): “Reinforcement learning is used in [133] to determine the policies for each agent in the scene representation, or for multi-goal overtaking maneuvers in [144] and automated lane change maneuvers in [145].”
Exploring applications of deep reinforcement learning for real-world autonomous driving systems (2019, methodology): “Q-function for lane change: A Reinforcement Learning approach is proposed in (Wang et al., 2018) to train the vehicle agent to learn an automated lane change in a smooth and efficient behavior, where the coefficients of the Q-function are learned from neural networks.”