<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper proposes an automated driving decision-making method based on the Wasserstein generative adversarial imitation learning–deep deterministic policy gradient (WGAIL–DDPG(<italic>λ</italic>)). Here the exact reward function is designed based on the requirements of a vehicle’s driving performance, i.e., safety, dynamic and ride comfort performance. The model’s training efficiency is improved through the proposed imitation learning strategy, and a gain regulator is designed to smooth the transition from imitation to reinforcement phases. Test results show that the proposed decision-making model can generate actions quickly and accurately according to the surrounding environment. Meanwhile, the imitation learning strategy based on expert experience and the gain regulator can effectively improve the training efficiency for the reinforcement learning model. Additionally, an extended test also proves its good adaptability for different driving conditions.</p>
</abstract>

Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper proposes an automated driving decision-making method based on the Wasserstein generative adversarial imitation learning–deep deterministic policy gradient (WGAIL–DDPG(λ)). Here the exact reward function is designed based on the requirements of a vehicle’s driving performance, i.e., safety, dynamic and ride comfort performance. The model’s training efficiency is improved through the proposed imitation learning strategy, and a gain regulator is designed to smooth the transition from imitation to reinforcement phases. Test results show that the proposed decision-making model can generate actions quickly and accurately according to the surrounding environment. Meanwhile, the imitation learning strategy based on expert experience and the gain regulator can effectively improve the training efficiency for the reinforcement learning model. Additionally, an extended test also proves its good adaptability for different driving conditions.

An Automated Driving Strategy Generating Method Based on WGAIL–DDPG

State Key Laboratory of Structure Analysis for Industrial Equipment

International Journal of Applied Mathematics and Computer Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"An Automated Driving Strategy Generating Method Based on WGAIL\u2013DDPG"}

Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper proposes an automated driving...

An Automated Driving Strategy Generating Method Based on WGAIL–DDPG

Published Online: Sep 27, 2021

Page range: 461 - 470

Received: Jan 22, 2021

Accepted: Jul 12, 2021

DOI: https://doi.org/10.34768/amcs-2021-0031

Keywords
automated driving system, deep learning, deep reinforcement learning, imitation learning, deep deterministic policy gradient

© 2021 Mingheng Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

An Automated Driving Strategy Generating Method Based on WGAIL–DDPG

Published Online: Sep 27, 2021

Page range: 461 - 470

Received: Jan 22, 2021

Accepted: Jul 12, 2021

DOI: https://doi.org/10.34768/amcs-2021-0031

Keywordsautomated driving system, deep learning, deep reinforcement learning, imitation learning, deep deterministic policy gradient

© 2021 Mingheng Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Keywords
automated driving system, deep learning, deep reinforcement learning, imitation learning, deep deterministic policy gradient