English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traffic scenarios in roundabouts pose substantial complexity for automateddriving. Manually mapping all possible scenarios into a state space islabor-intensive and challenging. Deep reinforcement learning (DRL) with itsability to learn from interacting with the environment emerges as a promisingsolution for training such automated driving models. This study explores,employs, and implements various DRL algorithms, namely Deep DeterministicPolicy Gradient (DDPG), Proximal Policy Optimization (PPO), and Trust RegionPolicy Optimization (TRPO) to instruct automated vehicles' driving throughroundabouts. The driving state space, action space, and reward function aredesigned. The reward function considers safety, efficiency, comfort, and energyconsumption to align with real-world requirements. All three tested DRLalgorithms succeed in enabling automated vehicles to drive through theroundabout. To holistically evaluate the performance of these algorithms, thisstudy establishes an evaluation methodology considering multiple indicatorssuch as safety, efficiency, and comfort level. A method employing the AnalyticHierarchy Process is also developed to weigh these evaluation indicators.Experimental results on various testing scenarios reveal that the TRPOalgorithm outperforms DDPG and PPO in terms of safety and efficiency, and PPOperforms best in terms of comfort level. Lastly, to verify the model'sadaptability and robustness regarding other driving scenarios, this study alsodeploys the model trained by TRPO to a range of different testing scenarios,e.g., highway driving and merging. Experimental results demonstrate that theTRPO model trained on only roundabout driving scenarios exhibits a certaindegree of proficiency in highway driving and merging scenarios. This studyprovides a foundation for the application of automated driving with DRL in realtraffic environments.

Safe, Efficient, Comfort, and Energy-saving Automated Driving through Roundabout Based on Deep Reinforcement Learning