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

Overtaking on two-lane roads is a great challenge for autonomous vehicles, asoncoming traffic appearing on the opposite lane may require the vehicle tochange its decision and abort the overtaking. Deep reinforcement learning (DRL)has shown promise for difficult decision problems such as this, but it requiresmassive number of data, especially if the action space is continuous. Thispaper proposes to incorporate guidance from an expert system into DRL toincrease its sample efficiency in the autonomous overtaking setting. Theguidance system developed in this study is composed of constrained iterativeLQR and PID controllers. The novelty lies in the incorporation of a fadingguidance function, which gradually decreases the effect of the expert system,allowing the agent to initially learn an appropriate action swiftly and thenimprove beyond the performance of the expert system. This approach thuscombines the strengths of traditional control engineering with the flexibilityof learning systems, expanding the capabilities of the autonomous system. Theproposed methodology for autonomous vehicle overtaking does not depend on aparticular DRL algorithm and three state-of-the-art algorithms are used asbaselines for evaluation. Simulation results show that incorporating expertsystem guidance improves state-of-the-art DRL algorithms greatly in both sampleefficiency and driving safety.

Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning