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/

Zendy Plus

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

Zendy Tools

Zendy Open

Due to the complexity of the natural world, a programmer cannot foresee allpossible situations, a connected and autonomous vehicle (CAV) will face duringits operation, and hence, CAVs will need to learn to make decisionsautonomously. Due to the sensing of its surroundings and information exchangedwith other vehicles and road infrastructure, a CAV will have access to largeamounts of useful data. While different control algorithms have been proposedfor CAVs, the benefits brought about by connectedness of autonomous vehicles toother vehicles and to the infrastructure, and its implications on policylearning has not been investigated in literature. This paper investigates adata driven driving policy learning framework through an agent-based modellingapproaches. The contributions of the paper are two-fold. A dynamic programmingframework is proposed for in-vehicle policy learning with and withoutconnectivity to neighboring vehicles. The simulation results indicate thatwhile a CAV can learn to make autonomous decisions, vehicle-to-vehicle (V2V)communication of information improves this capability. Furthermore, to overcomethe limitations of sensing in a CAV, the paper proposes a novel concept forinfrastructure-led policy learning and communication with autonomous vehicles.In infrastructure-led policy learning, road-side infrastructure senses andcaptures successful vehicle maneuvers and learns an optimal policy from thosetemporal sequences, and when a vehicle approaches the road-side unit, thepolicy is communicated to the CAV. Deep-imitation learning methodology isproposed to develop such an infrastructure-led policy learning framework.

An Agent-based Modelling Framework for Driving Policy Learning in Connected and Autonomous Vehicles