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

With the adoption of autonomous vehicles on our roads, we will witness amixed-autonomy environment where autonomous and human-driven vehicles mustlearn to co-exist by sharing the same road infrastructure. To attainsocially-desirable behaviors, autonomous vehicles must be instructed toconsider the utility of other vehicles around them in their decision-makingprocess. Particularly, we study the maneuver planning problem for autonomousvehicles and investigate how a decentralized reward structure can inducealtruism in their behavior and incentivize them to account for the interest ofother autonomous and human-driven vehicles. This is a challenging problem dueto the ambiguity of a human driver's willingness to cooperate with anautonomous vehicle. Thus, in contrast with the existing works which rely onbehavior models of human drivers, we take an end-to-end approach and let theautonomous agents to implicitly learn the decision-making process of humandrivers only from experience. We introduce a multi-agent variant of thesynchronous Advantage Actor-Critic (A2C) algorithm and train agents thatcoordinate with each other and can affect the behavior of human drivers toimprove traffic flow and safety.

Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic