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

Intersection is one of the most complex and accident-prone urban scenariosfor autonomous driving wherein making safe and computationally efficientdecisions is non-trivial. Current research mainly focuses on the simplifiedtraffic conditions while ignoring the existence of mixed traffic flows, i.e.,vehicles, cyclists and pedestrians. For urban roads, different participantsleads to a quite dynamic and complex interaction, posing great difficulty tolearn an intelligent policy. This paper develops the dynamic permutation staterepresentation in the framework of integrated decision and control (IDC) tohandle signalized intersections with mixed traffic flows. Specially, thisrepresentation introduces an encoding function and summation operator toconstruct driving states from environmental observation, capable of dealingwith different types and variant number of traffic participants. A constrainedoptimal control problem is built wherein the objective involves trackingperformance and the constraints for different participants and signal lightsare designed respectively to assure safety. We solve this problem by offlineoptimizing encoding function, value function and policy function, wherein thereasonable state representation will be given by the encoding function and thenserved as the input of policy and value function. An off-policy training isdesigned to reuse observations from driving environment and backpropagationthrough time is utilized to update the policy function and encoding functionjointly. Verification result shows that the dynamic permutation staterepresentation can enhance the driving performance of IDC, including comfort,decision compliance and safety with a large margin. The trained driving policycan realize efficient and smooth passing in the complex intersection,guaranteeing driving intelligence and safety simultaneously.

Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections