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

An online evolving framework is proposed to support modeling the safeAutomated Vehicle (AV) control system by making the controller able torecognize unexpected situations and react appropriately by choosing a betteraction. Within the framework, the evolving Finite State Machine (e-FSM), whichis an online model able to (1) determine states uniquely as needed, (2)recognize states, and (3) identify state-transitions, is introduced.  In this study, the e-FSM's capabilities are explained and illustrated bysimulating a simple car-following scenario. As a vehicle controller, theIntelligent Driver Model (IDM) is implemented, and different sets of IDMparameters are assigned to the following vehicle for simulating varioussituations (including the collision). While simulating the car-followingscenario, e-FSM recognizes and determines the states and identifies thetransition matrices by suggested methods.  To verify if e-FSM can recognize and determine states uniquely, we analyzewhether the same state is recognized under the identical situation. Thedifference between probability distributions of predicted and recognized statesis measured by the Jensen-Shannon divergence (JSD) method to validate theaccuracy of identified transition-matrices. As shown in the results, theDead-End state which has latent-risk of the collision is uniquely determinedand consistently recognized. Also, the probability distributions of thepredicted state are significantly similar to the recognized state, declaringthat the state-transitions are precisely identified.

An Online Evolving Framework for Modeling the Safe Autonomous Vehicle Control System via Online Recognition of Latent Risks