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

TL;DR

This paper introduces an online evolving framework using e-FSM to model and recognize latent risks in autonomous vehicle control systems, enhancing safety by accurately identifying states and transitions during driving scenarios.

Contribution

The study presents a novel online evolving Finite State Machine (e-FSM) capable of real-time state recognition and transition identification in autonomous vehicle control, validated through simulation.

Findings

e-FSM accurately recognizes the Dead-End latent-risk state.

Transition matrices are precisely identified with high consistency.

State recognition remains stable under identical situations.

Abstract

An online evolving framework is proposed to support modeling the safe Automated Vehicle (AV) control system by making the controller able to recognize unexpected situations and react appropriately by choosing a better action. Within the framework, the evolving Finite State Machine (e-FSM), which is 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 by simulating a simple car-following scenario. As a vehicle controller, the Intelligent Driver Model (IDM) is implemented, and different sets of IDM parameters are assigned to the following vehicle for simulating various situations (including the collision). While simulating the car-following scenario, e-FSM recognizes and determines the states and identifies the transition matrices by suggested methods. To verify if e-FSM can recognize and determine states uniquely, we analyze whether the same state is recognized under the identical situation. The difference between probability distributions of predicted and recognized states is measured by the Jensen-Shannon divergence (JSD) method to validate the accuracy of identified transition-matrices. As shown in the results, the Dead-End state which has latent-risk of the collision is uniquely determined and consistently recognized. Also, the probability distributions of the predicted state are significantly similar to the recognized state, declaring that the state-transitions are precisely identified.