REEEC-AGENT: human driver cognition and emotions-inspired rear-end collision avoidance method for autonomous vehicles

Abstract

Rear-end collision detection and avoidance is one of the most crucial driving tasks of self-driving vehicles. Mathematical models and fuzzy logic-based methods have recently been proposed to improve the effectiveness of the rear-end collision detection and avoidance systems in autonomous vehicles (AVs). However, these methodologies do not tackle real-time object detection and response problems in dense/dynamic road traffic conditions due to their complex computation and decision-making structures. In our previous work, we presented an affective computing-inspired Enhanced Emotion Enabled Cognitive Agent (EEEC_Agent), which is capable of rear-end collision avoidance using artificial human driver emotions. However, the architecture of the EEEC_Agent is based on an ultrasonic sensory system which follows three-state driving strategies without considering the neighbor vehicles types. To address these issues, in this paper we propose an extended version of the EEEC_Agent which contains human driver-inspired dynamic driving mode controls for autonomous vehicles. In addition, a novel end-to-end learning-based motion planner has been devised to perceive the surrounding environment and regulate driving tasks accordingly. The real-time in-field experiments performed using a prototype AV demonstrate the effectiveness of this proposed rear-end collision avoidance system.

Face mask detection and social distance monitoring system for COVID-19 pandemic

“…Social distancing is a significant safety measure to control the spread of COVID-19. Computer vision application has shown better applicability in detection [42] and emotion enable cognition task in real time environment [43]. In this regard, computer vision play an important role to dimensionality reduction with Matrix Factorization (MF) has valuable framework to treat against COVID-19 [44].…”

Low-latency GNSS multipath simulation and building wall detection in urban environments

“…Thus, we analyzed a derivative-free optimization algorithm (Nelder-Mead) and several line-search and trust-region algorithms in order to find an ideal optimization algorithm (Table 1). The linesearch algorithms were applied with simple backtracking (1) and backtracking using cubic approximation (2). If one of the algorithms requires derivatives, then a finite difference formula using 4 (central 4) or 2 (central 2) function evaluations is applied.…”

“…1 Recent works in this field of research addressed the collision avoidance and path tracking problems. An affective computing-inspired driving controller to avoid rear-end collisions is presented in Butt et al 2 A method for lane and obstacle detection using a camera module on a mobile robot is demonstrated in Singh et al 3 In Sun et al, 4 a Global Navigation Satellite System (GNSS)/compass fusion with the Adaptive Neuro Fuzzy Inference System (ANFIS)-based algorithm for real-time car-following status identification is developed. The GNSS/compass-ANFIS-fusion approach relies on localization coordinates with centimeter accuracy, which is not guaranteed in urban environments.…”

A review of automotive intelligent and adaptive headlight beams intensity control approaches

“…Fuzzy rules associated with these behaviors indicated the level of risk, and experimental results showed an average detection ratio of 95%, suggesting the potential for improving traffic safety. A control system mechanism based on fuzzy logic, incorporating reasonable control rules, was presented by Butt et al 52 Their aim was to explore the role of genetic algorithms in enhancing the efficiency of a fuzzy logic-based rear-end collision avoidance scheme. Results from the control mechanism indicated that the fuzzy controller is reliable and has diverse applications, making it a probable candidate for use by more designers.…”