Interconnected Sensor Networks and Decision-Making Self-Driving Car Control Algorithms in Smart Sustainable Urbanism.

• Author: Davies, Shirley
• Position: Report

1. Introduction

   Cutting-edge big data-driven developments in software, hardware, and communication systems are pivotal in intelligent transportation systems, self-driving cars, and vehicular networks. (Zeadally et al., 2020) Connected and autonomous transport systems can update their performance in case of malfunction or variable changing environmental conditions by use of decision-making self-driving car control algorithms. (Zimmermann and Wotawa, 2020) As an essential component of intelligent transport systems, the vehicular ad hoc networks are instrumental in cutting down car crashes while improving traffic efficiency in connected and autonomous vehicle mobility and the travel comfort of users. (Bylykbashi et al., 2020)

2. Conceptual Framework and Literature Review

   Sustainable and smart urban transport systems handle faults coherently, thus reaching a safe state. (Zimmermann and Wotawa, 2020) As self-driving cars have resources and services associated with algorithmic data-driven computing (Adami, 2019; Kassick, 2019; Lazaroiu et al., 2020a, b, c, d; Sawyer, 2020), decision processes, networking, storage, and monitoring capabilities, massive volumes of information can be processed, offloading huge traffic flows from the networked transport systems. (Bylykbashi et al., 2020) Groundbreaking technologies are integrated into autonomous vehicles, detecting possible road hazards while enhancing driving experience. (Zeadally et al., 2020) Self-driving cars have algorithm-driven sensing devices and computing technologies (Andrei et al., 2016a, b; Kliestik et al., 2018; Kovacova et al., 2019; Popescu et al., 2017a, b; Sion, 2019) enabling connected and autonomous vehicle mobility (Popescu et al., 2019; Zhuravleva et al., 2019) throughout intelligent vehicular networks. (Receveur et al., 2020)

3. Methodology and Empirical Analysis

   Building my argument by drawing on data collected from Abraham et al. (2017), Arm, ANSYS, Atomik Research, AUDI AG, Axios, BikePGH, Brookings, eMarketer, Ipsos, Kennedys, OpinionWay, and SAE, I performed analyses and made estimates regarding interconnected sensor networks and decision-making self-driving car control algorithms. The structural equation modeling technique was used to test the research model.

4. Results and Discussion

   Self-driving cars counterbalance internal faults taking place throughout the rides attempting to bring users to a safe halt under any circumstances. (Zimmermann and Wotawa, 2020) Autonomous vehicles are equipped with connected sensors, smart cameras and heterogeneous wireless communication technologies harnessed to collect data with reference to the surrounding environment and road conditions. The sensed data shape big data-driven algorithmic decision-making (Bourke et al., 2019; Kliestik et al., 2020a, b; Lazaroiu et al., 2017) utilizing the supplied information. (Bylykbashi et al., 2020) Integrity represents a pivotal performance indicator for real-time self-driving car navigation in safety-critical applications. Alert limit constitute a distinguishing feature in integrity monitoring, denoting the paramount acceptable positioning error for a safe performance. A satisfactory alert limit has to ensure the vehicle security, thoroughly leveraging the space between the car and the lane. (Meng and Hsu, 2020) (Tables 1-19)

   Connected and autonomous vehicle mobility constitutes an exemplary application domain for illustrating the capabilities of intelligent vehicular networks as a result of the association with big data-driven transportation planning and engineering. (Zimmermann and Wotawa, 2020) In smart sustainable urbanism, driving support technologies will enhance both traffic safety and transport performance depending on the assessment and sensing of the surrounding environment and their impact on chauffeuring behavior. (Bylykbashi et al., 2020) Smart connected sensors, urban transportation systems, and deep learning-based sensing and computing technologies are integrated into self-driving cars to configure intelligent vehicular networks and data-driven mobilities. (Zeadally et al., 2020) Heterogeneous moral decision-making paradigms articulated by ethical values may clarify how autonomous vehicles should behave in imminent car collisions. (Rhim et al., 2020)

   Decision-making self-driving car control algorithms have to counterbalance malfunctions in a manner that assures attaining a safe state in any circumstances, while operating...