Connected and Autonomous Vehicle Mobility: Socially Disruptive Technologies, Networked Transport Systems, and Big Data Algorithmic Analytics.

• Author: Lazaroiu, George
• Position: Report

1. Introduction

   A smart connected setting (Krizanova et al., 2019; Mihaila, 2018; Nica, 2018) with vehicle-to-vehicle and vehicle-to-infrastructure interaction performance may shape driving behavior and safety. (Ali et al., 2020) Networked and autonomous vehicles may enhance the operation of the transportation system by cutting down human errors. (Arvin et al., 2020) Highly automated and self-driving vehicles will have considerable consequences throughout intelligent vehicular networks. (Bin-Nun and Binamira, 2020)

2. Conceptual Framework and Literature Review

   Intelligent autonomous systems (Krylov, 2019; Nica, 2015; Noack, 2019; Popescu et al., 2018; Zhuravleva et al., 2019) such as self-driving vehicles can perceive, grasp, and forecast (Popescu et al., 2017a, b; Smith, 2020) human behavior. (Rudenko et al., 2020) Connectivity and intelligence have assisted autonomous vehicles in cooperating to carry out elaborate tasks (Groener, 2019; Lazaroiu et al., 2020a, b, c; Popescu, 2014; Roszko-Wojtowicz et al., 2019) that they cannot complete independently. (Rehman Javed et al., 2020) The likelihood of crash between self-driving cars and other road users is concrete in the absence of vehicle-to-vehicle interaction, in addition to the plausibility of navigation-aided equipment inaccuracies because of environmental or external aspects. (Hou et al., 2020)

3. Methodology and Empirical Analysis

   The data used for this study was obtained and replicated from previous research conducted by ANSYS, Atomik Research, Black & Veatch, Brookings, Capgemini, Charles Koch Institute, eMarketer, Ipsos/GenPop, Kennedys, KPMG, McKinsey, Pew Research Center, Schoettle & Sivak (2014), and Statista. We performed analyses and made estimates regarding socially disruptive technologies, networked transport systems, and big data algorithmic analytics. Data collected from 3,900 respondents are tested against the research model by using structural equation modeling.

4. Results and Discussion

   Driver networking with pedestrians and traffic lights in smart connected settings are safer. (Ali et al., 2020) Autonomous vehicles can identify the surrounding environment and car by harnessing heterogeneous on-board sensors, making algorithmic-based analysis and judgment, autonomously controlling vehicle movement unassisted, and reaching self-driving in conformity with specific collected data. (Dai and Lee, 2020) (Tables 1-13)

   Smart connected settings furnish surrounding traffic data to drivers by use of various cruising aids (e.g. speed reports, vehicle-following support, lane-changing assistance, and groundbreaking information as regards potential undetected hazards) that will enhance operating behavior and further the prevention of safety-critical events. (Ali et al., 2020) Self-driving cars can recognize and sense the surrounding environment, self-regulate their performance, and attain the maneuvering capabilities of human drivers. (Dai and Lee, 2020) Real-world connected vehicle data can enhance mobility performance, shaping autonomous vehicle driving behavior. (Arvin et al., 2020) The capacity to forecast the decisions of other road users is essential in big data-driven algorithmic driving. (Rudenko et al., 2020) By assimilating the vehicle-to-vehicle communication technology into self-driving cars, a cutting-edge and safer collision prevention/autonomous crash avoidance system can be advanced throughout intelligent vehicular networks. (Hou et al., 2020)

   Drivers perpetuate superior safety margins throughout vehicle-following and lane-changing maneuvers across the smart connected environment. (Ali et al., 2020) Self-driving cars can get a comprehensive image of the ongoing situations around them, indicating and discontinuing errors that cannot be detected and anticipated by the sensor systems. (Hou et al., 2020) Self-driving cars sharing the networked transport systems with human drivers have to identify other road users and surrounding obstacles, in addition to configuring the auditory driving environment that may contain pivotal data for safe road interactions. (King et al., 2021) Cutting-edge sensing technologies and autonomous vehicle decision-making algorithms will optimize the level of smart mobility and assistance systems as regards connected and networked driving. (Reina et al., 2020) Social influence and initial trust are instrumental in autonomous vehicle acceptance, adoption, and implementation. (Zhang et al., 2020) Harnessing shared, on-demand self-driving cars on a large scale may shape vehicle ownership and transportation...