Connected and autonomous vehicles as a grand challenge for middleware in cyber-physical systems

From autonomous vehicles to robotics and machinery, organizations are developing autonomous transportation systems in various domains. Strategic incentives point towards a fourth industrial revolution of cyber–physical systems with higher levels of automation and connectivity throughout the Internet of Things (IoT) that interact with the physical world. In the construction and mining sectors, these developments are still at their infancy, and practitioners are interested in autonomous solutions to enhance efficiency and reliability. This paper illustrates the enhanced design of a driverless bulldozer prototype using IoT-based solutions for the remote control and navigation tracking of the mobile machinery. We illustrate the integration of a cloud application, communication protocols and a wireless communication network to control a small-scale bulldozer from a remote workstation. Furthermore, we explain a new tracking functionality of work completion using maps and georeferenced indicators available via a user interface. Finally, we provide a preliminary safety and security risk assessment of the system prototype and propose guidance for application in real-scale machinery.

Download Full-text

Declarative cyber physical systems modeling to facilitate autonomous vehicles design

2015 International Conference on Connected Vehicles and Expo (ICCVE) ◽

10.1109/iccve.2015.78 ◽

2015 ◽

Cited By ~ 1

Author(s):

Wei Ding ◽

Feng-Jen Yang ◽

Sesha Srinivasan

Keyword(s):

Autonomous Vehicles ◽

Cyber Physical Systems ◽

Systems Modeling ◽

Physical Systems

Download Full-text

Outlining Nine Major Design Challenges of Open, Decentralized, Adaptive Cyber-Physical Systems

Volume 2B: 33rd Computers and Information in Engineering Conference ◽

10.1115/detc2013-12022 ◽

2013 ◽

Cited By ~ 5

Author(s):

Imre Horváth ◽

Bart H. M. Gerritsen

Keyword(s):

Design Theory ◽

Cyber Physical Systems ◽

Future Research ◽

Grand Challenge ◽

Physical Systems ◽

System Integrity ◽

Computational Support ◽

Support Tools ◽

Foundational Research ◽

And Behavior

Open, decentralized, adaptive cyber-physical systems (ODA-CPSs) have countless novel structural attributes and functional affordances. Consequently, they pose many design and engineering challenges. This paper identifies and analyzes nine of them. They are: (i) handling aggregative complexity, (ii) establishing static and dynamic compositional synergy, (iii) managing dynamic and evolutionary operation in time, (iv) multi-abstraction-based modeling, (v) system integrity verification and behavior validation, (vi) achieving dynamic scalability towards meta-systems, (vii) transformation of big data, (viii) employing testable surrogate prototyping, and (ix) attaining robust social compliance. These challenges should be addressed already in the course of conceptualization and design of these systems. It is shown that a kind of duality is hiding practically in each of these challenges, which are caused by the concurrence of short term dynamic behavior and long term evolution of ODA-CPSs. Though interrelated, these two aspects still need to be handled separate. In order to response effectively to the above challenges, foundational research and operative research need to produce new transdisciplinary insights and new practical principles, respectively. First, previous efforts in these dimensions are critically evaluated. Then it is circumscribed what new knowledge is needed in order to cope with the considered major challenges. Putting everything together, the paper concludes that the grand challenge is in the lack of a dedicated transdisciplinary design theory that could explain how ODA-CPSs should be ideated and synthesized, and that would allow the development of a comprehensive design methodology and computational support tools. Future research will attempt to propose concrete solutions for the discussed challenges and most probably identify other emerging ones.

Download Full-text

Fuzzy Control in Cyber-Physical Systems

International Journal of Cyber-Physical Systems ◽

10.4018/ijcps.2020070103 ◽

2020 ◽

Vol 2 (2) ◽

pp. 46-58

Author(s):

Michael Gr. Voskoglou

Keyword(s):

Fuzzy Control ◽

Autonomous Vehicles ◽

Input Data ◽

Fuzzy Numbers ◽

Geometric Approach ◽

Cyber Physical Systems ◽

Control Model ◽

Triangular Fuzzy Numbers ◽

Physical Systems ◽

Braking System

Controllers are devices regulating the operation of other devices or systems. Fuzzy controllers analyze the input data in terms of variables which take on continuous values in the interval [0, 1]. Since fuzzy logic has the advantage of expressing the solution of the problems in the natural language, the use of fuzzy instead of traditional controllers makes easier the mechanization of tasks that have been already successfully performed by humans. In the present paper a theoretical fuzzy control model is developed for the braking system of autonomous vehicles, which are included among the most characteristic examples of Cyber-Physical Systems. For this, a simple geometric approach is followed using triangular fuzzy numbers as the basic tools.

Download Full-text

A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems

Journal of Artificial Intelligence Research ◽

10.1613/jair.1.12716 ◽

2021 ◽

Vol 72 ◽

Author(s):

Anthony Corso ◽

Robert Moss ◽

Mark Koren ◽

Ritchie Lee ◽

Mykel Kochenderfer

Keyword(s):

Autonomous Vehicles ◽

Cyber Physical Systems ◽

Black Box ◽

State Spaces ◽

Physical Systems ◽

Safety Critical ◽

Simulated Environment ◽

Rigorous Testing ◽

Simulation Based ◽

Sampling Problem

Autonomous cyber-physical systems (CPS) can improve safety and efficiency for safety-critical applications, but require rigorous testing before deployment. The complexity of these systems often precludes the use of formal verification and real-world testing can be too dangerous during development. Therefore, simulation-based techniques have been developed that treat the system under test as a black box operating in a simulated environment. Safety validation tasks include finding disturbances in the environment that cause the system to fail (falsification), finding the most-likely failure, and estimating the probability that the system fails. Motivated by the prevalence of safety-critical artificial intelligence, this work provides a survey of state-of-the-art safety validation techniques for CPS with a focus on applied algorithms and their modifications for the safety validation problem. We present and discuss algorithms in the domains of optimization, path planning, reinforcement learning, and importance sampling. Problem decomposition techniques are presented to help scale algorithms to large state spaces, which are common for CPS. A brief overview of safety-critical applications is given, including autonomous vehicles and aircraft collision avoidance systems. Finally, we present a survey of existing academic and commercially available safety validation tools.

Download Full-text

Multi-Cloud Resource Management Techniques for Cyber-Physical Systems

Sensors ◽

10.3390/s21248364 ◽

2021 ◽

Vol 21 (24) ◽

pp. 8364

Author(s):

Vlad Bucur ◽

Liviu-Cristian Miclea

Keyword(s):

Resource Management ◽

Autonomous Vehicles ◽

Cyber Physical Systems ◽

Software Projects ◽

Physical Systems ◽

Cloud Resource Management ◽

Human Driver ◽

Resource Requirements ◽

Self Driving Cars ◽

Multi Cloud

Information technology is based on data management between various sources. Software projects, as varied as simple applications or as complex as self-driving cars, are heavily reliant on the amounts, and types, of data ingested by one or more interconnected systems. Data is not only consumed but is transformed or mutated which requires copious amounts of computing resources. One of the most exciting areas of cyber-physical systems, autonomous vehicles, makes heavy use of deep learning and AI to mimic the highly complex actions of a human driver. Attempting to map human behavior (a large and abstract concept) requires large amounts of data, used by AIs to increase their knowledge and better attempt to solve complex problems. This paper outlines a full-fledged solution for managing resources in a multi-cloud environment. The purpose of this API is to accommodate ever-increasing resource requirements by leveraging the multi-cloud and using commercially available tools to scale resources and make systems more resilient while remaining as cloud agnostic as possible. To that effect, the work herein will consist of an architectural breakdown of the resource management API, a low-level description of the implementation and an experiment aimed at proving the feasibility, and applicability of the systems described.

Download Full-text