Utilization of AVs in Industry 4.0 Environment
11.4.1 Understanding the Convergence of Industry 4.0 and Autonomous Vehicles
As a society, we’ve embraced a brave new world bursting with myriad emerging technologies so quickly that we haven’t taken the time to understand the interconnections. We see new entrants like cryptocurrency and the IoT as singular, when, in fact, they are symbiotic. Together, these trends form an extensive, disruptive infrastructure.
Groundbreaking technologies and the as-a-service economy are deeply interrelated. If we take time to think about the impact of these disruptive trends, we begin to identify the power of convergence and how seemingly unique ideas are ubiquitous and closely intertwined. Convergence is the truest form of digital transformation, and it’s happening all around us.
Bing Ads recently analyzed 600,000 instances of customer queries over 16 months from categories aligned with a variety of disruptive trends to better understand and quantify their momentum. The stream graph in Figure 11.5 shows six months of recent data and uses average site time as a proxy to understand user engagement (Veverka, 2018). Queries range from “FinTech” and “digital twin technology” to “predictive analytics.” In the figure, colored bands rise to the right across the у-axis over time. The thickness of each band provides insight into the frequency of activity. While some bands sustain their thickness, others get thicker or dissipate. The visualization specifically denotes increased interest in technology, manufacturing, and AVs as these trends continue their journey to convergence and eventual mainstream adoption.
Convergence is most profound in the seismic revolution of Industry 4.0. While the base of Industry 4.0 is manufacturing, McKinsey defines the core DNA of this convergent disruption as the proliferation of big data, advanced analytics, human-machine interfaces, and digital-to-physical transfers providing profound opportunities for new business models and delivery systems.
As we move forward, auto, retail, finance, technology, and telecommunications will all be profoundly entrenched in Industry 4.0, and the digitalization of these verticals will demonstrate the significant impact of convergence, which we will likely witness in real time (Veverka, 2018).
FIGURE 11.5 Recent data and used average site time as a proxy (Veverka, 2018).
11.4.2 Manufacturing and the Role of Robotics in Industry 4.0
Industry 4.0 impacts the whole manufacturing value chain—from raw materials to unfinished goods, the production shop floor, the warehouse, storage, and delivery. As information from each stage is leveraged to introduce more automation in the next, the manufacturing supply chain becomes smarter. Since automation is at the core of Industry 4.0, robots will be an essential part of manufacturing. Invariably, as smarter environments give rise to more information, robots will become more intelligent and easier to operate. Indeed, the ultimate goal of Industry 4.0 is an autonomous smart factory that can produce customizable products.
Otto Motors, a division of Clearpath Robotics, already builds self-driving vehicles for material transport in a manufacturing or industrial site. In fact, the burgeoning area of human-robot collaboration is transforming the manufacturing landscape. Robots, with their superior skills in repetitive tasks that are focused on precision and speed, provide workers with opportunities to focus on more complex tasks, such as those that involve working with large assemblies. The ideal factory of the future identifies no separation between automated and manual workstations: humans and robots will collaborate optimally without a safety fence separating them (Jain & Pai, 2019).
11.4.3 Industrial Autonomous Vehicles
Machine-to-machine (M2M) communication, along with the availability of cloud computing platforms and ubiquitous sensing, has led to the era of the Internet of Things (IoT) in industry. Combined advancements in robotics, autonomous technologies, and IoT have created an ideal environment for the adoption of connected industrial AVs across industries.
AVs have held the attention of futurists and technology enthusiasts for some time, as evidenced by the continuous research and development in AV technologies over the past two decades. Rapid advances in robotics, AI, computer vision, and edge computing capabilities are resulting in machines that can potentially think, see, hear, and move more deftly than humans. AVs in the form of self-driving cars have become the subject of both hype and intense competition among auto majors and technology companies.
Self-driving car prototypes with LiDARs, radars, cameras, ultrasonic sensors—along with heavy computational capabilities under the hood to recognize and maneuver around obstacles—are becoming a common sight in many cities. With the emergence of sophisticated AV technologies, we are on the cusp of their rapid deployment in industrial applications, and the confluence of the IoT and AV technologies is poised to remake and reimagine industries (Jain & Pai, 2019).
In manufacturing, robots traversing the shop floor can gather useful information from the production line on available inventory, tool availability, and calibration needs and identify potential hazards and near-misses to ensure worker safety. Robots can work around the clock and prepare the line for the next production shift. Robots are also connected and communicate with each other, collaboratively deciding which robot should do a particular task. All the autonomously moving robots, as well as machines on the floor, are connected to a back-end system, either on premises or cloud based, that will process the data these machines provide and accordingly perform tasks that optimize the system-level performance on the manufacturing floor. In this scenario, robots and humans collaboratively improve the operational efficiency and productivity of the manufacturing line. Similar use cases and associated benefits can be expected in other industries, such as mining and oil and gas.
Connected industrial AVs are poised to dramatically change the industrial landscape alongside the gradual but steady adoption of autonomous technologies in consumer automotive vehicles and public transport. The rise of industrial AVs signals an exciting future ahead (Jain & Pai, 2019).
- 11.4.4 Autonomous and Connected Vehicles: An Industry 4.0 Issue
- 11.4.4.1 Introduction
Industry 4.0 is characterized by innovative enabling technologies that provide the instruments through which a new collaborative environment is achieved in which humans and systems may interact, gaining advantages from self-organizing and optimizing in real time (see Figure 11.6) (Pieroni, Scarpato, & Brilli, 2018b).
The development of the processes belonging to Industry 4.0 is driven by innovations in the areas of IT, embedded systems, production, automation technique, and mechanical engineering. The aim is to create new factories able to manage much more complex systems (Laka & Gonzalez Rodriguez, 2015). Smart products and smart production equipment will be connected and will overview the entire process, from the product idea to the product design, supply chain, and manufacturing. This approach will permit more efficient results in all the value chain production. Smart production also covers the delivery
of products to the end users, after sales services, and product recycling. The connection of all elements within the value chain in real time is considered the basis of Internet 4.0.
The automotive industry is experiencing new challenges and frontiers with autonomous and connected vehicles which are becoming “smart” and totally connected with the rest of the world through Internet technologies. The improvements in modern technologies have allowed the comprehensive integration of essential systems and data for AV operations. Vehicles can process decisions based on defined criteria informed by actual conditions, with data provided by the following integrated systems (Pieroni, Scarpato, & Brilli, 2018b):
- • GPS: Gives a satellite-based global location and time reference for accurate and constant position tracking.
- • Inertial navigation system (INS): Monitors and calculates positioning, direction and speed of vehicles, assisted by sensors onboard.
- • LiDAR: Used a laser detection sensors to identify surrounding objects.
All mechanisms provide decision-making data necessary for the vehicle to be aware of position, traffic conditions, and possible movements.
There are presently two different categories of smart vehicles: autonomous vehicles (AVs) that perform all driving functions with or without a “human driver,” also called vehicles without drivers; connected autonomous vehicles (CAVs) which have advanced communication technologies linking them to other vehicles or infrastructure. Both will lead new investments in urban infrastructure to reinforce features (especially wireless communication) linking the vehicle and the infrastructure at the edge of the road (e.g., smart lamppost) to transmit in real time an increasing amount of bidirectional data between the vehicle and the urban infrastructure (Pieroni, Scarpato, & Brilli, 2018b).
11.4.4.2 The Technological Impact of CAVs
Several connected vehicles have been designed and developed to be tested in various markets around the globe (Kharpal, 2017). Figure 11.7 illustrates the conceptual vision of a smart, integrated, dynamic, and connected society in which the diffusion of connected AVs is growing.
FIGURE 11.7 US Department of Transportation’s (USDOT) CAV evolution vision (Pieroni, Scarpato, & Brilli. 2018b).
FIGURE 11.8 Complexity of modern software (Information is Beautiful. 2015).
However, the bidirectional flow of data between vehicles and infrastructure is raising concerns about the regulation about the privacy of the exchanged of data (Pieroni, Scarpato, & Brilli, 2018b).
Regulations on the privacy (Guadagni, 2015) of the collection, the preservation, and the use of data in a connected society exist, but they vary across states and countries. Several protocols have been implemented to collect data from vehicles to infrastructure (V2I) and between vehicles (V2V). The former is better defined as an infrastructure communication technology, and the latter as a cooperative communication technology (Pieroni, Scarpato, & Brilli, 2018b).
In the V2I protocol, the infrastructure plays a coordinating role by gathering global or local information on traffic and road conditions and then suggesting or imposing certain behaviors on a group of vehicles. The V2V protocol is more difficult to realize because of its decentralized structure and its aim to organize the interaction among vehicles and possibly develop collaborations (Dey, Rayamajhi, Chowdhury, Bhavsar, & Martin, 2016).
Progress in onboard computational technology has introduced “adaptive” intelligence, in other words, the vehicle changes its behavior according to environmental conditions (e.g., traffic condition). This processing must be performed in real time, considering at the same time the speed of the vehicle, the obstacles present in the roadway, and the traffic conditions, have the possibility to make appropriate changes keeping the vehicle in the lane and suggesting alternative itineraries.
Figure 11.8 illustrates the complexity (in MoC—million-of-line-code) of the software modules provided for a totally connected vehicle compared to the software onboard other types of vehicles (Pieroni, Scarpato, & Brilli, 2018b).
The software embedded in a totally connected vehicle can reach and exceed 100 millions of lines of code (Information is Beautiful, 2015). Even if the measure of line of code is not widely recognized, it can be a valid indicator of the software complexity in this type of vehicle. It is mandatory to reduce the computational time, the complexity of the embedded software while maintaining at the same time the availability and the reliability of software itself. This software complexity requires the availability of processors with increasing performance. As a consequence, the complexity of a vehicle embedded software is increasing, not only to ensure the performance of the various interactive function, but also to permit the development of an orchestration layer that allows communication between the various software modules and the on-road infrastructure (Pieroni, Scarpato, & Brilli, 2018b).
