THE CONCEPT OF AUTONOMOUS SYSTEMS IN INDUSTRY 4.0

Abstract

Recent tendencies – such as the life-cycles of products are shorter while consumers require more complex and more unique final products – poses many challenges to the production. The industrial sector is going through a paradigm shift. The traditional centrally controlled production processes will be replaced by decentralized control, which is built on the self-regulating ability of intelligent machines, products and workpieces that communicate with each other continuously. This new paradigm known as Industry 4.0. This conception is the introduction of digital network-linked intelligent systems, in which machines and products will communicate to one another in order to establish smart factories in which self-regulating production will be established. In this article, at first the essence, main goals and basic elements of Industry 4.0 conception is described. After it the autonomous systems are introduced which are based on multi agent systems. These systems include the collaborating robots via artificial intelligence which is an essential element of Industry 4.0.

Full text

Advanced Logistic Systems Vol. 12 No. 1 (2018) pp. 77-87, https://doi.org/10.32971/als.2019.006
THE CONCEPT OF AUTONOMOUS SYSTEMS IN INDUSTRY 4.0
RABAB BENOTSMANE1˗LÁSZLÓ DUDÁS2˗GYÖRGY KOVÁCS3
Abstract: Recent tendencies – such as the life-cycles of products are shorter while consumers require
more complex and more unique final products – poses many challenges to the production. The
industrial sector is going through a paradigm shift. The traditional centrally controlled production
processes will be replaced by decentralized control, which is built on the self-regulating ability of
intelligent machines, products and workpieces that communicate with each other continuously. This
new paradigm known as Industry 4.0. This conception is the introduction of digital network-linked
intelligent systems, in which machines and products will communicate to one another in order to
establish smart factories in which self-regulating production will be established. In this article, at first
the essence, main goals and basic elements of Industry 4.0 conception is described. After it the
autonomous systems are introduced which are based on multi agent systems. These systems include
the collaborating robots via artificial intelligence which is an essential element of Industry 4.0.
Keywords: Industry 4.0; Cooperating robots; Artificial intelligence.
1. INTRODUCTION
Industry 4.0 conception means the upcoming 4th industrial revolution. According to the
theory of the conception, the 1st industrial revolution was the mechanization characterized
by the appearance of the steam engine (Figure 1.). The 2nd industrial revolution was the
mass production through assembly lines on the base of the electricity. The 3rd industrial
revolution was the automated production by application of industrial robots [1].
The 4th industrial revolution means the age of the application of intelligent
manufacturing robots. In this conception the products control their own production, since
these products and components communicate with the machines and equipment by unique
product codes during their production. Smart factories will be self-regulating and optimize
their own operation. Consequently, it means that virtual and actual reality merges together
during the production.
In the first part of the article the characteristics, main goals and pillars of Industry 4.0
conception is described. In the second part of the paper the autonomous systems are
introduced which are based on multi agent systems. These systems include the
collaborating intelligent robots via artificial intelligence which is an essential pillar of
Industry 4.0 conception.
1MSc., Institute of Information Science and Technologies
Benrabab1@gmail.com
2PhD., Institute of Information Science and Technologies
iitdl@uni-miskolc.hu
3515 Miskolc, Hungary, University of Miskolc
3PhD., Institute of Logistics
altkovac@uni-miskolc.hu
3515 Miskolc, Hungary, University of Miskolc

78 Rabab Benotsmane˗László Dudás˗György Kovács
Figure 1. Stages of industrial development [2]
2. CHARACTERISTICS AND GOALS OF INDUSTRY 4.0 CONCEPTION
The essence of Industry 4.0 conception is the introduction of network-linked intelligent
systems, which realize self-regulating production: people, machines, tools and products will
communicate with each other continuously [3, 4]. Products control their own production;
the production scheduling will be controlled by the communicating products.
In smart factories everything is working in interaction between the products and the
machines, linked in a network itself connected to the digital supply chain, based on
information and communication technologies, sensors, software tools, using the highest
performance devices in order to transform industry into an interconnected global system
[5].
New technologies appear such as digitization in order to provide continuous
communication between machines, systems and products. The aim of the conception is to
make factories smarter and to create a digital platform, which brings together the main
tools: Sensors, Internet of things, Big data, Cloud computing, Collaborating robots,
Artificial intelligence, etc. [6].
Industry 4.0 conception is the origin of strategic project of the German government, that
was introduced at the Hanover Fair in 2011 [7], to support the digital revolution of the
global industry. Recently this conception is widely used not only in Europe but all over the
world.
The 5 main elements of the digital networked production according to the conception
can be defined by the following:
1. digital workpieces,
2. intelligent machines,
3. vertical network connection,
4. horizontal network connection,
5. smart workpieces.

The concept of autonomous systems in Industry 4.0 79
The essential goals of Industry 4.0 conception are the following:
• to create smart factories,
• to optimize the production which increase productivity,
• to establish more efficient, more flexible, and more customer-oriented production,
• to improve efficiency by automation of processes,
• to maximize the utilization of human- and machine resources,
• to save costs and reduce wastes and lead times,
• to adapt to the changing market demands more effectively,
• to create new opportunities and business models.
The results of application of the conception:
• physical systems will be digitized,
• customers will be satisfied who demand more complex and unique products in small
quantities,
• traditional centrally controlled and monitored production processes will be replaced
by decentralized controlling,
• factories will be self-regulating which optimize their own operation,
• productivity will be improved,
• fast solutions can be provided in case of production problems and abnormal
operations.
Industry 4.0 represents a globally interconnected world defined by digitization of economic
and production processes [8].
The Boston Consulting Group has identified the fundamentals of Industry 4.0 by nine
technological pillars [9] (Figure 2.):
1. Autonomous robots. Industrial robots are becoming more autonomous and
cooperative. The intelligent robots can interact with one another in order to improve
productivity and product quality. These machines can achieve more complex tasks
and manage unexpected problems [10].
2. Horizontal and Vertical system integration. Horizontal integration of system
elements aims to optimize the operation of the whole supply chain by connecting all
members of the value chain (e.g. suppliers, manufacturers, service providers,
customers). Vertical integration aims to optimize the reconfiguration of production
processes by connecting Cyber Physical Systems (sensors, actuators, etc.).
3. Industrial Internet of Things (IoT). Industrial IoT allows devices to communicate
and interact with one another. It is a network connection and data exchange of
objects, e.g. products, machines, equipment, vehicles or other incorporated devices,
so the devices can be used more efficiently and economically. System collects and
shares huge amounts of data inside the digital supply chain network that ensures the
exchange of information between the system elements.
4. Simulation. Simulation of processes is essential during product design, production
planning and in case of material flow processes, or in modeling of unexpected
stochastic events. In the future simulation will be used more often in plant
operations as well. Simulation is a tool for providing real-time data to observe the
physical world in a virtual surrounding, which can include machines, tools, products
and humans. It is an effective tool to optimize the production and maximize the
utilization of resources.

80 Rabab Benotsmane˗László Dudás˗György Kovács
5. Additive manufacturing. Additive Manufacturing is a terminology to describe the
technologies that build 3D objects by adding layer upon layer of a given material
(3D printing). This technology offers the possibility of manufacturing of more
complex components which is unachievable by other techniques. The technology
provides higher flexibility and efficiency of manufacturing of smaller batches and
more customized final products.
6. Cloud computing. The cloud offers an unlimited computing power to receive, store
and analyze Big Data needed for the optimal operation of systems. The stored
information and services can be available at any given place and device via internet
[12]. It allows all system elements to synchronize their activities and work on shared
data and services simultaneously in real time.
7. Augmented reality. Augmented reality provides the possibility of visualization by
transforming the real environment to a virtual environment [13]. The information
relating to the surrounding real world of the user becomes interactive and digitally
manipulable by the application of augmented reality technology.
8. Big data. Intelligent network-like systems require huge, almost unmanageable
amount of information. This data set is called big data. According to the IoT
principles, the collection and evaluation of this data set coming from many different
sources will become essential for real-time decision-making. The analysis of this
huge amount of information will optimize the operation of manufacturing systems.
9. Cybersecurity. The huge amount of data shared on network should be protected.
Cybersecurity includes technologies and processes which are designed to protect
systems, networks and data from cyber-attacks.
Figure 2. Pillars of Industry 4.0 [11]

The concept of autonomous systems in Industry 4.0 81
3. ARTIFICIAL INTELLIGENCE BASED ROBOT COLLABORATION
This age is the age of emerging intelligence, in every aspect of life. The questions of
human-robot and robot-robot cooperation become actual for today [14]. While this new
industrial age also has effects on social-level, industrial applications are in the forefront of
our article and require deeper analysis. Our research is carried out in accordance with the
Industry 4.0 concept, in which unmanned production and the development of smart
factories with intensive and wide use of artificial intelligence in many aspects are aimed at
automating of production forces on an unprecedented level. In the technical realization the
two central AI-related disciplines are Multi-Agent Systems and Distributed AI. In addition
to these essential information technologies the biologically inspired new ideas and methods
are also need mentioning.
Typically, in this regard an autonomous system is based on a multi-agent system which
is endowed by artificial intelligence, this concept aims to create intelligent machines
collaborating together to build a flexible environment [14] as shown in Figure 3 which
represents collaborating and cooperating manipulator arms in industry. These industrial
innovations are in the focus of today researches, some achievements and human-related
safety requirements are documented in the ISO 10218-1 Robot, ISO 10218-2 Robot
system/cell and in the ISO/TS 15066 Collaborative Robots standards [15].
Figure 3. Collaborating robots
3.1. Multi agent systems (MAS)
The agents can detect the signals of the environment and react to them. So people,
machines, computers, etc. can be agents and can cooperate and interact each other. In the
industry, these agents represent machines, controllers, robots which use a common
language to provide cohabitation and collective work. To design a multi-agent system, we
must know the model of each agent that will come into action and define their environment
and their interactions and the essential objectives to achieve [16 ]. A borderline can be set
up between reactive and cognitive agents: in opposition to the simple reflexive reactive

82 Rabab Benotsmane˗László Dudás˗György Kovács
agents the cognitive agents are can form plans to achieve their goals. Based on [17], two
types of communication among these agents can be defined:
1. Implicit communication. In this method the agent that uses various sensors
receives information about other agents acting in the same system through the
appropriate environment. This type of communication can be divided into passive or
active implicit types. The passive means that the agents communicate via their
environment, while the active use sensing to get the information.
2. Explicit communication. In this case there is direct communication among agents
for information sending and receiving, which can be done in the form of unicast or
intentional broadcast messages usually through a dedicated communication module.
This explicit communication helps to realize diverse coordination methods among
agents.
Ought to this explicit communication the agents can realize different advantageous
strategies. Meanwhile they alternate the active and passive roles and communicate with
messages according to the common strategies introduced by the following definitions [18,
19]:
• Coordination strategy of the agent means that they make a plan for longer period
that determines the arrangement and order of the tasks to be executed together. The
goal of the coordination is to unite the resources and forces to achieve the common
goal effectively. Agents use coordination protocols to define the requirements and
actions that are needed to fulfill the common goal.
• Cooperation strategy of the agents aims of solving such larger or complex tasks
that are too large for an individual agent. The strategy consists of the optimal
decomposition of the larger task into subtasks and has to take into the capabilities
and possibilities of the cooperating agents.
• Negotiation strategy of agents is necessary when the agents have different goals but
they would like to achieve a mutually advantageous solution. The two components
of this strategy are:
o Negotiation language helps to perform the communication and to transfer the
information analyzing the semantic of the content moreover defines the role of
communication primitives in the used protocols,
o Process of negotiation determines the behavior of the agents during negotiation.
3.2. Artificial Intelligence (AI)
This discipline is a prospect to the future. Includes many human intelligence inspired
techniques that can substitute human beings in their mental and cognitive activity [20].
Methods of AI used by the autonomous systems to solve high level tasks and unforeseen
situations. These methods implemented in machines, IoT components and in manipulator-
like and humanoid robots. The AI phenomenon can’t be separate from learning and from
adaptation of the agents to their environment [21]. The AI agent models the necessary part
of the world using different knowledge representation methods, like symbolic logic,
semantic networks and frames, or artificial neural networks. For the realization of the
intelligence different kinds of cognitive methods applied, like learning, concept
formalization, reasoning, searching, machine vision and even communication language.

The concept of autonomous systems in Industry 4.0 83
3.2.1. Distributed Artificial Intelligence (DAI)
This work deployment method can be used effectively when the tasks are distributable but
every of them needs intelligent solution. The DAI structure includes agent cooperation and
communication among intelligent agents [16]. DAI has an overlapping with MAS concept.
The relation among software systems based on agent technologies like DAI, MAS and
mobile agents (MA) is shown in Figure 4.
Figure 4. Relation among software systems based on agent technologies
3.2.2. Role of Multi Agent Systems in Industry 4.0.
Using a MRS in Smart factory can have several potential advantages over a single-agent
system such as robot [17]:
• A MRS has a better spatial distribution.
• A MRS can achieve better overall system performance. The performance metrics
could be the total time required to complete a task or the energy consumption of the
robots [22].
• A MRS introduces robustness that can benefit from data fusion and information
sharing among the robots, and fault-tolerance that can benefit from information
redundancy. For example, multiple robots can localize themselves more efficiently
if they exchange information about their position whenever they sense each other
[23].
• A MRS can have a lower cost. Using a number of simple robots can be simpler (to
program), cheaper (to build) than using a single powerful robot (that is complex and
expensive) to accomplish a task.
• A MRS can exhibit better system reliability, flexibility, scalability and versatility.
Robots with diverse abilities can be combined together to deal with complex task,
and one or several robots may fail without affecting the task completion [24].
3.2.3. Applied AI Methods in Intelligent Robot Behavior
The intelligence coming from different AI methods can be used in standalone robots to help
its working, like Swarm intelligence based joint position optimization, or use of
feedforward Artificial Neural Network for solving the inverse kinematical problem when
the determination of joint functions depending from the necessary path of the robot hand is
needed. In the future robots the use of AI will not be limited for solving such motion-
oriented tasks but can be imagined in cognitive processes like sensing, learning, problem
solving, machine vision and using language for communication [25]. These high level
cognitive functions that may evolve to machine problem solving, play important role in

84 Rabab Benotsmane˗László Dudás˗György Kovács
robot coordination, cooperation, evaluation and collaboration [18, 26]. The next table
systematize the well-known AI methods that can be used in different scenarios of collective
behavior of robots (see Table 1.)
Table I.
AI methods and their possible use in robots collaboration
AI method Role in collective robots behavior
Rule and symbolic logic based systems
[28] Knowledge representation, cooperative decision
making
Fuzzy Logic [29] Flexible common answering on environment
changes, decision making
Machine vision and sensing [30] Getting visual information of the objects and
location and actions of other robots, help self-
and cooperative localization
Possibility for detection of malfunctions
Serves as information source for – collective –
learning
Search methods Cooperative decision making and optimization
Evolutionary and genetic algorithm [31] Robot group efficiency and quality improvement
Swarm intelligence [32, 33]:
- Ant colony optimization
- Particle swarm optimization
- Shortest route finding
Creation of complex structures
System self-reorganization
Collective behavior planning and directing:
- Collective optimization
- Resources integration
- Common goal realization
Artificial Neural Networks [30] Process control and abnormality detection
Learning new features of the environment and
new scenarios through clustering
Cooperative decision making
3.2.4. The potential advantages of AI to many solutions in practice
Thanks to recent advances in artificial intelligence (AI), we are now at the cusp of a major
transformation in business, many leading companies have begun to embrace a new view of
business processes as more fluid and adaptive. In essence, they are moving beyond rigid
assembly lines toward the idea of organic teams that partner of humans with advanced AI
systems. This collaboration between workers and smart machines is leading to the
reinvention of many traditional processes. As BMW and Mercedes-Benz have experienced,
rigid assembly lines are giving way to flexible teams of employees working closely
alongside robots. Moreover, these novel types of teams can continuously adapt on the fly to

The concept of autonomous systems in Industry 4.0 85
new data and market conditions [34]. They are enabling companies to actually reimagine
various work processes.
Contrast the traditional assembly line with a factory where robots are much smaller and
more flexible, able to work alongside humans. This is a factory, where those robots and
other types of machinery are using embedded sensors and sophisticated AI algorithms.
Unlike earlier generations of industrial robotics which were typically bulky, unintelligent,
and somewhat dangerous pieces of machinery these new types of collaborative robots are
equipped with the ability to sense their environment, comprehend, act, and learn, thanks to
machine-learning software and other related AI technologies. All this then enables the work
processes to be self-adapting, with fixed assembly lines giving way to flexible human-
machine teams that can be put together on the fly.
Now, in order to fulfil customized orders and handle fluctuations in demand, employees
can partner with robots to perform new tasks without having to manually overhaul any
processes or manufacturing steps. Those changes are baked into the system and are
performed automatically. The advances are not just in manufacturing. AI systems are being
integrated across all departments, everything from sales and marketing to customer service
and production.
3.2.5. Implementation of AI at Companies
For a century, factory floors have been at the leading edge in robotic automation. From
conveyor belts to robotic arms with AI-infused operations systems, the factory is getting
smarter every day [27].
• Hitachi is using AI to analyze big data and workers’ routines to inform its robots,
which deliver instructions to employees to meet real-time fluctuating demand and
on-site kaizen objectives. In a pilot, the company observed an 8 percent productivity
improvement in logistics tasks.
• At Siemens, armies of spider-styled 3-D printed robots use AI to communicate and
collaborate to build things in the company’s Princeton lab. Each bot is equipped
with vision sensors and laser scanners. In aggregate, they join forces to manufacture
on the go.
• At Inertia Switch, robotic intelligence and sensor fusion enable robot-human
collaboration. The manufacturing firm uses Universal Robotics’ robots, which can
learn tasks on the go and can flexibly move between tasks, making them handy
helpers to humans on the factory floor.
4. SUMMARY
The content of the paper was divided into two parts. In the first the concept of Industry 4.0
automatization trend was introduced by introducing its main goals and its expectable
benefits, then the components that bring together the nine pillars of this industrial
revolution were analyzed, which can be defined as a cyberspace that controls everything
from demand to product design. This evolution includes intelligent automation and
integration of digital technologies like 3D printer, cloud computing, augmented reality,
Internet of Things, etc.
Secondly it discussed the autonomous systems that represent a useful factor for
successful digital transformation of the manufacturing and create a smart factory, known as

86 Rabab Benotsmane˗László Dudás˗György Kovács
multi-agent systems, in the industrial field these agents can be manipulators arms, sensors,
controllers endowed by artificial intelligence, this approach is one of the technologies
supported by Industry 4.0, it regroups different fields of research such as collaboration
between these agents based on the communication among them and their environment and
the principle of collective work led by swarm intelligence. The role of AI in the
environment of collaborating robots was described in a table covering all the important
main AI fields.
References
[1] Ahuett-Garza, H. & Kurfess, T. (2018). A brief discussion on the trends of habilitating
technologies for Industry 4.0 and Smart Manufacturing. Manufacturing Letters, 15, 60-63.
https://doi.org/10.1016/j.mfglet.2018.02.011
[2] Industry 4.0 and industrial IoT in manufacturing: A sneak peek. Retrieved from
https://www.aberdeen.com/ /opspro-essentials/industry-4-0-industrial-iot-manufacturing-sneak-
peek/
[3] Jay, L., Behrad, B. & Hung-An, K. (2015). A Cyber Physical Systems architecture for Industry
4.0 - based manufacturing systems. Manufacturing Letters, 3, 18-23.
https://doi.org/10.1016/j.mfglet.2014.12.001
[4] Stock, T. & Seliger, G. (2016). Opportunities of sustainable manufacturing in Industry 4.0.
Procedia CIRP, 40, 536-541. https://doi.org/10.1016/j.procir.2016.01.129
[5] Robla-Gomez, S., Becerra, V. M., Llata, J. R., Gonzalez-Sarabia, E., Torre-Ferrero, C. & Perez-
Oria, J. (2017). Working Together. A Review on safe human-robot collaboration in industrial
environments. IEEE Access, 5(26), 754-773. https://doi.org/10.1109/ACCESS.2017.2773127
[6] Zhong, R. Y., Klotz, X., Xu, E. & Newman, S. T. (2017). Intelligent manufacturing in the
context of Industry 4.0. A Review Engineering, 3(5), 616-630.
https://doi.org/10.1016/J.ENG.2017.05.015
[7] Sung, T. K. (2017). Industry 4.0: A Korea perspective. Technological Forecasting and Social
Change, 132, 40-45. https://doi.org/10.1016/j.techfore.2017.11.005
[8] Vaidya, S., Ambad, P. & Bhosle, S. (2018). Industry 4.0 - A Glimpse. Procedia Manufacturing,
20, 233-238. https://doi.org/10.1016/j.promfg.2018.02.034
[9] Burke, R., Mussomeli, A., Laaper, S., Hartigan, M. & Sniderman, B. The smart factory -
Responsive, adaptive, connected manufacturing. Retrieved from https://www2.deloitte.com/
insights/us/en/focus//industry-4-0/smart-factory-connected-manufacturing.html
[10] Kostal, P., Kiss, I. & Kerak, P. (2011). The intelligent fixture at flexible manufacturing. Annals
of the Faculty of Engineering Hunedoara – International journal of Engineering 9(1), 197-200.
[11] Industry 4.0 - The next revolution is here! Retrieved from
http://www.criticalmanufacturing.com/ en/ /newsroom/blog/posts/blog/industry-4-0-the-next-
revolution-is-here#.XAqpwNtKjb0
[12] Avornicului, M. (2013). Cloud computing: challenges and opportunities for small and medium-
sized business. Forumul Economic, 16(111), 32-45.
[13] Gubán, M. (2011). Non-linear programming model and solution method of ordering controlled
virtual assembly plants. In Proceedings of Logistics - The Eurasian Bridge: Materials of V
International Scientifically-Practical Conference, Krasnoyarsk, 49-58.
[14] Bonarini, A., Matteucci, M. & Restelli, M. (2001). Concepts for Anchoring in Robotics. Project
department of electronics and information. Retrieved from https://chrome.deib.polimi.it/
images/d/dc/Bonarini_2001_AIIA.pdf, https://doi.org/10.1007/3-540-45411-X_34
[15] Matthias, B. & Reisinger, T. (2016). Example application of ISO/TS 15066 to a collaborative
assembly scenario. 47th International Symposium on Robotics, Munich, Retrieved from
https://www.researchgate.net/publication/310951754_Example_Application_of_ISOTS_
15066_to_a_Collaborative_Assembly_Scenario

The concept of autonomous systems in Industry 4.0 87
[16] Stone, P., Ave, P. & Park, F. (1995). Multiagent Systems: A Survey from a machine learning
perspective. Robotics, 8, 345-353.
[17] Yan, Z., Jouandeau, N. & Cherif, A. (2013). A survey and analysis of multi-robot coordination.
Journal of Advanced Robotic Systems,10, 399-412. https://doi.org/10.5772/57313
[18] Zoghby, N. E., Loscri, V., Natalizio, E. & Cherfaoui, V. (2014). Robot cooperation and swarm
intelligence. World Scientific Publishing Company, 168-201.
https://doi.org/10.1142/9789814551342_0008
[19] Nicolle, A. (2000). L'organisation dans les systèmes multi-agents. Journées Colline, Ch. 1
[20] Lima, P. U. & Custodio, M. (2004). Artificial intelligence and systems theory: Applied to
cooperative robots. Journal of Advanced Robotic Systems, 1, 141- 148.
https://doi.org/10.5772/5630
[21] Wei, X. (2018). Artificial intelligence in robot control systems. IOP Conference Series:
Materials Science and Engineering, 363, 12-19. https://doi.org/10.1088/1757-
899X/363/1/012013
[22] Fox, D., Burgard, W., Kruppa, H. & Thrun, S. (2000). A Probabilistic Approach to
Collaborative Multi-Robot Localization. In Special issue of Autonomous Robots on
Heterogeneous Multi-Robot Systems. 8(3), pp. 325–344.
https://doi.org/10.1023/A:1008937911390
[23] Prorok, A., Bahr, A. & Martinoli, A. (2012). Low-Cost Collaborative Localization for Large-
Scale Multi- Robot Systems. Proceedings - IEEE International Conference on Robotics and
Automation. pp. 4236-4241. https://doi.org/10.1109/ICRA.2012.6225016
[24] Wawerla, J. & Vaughan, R. (2018). A Fast and Frugal Method for Team-Task Allocation in a
Multi-robot Transportation System. Proceedings - IEEE International Conference on Robotics
and Automation. pp. 1432–1437.
[25] Wang, P., Liu, H., Wang, L. & Gao. R. X. (2018). Deep learning-based human motion
recognition for predictive context-aware human-robot collaboration. CIRP Annals -
Manufacturing Technology, 67(1), 17-20. https://doi.org/10.1016/j.cirp.2018.04.066
[26] Blum, C. & Li, X. (2008). Swarm intelligence - Introduction and applications. Swarm
Intelligence in Optimization, Springer, pp. 43-85. https://doi.org/10.1007/978-3-540-74089-6_2
[27] Daugherty, P. R. & Wilson, H. J. (2018). Human + Machine: Reimagining Work in the Age of
AI. Harvard Business Review Press.
[28] Sun, S. & Chen, J. ( 2014). Knowledge Representation and Reasoning Methodology based on
CBR Algorithm for Modular Fixture Design. Journal of the Chinese Society of Mechanical
Engineers, 28(6), 593-604.
[29] Earl, C. (1995). The Fuzzy Systems Handbook: A Practitioner’s Guide to Building, Using, and
Maintaining Fuzzy Systems. SIAM Review. 37, 281-282. https://doi.org/10.1137/1037078
[30] Benyoucef, L. & Grabot, B. (2010) Artificial Intelligence Techniques for Networked
Manufacturing Enterprises Management. Springer Series in Advanced Manufacturing.
https://doi.org/10.1007/978-1-84996-119-6
[31] Haupt, R. & Wiley, A. (1998). Algorithms practical genetic algorithms. John Wiley & Sons,
Inc.
[32] Bayindir, L. & Sah, E. (2007). A review of studies in swarm robotics. Turkish Journal of
Electrical Engineering and Computer Science, 15, 115-147.
[33] Baheci, I. & Sahin, E. (2005). Evolving aggregation behaviours for swarm robotic systems: a
systematic case study. In Proceedings of IEEE Swarm Intelligence Symposium, Pasadena, 333-
340.
[34] Nikolaus, C. (2017). How Investing in Robots Actually Helps Human Jobs, Time. Retrieved
from http://time.com/4721687/investing-robots-help-human-jobs/