Conference PaperPDF Available

Towards an Operator 4.0 Typology: A Human-Centric Perspective on the Fourth Industrial Revolution Technologies


Abstract and Figures

[BEST PAPER AWARD] This paper presents early concepts and future projections of the so-called ‘Operator 4.0’, understood as a smart, skilled operator who performs not only cooperative work with robots but also aided work by machines as and if needed by means of human cyber-physical systems, advanced human-machine interaction technologies and adaptive automation towards achieving human-automation symbiosis work systems. This research introduces an Operator 4.0 typology as well as exploring a set of key enabling technologies that can support the development of human-automation symbiosis work systems for the Operator 4.0 in the Factory of the Future defined within the Industry 4.0 framework.
Content may be subject to copyright.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
David Romero1,4
, Johan Stahre2, Thorsten Wuest3, Ovidiu Noran4,
Peter Bernus4, Åsa Fast-Berglund2, Dominic Gorecky5
1Tecnológico de Monterrey, Mexico
2 Chalmers University of Technology, Sweden ,
3West Virginia University, USA
4Griffith University, Australia ,
5German Center for Artificial Intelligence, Germany
This paper presents early concepts and future projections of the so-called Operator 4.0’, understood
as a smart and skilled operator who performs not only cooperative work with robots but also work aided
by machines as and if needed by means of human cyber-physical systems, advanced human-machine
interaction technologies and adaptive automation towards achieving human-automation symbiosis
work systems. This research introduces an Operator 4.0 typology as well as exploring a set of key
enabling technologies that can support the development of human-automation symbiosis work systems
for the Operator 4.0 in the Factory of the Future defined within the Industry 4.0 framework.
Keywords: Industry 4.0, Operator 4.0, Human Cyber-Physical Systems, Advanced Human-Machine
Interaction Technologies, Adaptive Automation, Human-Automation Symbiosis, Work Systems,
Socially Sustainable Manufacturing, Exoskeletons, Augmented Reality, Virtual Reality, Wearable’s,
Intelligent Personal Assistants, Collaborative Robots, Social Networks, Big Data Analytics.
The German program Industrie 4.0 (or Industry 4.0) and corresponding international initiatives (e.g.
Smart Manufacturing, USA & Smart Factory, South Korea) will continue to transform the industrial
workforce and their work environment through 2025 [1]. This will have significant implications on
the nature of work in industry as Industry 4.0 will transform design, manufacture, operation, and
service of products and production systems [2]. At the same time, the demography is changing,
especially in Europe and Japan, which brings forth additional challenges for manufacturing
companies. Increasing immigration may relieve some of the effects of demographic change.
Corresponding Author
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
However, integration of new migrant workers with a high variety of technical skill and educational
levels and different culture is considered a great challenge. As a consequence, near-future
manufacturing enterprises, and in particular smart factories as socio-technical systems, will need
to form and adapt a social perspective to be proficient in assisting ageing, disabled and apprentice
operators by using advanced digital and industrial enabling technologies to help people to remain
in, return to or incorporate into the modern manufacturing workforce. Meanwhile, considering
the developments from a technical perspective, new connectivity and interaction technologies
among parts (cf. smart products), machines (cf. smart machines) and humans (cf. smart operators)
will make production systems more lean, agile, traceable, and adaptable [2] [3] [4].
To successfully embrace the Industry 4.0 paradigm in a socially sustainable way, manufacturing
enterprises will need to accompany its technological transformations with training and development
programs for their workforce, in new tools and technologies that skilled labor uses and by which
the operators are directly and indirectly affected. Furthermore, new working environments such as
the cyber-physical factory will directly affect the operator and the nature of work, creating new
interactions not only between humans and machines, but also between digital and physical worlds.
Therefore, socio-technical transformation towards the factory of the future (cf. factory 4.0 / smart
factory) will need new design and engineering philosophies for twofold ‘human-centric and cyber-
physical production systems where automation, robotics, and other advanced manufacturing
technologies are seen as possibilities for the further enhancement and augmentation of the human’s
physical, sensorial and cognitive capabilities rather than for unmanned, autonomous factories [5].
This new approach requires the rethinking of simple work design, moving towards design methods
similar to those used to design the working environment for aircraft pilots, process industry
operators and military personnel. These would typically include human supervisory control and
human situation awareness.
This paper explores early manifestations and future projections of the Operator 4.0 [5] as a smart
and skilled operator who performs not only - ‘cooperative work’ with robots - but also - work
aided’ by machines as and if needed - by means of human cyber-physical systems, advanced human-
machine interaction technologies and adaptive automation towards “human-automation symbiosis
work systems”. This research work introduces an Operator 4.0 typology as well as explores a set
of key enabling technologies for supporting the development of ‘human-automation symbiosis work
systems for the Operator 4.0 in the Factory of the Future.
The vision of the Operator 4.0 aims to create trusting and interaction-based relationships between
humans and machines, making possible for those smart factories to capitalize not only on smart
machines strengths and capabilities, but also empower their smart operators with new skills and
gadgets to fully capitalize on the opportunities being created by Industry 4.0 technologies. Hence,
a socially sustainable factory within the Industry 4.0 framework is a workplace where work systems
design and engineering uses collaborative robotics, kinematics, human-in-the-loop control systems,
sensors, manipulation, navigation and adaptive automation to improve the knowledge and
capabilities of operators. In this sense, a human-centric production system is characterized by
allowing a unification of planning and implementation, expecting the operator to be in control of
the work process and the technology and fostering the utilization of human competencies [6].
Furthermore, a human cyber-physical production system (H-CPPS) is defined as a work system
that improves operators’ abilities thanks to a dynamic interaction between humans and machines in
the cyber- and physical-worlds by means of ‘intelligent’ human-machine interfaces. H-CPPS will be
using human-computer interaction techniques designed to fit the operators’ cognitive and physical
needs, and improve human physical-, sensing- and cognitive-capabilities, by means of various
enriched and enhanced technologies [5]. Moreover, these cyber-physical and human-machine
interactions are supervised and controlled by adaptive control systems [7] [8] [9] within the human-
in-the-loop [10] paradigm and based on sharing and trading of control strategies [11] (e.g. critical-
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
event, measure-based and/or modeling-based) in order to allow a dynamic and seamless transition
of functions (tasks) allocation between humans and machines, always aiming for the operator
inclusiveness without compromising the production objectives [5].
This section presents an Operator 4.0 typology that depicts how the Industry 4.0 technologies can
assist operators to become smarter operators in their future factory workplaces (see Figure 1),
from a social manufacturing perspective. Furthermore, it is important to mention that these types
of Operators 4.0 may exist on the shop-floor as either single- or hybrid- types. A selection of various
augmentations of the original human capabilities are presented below; note however, that there
might be multiple other aspects that are part of the Operator 4.0. Those augmentations do not
only come in a variety of levels but also can be combined. It is also very likely that the future
Operator 4.0 may only be augmented in one specific area whereas the other aspects are neglected.
In some cases that will not even be possible (e.g. augmented reality functionality necessarily needs
a ‘connected operator’ to perform).
Figure 1: Operator 4.0 Typology
2.1 Operator + Exoskeleton = Super-Strength Operator [physical interaction]
Powered (Industrial) Exoskeletons are wearable lightweight, flexible and mobile, representing a
type of biomechanical system where the human-robotic exoskeleton powered by a system of
motors, pneumatics, levers or hydraulics works cooperatively with the operator to allow for limb
movement, increased strength and endurance. The idea of wearable exoskeletons has been around
for decades in industry, aiming to use powered mechanics to increase the strength of a human
operator for effort-less manual functions (tasks) (e.g. [12]).
Powered exoskeletons can help to reduce the trade-offs between manual and automated operations
in production systems - in other words, between flexibility and efficiency in balanced automation
systems as well as to increase the social sustainability of factories in the long-term, especially with
the outlook of a larger proportion of elderly workers due to changing demography.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
Powered exoskeletons may allow (e.g. in an assembly area, where most manual work takes place)
to have humans and technology cooperate in order to simplify the job and reduce the physical stress,
thus making the overall system more efficient and productive by auxiliary processes such as safe
lifting and moving of heavy items, enhancement of physical capabilities (endurance) to stay longer
in a demanding position or additional strength for handling weighty tools. In general, powered
exoskeletons can offer additional protection, support and strength to the operators and contribute
to the social sustainability of the workforce by improving the ergonomics of manual operations
(occupational health), helping to reduce injuries and accidents because of heavy work (safety),
boosting productivity and quality of work by improving the operator workload-handling capabilities
(e.g. decreasing the physical workload and relocating the energy to the sensorial and cognitive
capabilities), and assisting to keep elder/experienced operators longer in critical positions by
compensating for their loss of strength due to aging, while still capitalizing on their knowledge and
experience. An additional advantage is the possibility to equip the exoskeleton with tools and (heavy)
supporting equipment, which in the exoskeleton absence would reduce the humans’ productivity.
An example of this type of Operator 4.0 is the Robo-Mate system, defined as: “a user-friendly intelligent
cooperative light weight wearable human-robotic exoskeleton for manual handling work” [13].
2.2 Operator + Augmented Reality = Augmented Operator [cognitive interaction]
Augmented Reality (AR) is a technology enriching the real-world factory environment of the smart
operator with digital information and media (sound, video, graphics, GPS data, etc.) that is overlaid
in real-time in his/her field of view (e.g. head-gear, smart-phones, tablets or spatial AR projectors).
Hence, AR can be considered a key enabling technology for improving the transfer of information
from the digital to the physical world of the smart operator in a non-intrusive way.
AR technology may offer significant advantages (e.g. faster cycle times, reliability, reduced failure
rate and traceability) to support the smart operator in real-time during manual operations by
becoming a digital assistance system for reducing human errors and at the same time reducing
the dependence on printed work instructions, computer screens and operator memory, which need
to be interpreted first by a skilled worker. AR for example can enable ‘digital poka-yokes systems
for work-intensive functions (tasks) in order to reduce defects, rework and redundant inspection
by offering intuitive information and combining operator intelligence and flexibility with error-
proofing systems to increase the efficiency of manual work steps, while improving the quality of
work [14]. Moreover, AR technology can incorporate a new human-machine interface to manufacturing
IT applications and assets, displaying real-time feedback about smart manufacturing processes and
machines to the smart operator in order to improve decision-making [15]. This can be implemented
at machine level using traditional Programmable Logic Controllers (PLCs) and Supervisory Control
& Data Acquisition (SCADA) systems but also emerging Internet of Things (IoT) technologies for
assets condition monitoring. AR can be implemented also at mid-level operations like Manufacturing
Execution Systems (MES), novel production line simulations and big data-driven quality controls and
at higher levels such as the Enterprise Resource Planning (ERP) systems.
At machine level, AR can redefine the maintenance and repair of equipment, by means of diagnostic
intelligence derived from real-time sensor data about a machine or part performance; at operations
and enterprise levels, AR can allow production managers to view production KPIs and have an intra-
factory overview of workstations and production lines in real-time for monitoring, identifying,
analyzing, diagnosing and resolving problems and flaws (e.g. alerting on deviations) to keep
manufacturing processes moving towards operational efficiency. Furthermore, AR technology acting
as tag reader' may also create new human-product interactions enabled by QR codes, GPS, OCR,
barcodes, RFID and NFC technologies, allowing the smart operator to retrieve current and historical
information about a product and monitor and configure data and settings about it.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
Presently, an early-stage example of this type of Operator 4.0 is the Satisfactory system, defined as
“an augmented-enabled ecosystem for increasing satisfaction and working experience in smart
factory environments” [16].
2.3 Operator + Virtual Reality = Virtual Operator [cognitive interaction]
Virtual Reality (VR) is an immersive interactive multimedia and computer-simulated reality that can
digitally replicate a design, assembly or manufacturing environment and allow the smart operator
to interact with any presence within (e.g. a blueprint, a hand-tool, a product, a machine tool, a
robot, a production line, a factory), with reduced risk and real-time feedback.
VR technology can provide a combination of interactive virtual reality and advanced simulations of
realistic scenarios for optimized decision-making and training for the smart operator. For example,
at product design and engineering stage, VR will transform blueprints into 3D virtual models where
all types of design rules, guidelines and methodologies (cf. Design for eXcellence) can be digitally
threaded to upstream design and engineering decisions and check their impact along the product
lifecycle (e.g. design for manufacturability, design for assembly, design for serviceability, design
for maintainability, design for disassembly, design for repair-reuse-recyclability, etc.); at product
assembly stage, CAD models of parts, hand-tools and assemblies can be transformed into interactive
virtual simulations (assembly sequences) for training operators in complex assembly tasks; and at
product manufacturing stage, VR brings to life the ‘virtual factory’ as an integrated simulation model
of the major sub-systems of a factory in order to evaluate different factory layouts (arrangements
of machinery, equipment and inventories for smooth flow of work, material and finished products),
production line configurations (manufacturing processes sequences), production balance (automation
vs. mechanization) and production schedules (work and workloads scheduling) in order to optimize
the production master plan by means of what-if analyses, decision support systems and estimation
Several commercial software tools for Virtual Product Design (VPD), Computer-Aided Design (CAD),
and Computer-Aided Engineering (CAE) are available on the market. VR systems for dynamic
representation of humans are also available. Some examples of software supporting the Operator 4.0
are the VISTRA system: a virtual simulation and training system, which is used to train operators
and test manual assembly processes [17], and the VFF system: “a holistic, extensible, scalable
and standard virtual factory framework and integrated simulation environment that considers
the factory as a whole and provides advanced planning, decision support and validation capability
features to production managers” [18].
2.4 Operator + Wearable Tracker = Healthy Operator [physical and cognitive interaction]
Wearable Trackers are devices designed to measure exercise activity, stress, heart rate and other
health-related metrics as well as GPS location and other personal data (e.g. biometrics). With
the dawn of commercially available solutions like the Apple Watch, Fit-bit and Android wear, many
people all over the world are already using aspects of this envisioned system. Military applications
are going a step further and employ data analytics on bio-data to predict potentially problematic
situations before they emerge, e.g., for Special Forces combat divers during missions. Currently
there are already first steps being made to take this to the next level, with the potential to track
the complex nature of the human brain during different activities. While this might take decades
to be applicable in industry, it gives an indication of the potential this might offer.
Without entering into data privacy issues, rules and employment as well as law implications, wearable
trackers (bio-data sensors) can drive positive change via improved productivity, well-being and
proactive safety measures for the workforce. Different application levels are possible, e.g. both at
the individual and collective level, with the system boundaries for the collective level being flexible.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
A smart operator for example can use personal analytics to plan and schedule his/her work-shifts,
rest-breaks and overtime based on health-related metrics, can monitor his/her physical workload
(exercise activity) and cognitive workload (mental effort) during the work-shift and set alerts and
warnings to manage proper levels of occupational effort and stress. Using advanced data analytics
on bio-data might allow for utilizing subconscious cognitive states and thus allow for a warning
mechanism for imminent danger and/or potential harm to the worker him-/her-self and/or others.
As an aggregation of operators’ personal analytics, ‘workforce analyticscan prevent urgent threats
to operators’ safety and also production quality by monitoring health-related metrics and workloads
and alert decision-makers (e.g. production line supervisors and factory managers) for example if
the stress levels are or workload is too high, which may lead to human errors (e.g. accidents or poor
quality of labor) or on the contrary if energy levels of operators are high, controlled aggressive
production targets can be set and pushed to the workforce. Moreover, operators’ location inside a
big factory or warehouse can improve internal logistics (e.g. response time) and help to locate and
allocate the closest operator to an urgent function (task) in-hand.
A present example of this type of Operator 4.0 includes the use of smart-watches to leverage
awareness of biometrics, so a smart operator can make better decisions in regards to his/her
occupational health care self-management (e.g. fitness, wellness, medical). In this basic example,
however, the required technology is available today and the advanced data analytics capability
needed is progressing fast.
2.5 Operator + Intelligent Personal Assistant = Smarter Operator [cognitive interaction]
An Intelligent Personal Assistant (IPA) is a software agent or artificial intelligence that has been
developed to help a smart operator in interfacing with machines, computers, databases and other
information systems as well as managing time commitments and performing tasks or services in a
human-like interaction [19].
One of the main features of IPAs is their capability to offer a voice-interaction technology (a natural
language interface) to the smart operator, which induces productivity and operational efficiency
by allowing the operator to go hands-free to complete certain tasks. Some scenarios where IPAs can
create advantages for the smart operator and offer personal assistance are: in searching and retrieving
from a digital library, based on a voice request, the repair or maintenance manual of a machine tool
or part and reading the instructions to the operator while he/she performs the task; in scheduling
and setting reminders for actions or critical events in operations, inventory or assets management
(e.g. re-certifications, check stocks, preventive maintenance); planning activities, where human
creativity can be applied to solve problems of routing or staffing while utilizing the IPA to store
and visualize the underlying planning data; in providing mobility and location assistance for logistics
(e.g. GPS-based geographical navigation) and warehouse stocks whereabouts (e.g. IPS-indoor positing
system); interfacing with connected devices through voice commands (e.g. voice user interfaces);
detecting and diagnosing errors and problems and suggesting troubleshooting tools and strategies
in smart, connected machines and systems; and building predictive models by tracking operator or
machine behavior and alerting for proactive actions.
A present example of this type of Operator 4.0 are Apple’s Siri, Android’s ‘Hey Google’ and especially
Amazon’s Alexa. Especially Amazon’s Alexa allows external developers to access the API and build
additional apps and services using the existing functionalities and infrastructure. Alexa can already
perform tasks like ‘finding suitable recipes’ and writing a shopping list tasks that translate easily
in a shop-floor environment.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
2.6 Operator + Collaborative Robot = Collaborative Operator [physical interaction]
Collaborative Robots (CoBots) are industrial robots (cf. humanoid, robotic arm or SCARA configurations)
capable of performing a variety of repetitive and non-ergonomic tasks and that have been specially
designed to work in direct cooperation with the smart operator by means of safety (e.g. force
sensing and collision) and intuitive interaction technologies, including easy shop-floor programming.
Popular examples are Rethink-Robotics’ Baxter & Sawyer, which promise low-cost and easy to use
collaborative robots.
CoBots will allow co-working spaces and interaction with their human counterparts without the need
for traditional safety barriers. These possibilities will create benefits such as recovering shop-floor
space normally lost due to safety barriers (cf. safety cage) and savings for the costs associated to
their implementation; increasing the smart operator productivity and job satisfaction by augmenting
him/her to accomplish a task more effectively and relieving him/her from tedious, non-ergonomic and
vulnerable tasks (e.g. difficult placement of parts, “third-hand” functionality for assembly, heavy
and repetitive lifting, loading and handling of hazardous materials). Another societal positive effect
emerging from close collaboration of humans and robots in the workplace may be the increasing
acceptance of robotic help in the healthcare domain, again, being estimated to being highly
relevant due to demographic change in some areas.
A present example of this type of Operator 4.0 is the LIAA CoBot system: “a hybrid assembly systems
combining manual and automatic workstations in symbiotic human-robot collaborations to achieve a
balance between investment costs, batch size and flexibility in the assembly line” [20]. The INSA
project is another example of applied research leveraging advanced image recognition to create
safe collaborative workspaces for close human robot interaction [21].
2.7 Operator + Social Networks = Social Operator [cognitive interaction]
Enterprise Social Networking Services (E-SNS) focus on the use of mobile and social collaborative
methods to connect the smart operators at the shop-floor with the smart factory resources. Such
connections include social relations among the workforce (cf. social network services) and
between operators and smart things (cf. social Internet of Industrial Things [22]) to interact, share
and create information for decision-making support.
Social networking between smart operators, enabled by real-time mobile communication capabilities,
can empower the workforce to contribute their expertise across the production line and to the
shop-floor, can accelerate ideas generation for product and processes innovation and can facilitate
problems-solving by bringing together the right people with the right information and especially
knowledge management and knowledge creation within the enterprise. Knowledge creation and
management is (and always has been) challenging as there is still no ‘ideal way’ to proceed. Research
and industrial practice (e.g. Airbus) suggests that a personal approach to sharing, communicating
and managing knowledge within the enterprise (e.g. deriving knowledge from a future retiree) is
more successful than a technical and highly structured approach. Social networks embedded in the
companies knowledge system might present a chance to utilize the ‘social’ component and still
allow for storing and accessing collective knowledge. Meanwhile, the social IoIT can connect, through
‘interactive machine learning’, smart operators with smart things (cf. intelligent assets) in social
networks for sharing information and exchanging messages about their location, condition, operation
status and availability for improving (for example) at machine level the asset reliability (e.g. intelligent
maintenance) and at production line level the material flows and resources productivity (e.g. spotting
bottle-necks) towards social problems-solving and optimization of the production system.
In both cases, the final aim of enterprise social networking is to communicate and enable cooperation
between smart operators and smart machines via social relations to accomplish production goals.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
An example of this type of Operator 4.0 can be considered the internal (intranet) forums and wikis
(such as e.g. used at VW). However, this only utilizes parts of what is ultimately envisioned for
the Operator 4.0. Some companies and their employees make use of existing Social Network
Services (e.g. Facebook or LinkedIn) to communicate and connect. This is risky however, as the data
is then in the hand of private entities outside of the company and thus should be accompanied by
an in-depth risk analysis.
2.8 Operator + Big Data Analytics = Analytical Operator [cognitive interaction]
Big Data Analytics is the process of collecting, organizing and analyzing large sets of data (big data)
to discover useful information and predict relevant events. Its application to the smart factory
has given birth to manufacturing real-time analytics at the shop-floor, also known as ‘smart
Big Data analytics may help smart operators (e.g. production managers) to achieve better forecasts,
understand the smart factory performance (shop-floor control), fuel continuous improvement
(Six Sigma), provide greater visibility of KPIs (data visualization and interactive dashboard) and
real-time alerts based on predictive analytics (fault detection and quality improvement) in order
to leverage real-time information for driving the right response to prevent mistakes, quickly identify
problems and call for the right decisions to improve operational efficiency.
Data analytics and machine learning have several applications in manufacturing and are already
fairly widely employed [23]. However, the increase in available data through cheap sensors and
the Industrial IoT (connected devices) and also fast progress in unsupervised methods like deep
learning will bring forth even more powerful and applicable solutions in the near future.
The analytical operator is somewhat connected to several other applications as many of them
rely on advanced data analytics. So does the collaborative operator, who often utilizes image
recognition to allow working in close proximity to CoBots, the healthy operator who relies on
the analytics of the bio-data collected and the smarter operator using Artificial Intelligence
embedded in a virtual assistant.
This type of Operator 4.0 is illustrated by the variety of monitoring and control tools currently using
machine learning and data mining algorithms to improve quality, lead time, etc. [24].
This section briefly introduces related systems, strategies and enabling technologies to/for
the Operator 4.0. Thus, Figure 2 presents a generic human cyber-physical system control loop
depicting the interactions between humans and machines and cyber and physical worlds.
3.1 Towards Human Cyber-Physical Systems
Human Cyber-Physical Systems (H-CPS) are the new frontier of human-machine interactions and
physical-digital worlds interfacing for the augmentation or enhancement of human performance.
For the case of the Operator 4.0, H-CPS aim to become safety (fault tolerance) engineered systems
of systems with the human-in-the-loop, using context-sensitive, advanced communication and adaptive
control technologies to support inter-agent systems of humans, machines and software to interface
in the virtual and physical worlds towards a sustainable and human-centric production system (see
Figure 2).
H-CPS will be deployed in the near future at the shop-floor to optimise the outcome of a production
system considering the social sustainability of the manufacturing.
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
Figure 2: Generic Human Cyber-Physical System Control Loop
3.2 Adaptive Automation Control Systems Strategies
Adaptive Automation Control Systems rely on three main strategies for adaptive function and task
allocation in human-machine interactions towards supporting the Operator 4.0 [11]: (1) based on
‘critical event(s)’ that will trigger the sharing or trading of control between human-machine agents
in order to guarantee the completion of a critical to task by one or the other or by a hybrid or
emergent agent, or when the functioning of the overall system is endangered by the action(s) of an
agent; (2) ‘measurement-based’ as human and machine agents are continuously monitored in order
to detect deviations from their tasks or ideal performance and trigger the proper countermeasures;
and (3) ‘model-basedon cognitive human and machine models for handling effective and efficient
distribution of workload.
3.3 Human-Machine Interaction Technologies
Some relevant HMI technologies that will support the Operator 4.0 are: Dialogue Systems handling
the dialogue between humans and machines (e.g. using natural language interface); Control Devices
physical (e.g. keyboards, mouse, joystick, trackball, steering wheel, pedals, knobs and switches)
and digital ones (e.g. buttons, sliders and menu buttons) enhanced with haptics technology;
Multimedia-Multimodal Displays providing the smart operator multiple modes of interacting with a
system; and Adaptive Interfaces - which adapt their layout and elements to the needs of the smart
operator and/or context.
Human-centric manufacturing has been a core topic for most previous manufacturing paradigms;
that same is true for Industry 4.0. Computer-based manufacturing control requires the human to
handle complexity emerging beyond the imagination of manufacturing system designers. Therefore,
the full potential of Industry 4.0 and the achievement of a socially sustainable manufacturing
industry will only be realized if the Operator 4.0 is at its heart (cf. human-centric) and interacting
with the machines through physical and cognitive means. As mentioned by [25], human-automation
symbiosis [3] [5], manifested as the Operator 4.0 vision, is necessary for achieving sustainable
development in human society. However, it can only be secured through the use of intelligent
(smart) automation systems and human-machine interfacing technologies. There, the assumed
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
‘intelligence’ allows inclusion of the explicit representation of human goals and plans (e.g.
productivity, occupational health, safety, job inclusion and job satisfaction, etc.), thus constituting
the basis of human-machine interaction and social interaction with technology. The Operator 4.0
typology is useful in order to increase the understanding of the future roles of humans and machines
in the factories of Human Cyber-Physical Systems. By creating a typology and a transcript of
available assets and skills, traditional manufacturing companies can easily adopt the future
contributions of humans in Industry 4.0. Future work will identify and address the specific
challenges of the Operator 4.0 typology types.
[1] BCG Group. 2015. Report on Man and Machine in Industry 4.0: How Will Technology
Transform the Industrial Workforce Through 2025?
[2] BCG Group. 2015. Report on Industry 4.0: The Future of Productivity and Growth in
Manufacturing Industries.
[3] Romero, D., Noran, O., Stahre, J., Bernus, P., Fast-Berglund, Å. 2015. Towards a Human-
Centred Reference Architecture for Next Generation Balanced Automation Systems: Human-
Automation Symbiosis. Innovative Production Management towards Sustainable Growth,
Service, Manufacturing, and Resilient Value Chain, S. Umeda et al. (Eds.), IFIP, Part II, AICT
460, Springer, pp. 556-566.
[4] De Weck, O.L., Ross, A.M., Rhodes, D.H. 2012. Investigating Relationships and Semantic
Sets amongst System Lifecycle Properties (Ilities). 3rd Int’l Engineering Systems Symposium,
CESUN 2012, Delft University of Technology, 18-20 June 2012, pp. 1820.
[5] Romero, D., Bernus, P., Noran, O., Stahre, J., Fast-Berglund, Å. 2016. The Operator 4.0:
Human Cyber-Physical Systems & Adaptive Automation towards Human-Automation
Symbiosis Work Systems. Production Management Initiatives for a Sustainable World.
Springer. TO APPEAR.
[6] Charles, T., Charles, R., Roulstone, A. 1990. Prospects and Conditions for Anthropocentric
Production Systems in Britain, APS-Research Papers Series, Vol. 8, Commission of the
European Communities, Bruxelles.
[7] Hancock, P.A., Chignell, M.H. 1987. Adaptive Control in Human-Machine Systems. Human
Factors Psychology, pp. 305-345, North Holland: Elsevier Science Publishers.
[8] Hancock, P.A., Jagacinski, R.J., Parasuraman, R., Wickens, C.D., Wilson, G.F., Kaber,
D.B. 2013. Human-Automation Interaction Research: Past, Present and Future. Ergonomics
in Design, 21(2):9-14.
[9] Sheridan, T., Parasuraman, R. 2006. Human-Automation Interaction. Human Factors and
Ergonomics, 1(1):89-129.
[10] Munir, S., Stankovic, J.A., Liang, C-J.M., Lin, S. 2013. Cyber-Physical System Challenges
for Human-in-the-Loop Control. Feedback Computing.
[11] Inagaki, T. 2003. Adaptive Automation: Sharing and Trading of Control. Chapter 8 -
Handbook of Cognitive Task Design, pp. 147-169.
[12] Sylla, N., Bonnet, V., Colledani, F., Fraisse, P. (2014). Ergonomic Contribution of ABLE
Exoskeleton in Automotive Industry. Int’l J. of Industrial Ergonomics, 44(4): 475481.
[13] Robo-Mate (Intelligent exoskeleton based on human-robot interaction for manipulation of
heavy goods in Europe’s factories of the future)
CIE46 Proceedings, 29-31 October 2016, Tianjin / China, ISSN 2164-8670 CD-ROM, ISSN 2164-8689 ON-LINE [BEST PAPER AWARD]
[14] Gorecky, D.; Campos, R.; Chakravarthy, H.; Dabelow, R.; Schlick, J.; Zühlke, D. 2013.
Mastering Mass Customization A Concept for Advanced, Human-Centered Assembly.
Assembly Manufacturing Engineering Journal, 11(2):62-67.
[15] Gorecky, D.; Schmitt, M.; Loskyll, M.; Zühlke, D. 2014. Human-Machine-Interaction in the
Industry 4.0 Era. 12th IEEE International Conference on Industrial Informatics, pp. 289-294.
[16] Satisfactory (A collaborative and augmented-enabled ecosystem for increasing SATISfaction
and working experience in smart FACTORY environments)
[17] VISTRA (Virtual Simulation and Training of Assembly and Service Processes in Digital
[18] VFF (Holistic, extensible, scalable and standard Virtual Factory Framework) http://www.vff-
[19] Myers, K., Berry, P., Blythe, J., Conley, K., Gervasio, M., McGuinness, D.L., et al. 2007.
An Intelligent Personal Assistant for Task and Time Management AI Magazine, 28(2):47-61.
[20] LIAA (Lean Intelligent Assembly Automation)
[21] INSA (Protection and Integral Security Concepts in Cyber-Physical Systems) http://www.insa- In German.
[22] Wuest, T., Hribernik, K., Thoben, K.-D. 2012. Can a Product Have a Facebook? A New
Perspective on Product Avatars in Product Lifecycle Management. Rivest, L., Bouraz, A. &
Louhichi, B. (Eds.), PLM 2012, IFIP AICT 388, Heidelberg Berlin: Springer, pp. 400-410.
[23] Wuest, T., Weimer, D., Irgens, C., Thoben, K.-D. 2016. Machine Learning in Manufacturing:
Advantages, Challenges and Applications. Production & Manufacturing Research, DOI:
[24] Wuest, T., Irgens, C., Thoben, K.-D. 2014. An Approach to Quality Monitoring in
Manufacturing using Supervised Machine Learning on Product State Data. Journal of
Intelligent Manufacturing, 25(5):167-1180.
[25] Tzafestas, S. 2006. Concerning Human-Automation Symbiosis in the Society and the Nature.
Int’l J. of Factory Automation, Robotics and Soft Computing, 1(3):16-24.
... First attempts to structure these interactions are made, for example, by Romero et al. (2016), Ruppert et al. (2018) and Fantini et al. (2020), where the operator is interpreted in different roles, depending on the technologies used. As described by Romero et al. (2016), augmented reality used by an operator leads to the "augmented operator", who is presumably capable of making more informed decisions when maintaining a machine, for instance. ...
... First attempts to structure these interactions are made, for example, by Romero et al. (2016), Ruppert et al. (2018) and Fantini et al. (2020), where the operator is interpreted in different roles, depending on the technologies used. As described by Romero et al. (2016), augmented reality used by an operator leads to the "augmented operator", who is presumably capable of making more informed decisions when maintaining a machine, for instance. These works, however, still focus on technological possibilities for the worker without analysing their influences on HF demands and operator experience in depth. ...
... Six recent journal articles could be identified dealing with the "Operator 4.0" concept that have not been included in the reviews of Kadir et al. (2019) and Badri et al. (2018) that are generally based on technology-driven approaches. One of these works is the one of Ruppert et al. (2018) that grounds a survey on technologies for the "Operator 4.0" based on the systematization of Romero et al. (2016). The focus is on IoT-based infrastructure instead of software-based applications like Fig. 1. Outline of the paper and interdependencies between sections. ...
... The Cognitive Operator 4.0 [1] described three topics of particular interest for future R&D, aligned with the Industry 5.0 hallmarks [2] that emphasize human centricity, mental workload, cognitive embodiment, and communication (or human-technology communication rather). The latter of these -communication -outlines how information exchange and interaction between humans and technology is becoming increasingly important to enable efficient work practices for the Operator 4.0 [3]. Human-Technology Interaction (HTI) and communication are topics that are present in many, if not all, of the scenarios in the Operator 4.0 typology [3], and for good reason. ...
... The latter of these -communication -outlines how information exchange and interaction between humans and technology is becoming increasingly important to enable efficient work practices for the Operator 4.0 [3]. Human-Technology Interaction (HTI) and communication are topics that are present in many, if not all, of the scenarios in the Operator 4.0 typology [3], and for good reason. Fluid interaction between humans & technology is essential for effective technology utilization and use which is also identified in Industry 5.0 [2] through its emphasis on "humancentricity". ...
... In summary, one of the more pertinent scenarios of the Operator 4.0 typology [3] regards "collaborative robot" applications, and for these applications to be implemented effectively, for collaboration to run smoothly and effortlessly, the communication between human and robot is essential [1]. We have discussed how this collaboration can be further enhanced by understanding how humanmachine interaction actually unfolds and how the behavior of the robot itself might prove a valuable clue to predicting its movements. ...
Conference Paper
Full-text available
The Operator 4.0 typology depicts the collaborative operator as one of eight operator working scenarios of operators in Industry 4.0. It signifies collaborative robot applications and the interaction between humans and robots working collaboratively or cooperatively towards a common goal. For this collaboration to run seamlessly and effortlessly, human-robot communication is essential. We briefly discuss what trust, predictability, and intentions are, before investigating the communicative features of both self-driving cars and collaborative robots. We found that although communicative external HMIs could arguably provide some benefits in both domains, an abundance of clues to what an autonomous car or a robot is about to do are easily accessible through the environment or could be created simply by understanding and designing legible motions.
... Despite this potential, no works have been found out in the literature or in commercial products with this combination in the industrial context. This paper has the goal of showing some industrial shop floor scenarios where softbots and augmented reality are combined to create a working cognitive environment for the so-called "Resilient Operator 5.0" [1], extending the concept of 'augmented operator' [5]. In terms of domain problem, this work has focused on preventive maintenance, one of the most relevant issues being dealt by industries in their chasing for higher operational efficiency, zero error, and lower production costs [6]. ...
... There are many possible scenarios related to how maintenance operators can be assisted by AR with or without softbots, as discussed in e.g. [1,3,4,5,7] . Considering the main goals of this PoC for the target company, three scenarios have been devised and implemented having the Resilient Operator 5.0 [1] in mind 1 . ...
Full-text available
Industry 4.0 and 5.0 have been posing new challenges to industries. From a focus on supporting resilience at a corporate level, there is a need to do it at a more operational level, enabling people to act with resilience as well. The resilient operator 5.0 is a new concept emerged from this need. It has the aim of providing more intuitive, symbiotic, human-centered, and cognitive working computing environments to enhance human adaptation capabilities, productivity, and mental health. In this direction, this paper presents an approach that combines softbots and augmented reality, called ‘augmented softbot’. Looking at a specific company, a software prototype has been implemented to evaluate how this approach can be useful and feasible for preventive maintenance. Three scenarios have been devised for that, and they are summarized in the paper. The achieved results are discussed, showing the high potential of the approach.KeywordsIndustry 5.0Industry 4.0SoftbotsVirtual assistantsAugmented realityResilient operator 5.0Operator 4.0Maintenance
... Collaborative robots, a.k.a cobots, offer a solution for small and medium-sized companies that require a flexible, fast, and precise operational solution in a shared workspace [2]. These cobots have proven to be intrinsically safe due to their ability to detect collisions and react accordingly [3]. ...
Full-text available
Industry 4.0 transforms classical industrial systems into more human-centric and digitized systems. Close human–robot collaboration is becoming more frequent, which means security and efficiency issues need to be carefully considered. In this paper, we propose to equip robots with exteroceptive sensors and online motion generation so that the robot is able to perceive and predict human trajectories and react to the motion of the human in order to reduce the occurrence of the collisions. The dataset for training is generated in a real environment in which a human and a robot are sharing their workspace. An Encoder–Decoder based network is proposed to predict the human hand trajectories. A Model Predictive Control (MPC) framework is also proposed, which is able to plan a collision-free trajectory in the shared workspace based on this human motion prediction. The proposed framework is validated in a real environment that ensures collision free collaboration between humans and robots in a shared workspace.
... Operator 4.0 was presented as a smart and skilled operator of the future that involves leveraging the collaboration between cooperative robots and accurate machinery and the human being's ingenious unique potential [5]. In the Operator 4.0 typology, the healthy and smart operator has the ability to detect problems and suggest solutions in machines and systems that build predictive models for proactive actions [6]. In addition, Healthy Operator 4.0 architecture was suggested, which is composed of smart connection, integration and communication, modeling, and cognition layer [7]. ...
Full-text available
The value-driven Industry 5.0 has brought a shift in the approach towards worker well-being. However, the understanding of the effects on workers due to technological advancements of Industry 4.0, based on a human-centric approach, is limited. The reason for this limitation is that the tools are scarce, which is quantitatively evaluating and analyzing various factors in the workplace. To solve this problem, we propose a human digital twin system supporting decision-making regarding safety management and work management of workers. The human digital twin system consists of a digital twin module, an analysis module, and a visualization module. The proposed system connects a physical human and a virtual digital human model; analyzes the location, posture, and motion-time of workers; and delivers information about safety and work management. This information enables workers and managers to improve the work environment by making them resilient to workplace factors.
... Passive work attitude increasingly confronted with technologies that aim to assist them within their everyday activities (Romero et al., 2016). Assistive technologies can support employees at the industrial workplace by giving them either physical or cognitive assistance (Gerdenitsch and Korunka, 2019), and much research in engineering has contributed to further developing these technologies (Alc acer and Cruz-Machado, 2019). ...
Purpose-The deployment of assistive technologies affects well-being and productivity at industrial workplaces. Augmented reality (AR) is one of these technologies that has become increasingly deployed in manufacturing facilities to assist employees on the shopfloor. This paper aims to shed light on users' experiences with AR-based assistance systems, specifically on the sense of autonomy users experience during an AR-assisted assembly task. Based on that, this paper draws implications for the design of future industrial workplaces to improve workers' health, well-being and productivity. Design/methodology/approach-The authors conducted a laboratory experiment with 117 participants. Within semi-structured interviews, the authors asked the participants about their general experience, as well as their sense of autonomy and responsibility. Findings-The study results indicate a limited perception of autonomy. Connected to this, the participants took over a passive working attitude and experienced a limited sense of responsibility concerning the output of the AR-assisted assembly task. At the same time, however, the participants still attributed assembly errors internally. Originality/value-AR-assistance holds both benefits and risks for worker's health, well-being and productivity. With this study, the author aims to increase the understanding about the perception of autonomy and control at industrial workplaces. Thus, the authors conclude with design implications for developing and implementing assistive technologies in a way that beneficial effects for employees can be achieved.
The field of Explainable Artificial Intelligence (XAI) is a relatively new approach to AI, with the aim to provide black box algorithms with human intelligible narrative functionality. It is most often in end-of-life considerations of the asset lifecycle that sustainability issues are encountered. Modern maintenance practice requires a holistic understanding of lifecycle and options for sustainable asset treatments. human in the loop solutions offer a way to leverage both machine and human skill sets to provide the next level of automaton solutions for industrial maintenance activities. This paper presents a framework for human in the loop Intelligent and Sustainable Maintenance. In bridging the gap between machines and humans XAI leverages the best of both worlds to provide a new level of agility to cyber assisted maintenance activities and full lifecycle consideration of assets; a notion that is necessary throughout the organization in the achievement of sustainability goals set by governments around the world in the achievement of a net zero carbon emission economy.
Taking the cue from a general introduction to “blockchain”, the contribution strives to offer—also through a positive contamination with other spheres of knowledge and through the analysis of some regulatory sources that can be found, both on the Italian side and the European one—a theoretical analysis and a critical reflection on the impact blockchain produces on employment relationship, labour market and regulation, exploring this new disruptive technology as a sort of fertile ground for the experimentation of a new relationship between humanism and technique.KeywordsBlockchainDigital transformationDisintermediation
The Operator 4.0 generation denotes a smart and skilled operator accomplishing ‘cooperative work’ with robots, machines and cyber-physical systems. In this taxonomy, a healthy operator is an operator equipped with wearable technology to monitor biometrics in a workplace to monitor and ideally prevent urgent threats to safety, stress in manufacturing and production quality. In a digitalized context, a cloud manufacturing platform for occupational health assessment, capable of collecting physiological, environmental and manufacturing process data can potentially enable prompt action to prevent fatalities. This paper proposes a novel machine learning-based framework and associated methods to classify physiological data acquired using wearable sensors during manufacturing work, to be utilized in a fuzzy-based expert system to determine the level and type of health risk for Operator 4.0. Classification algorithms are presented and a manufacturing case study is illustrated to exemplify the proposed methodology and to evaluate the industrial suitability.
Despite the increasing degree of automation in industry, manual or semi-automated are commonly and inevitable for complex assembly tasks. The transformation to smart processes in manufacturing leads to a higher deployment of data-driven approaches to support the worker. Upcoming technologies in this context are oftentimes based on the gesture-recognition, − monitoring or – control. This contribution systematically reviews gesture or motion capturing technologies and the utilization of gesture data in the ergonomic assessment, gesture-based robot control strategies as well as the identification of COVID-19 symptoms. Subsequently, two applications are presented in detail. First, a holistic human-centric optimization method for line-balancing using a novel indicator – ErgoTakt – derived by motion capturing. ErgoTakt improves the legacy takt-time and helps to find an optimum between the ergonomic evaluation of an assembly station and the takt-time balancing. An optimization algorithm is developed to find the best-fitting solution by minimizing a function of the ergonomic RULA-score and the cycle time of each assembly workstation with respect to the workers’ ability. The second application is gesture-based robot-control. A cloud-based approach utilizing a generally accessible hand-tracking model embedded in a low-code IoT programming environment is shown.
Conference Paper
Full-text available
A vision for the Operator 4.0 is presented in this paper in the context of human cyber-physical systems and adaptive automation towards human-automation symbiosis work systems for a socially sustainable manufacturing workforce. Discussions include base concepts and enabling technologies for the development of human-automation symbiosis work systems in Industry 4.0.
Full-text available
The nature of manufacturing systems faces ever more complex, dynamic and at times even chaotic behaviors. In order to being able to satisfy the demand for high-quality products in an efficient manner, it is essential to utilize all means available. One area, which saw fast pace developments in terms of not only promising results but also usability, is machine learning. Promising an answer to many of the old and new challenges of manufacturing, machine learning is widely discussed by researchers and practitioners alike. However, the field is very broad and even confusing which presents a challenge and a barrier hindering wide application. Here, this paper contributes in presenting an overview of available machine learning techniques and structuring this rather complicated area. A special focus is laid on the potential benefit, and examples of successful applications in a manufacturing environment.
Full-text available
Human-centricity in manufacturing is becoming an essential enabler to achieve social sustainable manufacturing. In particular, human-centric automation can offer new means to increase competitiveness in the face of new social challenges for the factories of the future. This paper proposes a Human-Centred Reference Architecture that can structure and guide efforts to engineer Next Generation Balanced Automation Systems featuring adaptive automation that take into account various criteria in the operating environment such as time-lapse, performance degradation, age-, disability-and inexperience-related limitations of operators to increase their working capabilities.
Conference Paper
Full-text available
This paper articulates three main challenges for employ-ing feedback control with humans in the loop. They are: (i) the need for a comprehensive understanding of the complete spectrum of the types of human-in-the-loop controls, (ii) the need for extensions to system identi-fication or other techniques to derive models of human behaviors, and (iii) most importantly, determining how to incorporate human behavior models into the formal methodology of feedback control.
Conference Paper
The development of Industry 4.0 will be accompanied by changing tasks and demands for the human in the factory. As the most flexible entity in cyber-physical production systems, workers will be faced with a large variety of jobs ranging from specification and monitoring to verification of production strategies. Through technological support it is guaranteed that workers can realize their full potential and adopt the role of strategic decision-makers and flexible problem-solvers. The use of established interaction technologies and metaphors from the consumer goods market seems to be promising. This paper demonstrates solutions for the technological assistance of workers, which implement the representation of a cyber-physical world and the therein occurring interactions in the form of intelligent user interfaces. Besides technological means, the paper points out the requirement for adequate qualification strategies, which will create the required, inter-disciplinary understanding for Industry 4.0.
The ilities are properties of engineering systems that often manifest and determine value after a system is put into initial use (e.g. resilience, interoperability, flexibility). Rather than being primary functional requirements, these properties concern wider system impacts with respect to time and stakeholders. Over the past decade there has been increasing attention to ilities in industry, government and academia. Our research suggests that investigating ilities in sets may be more meaningful than study of single ilities in isolation. Some ilities are closely related and do in fact form semantic sets. Here, we use two methods to investigate over twenty ilities in terms of their prevalence and their interrelationships. We look for trends related to ilities of interest in relation to system type and an understanding of their collective use. First, we conducted a prevalence analysis of 22 ilities using both the internet as well as the Compendex/Inspec database as a source. We found over 1,275,000 scientific articles published between 1884 and 2010 and over 1.9 billion hits on the internet, exposing a clear prevalence-based ranking of ilities. Two questions we seek to address are: why and how are the ilities related to one another, and what can we do with this information. Initial steps to answer the first question include a 2-tupel-correlation matrix analysis that exposes the strongest relationships amongst ilities based on concurrent usage. Moreover, we conducted some preliminary experiments that indicate that a hierarchy of ilities with a few major groupings may be most useful. The overall objective for this research is to develop a formal framework and prescriptive guidance for effectively incorporating sets of ilities into the design of complex engineering systems.
In PSA Peugeot Citroen factories, high precision requirements of workstations make them being manual. One of the main goal of the car manufacturer is to minimize the pain of workers while maintaining high efficiency of production lines. Consequently, assisting operators with an exoskeleton is a potential solution for improving ergonomics of painful workstations while respecting industrial constraints. To determine ergonomic performances of an exoskeleton, human joint angles and torques, ground reaction forces, and duration of operations are analysed for eight subjects performing a representative screwing task. Experiments were performed using ABLE upper-limb exoskeleton, developed by the French Atomic Energy Commission (CEA), which has the functionality to compensate arm and tools loads. Results show a clear reduction of the sum of the joints torques, up to 38.9%, given by ABLE supply and invite to make concrete the use of exoskeletons in car assembly lines. Relevance to industry In industries, workers performing manual operations are subjected to musculoskeletal disorders (MSD). The usage of robotic devices such as exoskeletons might then be a relevant solution to reduce workers pain and prevent MSD. The paper describes how to assess ergonomic performances of such robotic devices for a future usage in industry.
Conference Paper
This chapter discusses contemporary advances in the understanding of adaptive control as applied to systems that include the cooperative action of a machine and its operator. The key component of an adaptive interface is a reasoning process that selects a task allocation policy that changes the loading on the human in such a way as to improve overall system performance. This process must have access to both overall system goals (a model of the task) and information about what the person and machine components of the system are capable of accomplishing (person and system models). As an initial foundation, it is recognized in the chapter that the prosthetics that can surround individuals and augment their capabilities allow human operators to traverse the traditional boundary constraints imposed by the environment. A different approach is advocated where a hierarchical model of the task is built in terms of procedural and knowledge-based components. The human–machine interaction is a view of the task as a knowledge system that requires combined human–machine intelligence along with an interface that permits and controls joint human–machine reasoning. The chapter describes some developments in the understanding of human-adaptive response and the way by which such adaptive capability may be replicated in human–machine systems.