Moving into Co-Creative Robotics

Sanaz Nikghadam-Hojjati

1 a

, Eda Marchetti

2 b

, Jose Barata

1 c

and Antonello Calabr

2 d

UNINOVA-CTS and LASI, Caparica, Portugal

Istituto di Scienza e Tecnologie dell’Informazione “A. Faedo”, CNR, Pisa, Italy

Keywords:

Industry 4.0, IoT Cybersecurity, Industry 5.0.

Abstract:

In the volatile, uncertain, complex, ambiguous (VUCA) world, robots should be able to adapt to different as-

pects of human life and create a positive impact. To achieve this, it is important to create and develop not only

technically advanced but also, from a social point of view, adaptable, autonomous, creative, collaborative, and

ethical robots. This paper introduces the concepts of Co-Creative Robotics and analyses the role of collabora-

tive networks in advancing it. Alongside introducing technological dimensions of Co-Creative Robotics, the

paper compares Co-Creative Robotics characteristics with computational creativity and traditional robotics.

Finally, to support the advancement of this ﬁeld, the authors investigated the role of different categories of

collaborative networks for Co-Creative Robotics advancement.

1 INTRODUCTION

Robots have become integral components of various

aspects of human life, deeply impacting society, in-

dustry, economy, and beyond (Cai et al., 2021). They

designed for speciﬁc tasks in various domains share

common advantages such as productivity (Cresswell

et al., 2018) and reliability (Santos et al., 2021), ef-

ﬁciency (Leigh et al., 2020) and quality, consistency

and accuracy improvement (Fragapane et al., 2022),

assistance to humans (Narayan et al., 2022), enhance-

ment of human capabilities (Kalaitzidou and Pachidis,

2023), cost reduction through automation, and con-

tinuous operation (Mor et al., 2022). However, de-

spite the beneﬁts that these specialized robots offer,

they also have common limitations such as rigidity

in operation, limited autonomy, lack of creative ca-

pacity, posing a challenge to current human skills

and jobs, and limited versatility and adaptability in

volatile, uncertain, complex, and ambiguous (VUCA)

environments (Javaid et al., 2021; Liu et al., 2023).

Moreover, they require specialized expertise and

have difﬁculty addressing complex challenges and ill-

structured problems in real-world scenarios (Wong

et al., 2018). In response to these limitations, we in-

troduce the new concept of Co-Creative Robotics for

https://orcid.org/0000-0002-0839-9250

https://orcid.org/0000-0003-4223-8036

https://orcid.org/0000-0002-6348-1847

https://orcid.org/0000-0001-5502-303X

IoT, i.e., an interdisciplinary ﬁeld combining the prin-

ciples of computational creativity(Nikghadam-Hojjati

and Barata, 2019), and robotics to develop robots

able to generate human-like novel ideas, solutions,

and artistic expressions or collaborate in creative

tasks. Therefore, Co-Creative Robotics offers a trans-

formative approach to robotics research and devel-

opment, leveraging the naive concepts of creative

robotics (Hooman, 2023) to the IoT domain and open-

ing the path to new possibilities for innovation, col-

laboration, and societal impact.

By emphasizing adaptability, creativity, and inclu-

sivity, Co-Creative Robotics unlocks the way for a

future where robots play a central role in addressing

complex challenges and improving the quality of life

for human beings.

In presenting the new concepts of Co-Creative

Robotics, the following Research Questions [RQs]

have been addressed:

1. RQ1 What is Co-Creative Robotics and what are

the key differences with traditional robotics?

2. RQ2 Which is a possible technical solution to

support Co-Creative Robotics advancement?

The deﬁnition of Co-Creative Robotics and the an-

swer to the proposed RQs are based on an overview

of the most relevant literature and Focused Group

Brainstorming, which involves stating research ques-

tions, selecting participants, and setting ground rules.

Focused Group Brainstorming participants engage in

Nikghadam-Hojjati, S., Marchetti, E., Barata, J. and Calabrò, A.

Moving into Co-Creative Robotics.

DOI: 10.5220/0013000400003825

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 20th International Conference on Web Information Systems and Technologies (WEBIST 2024), pages 307-314

ISBN: 978-989-758-718-4; ISSN: 2184-3252

307

Figure 1: Main Milestones in Robotics History.

5 in-person and ﬁve online brainstorming meetings,

generating and discussing ideas. Results are anony-

mously presented to a validating group (including 8

experts), and the most effective ideas were selected in

individual meetings during the validating phase.

2 BACKGROUND

The development of the robotics ﬁeld results from

human creativity and continued efforts to achieve

higher efﬁciency and automation in different tasks.

From ancient civilizations´ early mechanical birds,

which used steam to propel themselves (Archytas

- 350 B.C.) (Yao, 2021), until today’s cutting-edge

machines, which try to think and perform better

than humans, robotics has evolved through a series

of signiﬁcant milestones (Hor

akov

a and Kelemen,

2008). These milestones, summarized in Figure 1,

not only highlight technological progress in robotics

but also underscore the potential of robots to trans-

form industries and improve the quality of human

life. However, with the evolution of technology,

real-world challenges and opportunities are also be-

coming more volatile, uncertain, complex, and am-

biguous (VUCA), which requires a change in current

robotics. Future generations of robots/cobots need

to navigate and positively contribute to diverse soci-

etal, economic, and environmental contexts and in-

teract with humans in their performance. To develop

robots with the mentioned capabilities, this paper pro-

poses integrating two emerging ﬁelds in the newly

conceived Co-Creative Robotics discipline: compu-

tational creativity (Nikghadam-Hojjati and Barata,

2019) and robotics. This interdisciplinary approach

aims to utilize computational methods and techniques

from computational creativity to model, simulate, or

enhance human creativity. It will leverage artiﬁcial in-

telligence, cognitive psychology, philosophy, and art

to study, emulate, motivate, and enhance human cre-

ativity to achieve speciﬁc goals:

• Developing models, methods, and computer-

based programs that can stimulate and enhance

human creativity without necessarily being cre-

ative themselves.

• Developing models, methods, and computer-

based programs that can generate human-level

creative ideas.

• Better studying and understanding the nature and

processes of human creativity and applying a

computer perspective on human creative behavior.

3 CO-CREATIVE ROBOTICS

DEFINITION

The proposed Co-Creative Robotics emerges as a

natural extension of this concept, where the principles

of computational creativity are applied to robotics to

create technically proﬁcient and creatively capable

robots. In this regard, and reply to the [RQ1]:

“What is the Co-Creative Robotics, and what are the

key differences with traditional robotics?” authors

proposed the following deﬁnition as:

Co-Creative Robotics is an interdisciplinary

ﬁeld that integrates computational creativity and

robotics principles to develop machines capable of

demonstrating or supporting creative behavior by

generating human-like novel ideas, solutions, and

artistic expressions or collaborating in creative tasks.

As detailed in Table 1 the Co-Creative Robotics

includes:

• Developing computational creativity-based robots

that support humans in their creative tasks and

stimulate and enhance their creative behavior

without being creative themselves.

• Developing computational creativity-based robots

that can generate human-level creative ideas,

learn, and demonstrate creative behavior from

their interacted environment.

• Understanding human creativity and collaborative

creativity from various perspectives, such as phi-

losophy, neuroscience, psychology, anatomy and

WEBIST 2024 - 20th International Conference on Web Information Systems and Technologies

308

Table 1: Overview of differences within Co-Creative Robotics, Computational Creativity and Traditional Robotics.

Criteria Traditional Robotics Cocreative Robotics

Creativity

Typically, not designed for creative asks and mainly

are limited to predeﬁned tasks and environments

Capable of generating novel solutions, ideas, and

artistic expressions independently or in collaboration

Autonomy

Often require human supervision or control and have limitations

in adaptability outside of their predeﬁned tasks

Capable of operating autonomously in various environments

and adapt to changing conditions creatively

Physical

Capabilities

May have advanced physical capabilities

for tasks such as manipulation, navigation, or assembly

Capable of physically manipulating objects, interacting

with the environment, and expressing creative behavior

Human

Interaction

Limited ability to engage in natural interactions or understand

human emotions; Often lack social and emotional intelligence

Can engage in meaningful interactions with humans,

collaborate on creative tasks, and respond to emotional cues

Adaptability

Limited adaptability to new situations or environments

outside of predeﬁned tasks and environments

Capable of adapting to dynamic and

uncertain environments and tasks creatively

Ethical

Considerations

Typically follow predetermined rules and algorithms

without consideration of broader ethical implications

Can consider ethical and cultural dilemmas and

make value-based judgments

Learning

Limited learning capabilities beyond predeﬁned tasks

and environments

Capable of learning from experience and feedback

to enhance creativity over time

biology, cognitive science, and art, is essential for

studying its nature and processes.

Table 1 presents the main limitations of traditional

robotics. While Co-Creative Robotics could over-

come these limitations, even though they may have

restrictions in representing human behavior due to

physical capabilities, task complexity, and interaction

with unpredictable environments.

Figure 2 provides a schematic summary of the

technological perspectives involved in the proposed

Co-Creative Robotics discipline that can be inherited

from the Computational creativity or robotics area.

They encompass components and principles that en-

able robots to engage in creative tasks and behaviours

as the main actors or collaborators.

Just as examples, Co-Creative Robotics incorpo-

rates the computational creativity of the AI disci-

pline. AI can be used for developing algorithms,

methods, models, and computer programs that sim-

ulate or enhance human creativity, allowing robots to

produce innovative ideas, solutions, and artistic ex-

pressions (Ventura, 2019). Indeed, ML, deep learn-

ing, and Natural Language Processing (NLP) could

enable robots to autonomously learn, reason, and gen-

erate novel and appropriate ideas and solutions.

Considering Affective Computing inside the com-

putational creativity, Co-Creative Robotics can ex-

ploit the algorithms and methods enabling robots to

understand, interpret, and respond to human emo-

tions, which is fundamental Human-Computer Inter-

action HRI (Kappas and Gratch, 2023).

Moreover, ethics and cybersecurity principles in-

side computational creativity can be used by Co-

Creative Robotics to leverage ethical considerations

as robots engage in creative tasks and interact with hu-

mans (Pawlicka et al., 2022). Indeed, for Co-Creative

Robotics, it is imperative to uphold fairness, trans-

parency, and accountability throughout the creative

process while addressing privacy, safety, and societal

impact concerns.

Finally, considering the complexity of designing,

developing, and implementing Co-Creative Robotics,

it must adopt the collaborative, interdisciplinary, mul-

tidimensional, and multi-actor approaches typical of

computational creativity. By bringing together ex-

perts and involved entities from diverse ﬁelds, Co-

Creative Robotics can tackle the multifaceted VUCA

challenges and develop innovative solutions that push

the boundaries of what creative robots can achieve.

Considering instead the Robotic technical dimen-

sions, the Co-Creative Robotics can take advantage of

the sensory systems management. Indeed, cameras,

microphones, and tactile sensors can enable robots to

perceive and understand their environment and inter-

act with objects, people, and surroundings (Thuruthel

et al., 2019). Additionally, robots require algorithms

for planning, reasoning, and adapting creatively to

dynamic conditions, enabling them to make indepen-

dent decisions based on task comprehension, environ-

mental factors, and objectives (Maroto-G

omez et al.,

2023). The physical manifestation of robots, such

as robotic arms, hands, or humanoid bodies, plays

a pivotal role in Co-Creative Robotics by serving as

the medium through which creative outputs are ex-

pressed. Furthermore, Co-Creative Robotics inte-

grates feedback mechanisms that enable them to as-

sess and learn from their actions, reﬁning their cre-

ative abilities over time through iterative processes.

4 COLLABORATIVE NETWORKS

FOR ADVANCEMENT

To answer the second research question, [RQ2],

the focused group brainstorming sessions were per-

formed as described in the introduction. Based on ex-

perts’ understanding and opinion and analyzing the

Moving into Co-Creative Robotics

309

Figure 2: Main Technological Dimensions of Co-Creative Robotics.

proposals and distinct categories suggested, a com-

mon point has been identiﬁed in using collaborative

networks (CNs) (Marchetti et al., 2023). A collab-

orative network is a system of interconnected enti-

ties, such as organizations or individuals, working to-

gether to achieve common goals. It leverages shared

resources, information, and expertise to enhance per-

formance and innovation. Participants in the network

maintain autonomy while engaging in coordinated ac-

tions. The collaboration often spans across different

sectors, disciplines, and geographic locations. Effec-

tive communication and trust are critical for the suc-

cess of a collaborative network.

Thus, considering that hybridization is one

of the main characteristics of fourth (Camarinha-

Matos and Afsarmanesh, 2021) and ﬁfth (Marchetti

et al., 2023) generations of Cs, which repre-

sent collaboration between diverse entities, we

can classify CNs based on the entities involved

into seven main categories include Human-Haman

CNs (HHCNs), Human-Machine CNs (HMCNs),

Human-Nature CNs (HNCNs), Machine-Machine

CNs (MMCNs), Machine-Nature CNs (MNCNs),

Nature-Nature CNs (NNCNs), and Human-Machine-

Nature CNs (HMNCNs)(Camarinha-Matos and Af-

sarmanesh, 2021) ( Figure 3).

In the case of Co-Creative Robotics ﬁeld evo-

lution, collaboration within different types of CNs

plays a powerful catalyst that increases the rate of

advancement. Interdisciplinary, multidimensional,

multifaceted, and hybrid collaborative networks sup-

port stakeholders in addressing the requirements Co-

Creative Robotics and mitigating its advancement

challenges through contribution in many aspects such

as integrating diverse expertise, accelerating knowl-

edge sharing, pooling resources, enhancing problem-

solving capabilities, addressing ethical concerns, fos-

tering cross-disciplinary innovation, and promoting

global standards (Marchetti et al., 2023). To high-

light the role of CNs in providing a possible technical

solution to support the advancement of Co-Creative

Robotics, in the next sections, a discussion about each

of the mentioned CN categories is provided.

4.1 HHCNs

In this category of CNs, individuals or groups

of humans collaborate with other individuals or

groups to achieve common goals or solve prob-

lems (Guerrini and Yamanari, 2019). In Co-

Creative Robotics, advancement, HHCNs facilitate

interdisciplinary collaboration and knowledge ex-

change among researchers, psychologists, engineers,

artists, and other stakeholders; they contribute to a

deeper understanding of human creativity, cognitive

processes, and socio-cultural inﬂuences.

HHCNs enable AI and ML experts to cre-

ate cutting-edge algorithms and share high-quality

datasets. These networks support developing cre-

ativity evaluation metrics for robotic systems, which

consider creativity’s subjectivity and context depen-

dence. HHCNs, by involving interaction experts and

psychologists, could support enhancing human-robot

interaction (HRI). Their interdisciplinary collabora-

tion can break down barriers and coordinate efforts to

solve VUCA problems. In addition, these networks

optimize computational resources, ensure robustness

and reliability, and handle scalability issues.

They promote transparency in models, address

ethical concerns, and ensure cultural sensitivity by in-

tegrating diverse perspectives.

Involving legal and policy experts, regulatory

frameworks could be developed, and IP challenges

could be navigated. Furthermore, by leveraging col-

lective strengths, HHCNs can effectively address the

multifaceted challenges in Co-Creative Robotics, fos-

tering innovation and responsible practice.

4.2 HMCNs

HMCNs involve collaboration between humans and

machines or AI systems (Kattel et al., 2020). In

these networks, humans interact with machines to

perform tasks, share information, or achieve speciﬁc

WEBIST 2024 - 20th International Conference on Web Information Systems and Technologies

310

Figure 3: Categorization of Collaborative Networks based on the Involved Entities.

objectives, often combining human creativity, intu-

ition, and decision-making with machine efﬁciency

and computational power.

HMCNs can signiﬁcantly advance Co-Creative

Robotics by facilitating synergistic interactions be-

tween humans and machines. They facilitate the in-

tegration of diverse cognitive, emotional, and socio-

cultural perspectives to enhance models of human cre-

ativity and, by combining human creativity with ma-

chine efﬁciency, develop innovative algorithms for

VUCA problems. These networks facilitate balanc-

ing subjective human insights with objective machine

analysis to create comprehensive creativity evaluation

metrics for Co-Creative Robotics systems.

HMCNs, by enhancing communication and im-

proving understanding, foster the trustworthiness and

reliability of human-robot collaboration and inter-

action. They facilitate and enhance the collection

and sharing of creative data, qualitative and diverse

dataset development, and promote knowledge ex-

change and resource management through support-

ing interdisciplinary collaboration, increasing inter-

operability, and standardization. Interpretability and

explainability are improved through transparent com-

munication, making machine outputs understandable

and culturally relevant.

HMCNs optimize computational resources by as-

signing tasks based on the strengths of both humans

and machines. They enhance robustness and relia-

bility by combining human oversight with machine

precision, and improve scalability for handling larger

datasets and VUCA tasks.

Ethical concerns can be addressed by incorporat-

ing human values into robotic system design and de-

ployment. HMCNs ensure cultural sensitivity by in-

volving diverse human inputs. In addition, HMCNs

can potentially improve public and user acceptance

by creating user-friendly and culturally relevant cre-

ative robots. They also can promote the utilization

of sustainable materials by combining human exper-

tise in sustainability with machine capabilities. HM-

CNs facilitate IP protection by establishing and dis-

seminating clear guidelines for ownership and author-

ship, and beneﬁt regulatory framework development

through interdisciplinary collaboration.

4.3 HNCNs

In HNCNs, humans collaborate with natural ele-

ments, such as ecosystems, animals, or natural phe-

nomena (Kluger et al., 2020). They may involve

studying nature for inspiration, working with natural

processes to address environmental challenges, or in-

tegrating nature into human-designed systems.

To advance Co-Creative Robotics, HNCNs have

the potential to integrate diverse human perspectives

with natural models of creativity observed in biolog-

ical systems and enhance our understanding of cre-

ativity to the development of innovative algorithms.

By taking inspiration from nature, HNCNs facili-

tate the creation of comprehensive creativity evalua-

tion metrics, improve human-robot collaboration, and

optimize data collection. They also foster interdis-

ciplinary collaboration, optimize computational re-

sources, and enhance creative robotic systems’ ro-

bustness, reliability, and scalability.

HNCNs can improve interpretability and explain-

ability by using natural analogies to make machine

outputs more comprehensible. They can support ad-

dressing ethical concerns by incorporating human val-

ues and natural principles, ensuring cultural sensi-

tivity, and fostering public acceptance through user-

friendly and culturally relevant robots. In addition,

HNCNs promote sustainable materials and support

the development of regulatory frameworks to ensure

responsible innovation. Furthermore, they help estab-

lish clear guidelines for intellectual property protec-

tion, ensuring fair and transparent practices.

Moving into Co-Creative Robotics

311

4.4 MMCNs

MMCNs involve collaboration among different ma-

chines, including intelligent autonomous systems, to

accomplish tasks or solve problems. These networks

often rely on machine-to-machine communication,

data sharing, and coordinated actions to achieve com-

mon objectives efﬁciently (N

obrega et al., 2023).

MMCNs provide a multifaceted approach to ad-

dress the diverse challenges of advancing Co-Creative

Robotics. By harnessing distributed computing

power, MMCNs facilitate a deeper understanding of

human creativity by aggregating and analysing large

amounts of data from various sources. They enable

the development of complex algorithms that navigate

VUCA problem spaces while balancing novelty and

appropriateness in creative outputs.

Moreover, MMCNs support enhancing human-

robot collaboration by improving communication,

adaptability, and trust through seamless interaction

and intuitive interfaces. By pooling resources and

automating data processing, MMCNs mitigate data

availability and quality limitations, supporting the de-

velopment of robust and generalizable Co-Creative

Robotics systems.

MMCNs also optimize computational resource

usage, ensure scalability, and enhance interpretabil-

ity and explainability, addressing ethical concerns and

promoting cultural sensitivity. By fostering public ac-

ceptance and regulatory compliance, MMCNs facili-

tate the responsible and sustainable integration of Co-

Creative Robotics into various ﬁelds, ensuring relia-

bility, safety, and adherence to ethical standards.

4.5 MNCNs

in MNCNs, collaboration happens between machines

and elements of the natural world. These networks

may include deploying machines for environmen-

tal monitoring, utilizing nature-inspired design prin-

ciples in machine engineering, or developing tech-

nologies to work harmoniously with natural ecosys-

tems (Camarinha-Matos and Afsarmanesh, 2018).

MNCNs, by integrating machine intelligence with

insights from the natural world, can provide novel

solutions to VUCA problems. They can leverage

biomimicry to simulate creative processes observed

in nature, such as the collective intelligence of social

insect colonies or the adaptive problem-solving strate-

gies of animals. MNCNs can draw inspiration from

ecological systems, where complex interactions lead

to emergent behaviors.

Moreover, they address Data Limitations chal-

lenges by employing bio-inspired data collection and

processing techniques. MNCNs can also serve as

platforms for integrating expertise from diverse ﬁelds,

mirroring the interconnectedness of ecosystems.

Furthermore, MNCNs contribute to ”Scalability”

by leveraging principles of self-organization and scal-

ability observed in natural systems. They can take

inspiration from natural systems’ ability to adapt to

changing environments and stakeholder feedback.

4.6 NNCNs

NNCNs represent CNs where elements of the natural

world (including humans) collaborate (Camarinha-

Matos and Afsarmanesh, 2018). These networks en-

compass interactions and relationships between dif-

ferent components of ecosystems, ecological pro-

cesses, or natural phenomena, contributing to the

functioning and resilience of natural systems.

Through observation of processes and outcomes

of NNCNs, Co-Creative Robotics ﬁeld experts can

take inspiration from observed principles in natural

systems to develop innovative solutions to different

challenges and requirements of this ﬁeld. For in-

stance, insights from biological systems can support

robotic system designers to design and develop more

adaptive and resilient robotic algorithms by replicat-

ing how different natural organisms respond to envi-

ronmental changes.

Additionally, NNCNs can facilitate interdisci-

plinary collaboration by bringing together biology,

engineering, and computer science experts to ex-

change ideas and develop novel approaches to Co-

Creative Robotics. Moreover, NNCNs can contribute

to developing more sustainable and environmentally

friendly robotic systems by incorporating principles

of biomimicry and utilizing eco-friendly materials

and energy sources.

4.7 HMNCNs

HMNCNs integrate collaboration between humans,

machines, and natural elements. They leverage hu-

man creativity, machine intelligence and efﬁciency,

and natural processes to address VUCA challenges

and requirements, promote sustainability, or enhance

society’s and the environment’s well-being (Zhuge,

2020).

This complex category, which integrates human

expertise, ML algorithms, and insights from natu-

ral systems, addresses key challenges across various

fronts. From understanding the complexity of hu-

man creativity to navigating algorithmic challenges,

HMNCNs leverage interdisciplinary collaboration to

develop innovative solutions. These networks facili-

WEBIST 2024 - 20th International Conference on Web Information Systems and Technologies

312

tate robust human-robot collaboration, improve data

collection and sharing, optimize computational re-

sources, and enhance the interpretability and reliabil-

ity of Co-Creative Robotics systems.

Moreover, HMNCNs foster ethical considera-

tions, cultural sensitivity, and public acceptance by

engaging diverse stakeholders and aligning with soci-

etal values. Promoting sustainability, regulatory com-

pliance, and intellectual property protection ensures

responsible and ethical innovation in the ﬁeld of Co-

Creative Robotics. HMNCNs harness the collective

intelligence, creativity, and adaptability of humans,

machines, and natural systems to drive progress and

overcome the complex challenges in advancing Co-

Creative Robotics.

5 CONCLUSION AND FUTURE

WORKS

The current generation of robotic systems is required

to operate in VUCA environments and solve VUCA

problems. These dynamic and unpredictable condi-

tions demand robots to possess high adaptability, au-

tonomy, creativity, interaction, and decision-making

skills. We can signiﬁcantly improve robots’ per-

formance and reliability in tackling complex real-

world challenges by developing robots with these ad-

vanced capabilities. For such, this paper presented a

conceptual expansion research work that investigated

the historical background, nature, characteristics, and

technological dimensions of Co-Creative Robotics, as

well as the difference between traditional robotics and

Co-Creative Robotics. The authors showed that tradi-

tional robots are mainly designed for speciﬁc tasks in

controlled settings, struggle to adapt to dynamic and

unpredictable conditions, and lack the autonomy and

creativity necessary for innovation.

A new paradigm of Co-Creative Robotics through

integrating computational creativity with robotics

principles has emerged to address these limitations.

Co-Creative Robotics can generate novel ideas, so-

lutions, behaviour, and artistic expressions indepen-

dently or in collaboration with humans. This inter-

disciplinary ﬁeld incorporates AI, affective comput-

ing, sensory perception, and HRI technologies to em-

power robots with creativity, adaptability, and ethical

decision-making capabilities. Co-Creative Robotics,

by adopting a collaborative and multidimensional ap-

proach involving experts from various ﬁelds, aims to

overcome the challenges of VUCA environments and

push the boundaries of what robots can achieve in

diverse contexts. Inspired by the role of collabora-

tion in life evolution, it has been considered a valu-

able approach in advancing Co-Creative Robotics.

In this regard, the authors answered the second re-

search question of this work, which investigates the

role of CNs in Co-Creative Robotics advancement.

The authors proposed a new categorization of CNs

based on the involved entities, including human-

human, human-machine, human-nature, machine-

machine, machine-nature, nature-nature, and human-

machine-nature CNs.

Based on this categorization, experts propose pos-

sible roles and impacts of CNs during several focused

group brainstorming sessions. CNs’ contributions to

Co-Creative Robotics advancement include facilitat-

ing interdisciplinary collaboration, knowledge shar-

ing, resource pooling, problem-solving, and address-

ing ethical considerations. These networks enable the

integration of diverse perspectives and expertise to ad-

dress the challenges of Co-Creative Robotics, foster-

ing innovation, reliability, and responsible practice.

Future research in the ﬁeld of Co-Creative

Robotics has signiﬁcant potential for advancing the

capabilities and applications of robotic systems. One

area for future exploration is developing the inter-

disciplinary nature of Co-Creative Robotics by inte-

grating insights from cognitive science, neuroscience,

psychology, and design. Also, research could focus

on better adaptability and resilience of Co-Creative

Robotics to navigate VUCA environments effectively.

Also, innovative approaches to ML, sensor tech-

nologies, and decision-making algorithms that enable

robots real-time learning and adaptation are needed.

Furthermore, ethical and societal implications of Co-

Creative Robotics, including privacy, autonomy, and

the impact on human well-being, are investigable.

In CNs, it is important to conduct empirical studies

to examine how various collaborative network con-

ﬁgurations impact the development and implemen-

tation of creative robotic systems. Additionally, de-

veloping frameworks or methodologies for establish-

ing and managing CNs in the context of Co-Creative

Robotics, including strategies for building trust, fos-

tering communication, and aligning goals among di-

verse stakeholders, are required.

ACKNOWLEDGEMENTS

This work was funded by the Portuguese “Fundac¸

para a Ci

encia e Tecnologia” through “Strategic pro-

gram UIDB/00066/2020” (UNINOVA-CTS).

Moving into Co-Creative Robotics

313

REFERENCES

Cai, X., Ning, H., Dhelim, S., Zhou, R., Zhang, T., Xu, Y.,

and Wan, Y. (2021). Robot and its living space: A

roadmap for robot development based on the view of

living space. Digital Communications and Networks,

7(4):505–517.

Camarinha-Matos, L. M. and Afsarmanesh, H. (2018).

Roots of collaboration: nature-inspired solutions for

collaborative networks. IEEE Access, 6:30829–

30843.

Camarinha-Matos, L. M. and Afsarmanesh, H. (2021). The

evolution path to collaborative networks 4.0. Ad-

vancing Research in Information and Communication

Technology: IFIP’s Exciting First 60+ Years, Views

from the Technical Committees and Working Groups,

pages 170–193.

Cresswell, K., Cunningham-Burley, S., and Sheikh, A.

(2018). Health care robotics: qualitative exploration

of key challenges and future directions. Journal of

medical Internet research, 20(7):e10410.

Fragapane, G., Ivanov, D., Peron, M., Sgarbossa, F., and

Strandhagen, J. O. (2022). Increasing ﬂexibility and

productivity in industry 4.0 production networks with

autonomous mobile robots and smart intralogistics.

Annals of operations research, 308(1):125–143.

Guerrini, F. M. and Yamanari, J. S. (2019). A systematic re-

view of collaborative networks: implications for sens-

ing, smart and sustainable enterprises. In Collabora-

tive Networks and Digital Transformation: 20th IFIP

WG 5.5 Working Conference on Virtual Enterprises,

PRO-VE 2019, Turin, Italy, September 23–25, 2019,

Proceedings 20, pages 69–80. Springer.

Hooman, S. (2023). Creative Robotics. Colour Edition.

Hor

akov

a, J. and Kelemen, J. (2008). The robot story: why

robots were born and how they grew up.

Javaid, M., Haleem, A., Singh, R. P., and Suman, R. (2021).

Substantial capabilities of robotics in enhancing i4.0

implementation. Cognitive Robotics, 1:58–75.

Kalaitzidou, M. and Pachidis, T. P. (2023). Recent robots in

steam education. Education Sciences, 13(3):272.

Kappas, A. and Gratch, J. (2023). These aren’t the droids

you are looking for: Promises and challenges for the

intersection of affective science and robotics/ai. Affec-

tive Science, 4(3):580–585.

Kattel, R., Lember, V., and T

onurist, P. (2020). Collabora-

tive innovation and human-machine networks. Public

management review, 22(11):1652–1673.

Kluger, L. C., Gorris, P., Kochalski, S., Mueller, M. S., and

Romagnoni, G. (2020). Studying human–nature re-

lationships through a network lens: A systematic re-

view. People and Nature, 2(4):1100–1116.

Leigh, N. G., Kraft, B., and Lee, H. (2020). Robots, skill

demand and manufacturing in us regional labour mar-

kets. Cambridge Journal of Regions, Economy and

Society, 13(1):77–97.

Liu, J., Wang, Z., Qian, L., Luo, R., and Luo, X. (2023).

Task-oriented systematic design of a heavy-duty elec-

trically actuated quadruped robot with high perfor-

mance. Sensors, 23(15):6696.

Marchetti, E., Nikghadam-Hojjati, S., and Barata, J. (2023).

Collaborative network 5.0: By design human values

and human-centred based extended collaborative net-

works. In Working Conference on Virtual Enterprises,

pages 415–430. Springer.

Maroto-G

omez, M., Castro-Gonz

alez,

A., Malfaz, M.,

and Salichs, M.

A. (2023). A biologically inspired

decision-making system for the autonomous adaptive

behavior of social robots. Complex & Intelligent Sys-

tems, 9(6):6661–6679.

Mor, R. S., Kumar, D., Singh, A., and Neethu, K. (2022).

Robotics and automation for agri-food 4.0: Innovation

and challenges. In Agri-food 4.0: Innovations, chal-

lenges and strategies, pages 189–199. Emerald Pub-

lishing Limited.

Narayan, S., Aquif, M., Kalim, A. R., Chagarlamudi, D.,

and Harshith Vignesh, M. (2022). Search and re-

connaissance robot for disaster management. In Ma-

chines, Mechanism and Robotics: Proceedings of iN-

aCoMM 2019, pages 187–201. Springer.

Nikghadam-Hojjati, S. and Barata, J. (2019). Computa-

tional creativity to design cyber-physical systems in

industry 4.0. In Collaborative Networks and Digi-

tal Transformation: 20th IFIP WG 5.5 Working Con-

ference on Virtual Enterprises, PRO-VE 2019, Turin,

Italy, September 23–25, 2019, Proceedings 20, pages

29–40. Springer.

obrega, L., Marchhausen, L., Martinez, L. F., Lima, Y.,

Almeida, M., Lyra, A., Barbosa, C. E., and Moreira de

Souza, J. (2023). Ai delphi: Machine-machine collab-

oration for exploring the future of work. Available at

SSRN 4660589.

Pawlicka, A., Pawlicki, M., Kozik, R., and Chora

s, M.

(2022). Human-driven and human-centred cybersecu-

rity: policy-making implications. Transforming Gov-

ernment: People, Process and Policy, 16(4):478–487.

Santos, N. B., Bavaresco, R. S., Tavares, J. E., Ramos, G.

d. O., and Barbosa, J. L. (2021). A systematic map-

ping study of robotics in human care. Robotics and

Autonomous Systems, 144:103833.

Thuruthel, T. G., Shih, B., Laschi, C., and Tolley, M. T.

(2019). Soft robot perception using embedded soft

sensors and recurrent neural networks. Science

Robotics, 4(26):eaav1488.

Ventura, D. (2019). Autonomous intentionality in compu-

tationally creative systems. Computational creativity:

The philosophy and engineering of autonomously cre-

ative systems, pages 49–69.

Wong, C., Yang, E., Yan, X.-T., and Gu, D. (2018). Au-

tonomous robots for harsh environments: a holistic

overview of current solutions and ongoing challenges.

Systems Science & Control Engineering, 6(1):213–

219.

Yao, B. (2021). International research collaboration: chal-

lenges and opportunities. Journal of Diagnostic Med-

ical Sonography, 37(2):107–108.

Zhuge, H. (2020). Cyber-physical-social intelligence.

Cyber-Physical-Social Intelligence.

WEBIST 2024 - 20th International Conference on Web Information Systems and Technologies

314