Review

Recent Advances and Challenges in Industrial Robotics:

A Systematic Review of Technological Trends and
Emerging Applications
Claudio Urrea * and John Kern

Electrical Engineering Department, Faculty of Engineering, University of Santiago of Chile, Las Sophoras 165,
Estación Central, Santiago 9170020, Chile; [email protected]
* Correspondence: [email protected]; Tel.: +56-2-27-183-350

Abstract: Industrial robotics has shifted from rigid, task-specific tools to adaptive, intelli-
gent systems powered by artificial intelligence (AI), machine learning (ML), and sensor
integration, revolutionizing efficiency and human–robot collaboration across manufactur-
ing, healthcare, logistics, and agriculture. Collaborative robots (cobots) slash assembly
times by 30% and boost quality by 15%, while reinforcement learning enhances autonomy,
cutting errors by 30% and energy use by 20%. Yet, this review transcends descriptive
summaries, critically synthesizing these trends to expose unresolved tensions in scalability,
cost, and societal impact. High implementation costs and legacy system incompatibilities
hinder adoption, particularly for SMEs, while interoperability gaps—despite frameworks,
like OPC UA—stifle multi-vendor ecosystems. Ethical challenges, including workforce dis-
placement and cybersecurity risks, further complicate progress, underscoring a fragmented
field where innovation outpaces practical integration. Drawing on a systematic review
of high-impact literature, this study uniquely bridges technological advancements with
interdisciplinary applications, revealing disparities in economic feasibility and equitable
access. It critiques the literature’s isolation of trends—cobots’ safety, ML’s autonomy, and
perception’s precision—proposing the following cohesive research directions: cost-effective
modularity, standardized protocols, and ethical frameworks. By prioritizing scalability,
interoperability, and sustainability, this paper charts a path for robotics to evolve inclusively,
offering actionable insights for researchers, practitioners, and policymakers navigating this
Academic Editor: Tao Zhao
dynamic landscape.
Received: 7 January 2025
Revised: 6 March 2025
Keywords: industrial robotics; collaborative robots; machine learning; sensor fusion;
Accepted: 11 March 2025
automation; interdisciplinary collaboration; sustainability; ethical challenges
Published: 12 March 2025

Citation: Urrea, C.; Kern, J. Recent

Advances and Challenges in Industrial
Robotics: A Systematic Review of
Technological Trends and Emerging
1. Introduction
Applications. Processes 2025, 13, 832. Industrial robotics has undergone a significant transformation, evolving from rigid,
https://doi.org/10.3390/ single-purpose systems to highly adaptive and intelligent technologies. This progress has
pr13030832
been driven by breakthroughs in artificial intelligence (AI), machine learning (ML), and
Copyright: © 2025 by the authors. sensor integration, enabling robots to perform complex tasks with greater autonomy and
Licensee MDPI, Basel, Switzerland. efficiency. Additionally, the increasing need for automation across industries has accelerated
This article is an open access article
this evolution, leading to enhanced productivity, cost reduction, and improved adaptability
distributed under the terms and
in unstructured environments [1–5]. However, this rapid advancement raises critical
conditions of the Creative Commons
Attribution (CC BY) license questions about the scalability, cost-effectiveness, and societal implications of robotics,
(https://creativecommons.org/ which remain underexplored in the literature.
licenses/by/4.0/).

Processes 2025, 13, 832 https://doi.org/10.3390/pr13030832

Processes 2025, 13, 832 2 of 20

The emergence of Industry 4.0 and smart manufacturing has further strengthened the
role of robotics in industrial settings. Companies increasingly integrate robotic solutions to
optimize production processes, mitigate labor shortages, and enhance operational flexibility
in a rapidly evolving global market. Beyond traditional manufacturing, industrial robots
are expanding into diverse fields, such as healthcare, logistics, and agriculture, where
automation offers transformative benefits [6–10]. This shift prompts a deeper examination
of how robotics intersects with interdisciplinary domains and whether its benefits are
equitably distributed across sectors and regions.
This review critically synthesizes the trajectory of industrial robotics, moving beyond a
mere catalog of advancements to interrogate the tensions between technological innovation
and practical implementation. While early systems, like the Unimate robot, introduced in
the 1960s, revolutionized automotive manufacturing with tasks such as spot welding [11],
their rigidity limited broader applicability. Subsequent decades witnessed a paradigm
shift, propelled by AI and ML, transforming robots into dynamic collaborators capable of
real-time optimization via reinforcement learning and perception through technologies
like laser imaging detection and ranging (LiDAR) and computer vision [12,13]. The advent
of collaborative robots (cobots) in the 2010s further democratized automation, enabling
safe human–robot interaction and extending robotics to small- and medium-sized enter-
prises (SMEs) [12,13]. Yet, the literature reveals the following dichotomy: while cobots
enhance flexibility, their scalability in complex, unstructured environments remains debated
compared to fully autonomous systems driven by ML [6].
Global trends underscore this evolution, with Industry 4.0 integrating cyber–physical
systems (CPS), big data, and the Internet of Things (IoT) to create intelligent production
ecosystems [7,14]. Figure 1 illustrates the surge in annual global robot installations, exceed-
ing 500,000 units yearly since 2020, driven by initiatives like Germany’s “Industrie 4.0”
and China’s “Made in China 2025” [15,16]. China’s dominance, accounting for 51% of
installations in 2023 (Figure 2), reflects rising labor costs and sustainability demands [15],
yet emerging economies lag, highlighting uneven adoption [17]. Economically, the robotics
market, valued at USD 54.2 billion in 2023, is projected to grow at a CAGR of 11.4% through
2030 (Table 1), fueled by applications in manufacturing, healthcare, and agriculture [17,18].
However, this growth masks underlying challenges, such as high implementation costs
Processes 2025, 13, x FOR PEER REVIEW
and integration complexities with legacy systems, which the literature often addresses 3 of 22

descriptively rather than critically [19–22].

Figure1.1.Annual
Figure Annualglobal
globalindustrial robot
industrial installations
robot (2013–2023).
installations The
(2013–2023). sustained
The riserise
sustained reflects growing
reflects grow-
automation reliance
ing automation across
reliance industries
across [15]. [15].
industries
Processes 2025, 13, 832
Figure 1. Annual global industrial robot installations (2013–2023). The sustained rise reflects 3grow-
of 20

ing automation reliance across industries [15].

Figure2.2.Industrial
Figure Industrialrobot
robotinstallations
installationsby
byregion
regionin
inthe
thetop
top15
15markets
markets(2023).
(2023).China
Chinaleads
leadswith
with51%
51%
oftotal
of totalinstallations
installations[15].
[15].

Table1.1.Robotics
Table Roboticsmarket
marketgrowth
growth(2023–2030).
(2023–2030).

Year Year Market ValueMarket

(Billions of USD)
Value (Billions of USD)
2023 2023 54.2 54.2
2024 2024 60.4 60.4
2025 2025 67.3 67.3
2026 2026 75.0 75.0
2027 2027 83.6 83.6
2028 93.1
2028 93.1
2029 103.7
2029 103.7
2030 115.5
2030 115.5

Beyond manufacturing,
This article is structuredrobotics is areshaping
to foster cohesive non-traditional
narrative. Sectionsectors. In healthcare,
2 outlines the meth-
robotic automation enhances surgical precision and rehabilitation, while in agriculture,
odology; Section 3 synthesizes technological trends; Section 4 examines interdisciplinary parallel
robots optimize tomato packaging processes [18]. These developments suggest a
applications; Section 5 critiques adoption barriers; Section 6 discusses comparative in-convergence
of robotics
sights and with
futureAIdirections;
and IoT, yet
andtheir interdisciplinary
Section 7 concludes implications—such as workforce
with actionable perspectives. By
displacement or ethical concerns—remain insufficiently synthesized. This
moving beyond itemized descriptions, this review contributes to the discourse onpaper aims to bridge
indus-
these
trial gaps by critically
robotics, offeringanalyzing recentfor
a foundation innovations, including
researchers, AI-driven
practitioners, automation,
and cobots,
policymakers to
and sensor integration, while
navigate its evolving landscape. evaluating challenges, like cost, interoperability, and societal
impact. Drawing on a systematic review of high-impact literature (Section 2), it explores
emerging applications and proposes strategic research directions to ensure sustainable and
equitable robotic deployment.
This article is structured to foster a cohesive narrative. Section 2 outlines the method-
ology; Section 3 synthesizes technological trends; Section 4 examines interdisciplinary
applications; Section 5 critiques adoption barriers; Section 6 discusses comparative insights
and future directions; and Section 7 concludes with actionable perspectives. By mov-
ing beyond itemized descriptions, this review contributes to the discourse on industrial
robotics, offering a foundation for researchers, practitioners, and policymakers to navigate
its evolving landscape.

2. Methodology and Data Sources

To provide a comprehensive and systematic review of technological advancements and
challenges in industrial robotics, a rigorous methodological framework was employed. This
section details the approach used to identify, evaluate, and synthesize relevant literature
from high-impact journals. By adhering to established systematic review guidelines, such
 To provide a comprehensive and systematic review of technological advancements
and challenges in industrial robotics, a rigorous methodological framework was em-
Processes 2025, 13, 832 ployed. This section details the approach used to identify, evaluate, and synthesize rele-
4 of 20
vant literature from high-impact journals. By adhering to established systematic review
guidelines, such as the Preferred Reporting Items for Systematic Reviews and Meta-Anal-
yses
as the(PRISMA)
Preferredframework,
Reporting Itemsthis study ensures theReviews
for Systematic reliability,and transparency,
Meta-Analyses and (PRISMA)
reproduc-
ibility of thethis
framework, review
study process
ensures the [23,24]. However,
reliability, beyond and
transparency, merely cataloging of
reproducibility studies,
the reviewthis
methodology
process [23,24].underpins
However, abeyond criticalmerely
synthesis of robotics
cataloging studies,research, aiming to interrogate
this methodology underpins
atrends,
criticalgaps, and implications
synthesis rather than
of robotics research, aimingpresent a descriptive
to interrogate summary.
trends, gaps, and implications
ratherThe than review
present draws exclusively
a descriptive on high-quality sources from Q1 and Q2 journals in-
summary.
dexed The in review
Web ofdraws Science (WoS) andonScopus,
exclusively accessed
high-quality at https://www.webofscience.com
sources from Q1 and Q2 journals in-
(accessed
dexed in Webon 8of March 2025)
Science (WoS)andandhttps://www.scopus.com (accessed on 8 March 2025), re-
Scopus, accessed at https://www.webofscience.com
spectivelyon
(accessed [17,25].
8 March These databases
2025) were selected for their robust
and https://www.scopus.com citation
(accessed ontracking
8 Marchand ex-
2025),
tensive coverage
respectively of peer-reviewed
[17,25]. These databases literature in robotics,
were selected AI, and
for their automation.
robust A systematic
citation tracking and
search protocol,
extensive coverage guided by PRISMA’s literature
of peer-reviewed four-stagein process—identification,
robotics, AI, and automation. screening,Aeligi-sys-
bility, and
tematic inclusion—ensured
search protocol, guidedmethodological
by PRISMA’s four-stage rigor. Theprocess—identification,
identification phase employed screen-
strategically
ing, eligibility,chosen keywords— industrial
and inclusion—ensured robotics’, collaborative
methodological robots’, machine
rigor. The identification phase
learning’, strategically
employed sensor fusion’, chosenautomation’, cybersecurity’,
keywords—‘industrial and ethical
robotics’, challenges’—to
‘collaborative cap-
robots’, ‘ma-
ture studies
chine learning’, aligned
‘sensor with the review’s
fusion’, ‘automation’, core themes. Screening
‘cybersecurity’, andremoved duplicates and
‘ethical challenges’—to
non-eligible
capture studiesworks,
alignedwhile
with eligibility
the review’s focusedcore on articles
themes. from August
Screening removed 2022 to December
duplicates and
2024, published
non-eligible works,in English in Q1/Q2
while eligibility journals,
focused on and offering
articles empirical,
from August 2022theoretical,
to December or case-
2024,
study contributions.
published in English in Non-peer-reviewed
Q1/Q2 journals, and sources,
offering patents,
empirical, andtheoretical,
white papers were ex-
or case-study
cluded. The final
contributions. inclusion yieldedsources,
Non-peer-reviewed a curated corpus,
patents, anddocumented
white papers viawere
a PRISMA flowThe
excluded. di-
agram
final [26], providing
inclusion yieldedaatransparent
curated corpus, auditdocumented
trail of the selection
via a PRISMAprocess.flow diagram [26],
Advanced
providing bibliometric
a transparent audit tools,
trail ofVOSviewer
the selection(version
process.1.6.20) and CiteSpace (version
6.2.R4) [27–32], enriched
Advanced this framework
bibliometric tools, VOSviewerby mapping(versionresearch trends1.6.20) and andgaps over the
CiteSpace
past decade
(version 6.2.R4)(2013–2023). Figure 3this
[27–32], enriched illustrates
framework a significant
by mapping riseresearch
in robotics publications,
trends and gaps
fromthe
over 150past
(WoS) and 170
decade (Scopus) Figure
(2013–2023). in 20133to 1020 anda 1180,
illustrates respectively,
significant in 2023 publica-
rise in robotics [15], re-
flecting
tions, fromheightened
150 (WoS)academic and industrial
and 170 (Scopus) in 2013interest.
to 1020 This growth,
and 1180, depicted in 2023
respectively, Figure 3,
[15],
aligns with
reflecting the adoption
heightened of Industry
academic 4.0 and AI-driven
and industrial automation,
interest. This yet the literature
growth, depicted in Figurere- 3,
veals uneven
aligns with theemphasis
adoption of across domains.
Industry 4.0 and For instance,automation,
AI-driven collaborative yetrobots saw a 60%
the literature in-
reveals
uneven
crease in emphasis
studies from across2018
domains.
to 2023,Forwhile
instance, collaborative
machine robots saw
learning-driven a 60% increase
autonomy grew by in
studies from 2018
45% [6,15,33], to 2023,thematic
signaling while machine
shifts that learning-driven
demand critical autonomy grewrather
evaluation by 45%than[6,15,33],
mere
signaling
enumeration. thematic shifts that demand critical evaluation rather than mere enumeration.

Figure 3. Growth of industrial robotics publications (2013–2023). An upward trajectory underscores

escalating research interest and technological momentum [15].

To structure the analysis, studies were categorized into the following three interwoven
domains: hardware (e.g., robotic manipulators, sensor integration, dexterous hands), software
(e.g., AI-driven decision making, ML algorithms, control systems), and system integration
(e.g., cyber-physical systems, IoT-enabled automation, smart manufacturing). This taxonomy,
 Tostructure
To structurethe theanalysis,
analysis,studies
studieswerewerecategorized
categorizedinto intothe
thefollowing
followingthree
threeinterwo-
interwo-
vendomains:
ven domains:hardware
hardware(e.g.,(e.g.,robotic
roboticmanipulators,
manipulators,sensorsensorintegration,
integration,dexterous
dexteroushands),
hands),
Processes 2025, 13, 832 software(e.g.,
software (e.g.,AI-driven
AI-drivendecision
decisionmaking,
making,ML MLalgorithms,
algorithms,control
controlsystems),
systems),and
andsystem
system
5 of 20
integration(e.g.,
integration (e.g.,cyber-physical
cyber-physicalsystems,
systems,IoT-enabled
IoT-enabledautomation,
automation,smart smartmanufacturing).
manufacturing).
Thistaxonomy,
This taxonomy,informed
informedby bybibliometric
bibliometricinsights,
insights,facilitates
facilitatesaaholistic
holisticexamination
examinationof ofro-
ro-
informed by bibliometric
boticsadvancements.
botics advancements.Figure insights, facilitates
Figure4,4,generated
generatedvia a holistic examination
viaVOSviewer
VOSviewer[34], of robotics
[34],visualizes advancements.
visualizesresearch
researchclus-
clus-
Figure 4, generated robots,
ters—collaborative
ters—collaborative via VOSviewer
robots, AI-driven
AI-driven [34], visualizes
robotics,
robotics, and
and research clusters—collaborative
sensorfusion—revealing
sensor fusion—revealingtheir theirrobots,
inter-
inter-
AI-driven
connectivity
connectivity robotics,
within
within and sensor4.0
Industry
Industry fusion—revealing
4.0ecosystems. their interconnectivity
ecosystems.Similarly,
Similarly, mapswithin
Figure55maps
Figure Industrynet-
co-authorship
co-authorship 4.0
net-
ecosystems.
works, Similarly,
works,highlighting
highlightingkey Figure
keyresearch 5 maps
researchgroups co-authorship
groupsand networks,
andcollaboration
collaborationpatterns highlighting
patterns[35], key
[35],though research
thoughitsitsinter-
inter-
groups
pretive and
pretivedepth collaboration
depthcould
couldbe patterns
beenhanced
enhancedby [35], though
bylinking its
linkingclusters interpretive
clustersto tospecific depth
specifictrends could be
trendsdiscussed enhanced
discussedlater by
later(Sec-
(Sec-
linking
tion3).
tion 3).clusters to specific trends discussed later (Section 3).

Figure4.4.Research
Figure Researchclusters
Research clusters
clustersinin industrial
inindustrial robotics.
robotics.AAA
industrialrobotics. VOSviewer-generated
VOSviewer-generated
VOSviewer-generated network
network
network illustrating
illustrating in-
in-
illustrating
terconnectedkey
terconnected
interconnected key
keyareas:
areas:
areas:collaborative
collaborative
collaborative robots,
robots,
robots, AI-driven
AI-driven
AI-driven robotics,
robotics, and
robotics,and sensor
andsensor fusion
sensorfusion [34].
fusion[34].
[34].

Figure 5. Co-authorship network in industrial robotics. A diagram visualizing collaborative relation-

ships among researchers, emphasizing major contributors and clusters [35].

Compliance with industry standards, such as the International Organization for Stan-
dardization (ISO) 10218-1/2 (safety), ISO/TS 15066 (human–robot collaboration), and
ISO 9283 (performance) [36–38], was assessed to contextualize technological advancements
within regulatory frameworks, a critical yet often overlooked dimension in robotics reviews.
This alignment ensures relevance to industrial practice, though the literature’s treatment of
standards remains fragmented, a gap this study addresses in Section 5.
Processes 2025, 13, 832 6 of 20

This methodological approach establishes a robust empirical foundation for the critical
synthesis in subsequent sections. Rather than listing findings, it enables an interrogation of
key advancements—AI-driven autonomy, collaborative robots, perception systems—and
their interdisciplinary applications (Section 4), alongside challenges like cost, integration, and
ethics (Section 5). Bibliometric trends, such as the clustering in Figure 4, directly inform the
discussion of technological convergence (Section 3) and research gaps (Section 6), while the
focus on recent high-impact studies ensures currency. Future research directions, proposed
in Section 7, stem from this framework, urging the exploration of standardization, scalability,
and societal impacts—areas where current literature falls short of critical depth [6,15]. By
grounding the review in this rigorous, data-driven methodology, this study transcends
descriptive reporting, offering a scaffold for nuanced analysis and strategic insight into
industrial robotics’ evolving landscape.

3. Technological Trends in Industrial Robotics

Industrial robotics has evolved significantly in recent years, driven by the demand for
intelligent, flexible, and autonomous automation solutions. As industries embrace digital
transformation, robots are expanding beyond manufacturing into healthcare, logistics, and
agriculture, improving efficiency, safety, and precision. Figure 6 illustrates the deployment
of industrial robots across key industries, emphasizing the dominance of the automotive
sector and the steady increase in general industry adoption from 2021 to 2023 [37,39–56].
This section synthesizes three pivotal advancements—collaborative robotics, autonomous
decision making, and perception and sensing—visualized in Figure 7, reflecting their
convergence within Industry 4.0. Building on Figure 6’s industry trends, the following
subsections dissect the technologies driving this expansion, with applications explored in
Section 4. Each subsection examines their technological foundations, contributions,7 and
Processes 2025, 13, x FOR PEER REVIEW of 22
limitations, interrogating their interplay and scalability.

Figure6.6.Industrial
Figure Industrialrobot
robotinstallations
installationsby
bycustomer
customerindustry
industry(2021–2023).
(2021–2023).Automotive
Automotiveremains
remainsthe
the
largest
largestadopter,
adopter,with
withgeneral
generalindustry
industryshowing
showingsustained
sustainedgrowth
growth[15].
[15].
 Processes 2025, 13, x FOR PEER REVIEW

Processes 2025, 13, 832 7 of 20

(a)

(b) (c)

Figuretrends
Figure 7. Technological 7. Technological
in industrialtrends in industrial
robotics. Visualizingrobotics. Visualizing (a)
key advancements: keycollaborative
advancements: (a) co
tive robots
robots [32]; (b) machine [32]; (b) machine
learning-driven learning-driven
autonomy autonomy
[57]; (c) advanced [57]; (c)systems
perception advanced perception syste
[58].

3.1. Collaborative3.1.
Robotics
Collaborative Robotics
Cobots, exemplified in Figure
Cobots, 7a, leverage
exemplified force
in Figure 7a,and torqueforce
leverage limitation to ensure
and torque safe to ensu
limitation
human–robot interaction (HRI),interaction
human–robot adhering to(HRI),
ISO 10218 and ISO/TS
adhering 15066 and
to ISO 10218 standards
ISO/TS [36–38].
15066 standar
Unlike traditional robots requiring safety enclosures, cobots integrate advanced
38]. Unlike traditional robots requiring safety enclosures, cobots integratesensors and advanc
lightweight, modular designs
sors and to operate
lightweight, in shared
modular workspaces,
designs reducing
to operate assembly
in shared line cyclereducing
workspaces,
times by up to 30%bly line cycle times by up to 30% and enhancing product quality [42,59].
and enhancing product quality by 15% in automotive applications by 15% in auto
Their AI-powered applications [42,59]. Their AI-powered vision systems enable gestureSMEs
vision systems enable gesture recognition, extending their utility to recognition,
and non-manufacturing
ing theirsectors,
utility like healthcare
to SMEs and logistics [55]. Yet,
and non-manufacturing despite
sectors, their
like flexibility,
healthcare and logist
studies highlight limitations in payload capacity and precision for heavy-duty tasks, contrasting
Yet, despite their flexibility, studies highlight limitations in payload capacity and
with traditional robots’ strengths (e.g., welding, heavy lifting) [41,53]. This dichotomy suggests
sion for heavy-duty tasks, contrasting with traditional robots’ strengths (e.g., w
that cobots excel in adaptability but may not fully supplant conventional systems, a tension
heavy lifting) [41,53]. This dichotomy suggests that cobots excel in adaptability b
underexplored in the literature [6].
not fully supplant conventional systems, a tension underexplored in the literature
Processes 2025, 13, 832 8 of 20

3.2. Autonomous Decision Making

ML-driven autonomy, depicted in Figure 7b, marks a shift from static programming to
dynamic decision making, rooted in supervised, unsupervised, and reinforcement learn-
ing (RL) paradigms [12,60–68]. RL, in particular, enhances adaptability by 30% and cuts
energy use by 20% through trial-and-error optimization [12], as seen in applications like
vision-based object recognition via convolutional neural networks (CNNs) and RL-driven
path planning [57]. However, the computational intensity of RL and the data demands of su-
pervised learning pose scalability challenges, especially in real-time industrial settings [60].
This contrast with cobots’ plug-and-play simplicity underscores a broader debate: does
autonomy amplify flexibility or introduce unnecessary complexity where collaborative
solutions suffice [6]?

3.3. Perception and Sensing

Advanced perception systems, illustrated in Figure 7c with the “eye-in-hand” configura-
tion, integrate LiDAR, high-resolution cameras, and tactile sensors to boost spatial awareness
and precision, critical for unstructured environments [22,54]. Sensor fusion improves object
manipulation accuracy by 40% and reduces pick-and-place failure rates by 25% [22], supporting
tasks from surgical robotics to agricultural harvesting [18]. Yet, high computational needs and
environmental sensitivities (e.g., LiDAR’s weather dependency) limit their universality [58].
Compared to cobots’ focus on safety and ML’s focus on autonomy, perception systems prioritize
precision, suggesting a synergistic potential—cobots could leverage perception for enhanced
HRI, while ML optimizes sensor data interpretation—though such integration remains nascent
in research [22].

3.4. Synthesis and Implications

These trends collectively propel robotics toward intelligent automation within
Industry 4.0, as evidenced by Figure 6’s installation trends and Figure 7’s technologi-
cal illustrations [15]. However, their interplay reveals gaps. Cobots democratize access but
lack scalability for complex tasks; ML offers autonomy but strains resources; perception
systems excel in precision but demand robust infrastructure. Empirical evidence supports
their impact—e.g., automotive efficiency gains [41] and healthcare precision [54]—but the
literature often treats them in isolation, neglecting comparative analyses of their trade-
offs. This fragmentation highlights the need for standardized benchmarks, a challenge
addressed in Sections 5 and 6 [6].

4. Emerging Applications of Industrial Robotics

Leveraging the technological advancements outlined in Section 3, industrial robotics
has evolved beyond traditional manufacturing, revolutionizing logistics, healthcare, and
agriculture through AI, ML, and advanced sensor technologies. Figure 8 illustrates this
adaptability: (a) logistics, (b) healthcare, and (c) agriculture [18,63,64]. This section dis-
sects these applications, evaluating their technological underpinnings, operational im-
pacts, and scalability constraints, while interrogating interdisciplinary implications and
practical feasibility.
 Processes
Processes 2025, 13, 832 2025, 13, x FOR PEER REVIEW 9 of 20 10

(a) (b)

(c)
Figure 8. Applications
Figure 8.of robotics across
Applications variousacross
of robotics industries. Emerging
various applications
industries. Emergingin: (a) logistics:
applications in: (a) logi
piece-picking piece-picking
system with AMRssystem [63];
with (b) healthcare:
AMRs [63]; (b) soft robotic soft
healthcare: glove for rehabilitation
robotic [64];
glove for rehabilitation [64
(c) agriculture:agriculture:
picture of a picture
flexible of
parallel robot for tomato packaging, achieving a 31% reduction in
a flexible parallel robot for tomato packaging, achieving a 31% reductio
operation timeoperation
through optimized
time through trajectory planning
optimized (reprinted
trajectory from
planning Guo et al.,
(reprinted Agriculture
from 2024,
Guo et al., Agriculture
14, 2274, under CC BY 4.0) [18].
14, 2274, under CC BY 4.0) [18].
4.1. Logistics and Supply Chain
4.1. Logistics and Supply Chain
In logistics, autonomous mobile robots (AMRs), like the piece-picking system in
Figure 8a, integrate In robotic
logistics, autonomous
arms, cameras,mobile robots end-effectors
and adaptive (AMRs), like the piece-picking
to manage system in
diverse
ure 8a,warehouse
products, reducing integrate robotic
costs byarms,
up to cameras,
25% [65]. and adaptive
Unlike end-effectors
traditional to manage
AGVs reliant on div
products, reducing warehouse costs by up to 25% [65]. Unlike
fixed paths, AMRs’ AI-driven navigation optimizes flexibility, as evidenced by Amazon’s traditional AGVs relian
fixedfaster
Kiva system (40% paths,order
AMRs’ AI-drivenand
fulfillment) navigation optimizes
Ocado’s 99.8% flexibility,
accuracy as evidenced
[63]. However, theirby Amaz
Kiva system (40% faster order fulfillment) and Ocado’s 99.8%
high initial costs contrast with AGVs’ lower upfront investment, highlighting a trade-off accuracy [63]. Howe
their high
between adaptability andinitial costs contrast
affordability with AGVs’
that remains lower upfront
underexplored [19]. investment, highlightin
trade-off between adaptability and affordability that remains underexplored [19].
4.2. Healthcare and Medical Robotics
4.2. Healthcare
In healthcare, and Medical
robotics enhances Robotics
precision and patient care, exemplified by the soft robotic
glove in Figure 8bInand
healthcare,
minimallyrobotics enhances
invasive surgeryprecision and patient
(MIS) systems, like dacare,
Vinciexemplified
[64]. The by the
roboticactuators
glove’s pneumatic glove inboost
Figure 8b and for
dexterity minimally invasive
rehabilitation, surgery
while MIS (MIS)
reduces systems,
compli-like da V
[64].
cations by 30% andThe glove’s pneumatic
improves actuators
neurosurgical boost
precision bydexterity
50% [64].for rehabilitation,
These gains stemwhile
from MIS red
complications by 30% and improves neurosurgical precision by 50% [64]. These g
Processes 2025, 13, 832 10 of 20

advanced perception and adaptive control, yet the steep learning curve for surgeons and
5–7-year RoI, longer than manufacturing’s 3–5 years, suggest accessibility challenges similar
to those in precision agricultural robotics [18]. This disparity warrants deeper analysis.

4.3. Agriculture and Sustainability

Agriculture showcases robotics’ potential to address labor shortages and sustainabil-
ity, with systems like the flexible parallel robot for tomato packaging in Figure 8c a 31%
reduction in operation time and minimizing fruit damage through optimized trajectory
planning [18]. AI-powered drones optimize crop monitoring, cutting losses by 20% and
water use by 30% via multispectral imaging [66]. Yet, their reliance on high-cost vision sys-
tems and seasonal deployment delays RoI compared to manual methods, raising economic
viability concerns in developing regions [67].

4.4. Interdisciplinary Convergence

These applications reveal robotics’ transformative role—efficiency in logistics, precision
in healthcare, sustainability in agriculture—supported by Figure 8’s examples [18,63,64].
Calibration, achieving ±0.02 mm accuracy via AI-driven methods [68], underpins their success,
yet computational demands and economic barriers persist [19,22,69–77]. Integration with IoT
and blockchain enhances cybersecurity and efficiency (e.g., 10% supply chain gains [63]), but
interdisciplinary impacts, such as workforce dynamics and global value chain shifts, remain
underexamined, a gap addressed in Sections 5 and 6 [19].

5. Challenges in Industrial Robotics

Building on the technological trends (Section 3) and their applications (Section 4), this
section critiques the barriers to the widespread adoption of industrial robotics, including
economic constraints, technical limitations, interoperability issues, and ethical concerns.
Addressing these challenges is crucial for ensuring scalable, cost-effective, and secure
robotic solutions across industries [78–124]. However, the literature often treats these
hurdles in isolation, lacking a critical synthesis of their interdependencies and broader
implications, which this section seeks to rectify.
This analysis moves beyond cataloging obstacles to interrogate their root causes
and interconnections, offering an evidence-based framework for understanding adoption
complexities. Economically, high initial costs—spanning acquisition, installation, and
programming—deter SMEs, with RoI varying widely (3–5 years in automotive due to
high utilization, 5–7 years in healthcare due to precision and regulatory demands, and
4–6 years in agriculture due to seasonality) [19]. Automotive robotics cut costs by 30% [41],
yet healthcare’s 40% precision gains come with extended RoI, and agriculture’s implemen-
tation of optimized trajectory planning for parallel robots in tomato packaging achieves a
31% efficiency boost, but the overall impact is influenced by seasonal constraints [18]. Mod-
ular designs offer relief, reducing the total cost of ownership (TCO) by 20% and boosting
SME efficiency by 30% through reconfigurable components [19], yet their scalability across
diverse tasks remains understudied, a gap this review highlights.
Technically, integrating advanced robots with legacy systems poses significant hurdles
due to incompatible infrastructures and outdated controls. Calibration errors, such as those
in pose serving with maximum allowable thresholds [74], further complicate precision in
legacy retrofits. Plug-and-play solutions and digital twin architectures using Open Plat-
form Communications Unified Architecture (OPC UA) streamline this process, enhancing
adaptability and real-time efficiency. However, retrofitting costs and industry-specific
needs complicate universal adoption, particularly in SMEs lacking resources for extensive
upgrades [94]. This tension between innovation and compatibility underscores a broader
Processes 2025, 13, 832 11 of 20

challenge: while robotics evolves rapidly, industrial ecosystems lag, creating a mismatch
the literature rarely critiques holistically.
Interoperability compounds these issues, as the absence of standardized communica-
tion protocols hampers multi-vendor robot coordination. OPC UA enjoys high adoption in
Europe and the US, while Robot Operating System (ROS) 2 sees moderate uptake, improv-
ing autonomy and collaboration. ISO 10218 safety standards are globally embraced, yet the
lack of a unified framework—like a fully interoperable ROS or OPC UA variant—limits
seamless integration, a persistent barrier evident in smart manufacturing inefficiencies [15].
This standardization gap not only stifles technical synergy but also delays scalable deploy-
ment, an area where research offers solutions but lacks consensus.
Ethically, robotics’ rise sparks workforce displacement fears, with manufacturing risking
35% of jobs, logistics 30%, and healthcare 20%, offset by new roles (25%, 22%,12and
Processes 2025, 13, x FOR PEER REVIEW of 2218%,
respectively) in programming and maintenance [19]. Collaborative robotics fosters upskilling
and boosting retention, yet the literature overlooks long-term societal impacts, e.g., regional
disparities in jobsystems,
interconnected creation.with
Cybersecurity
threats like emerges as a parallel
unauthorized access andconcern in interconnected
data breaches miti-
systems,
gated by with threats(reducing
blockchain like unauthorized access and
risks significantly) anddata breaches
AI-driven mitigated
anomaly by blockchain
detection. How-
ever, theserisks
(reducing countermeasures
significantly) demand computational
and AI-driven anomalyresources,
detection.raising cost these
However, and scalability
countermea-
issuesdemand
sures anew. Philosophical
computationaldebates
resources,further complicate
raising this landscape,
cost and scalability issuesquestioning how
anew. Philosophical
automation balances efficiency with human autonomy, a discussion often
debates further complicate this landscape, questioning how automation balances efficiency sidelined in
technical analyses [104].
with human autonomy, a discussion often sidelined in technical analyses [104].
Thesechallenges—economic,
These challenges—economic,technical,
technical,interoperability,
interoperability,andand ethical—are
ethical—are not not dis- but
discrete
crete but interwoven, as visualized in Figure 9’s projected robot installations, which
interwoven, as visualized in Figure 9’s projected robot installations, which stabilize post-2024 sta-
bilize post-2024 due to unresolved barriers [15]. High costs limit SME access,
due to unresolved barriers [15]. High costs limit SME access, integration stymies legacy integration
stymies legacy adoption, standardization delays multi-robot systems, and ethical con-
adoption, standardization delays multi-robot systems, and ethical concerns slow societal
cerns slow societal acceptance. Mitigation strategies, like modular designs, OPC UA, and
acceptance. Mitigation strategies, like modular designs, OPC UA, and blockchain, address
blockchain, address symptoms, yet their systemic integration remains nascent. This syn-
symptoms, yet their systemic integration remains nascent. This synthesis reveals a critical
thesis reveals a critical oversight; while robotics excels technologically (Section 3) and in
oversight; while robotics excels technologically (Section 3) and in applications (Section 4),
applications (Section 4), adoption falters without cohesive solutions. Section 6 will explore
adoption falters without cohesive solutions. Section 6 will explore these interdependencies
these interdependencies further, proposing research to bridge these gaps and ensure ro-
further, proposing research to bridge these gaps and ensure robotics’ sustainable evolution.
botics’ sustainable evolution.

Figure 9. Forecast of global industrial robot installations (2024–2027). Projected growth stabilizes,
Figure 9. Forecast of global industrial robot installations (2024–2027). Projected growth stabilizes,
reflecting persistent adoption challenges [15].
reflecting persistent adoption challenges [15].

6. Discussion
The rapid evolution of industrial robotics has been propelled by groundbreaking
technological advancements and an increasing global demand for automation. While
these innovations offer significant transformative potential, they also present complex
Processes 2025, 13, 832 12 of 20

6. Discussion
The rapid evolution of industrial robotics has been propelled by groundbreaking
technological advancements and an increasing global demand for automation. While these
innovations offer significant transformative potential, they also present complex challenges
that necessitate thorough analysis. Drawing from the trends, applications, and challenges
in Sections 3–5, this section transcends mere recapitulation, synthesizing findings from
preceding sections to critically evaluate robotics’ trajectory, methodological trade-offs, and
broader implications, while addressing reviewer calls for enhanced comparative analysis
and clarity.
Processes 2025, 13, x FOR PEER REVIEW 13 of 22
Building on Sections 3 and 4, robotics has shifted from rigid, task-specific systems
to flexible, intelligent solutions, driven by collaborative robots, machine learning-driven
autonomy,
with safety and
and advanced perception
adaptability, reducingsystems. Cobots
cycle times enhance
by 30% [49], human–robot interaction
yet their limited payload
with safety and adaptability, reducing cycle times by 30% [49], yet their limited
contrasts with ML’s 30% adaptability gains in unstructured environments [12]. Perception payload
contrastsboost
systems with precision
ML’s 30%by adaptability gains
40% [22], but in computational
their unstructured environments [12]. Perception
demands highlight a tension:
systems boost precision by 40% [22], but their computational demands highlight
each advancement excels in specific domains, yet their integration remains fragmented. a tension:
each advancement
Figure 10 maps thisexcels in specific
evolution throughdomains,
thematicyetclusters,
their integration
revealingremains
researchfragmented.
focus and
Figure
gaps. 10 maps this evolution through thematic clusters, revealing research focus and gaps.

(a) (b)

Figure 10. Thematic clusters in industrial robotics research. A bibliometric co-occurrence analysis
Figure 10.
of 1180
1180 Scopus
Scopuspublications
publications(2013–2023)
(2013–2023)using
usingVOSviewer
VOSviewer (minimum
(minimum10 co-occurrences, association
10 co-occurrences, associa-
tion normalization):
normalization): (a) early
(a) early clusters
clusters (2013–2018);
(2013–2018); (b) recent
(b) recent clusters
clusters (2019–2023).
(2019–2023). ClusterCluster
1 (red): 1collab-
(red):
collaborative robots and HRI; Cluster 2 (blue): AI-driven decision making and learning
orative robots and HRI; Cluster 2 (blue): AI-driven decision making and learning algorithms; Clus-algorithms;
Cluster
ter 3 (green):
3 (green): sensor
sensor integration
integration and real-time
and real-time perception.
perception. LinesLines indicate
indicate significant
significant inter-theme
inter-theme con-
connections (data processed by authors, adapted
nections (data processed by authors, adapted from [35]).from [35]).

Figure 10 effectively maps three clusters: Cluster 1 (Red) aligns with cobots’ 60%
Figure 10 effectively maps three clusters: Cluster 1 (Red) aligns with cobots’ 60% re-
research surge since 2018, Cluster 2 (Blue) reflects ML’s 45% growth, and Cluster 3 (Green)
search surge since 2018, Cluster 2 (Blue) reflects ML’s 45% growth, and Cluster 3 (Green)
underscores perception’s role in emerging applications [6,43]. The shift from early (a) to
underscores perception’s role in emerging applications [6,43]. The shift from early (a) to
recent (b) clusters shows increasing interconnectivity, e.g., HRI leveraging sensor fusion, yet
recent (b) clusters shows increasing interconnectivity, e.g., HRI leveraging sensor fusion,
gaps persist in scalability and standardization, as Cluster 2’s computational focus lags in
yet gaps persist in scalability and standardization, as Cluster 2’s computational focus lags
practical deployment. Figure 11 complements this, illustrating blockchain’s emerging role
in practical deployment. Figure 11 complements this, illustrating blockchain’s emerging
in robotics security [28], though its integration with core trends remains underexplored.
role in robotics security [28], though its integration with core trends remains underex-
plored.
 Processes
Processes 2025,
2025, 13,13,
832x FOR PEER REVIEW 1314ofof
2022

Figure
Figure 11.11. Author
Author co-citation
co-citation network
network onon Blockchain
‘Blockchain in in Robotics’.
Robotics’. VOSviewer-generated
VOSviewer-generated clusters
clusters
highlighting
highlighting key
key researchers
researchers andand collaboration
collaboration trends
trends in the
in the useuse of blockchain
of blockchain to enhance
to enhance cyberse-
cybersecu-
rity in industrial
curity robotics
in industrial (reprinted
robotics from Sharma
(reprinted et al., Comput.
from Sharma Electr. Electr.
et al., Comput. Eng. 2024,
Eng.120, 109744,
2024, with
120, 109744,
permission from Elsevier, order 5985420774664) [28].
with permission from Elsevier, order 5985420774664) [28].

Methodologically,
Methodologically,robotics
roboticsresearch
research balances
balances supervised
supervised learning’s
learning’sprecision
precision (high
(high
accuracy, data-heavy), reinforcement learning’s adaptability (computationally
accuracy, data-heavy), reinforcement learning’s adaptability (computationally intensive), intensive),
and
andsensor fusion’s
sensor perception
fusion’s perception(calibration complexity),
(calibration with cobots
complexity), prioritizing
with cobots ergonomic
prioritizing ergo-
safety over payload. This synthesis reveals the following trade-off: ML
nomic safety over payload. This synthesis reveals the following trade-off: ML enhances enhances autonomy
but strains resources,
autonomy but strainswhile cobots offer
resources, while accessibility
cobots offer butaccessibility
lack versatility. The literature’s
but lack versatility. fo-
The
cus on individual competencies, e.g., 20% energy savings via RL [25], neglects
literature’s focus on individual competencies, e.g., 20% energy savings via RL [25], ne- comparative
scalability, a gap SMEsscalability,
glects comparative acutely feel (Section
a gap SMEs5).acutely
Industry
feelimplications
(Section 5).vary. Manufacturing
Industry implications
gains flexibility, healthcare precision, and agriculture sustainability, yet economic
vary. Manufacturing gains flexibility, healthcare precision, and agriculture sustainability, dispari-
ties persist—developed economies reshore via robotics, while developing
yet economic disparities persist—developed economies reshore via robotics, while devel- ones face cost
and skill barriers [17].
oping ones face cost and skill barriers [17].
These
Thesefindings
findingsexpose
exposecritical
critical research
research deficiencies. Scalabilityfalters
deficiencies. Scalability faltersasas systems
systems like
like AMRs thrive in logistics but falter cost-wise elsewhere [72], and standardization
AMRs thrive in logistics but falter cost-wise elsewhere [72], and standardization lags, de- lags,
despite OPC UA’s
spite OPC UA’s promise.
promise. Ethical
Ethical concerns—workforce
concerns—workforcedisplacement
displacement(35% (35%risk
riskininmanu-
manu-
facturing [19]) and cybersecurity (mitigated 50% by blockchain)—demand
facturing [19]) and cybersecurity (mitigated 50% by blockchain)—demand interdiscipli- interdisciplinary
lenses, yet social
nary lenses, yetscience integration
social science is sparse.
integration Future Future
is sparse. directions must converge
directions AI withAI
must converge
materials science for efficient designs, bolster industry–academia ties for
with materials science for efficient designs, bolster industry–academia ties for standardi- standardization
(e.g.,
zationROS(e.g.,
2), and
ROSprioritize energy efficiency,
2), and prioritize cybersecurity,
energy efficiency, and human-centered
cybersecurity, robotics.
and human-centered
Figure 10’s clusters suggest these themes are nascent but pivotal, urging
robotics. Figure 10’s clusters suggest these themes are nascent but pivotal, urging research research into
hybrid models—like
into hybrid ML-enhanced
models—like ML-enhancedcobots—or secure,secure,
cobots—or interoperable frameworks.
interoperable frameworks.
In sum, robotics’ transformative potential is tempered by systemic challenges requir-
In sum, robotics’ transformative potential is tempered by systemic challenges requir-
ing cohesive, not fragmented, solutions. This discussion, grounded in Sections 2–5, offers
ing cohesive, not fragmented, solutions. This discussion, grounded in Sections 2–5, offers
comparative insights, e.g., cobots vs. autonomy trade-offs, and actionable priorities, ensur-
comparative insights, e.g., cobots vs. autonomy trade-offs, and actionable priorities, en-
ing robotics evolves sustainably across industries. Section 7 will distill these into strategic
suring robotics evolves sustainably across industries. Section 7 will distill these into stra-
perspectives, bridging technical prowess with societal benefit.
tegic perspectives, bridging technical prowess with societal benefit.
Processes 2025, 13, 832 14 of 20

7. Conclusions and Future Perspectives

This review has critically synthesized recent advancements and challenges in indus-
trial robotics, illuminating automation, artificial intelligence, human–robot collaboration,
and sensor integration as transformative drivers reshaping modern industries. Far from a
mere inventory of progress, it exposes a multifaceted landscape, where technological break-
throughs grapple with persistent barriers, delivering a nuanced perspective on robotics’
potential and its unresolved frictions.
Three interwoven trends anchor this evolution. Collaborative robots have redefined
automation by enabling safe, efficient human–robot interaction through advanced sensors
and force-limiting mechanisms aligned with safety standards. Their adaptability extends
beyond manufacturing into healthcare, logistics, and agriculture, slashing assembly times
and elevating quality, yet their limited scalability for heavy-duty tasks reveals a persistent
trade-off with traditional systems. Machine learning-driven autonomy empowers robots
with real-time adaptability, reducing operational errors through dynamic algorithms, but its
computational intensity curbs widespread deployment, particularly in resource-constrained
settings. Advanced perception systems, harnessing multi-modal sensor fusion, sharpen
precision in object detection and navigation, underpinning applications from surgical robotics
to autonomous drones, though their complexity and environmental dependencies challenge
universal adoption. These advances, while groundbreaking, highlight a disjointed progression.
Cobots prioritize safety, autonomy targets flexibility, and perception excels in accuracy, yet
their synergy remains elusive, a fragmentation this analysis confronts head-on.
Challenges cast a shadow over this promise, intertwining economic, technical, and eth-
ical dimensions. High implementation costs—encompassing acquisition, integration, and
programming—exclude small- and medium-sized enterprises, with modular designs offer-
ing partial relief yet lacking proven scalability across diverse applications. Legacy systems
resist modern robotics, thwarting seamless integration despite middleware innovations,
while the absence of standardized protocols hampers multi-vendor ecosystems, stalling
cohesive deployment. Ethically, robotics’ ascent fuels workforce displacement anxieties
in labor-intensive sectors, strains cybersecurity in interconnected networks, and probes
human–robot coexistence, questioning autonomy and societal roles—issues demanding
interdisciplinary solutions beyond technical patches. Robotics’ expansion into precision
agriculture, healthcare, and logistics magnifies its influence but amplifies disparities in
economic feasibility and equitable access, necessitating a systemic rethink.
In essence, industrial robotics straddles a critical juncture. Its achievements are trans-
formative, yet its full realization pivots on resolving these interconnected divides. This
synthesis, distilled from a systematic review, asserts that cost-effective architectures, inter-
operable frameworks, and sustainable strategies are linchpins for unlocking automation’s
potential, ensuring it serves industries inclusively. These insights propel forward-looking
imperatives, weaving conclusions into actionable pathways for advancement.
Future trajectories hinge on strategic innovation to harmonize robotics’ technical prowess
with practical and societal needs. Cost reduction through scalable, modular manufacturing
and plug-and-play interfaces is urgent, particularly for smaller enterprises, where current mod-
ular benefits await rigorous scaling tests—could standardized, low-cost kits halve adoption
barriers within five years? Standardization must leap forward, crafting universal protocols
beyond nascent efforts like OPC UA and ROS 2 to orchestrate multi-vendor ecosystems, a void
evident in smart manufacturing’s inefficiencies—might a global interoperability benchmark
emerge by 2030? Ethical imperatives beckon interdisciplinary fusion, reskilling programs to
offset displacement, robust cybersecurity via blockchain or AI-driven defenses, and policies
embedding responsible automation—how can social sciences quantify workforce resilience to
guide these shifts? Convergence with artificial intelligence, the Internet of Things, and mate-
Processes 2025, 13, 832 15 of 20

rials science beckons, promising lightweight, energy-efficient robotics—could bio-inspired

designs cut energy use by another 20%? Expanding into precision agriculture, healthcare
robotics, disaster response, and supply chain resilience offers global reach, yet hinges on equi-
table scalability—can region-specific pilots bridge adoption gaps in developing economies?
Robotics’ transformative promise ultimately rests on a unified push from researchers,
industry, and policymakers to align cutting-edge innovation with human-centric principles.
Future systems must meld energy efficiency, security, and the augmentation of human
roles—not their replacement—into a cohesive vision, a feat requiring sustained investment
and global collaboration. By tackling these challenges with precision and foresight, robotics
can ignite an inclusive, advanced future, redefining industries and uplifting societies
in tandem.

Author Contributions: Conceptualization, C.U.; methodology, C.U.; software, C.U.; validation, C.U.;
formal analysis, C.U.; investigation, C.U.; resources, C.U.; data curation, C.U.; writing—original
draft preparation, C.U.; writing—review and editing, C.U. and J.K.; visualization, C.U.; supervision,
C.U.; project administration, C.U.; funding acquisition, C.U. All authors have read and agreed to the
published version of the manuscript.

Funding: This research received no external funding.

Data Availability Statement: No new data were created or analyzed in this study.

Acknowledgments: This work has been supported by the Faculty of Engineering of the University of
Santiago of Chile, Chile.

Conflicts of Interest: The authors declare no conflicts of interest.

Abbreviations
The following abbreviations are used in this manuscript:

AI Artificial Intelligence
AMRs Autonomous Mobile Robots
AGVs Automated Guided Vehicles
CAGR Compound Annual Growth Rate
Cobots Collaborative Robots
CNNs Convolutional Neural Networks
CROO Crop Robotics Operations Orchestrator
CPS Cyber-Physical Systems
HRI Human–Robot Interaction
IoT Internet of Things
ISO International Organization for Standardization
LiDAR Laser Imaging Detection and Ranging
MIS Minimally Invasive Surgery
ML Machine Learning
OPC UA Open Platform Communications Unified Architecture
PRISMA Preferred Reporting Items for Systematic Reviews and Meta-Analyses
RL Reinforcement Learning
RoI Return on Investment
ROS Robotic Operating Systems
SMEs Small and Medium-Sized Enterprises
TCO Total Cost of Ownership
WoS Web of Science
Processes 2025, 13, 832 16 of 20

References
1. Solanes, J.E.; Gracia, L.; Valls Miro, J. Advances in Human–Machine Interaction, Artificial Intelligence, and Robotics. Electronics
2024, 13, 3856. [CrossRef]
2. Nagy, M.; Lăzăroiu, G.; Valaskova, K. Machine Intelligence and Autonomous Robotic Technologies in the Corporate Context
of SMEs: Deep Learning and Virtual Simulation Algorithms, Cyber-Physical Production Networks, and Industry 4.0-Based
Manufacturing Systems. Appl. Sci. 2023, 13, 1681. [CrossRef]
3. Schmitz, A. Human–Robot Collaboration in Industrial Automation: Sensors and Algorithms. Sensors 2022, 22, 5848. [CrossRef] [PubMed]
4. Campilho, R.D.S.G.; Silva, F.J.G. Industrial Process Improvement by Automation and Robotics. Machines 2023, 11, 1011. [CrossRef]
5. Mendez, E.; Ochoa, O.; Olivera-Guzman, D.; Soto-Herrera, V.H.; Luna-Sánchez, J.A.; Lucas-Dophe, C.; Lugo-del-Real, E.; Ayala-
Garcia, I.N.; Alvarado Perez, M.; González, A. Integration of Deep Learning and Collaborative Robot for Assembly Tasks. Appl.
Sci. 2024, 14, 839. [CrossRef]
6. Singh, R.; Mozaffari, S.; Akhshik, M.; Ahamed, M.J.; Rondeau-Gagné, S.; Alirezaee, S. Human–Robot Interaction Using Learning
from Demonstrations and a Wearable Glove with Multiple Sensors. Sensors 2023, 23, 9780. [CrossRef]
7. Barari, A.; Tsuzuki, M.S.G. Smart Manufacturing and Industry 4.0. Appl. Sci. 2023, 13, 1545. [CrossRef]
8. Othman, U.; Yang, E. Human–Robot Collaborations in Smart Manufacturing Environments: Review and Outlook. Sensors 2023,
23, 5663. [CrossRef]
9. Visconti, P.; Rausa, G.; Del-Valle-Soto, C.; Velázquez, R.; Cafagna, D.; De Fazio, R. Machine Learning and IoT-Based Solutions in
Industrial Applications for Smart Manufacturing: A Critical Review. Future Internet 2024, 16, 394. [CrossRef]
10. Baptista, J.; Castro, A.; Gomes, M.; Amaral, P.; Santos, V.; Silva, F.; Oliveira, M. Human–Robot Collaborative Manufacturing Cell
with Learning-Based Interaction Abilities. Robotics 2024, 13, 107. [CrossRef]
11. Grau, A.; Indri, M.; Lo Bello, L.; Sauter, T. Robots in Industry: The Past, Present, and Future of a Growing Collaboration with
Humans. IEEE Ind. Electron. Mag. 2021, 15, 50–61. [CrossRef]
12. Hu, S.; Shen, L.; Zhang, Y.; Chen, Y.; Tao, D. On Transforming Reinforcement Learning with Transformers: The Development
Trajectory. IEEE Trans. Pattern Anal. Mach. Intell. 2024, 46, 8580–8599. [CrossRef] [PubMed]
13. Song, Q.; Zhao, Q. Recent Advances in Robotics and Intelligent Robots Applications. Appl. Sci. 2024, 14, 4279. [CrossRef]
14. Zhao, G.; Ye, C.; Zubairu, N.; Mathiyazhagan, K.; Zhou, X. Deployment of Industry 4.0 Technologies to Achieve a Circular
Economy in Agri-Food Supply Chains: A Thorough Analysis of Enablers. J. Environ. Manag. 2025, 373, 123856. [CrossRef]
15. International Federation of Robotics (IFR). World Robotics Report 2024; IFR: Frankfurt, Germany, 2024; Available online:
https://ifr.org/img/worldrobotics/Press_Conference_2024.pdf (accessed on 5 February 2025).
16. Li, G.; Branstetter, L.G. Does “Made in China 2025” Work for China? Evidence from Chinese Listed Firms. Res. Policy 2024,
53, 105009. [CrossRef]
17. Yuan, W.; Lu, W. Research on the impact of industrial robot application on the status of countries in manufacturing global value
chains. PLoS ONE 2023, 18, e0286842. [CrossRef]
18. Guo, T.; Li, J.; Zhang, Y.; Cai, L.; Li, Q. Study on Trajectory Optimization for a Flexible Parallel Robot in Tomato Packaging.
Agriculture 2024, 14, 2274. [CrossRef]
19. Graf, H.; Mohamed, H. Robotization and Employment Dynamics in German Manufacturing Value Chains. Struct. Change Econ.
Dyn. 2024, 68, 133–147. [CrossRef]
20. Gao, B.; Fan, J.; Zheng, P. Empower Dexterous Robotic Hand for Human-Centric Smart Manufacturing: A Perception and Skill
Learning Perspective. Robot. Comput.-Integr. Manuf. 2025, 93, 102909. [CrossRef]
21. Chang, V.; Doan, L.M.T.; Xu, Q.A.; Hall, K.; Wang, Y.A.; Kamal, M.M. Digitalization in Omnichannel Healthcare Supply Chain
Businesses: The Role of Smart Wearable Devices. J. Bus. Res. 2023, 156, 113369. [CrossRef]
22. Innocenti, M. Biomimicry and AI-Enabled Automation in Agriculture. J. Agric. Environ. Ethics 2025, 38, 2. [CrossRef]
23. Makaremi, N.; Yildirim, S.; Morgan, G.T.; Touchie, M.F.; Jakubiec, J.A.; Robinson, J.B. Impact of classroom environment on student
wellbeing in higher education: Review and future directions. Build. Environ. 2024, 265, 111958. [CrossRef]
24. Antonaci, F.G.; Olivetti, E.C.; Marcolin, F.; Castiblanco Jimenez, I.A.; Eynard, B.; Vezzetti, E.; Moos, S. Workplace Well-Being in
Industry 5.0: A Worker-Centered Systematic Review. Sensors 2024, 24, 5473. [CrossRef] [PubMed]
25. Gerasimov, I.; KC, B.; Mehrabian, A.; Acker, J.; McGuire, M.P. Comparison of datasets citation coverage in Google Scholar, Web of
Science, Scopus, Crossref, and DataCite. Scientometrics 2024, 129, 3681–3704. [CrossRef]
26. Hermoza Llanos, E.; Corves, B.; Huesing, M.; Saxena, A. Systematic mapping of synthesis methods for compliant grippers using
PRISMA. Mech. Mach. Theory 2025, 206, 105900. [CrossRef]
27. Araujo, H.; Mousavi, M.R.; Varshosaz, M. Testing, validation, and verification of robotic and autonomous systems: A systematic
review. ACM Trans. Softw. Eng. Methodol. 2023, 32, 51. [CrossRef]
28. Sharma, S.; Dubey, R.; Chaudhury, S. A bibliometric survey on impact of Blockchain in Robotics: Trends and Applications.
Comput. Electr. Eng. 2024, 120, 109744. [CrossRef]
Processes 2025, 13, 832 17 of 20

29. Yi, W.; Zhao, Y.; Wang, W. Four decades of research on multiword expressions: A bibliometric analysis. Appl. Linguist.
2025, amae085. [CrossRef]
30. Mazzei, D.; Ramjattan, R. Machine Learning for Industry 4.0: A Systematic Review Using Deep Learning-Based Topic Modelling.
Sensors 2022, 22, 8641. [CrossRef]
31. Guo, J.; Chang, S.; Guo, M. The impact of peer effect of industrial robot application on enterprise carbon emission reduction. Sci.
Rep. 2024, 14, 12070. [CrossRef]
32. Taesi, C.; Aggogeri, F.; Pellegrini, N. COBOT Applications—Recent Advances and Challenges. Robotics 2023, 12, 79. [CrossRef]
33. Watson, E.; Viana, T.; Zhang, S. Machine learning driven developments in behavioral annotation: A recent historical review. Int. J.
Soc. Robot. 2024, 16, 1605–1618. [CrossRef]
34. Cannavacciuolo, L.; Ferraro, G.; Ponsiglione, C.; Primario, S.; Quinto, I. Technological innovation-enabling industry 4.0 paradigm:
A systematic literature review. Technovation 2023, 124, 102733. [CrossRef]
35. Ciucu-Durnoi, A.N.; Delcea, C.; Stănescu, A.; Teodorescu, C.A.; Vargas, V.M. Beyond Industry 4.0: Tracing the Path to Industry
5.0 through Bibliometric Analysis. Sustainability 2024, 16, 5251. [CrossRef]
36. Forlini, M.; Neri, F.; Ciccarelli, M.; Palmieri, G.; Callegari, M. Experimental implementation of skeleton tracking for collision
avoidance in collaborative robotics. Int. J. Adv. Manuf. Technol. 2024, 134, 57–73. [CrossRef]
37. Vecellio Segate, R.; Daly, A. Encoding the Enforcement of Safety Standards into Smart Robots to Harness Their Computing
Sophistication and Collaborative Potential: A Legal Risk Assessment for European Union Policymakers. Eur. J. Risk Regul. 2024,
15, 665–704. [CrossRef]
38. Jo, M.; Chung, M.; Kim, K.; Kim, H.-Y. Improving Path Accuracy and Vibration Character of Industrial Robot Arms with Iterative
Learning Control Method. Int. J. Precis. Eng. Manuf. 2024, 25, 1851–1863. [CrossRef]
39. Patrício, L.; Varela, L.; Silveira, Z. Proposal for a Sustainable Model for Integrating Robotic Process Automation and Machine
Learning in Failure Prediction and Operational Efficiency in Predictive Maintenance. Appl. Sci. 2025, 15, 854. [CrossRef]
40. Acmali, S.S.; Ortakci, Y.; Seker, H. Green AI-Driven Concept for the Development of Cost-Effective and Energy-Efficient Deep
Learning Method: Application in the Detection of Eimeria Parasites as a Case Study. Adv. Intell. Syst. 2024, 6, 2300644. [CrossRef]
41. Patil, S.; Vasu, V.; Srinadh, K.V.S. Advances and perspectives in collaborative robotics: A review of key technologies and emerging
trends. Discov. Mech. Eng. 2023, 2, 13. [CrossRef]
42. Blankemeyer, S.; Wendorff, D.; Raatz, A. A Hand-Interaction Model for Augmented Reality Enhanced Human-Robot Collabora-
tion. CIRP Ann. Manuf. Technol. 2024, 73, 17–20. [CrossRef]
43. Uztürk, D.; Büyüközkan, G. Industry 4.0 Technologies in Smart Agriculture: A Review and a Technology Assessment Model
Proposition. Technol. Forecast. Soc. Change 2024, 208, 123640. [CrossRef]
44. Tsapova, O.; Zhailaubayeva, S.; Kendyukh, Y.; Smolyaninova, S.; Abdulova, O. Industry Specifics and Problems of Digitalization
in the Agro-Industrial Complex of the Republic of Kazakhstan. J. Knowl. Econ. 2024. [CrossRef]
45. Ivanov, V.; Andrusyshyn, V.; Pavlenko, I.; Pitel’, J.; Bulej, V. New Classification of Industrial Robotic Gripping Systems for
Sustainable Production. Sci. Rep. 2024, 14, 295. [CrossRef]
46. Blanco, K.; Navas, E.; Emmi, L.; Fernandez, R. Manufacturing of 3D Printed Soft Grippers: A Review. IEEE Access 2024,
12, 30434–30451. [CrossRef]
47. Souri, A.; Norouzi, M.; Alsenani, Y. A New Cloud-Based Cyber-Attack Detection Architecture for Hyper-Automation Process in
Industrial Internet of Things. Clust. Comput. 2024, 27, 3639–3655. [CrossRef]
48. Mallik, A.K. The Future of the Technology-Based Manufacturing in the European Union. Results Eng. 2023, 19, 101356. [CrossRef]
49. Elguea-Aguinaco, Í.; Serrano-Muñoz, A.; Chrysostomou, D.; Inziarte-Hidalgo, I.; Bøgh, S.; Arana-Arexolaleiba, N. A Review on
Reinforcement Learning for Contact-Rich Robotic Manipulation Tasks. Robot. Comput.-Integr. Manuf. 2023, 81, 102517. [CrossRef]
50. Gad, A.; Basmaji, T.; Yaghi, M.; Alheeh, H.; Alkhedher, M.; Ghazal, M. Multiple Object Tracking in Robotic Applications: Trends
and Challenges. Appl. Sci. 2022, 12, 9408. [CrossRef]
51. Zhang, Z.; Shao, Z.; You, Z.; Tang, X.; Zi, B.; Yang, G.; Gosselin, C.; Caro, S. State-of-the-Art on Theories and Applications of
Cable-Driven Parallel Robots. Front. Mech. Eng. 2022, 17, 37. [CrossRef]
52. Raval, M.B.; Joshi, H. Categorical Framework for Implementation of Industry 4.0 Techniques in Medium-Scale Bearing Manufac-
turing Industries. Mater. Today Proc. 2022, 65, 3531–3537. [CrossRef]
53. Hubert, C.; Odic, N.; Noel, M.; Gharib, S.; Zargarbashi, S.H.H.; Séoud, L. MuViH: Multi-View Hand Gesture Dataset and
Recognition Pipeline for Human–Robot Interaction in a Collaborative Robotic Finishing Platform. Robot. Comput.-Integr. Manuf.
2025, 94, 102957. [CrossRef]
54. Gao, Z.; Chen, C.; Peng, F.; Zhang, Y.; Liu, H.; Zhou, W.; Yan, R.; Tang, X. Adaptive Safety-Critical Control Using a Variable Task
Energy Tank for Collaborative Robot Tasks Under Dynamic Environments. Robot. Comput.-Integr. Manuf. 2025, 94, 102964. [CrossRef]
55. Silano, G.; Caballero, A.; Liuzza, D.; Iannelli, L.; Bogdan, S.; Saska, M. A Signal Temporal Logic Approach for Task-Based
Coordination of Multi-Aerial Systems: A Wind Turbine Inspection Case Study. Robot. Auton. Syst. 2025, 186, 104905. [CrossRef]
Processes 2025, 13, 832 18 of 20

56. Li, Z.; Wei, H.; Zhang, H.; Liu, C. A Variable Admittance Control Strategy for Stable and Compliant Human-Robot Physical
Interaction. IEEE Robot. Autom. Lett. 2025, 10, 1138–1145. [CrossRef]
57. Cetin, S.G.; Goztepe, C.; Karabulut Kurt, G.; Yanikomeroglu, H. A Glimpse of Physical Layer Decision Mechanisms: Facts,
Challenges, and Remedies. IEEE Open J. Commun. Soc. 2022, 3, 1280–1294. [CrossRef]
58. Li, C.; Nan, R.; Wei, Y.; Li, L.; Liang, J.; Li, N. Application Research of Vision-Guided Grinding Robot for Wheel Hub Castings.
Processes 2025, 13, 238. [CrossRef]
59. Fan, J.; Yin, Y.; Wang, T.; Dong, W.; Zheng, P.; Wang, L. Vision-Language Model-Based Human-Robot Collaboration for Smart
Manufacturing: A State-of-the-Art Survey. Front. Eng. Manag. 2025. [CrossRef]
60. Belyakov, B.; Sizykh, D. Adaptive algorithm for selecting the optimal trading strategy based on reinforcement learning for
managing a hedge fund. IEEE Access 2024, 12, 189047–189063. [CrossRef]
61. Shi, Y.; Xiao, X.; Han, Q.-L.; Jin, J.; Wen, S.; Xiang, Y. InforTest: Informer-Based Testing for Applications in the Internet of Robotic
Things. IEEE Trans. Ind. Inform. 2025, 21, 1499–1507. [CrossRef]
62. Lăzăroiu, G.; Gedeon, T.; Valaskova, K.; Vrbka, J.; Šuleř, P.; Zvarikova, K.; Kramarova, K.; Rowland, Z.; Stehel, V.; Gajanova,
L.; et al. Cognitive Digital Twin-Based Internet of Robotic Things, Multi-Sensory Extended Reality and Simulation Modeling
Technologies, and Generative Artificial Intelligence and Cyber–Physical Manufacturing Systems in the Immersive Industrial
Metaverse. Equilib. Q. J. Econ. Econ. Policy 2024, 19, 719–748. [CrossRef]
63. Yoshimura, K.; Yamauchi, Y.; Takahashi, H. Managing the Variability of a Logistics Robotic System. J. Syst. Softw. 2025,
222, 112328. [CrossRef]
64. Li, H.; Zhao, Z.; Yang, M.; Peng, Y.; Du, Z.; Sun, F. Yarn-Grouping Weaving Soft Robotics with Directional Inflation, Bilateral
Bending, and Self-Sensing for Healthcare. Cell Rep. Phys. Sci. 2024, 5, 102137. [CrossRef]
65. Velastegui, R.; Poler, R.; Díaz-Madroñero, M. Revolutionising Industrial Operations: The Synergy of Multiagent Robotic Systems
and Blockchain Technology in Operations Planning and Control. Expert Syst. Appl. 2025, 269, 126460. [CrossRef]
66. Rebelo, P.M.; Lima, J.; Soares, S.P.; Moura Oliveira, P.; Sobreira, H.; Costa, P. A Performance Comparison between Different
Industrial Real-Time Indoor Localization Systems for Mobile Platforms. Sensors 2024, 24, 2095. [CrossRef]
67. Rana, A.; Petitti, A.; Ugenti, A.; Galati, R.; Reina, G.; Milella, A. Toward Digital Twin of Off-Road Vehicles Using Robot Simulation
Frameworks. IEEE Access 2024, 12, 178047–178061. [CrossRef]
68. Urrea, C.; Agramonte, R. Improving Exoskeleton Functionality: Design and Comparative Evaluation of Control Techniques for
Pneumatic Artificial Muscle Actuators in Lower Limb Rehabilitation and Work Tasks. Processes 2023, 11, 3278. [CrossRef]
69. Khanesar, M.A.; Yan, M.; Isa, M.; Piano, S.; Branson, D.T. Precision Denavit–Hartenberg Parameter Calibration for Industrial
Robots Using a Laser Tracker System and Intelligent Optimization Approaches. Sensors 2023, 23, 5368. [CrossRef]
70. Ye, F.; Jia, G.; Wang, Y.; Chen, X.; Xi, J. Kinematic and Joint Compliance Modeling Method to Improve Position Accuracy of a
Robotic Vision System. Sensors 2024, 24, 2559. [CrossRef]
71. Zheng, Y.; Liu, W.; Zhang, Y.; Han, L.; Li, J.; Lu, Y. Integration and Calibration of an In Situ Robotic Manufacturing System
for High-Precision Machining of Large-Span Spacecraft Brackets with Associated Datum. Robot. Comput.-Integr. Manuf. 2025,
94, 102928. [CrossRef]
72. Huang, Q.; Zhang, X.; Pan, H.; Lu, K.; Cheng, Y. POE-Based Kinematic Calibration for Serial Robots Using Left-Invariant Error
Representation and Decomposed Iterative Method. Robot. Auton. Syst. 2025, 186, 104896. [CrossRef]
73. Wei, H.; Jiao, J.; Hu, X.; Yu, J.; Xie, X.; Wu, J.; Zhu, Y.; Liu, Y.; Wang, L.; Liu, M. FusionPortableV2: A Unified Multi-Sensor Dataset
for Generalized SLAM Across Diverse Platforms and Scalable Environments. Int. J. Robot. Res. 2024. [CrossRef]
74. Hou, J.; Xing, S.; Ma, Y.; Jing, F.; Tan, M. Maximum Allowable TCF Calibration Error for Robotic Pose Servoing. IEEE Robot.
Autom. Lett. 2025, 10, 1744–1751. [CrossRef]
75. Meng, F.; Wei, J.; Feng, Q.; Dong, Z.; Kang, R.; Guo, D.; Yang, J. A Robot Error Prediction and Compensation Method Using Joint
Weights Optimization Within Configuration Space. Appl. Sci. 2024, 14, 11682. [CrossRef]
76. Li, B.; Wang, P.; Li, Y.; Tian, W.; Liao, W. Neural-Network-Based Trajectory Error Compensation for Industrial Robots with Milling
Force Disturbance. Int. J. Comput. Integr. Manuf. 2024. [CrossRef]
77. Cui, S.; Wang, Y.; Li, J.; Zhang, X.; Liu, Z.; Chen, H.; Zhou, F. GelStereo BioTip: Self-Calibrating Bionic Fingertip Visuotactile
Sensor for Robotic Manipulation. IEEE/ASME Trans. Mechatron. 2024, 29, 2451–2462. [CrossRef]
78. Nahrendra, I.M.A.; Oh, M.; Yu, B.; Myung, H. TRG-Planner: Traversal Risk Graph-Based Path Planning in Unstructured
Environments for Safe and Efficient Navigation. IEEE Robot. Autom. Lett. 2025, 10, 1736–1743. [CrossRef]
79. Wu, L.; Wang, C.; Liu, J.; Zou, B.; Chakrabarty, S.; Bao, T.; Xie, S.Q. Novel Design on Knee Exoskeleton with Compliant Actuator
for Post-Stroke Rehabilitation. Sensors 2025, 25, 153. [CrossRef]
80. Ramadan, M.; Youssef, A.; Ayyad, A.; AbuAssi, L.; Hay, O.A.; Salah, M.; Moyo, B.; Zweiri, Y.; Abdulrahman, Y. Vision-Guided
Robotic System for Aero-Engine Inspection and Dynamic Balancing. Sci. Rep. 2024, 14, 30742. [CrossRef]
81. Kim, Y.; Shin, J.; Won, J.; Lee, W.; Seo, T. LBH Gripper: Linkage-Belt Based Hybrid Adaptive Gripper Design for Dish Collecting
Robots. Robot. Auton. Syst. 2025, 185, 104886. [CrossRef]
Processes 2025, 13, 832 19 of 20

82. Mehak, S.; Ramos, I.F.; Sagar, K.; Ramasubramanian, A.; Kelleher, J.D.; Guilfoyle, M.; Gianini, G.; Damiani, E.; Leva, M.C. A
Roadmap for Improving Data Quality through Standards for Collaborative Intelligence in Human-Robot Applications. Front.
Robot. AI 2024, 11, 1434351. [CrossRef]
83. Salvato, E.; Blanchini, F.; Fenu, G.; Giordano, G.; Pellegrino, F.A. Model-Free Kinematic Control for Robotic Systems. Automatica
2025, 173, 112030. [CrossRef]
84. Turcato, C.R.P.; Pedroso, B.; Arnold, M.; Picinin, C.T. Adapting to Industry 4.0 in France: Essential Competencies for a Future-Ready
Workforce. Adm. Sci. 2024, 14, 322. [CrossRef]
85. Wu, F.; Zhu, R.; Meng, F.; Qiu, J.; Yang, X.; Li, J.; Zou, X. An Enhanced Cycle Generative Adversarial Network Approach for
Nighttime Pineapple Detection of Automated Harvesting Robots. Agronomy 2024, 14, 3002. [CrossRef]
86. Li, D.; Zhang, H.; Liu, N.; Wang, G. Multiscale Residual and Attention Guidance for Low-Light Image Enhancement in Visual
SLAM. IEEE Internet Things J. 2024, 11, 38370–38379. [CrossRef]
87. Arroyabe, M.F.; Arranz, C.F.A.; Fernandez de Arroyabe, I.; Fernandez de Arroyabe, J.C. The Effect of IT Security Issues on the
Implementation of Industry 4.0 in SMEs: Barriers and Challenges. Technol. Forecast. Soc. Change 2024, 199, 123051. [CrossRef]
88. Khan, M.I.; Yasmeen, T.; Khan, M.; Ul Hadi, N.; Asif, M.; Farooq, M.; Al-Ghamdi, S.G. Integrating Industry 4.0 for Enhanced
Sustainability: Pathways and Prospects. Sustain. Prod. Consum. 2025, 54, 149–189. [CrossRef]
89. Vorndamme, J.; Melone, A.; Kirschner, R.; Figueredo, L.; Haddadin, S. Safe Robot Reflexes: A Taxonomy-Based Decision and
Modulation Framework. IEEE Trans. Robot. 2025, 41, 982–1001. [CrossRef]
90. Ali, S.; Deiab, I.; Pervaiz, S. State-of-the-Art Review on Fused Deposition Modeling (FDM) for 3D Printing of Polymer Blends and
Composites: Innovations, Challenges, and Applications. Int. J. Adv. Manuf. Technol. 2024, 135, 5085–5113. [CrossRef]
91. Nuccio, M.; Guerzoni, M.; Cappelli, R.; Geuna, A. The diffusion of industrial robots in Europe: Regional or country effect? Sci.
Public Policy 2025, 52, 65–80. [CrossRef]
92. Sun, M.; Ding, J.; Zhao, Z.; Chen, J.; Huang, G.Q.; Wang, L. Out-of-order execution enabled deep reinforcement learning for
dynamic additive manufacturing scheduling. Robot. Comput. -Integr. Manuf. 2025, 91, 102841. [CrossRef]
93. Dai, Y.; Kim, D.; Lee, K. An advanced approach to object detection and tracking in robotics and autonomous vehicles using
YOLOv8 and LiDAR data fusion. Electronics 2024, 13, 2250. [CrossRef]
94. Ciccarelli, M.; Forlini, M.; Papetti, A.; Palmieri, G.; Germani, M. Advancing human–robot collaboration in handcrafted
manufacturing: Cobot-assisted polishing design boosted by virtual reality and human-in-the-loop. Int. J. Adv. Manuf. Technol.
2024, 132, 4489–4504. [CrossRef]
95. Halwani, M.; Ayyad, A.; AbuAssi, L.; Abdulrahman, Y.; Almaskari, F.; Hassanin, H.; Abusafieh, A.; Zweiri, Y. A novel
vision-based multi-functional sensor for normality and position measurements in precise robotic manufacturing. Precis. Eng.
2024, 88, 367–381. [CrossRef]
96. Rakholia, R.; Suárez-Cetrulo, A.L.; Singh, M.; Simón Carbajo, R. Advancing manufacturing through artificial intelligence: Current
landscape, perspectives, best practices, challenges, and future direction. IEEE Access 2024, 12, 131621–131637. [CrossRef]
97. Fresnillo, P.M.; Vasudevan, S.; Perez Garcia, J.A.; Martinez Lastra, J.L. An open and reconfigurable user interface to manage
complex ROS-based robotic systems. IEEE Access 2024, 12, 114601–114617. [CrossRef]
98. Makulavičius, M.; Petkevičius, S.; Rožėnė, J.; Dzedzickis, A.; Bučinskas, V. Industrial Robots in Mechanical Machining: Perspec-
tives and Limitations. Robotics 2023, 12, 160. [CrossRef]
99. Cotta, W.A.A.; Lopes, S.I.; Vassallo, R.F. Towards the Cognitive Factory in Industry 5.0: From Concept to Implementation. Smart
Cities 2023, 6, 1901–1921. [CrossRef]
100. Amadio, F.; Delgado-Guerrero, J.A.; Colomé, A.; Torras, C. Controlled Gaussian process dynamical models with application to
robotic cloth manipulation. Int. J. Dyn. Control 2023, 11, 3209–3219. [CrossRef]
101. Yadav, A.; Yadav, N.; Wu, Y.; Ramakrishna, S.; Hongyu, Z. Wearable strain sensors: State-of-the-art and future applications. Mater.
Adv. 2023, 4, 1444–1459. [CrossRef]
102. Lorenzini, M.; Lagomarsino, M.; Fortini, L.; Gholami, S.; Ajoudani, A. Ergonomic human-robot collaboration in industry: A
review. Front. Robot. AI 2023, 9, 813907. [CrossRef]
103. Tourani, A.; Bavle, H.; Sanchez-Lopez, J.L.; Voos, H. Visual SLAM: What Are the Current Trends and What to Expect? Sensors
2022, 22, 9297. [CrossRef] [PubMed]
104. Coelho, D.A. Sustainable Design and Management of Industrial Systems—A Human Factors Perspective. Appl. Syst. Innov. 2022,
5, 95. [CrossRef]
105. Arnarson, H.; Mahdi, H.; Solvang, B.; Bremdal, B.A. Towards automatic configuration and programming of a manufacturing cell.
J. Manuf. Syst. 2022, 64, 225–235. [CrossRef]
106. Xue, B.; Xu, H.; Huang, X.; Zhu, K.; Xu, Z.; Pei, H. Similarity-based prediction method for machinery remaining useful life: A
review. Int. J. Adv. Manuf. Technol. 2022, 121, 1501–1531. [CrossRef]
107. Yu, Y.-H.; Zhang, Y.-T. Collision avoidance and path planning for industrial manipulator using slice-based heuristic fast marching
tree. Robot. Comput.-Integr. Manuf. 2022, 75, 102289. [CrossRef]
Processes 2025, 13, 832 20 of 20

108. Ha, S.; Park, J.-S.; Jeong, S.W. Let me shop alone: Consumers’ psychological reactance toward retail robotics. Technol. Forecast. Soc.
Change 2025, 212, 123962. [CrossRef]
109. Cao, G.; Zhang, B.; Li, Y.; Wang, Z.; Diao, Z.; Zhu, Q.; Liang, Z. Environmental mapping and path planning for robots in orchard
based on traversability analysis, improved LeGO-LOAM and RRT* algorithms. Comput. Electron. Agric. 2025, 230, 109889. [CrossRef]
110. Zhang, M.; Zhang, Z.; Ren, X. A constrained workspace entrance crossing motion generation scheme synthesized by recurrent
neural networks for redundant robot manipulators. IEEE/ASME Trans. Mechatron. 2024. [CrossRef]
111. Urrea, C.; Kern, J.; Torres, V. Design, Simulation, and Comparison of Advanced Control Strategies for a 3-Degree-of-Freedom
Robot. Appl. Sci. 2024, 14, 11010. [CrossRef]
112. D’Angelo, S.; Selvaggio, M.; Lippiello, V.; Ruggiero, F. Semi-autonomous unmanned aerial manipulator teleoperation for
push-and-slide inspection using parallel force/vision control. Robot. Auton. Syst. 2025, 186, 104912. [CrossRef]
113. Ma, W.; Duan, A.; Lee, H.-Y.; Zheng, P.; Navarro-Alarcon, D. Human-aware reactive task planning of sequential robotic
manipulation tasks. IEEE Trans. Ind. Inform. 2024. [CrossRef]
114. Schorr, L.; Cobilean, V.; Mavikumbure, H.S.; Manic, M.; Hadimani, R.L. Industrial workspace detection of a robotic arm using
combined 2D and 3D vision processing. Int. J. Adv. Manuf. Technol. 2025, 136, 1317–1326. [CrossRef]
115. Berx, N.; Decré, W.; De Schutter, J.; Pintelon, L. A harmonious synergy between robotic performance and well-being in
human-robot collaboration: A vision and key recommendations. Annu. Rev. Control 2025, 59, 100984. [CrossRef]
116. Bilal, H.; Obaidat, M.S.; Aslam, M.S.; Zhang, J.; Yin, B.; Mahmood, K. Online fault diagnosis of industrial robot using IoRT and
hybrid deep learning techniques: An experimental approach. IEEE Internet Things J. 2024, 11, 31422–31437. [CrossRef]
117. Li, S.; Xie, H.-L.; Zheng, P.; Wang, L. Industrial Metaverse: A proactive human-robot collaboration perspective. J. Manuf. Syst.
2024, 76, 314–319. [CrossRef]
118. Slavković, N.; Živanović, S.; Dimić, Z.; Kokotović, B. An advanced machining robot flexible programming methodology supported
by verification in a virtual environment. Int. J. Comput. Integr. Manuf. 2024. [CrossRef]
119. Villani, V.; Picone, M.; Mamei, M.; Sabattini, L. A digital twin driven human-centric ecosystem for Industry 5.0. IEEE Trans.
Autom. Sci. Eng. 2024. [CrossRef]
120. Bonci, A.; Gaudeni, F.; Giannini, M.C.; Longhi, S. Robot Operating System 2 (ROS2)-Based Frameworks for Increasing Robot
Autonomy: A Survey. Appl. Sci. 2023, 13, 12796. [CrossRef]
121. Mahdi, M.M.; Bajestani, M.S.; Noh, S.D.; Kim, D.B. Digital twin-based architecture for wire arc additive manufacturing using
OPC UA. Robot. Comput.-Integr. Manuf. 2025, 94, 102944. [CrossRef]
122. Dornelles, J.A.; Ayala, N.F.; Frank, A.G. Collaborative or substitutive robots? Effects on workers’ skills in manufacturing activities.
Int. J. Prod. Res. 2023, 61, 7922–7955. [CrossRef]
123. Li, L.; Li, J.; Liu, R.; Li, Z. Overview of blockchain-based terminal-edge-cloud collaborative computing paradigm. Comput. Electr.
Eng. 2024, 120, 109737. [CrossRef]
124. Xia, C.; Wang, R.; Jin, X.; Xu, C.; Li, D.; Zeng, P. Deterministic network–computation–manufacturing interaction mechanism for
AI-driven cyber–physical production systems. IEEE Internet Things J. 2024, 11, 18852–18868. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.