Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
125
Acumen: International Journal of Multidisciplinary
Research
Data Fusion Research for Collaborative Robots-Manipulators within
Industry 5.0
Vladyslav Yevsieiev 1, Svitlana Maksymova 1, Dmytro Gurin 1, Ahmad
Alkhalaileh 2
1Department of Computer-Integrated Technologies, Automation and Robotics,
Kharkiv National University of Radio Electronics, Ukraine
2Senior Developer Electronic Health Solution, Amman, Jordan
Abstract:
The article examines methods of data fusion (Data Fusion) for
collaborative manipulator robots in the context of Industry 5.0. Three approaches are
considered: Kalman filter, Bayesian estimation and Dempster-Shafer theory. The
Kalman filter has proven to be effective for linear systems, but requires modification
for nonlinear problems. Bayesian estimation provides accuracy for complex systems,
although it requires more resources. The Dempster-Shafer theory is effective under data
uncertainty, but has a high computational complexity. The conclusions indicate the
importance of choosing a data fusion method depending on the requirements for
accuracy and adaptability of robots in the production conditions of Industry 5.0.
Key words:
Industry 5.0, Collaborative Robot, Work Area, Computer Vision,
Sensor, Data, Data Fusion.
Introduction
In today's world, where production processes are becoming increasingly
automated, the concept of Industry 5.0 emphasizes human-robot collaboration to
achieve a high level of integration, personalization and flexibility [1]-[16].
Collaborative robot manipulators are central to this development, as they can
directly interact with humans in real time to perform complex tasks [17]-[19].
However, to ensure effective cooperation and reliable functioning of such robots,
accurate and prompt decision-making regarding their behavior in a dynamic
environment is necessary. In this context, Data Fusion becomes a key tool for
increasing the accuracy and reliability of managing collaborative manipulator robots.
Data Fusion allows you to combine information from different sources, such as
sensors, video cameras, lidar and other systems that provide information about the
external environment and internal states of the robot.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
126
Acumen: International Journal of Multidisciplinary
Research
This is critically important for decision-making, since no single sensor can
provide complete and reliable information about all aspects of the surrounding space
and task conditions. For example, optical sensors can provide highly accurate data
about the location of objects, but their effectiveness decreases in poor lighting or in the
case of partial obstacles.
On the other hand, inertial sensors can provide information about the robot's
movements even in difficult conditions, but on their own they are not accurate enough
to make decisions at the micro level. Data fusion allows you to combine these sources
to get a more accurate picture of the situation.
In the framework of Industry 5.0, this research is of particular importance due to
the need for adaptive and safe solutions in conditions where a robot works side by side
with a person [20]-[22]. Making decisions based on integrated data allows you to
significantly reduce the risks of errors in the operation of the manipulator, improve the
accuracy and stability of task performance, and also ensure a high level of safety for
the operator.
Various methods and approaches can be used here [23]-[40].
The importance of such research lies in the creation of new methods and
algorithms capable of efficiently processing large volumes of heterogeneous data in
real time, which will allow the robot to quickly respond to changes in the environment
and make the right decisions.
Related works
The use of data fusion is widely used to process data obtained from mobile
robot sensors. Naturally, many scientific works are devoted to this technology. Let us
look at some of these recent works.
Nascimento, H., & et al. in [41] consider the problem ensuring co-existence and
space sharing between human and robot. Here collision avoidance is one of the main
strategies for interaction between them without contact.
The authors in [42] analyze the detection process of intelligent detection robots
for massage chairs, theoretical research is carried out from two aspects of decision-
level fusion and data-level fusion.
The study [43] considers the problem hand gesture recognition. It is noted that
the accuracy and reliability of hand gesture recognition are the keys to gesture-based
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
127
Acumen: International Journal of Multidisciplinary
Research
human–robot interaction tasks. To solve this problem, a method based on multimodal
data fusion and multiscale parallel convolutional neural network is proposed in this
paper to improve the accuracy and reliability of hand gesture recognition.
Researchers in [44] presents a survey of simultaneous localization and mapping
and data fusion techniques for object detection and environmental scene perception in
unmanned aerial vehicles.
In [45] a comprehensive study on devices/sensors and prevalent sensor fusion
techniques developed for tackling issues like localization, estimation and navigation in
mobile robot are presented as well in which they are organized according to relevance,
strengths and weaknesses.
The paper [46] focuses on data fusion, which is fundamental to one of the most
important modules in any autonomous system: perception. There are presented various
types of sensors, their data, and the need for fusion of the data with each other to output
the best data for the task at hand, which in this case is autonomous navigation.
Qi, W., and co-authors in [47] designed a multi-sensor data fusion model for
performing interference in the presence of occlusions. A multilayer Recurrent Neural
Network consisting of a Long Short-Term Memory module and a dropout layer is
proposed for multiple hand gestures classification. Detected hand gestures are used to
perform a set of human-robot collaboration tasks on a surgical robot platform.
In the work [48] a complementary multi-modal sensor fusion approach is
presented that improves the reliability of the pose estimation process for aerial robots
by fusing visual-inertial and thermal-inertial odometry estimates with a LiDAR
odometry and mapping solution.
Thus, we see that fusion technology is widely used in modern science. Next, we
will consider our approach to using data fusion for a robot-manipulator.
Study of methods used for the data fusion process for collaborative robots.
Data Fusion for collaborative robots-manipulators within Industry 5.0 is the
process of integrating and harmonizing information from various sensors and sources
to obtain more accurate, complete and reliable information about the state of the
system, environment or objects. This allows robots to work more efficiently in complex
and dynamic environments.
For the mathematical representation of the data fusion process for collaborative
robots different methods are used:
- Kalman filter for linear systems;
- Extended Kalman Filter for nonlinear systems;
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
128
Acumen: International Journal of Multidisciplinary
Research
- Bayesian estimation for probabilistic representation of uncertainty;
- Dempster-Shafer Theory of trust for combining evidence from different
sources.
Within the framework of this study, we will indicate the following parameters:
x
t
- the state vector of the collaborative robot (positions of the manipulator joints,
speed);
u
t
- control signals (commands for drives or motors);
z
t
- data from sensors
(cameras, lidars, inertial sensors);
w
t
and
v
t
- process and measurement noise (sensor
errors);
P
t|t
- covariance matrix (determines uncertainty in the state);
K
t
- Kalman matrix
(balance between measurement and prediction).
Let the collaborative robot system be described by the following state and
observation equations:
- the state of the system can be described by the following model:
x
t
=f(x
t-1
,u
t
)+w
t
(1)
x
t
– system state vector in time
t
(e.g., positions, speeds, manipulator angles);
f(x
t-1
,u
t
)
- state transition function (describes system dynamics, robot control);
u
t
- vector of control actions (for example, signals to drives);
w
t
- process noise assumed to be normal with covariance
Q
.
- the observation model can be presented as follows:
Zt
=h(x
t
)+v
t
(2)
Zt
- vector of measurements from sensors (e.g., data from cameras, lidars,
accelerometers);
h(x
t
)
- an observation function that describes how the state of a system is
transformed into a measurement;
v
t
- measurement noise, which is also assumed to be normal with covariance
R
.
In the context of collaborative manipulator robots, the covariance (
Q,R
) allows
to evaluate the dependence between various sensors collecting data about the
environment and the state of the robot itself.
For example, if one sensor measures the tilt angle of a manipulator, and another
measures its position in space, the covariance of these two variables can help to
understand how related they are. If the covariance is high, it means that changes in one
parameter are accompanied by changes in another.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
129
Acumen: International Journal of Multidisciplinary
Research
If the covariance is low or negative, then these variables may be independent or
moving in opposite directions.
From a mathematical point of view, covariance is defined as the average product
of the deviations of two variables from their average values:
𝐶𝑜𝑣(𝑋, 𝑌) =
1
𝑛
∑(𝑋
𝑖
− 𝜇
𝑥
)(𝑌
𝑖
− 𝜇
𝑦
)
𝑛
𝑖=1
(3)
X
and
Y
- are the variables for which the covariance is calculated,
X
i
and
Y
i
are
individual observations of these variables,
µ
x
and
µ
y
are their mean values.
In Data Fusion research for robots, covariance helps improve decision-making
accuracy.
For example, when combining data from different sensors in a Kalman filter, a
covariance matrix is used to model how errors are propagated between measurements.
This allows the robot to adjust its actions based on the data fusion, reducing
inaccuracies in measurements and predictions.
For data fusion in the case of a linear system, the Kalman filter can be used. It is
a recursive algorithm that combines current measurements with state predictions.
It can be represented by the following expressions based on 1-2:
- updating the predicted state:
x
t|t-1
=f(x
t-1|t-1
,u
t
)
(4)
x
t|t-1
- predicted state for time
t
, based on the previous state
x
t-1|t-1
.
- updating the predicted covariance:
P
t|t-1
=F
t
P
t-1|t-1
F
t
T
+Q
t
(5)
F
t
- matrix of partial derivatives of the state transition function.
- status updates based on measurements:
K
t
=P
t|t-1
H
t
T
(H
t
P
t-1|t-1
H
t
T
+R)
-1
(6)
x
t|t
=x
t|t-1
+K
t
(z
t
-h(x
t-1|t-1)
)
(7)
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
130
Acumen: International Journal of Multidisciplinary
Research
K
t
- the Kalman matrix, which determines how much to trust measurements
versus predictions.
If the system is nonlinear, the extended Kalman filter (EKF) is used, which
linearizes the system using derivatives:
- linearization of the transition function:
𝑭
𝑡
=
𝜕𝑓(𝒙, 𝒖)
𝜕𝒙
|
𝒙
̂
𝑡−1|𝑡−1
,𝒖
𝑡
(8)
- linearization of the observation function:
𝑯
𝑡
=
𝜕ℎ(𝒙)
𝜕𝒙
|
𝒙
̂
𝑡|𝑡−1
(9)
A Bayesian approach to data fusion uses a probabilistic representation of
uncertainty. The state of the system is modeled as a probability distribution
p(x
t
|z
1:t
)
,
where
z
1:t
- all received measurements up to time
t
.
- estimation of a priori probability:
𝜌(𝒙
𝑡
|𝒛
1:𝑡−1
) = ∫ 𝜌 (𝒙
𝑡
|𝒙
𝑡−1
)𝜌(𝒙
𝑡−1
|𝒛
1:𝑡−1
)𝑑𝒙
𝑡−1
(10)
- update by measurements:
𝜌(𝒙
𝑡
|𝒛
1:𝑡
) ∝ 𝜌(𝒛
𝑡
|𝒙
𝑡
)𝜌(𝒙
𝑡
|𝒛
1:𝑡−1
)
(11)
Dempster-Shafer theory, this method of data fusion allows working with
uncertain and partially contradictory data. It generates confidence masses that represent
the degree of support for various hypotheses about the state of the system. It can be
represented as follows:
𝑚(𝐴) =
1
1 − 𝐾
∑ 𝑚
1
(𝐵)𝑚
2
(𝐶)
𝐵∩𝐶=𝐴
(12)
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
131
Acumen: International Journal of Multidisciplinary
Research
m(A)
- the confidence level for a hypothesis
A
represents the confidence that the
hypothesis is true;
K
- conflict ratio between different data sources.
Table 1 shows a comparison of the main advantages and disadvantages of three
methods of data fusion: the Kalman filter, Bayesian estimation and Dempster-Shafer
theory in the context of application for collaborative robots-manipulators within the
framework of Industry 5.0.
Table 1:
Comparison of advantages and disadvantages of using data fusion
methods: Kalman filter, Bayesian estimation and Dempster-Shafer theory in the
context of application for collaborative manipulator robots within Industry 5.0.
Method
Advantages
Disadvantages
Kalman filter
- High accuracy in real time,
especially in the presence of
small Gaussian noises
- Optimal for linear systems
- Ease of implementation
- Difficult to use for non-
linear systems without
adaptation (extended or
Unscented Kalman filter)
- Sensitivity to incorrect
initial conditions
Bayesian
estimation
- The possibility of using
complex a priori knowledge
- Well suited for non-linear
systems
- Flexible in cases where the
probabilities are not Gaussian
- High computational
complexity
- Requires accurate
determination of a priori
probabilities, which can be
difficult with limited
information
Dempster-Shafer
theory
- Can handle uncertainty and
conflicting data
- Does not require an exact
setting of a priori probabilities
- Handles incomplete data
well
- High computational cost for
large sets of hypotheses
- Difficulty in interpreting the
results in case of a high degree
of uncertainty or inconsistency
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
132
Acumen: International Journal of Multidisciplinary
Research
Analyzing Table 1, the following conclusions can be drawn:
- the Kalman filter is effective for real-time problems where the system has
Gaussian noise and linear models, which makes it particularly convenient for
controlling the position and movement of the manipulator. However, for non-linear
problems, it needs to be modified, which complicates the implementation;
- Bayesian estimation provides flexibility in considering complex probabilities
and non-linear models. This is important for complex Industry 5.0 work environments,
but this approach requires significant computing resources and accurate a priori data;
- the Dempster-Shafer theory is well suited for working with uncertain or
incomplete data, which can be useful for unstable sensors or in difficult production
conditions. However, the complexity of this method makes it difficult to apply it to
large data sets.
Conclusion
During the study Data Fusion for collaborative manipulator robots within
Industry 5.0, three main mathematical models were considered: the Kalman filter,
Bayesian estimation and the Dempster-Shafer theory. Each of these methods has its
strengths and limitations in solving the tasks of data integration from different sources
to improve the accuracy, reliability and adaptability of robots in the dynamic conditions
of modern production. The Kalman filter demonstrates efficiency in real-time problems
for linear systems with predictable noise, making it an optimal choice for systems
where fast decision-making based on sensory information is required. However, for
nonlinear environments, this approach needs to be extended through the use of
nonlinear modifications. Bayesian estimation provides flexibility and accuracy in
complex and nonlinear environments, allowing efficient use of a priori information,
but requires significant computational resources and accurate a priori data. The
Dempster-Shafer theory, in turn, is useful in conditions of high uncertainty and when
working with incomplete or contradictory data, which allows to expand the possibilities
of managing collaborative works, but this method is characterized by complexity and
high computational cost when processing large arrays of information. In conclusion,
each of the considered methods has the potential to be used in Industry 5.0 depending
on the requirements for the data fusion system, but their effectiveness depends on the
specifics of the environment, the nature of the data, and the complexity of the tasks
faced by manipulator robots.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
133
Acumen: International Journal of Multidisciplinary
Research
References:
1.
Yevsieiev, V., & et al. (2024). Human Operator Identification in a
Collaborative Robot Workspace within the Industry 5.0 Concept. Multidisciplinary
Journal of Science and Technology, 4(9), 95-105.
2.
Abu-Jassar, A., & et al. (2023). Obstacle Avoidance Sensors: A Brief
Overview. Multidisciplinary Journal of Science and Technology, 3(5), 4-10.
3.
Gurin, D., & et al. (2024). Using the Kalman Filter to Represent
Probabilistic Models for Determining the Location of a Person in Collaborative Robot
Working Area. Multidisciplinary Journal of Science and Technology, 4(8), 66-75.
4.
Basiuk, V., & et al. (2024). Command recognition system research.
Technical Science Research in Uzbekistan, 2(5), 50-61.
5.
Baker, J. H., Laariedh, F., Ahmad, M. A., Lyashenko, V., Sotnik, S., &
Mustafa, S. K. (2021). Some interesting features of semantic model in Robotic Science.
SSRG International Journal of Engineering Trends and Technology, 69(7), 38-44.
6.
Abu-Jassar, A. T., Al-Sharo, Y. M., Lyashenko, V., & Sotnik, S. (2021).
Some Features of Classifiers Implementation for Object Recognition in Specialized
Computer systems. TEM Journal: Technology, Education, Management, Informatics,
10(4), 1645-1654.
7.
Sotnik, S., Mustafa, S. K., Ahmad, M. A., Lyashenko, V., & Zeleniy, O.
(2020). Some features of route planning as the basis in a mobile robot. International
Journal of Emerging Trends in Engineering Research, 8(5), 2074-2079.
8.
Nevliudov, I., & et al.. (2020). Method of Algorithms for CyberPhysical
Production Systems Functioning Synthesis. International Journal of Emerging Trends
in Engineering Research, 8(10), 7465-7473.
9.
Mustafa, S. K., Yevsieiev, V., Nevliudov, I., & Lyashenko, V. (2022). HMI
Development Automation with GUI Elements for Object-Oriented Programming
Languages Implementation. SSRG International Journal of Engineering Trends and
Technology, 70(1), 139-145.
10.
Nevliudov, I., Yevsieiev, V., Lyashenko, V., & Ahmad, M. A. (2021). GUI
Elements and Windows Form Formalization Parameters and Events Method to
Automate the Process of Additive Cyber-Design CPPS Development. Advances in
Dynamical Systems and Applications, 16(2), 441-455.
11.
Maksymova, S., Matarneh, R., Lyashenko, V. V., & Belova, N. V. (2017).
Voice Control for an Industrial Robot as a Combination of Various Robotic Assembly
Process Models. Journal of Computer and Communications, 5, 1-15.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
134
Acumen: International Journal of Multidisciplinary
Research
12.
Ahmad, M. A., Baker, J. H., Tvoroshenko, I., & Lyashenko, V. (2019).
Modeling the structure of intellectual means of decision-making using a system-
oriented NFO approach. International Journal of Emerging Trends in Engineering
Research, 7(11), 460-465.
13.
Lyashenko, V., Abu-Jassar, A. T., Yevsieiev, V., & Maksymova, S. (2023).
Automated Monitoring and Visualization System in Production. International Research
Journal of Multidisciplinary Technovation, 5(6), 9-18.
14.
Abu-Jassar, A. T., Attar, H., Lyashenko, V., Amer, A., Sotnik, S., &
Solyman, A. (2023). Access control to robotic systems based on biometric: the
generalized model and its practical implementation. International Journal of Intelligent
Engineering and Systems, 16(5), 313-328.
15.
Al-Sharo, Y. M., Abu-Jassar, A. T., Sotnik, S., & Lyashenko, V. (2023).
Generalized Procedure for Determining the Collision-Free Trajectory for a Robotic
Arm. Tikrit Journal of Engineering Sciences, 30(2), 142-151.
16.
Ahmad, M. A., Sinelnikova, T., Lyashenko, V., & Mustafa, S. K. (2020).
Features of the construction and control of the navigation system of a mobile robot.
International Journal of Emerging Trends in Engineering Research, 8(4), 1445-1449.
17.
Yevsieiev, V., & et al. (2024). Research of Existing Methods of
Representing a Collaborative Robot-Manipulator Environment within the Framework
of Cyber-Physical Production Systems. Multidisciplinary Journal of Science and
Technology, 4(9), 112-120.
18.
Vizir, Y., & et al. (2024). Lighting Control Module Software
Development. ournal of Universal Science Research, 2(2), 29–42.
19.
Gurin, D., & et al. (2024). MobileNetv2 Neural Network Model for
Human Recognition and Identification in the Working Area of a Collaborative Robot.
Multidisciplinary Journal of Science and Technology, 4(8), 5-12.
20.
Samoilenko, H., & et al. (2024). Review for Collective Problem-Solving
by a Group of Robots. Journal of Universal Science Research, 2(6), 7-16.
21.
Gurin, D., & et al. (2024). CAMShift Algorithm for Human Tracking in
the Collaborative Robot Working Area. Journal of Universal Science Research, 2(8),
87–101.
22.
Basiuk, V., & et al. (2023). Mobile Robot Position Determining Using
Odometry Method. Multidisciplinary Journal of Science and Technology, 3(3), 227-
234.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
135
Acumen: International Journal of Multidisciplinary
Research
23.
Vasiurenko, O., Lyashenko, V., Baranova, V., & Deineko, Z. (2020).
Spatial-Temporal Analysis the Dynamics of Changes on the Foreign Exchange Market:
an Empirical Estimates from Ukraine. Journal of Asian Multicultural Research for
Economy and Management Study, 1(2), 1-6.
24.
Mustafa, S. K., Ayaz, A. M., Baranova, V., Deineko, Z., Lyashenko, V., &
Oyouni, A. A. A. (2020). Using wavelet analysis to assess the impact of COVID-19 on
changes in the price of basic energy resources. International Journal of Emerging
Trends in Engineering Research, 8(7), 2907-2912.
25.
Lyashenko, V. V., Lyubchenko, V. A., Ahmad, M. A., Khan, A., & Kobylin,
O. A. (2016). The Methodology of Image Processing in the Study of the Properties of
Fiber as a Reinforcing Agent in Polymer Compositions. International Journal of
Advanced Research in Computer Science, 7(1), 15-18.
26.
Lyubchenko, V., & et al.. (2016). Digital image processing techniques for
detection and diagnosis of fish diseases. International Journal of Advanced Research
in Computer Science and Software Engineering, 6(7), 79-83.
27.
Lyashenko, V. V., Matarneh, R., Kobylin, O., & Putyatin, Y. P. (2016).
Contour Detection and Allocation for Cytological Images Using Wavelet Analysis
Methodology. International Journal, 4(1), 85-94.
28.
Kuzemin, O., & Lyashenko, V. Microsituation Concept in GMES Decision
Support Systems/A. Kuzemin, V. Lуashenko. Intelligent Data Processing in Global
Monitoring for Environment and Security (pр. 217–238).–2011.–Р, 217-238.
29.
Lyashenko, V., Laariedh, F., Ayaz, A. M., & Sotnik, S. (2021). Recognition
of Voice Commands Based on Neural Network. TEM Journal: Technology, Education,
Management, Informatics, 10(2), 583-591.
30.
Orobinskyi, P., Deineko, Z., & Lyashenko, V. (2020). Comparative
Characteristics of Filtration Methods in the Processing of Medical Images. American
Journal of Engineering Research, 9(4), 20-25.
31.
Sotnik S., & et al.. (2022). Key Directions for Development of Modern
Expert Systems. International Journal of Engineering and Information Systems
(IJEAIS), 6(5), 4-10.
32.
Sotnik S., & Lyashenko V. (2022). Prospects for Introduction of Robotics
in Service. International Journal of Academic Engineering Research (IJAER), 6(5), 4-
9.
33.
Lyashenko, V., & Sotnik, S. (2022). Overview of Innovative Walking
Robots. International Journal of Academic Engineering Research (IJAER), 6(4), 3-7.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
136
Acumen: International Journal of Multidisciplinary
Research
34.
Baranova, V., Orlenko, O., Vitiuk, A., Yakimenko-Tereschenko, N., &
Lyashenko, V. (2020). Information system for decision support in the field of tourism
based on the use of spatio-temporal data analysis. International Journal of Advanced
Trends in Computer Science and Engineering, 9(4), 6356-6361.
35.
Sotnik, S., & et al.. (2022). Modern Industrial Robotics Industry.
International Journal of Academic Engineering Research, 6(1),. 37-46.
36.
Lyashenko, V., Kobylin, O., & Baranchykov, Y. (2018, October). Ideology
of Image Processing in Infocommunication Systems. In 2018 International Scientific-
Practical Conference Problems of Infocommunications. Science and Technology (PIC
S&T) (pp. 47-50). IEEE.
37.
Lyashenko, V., & Sotnik, S. (2020). Analysis of Basic Principles for
Sensor System Design Process Mobile Robots. Journal La Multiapp, 1(4), 1-6.
38.
Lyashenko V, Matarneh R, Sotnik S. Modeling of Machine Design with
Numerical Control in UG NX 7.5 System. The International Journal of Engineering
and Science (IJES), 2018, 7(7), pp. 28-37.
39.
Matarneh, R., Sotnik, S., & Lyashenko, V. (2018). Search of the molding
form connector plane on the approximation basis by the many-sided surface with use
of the convex sets theory. International Journal of Mechanical and Production
Engineering Research and Development, 8(1), 977-988.
40.
Babker, A. M., Suliman, R. S., Elshaikh, R. H., Boboyorov, S., &
Lyashenko, V. (2024). Sequence of Simple Digital Technologies for Detection of
Platelets in Medical Images. Biomedical and Pharmacology Journal, 17(1), 141-152.
41.
Nascimento, H., & et al. (2020). Collision avoidance interaction between
human and a hidden robot based on kinect and robot data fusion. IEEE Robotics and
Automation Letters, 6(1), 88-94.
42.
He, B., & et al. (2021). Data fusion-based sustainable digital twin system
of intelligent detection robotics. Journal of Cleaner Production, 280, 124181.
43.
Gao, Q., & et al. (2021). Hand gesture recognition using multimodal data
fusion and multiscale parallel convolutional neural network for human–robot
interaction. Expert Systems, 38(5), e12490.
44.
Gupta, A., & et al. (2022). Simultaneous localization and mapping (slam)
and data fusion in unmanned aerial vehicles: Recent advances and challenges. Drones,
6(4), 85.
45.
Alatise, M. B., & et al. (2020). A review on challenges of autonomous
mobile robot and sensor fusion methods. IEEE Access, 8, 39830-39846.
Acumen:
International Journal of
Multidisciplinary Research
Volume 1, Issue 4
137
Acumen: International Journal of Multidisciplinary
Research
46.
Kolar, P., & et al. (2020). Survey of datafusion techniques for laser and
vision based sensor integration for autonomous navigation. Sensors, 20(8), 2180.
47.
Qi, W., & et al. (2021). Multi-sensor guided hand gesture recognition for
a teleoperated robot using a recurrent neural network. IEEE Robotics and Automation
Letters, 6(3), 6039-6045.
48.
Khattak, S., & et al. (2020). Complementary multi–modal sensor fusion
for resilient robot pose estimation in subterranean environments. In 2020 International
Conference on Unmanned Aircraft Systems (ICUAS), IEEE, 1024-1029.
