A Review on Deformable Voronoi Diagrams for

Robot Path Planning in Dynamic Environments

Moveh Samuel Mahmoud Aldababsa
Robotic Department Khalid Yahya Department of Electrical and
Engineering Faculty Transport and Department of Electrical and Electronics Engineering
Telecommunication Institute, Riga, Electronics Engineering Nisantasi University
1019, Latvia Istanbul Gelisim University Istanbul, Turkey
[email protected] Istanbul, Turkey [email protected]
[email protected]

Ayman Amer Emmanuel Alejandro Merchán-Cruz

Faculty of Engineering Jamal Ali Ramada Dofan
Robotics Department
Zarqa Universsity, Zarqa, Jordan Department of Electrical
Engineering Faculty Transport and
College of Engineering, University of Gharian University
Telecommunication Institute, Riga,
Business and Technology, Jeddah, Gharian, Libya
1019, Latvia
21448, Saudi Arabia [email protected] [email protected]
[email protected]

Mohamed Hafez
Faculty of Engineering FEQS
INTI-IU-University
Nilai, Malaysia
[email protected]

Abstract— Route planning for mobile robots presents a on robot navigation in both static and dynamic situations.
complex challenge, mainly when designing pathways in dynamic Some of these works include [1], which illustrated the design
environments. This complexity arises from the robot's need to of a method for planning paths for mobile robots in a dynamic
balance the demand for efficient and optimal routes while also environment and specifically emphasized the use of the online
handling unexpected obstacles. This paper introduces an
process for dynamic environments by developing an optimal
algorithm that combines two key concepts: the Voronoi
Diagram, utilized for environment representation, and time path planner, and [2], [3]which focused on how robots
Deformation Retracts, integrated into the system to enable the could socially interact with humans in the same environment
path planner to adapt to moving obstacles by deforming the without conflict. On the other hand, path planning for robots
Voronoi Diagram. The combination of the previously described in changing surroundings has lately been a focus for many
notions, Voronoi Diagrams, and Deformation Retracts from academics.
related areas (Computational geometry and Algebraic topology)
has not yet been studied in robotics applications. The idea is According to research from [4], there are two types of
supposed first to compute a Generalised Voronoi Diagram route planning systems: online planning systems and offline
(GVD) and construct a pre-planned robot route, after which the planning systems. The whole knowledge about the
Deformation retract might be applied to the open space of the surroundings is known in online route planning. The Voronoi
Voronoi Diagram formed after an interference due to a moving Diagram and the Visibility graph are also utilized for online
object. The map will be distorted, and the starting route will be route planning. [5]Local route planning methods, when
modified to a different path if one exists. This approach has a obstacle movements cannot be predicted in advance, have
promising future since the dimension of the map has been
reduced to one that depicts the retracting free space in the
been the most popular in recent years. The robots in local route
surroundings. As a result, the new method is relevant to robot planning get input from sensors; an appropriate technique
navigation in complicated settings, as well as other disciplines utilized in local path planning is the Artificial potential field
such as game theory, virtual reality, and computational [6]. This study helps robot route planning and obstacle
geometry, to name a few. avoidance solutions in a dynamic environment.

Keywords—Deformable, Path, Robot, Voronoi According to the study, the first approaches for route
Diagrams, Dynamic, Environment planning issues were the visibility graph, Voronoi diagram,
cell decomposition, and artificial potential field. [7]
I.INTRODUCTION Nevertheless, these systems have several limitations, such as
Numerous academics have been working persistently to enormous processing costs and long execution times of
discover practical solutions to route planning difficulties since algorithms even when just a small number of robots are
mobility is one of the critical responsibilities of a mobile robot employed and locked in local minima [8] that worsen as the
while achieving its objective. There have been several studies environment changes. Fuzzy logic [9], Ant Colony
optimization [10], [11]Genetics algorithms [12], and Neural

XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE

networks [13] were among the other heuristic or soft
computing approaches employed for robot route planning
applications.
II. PATH PLANNING TECHNIQUES
Path planning approaches have been studied since the
1960s, but this field did not get much attention until [14]
revealed his work on spatial planning; he offered a
configuration strategy, which was used to determine how to
move an item without colliding. Yet, mobile robots are used
in many fields, including health care, manufacturing, undersea
operations, space exploration, and nuclear power plants[15],
so they are regarded as smart operating instruments . A good Bug1 Bug2
path-planning system must minimize the danger to the robot,
take care of uncertainties, find an optimal path quickly[16], Figure 1: Mobile robot's path [28] (Nguyen & Le, 2016)
[17], [18], and report to the user if there is none [7]. A good
path-planning system must minimize the danger to the robot, III. SAMPLING-BASED APPROACH, ARTIFICIAL POTENTIAL
take care of uncertainties, find an optimal path quickly, and FIELD APPROACH AND THE GRAPH-THEORETIC APPROACHES
report to the user if there is none. In the 1990s, a sampling-based strategy was proposed to
overcome the challenge of deterministic route planning
Currently, two types of route planning techniques are
strategies for robots with six degrees of freedom under various
traditional and biologically inspired [19]. Which are
restrictions [29]. The primary idea is to limit the search to the
traditional and which are biologically motivated, I would randomly examined configuration space rather than the whole
emphasize. Bug Algorithms, Roadmap Approach, Cell space, including obstacle spaces. As a result, the route
Decomposition, Potential field methods, Sampling-based planning algorithm's design is less reliant on the geometric
Approach, Kalman Filtering, Heuristic Approaches such as model. The sole source of information in the sampling-based
Artificial Neural Networks, Ant colony optimization, and strategy is a collision detector. Numerous samples in the open
Genetics Algorithms are a few examples. Each strategy is space are linked with free pathways to solve the path-planning
helpful for distinct types of route planning challenges[20]. issue [30]. Although a sample-based technique is basic, it
works despite several obstacles or limits. Some of the studies
Further information on the approaches mentioned above is
on these constraints include:
given in the following sections.
1. Kinematic and/or dynamic motion constraints [29].
1. Bug Algorithm
2. Closure constraints [31].
The most often used Bug Algorithms in route planning
issues are Bug1, Bug2, Vis Bug, DistBug, and Tangent Bug 3. Kinematic and/or dynamic motion constraints [32].
[21], [22]. The Bug's algorithms are simple path planning
4. Re-configurable robots [33].
techniques with high assurance [21], [23]and the basic
concept of Bug1 is that the robot continues to navigate 5. Manipulation constraints [34].
towards the goal along the path from the goal until an obstacle
6. Contact state constraints [35].
is encountered, at which point the robot explores alternative
paths around the obstacle until the motion to the goal is 7. Brief inspection constraints [36].
available again (or concludes that there is no path) [24].
Meanwhile, in Bug 2, the robot continually follows the While it may be straightforward in a cluster setting with a
straight line to the objective, and if an obstacle is encountered, sampling strategy, the planning time is longer, making it
it follows the edges of the obstacles until the line to the goal is inefficient.
found [25]. Bug algorithms are helpful for online route In recent years, the artificial potential field approach has
planners with few sensors [26], [27]. Despite these strategies received much attention for obstacle avoidance difficulties in
having shown that they offer a comprehensive solution, the robotics research. This method's core concept is that artificial
key limitation is the length of the pathways and time. forces operate on robots [6]. The attractive force that draws
the robot to the objective and the repulsive force that repels
H1 and H2 are hit sites for the Bug1 algorithm. Bug2 the robot from obstacles are both artificial forces. This method
algorithm using H11, H1, and H2 as hit points and L1 and L2 is helpful for global route planning with convex barriers [37].
as leave points. L11, L12, and L2 are leaving points. Fig.1 But it is its simplicity that distinguishes it from other
shows an example. techniques. [38] employed an artificial potential field
technique with sensor data for a mobile robot, while [39] used
a potential field method for offline and online route planning.
The APF approach suffers from the issue of local minima, in
which a robot becomes stranded and the objective is not
reached [40].[41]
 This method produces the shortest route; however, the
pathways may be unsafe since the robot collides with objects
while travelling toward the target. There are also various
intricate pathways to be looked for, which affects the method's
search efficiency[46].

Figure 1: Artificial Potential Field Approach

The graph-based technique is one of the oldest methods

of creating open space for the robot. Edges link together
these open areas to form free routes. The vertices may be
considered free spaces, and the graph-based technique uses
the network between the free spaces (vertices) and the lines
(edges) to construct a collision-free route for the robot. This Figure 2: Visibility graph
method works in both static and dynamic contexts. The
Visible graph and Voronoi diagram are two graph-based
route planning tools.
For over four decades, the Voronoi notion was used.
IV.A ROAD MAP
Structures resembling the Voronoi diagram can be traced back
A piece of paper was used to accomplish the to the work of Rene Descartes (a creative mathematician of
connectedness of the graph in free space, and the roadmap the first order) in 1644 when he used a Voronoi-like diagram
technique was utilized. [42] outlined three phases to to cite the location of matter within the solar system. Since
consider while applying the roadmap approach: then, researchers have developed numerous algorithms for
1. Robot navigation from source to target on the computing the Voronoi diagram. A summary of some of these
roadmap. works may be found in [47], [48], and [49], which describe
2. Then, go from the objective to another place on several algorithms and their applications to Voronoi diagrams.
the roadmap. [50] presented work on a Voronoi diagram as an aid in robot
3. Connect the two spots using lines. route planning, demonstrating how a search for a path in a
specific place may be simplified to a search in one-
The roadmap-based method may also address dimensional space. For a long time, numerous scholars have
computational problems in a complicated setting. It may also employed the GVD as a foundation for route design, as seen
use an undirected graph structure to reduce free space [43]. by the works of [47]-[50]
Visibility graphs and Voronoi diagrams are further roadmap-
based approaches with computational geometry components.
Visibility graphs are used to identify the shortest route, while
Voronoi diagrams are used to determine the greatest clearance
pathways. Despite the Visible graph providing the shortest
pathways, the robots may come into contact with obstructions
while navigating, which may be hazardous to the robots. By
establishing maximum clearance, Voronoi diagrams address
the issue of visibility diagrams. [44] pointed out that each zone
in a Voronoi diagram corresponds to a site, implying that all
points in that region are closer to the site in that region than
any other site in that region. Retraction occurs when the
roadmap technique reduces the route planning issue to a one-
dimensional problem.
V.A VISIBILITY GRAPH, VORONOI DIAGRAMS AND
GENERALISED VORONOI DIAGRAMS
Figure 3: Voronoi Diagram
The aim behind the Visibility graph is to create a network (http:/en.wikipedia.org/wiki/Voronoi_diagram)
or graph of polygon vertices (obstacles). [45] said that two
vertices must be visible to be linked, while Dijkstra's method
is used to find the shortest route. [7] their study shows that a According to [21], the generalized Voronoi diagram is a
visibility graph is a collection of lines in free space that link
collection of equidistant points in the workspace from distinct
the features of one barrier to another, where these qualities are
areas. Meanwhile,[55], [56] proposed a strategy for creating a
the visibility graph's nodes of polygonal shapes with edges.
generalized local Voronoi diagram and a Voronoi diagram in II. Time- the execution duration should be as
a dynamic context. Though constructing an efficient short as feasible.
generalized Voronoi diagram has always been a challenge in III. Robustness- the algorithm's ability to tolerate
path planning, researchers such as [51], [52] have presented faults should be good.
solutions where an algorithm solution, called the hierarchical IV. Simplicity- the algorithm's implementation
generalized Voronoi graph, was designed for a robot to should be as fundamental as feasible.
navigate a changing environment, and (Steven et al., 1999)
show how the points on the diagram can be searched without V1I RELATED WORKS ON PATH PLANNING USING
constructing the entire map[57]. COMBINED METHODS
The references [67], [73] demonstrated how to
combine multiple route planning strategies to solve path
planning challenges. A handful of these works are
discussed here.
1. Voronoi Diagrams and Fast Marching

[74] devised a method for mobile robot path planning

based on a Voronoi diagram and fast marching [75], in
which the Voronoi diagram was used to reduce the
configuration space into a unidimensional space, and fast
marching was used to obtain the path from the collision-
free areas of the Voronoi diagrams. This approach works
well in a static setting because the trajectories it
generates are smooth and safe. In terms of execution
time, it is also averagely effective in route planning
issues.
2. Tube Skeleton structure and Fast Marching
Figure 4: Generalized Voronoi Diagram (https://th.bing.com/th/id/)
A similar study was described in reference [76], but
VI.DEFORMATION RETRACTS, HEURISTIC APPROACHES
instead of utilizing a Voronoi diagram to extract safe
AND PATH PLANNING ALGORITHMS regions, a tube skeleton was used to represent the safest
The primary idea of deformation retraction is to areas in a tube form, and rapid marching was utilized to
seamlessly alter a route or map without losing part of its generate the collision-free route from the tube skeleton.
original qualities. [58] presented a motion planning This approach is sensor-based and works well in static
algorithm for autonomous robots in a dynamic situations. It is effective; it creates smooth trajectories
environment that used deformable links and dynamically and is distinguished by non-holonomic constraints.
retracted to capture the connectivity of free space, and
[59] presented a method for reactive obstacle avoidance 3. Voronoi Diagrams and Genetic Algorithms
for non-holonomic systems that was based on
Deformation of an initial motion generated by a path We created a technique for route planning in a static
planner. environment utilizing Voronoi diagrams, where
While conventional route planning methods have generating points represent barriers and the evolutionary
issues such as long algorithm execution times and the algorithm is utilized to find the way. They employed the
occurrence of local minima that limit the effectiveness fitness function to determine the optimality route. This
of their implementation, heuristic approaches offer some approach is suitable for static contexts; it is efficient and
algorithmic solutions to solve some of these issues. As a has a short execution time [77].
result, several papers on heuristic techniques have been 4. Ant Colony Optimization and Dynamic
published, including Neural Networks[60] [61], Genetic Voronoi Diagrams
Algorithms [62][63], Simulated Annealing [64], Ant
Colony Optimization [65], PSO [66] [45], Tabu Search
[67], and Fuzzy Logic[68], [69], [70], [71] [72]. Most Reference [77] devised a technique for modeling the
conventional and heuristic strategies are used to create dynamic environment using a dynamic Voronoi
an efficient route planner. diagram, and Ant Colony Optimization is used to
generate a route from the Voronoi diagram model of the
The primary feature of a route planning algorithm is environment. This is suitable for dynamic surroundings,
convergence. This implies that the algorithm must be encourages flexibility, and has a high efficiency in route
capable of finding a path if one exists, alerting the user planning.
if such a path does not exist, and then terminating the
search process.Convergent Algorithms have the 5. Voronoi diagram using Parameter Clearance-
following characteristics: based Shortest Path
I. Length- the distance between the source and Reference [78] provided a study in which the
the target should be as small as possible. optimum route was determined from the Voronoi
diagram utilizing a clearing condition or constraint that
 the user first specified. This ensures that the route is MRI and CT for Atherosclerosis in Carotid Artery,”
optimum. This is employed in a dynamic setting and is Multimed Tools Appl, pp. 1–22, 2023.
more effective in speed and quality. [4] M. Dirik and F. KOCAMAZ, “Rrt-dijkstra: An
6. Voronoi Diagram and Probability Roadmap improved path planning algorithm for mobile
robots,” Journal of Soft Computing and Artificial
Reference [79] developed a strategy based on Intelligence, vol. 1, no. 2, pp. 69–77, 2020.
sample-based methodologies that allowed the issue to be [5] A. A. Alomoush, A. R. A. Alsewari, K. Z. Zamli, A.
placed in an artificial context. This is suitable for a Alrosan, W. Alomoush, and K. Alissa, “Enhancing
dynamic environment; it is distinguished by the period three variants of harmony search algorithm for
between re-planning and Deformation. This is also continuous optimization problems,” Int. J. Electr.
efficient[80]. Comput. Eng.(IJECE), vol. 11, pp. 2343–2349, 2021.
[6] P. Bautista-Camino, A. I. Barranco-Gutiérrez, I.
7. Obstacle Avoidance Cervantes, M. Rodríguez-Licea, J. Prado-Olivarez,
and F. J. Pérez-Pinal, “Local path planning for
Obstacle avoidance is critical in robot route planning
autonomous vehicles based on the natural behavior of
since a robot must reach its goal without colliding with
the biological action-perception motion,” Energies
obstacles. A route, on the other hand, is considered to be
free if impediments are avoided during robot navigation. (Basel), vol. 15, no. 5, p. 1769, 2022.
[6] designed a unique real-time collision avoidance [7] B. K. Patle, A. Pandey, D. R. K. Parhi, and A.
method for mobile robots and manipulators using Jagadeesh, “A review: On path planning strategies
artificial potential fields to enable robots in a real-time for navigation of mobile robot,” Defence Technology,
dynamic environment, [27] designed a framework for vol. 15, no. 4, pp. 582–606, 2019.
underwater vehicle path planning and obstacle [8] T. Weerakoon, “Artificial potential field and feature
avoidance for sonar purposes, and [20] used an online extraction method for mobile robot path planning in
technique to develop an algorithm for obstacle structured environments,” Kyushu Institute of
avoidance or reactive control during robot motion. [33] Technology, 2016.
also provided a route deformation method for obstacle [9] A. Saffiotti, “The uses of fuzzy logic in autonomous
avoidance. robot navigation,” Soft comput, vol. 1, pp. 180–197,
1997.
VIIICONCLUSIONS [10] Z. Bi, Y. Yimin, and X. Yisan, “Mobile robot
Many representation techniques have been navigation in unknown dynamic environment based
examined, and it has been established that no approach on ant colony algorithm,” in 2009 WRI Global
is ideal. All of the approaches examined had limitations. Congress on Intelligent Systems, IEEE, 2009, pp. 98–
Nevertheless, several strategies were integrated to 102.
overcome some of these restrictions, and the suggested [11] M. Alweshah et al., “Vehicle routing problems based
method in this study is an example. The review research on Harris Hawks optimization,” J Big Data, vol. 9,
suggests combining the Voronoi diagram with the no. 1, pp. 1–18, 2022.
Deformation retract technique for the planner. This
[12] S. H. A. Rahmati, V. Hajipour, and S. T. A. Niaki,
technique is built on a roadmap and employs a
“A soft-computing Pareto-based meta-heuristic
computational geometry data structure. The reasons for
choosing this technique are as follows: to produce a algorithm for a multi-objective multi-server facility
maximum clearance route, the Voronoi diagram is location problem,” Appl Soft Comput, vol. 13, no. 4,
created in time, and finally, querying for a path in this pp. 1728–1740, 2013.
way is quicker than in other methods. Since the quality [13] I. Engedy and G. Horváth, “Artificial neural network
of pathways created by the Voronoi diagram is far from based mobile robot navigation,” in 2009 IEEE
optimum, it was suggested that another approach, International Symposium on Intelligent Signal
Deformation retracts, be used to update and distort the Processing, IEEE, 2009, pp. 241–246.
map while responding to environmental changes caused [14] C. Zhou, B. Huang, and P. Fränti, “A review of
by moving objects. motion planning algorithms for intelligent robots,” J
Intell Manuf, vol. 33, no. 2, pp. 387–424, 2022.
REFERENCES [15] F. R. Ahmed, S. A. Alsenany, S. M. F. Abdelaliem,
and M. A. Deif, “Development of a hybrid LSTM
[1] Y. Ming, Y. Li, Z. Zhang, and W. Yan, “A survey of
with chimp optimization algorithm for the pressure
path planning algorithms for autonomous vehicles,”
ventilator prediction,” Sci Rep, vol. 13, no. 1, p.
SAE Int J Commer Veh, vol. 14, no. 02-14-01–0007,
20927, 2023.
pp. 97–109, 2021.
[16] Sánchez-Ibáñez, José Ricardo, Carlos J. Pérez-del-
[2] Á. G. O. M. P. S. L. J. A. I. M. A. L. E. Raquel
Pulgar, and Alfonso García-Cerezo. "Path planning
Fuentetaja Pizán, Advances in Physical Agents, 1st
for autonomous mobile robots: A review." Sensors
ed., vol. 855. Madrid: Springer Cham, 2019.
21, no. 23 (2021): 7898.
Accessed: Jan. 25, 2024. [Online]. Available:
[17] Zafar, Mohd Nayab, and J. C. Mohanta.
https://link.springer.com/book/10.1007/978-3-319-
"Methodology for path planning and optimization of
99885-5
mobile robots: A review." Procedia computer science
[3] H. Attar et al., “Modeling and computational fluid
133 (2018): 141-152.
dynamics simulation of blood flow behavior based on
[18] Y. Ming, Y. Li, Z. Zhang, and W. Yan, “A survey of Proceedings 2001 ICRA. IEEE International
path planning algorithms for autonomous vehicles,” Conference on Robotics and Automation (Cat. No.
SAE Int J Commer Veh, vol. 14, no. 02-14-01–0007, 01CH37164), IEEE, 2001, pp. 692–698.
pp. 97–109, 2021. [32] R. Fitch, Z. Butler, and D. Rus, “Reconfiguration
[19] W. Alomoush, A. Alrosan, Y. M. Alomari, A. A. planning for heterogeneous self-reconfiguring
Alomoush, A. Almomani, and H. S. Alamri, “Fully robots,” in Proceedings 2003 IEEE/RSJ
automatic grayscale image segmentation based fuzzy International Conference on Intelligent Robots and
C-means with firefly mate algorithm,” J Ambient Systems (IROS 2003)(Cat. No. 03CH37453), IEEE,
Intell Humaniz Comput, vol. 13, no. 9, pp. 4519– 2003, pp. 2460–2467.
4541, 2022. [33] F. Lamiraux and L. E. Kavraki, “Planning paths for
[20] K. N. McGuire, G. C. H. E. de Croon, and K. Tuyls, elastic objects under manipulation constraints,” Int J
“A comparative study of bug algorithms for robot Rob Res, vol. 20, no. 3, pp. 188–208, 2001.
navigation,” Rob Auton Syst, vol. 121, p. 103261, [34] X. Ji and J. Xiao, “Planning motions compliant to
2019. complex contact states,” Int J Rob Res, vol. 20, no. 6,
[21] S. K. Palvadi, P. Dixit, and V. Dutt, “Introduction to pp. 446–465, 2001.
Robotics,” AI and IoT‐Based Intelligent Automation [35] T. Danner and L. E. Kavraki, “Randomized planning
in Robotics, pp. 1–14, 2021. for short inspection paths,” in Proceedings 2000
[22] W. Alomoush et al., “Digital image watermarking ICRA. Millennium Conference. IEEE International
using discrete cosine transformation based linear Conference on Robotics and Automation. Symposia
modulation,” Journal of Cloud Computing, vol. 12, Proceedings (Cat. No. 00CH37065), IEEE, 2000, pp.
no. 1, pp. 1–17, 2023. 971–976.
[23] F. Paquin, J. Rivnay, A. Salleo, N. Stingelin, and C. [36] A. Ataka, H.-K. Lam, and K. Althoefer, “Magnetic-
Silva, “Multi-phase semicrystalline microstructures field-inspired navigation for robots in complex and
drive exciton dissociation in neat plastic unknown environments,” Front Robot AI, vol. 9, p.
semiconductors,” arXiv preprint arXiv:1310.8002, 29, 2022.
2013. [37] F. You, R. Zhang, G. Lie, H. Wang, H. Wen, and J.
[24] E. Magid and E. Rivlin, “CAUTIOUSBUG: A Xu, “Trajectory planning and tracking control for
competitive algorithm for sensory-based robot autonomous lane change maneuver based on the
navigation,” in 2004 IEEE/RSJ International cooperative vehicle infrastructure system,” Expert
Conference on Intelligent Robots and Systems Syst Appl, vol. 42, no. 14, pp. 5932–5946, 2015.
(IROS)(IEEE Cat. No. 04CH37566), IEEE, 2004, pp. [38] U. Orozco-Rosas, O. Montiel, and R. Sepúlveda,
2757–2762. “Mobile robot path planning using membrane
[25] W. NGAH, N. Buniyamin, and Z. Mohamad, “Point evolutionary artificial potential field,” Appl Soft
to point sensor based path planning algorithm for Comput, vol. 77, pp. 236–251, 2019.
autonomous mobile robots,” in Proceedings of the [39] U. Orozco-Rosas, K. Picos, and O. Montiel, “Hybrid
9th WSEAS International Conference on System path planning algorithm based on membrane pseudo-
Science and Simulation in Engineering, 2010, pp. bacterial potential field for autonomous mobile
186–191. robots,” IEEE Access, vol. 7, pp. 156787–156803,
[26] S. Behnke, “Local multiresolution path planning,” in 2019.
RoboCup 2003: Robot Soccer World Cup VII 7, [40] M. Alswaitti, K. Siddique, S. Jiang, W. Alomoush,
Springer, 2004, pp. 332–343. and A. Alrosan, “Dimensionality reduction,
[27] D. Li, P. Wang, and L. Du, “Path planning modelling, and optimization of multivariate problems
technologies for autonomous underwater vehicles-a based on machine learning,” Symmetry (Basel), vol.
review,” Ieee Access, vol. 7, pp. 9745–9768, 2018. 14, no. 7, p. 1282, 2022.
[28] W. Jing, J. Polden, W. Lin, and K. Shimada, [41] S. H. Tang, W. Khaksar, N. Ismail, and M. Ariffin,
“Sampling-based view planning for 3d visual “A review on robot motion planning approaches,”
coverage task with unmanned aerial vehicle,” in 2016 Pertanika J Sci Technol, vol. 20, no. 1, pp. 15–29,
IEEE/RSJ International Conference on Intelligent 2012.
Robots and Systems (IROS), IEEE, 2016, pp. 1808– [42] S.-H. Chia, K.-L. Su, J.-H. Guo, and C.-Y. Chung,
1815. “Ant colony system based mobile robot path
[29] Y. Xue and J.-Q. Sun, “Solving the path planning planning,” in 2010 fourth international conference
problem in mobile robotics with the multi-objective on genetic and evolutionary computing, IEEE, 2010,
evolutionary algorithm,” Applied Sciences, vol. 8, no. pp. 210–213.
9, p. 1425, 2018. [43] M. Sainlot, V. Nivoliers, and D. Attali, “Restricting
[30] L. Han and N. M. Amato, “A kinematics-based Voronoi diagrams to meshes using corner
probabilistic roadmap method for closed chain validation,” in Computer Graphics Forum, Wiley
systems: Li han, texas a nancy m. amato, texas a,” in Online Library, 2017, pp. 81–91.
Algorithmic and computational robotics, AK [44] R. Lewis, “Algorithms for finding shortest paths in
Peters/CRC Press, 2001, pp. 243–251. networks with vertex transfer penalties,” Algorithms,
[31] J. Kuffner, K. Nishiwaki, S. Kagami, M. Inaba, and vol. 13, no. 11, p. 269, 2020.
H. Inoue, “Motion planning for humanoid robots [45] W. Alomoush et al., “Fuzzy Clustering Algorithm
under obstacle and dynamic balance constraints,” in Based on Improved Global Best-Guided Artificial
 Bee Colony with New Search Probability Model for [59] Zhao, Tao, Haodong Li, and Songyi Dian. "Multi-
Image Segmentation,” Sensors, vol. 22, no. 22, p. robot path planning based on improved artificial
8956, 2022. potential field and fuzzy inference system." Journal
[46] C. Wormser and C. Wormser, “PhD THESIS of Intelligent & Fuzzy Systems 39, no. 5 (2020):
Specialized in Computational Geometry Generalized 7621-7637.
Voronoi Diagrams and Applications,” 2019, [60] P. Auer et al., “A new heuristic and an exact approach
Accessed: Jan. 25, 2024. [Online]. Available: for a production planning problem,” Cent Eur J Oper
https://theses.hal.science/tel-00410850 Res, vol. 29, pp. 1079–1113, 2021.
[47] M. d Berg, Computational geometry, in [61] Tahseen, Abu-Jassar Amer, et al. "Access control to
Computational geometry. Springer, 1997. robotic systems based on biometric: the generalized
[48] A. Okabe, B. Boots, K. Sugihara, and S. N. Chiu, model and its practical implementation." (2023).
“Spatial tessellations: concepts and applications of [62] S. Erke, D. Bin, N. Yiming, Z. Qi, X. Liang, and Z.
Voronoi diagrams,” 2009. Dawei, “An improved A-Star based path planning
[49] J. , D. B. Canny, Simplified Voronoi Diagrams. In: algorithm for autonomous land vehicles,” Int J Adv
Cox, I.J., Wilfong, G.T. (eds) Autonomous Robot Robot Syst, vol. 17, no. 5, p. 1729881420962263,
Vehicles. New York, UK: Springer, 1990. Accessed: 2020.
Jan. 25, 2024. [Online]. Available: [63] S. Aine, S. Swaminathan, V. Narayanan, V. Hwang,
https://link.springer.com/chapter/10.1007/978-1- and M. Likhachev, “Multi-heuristic a,” Int J Rob Res,
4613-8997-2_21#citeas vol. 35, no. 1–3, pp. 224–243, 2016.
[50] H. Choset and J. Burdick, “Sensor based planning. II. [64] M. M. Mohamad, N. K. Taylor, and M. W. Dunnigan,
Incremental construction of the generalized Voronoi “Articulated robot motion planning using ant colony
graph,” in Proceedings of 1995 IEEE international optimisation,” in 2006 3rd International IEEE
conference on robotics and automation, IEEE, 1995, Conference Intelligent Systems, IEEE, 2006, pp.
pp. 1643–1648. 690–695.
[51] H. Choset, Sensor based motion planning: The [65] Koubâa, Anis, Hachemi Bennaceur, Imen Chaari,
hierarchical generalized Voronoi graph. California Sahar Trigui, Adel Ammar, Mohamed-Foued Sriti,
Institute of Technology, 1996. Maram Alajlan, Omar Cheikhrouhou, and Yasir
[52] C. ó’Dúnlaing, M. Sharir, and C. K. Yap, Javed. Robot path planning and cooperation. Vol.
“Retraction: A new approach to motion-planning,” in 772. Cham, Switzerland: Springer International
Proceedings of the fifteenth annual ACM symposium Publishing, 2018.
on Theory of computing, 1983, pp. 207–220. [66] E. Masehian and M. R. Amin‐Naseri, “A voronoi
[53] S. A. Wilmarth, N. M. Amato, and P. F. Stiller, diagram‐visibility graph‐potential field compound
“MAPRM: A probabilistic roadmap planner with algorithm for robot path planning,” J Robot Syst, vol.
sampling on the medial axis of the free space,” in 21, no. 6, pp. 275–300, 2004.
Proceedings 1999 IEEE International Conference on [67] M. A. Deif and M. A. A. Eldosoky, “Adaptive Neuro-
Robotics and Automation (Cat. No. 99CH36288C), Fuzzy Inference System for Classifcation of
IEEE, 1999, pp. 1024–1031. Urodynamic Test,” Int J Comput Appl, vol. 118, no.
[54] R. Mahkovic and T. Slivnik, “Generalized local 16, 2015.
Voronoi diagram of visible region,” in Proceedings. [68] Qin, Hongwei, Shiliang Shao, Ting Wang, Xiaotian
1998 IEEE International Conference on Robotics Yu, Yi Jiang, and Zonghan Cao. "Review of
and Automation (Cat. No. 98CH36146), IEEE, 1998, autonomous path planning algorithms for mobile
pp. 349–355. robots." Drones 7, no. 3 (2023): 211.
[55] K. Nagatani, H. Choset, and S. Thrun, “Towards [69] Tan, Chee Sheng, Rosmiwati Mohd-Mokhtar, and
exact localization without explicit localization with Mohd Rizal Arshad. "A comprehensive review of
the generalized voronoi graph,” in Proceedings. 1998 coverage path planning in robotics using classical
IEEE International Conference on Robotics and and heuristic algorithms." IEEE Access 9 (2021):
Automation (Cat. no. 98CH36146), IEEE, 1998, pp. 119310-119342.
342–348. [70] Zhao, Tao, Haodong Li, and Songyi Dian. "Multi-
[56] A. Alrosan et al., “Automatic data clustering based robot path planning based on improved artificial
mean best artificial bee colony algorithm,” potential field and fuzzy inference system." Journal
Computers, Materials & Continua, vol. 68, no. 2, pp. of Intelligent & Fuzzy Systems 39, no. 5 (2020):
1575–1593, 2021. 7621-7637.
[57] T. A. Badmos, “A Sheffield Hallam University [71] T.-L. Lee and C.-J. Wu, “Fuzzy motion planning of
thesis,” A Sheffield Hallam University , BADMOS, mobile robots in unknown environments,” J Intell
Tajudeen, 2021. Accessed: Jan. 25, 2024. [Online]. Robot Syst, vol. 37, pp. 177–191, 2003.
Available: http://shura.shu.ac.uk/20029/ [72] Z. Dongbin and Y. Jianqiang, “Robot planning with
[58] B. K. Oleiwi, “Optimum Path Planning for Multi ant colony optimization algorithms,” in 2006 Chinese
Mobile Robots with Speed of Work Achievement as Control Conference, IEEE, 2006, pp. 1460–1465.
Constrain,” Journal of University of Babylon for [73] L. S. Garrido Bullón, L. E. Moreno Lorente, M. D.
Engineering Sciences, vol. 26, no. 10, pp. 181–196, Blanco Rojas, and P. P. Jurewicz Slupska, “Path
2018. Planning for Mobile Robot Navigation using Voronoi
Diagram and Fast Marching,” 2011.
[74] J. A. Sethian, “Fast marching methods,” SIAM Diagram Roadmap algorithm,” Sci Afr, vol. 12, p.
review, vol. 41, no. 2, pp. 199–235, 1999. e00745, 2021.
[75] S. Garrido, L. Moreno, M. Abderrahim, and D. [78] S. Liu et al., “Planning dynamically feasible
Blanco, “Robot navigation using tube skeletons and trajectories for quadrotors using safe flight corridors
fast marching,” in 2009 International Conference on in 3-d complex environments,” IEEE Robot Autom
Advanced Robotics, IEEE, 2009, pp. 1–7. Lett, vol. 2, no. 3, pp. 1688–1695, 2017.
[76] E. F. E. S., “Path Planning Using Heuristic Algorithm [79] W. Alomoush et al., “A survey: challenges of image
in Dynamic Environment,” 2019. segmentation based fuzzy C-means clustering
[77] B. B. K. Ayawli, A. Y. Appiah, I. K. Nti, F. algorithm,” J Theor Appl Inf Technol, 2018.
Kyeremeh, and E. I. Ayawli, “Path planning for
mobile robots using Morphological Dilation Voronoi