161 American Academic Scientific Research Journal for Engineering, Technology, and Sciences ISSN (Print) 2313-4410, ISSN (Online) 2313-4402 http://asrjetsjournal.org/ Survey on Path Planning of Mobile Robot with Multi Algorithms Ali H. Al-Beaty a* , Nemir Al-Azzawi b , Ahmed R.J. Almusawi c a,b,c University of Baghdad /Al-Khwarizmi College of Engineering, Baghdad, Iraq a Email: alialbeatymeca@gmail.com b Email: dr.nemir@kecbu.uobaghdad.edu.iq c Email: Ahmedalmusawi@kecbu.uobaghada.edu.iq Abstract Sensible practical environment for path and continuous motion preparation problems usually involves various operational areas coupled with indoor usage comprising of multiple apartments, corridors, a few doors and several static and active obstacles in between. The disintegration of this system into limited areas or regions indicates an effect on the fun preparation of appropriate pathways in a complex setting. Many algorithms are designed to solve problems with narrow passages and with optimal solution for more than one field. Independent mobile robot gadget would have felt the stability of its abilities, the steadfastness and the question of resilience with the project and the implementation of an innovative as well as an efficient plan with the best approach. Navigation algorithms reaching a certain sophistication in the field of autonomous mobile robot, which ensures that most work now focuses on more specialized activities such as efficient route planning and navigation across complex environments. Adaptive way to prepare and maneuver needs to establish learning thresholds, legislation to identify areas and to specify planned requirements of the library. The aim of this survey is studying many algorithms to view the advantage and disadvantage for each method then can use optimal method depended on this study. Keywords: Mobile robot; path planning; Fuzzy logic; Generic algorithm; Ant colony algorithm; A*algorithm. 1. Introduction The path planning of intelligent mobile robot Is one of the most essential robotic studies areas. In this article the technique of path planning is classified into four categories. Template based, artificial capacity discipline based, map building primarily based and artificial smart totally based strategies. First, the primary theories of the direction making plans methods are added in short. Then, the advantages and obstacles of the methods are pointed out. Finally, the technology developments of sensible mobile robot direction making plans are given. ------------------------------------------------------------------------ * Corresponding author. http://asrjetsjournal.org/ American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 162 2. Types of algorithms 2.1 Fuzzy logic Fuzzy common sense manage is described by the utilization of etymological rules to control and execute human skill in control machine with the intention to manage the uncertainty present inside the surroundings. The authors in [1] advanced conduct-based management system under which the basic activity of every community navigation enterprise is analyzed. He often used a combination of blurred laws and stereo vision system to wear loose navigation risks. The authors in [2] not that new technique, minimum chance technique, to deal with the nearby course planning to break out from local minimum for the duration of purpose-orientated robotic navigation in unknown environments. Scientifically this method is designed to maintain global continuity even in long-wall, unstructured, cluttered, labyrinthine, and updated settings. Theoretically, the lowest risk strategy is known to ensure consistency even in long walls, large concave, recurrent U-forms, unstructured, cluttered, labyrinthine and changed environments. The fuzzy good decision system outperforms theoretical methods of identification and departure of norms accompanied by other approaches. The authors in [3] proposed to use the fuzzy control algorithm to minimizes the iterative learning error of the ant colony optimization (ACO) algorithm. The major purpose of this algorithm to find the easy and shorter path of mobile robot. Used Ultrasonic sensors to detects any obstacles in the way of mobile robot. In the experimental work used two environments of mobile robot. The first environment was without obstacles and shorter path planning. The second environment with obstacles and shorter. This article Ming‐Feng Cheng compares test in a Z-shaped environment map and in complicated environment map. The authors in [4] proposed a fuzzy logic and filter Smoothing primarily based on the information from the laser test sensor. The path making plans and self- sufficient impediment avoidance primarily based in this set of rules is emphasized due to the fact it can routinely find the first-class course in line with the size and position of gaps among the barriers inside the dynamic environment. Table 1: Relationship between destination angle and Turing direction Destination angle Turning direction 340 ° ~ 20 ° while stop_ forward = 0 Forward 20 ° ~ 160 ° right 160 ° ~ 200 ° while stop_ backward = 0 backward 200 ° ~ 340 ° Left American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 163 The authors in [5] proposed strategy, it considers data from sensors mounted on the device, consisting of the space from the closest impediment to the south, front and right next to the details from the angular version of the target. The Fuzzy rules are used to manipulate the robotic 's rate of left and right wheels. A defuzzification technique is applied to the right and left wheels and tests are matched with the defuzzified values produced from the Sugeno weighted average process. The second method disregards the 4 inputs and follows the same fuzzy approach. A combination between the two methods indicates the better approach is the main one. Finally, route making plans the usage of Sugeno-primarily based fuzzy common-sense controller has applied in Create mobile robot via interfacing with Arduino Uno. The authors in [6] this article explores the usage of Fuzzy Artificial Potential (FAP) method in two separate strategies for the path preparation of a humanoid robotic in an Uncertain setting. In the first method, the path of the robot transition is obtained from a fuzzified discipline of synthetic skill, whereas in the second the route of the robotic is extracted from those linguistic laws that may be stimulated from the field of synthetic skill. Such two brought trajectory model techniques are established as certain software and hardware are present in the loop simulations and the experimental results demonstrate the supremacy of the proposed processes in the real-time trajectory of humanoid robot causing plans trouble. The authors in [7] introduces a single-tone type-1 fuzzy logic system (T1-SFLS) controller and a combination of Fuzzy-WDO for autonomous mobile robot navigation and collision avoidance in an undefined static and dynamic environment. The WDO Algorithm optimizes and sets the feature parameters of the fuzzy device input / output club. The WDO algorithm operates primarily based on the atmospheric passage of infinitesimal tiny air parcels moving through an N-dimensional field. Using Khepera-III mobile robot, the efficiency of this proposed methodology was measured via several computer simulations and real-time experiments. As compared to the T1-SFLS controller the fuzzy-WDO set of rules is observed right agreement for mobile robot navigation. Simulation and experimental effects demonstrate the Fuzzy WDO controller offer higher performance compared to the T1-SFLS controller. Figure 1: The structure of a T1-SFLS controller for mobile robot navigation The authors in [8] suggested the controller is liable for stopping mobile robots as well as touring across a chart from the starting point to the goal location. The FLC is built as an essentially intelligent system (IA)-based sub- program. The device system utilizes the superior application Robots Interface (ARIA), configured miles with a C++ kit (visible C++.Net), and networking device is used to set up wireless TCP / IP Ethernet-to-Serial communication between robot and computer. The outcomes display that the developed cellular robotic travels American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 164 efficiently from one region to another and reaches its goal after fending off all limitations which are positioned in its way. 2.2 Genetic Algorithm (GA) Genetic set of rules are very famous meta-heuristic strategies for producing optimized result. Through this method, the candidate answer population is advanced to aim better based on herbal collection. In GA, a preliminary population collection is created randomly, after which the fitness price of each solution is determined by applying the objective feature of the problem. Then the broader suit response is determined, and genetic process replication and fusion is added to them in order to build a brand-new community of further suit applicants. This process is replicated before the largest generation range is met or significant exercise costs are achieved. This approach is pursued by numerous researchers to produce and test perfectly tailored effects for specific usage. The FLC is constructed as a sub-program based basically on an intelligent machine (IA). The controller [9] noted that a dynamic direction making plans technique primarily based on genetic set of rules for cell robotic under unknown surroundings. The actual coding, exercise characteristics and genetic operators are built to improve algorithm convergence and operational accuracy. Under uncertain chaotic conditions, the genetic collection of rules used on this paper will yield exciting route planning outcomes. The simulation findings show that the genetic collection of laws is robustly adaptable to complex and uncertain conditions. The genetic collection of rules typically begins without capturing the true answer as well as depending solely on answers from its environment and the operators of evolution i.e. Mutation replication and fusion in order to produce solution of first quality. Consequently, by adding multiple individual variables and concurrently looking at them, the collection of rules converges into suboptimal responses by holding local minimums off. Genetic discovery collection of rules is used to create through points via the vision device after the gadgets are discovered. The fitness fee for the tracks created is measured in terms of security from the obstructing dynamic impediment and room to the position of the target. Genetic algorithm used drastically in pathway planning applications. Genetic rule collection uses near-reminiscence for complex zone chromosomes. The method suffers from a big quantity of computation. The main deficiency of the genetic algorithm methodology in the area of preparation is that in complex settings it is not feasible. Because it operates on a grid map or uses a set decision in the vicinity of the search, it also does not control the variety of populations which cause early convergence. The most important drawback of the hereditary system of laws is attributed to weakly understood performance capacities that produce the poorest sets of chromosomes, rather than merely the idea that the correct chromosome sets cannot cover away those issues of optimization. The authors in [10] proposed a genetic set of rules carried out to single point as opposed to entire workspace. The authors in [11] proposed an evolutionary method for a cell robot's route planning problem in the surroundings, which can also integrate a variety of unexplained polygonal barriers. The authors in [12] proposed for using genetic algorithm with controllable mobile robot to optimal path between two points in a grid surrounding. Also, mobile robot finds optimal path and reduce the number of steps between the start point and end point. GAs Can triumph over many problems encountered by using Traditional seek techniques along with the gradient based strategies. They explored the overall performance of the evolutionary device with varies Population size. They also, proposed a simplified fitness characteristic. American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 165 Figure 2: Convergence process for GAs with a 100×100 grid with obstacle free environment The authors in [13] proposed a specific type of technique for dynamic movement preparation problems of mobile robots in unpredictable complex environments focused primarily on control dynamics. The imaginative behavior of a mobile robot in motion preparation acts as a complex interplay process between the machine and its adjacent environments, and it's miles designed and controlled for travel planning purposes. It is recommended that superior genetic algorithm operators be used to decorate the charge of divergence and that pathways be finished with affordable time. The authors in [14] proposed show the usefulness of strategies in the preparation of routes, in particular probabilistic roadmap (PRM) and genetic algorithm (GA). Two maps were used, one easy and one complex, to analyze their performances. In PRM, a map was initially loaded and followed the quantity of identifying nodes then, preliminary and final positions had been defined. Then the algorithm created a group of potential node relations between the preliminary and the final positions. The algorithm finally checked this network of connected nodes to go back to a collision-free path. In GA, by selecting the GA parameters, a map changed into observed initially loaded as well. These GA parameters have been investigated as to which set of values will shape the problem. Then, there were specified preliminary and final places. The related price included the distance or number of segments for each of the directions created. Penalties had been brought every time the generated path involved an obstacle. As a consequence, GA creates cleaner pathways that add to the ease of mobile robots' navigation, but absorbs extra computing time, rendering it impossible to incorporate real-time navigation. The authors in [15] proposed affords a brand new method for solving CPP. Through this procedure, the position of protection is separated into tiny squares where the diagonal squares are the robotic tool scale. There are four important movements described in a square, which can be forward, left flip, right turn and U-flip. A price method is used in which a fixed rate is used for any fundamental motion in a square and prices are added up for all motions in order to get an average cost for a path. This feature American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 166 makes it possible to find the best path between trails with the same repeated visits in addition, genetic algorithm (GA) is used to evaluate the optimal path to cover an region. By convergence, discovery and evolution, GA strengthens existing pathways culminating in virtually the most effective alternatives to the gold standard. The authors in [16] proposed the smooth course making plans trouble is taken into consideration for a mobile robot primarily based at the genetic set of rules and the Bezier curve. The workspace of a cell robotic is represented by way of a brand-new grid-based illustration (2n × 2n grids) that allows the operations of the followed genetic set of rules. The chromosome of the genetic set of rules is composed of a chain of binary numbered grids (i.E., control factors of the Bezier curve). Ordinary genetic operators which include crossover and mutation are used to look the most efficient chromosome wherein the optimization criterion is the duration of a piecewise collision-free Bezier curve course determined by means of the control points. A numerical test is given to illustrate the effectiveness of the proposed easy course making plans technique for a mobile robot. The authors in, [17] A series of new concepts and specialized genetic operators of a genetic algorithm ( GA) was suggested and introduced to explain the problem of course preparation for mobile robot (MR) in complex environments. The method suggested has two superiorities: fast progress towards the environment superior and the viability of all responses in the community. Roadmaking proposals aim at offering a high-quality path from a starting area to a destination region, avoiding crashes or so-called preventing obstacles. The primary thoughts on Xiaolei Zhang1, Yan Zhao1*, Nianmao Deng2 and Kai'articles are visible space, matrix coding and new mutation operators. A viable path may be acquired unexpectedly based on seen area. Infeasible paths can be changed easily and with an incredible degree of productivity after genetic operations with the aid of utilizing seen space. Through the use of new mutation operators, the approach may additionally rapidly converge closer to an international ideal solution with better possibility than different strategies, not handiest in static environments however additionally in dynamic environments. 2.3 Ant Colony Algorithm The ant colony optimization algorithm (ACO) is a probabilistic tool for solving numerical issues in computer science and organizational analysis that can be reduced to finding good paths through graphs. Artificial ants are multi-agent tactics that are inspired by the behavior of actual ants. The contact of biological ants based on pheromones is also the key model used. For various optimization tasks requiring some kind of database, such as vehicle routing and internet routing, combinations of Artificial Ants and local search algorithms have become a tool of choice. The authors in [18] in order to overcome the convergence rate problems in the ant colony algorithm, a stepped-forward ant colony optimization algorithm is suggested for the route planning of mobile robots inside the area demonstrating the usage of the grid technique. Pheromone diffusion and spatial neighborhood optimization was combined in the scanning technique for the regional norm pathway. During the ant-looking phase, the current way pheromone diffuses in the route of the skill subject power, so that ants begin to search for a higher fitness subspace and the hunting region of the test pattern is smaller. Using the geometric method, the direction that is first designed for the application of the rules collection of ant colony. The first optimal route pheromones and the second optimal route are both modified at the same time. The simulation results indicate that the advanced series of rules for the optimization of ant colony was especially successful. The authors in [19] averting collision with barriers is a field of contemporary capacity studies to discover consistency feasible route from start to finish, which decreases time and distance, in a given setting. This article American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 167 provides SACO and ACO-MH algorithms to solve the issue of mobile robotic route making plans to enter the end station without collision from the first stop. The SACO and ACO-MH algorithms have the largest collision- free route. The mobile robot environment is managed as a grid-based environment in which each grid can be represented by a pair of ordered row varieties and column varieties. The tests of ACO-MH indicate higher convergence velocity and numerical time reduction than those of SACO via several MATLAB experiments. Figure 3: Flowchart Ant Colony Optimization Algorithm The authors in [20] worked together to sort out the problem of robot path planning (RPP). They suggested a clear description of the heuristic and visibility equations of the Kingdom transfer regulations. In a regional static map with feasible free region nodes, the suggested algorithm is implemented. The authors in [21] the object provides the usage of the rules set of ant colony for the course planning of cell robots. It solves the goal quest for the ability to refine the ant colony algorithm and manipulates the cellular robot change from the start location (nest) in the collision-free region to the target task (meals). 4 variety type limitations have been applied to program the motion path using a collection of rules for ant colony and try the optimization route of the cellular robot transfer to the target position. In destiny, we need to extend the algorithm of ant colony to be American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 168 executed in the multi-robot method and try the path of motion optimization in the collision-free region. 2.4 A star(A*) algorithm A-star is a graph traversal and path searching algorithm that is mostly used because of its completeness, optimality and maximal performance in many computer sciences fields. Its spatial complexity is one big functional downside, as it stores all created nodes in memory. Therefore, algorithms that can pre-process the graph to produce improved efficiency, as well as memory-bounded methods, are normally outperformed in realistic travel-routing systems; however, A * is in many instances still the best solution. The authors in [22] improved A * collection of rules has been evaluated and applied on this paper, and the traditional A * set of rules has been updated by means of weighted assessment characteristic analysis, which has reduced the presence measures from 200 to 80 and the quest period from 4,359s to 2,823s inside the feasible route planning. The synthetic search marker, which could effectively and quickly get away from the barrier trap, is also delivered to keep away from looking over and over at the invalid vicinity, making the algorithm extra powerful and correct in finding the feasible course in unknown environments. Figure 4: The searing results of the optimal path applying A* algorithm The authors in [23] a green and low cost robotic APF cell is proposed and built with obstacles and avoidance of collisions. A window based IPM GUI is developed that serves as a course simulation platform and APF robotic course downloader. Measurement of displacement blunders was conducted in the virtual route and the actual test course. The authors in [24] article, a hybrid methodology focused entirely on A * algorithm and a genetic collection of rules in the grid map is suggested to address the first route of mobile robot planning. A * algorithm is used to rapidly find a restricted shortest path and the global gold standard route is obtained using genetic rules to refine the course. The strategy makes the path node not limited to the grid core, and no longer has to select how the road intersects with the impediment. The strategy does not limit the path node to the middle of the grid and does not need to select now if the direction intersects with the impediment. Simulation tests indicate that the American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 169 proposed approach can not only increase the hunting speed and excellent quest but can also be used in exceptional environments. The authors in [25] suggested an internet route through which mobile robot aims to use updated real time A * series of laws through grid-map surroundings. This series of rules has been applied in virtual and Khepera-II environments and determines the optimal path from a pre-defined location to a pre- defined goal point by holding obstacles off in its path trajectory. The course searching method is formulated of quadrant definition in a grid map and cluttered world of static and fluid limitations. Usage of this algorithm is calculated by optimizing the path since the aim is present in each of the four quadrants and restricts the robotic movement to the right quadrant. Robot can plot the most favorable path in its way through fending off obstructions and reducing time, money, and distance as the charge, but the original A * series of rules no longer consider the shortest route configured. Table 2: An Advantage and Disadvantage for Algorithms Algorithms Advantage Disadvantage Fuzzy logic Simplification and versatility, Problems can be treated with incorrect and imperfect data, and Cheaper to expand. It is easy and justifiable to organize Fuzzy Logic structures. Genetic (GA) There are many local optimists, it is very high for the number of parameters. GA is costly in terms of computing, i.e., time consuming. Ant Colony A star (A*) Can scan simultaneously amongst a population, and Successful solutions can be found easily. it is optimum and complete, it is perfectly efficient, and using to overcome incredibly difficult problems. Have a demanding theoretical examination, and the time for convergence is unknown. It has difficulty with ambiguity 3. Analysis methods of algorithms 3.1 Fuzzy logic The authors in [1] noted that  Fuzzy control American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 170 The robot's behavior is based on the venture to be realized. In this picture, they would decide to enforce all the habits besides. They will detail our technique for the bushy rule base modular employer for each course- following and purpose of conducting behavior and preventing behavior  Path following behavior Path of behavior is used to guide the robot opposite the desired deliberate direction. They use the concept that includes lowering the orientation errors α, which is the discrepancy between the target heading and the actual heading. Likewise, they aim to reduce the gap errors d of the real robot role with admire on the road (Δ) as shown in part 2, such as: d = √(xt − xr)2 + (yt − yr)2 (1) α = φ − atan 2((yt − yr). (Xt − Xr)) (2) 3.2 Genetic Algorithm (GA) The authors in [13] noted that Here 15 individual tasks are considered to execute with single and a couple of robotics in which each robotic is allocated independently to a totally specific collection of responsibilities and completes the route by returning from the same point to the mission began. Here, the following are a few modeling studies with 15 responsibilities and four separate instances:  Single Robot with 15 tasks (Case-I)  Four Robots with 15 independent tasks (Case-II)  Four Robots with 15 tasks with constrained (Case-III)  Four Robots with 15 tasks with initial and destination (Case-IV) 3.3 Ant colony algorithm R. Rashid, Perumal, N., Elamvazuthi, I., Tageldeen, M. K., Khan, M. K. A. A., & Parasuraman, S, [19] When ant k can select the next jth grid point at the ith grid point (x, y), by selecting one of its 8 neighboring locations: [(x-1, y+1), (x, y+1), (x+1, y+1), (x-1, y), (x, y), (x+1, y), (x-1, y1), (x, y-1) and (x+1, y-1)]. Use these equations to solve obstacles problem American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 171 τⅈj(t + 1) = (1 − ρ) ⋅ τij(t) + ∑ Δ μ k=1 τi ⋅ j (3) ΔτIj k = 1 ∕ Lk (4) 3.4 A*algorithm The authors in [25] noted that Presents grid surroundings with a given boundary and the robot's deliberate path trajectory is seen within the arrow mark form. Here, in a single new version, the robot traverses one of the neighborhood grid variables, but cannot move diagonally to the nearest row. A robot is represented by the theoretical motion plan of a robot in grip map and circle. The subsequent equation is used to find the placement of the aim wherein quadrant it's miles present. Let us consider the coordinate point of the goal is (x_g. y_g) the initial coordinate point of the robot is (x_c. y_c). The robot determines the goal quadrant by eliminating the target coordinate element and the robot 's initial coordinate point. Let (Cx, Cy) be the difference value of (x_g. y_g) and (x_c. y_c). Now if, 𝐟(𝐧) = g(n) + r(n) + h(n) + S(n) (5) h(n) = √(xi − xg) 2 + (yi − yg) 2 (6) 4. Experiments and Results Used A star algorithm in this article to solve problems with path planning in mobile robots. May find the best solution for track preparation by using below equation. Let us assume the goal point is (x_1.y_1 )and start point is (x_2.y_2 ). Let (C1, C2) is the different value between the start point and goal point. 𝐟(𝐧) = 𝐠(𝐧) + 𝐫(𝐧) + 𝐡(𝐧) + 𝐒(𝐧) (𝟕)[𝟐𝟒] 𝐡(𝐧) = √(𝐱𝟐 − 𝐱𝟏)𝟐 + (𝐲𝟐 − 𝐲𝟏)𝟐 (𝟖)[𝟐𝟒] Where g(n) the generation costs the not turn required for the robot to rotate from the current position to the next position in the direction of motion, r(n) the estimated cost of movement from the robot's starting point to the target point, h(n) the direction in which the mobile robot moves around the obstacle S(n) after using the above equations. A star algorithm is used to apply path planning for mobile robot in environment that has three walls and two obstacles as shown in the figure 5. American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 172 Figure 5 5. Conclusions This article complicated evaluation of the approaches used in the preparation of mobile robot courses and shortest course navigation problems this review described various methods and explains their advantages and drawbacks. There are a few traditional approaches inside the actual global implementation that might not be continuous, because they are unable to deal with the volatile complex and unsure surroundings of live-global. Classical methods required massive computation and reminiscence, while heuristic techniques with certain adjustments can overcome the actual global problem. The mobile robot track creating strategies totally dependent on predefined mapping is more complicated due to the intermittent noise and complex design of actual international utility. Heuristic approaches genetic algorithms, Fuzzy logic, ant colony optimization and A star algorithms for a mobile robot navigation. As a result, the autonomous cell robots will heuristically reach the side with all sorts with constraints without colliding with them, competently. Such approaches provide an integrated solution to challenging problems. We have been used A star algorithm in this current work and found that the results from this algorithm is better than from other algorithms in terms of speed in performance and quality. References [1] F. Abdessemed et al., “A hierarchical fuzzy control design for indoor mobile robot,” Int. J. Adv. Robot. Syst., vol. 11, no. 1, 2014, doi: 10.5772/57434. [2] M. Wang and J. N. K. Liu, “Fuzzy logic based robot path planning in unknown environment,” 2005 Int. Conf. Mach. Learn. Cybern. ICMLC 2005, vol. 1, no. August, pp. 813–818, 2005, doi: 10.1109/icmlc.2005.1527055. [3] C. T. Yen and M. F. Cheng, “A study of fuzzy control with ant colony algorithm used in mobile robot American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 173 for shortest path planning and obstacle avoidance,” Microsyst. Technol., vol. 24, no. 1, pp. 125–135, 2018, doi: 10.1007/s00542-016-3192-9. [4] Y. Yan, & Li, Y, " Mobile robot autonomous path planning based on fuzzy logic and filter smoothing in dynamic environment," World Congress on Intelligent Control and Automation (WCICA). vol. 7, pp. 1-6, 2016. [5] D. Davis, & Supriya, P, " Implementation of Fuzzy-Based Robotic Path Planning," Proceedings of the Second International Conference on Computer and Communication Technologies, vol. 8, pp. 1-9, 2015. [6] M. Fakoor, A. Kosari, and M. Jafarzadeh, “Revision on fuzzy artificial potential field for humanoid robot path planning in unknown environment,” Int. J. Adv. Mechatron. Syst., vol. 6, no. 4, pp. 174– 183, 2015, doi: 10.1504/ijamechs.2015.072707. [7] A. Pandey and D. R. Parhi, “Optimum path planning of mobile robot in unknown static and dynamic environments using Fuzzy-Wind Driven Optimization algorithm,” Def. Technol., vol. 13, no. 1, pp. 47–58, 2017, doi: 10.1016/j.dt.2017.01.001. [8] N. K. A. Al-Sahib and A. R. Jasim, “Guiding Mobile Robot by Applying Fuzzy Approach on Sonar Sensors,” Al-Khwarizmi Eng. J., vol. 6, no. 3, pp. 36–44, 2010. [9] P. Shi and Y. Cui, “Dynamic path planning for mobile robot based on genetic algorithm in unknown environment,” 2010 Chinese Control Decis. Conf. CCDC 2010, pp. 4325–4329, 2010, doi: 10.1109/CCDC.2010.5498349. [10] Y. G. Toolika Arora, Vijay Arora, "Robotic path planning using genetic algorithm in dynamic environment‏," International Journal of Computer Applications, vol. 89, no 11, pp. 2-7, 2014. [11] H. S. Lin, J. Xiao, and Z. Michalewicz, “Evolutionary navigator for a mobile robot,” Proc. - IEEE Int. Conf. Robot. Autom., no. pt 3, pp. 2199–2204, 1994, doi: 10.1109/robot.1994.350958. [12] A. S. a. M. A.-W. Ismail AL-Taharwa, " A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment," Journal of Computer Science, vol. 6, pp. 1-4, 2008. [13] R. K. Panda and B. B. Choudhury, “An effective path planning of mobile robot using genetic algorithm,” Proc. - 2015 IEEE Int. Conf. Comput. Intell. Commun. Technol. CICT 2015,vol. 22, pp. 1- 5, 2015, doi: 10.1109/CICT.2015.145. [14] R. M. C. Santiago, A. L. De Ocampo, A. T. Ubando, A. A. Bandala, and E. P. Dadios, “Path planning for mobile robots using genetic algorithm and probabilistic roadmap,” HNICEM 2017 - 9th Int. Conf. Humanoid, Nanotechnology, Inf. Technol. Commun. Control. Environ. Manag., vol 20. 2018-Janua, American Academic Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) (2022)Volume90, No1, pp161-174 174 pp. 1–5, 2017, doi: 10.1109/HNICEM.2017.8269498. [15] T. R. Schäfle, S. Mohamed, N. Uchiyama, and O. Sawodny, “Coverage path planning for mobile robots using genetic algorithm with energy optimization,” Proc. - 2016 Int. Electron. Symp. IES 2016, vol. 12, pp. 2-6, 2017, doi: 10.1109/ELECSYM.2016.7860983. [16] B. Song, Z. Wang, and L. Sheng, “A new genetic algorithm approach to smooth path planning for mobile robots,” Assem. Autom., vol. 12, pp. 2-6, 2016, doi: 10.1108/AA-11-2015-094. [17] X. Zhang, Y. Zhao, N. Deng, and K. Guo, “Dynamic Path Planning Algorithm for a Mobile Robot Based on Visible Space and an Improved Genetic Algorithm,” Int. J. Adv. Robot. Syst., vol. 13, no. 3, 2016, doi: 10.5772/63484. [18] J. Liu, J. Yang, H. Liu, X. Tian, and M. Gao, “An improved ant colony algorithm for robot path planning,” Soft Comput., vol. 21, no. 19, pp. 2–9, 2017, doi: 10.1007/s00500-016-2161-7. [19] K. Akka and F. Khaber, “Mobile robot path planning using an improved ant colony optimization,” Int. J. Adv. Robot. Syst., vol. 15, no. 3, pp. 1–6, 2018, doi: 10.1177/1729881418774673. [20] N. Buniyamin, N. Sariff, N. W. A. J. Wan, and Z. Mohamad, “Robot global path planning overview and a variation of ant colony system algorithm,” Int. J. Math. Comput. Simul., vol. 5, no. 1, pp. 9–16, 2011. [21] S. H. Chia, K. L. Su, J. H. Guo, and C. Y. Chung, “Ant colony system based mobile robot path planning,” Proc. - 4th Int. Conf. Genet. Evol. Comput. ICGEC 2010, vol. 54, pp. 3-4, 2010, doi: 10.1109/ICGEC.2010.59. [22] J. Yao, C. Lin, X. Xie, A. J. A. Wang, and C. C. Hung, “Path planning for virtual human motion using improved A* algorithm,” ITNG2010 - 7th Int. Conf. Inf. Technol. New Gener.,vol. 61, pp. 2-5, 2010, doi: 10.1109/ITNG.2010.53. [23] W. Y. Loong, L. Z. Long, and L. C. Hun, “a Star Path Following,” 4th International Conference on Mechatronics (ICOM). vol. 71, pp. 3-7, 2011. [24] L. Zhang, H. Min, H. Wei, and H. Huang, “Global path planning for mobile robot based on a algorithm and genetic algorithm,” 2012 IEEE Int. Conf. Robot. Biomimetics, ROBIO 2012 - Conf. Dig., vol. 74, pp. 2-5, 2012, doi: 10.1109/ROBIO.2012.6491228. [25] P. K. Das, Behera, H. S., Pradhan, S. K., Tripathy, H. K., & Jena, P. K, " A Modified Real Time A* Algorithm and Its Performance Analysis for Improved Path Planning of Mobile Robot," Smart Innovation, Systems and Technologies, 221–234, vol. 62, pp. 3-12, 2014.