Dissertations / Theses on the topic 'Wall following robot'
To see the other types of publications on this topic, follow the link: Wall following robot.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 17 dissertations / theses for your research on the topic 'Wall following robot.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Daltorio, Kathryn A. "Obstacle Navigation Decision-Making: Modeling Insect Behavior for Robot Autonomy." Case Western Reserve University School of Graduate Studies / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=case1365157897.
Full text
2
Vožda, Ondřej. "Řízení invalidního vozíku." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2013. http://www.nusl.cz/ntk/nusl-220145.
Full textAbstract:
This thesis describes development of control algorithm for a wheelchair. Wheelchair should be capable of tracking and following a wall or a similar flat surface. Thesis is supposed to be an extension of the previous concept, whose purpose was to allow remote telepresence control of this wheelchair. SRF08 ultrasonic range finders are used to measure distance from the wall. Furthermore, image processing for mark detection is discussed. Purpose of these marks is to increase precision during final phase of the parking.
3
Chien, Chung-Wei, and 簡宗緯. "Mobile-Robot Wall-Following Control Design." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/21392174241916514565.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
102
A mechanism of robot vehicle that can walk along the wall was proposed in this thesis. The main part of the robot vehicle is consists of five SHARP short-distance infrared sensors ,two PWM servo motor and ALTERA DE0-Nano experimental board. One of the short-distance infrared sensors was installed on the front, the other two infrared sensors were in the left and right sides which has 45 degree angle from the front, and the last two sensor were also in both sides but they are vertical from the front. By the cooperation of these infrared sensors which were considered about their position and angle. The mobile-robot’s scanning range could up to 180 degrees. By receiving signal of infrared sensors from different directions and deliver them to CPU which is developed by ourselves. After a series of calculation and with the writing of firmware. The best executing mode could be choice exactly and then make the corresponding action to control motor's rotation. Finally, we implement this system and test in the actual environment. The results showed that the robot vehicle can achieve functions which we look forward to.
4
Dai-Hua, Jinag, and 江岱樺. "Wall-Following Fuzzy Control for Mobile Robot." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/79334524305267305766.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
103
This thesis proposes wall-following fuzzy control for mobile robots. The goal is to design a mobile robot that can follow the wall in various environments so that the mobile robot has to equip five infrared sensors to collect data. The W5 processor processes the obtained information from sensors into fuzzy states. Each fuzzy state is related to some specific behaviors. Fuzzy states are correlated to their matching behaviors via if-then rules which are designed by human reasoning. In order to achieve our goal, state registers are needed to record behavior state. It was proved that, using the fuzzy control, the mobile robot is able to deal with different wall conditions includes straight, concave and convex shapes. The result shows that the wall-following fuzzy control is successful for the mobile robot.
5
HUNG, YOU-JIA, and 洪佑嘉. "Speed-Controller-Based Mobile Robot for Wall-Following Control." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/56881208377383619476.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
104
A mechanism of robot vehicle that can walk along the wall is proposed in this thesis. The main part of the robot vehicle consists of eight SHARP middle-distance infrared sensors, two direct current (DC) motor, one DC motor driver board and ALTERA DE0-Nano experimental board. Two of the middle-distance infrared sensors is installed on the front, the other three infrared sensors were on the left and right sides. By the cooperation of these infrared sensors which are considered about their position and angle. The mobile robot's scanning range can up to 180 degrees. After receiving signal of infrared sensors from various directions and transmit them to CPU which is developed by ourselves, then process with the coding of firmware. The best executing mode can be chosen exactly and then make the corresponding action to control motor's rotation. Finally, this system is implemented and tested in the actual environment. The results show that the robot vehicle can achieve a goal which is following wall properly.
6
WANG, HAO-HSUAN, and 王皓暄. "Narrow-Tunnel Wall-Following Control Design for Mobile Robot." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/66wz2k.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
107
In recent years, reduce human labor force become a critical issue worldwide. There has been an increase need for automated manufacturing. Major companies around the world have also begun to invest in automation-related industries. Since Taiwan is a famous foundry country in the world, the requirements for automated facilities have also created the demand for automated robots. In the meantime, robot industry become a popular topic. In order to let the robot can move freely in any terrain. Sensor and algorithm of robot is crucial for this problem. This thesis propose a new algorithm for robot to enter a narrower tunnel then previous version.
7
Chen, Ying-Han, and 陳盈翰. "Hexapod Robot Wall-Following Control Using Fuzzy Controller with Advanced Differential Evolution." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/08498478739892016808.
Full textAbstract:
碩士國立中興大學
電機工程學系所
100
This thesis proposes advanced species differential evolution (ASDE) algorithm designed fuzzy controller (FC) to perform hexapod robot wall following. The ASDE uses the concept of the species (clustering). The solution vectors are clustered into different species based on their performances at each iteration. The ASDE dynamically generates a species-based mutant vector or a general mutant vector in the mutation operation according to an iteration-based adaptive probability value. The ASDE is applied to design an FC for robot wall-following control. All of the free parameters in the FC are learned through ASDE, which avoids the time-consuming manual design task. The FC inputs are three infrared distance sensor values. The FC controls the swing angle changes of the left- and right-middle legs of the hexapod robot to perform a suitable turning direction while moving forward at the same time. A new cost function is defined to quantitatively evaluate the performance an FC. Two different training environments are created for building this wall-following behavior without an exhaustive collection of input-output training pairs in advance. Simulations are conducted to verify the effectiveness of the evolutionary wall-following learning approach. Comparisons with other advanced differential evolution algorithms show that the ASDE achieves better performance in the wall-following control task.
8
Hung, Yi-Jan, and 洪翊展. "Wall-Following Hexapod Walking Robot Using Fuzzy Neural Network and Locomotion Control." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/a4326y.
Full textAbstract:
碩士國立中央大學
電機工程學系
105
This thesis applies a fuzzy neural network controller and Kalman filter to control the hexapod for wall following and efficiently adjust the gait to realize stability locomotion. According to the angle position, measured by ultrasonic sensor, between the robot and the wall, the fuzzy neural network controller can control the swing amplitude of the left and right legs of the robot, so that the robot can walk in the complex environment successfully. In addition to walking in an unknown environment, the stability of the hexapod is also a very important theme. The Kalman filter uses an accelerometer and a gyroscope to obtain the real-time robot body attitude, while the tilt angles are separated to the leg directions to change the amplitude by inverse kinematics. Thus, the robot can move forward, and instantly restore horizontal body attitude when walking on oblique terrain. The experimental results show that the method proposed in this research can successfully applied to a real hexapod robot control.
9
Du, Hong-Yi, and 杜宏逸. "Mobile Robot Wall-Following Control Using Fuzzy Controller with Evolutionary Reinforcement Learning." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/jhbjga.
Full textAbstract:
碩士國立虎尾科技大學
電機工程系碩士班
105
In this thesis, an improved differential search algorithm (IDS) is proposed to optimize the fuzzy logic controller (FLC) with the reinforcement learning (FLC_R-IDS). Using the reward and punishment mechanism of reinforcement learning to train the mobile robot wall-following control. The differential search algorithm has the ability to search for solution space, but often fall into the local best solution. Therefore, this study proposes an improved differential search algorithm, which uses parameter adaptation to adjust the control parameters (p1, p2).Change the number of superorganism involved in the stopover site to improve the exploration ability of the algorithm. In the training environment, the four sensors on the right side of the mobile robot are the input of the FLC. The output is the left wheel and right wheel speed. This study uses reinforcement learning to guide the behavior of the robot. Design three reward conditions as whether correct of robot behavior. These three conditions are for the distance follow the wall, judge the road ahead and avoid robots stop. When the mobile robot satisfy three reward conditions at the same time, get reward +1. On the contrary, once the mobile robot violates the three reward conditions, stop the current controller training, the accumulated reward value is used as the basis for the controller evaluation. And replace the next controller training. As a controller of the reward value of the cumulative amount of 6000, decided to learn finished. This study trained mobile robots along the wall in a simple environment, testing the learning controller in complex environments. Each algorithm independently trained 30 controllers for testing and comparison. The experimental results show that the improved differential search algorithm optimize the FLC has a better learning rate than the original differential search algorithm optimize the FLC. The performance better and stable than the original differential search algorithm optimize the FLC and chaos differential search algorithm optimize the FLC. Finally, the completed learn controller is tested in the training environment and the test environment. The experimental results show that the mobile robot using the fuzzy controller with evolutionary reinforcement learning can effectively implement the behavior along the wall.
10
HSU, Cheng-You, and 徐承佑. "Design of a Fuzzy Controller for the Wall Following Behavior of a Robot." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/44540250570460183083.
Full textAbstract:
碩士國立中興大學
電機工程學系所
95
The aim of this thesis is to design a fuzzy controller for a robot system, which is capable of executing the wall-following behavior and the adaptation under varying conditions, such as obstacle avoidance, making turns, and wall-searching. With these capabilities, the proposed robot is competent to walk along the walls in any environment. Furthermore, with the concept of neural network, an adaptive fuzzy controller is designed based on the back-propagation algorithm. Using the information obtained from the infrared sensor, the control output is computed. To improve the performance of the system, the error of the system is utilized to modify the parameters of the adaptive fuzzy controller according to the gradient descent updating rule. Through the simulation and experiments, the proposed robot system has been proved to be reliable and effective. Through the simulation and experiments, the robot system proposed has been proved to be reliable and effective.
11
Jhan, Yue-Hua, and 詹曜華. "Hexapod Robot Wall-Following Control Using Multi-Objective Advanced Continuous Ant Colony Optimized Fuzzy Controller." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/07327202827515517155.
Full textAbstract:
碩士國立中興大學
電機工程學系所
102
This thesis proposes a new multi-objective evolutionary fuzzy control approach to controlling both orientation and velocity of a hexapod robot for wall following. According to the measurements of four distance sensors, a fuzzy controller (FC) controls the walking speed of the robot by identically changing the basic swing amplitudes of the six legs. The FC also controls the orientation of the robot by applying additional changes of swing amplitudes of the left- and right-middle legs. In contrast to walking with a constant speed, control of the robot speed helps the robot successfully walk in complex environments such as those with inner right corners. In addition to the basic requirement that the robot should successfully walk along the wall in an unknown environment, the control objectives are that the robots should maintain a proper robot-wall distance and walk with a high speed. To this end, an advanced, multi-objective, continuous ant colony optimization (AMO-CACO) is proposed to optimize FCs in a simulated training environment. In contrast to the time-consuming manual design approach, the data-based AMO-CACO design approach helps reduce design effort and improve control performance. In contrast to single-objective optimization algorithms than find only a single FC, the AMO-CACO finds Pareto optimal solutions of different FCs at the same time. Optimization performance of the AMO-CACO is verified through comparisons with various multi-objective optimization algorithms in the robot control problem. Experimental results on controlling a real robot in unknown environments are conducted to verify the designed FCs.
12
Wei, Shih-Min, and 魏世旻. "Mobile Robot Wall-following Control Using a Fuzzy CMAC with Group-based Strategy Bacterial Foraging Optimization." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/20707906136341859210.
Full textAbstract:
碩士國立勤益科技大學
資訊工程系
103
In this paper, a fuzzy cerebellar model articulation controller (FCMAC) with group-based strategy bacterial foraging optimization (GSBFO) for mobile robot wall-following control is proposed. In the proposed FCMAC controller, the inputs are the distance between the sonar and the wall, the outputs are the angular velocity of two wheels. Through using the GSBFO to adjust parameters of FCMAC. A new fitness function is defined to evaluate the evolution of mobile robot wall-following. The fitness function includes four assessment factors which are defined as follows: maintaining safe distance between the mobile robot and the wall, ensuring successfully running a cycle, avoiding mobile robot collisions, and mobile robot running at a maximum speed. The simulation results show that the improved BFO is better than the traditional BFO. After learning, mobile robot travels wall-following successfully in unknown environment.
13
Hsu, Chia-Hung, and 許嘉宏. "Advanced Continuous Ant Colony Optimization for Multi-Objective Fuzzy Control with Intelligent Robot Wall-Following Applications." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/31545158559800650938.
Full textAbstract:
博士國立中興大學
電機工程學系所
101
This dissertation proposes three evolutionary fuzzy systems using different continuous ant colony optimization (CACO) algorithms, which avoids the time-consuming task of rule design by human experts and exhaustive collection of supervised input-output training pairs. Representations and generations of solutions in the proposed CACO algorithms are graphically explained in terms of nodes and path segments. The first algorithm is advanced CACO (ACACO), which uses a novel ant-path selection scheme for new solution generation and learning performance improvement. The ACACO is applied to multi-objective fuzzy lead-lag control of flexible AC transmission system (FACTS) devices in a multi-machine power system (PS), where multi-objective functions are linearly combined into a single objective function. The second one is a Species-Differential-Evolution (SDE) activated CACO (SDE-CACO) algorithm, which introduces a SDE mutation operation into a CACO algorithm for optimization performance improvement. The SDE-CACO is applied to multi-objective type-2 fuzzy control of a real robot performing a wall-following task. A two-stage learning control configuration is proposed to address the multi-objective robot control problem. The third one is a Multi-Objective Rule-Coded Advanced CACO (MO-RACACO) algorithm. Unlike the above two modified CACO algorithms that find a single solution in a multi-objective optimization problem, the MO-RACACO finds Pareto-optimal solutions. The MO-RACACO is also applied to the real robot wall-following control problem with multiple control objectives. Performances of these three optimization algorithms are verified through comparisons with various population-based optimization algorithms.
14
Nian, Zhu-Hong, and 粘竺弘. "Reinforcement Neural Fuzzy Surrogate –Assisted Multiobjective Continuous Ant Colony Optimized Fuzzy Controller For Robot Wall-Following Control." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/99479315809110355050.
Full textAbstract:
碩士國立中興大學
電機工程學系所
104
This paper proposes a multiobjective front-guided CACO (MO-FCACO) algorithm designed fuzzy controller (FC) with reinforcement neural-fuzzy surrogate-assisted learning method and applies it to autonomous mobile robot wall-following control task. Unlike the single-objective continuous ant colony optimization (ACO) algorithms that find only a single solution in a multi-objective optimization problem, the MO-FCACO finds Pareto-optimal solutions. This thesis proposes the incorporation of the SONFIN surrogate into the multiobjective evolutionary fuzzy control for the sake of avoiding the time-consuming task of multiobjective evolutionary FC learning. Objective-function value estimation which supersedes the original learning process is the key to tackling this issue. Also, in order to improve the accuracy of estimation, reinforcement learning (RL) is used for objective-function value estimation of an FC. Simulation and experimental results verify the effectiveness and efficiency of the new approach.
15
Yao, Yeh-Cheng, and 葉政耀. "Design of Fuzzy Controllers for the Wall Following Behavior of a Mobile Robot with a Laser Range Finder." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/08121254204316642861.
Full textAbstract:
碩士國立中興大學
電機工程學系所
99
In this thesis, an effective wall following control system for mobile robot is proposed. In order to use a simple two-dimensional fuzzy controller, we design an suitable and smooth local reference path from the high accurate raw laser range finder readings based on the morphological image processing techniques. By using the genetic algorithm to optimize the fuzzy control system, we can improve the efficiency of the control system. According to the simulation results, the robot can be controlled to approach the desired path and provide satisfactory performance.
16
Lin, Shih-Hao, and 林士豪. "Mobile Robot Wall-Following Control Using An Improved Artificial Bee Colony Algorithm for A Compensatory Fuzzy Logic Controller Design." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/33v3xs.
Full textAbstract:
碩士國立虎尾科技大學
電機工程研究所
102
This dissertation proposes an improved artificial bee colony (IABC) algorithm for designing a compensatory fuzzy logic controller (CLFC) in order to achieve an actual mobile robot wall-following task. During the wall-following task, the CFLC inputs measure the distance between the ultrasonic sensors and the wall, and the outputs of the CFLC are the robot''s left-wheel and right-wheel speeds. A cost function is defined to evaluate the performance of the CFLC in the wall-following task. The cost function includes three control factors (CF) which are defined as follows: maintaining a user-defined robot-wall distance, avoiding robot-wall collision, and ensuring that the robot can successfully negotiate the venue. The original artificial bee colony algorithm (ABC) simulates the intelligent foraging behavior of honey-bee swarms, which are good at exploration but poor at exploitation. An improved ABC algorithm, the IABC algorithm, is proposed that adopts the mutation strategies of differential evolution to balance exploration and exploitation. The IABC algorithm applies a new reward-based roulette wheel selection where an obtained a better solution by gains a reward during the learning stage. To demonstrate the performance of the IABC designed CFLC, the method was compared with other population-based algorithms with respect to the efficiency of the wall-following task. To demonstrate the feasibility of the design, experiments carried out on an actual mobile robot (PIONEER 3-DX) are included in this research.
17
Bui, Trong-Bac, and 裴仲北. "On New Techniques to Improve the Learning Efficiency of Multi-Objective Continuous ACO-based Fuzzy Controller for Robot Wall-Following Control." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/24443603752257881300.
Full textAbstract:
碩士國立中興大學
電機工程學系所
105
This thesis proposes two learning techniques to improve the learning efficiency of multi-objective evolutionary fuzzy systems (FSs) for mobile robot control. The first technique focuses on proposing a new multi-objective evolutionary optimization algorithm to improve FS optimization performance. An advanced multi-objective cooperative continuous ant colony optimization (ACO) with auxiliary colony optimization (AMO-CCACO) is proposed. In the AMO-CCACO algorithm, multiple sub-colonies are created, with each sub-colony optimizing only a single rule. An auxiliary colony is also generated to save the best so far N FSs. To evaluate the performance of a newly generated single rule, it is combined with other rules selected from the best FS in the auxiliary colony to create a full FS. The Pareto non-dominated sorting and the crowding distance algorithm are used to rank the performance of new fuzzy FSs with the original auxiliary colony. To increase the efficiency of AMO-CCACO, after update of the sub-colonies, the auxiliary colony also generates new complete FSs for update. The second technique is proposed to reduce the number of performance trials in the optimization process. In the proposed approach, a surrogate-assisted multi-objective ACO based on reinforcement neural fuzzy system (RNFS) is proposed. In this approach, the RNFS functions as a surrogate and is used to estimate the multi-objective function values of an FS without applying it to control a robot. The RNFS is online trained through reinforcement learning and temporal difference algorithms. Simulations and experiments are performed to verify the effectiveness and efficiency of the new approach.