To see the other types of publications on this topic, follow the link: Robot Soccer.
Dissertations / Theses on the topic 'Robot Soccer'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Robot Soccer.'
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
Graf, Birgit. "Robot soccer." [S.l.] : Universität Stuttgart , Fakultät Informatik, 1999. http://www.bsz-bw.de/cgi-bin/xvms.cgi?SWB7987414.
Full text
2
Holen, Vidar, and Audun Marøy. "Learning robot soccer with UCT." Thesis, Norwegian University of Science and Technology, Department of Computer and Information Science, 2008. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-9709.
Full textAbstract:
Upper Confidence bounds applied to Trees, or UCT, has shown promise for reinforcement learning problems in different kinds of games, but most of the work has been on turn based games and single agent scenarios. In this project we test the feasibility of using UCT in an action-filled multi-agent environment, namely the RoboCup simulated soccer league. Through a series of experiments we test both low level and high level approaches. We were forced to conclude that low level approaches are infeasible, and that while high level learning is possible, cooperative multi-agent planning did not emerge.
3
Kelsey, Jed M. "AUTONOMOUS SOCCER-PLAYING ROBOTS: A SENIOR DESIGN PROJECT." International Foundation for Telemetering, 1999. http://hdl.handle.net/10150/608518.
Full textAbstract:
International Telemetering Conference Proceedings / October 25-28, 1999 / Riviera Hotel and Convention Center, Las Vegas, NevadaThis paper describes the experiences and final design of one team in a senior design competition to build a soccer-playing robot. Each robot was required to operate autonomously under the remote control of a dedicated host computer via a wireless link. Each team designed and constructed a robot and wrote its control software. Certain components were made available to all teams. These components included wireless transmitters and receivers, microcontrollers, overhead cameras, image processing boards, and desktop computers. This paper describes the team’s hardware and software designs, problems they encountered, and lessons learned.
4
Johnson, Walter H., and Rob Franklin. "Effective Ball Handling and Control in Robot Soccer." International Foundation for Telemetering, 2002. http://hdl.handle.net/10150/606386.
Full textAbstract:
International Telemetering Conference Proceedings / October 21, 2002 / Town & Country Hotel and Conference Center, San Diego, CaliforniaAn autonomous soccer-playing robot was designed and constructed as part of the electrical engineering senior project at Brigham Young University. Unique physical features enable ball handling abilities. A front-side rotating drum retains the ball by applying backspin. A pneumatic kicker allows for fast accurate kicks. Robot movement control is performed by three different systems. The low-level velocity controller ensures output of desired forward and angular velocities. The position controller is used to match the robot's position with a desired position. Path generation directs the robot along a desired path at a specified velocity. The locations of the robots and ball on the soccer field is determined by the vision system. This document is a formal description of the unique designs and construction of the our team's robot.
5
Lei, Wai Ip. "A multi agents control approach to robot soccer competition." Thesis, University of Macau, 2004. http://umaclib3.umac.mo/record=b1446190.
Full text
6
Zhao, Hong Bin. "Real time control strategy towards the robot soccer system." Thesis, University of Macau, 2002. http://umaclib3.umac.mo/record=b1447842.
Full text
7
Thomas, Peter James, and p. thomas@cqu edu au. "Evolutionary Learning of Control and Strategies in Robot Soccer." Central Queensland University. School of Advanced Technologies and Processes, 2003. http://library-resources.cqu.edu.au./thesis/adt-QCQU/public/adt-QCQU20040628.153250.
Full textAbstract:
Robot soccer provides a fertile environment for the development of artificial intelligence techniques. Robot controls require high speed lower level reactive layers as well as higher level deliberative functions.
This thesis focuses on a number of aspects in the robot soccer arena. Topics covered include boundary avoidance strategies, vision detection and the application of evolutionary learning to find fuzzy controllers for the control of mobile robot.
A three input, two output controller using two angles and a distance as the input and producing two wheel velocity outputs, was developed using evolutionary learning. Current wheel velocities were excluded from the input. The controller produced was a coarse control permitting only either forward or reverse facing impact with the ball. A five input controller was developed which expanded upon the three input model by including the current wheel velocities as inputs. The controller allowed both forward and reverse facing impacts with the ball.
A five input hierarchical three layer model was developed to reduce the number of rules to be learnt by an evolutionary algorithm. Its performance was the same as the five input model.
Fuzzy clustering of evolved paths was limited by the information available from the paths. The information was sparse in many areas and did not produce a controller that could be used to control the robots.
Research was also conducted on the derivation of simple obstacle avoidance strategies for robot soccer. A new decision region method for colour detection in the UV colour map to enable better detection of the robots using an overhead vision system. Experimental observations are given.
8
Olson, Steven A. R., Chad S. Dawson, and Jared Jacobson. "DESIGN AND DEVELOPMENT OF AN AUTONOMOUS SOCCER-PLAYING ROBOT." International Foundation for Telemetering, 2002. http://hdl.handle.net/10150/607517.
Full textAbstract:
International Telemetering Conference Proceedings / October 21, 2002 / Town & Country Hotel and Conference Center, San Diego, CaliforniaThis paper describes the construction of an autonomous soccer playing robot as part of a senior design project at Brigham Young University. Each participating team designed and built a robot to compete in an annual tournament. To accomplish this, each team had access to images received from a camera placed above a soccer field. The creation of image processing and artificial intelligence software were required to allow the robot to perform against other robots in a one-on-one competition. Each participating team was given resources to accomplish this project. This paper contains a summary of the experiences gained by team members and also a description of the key components created for the robot named Prometheus to compete and win the annual tournament.
9
Peel, Andrew Gregory. "On designing a mobile robot for robocup /." Connect to thesis, 2006. http://eprints.unimelb.edu.au/archive/00003101.
Full text
10
Ros, Espinoza Raquel. "Action Selection in Cooperative Robot Soccer using Case-Based Reasoning." Doctoral thesis, Universitat Autònoma de Barcelona, 2008. http://hdl.handle.net/10803/5783.
Full textAbstract:
La tasca de dissenyar el mecanisme de presa de decisions d'un equip de robots és un gran repte, no només per la complexitat de l'entorn en el qual els robots realitzen les seves tasques, que comporta incertesa, dinamicitat i imprecisió, sinó també perquè la coordinació entre els robots s'ha de tenir en compte a l'hora de dissenyar el mecanisme. Els robots han de ser conscients de les accions dels altres robots per tal de cooperar i assolir satisfactòriament els objectius de l'equip. Aquesta tesi doctoral presenta una novedosa aproximació basada en casos per la selecció d'accions i la coordinació de tasques cooperatives en equips de robots. Aquesta aproximació s'ha aplicat i avaluat en un domini molt representatiu, com és el del futbol robòtic, tot i que les idees presentades són aplicables a altres dominis com les operacions de rescat, l'exploració d'entorns desconeguts i la vigilància submarina, entre d'altres.
El procés de selecció proposa un cas per reutilitzar, avaluant els casos candidats amb una sèrie de criteris per tal de tenir en compte les característiques d'un entorn real, incloent-hi la presència d'adversaris, que és un factor clau en el domini del futbol robòtic. A diferència dels sistemes de raonament basats en casos clàssics, la reutilització del cas consisteix en l'execució d'un conjunt d'accions per part d'un equip de robots. Per tant, des de la perspectiva multi- robot, el sistema ha d'incloure un mecanisme per tal de decidir qui fa què i com. En aquesta tesi, es presenta una arquitectura multi-robot juntament amb un mecanisme de coordinació per tal d'atacar aquests reptes.
Hem validat experimentalment l'aproximació tant en simulació com amb robots reals. L'experimentació ha permès comprovar que l'aproximació presentada assoleix els objectius de la tesi, és a dir, el disseny de comportaments d'un equip de robots cooperatius. Així mateix, els resultats obtinguts també mostren els avantatges d'utilitzar una estratègia col·laborativa en entorns en els quals el component adversari juga un paper important, en contrast amb comportaments individualistes.
Designing the decision-making engine of a team of robots is a challenging task, not only due to the complexity of the environment where the robots usually perform their task, which include uncertainty, dynamism and imprecision, but also because the coordination of the team must be included in this design. The robots must be aware of other robots' actions to cooperate and to successfully achieve their common goal. Besides, decisions must be made in real-time and with limited computational resources.
This thesis contributes a novel case-based approach for action selection and coordination in joint multi-robot tasks in real environments. This approach has been applied and evaluated in the representative domain of robot soccer, although the ideas presented are applicable to domains such as disaster rescue operations, exploration of unknown environments and underwater surveillance, among others.
The retrieval process proposes a case to reuse, evaluating the candidate cases through different measures to overcome the real world characteristics, including the adversarial component which is a key ingredient in the robot soccer domain. Unlike classical case- based reasoning engines, the case reuse consists in the execution of a set of actions through a team of robots. Therefore, from the multi- robot perspective, the system has to include a mechanism for deciding who does what and how. In this thesis, we propose a multi- robot architecture along with a coordination mechanism to address these issues.
We have validated the approach experimentally both in a simulated environment and with real robots. The results showed that our approach achieves the expected goals of the thesis, i.e. designing the behavior of a cooperative team of robots. Moreover, the experimentation also showed the advantages of using collaborative strategies in contrast to individualistic ones, where the adversarial component plays an important role.
11
Johansson, John. "An Electric Field Approach : A Strategy for Sony Four-Legged Robot Soccer." Thesis, Blekinge Tekniska Högskola, Institutionen för programvaruteknik och datavetenskap, 2001. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4971.
Full textAbstract:
Using physical analogies when solving computational problems is not uncommon. The Electric Field Approach is such an analogy using potential fields for describing the situation in a robotic soccer match and for proposing the next step in optimizing the situation. The approach was developed and implemented during the summer of 2000 and was later used and tested during the fourth Robot Soccer World Cup in Melbourne, Australia. The results of the games prove that the approach is applicable in this narrow but interesting domain, combining artificial intelligence and robotics. The theory of the approach is general and can also be applied on various other domains. This is not the first potential field approach, but the ability of both handling navigation and manipulation of the environment is unique.
12
Levesque, Sally-Ann. "Omnidirectional robotic platform : the control of an omnidirectional robotic platform for use in robot soccer." Master's thesis, University of Cape Town, 2008. http://hdl.handle.net/11427/5518.
Full textAbstract:
Includes abstract.Includes bibliographical references.
The University of Cape Town competes in a national robot soccer competition. Teams of five small robots compete in the game of soccer without any human intervention. The robots are controlled by the artificial intelligence on a host computer connected to an overhead imaging system. The host computer controls the robots by sending them instructions via wireless communications. The robot soccer platform calls for the integration of electronic, mechanical and computer technologies and provides an exciting area for research. UCT first competed in the robot soccer competition in 2003, using differential drive robots designed by Graeme McPhillips. Research has shown that in the international robot soccer competition, teams are replacing their differential drive robots with omnidirectional robots – robots which can move in any direction without first changing their orientation to face the direction of motion. These robots have proved to be highly manoeuvrable and the winning teams in the small robot league are consistently those that use omnidirectional robots. In 2004, Craig Inman-Bamber designed and implemented UCT’s first omnidirectional robot platform. It is this platform that this dissertation is concerned with controlling. Electronic components were designed and implemented and software code written to control the robot in an omnidirectional manner.
13
Aronsson, Claes. "Evolution of Neural Controllers for Robot Teams." Thesis, University of Skövde, Department of Computer Science, 2002. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-732.
Full textAbstract:
This dissertation evaluates evolutionary methods for evolving cooperative teams of robots. Cooperative robotics is a challenging research area in the field of artificial intelligence. Individual and autonomous robots may by cooperation enhance their performance compared to what they can achieve separately. The challenge of cooperative robotics is that performance relies on interactions between robots. The interactions are not always fully understood, which makes the designing process of hardware and software systems complex. Robotic soccer, such as the RoboCup competitions, offers an unpredictable dynamical environment for competing robot teams that encourages research of these complexities. Instead of trying to solve these problems by designing and implement the behavior, the robots can learn how to behave by evolutionary methods. For this reason, this dissertation evaluates evolution of neural controllers for a team of two robots in a competitive soccer environment. The idea is that evolutionary methods may be a solution to the complexities of creating cooperative robots. The methods used in the experiments are influenced by research of evolutionary algorithms with single autonomous robots and on robotic soccer. The results show that robot teams can evolve to a form of cooperative behavior with simple reactive behavior by relying on self-adaptation with little supervision and human interference.
14
Cruz, Luís Miranda. "Humanoid Robot NAO : developing behaviours for soccer humanoid robots." Master's thesis, 2011. http://hdl.handle.net/10216/61272.
Full text
15
Cruz, Luís Miranda. "Humanoid Robot NAO : developing behaviours for soccer humanoid robots." Dissertação, 2011. http://hdl.handle.net/10216/61272.
Full text
16
Wu, Chih-En, and 吳之恩. "ROS-based Soccer Robot Strategy System." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/shg2p3.
Full textAbstract:
碩士淡江大學
電機工程學系碩士班
103
In this paper, we built a soccer robot strategy system that is based on Robot Operating System (ROS). The soccer robot strategy system is capable with FIRA RoboSot competition rule. Nowadays, the development of a robot software system became more and more complex. Developers of robot software system may not have very well knowledge about computer science field. So this paper proposes a soccer robot software system based on ROS that we can use tools of ROS to help and develop the strategy system, like actionlib package, SMACH package, tf package, etc. The system architecture of ROS is a distributed system. The ROS uses peer-to-peer network to link all processes to exchange data. Due to this kind of architecture, we can parallel process data and divide the work easily. The soccer robot strategy system we proposed is including a world model package, strategy package and trajectory package. About strategy package, we used dynamic role assignment. About world package, we used tf module to manage axes of objects. And the trajectory package is used to path planning and velocity planning. So the robot can change role dynamically in a game. Finally, we built a 3D simulation environment in Gazebo simulator to verify the soccer robot strategy system.
17
Hsu, Yi-Chung, and 許藝鐘. "Research of Robot Soccer Simulation System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/mdjmpu.
Full textAbstract:
碩士南台科技大學
電機工程系
97
This thesis mainly discusses the strategies of the soccer robots and designs the planning of obstacle avoidance, and the corresponding routes. We propose a method using assign roles-rules to assign roles and jobs to the robots swiftly. Among these, assign roles rules decides the role and job of the robot according to the distance and angle for reaching the goal. At the aspect of attacking, we will propose a shot-at-the-goal mode and obstacle avoidance to help the robots belonging to our team to score. Regarding the planning of obstacle avoidance, we address a scheme with ant colony algorithm to design the optimal route of soccer robot. Finally, we add average algorithm control to assist our robots to predict the nextpositions or movements of the target to make the whole strategy more flawless.
18
"An automated internet-based robot soccer system." 2011. http://library.cuhk.edu.hk/record=b5894524.
Full textAbstract:
Long, Qiaoxi.Thesis (M.Phil.)--Chinese University of Hong Kong, 2011.
Includes bibliographical references.
Abstracts in English and Chinese.
Abstract --- p.2
摘要 --- p.3
Table of Contents --- p.4
Acknowledgements --- p.6
List of Figures --- p.7
List of Tables --- p.9
Chapter Chapter 1 --- Introduction --- p.10
Chapter 1.1 --- Robot Soccer --- p.10
Chapter 1.2 --- IRIP and IRIS --- p.11
Chapter 1.3 --- Motivation and Literature Review --- p.14
Chapter 1.4 --- Technical issues and Contributions --- p.15
Chapter 1.5 --- Thesis Outline --- p.16
Chapter Chapter 2 --- The IRIS system --- p.17
Chapter 2.1 --- Hardware setup --- p.17
Chapter 2.2 --- Software architecture --- p.21
Chapter Chapter 3 --- Internet Accessibility --- p.26
Chapter Chapter 4 --- Auto-charging --- p.32
Chapter 4.1 --- Hardware setup --- p.33
Chapter 4.2 --- Communication --- p.36
Chapter 4.3 --- Vision --- p.41
Chapter 4.4 --- Motion control --- p.44
Chapter 4.4.1 --- APF --- p.44
Chapter 4.4.2 --- CRC --- p.50
Chapter 4.5 --- Processing Schemes --- p.51
Chapter Chapter 5 --- Auto-Scoring and Auto-Judging --- p.56
Chapter 5.1 --- Auto-scoring --- p.56
Chapter 5.2 --- Auto-judging --- p.57
Chapter 5.3 --- Judge robot --- p.59
Chapter Chapter 6 --- Experimental Results --- p.63
Chapter Chapter 7 --- Conclusions --- p.69
Chapter 7.1 --- Summary --- p.69
Chapter 7.2 --- Future work --- p.70
Appendix A --- p.72
Bibliography --- p.73
19
Yang, Cheng-Hsun, and 楊政勳. "Design of path planning for robot soccer." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/64y43t.
Full textAbstract:
碩士國立臺北科技大學
自動化科技研究所
100
This thesis focuses on path planning for a robot soccer game. In a soccer game, path planning helps a robot go toward a ball. Conventional path-planning methods use sensors to make a robot avoid obstacles and then achieve a goal. However, path-planning methods based on obstacle avoidance are slow and problematic because robots on a soccer field using sensors to avoid obstacles might be toward to the same direction. Thus, a fast path-planning method is important to a robot soccer game. This work uses the rapidly-exploring random tree (RRT) algorithm to provide fast path planning and enhances it to derive a shorter path than the basic RRT algorithm. The enhanced RRT algorithm makes the path generated by the basic RRT algorithm smooth and adapts the planned path to avoid dynamic obstacles. Accordingly, the proposed method for path planning in a soccer game is competitive. In the simulation results, this work demonstrates the capability of path planning for dynamic obstacles and compares with several common path-planning methods. The results show that the proposed method is generally superior to the other methods in distance and spent time. Particularly, the proposed method provides a shorter path than the RRT method adopted in B-human team, the RoboCup 2011 champion.
20
Liang, Chao-Chiun, and 梁兆鈞. "Development of A Muliple-Soccer-Robot System." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/51093387653694671489.
Full textAbstract:
博士國立臺灣大學
機械工程學研究所
88
Development of A Multiple-Soccer-Robot System Abstract Multiple robots can cooperatively achieve such tasks that are difficult or even impossible for a single robot. The coordination of multiple robots increases the flexi-bility and robustness of the system at the expense of increasing the complexity of performing tasks. Although multiple-robot systems can achieve very complicated co-operative tasks in determinate and static environments, they cannot work effectively in unknown and dynamic circumstances. In order to dynamically cooperate multiple robots, this dissertation developed a multiple-soccer-robot system --- NTU-Formosa. The objective is to make multiple robots work efficiently in an unknown and dynamic environment. The main aspects of this dissertation are derivation and analysis of soc-cer dynamics, construction of motion control systems of soccer robots, design of soc-cer strategies, and development of decision-making systems. For better understanding the behaviors of the ball and robots in a robot soccer game, this dissertation derived and analyzed the free motion dynamics of the robots and ball and the collision dynamics among them. The derived dynamics are useful for the computer simulation of a robot soccer game, the development of soccer strategies, and the designs of the mechanism and controllers of soccer robots. To well understand the status in a soccer game, this study proposed the concept “attack angle” to describe the dynamics of the soccer games. Based on the attack angles of the soccer games, most powerful game strategies can be understood, designed, and programmed. Based on the structure of Cerebellar Model Articulation Controllers (CMAC), this dissertation proposed a self-organizing fuzzy CMAC aiming at the motion control of soccer robots. The objective is to control the soccer robots to track the planned tra-jectories in the unknown and dynamic environment of a robot soccer game. Among the numerous models of neural networks, CMAC may be the model with the best real-time capability. It is a controller developed to mimic the structure and functions of human cerebellum. The characteristics of fast learning and convergence make CMAC a real-time controller. There are many successful applications of CMAC in real-time control of manipulators. For the sake of its structure, CMAC has a limitation in its input resolution. For practical applications, CMAC uses some method to reduce the required memory space. This causes some troubles in the learning process of CMAC, and hence reduces its performance. This dissertation developed a fuzzy CMAC to solve these problems. The proposed fuzzy CMAC uses fuzzification at its input to increase its input resolution and effectively compress the input data. This can naturally reduce the required memory space and the troubles in the learning process. The learning law of traditional CMAC is supervised. This is not suitable for the soc-cer robot control and other applications where the desired output of CMAC is un-known. Therefore, it is necessary to extend the learning law of CMAC to unsuper-vised learning. To fulfill this requirement, this dissertation proposed a self-organizing fuzzy CMAC: Model-based Fuzzy CMAC (MFCMAC). It performs an on-line model-identification, then uses the result to calculate the required modification for the output of MFCMAC, and adjusts its weights to obtain the desired solution. MFCMAC was applied to the control of a mobile robot to track the planned trajectories. In sev-eral experiments of tracking various trajectories, MFCMAC is significantly superior to the traditional PID controller. In order to cope with the various situations in robot soccer games, this disserta-tion developed a set of soccer strategies based on soccer dynamics. A strategy-based flexible decision-making system was proposed to choose among the developed strate-gies according to the situation of the soccer field. It then performs centralized coordi-nation control to coordinate the multiple mobile robots to play a soccer game in ac-cordance with the adopted strategies. Through simulations and experiments, NTU-Formosa exhibits satisfactory performance in cooperative and competitive tasks of multiple mobile robots. Based on the proposed attack angle, the soccer strategies can well handle the situations and opportunities in a robot soccer game. To fast and flexibly decide effective soccer strategies, the proposed decision-making system is implemented using decision trees. The advantages of traditional decision trees are simple, apparent and fast reasoning. However, traditional decision trees need to hold considerable data in each of its non-terminal node. This increases the required mem-ory space and computation time. This dissertation proposed a fuzzy decision tree to overcome this drawback. Under the structure of decision trees, the proposed fuzzy decision tree uses fuzzy statistics to calculate fuzzy sets for representing and com-pressing the training data in order to save computation memory and increase tree-generation speed. A clustering technique and a sub-optimal splitting criterion are then used to generate a decision tree from the resultant fuzzy sets. The proposed fuzzy decision trees not only keep the advantages of traditional decision trees but also have much faster learning speed. Traditional decision trees have another feature of batch learning: learn all the training data at a time to generate the desired decision tree. This feature is another disadvantage. To conquer this disadvantage, this dissertation pro-posed a self-organizing fuzzy decision tree. According to the recognition results, it can real-time tune its parameters and adapt its structure to reflect the change in any part of the training data. To analyze their performance, the proposed fuzzy decision trees are mapped into function-equivalent rule-based systems and multi-layer percep-trons and their performance are compared. The results revealed that the proposed fuzzy decision trees indeed have some advantages over rule-based systems and multi-layer perceptrons.
21
Fu, Wei-Kang, and 傅為剛. "Keyframe Detection for Multi-robot Simultaneous Localizationand Tracking in Robot Soccer Scenario." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/43u9rg.
Full textAbstract:
碩士國立臺灣大學
資訊工程學研究所
106
The algorithm of multi-robot cooperative localization has become more and more powerful. However, it is needed to consider the limited computing resources and network resources in implementation. Therefore, in order to reduce the use of redundant information, many studies make use keyframe detection to measure the importance of information before localization process. In robot soccer scenario, we adopt multi-robot cooperative localization and tracking, or MR-SLAT, which can provide good localization result under stable communication situation. But, in the measurement update step, the number of measurements sharing among robots can cause significant overhead to the system. Existing keyframe detection solutions against image content can be mainly classified into two categories, color-based and feature-based. Color-based approaches execute efficiently, but they lose the spacing information of interested objects. Feature-based approaches provide more robust performance but spend more computational cost for extracting features. This thesis base on the MR-SLAT framework and propose a keyframe selection mechanism as a preprocessing for MR-SLAT. We design an utility function based on Shannon Entropy to provide a mechanism for calculating the utility of measurements. The proposed utility function, without the use of feature points, measure low-level data including moving objects and stationary objects which are extracted from an image. The experimental results show that, our method can detect the change of scene. In localization experiment, the trajectory of localization can be significantly improved for up to 3x from odometry by using 25% of image data. when the trajectory error ratio between using all frames and odometry is close to 1, the best performance of the keyframe-based localization system is about 85% of by using all frames.
22
Yen-Hsun, Wu. "Development of a Global Vision Soccer Robot System." 2005. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-1506200515163800.
Full text
23
Chen, Yu-Huai, and 陳堉淮. "Development of Visual Servoing System for Robot Soccer." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/42918049557742197634.
Full textAbstract:
碩士國立雲林科技大學
電機工程系碩士班
89
A system of a soccer robot visual servoing is developed in this thesis. This thesis is composed of four parts: (1)hardware structure of visual servoing system, (2) software implementation, (3)color distribution modeling and (4)adaptive feature color search algorithm . The main purpose of the vision system is to exact the 2D position data of the players, ball and the filed goals. These data are used in the decision system for planning the strategy of the game. The procedure executed by the vision system consists of the following steps: (1) Build the color distribution model for each chosen target. (2) Use the model parameters to set up the threshold value for searching. (3) Calculate the position and velocity of the searched target. (4) Pass the position velocity data to decision system. When lighting condition of the environment is stable, the above algorithm can easily find all the targets. However, the variation of illumination conditions and the ambient lighting can change the color distribution and cause the failure of target searching. In this study, we present an algorithm for adaptive feature color modeling to deal with this problem and increase the robustness of the search algorithm.
24
Wu, Yen-Hsun, and 吳彥勳. "Development of a Global Vision Soccer Robot System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/27177741609953003716.
Full textAbstract:
碩士國立臺灣大學
機械工程學研究所
93
Wide range of technologies are integrated, developed and implemented in the global vision soccer robot system. This thesis is involved in three of them: Color object recognition and tracking, wheeled mobile robot control, and multi-agent collaboration. The task of global vision module is to extract meaningful data for strategy decision module. These data are reliable and accurate for efficient tactics planning. Robust color classification plays a dramatic role for color-based image analysis. In addition, appropriate color classification reduces computational time and improves reliability by eliminating uninterested background information. Principal Component Analysis (PCA) is adopted to seek for a color space in which a color classification model is constructed straightforward. According to this model, slight color variation is robustly classified. Based on extracted data, the decision-making module estimates the field condition, and then plans strategies to collaborate agents. Role assignment enormously affects the efficiency of plan achievement. A bottom-up strategy generation mechanism simplifies the procedure to create strategies for highly dynamical environment. Dynamic feedback linearization control is adopted for the mobile robot’s motion control. The performance is good enough for robot to dribble the ball and score goal. The entire system has been completely implemented, and won the first place of 2004 National Competition of Soccer Robots.
25
Luo, Shi-Chao, and 羅勢超. "DESIGN AND IMPLEMENTATION OF OMNI-DIRECTIONOAL SOCCER ROBOT." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/07558893585296757253.
Full textAbstract:
碩士龍華科技大學
電子系碩士班
93
Mobility of mobile robots is a vital factor of competition for playing soccer in RoboCup. In this paper, omni-directional soccer robots are designed and implementated for the small-size league of RoboCup. In mechanism, it provides not only an omni-directional drive device for holonomic mobility, but also includes dribbler and kicker device, in order to enhance robot’s holding and passing ability in the game. In system, we use MC68332 as system core, and design a microprocessor control system for the omni-directional soccer robot. According to control circuit, we design a series of program function to integrate a control system that can manipulate control robot’s motion behavior. Finally, experiments are aimed to reveal characteristics of the omni-directional soccer robot for promoting control performance.
26
Yang, Chun-Ming, and 楊駿明. "Development of a Middle Size Robot Soccer System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/94616553970010116515.
Full textAbstract:
碩士長庚大學
機械工程研究所
93
This work proposes the hands-on implementations of the “Formosa middle size soccer robot”, which is developed based on the intelligent vision fusion sensing architecture. The proposed autonomous soccer robot consists of the mechanical platform, motion control module, “MapCam360” omni-directional vision module, front vision module, image processing and recognition module, investigated target object positioning and real coordinate reconstruction, robot path planning, subgoal definition and competition strategies. Especially, in order to increase the robustness of the vision sensing, the catadioptric omni-directional and front vision modules are dynamically switched according to the ball recognition results of the omni-directional camera. The previous mentioned hardware and software modules and components are all integrated, and the control modes are fused based on the relationships among the positions of the enemy robot, ball, goal, and field boundaries. In order to increase the motility and attackability, we design the dribbling and kicking mechanisms. In addition, the PC-based soccer robot controller is developed based on the embedded Linux platform. The motion control uses the Mitsubishi AC-servo motors and controllers to achieve higher reliability. Finally, the physical robot had been finished and tested, and we also validate the functional performance.
27
Chou, Ming-Fong, and 周明豐. "Design of Robot Soccer Using the DSP-Controller." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/85618600454303775574.
Full textAbstract:
碩士淡江大學
電機工程學系
89
In this thesis, the hardware architecture of the robot soccer system is accomplished and one algorithm for path planning of robot soccer is proposed. By this procedure, a mode of sport action, like human behavior on soccer field, is developed. The following four parts of the robot soccer system are considered: (1) Robot Soccer (RoboDSP for short), (2) Global vision system, (3) Host computer and (4) Wireless communication system. First, a global vision of image is captured by a digital video camera placed above the field. After image processing and path planning of the host computer, the coordinates among the robot soccer, obstacle, and ball are extracted. Then the rotational angle which the robot soccer avoids obstacle is calculated by Fuzzy-Obstacle-Avoidance-Path algorithm (FOAP algorithm). Once the rotational angle is determined, the commands are transmitted to the robot soccer by a wireless radio modem. Finally, based on the received commands, the TI TMS320F240 DSP implemented in the robot soccer is designed to control the motion of the robot soccer to avoid the obstacle to the ball. This thesis uses the TI TMS320F240 digit signal processor (DSP), which produced by Texas Instrument, as controller core of robot soccer and designs one-on-one robot soccer game. This real-time experiment is considered to illustrate the effectiveness and applicability of the Fuzzy-Obstacle-Avoidance-Path algorithm.
28
Po-Chang, Yu, and 俞伯璋. "Design of Fuzzy Controllers in Robot Soccer Systems." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/00887250178313934527.
Full textAbstract:
碩士國立中興大學
電機工程學系
91
This thesis develops methodologies and techniques for the design of fuzzy controllers to make soccer robots complete certain specific behaviors. In order to equip the soccer robots with the ability of shooting, intercepting, blocking, sweeping, and standing by, a path planning method using Hermite polynomials is proposed. The parameters in the fuzzy controller are designed with the genetic algorithm. The fitness function in the genetic algorithm is designed to reflect the fact that a good fuzzy controller can make soccer robots follow the path rapidly and exactly. Simulation results are included for illustrating the feasibility of the fuzzy controller design.
29
He, Yuchen. "Localization using natural landmarks off-field for robot soccer." Thesis, 2013. http://hdl.handle.net/2152/24333.
Full textAbstract:
Localization is an important problem that must be resolved in order for a robot to make an estimation of its location based on observation and odometry updates. Relying on artificial landmarks such as the lines, circles, and goalposts in the robot soccer domain, current robot localization requires prior knowledge and suffers from uncertainty problems due to partial observation, and thus is less generalizable compared to human beings, who refer to their surroundings for complimentary information. To improve the certainty of the localization model, we propose a framework that recognizes orientation by actively using natural landmarks from the off-field surroundings, extracting these visual features from raw images. Our approach involves identifying visual features and natural landmarks, training with localization information to understand the surroundings, and prediction based on matching of features. This approach can increase the precision of robot orientation and improve localization accuracy by eliminating uncertain hypotheses, and in addition, it is also a general approach that can be extended and applied to other localization problems as well.text
30
Chen, Chun-Hsu, and 陳俊旭. "Strategy and Path Design in the Robot Soccer Simulation." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/96516792078182387649.
Full textAbstract:
碩士南台科技大學
電機工程系
99
This thesis focuses on the design of robot soccer strategies, particularly in the task assignment and path design. In this thesis, we use fuzzy controllers to determine the task assignment and action mode for each robot. Based on the distance and angle between the robot and the target, the fuzzy controller assigns the task of each robot and controls the movement of robot wheels. On task assignment, we propose shooting mode and obstacle avoidance mode to improve scoring rate for our robot. On the path planning, novel genetic-particle swarm optimization (GPSO) algorithm was adopted to adjust our robot path and to seek the balance between the optimal path and speed. Finally, we demonstrate the efficacy of our design in FIRA simulation platform
31
Yang, Wang Kuo, and 王國揚. "Strategy and Path Design in the Robot Soccer Simulation." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/71177392977520556649.
Full textAbstract:
碩士南台科技大學
電機工程系
95
This paper mainly discusses the strategies of the soccer robots and the design and research of the routes. We propose the method using fuzzy control to distribute every role and job to the robot rapidly. Among this, fuzzy controller decides the role and job of the robot according to the distance and angle for reaching the goal. At the aspect of strategy, we will propose a shot-at-the-goal mode and obstacle avoidance to help the robots belonging to us to score. And the planning of the route, we address a scheme with support vector machine to emend the route of our robots and then using the same way to amend the optimal speed of our robots to reach the goal. Finally, we add general predictive control to assist our robot to anticipate the next position or movement of the target to make the whole strategy more flawless.
32
(9839792), Peter Thomas. "Evolutionary learning of control and strategies in robot soccer." Thesis, 2003. https://figshare.com/articles/thesis/Evolutionary_learning_of_control_and_strategies_in_robot_soccer/13423691.
Full textAbstract:
"Robot soccer provides a fertile environment for the development of artificial intelligence techniques. Robot controls require high speed lower level reactive layers as well as higher level deliberative functions. This thesis focuses on a number of aspects in the robot soccer arena. Topics covered include boundary avoidance strategies, vision detection and the application of evolutionary learning to find fuzzy controllers for the control of mobile robot. A three input, two output controller using two angles and a distance as the input and producing two wheel velocity outputs, was developed using evolutionary learning. Current wheel velocities were excluded from the input. The controller produced was a coarse control permitting only either forward or reverse facing impact with the ball. A five input controller was developed which expanded upon the three input model by including the current wheel velocities as inputs. The controller allowed both forward and reverse facing impacts with the ball. A five input hierarchical three layer model was developed to reduce the number of rules to be learnt by an evolutionary algorithm. Its performance was the same as the five input model. Fuzzy clustering of evolved paths was limited by the information available from the paths. The information was sparse in many areas and did not produce a controller that could be used to control the robots. Research was also conducted on the derivation of simple obstacle avoidance strategies for robot soccer. A new decision region method for colour detection in the UV colour map to enable better detection of the robots using an overhead vision system. Experimental observations are given." -- abstract.
33
Nien-ChuFang and 方念主. "Multi-Robot Coordination Strategy for 3 vs. 3 Teen-sized Humanoid Robot Soccer Game." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/z5yn56.
Full textAbstract:
碩士國立成功大學
電機工程學系
105
Robot competitions are always good platforms for researchers to test and compete their robot systems and algorithms. For the humanoid robot soccer game, any active sensor are prohibited according to the premise of “human-like”. The robot has to plan gaits and maintain balance during moving or kicking a ball to complete the competition. However, with the progress of robot development, multiple-robot coordination and cooperation becomes more and more important. Therefore, this thesis proposes a multi-robot coordination strategy system concerning 3 vs. 3 teen-sized humanoid robot soccer game. Three main technologies are integrated in the system, including object recognition and self-localization, communication, and coordination strategy. Because the line, ball, and goal posts are colored white, we utilize the contour features to recognize them and calculate their positions in robot coordinate. Hence, suppose the robot position in the world coordinate is known, the position of the line, ball, and goal posts in world coordinate can be determined. We figure out the initial position of the robot and update the position by the value of the Inertial Measurement Unit (IMU) and the estimated movement distance. Every robot transmits its location and his own information to the central control player through a communication network to construct a global map used to generate a suitable strategy and to assign roles. A simulation software is constructed in this thesis according to the characteristics of the real robot player and real competitions. After that, experiments show the strategy is effective on humanoid robots. These results illustrate the efficiency of the proposed coordination strategy, where the robot soccer team with the coordination strategy gets more wins.
34
CHEN, YI-ZHANG, and 陳奕璋. "Application of Cooperative Robots Based on Distributed Intelligence – in Three-on-Three Soccer Robot Competition." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/3uhcva.
Full textAbstract:
碩士世新大學
資訊管理學研究所(含碩專班)
106
This research focused on how to apply distributed intelligence to cooperative robots such that the learned robots can efficiently perform on the three-on-three robot soccer competition. First, the distributed intelligence algorithm, based on reinforcement learning, was derived for primitive actions and complicated behaviors of cooperative robots. Then, the application of distributed intelligence in three-on-three robot soccer competition was conducted by weighted behavior Q-Learning approach. Finally, to validate the proposed learning approach of distributed intelligence, computer programs were developed to simulate the three-on-three robot soccer competition.
35
Liu, Ren-Cheng, and 劉人誠. "Implementation of Fuzzy Shooting Control for Car-Type Soccer Robot." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/19085116182948049452.
Full textAbstract:
碩士國立成功大學
電機工程學系
88
This thesis is devoted to design and implement a fuzzy controller for the soccer robot shooting action. The control object is that the host computer sends command to soccer robot through wireless modem. In the same time, the microcomputer mounted on the soccer robot will get the suitable performance based on the instructions from the host computer. First, we will introduce the structure of robot soccer game and then describe the architecture of the soccer robot, the image processing system, and the wireless communication system. All the hardware arrangements of the system are introduced in detail in this thesis. Two different shooting control actions are proposed. Finally, both simulations and the practical experiments demonstrate the feasibility and effectiveness of the investigated schemes. Real-time experiments are also recorded in the videotape.
36
Te-KaiWang and 王德凱. "Design and Implementation of Double Passing Strategy forHumanoid Soccer Robot." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/54831048422433592862.
Full textAbstract:
碩士國立成功大學
電機工程學系碩博士班
98
The goal of this thesis is to achieve a technical challenge of double passing soccer game for humanoid soccer robots in RoboCup competition. There are many topics involved in order to finish the entire procedure, such as image processing algorithms, motion control, localization, and a proper scheme of strategy system. The development of vision and strategy system is mainly concerned in this thesis. The image information is captured by a CMOS sensor and then the image data are processed by an embedded CPU board Pico-820. Vision system works on the tasks of object recognition, which includes the goal, landmark poles and the interval of two black poles. A fast object segmentation method in the image with the need of only one execution loop is used to make the recognition more efficient. After recognitions, a simple mean shift algorithm is adopted to further improve the efficiency and performance of vision system. The computational time is reduced greatly by the algorithm and that time can be utilized to do the localization or control strategies. The strategies of double passing of each robot player are illustrated in flowcharts and the communication between them is via wireless network. The strategies of some more detailed situation are also discussed. All the strategies are also processed in Pico-820. Overall functions of vision and strategy system are programmed in C++. Finally, the experiment results demonstrate that the proposed vision and control strategy system can successfully perform the double passing soccer game.
37
Huang, Wei-Sung, and 黃偉菘. "Real-Time Vision Sytem for Small Size League Robot Soccer." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/06734633042139108569.
Full textAbstract:
碩士國立中正大學
電機工程研究所
92
RoboCup is a game for small sized robots to complete against other teams in a game of soccer. In the small size league, the movement of the robots are managed by the strategy of the robot soccer system. Real-time visual information provided by the cameras and dynamic image analysis are usually required for the strategy system to make a decision on the movement of the robots. The goal of this work is to to develop a real-time vision system for the small size robot league. Developing such system requires high quality input images, robust and fast running functions, and careful memory allocation. In this work, a digital video camera with IEEE 1394 interface is used for image acquisition, instead of analog data transmission with frame grabber, to ensure the quality and reliability of the image data. Robust object identification and tracking algorithms are implemented in HSV color space. The video camera is also calibrated to reduce the radial distortion caused by wide-lens imaging. Experimental results have shown that our real-time vision system is able to provide accurate and stable tracking of multiple objects at the frame rate of 30 fps.
38
Lin, Ying Hom, and 林英宏. "Study on Dynamic Prediction Based Autonomous Soccer Robot Behavior Control." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/53598453124735472646.
Full textAbstract:
碩士長庚大學
機械工程研究所
94
Middle size soccer robot is a real time and dynamic control system, and it is capable of dealing with complicated competition environment in terms of advanced artificial intelligence. In general, the middle size soccer robot is composed of the modules of the vision, path planning, motion control, and mechanical and driving robot body. In this work, the kinematics and dynamics of ball and robot are modeled to assist the fuzzy based decision system. In this manner, the decision of robot path planning is inferred from static ball location to the dynamically estimated ball path. Consequently, the proposed decision system is capable of predicting ball motion and then deciding the kick location, velocity and direction. Therefore, the robot moves towards the desired kick location instead of the current ball location. On the other hand, the omni-based image system acts as the position module. To propose a more precise positioning system, a zone-dependent multi-curve omni-vision regression algorithm is proposed in this work. Based on the proposed omni-vision regression algorithm, the bias of installing anamorphoscope and the complicated curve function of anamorphoscope can be dealt with as well. Finally, this thesis proposes a high precision omni-vision positioning methodology and a prediction based motion planning algorithm for the moving ball, and these approaches improve the performance of motion decision system in real competition environment.
39
Dan, Jui-Cheng, and 旦瑞誠. "Strategy Design in the Five-to-Five Robot Soccer Simulator." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/49347382899348791042.
Full textAbstract:
碩士淡江大學
電機工程學系
90
In this thesis, how to design efficient strategies on the platform of FIRA’s 3D robot soccer simulator in a five-to-five robot soccer game is discussed and proposed. First, the simulator and the language of the simulator-Lingo are introduced in detail. Then, three basic motions: obstacle avoidance, shooting, and pass are designed for robot soccer players by using the Lingo language. In the obstacle avoidance, the best path is chosen according to the determination of path node around the obstacle when obstacles obstruct the straight path between the robot and goal. The choice of path node is based on two conditions: obstacle-free and the shortest path to goal. The best path is updated real-time and the obstacle avoidance is achieved in a dynamic environment. In the shooting, a method is proposed for any initial positions of ball, goal, and robots such that it always let the robot toward the direction of ball to goal when the robot reaches the shot position. In the pass action, two robots are considered to execute this motion. One robot that passes ball to the other robot is considered to execute the shooting action. The other robot that catches the pass ball is considered to be the goal, and it executes the goalkeeper’s action in the defend mode to receive the ball. The 3D robot soccer simulator is used to simulate these basic motions of robots, and some serial pictures are presented to show the simulation results. Finally, some strategies of five-to-five robot soccer game based on the position of the ball are proposed. Some results of the five-to-five robot soccer game are presented in the simulator. The simulation results illustrate that the propose strategies are efficient and feasible.
40
Chen, Tse-Yu, and 陳澤宇. "Reinforcement Learning in Zero-Sum Games for Robot Soccer Systems." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/29615769696503275189.
Full textAbstract:
碩士國立中正大學
電機工程研究所
91
The objective of this thesis is to develop a strategy system in a robot soccer system with cooperative ability which is improved by self-learning. A reinforcement learning method according to the zero-sum game theory is developed in this thesis. It enforces the learning systems to choose appropriate strategy on the opponent’s actions. In order to achieve the purpose of cooperation, two sub systems have been used, one is a role assignment system and the other one is a reinforcement learning system. In the role assignment system, four roles are assigned. They are Attacker, Helper, Defender, and Goalkeeper. Each role has its own behaviors and tasks different from other roles’. Helper and Defender use the reinforcement learning system to improve their policy selections on the game field. Furthermore, the physical and mechanical conditions of robots are all the same. Robots need not play the same kind of role. They can change to any kind of roles dynamically according to the state situation on the game field. In the reinforcement learning system, we have further two sub learning systems. Each learning system learns their tasks. One learns to figure up how Helper helps its teammates, to form an attack or a defense type. Meanwhile, the other learns to stand a proper defensive strategy. Two sub systems work in the same time, such that they can cooperate with each other. They can learn to improve their performance from game experience.
41
Chang-Chuan, You, and 游章釧. "Coordination and Control of Multi Agent Systems for Robot Soccer." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/01874580615524350339.
Full textAbstract:
碩士國立臺灣大學
機械工程學研究所
89
In this thesis, a complete robot soccer system is developed, tested, and proven to be a fine performer. We proposed a complete software structure for developing multi agent/robot coordination control. This software structure helps coding of multi agent systems. This software structure is implemented in a single-host-computer environment while reserving the nature of a distributed system. Thus the derived software and algorithms can be executed in distributed hardware systems as well. This feature greatly increases feasibility and practicality. As for AI, this system has complete strategy and decision-making mechanisms for single/multiple robot control. Based on local behaviors of the member agents, coordination and cooperation are achieved through communication and interaction. This thesis proposed a complete set of robot motion control algorithms to enable robots capable of performing complex and difficult soccer skills. These algorithms consist of path planning and path following. A delay compensation algorithm is also included to overcome the inherent delay aside the robot hardware. This delay compensation method can greatly increase the motion accuracy under high speed. This algorithm is not restricted to soccer robots. It can be applied to various systems with delay problems. Machine learning methods are also proposed in this thesis to solve the highly nonlinear behavior of controlling robots. Machine learning is used to help parameter tuning and estimate robots’ states.
42
Huang, Po-Chiao, and 黃柏喬. "Studies on Localization and Tracking Control for Humanoid Robot Soccer." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/00830265260217149534.
Full textAbstract:
碩士國立高雄第一科技大學
電機工程研究所碩士班
102
Localization and tracking control of robots ground the fundamental of Artificial Intelligence. Complicated kinematic mechanism of humanoid robots makes it localization and tracking control more difficult. In this study, Adaptive Neuron Fuzzy Inference System (ANFIS) having learning capability constructs the localization system of humanoid robot, and fuzzy theory is designed for tracking control. Hopefully, this study grounds the fundamental of artificial intelligent for humanoid robots in complicated kinematic mechanism. For exact demonstration this study, the experiments carried out by the humanoid robot on the play field of RoboCup and HuroCup are also included. The robot location in the play field and the goal mouth image captured by camera are used as training data of ANFIS to construct the localization system. The triangular localization method is engaged to capture the goal mouth image for robot position, but single camera can only get two-dimension message. Therefore, Inverse Perspective Mapping (IPM) is applied to get distance information. Because of extremely nonlinear relationship and imprecise distance information got by IPM, ANFIS is trained step-by-step until the convergent error in an accepted range. In addition, tracking control replies on trigger source from both of the orientation of the camera on head and the target location calculated by the captured image. To track the target, the trigger source decides turning angle of the servo motor at the hip of the humanoid robot. However the relationship between the trigger source and servo motor turning angle is hard to model. Therefore, a fuzzy controller is designed for the tracking control. Finally, the experiments using an exact humanoid robot demonstrate the studies. In the experiments, the humanoid robot controlled to track a ball in the play field, and then shooting the ball for a score after autonomous localization is also included.
43
Lin, Huan-Sheng, and 林煥昇. "Strategy Design in the Five-to-Five Robot Soccer Simulation." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/11075533243501404146.
Full textAbstract:
碩士南台科技大學
電機工程系
94
In this thesis, the control strategy design of robot soccer game is mainly conferred. The dynamical role assignment mechanism is achieved by examining the decision tree method in this paper. According to the position of ball, the decision tree resolves which role each robot should play. In the strategies, we propose the weighting methods and fuzzy weighting methods. The fuzzy weighting method can improve the subjectivity of the weighting methods efficiently but the expert system of them needs a long time to set up. In this thesis, by utilizing genetic algorithms we make every strategy to be a chromosome and let them evolve generationally till we get the suitable expert system for the robot. According to the experimental results, the score efficiency obtained by using the genetic algorithms is better than with the weighting method by 50%, and is better than that with the fuzzy weighting method by 15%.
44
Chang, Ke-Hao, and 張格豪. "Design and Implementation of a Small-Size Humanoid Soccer Robot." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/54763635672266961498.
Full textAbstract:
碩士南台科技大學
電機工程系
95
This thesis presents the design of a small-size humanoid robot and its application to robot soccer games. In which, there are three sub-systems discussed mainly, that is the visual perception, the locomotion control and the decision-making sub-systems. In the visual perception sub-system, color image processing procedures, which include color and geometry segmentations and the multi-condition color mask model, provide the robot the ability to distinguish those different objects with the same color under varied brightness. Besides, since a high performance DSP is adopted as the visual processor, a real-time robotic vision can be achieved. Moreover, this thesis proposes a design method of biped robot locomotion controllers based on the inverse learning model of ANFIS (Adaptive Neuro-Fuzzy Inference Systems). In which, an integrated ANFIS structure were training to be the system identifier for modeling the inverse dynamics of the biped robot. After the modeling, the resultant parameters can be duplicated as those of the biped locomotion controller to provide favorable control actions. For robot soccer games, the decision-making sub-system based on the finite state machine was proposed to switch behavior modes of the robot according to the visual feedback signals. As the experimental results show, this small-size humanoid robot is capable to play robot soccer games with satisfactory performance.
45
Oliveira, João Manuel Pinto Marques de. "Microsoft robotics soccer challenge : movement optimization of a quadruped robot." Master's thesis, 2008. http://hdl.handle.net/10216/59315.
Full textAbstract:
Estágio realizado na Universidade de Aveiro e orientado pelo Prof. Doutor Nuno LauTese de mestrado integrado. Engenharia Electrotécnica e de Computadores. Faculdade de Engenharia. Universidade do Porto. 2008
46
Teixeira, Henrique da Silva. "Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer." Master's thesis, 2020. https://hdl.handle.net/10216/126574.
Full textAbstract:
Robotics and Artificial Intelligence are two deeply intertwined fields of study, currently experiencing formidable growth. To foster these developments, the RoboCup initiative is a fantastic test bed to experiment new approaches. This dissertation seeks to gather these possibilities to design and implement a humanoid robotic kick system employing deep neural networks, capable of fluidly kicking a ball while walking. This dissertation's work is rooted in the groundwork laid by previous FCPortugal3D teams so as to take the existing algorithms and skills into its consideration. In this way, a transition between a dynamic movement situation and one where the agent is kicking is achieved. Furthermore, it uses the new agent framework developed by the FCPortugal3D team so as to allow these tests to be built upon for future situations with ease.
47
Teixeira, Henrique da Silva. "Humanoid Robot Kick in Motion Ability for Playing Robotic Soccer." Dissertação, 2020. https://hdl.handle.net/10216/126574.
Full textAbstract:
Robotics and Artificial Intelligence are two deeply intertwined fields of study, currently experiencing formidable growth. To foster these developments, the RoboCup initiative is a fantastic test bed to experiment new approaches. This dissertation seeks to gather these possibilities to design and implement a humanoid robotic kick system employing deep neural networks, capable of fluidly kicking a ball while walking. This dissertation's work is rooted in the groundwork laid by previous FCPortugal3D teams so as to take the existing algorithms and skills into its consideration. In this way, a transition between a dynamic movement situation and one where the agent is kicking is achieved. Furthermore, it uses the new agent framework developed by the FCPortugal3D team so as to allow these tests to be built upon for future situations with ease.
48
Immel, Rainer. "Development and Validation of a Mobile Autonomous Omnidirectional Soccer Robot." Phd thesis, 2006. http://tuprints.ulb.tu-darmstadt.de/693/1/Dissertation_RainerImmel_1971-08-15.pdf.
Full textAbstract:
An autonomous mobile robot is developed and experimentally validated. The robot is designed according to the regulations of the RoboCup Middle Size League 1999. Two basic skills are identified as underdeveloped in the robots participating in the 1999 RoboCup competition: Vision and agility. The goal of this research project is to develop a robot equipped with these two skills. All aspects of the robot being a mechatronic system are covered, including an omnidirectional propulsion system, an omnidirectional vision system, and a simple ball handling mechanism for dribbling a soccer ball. Video cameras are used as sensors, and a video image recognition algorithm is developed that computes both robot and ball position. A robust trajectory planning algorithm based on a global coordinate system is developed. It computes a robot trajectory surrounding a set of control points in given orientations, accounting for the interaction between robot and ball. A controller closes the feedback loop from sensors to actuators keeping the robot on its predetermined course. An experimental validation examines sensor accuracy, performance of actuators and controllers, and the overall skill to dribble a ball along a given trajectory. The vision system computes both robot and ball position 25 times per second. The average error of the robot position is below 10 mm, the average error of the ball position is below 5 percent of the ball's distance from the robot. All driving tests are carried out using a benchmark slalom course. The actuators behave as expected according to their specifications, they allow dynamic driving with longitudinal and lateral accelerations of up to 4 m/s². In that extreme case, the controllers manage the robot to stay on its course with maximum total and lateral deviations below 0.25 m and 0.1 m, respectively. A stable ball dribbling is possible at a maximum velocity and lateral acceleration of 1.5 m/s and 2.5 m/s², respectively.
49
Chen, Szu-Yu, and 陳思羽. "Simulation Study of Winning Strategies for Multi-Robot Soccer Game." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/84562236203484319536.
Full textAbstract:
碩士國立臺灣師範大學
應用電子科技學系
99
In the recent years, the development of robots boosts rapidly, and there are many successful examples. The trend of the robots also evolves from Single-robot into Multi-robot. Compared with single-robot’s independent operations, the multi-robot functions with a capacity of mutual cooperation and communication. The robot soccer is a good example among it. In this paper, the robot soccer game software, FIRA Robot Soccer v1.5a, is used to simulate the robots in order to investigate the strategy that robots applied in the games. The main purpose of this study is to design a strategy for FIRA soccer robots in the 5 on 5 games, and implement the winning strategies in simulation action. The obstacle avoidance and Dijkstra’s algorithm are used for the optimal path planning. After the experiments, the strategy is confirmed to increase the rates of scoring and achieve the goals effectively.
50
Oliveira, João Manuel Pinto Marques de. "Microsoft robotics soccer challenge : movement optimization of a quadruped robot." Dissertação, 2008. http://hdl.handle.net/10216/59315.
Full textAbstract:
Estágio realizado na Universidade de Aveiro e orientado pelo Prof. Doutor Nuno LauTese de mestrado integrado. Engenharia Electrotécnica e de Computadores. Faculdade de Engenharia. Universidade do Porto. 2008