Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974519
M. Misic, A. Dordevic, A. Arsic
The current effects of rapid development, high population density in large residential areas and pressures on organizations to protect the environment, create a provocative framework for waste management in modern cities. The complexity of the process of garbage collection is large, and therefore a major concern for public authorities in terms of collection, transport and further processing of solid waste. In this paper, the authors have presented a two-step solution formed from a nearest neighbor search and genetic algorithm to optimize the path of trucks with a specified capacity for garbage collection. This method firstly performs a search for the optimal solution with a nearest neighbors' algorithm (NNA) over a set of possible solutions, and then in the second step gives that solution with other random solutions to a genetic algorithm (GA) for further improvement; the goal is to extract the solution with minimal trajectory and maximum capacity utilization of trucks that are available. Testing was done on a range of problems with a certain number of trucks, with a given capacity and the number and location of sites for waste collection.
{"title":"The optimization of vehicle routing of communal waste in an urban environment using a nearest neighbirs' algorithm and genetic algorithm: Communal waste vehicle routing optimization in urban areas","authors":"M. Misic, A. Dordevic, A. Arsic","doi":"10.1109/ICACI.2017.7974519","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974519","url":null,"abstract":"The current effects of rapid development, high population density in large residential areas and pressures on organizations to protect the environment, create a provocative framework for waste management in modern cities. The complexity of the process of garbage collection is large, and therefore a major concern for public authorities in terms of collection, transport and further processing of solid waste. In this paper, the authors have presented a two-step solution formed from a nearest neighbor search and genetic algorithm to optimize the path of trucks with a specified capacity for garbage collection. This method firstly performs a search for the optimal solution with a nearest neighbors' algorithm (NNA) over a set of possible solutions, and then in the second step gives that solution with other random solutions to a genetic algorithm (GA) for further improvement; the goal is to extract the solution with minimal trajectory and maximum capacity utilization of trucks that are available. Testing was done on a range of problems with a certain number of trucks, with a given capacity and the number and location of sites for waste collection.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116440030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974487
Han Liu, Ella Haig, Alaa Mohasseb, Mohamed Bader
Classification is one of the most popular tasks of machine learning, which has been involved in broad applications in practice, such as decision making, sentiment analysis and pattern recognition. It involves the assignment of a class/label to an instance and is based on the assumption that each instance can only belong to one class. This assumption does not hold, especially for indexing problems (when an item, such as a movie, can belong to more than one category) or for complex items that reflect more than one aspect, e.g. a product review outlining advantages and disadvantages may be at the same time positive and negative. To address this problem, multi-label classification has been increasingly used in recent years, by transforming the data to allow an instance to have more than one label; the nature of learning, however, is the same as traditional learning, i.e. learning to discriminate one class from other classes and the output of a classifier is still single (although the output may contain a set of labels). In this paper we propose a fundamentally different type of classification in which the membership of an instance to all classes(/labels) is judged by a multiple-input-multiple-output classifier through generative multi-task learning. An experimental study is conducted on five UCI data sets to show empirically that an instance can belong to more than one class, by using the theory of fuzzy logic and checking the extent to which an instance belongs to each single class, i.e. the fuzzy membership degree. The paper positions new research directions on multi-task classification in the context of both supervised learning and semi-supervised learning.
{"title":"Transformation of discriminative single-task classification into generative multi-task classification in machine learning context","authors":"Han Liu, Ella Haig, Alaa Mohasseb, Mohamed Bader","doi":"10.1109/ICACI.2017.7974487","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974487","url":null,"abstract":"Classification is one of the most popular tasks of machine learning, which has been involved in broad applications in practice, such as decision making, sentiment analysis and pattern recognition. It involves the assignment of a class/label to an instance and is based on the assumption that each instance can only belong to one class. This assumption does not hold, especially for indexing problems (when an item, such as a movie, can belong to more than one category) or for complex items that reflect more than one aspect, e.g. a product review outlining advantages and disadvantages may be at the same time positive and negative. To address this problem, multi-label classification has been increasingly used in recent years, by transforming the data to allow an instance to have more than one label; the nature of learning, however, is the same as traditional learning, i.e. learning to discriminate one class from other classes and the output of a classifier is still single (although the output may contain a set of labels). In this paper we propose a fundamentally different type of classification in which the membership of an instance to all classes(/labels) is judged by a multiple-input-multiple-output classifier through generative multi-task learning. An experimental study is conducted on five UCI data sets to show empirically that an instance can belong to more than one class, by using the theory of fuzzy logic and checking the extent to which an instance belongs to each single class, i.e. the fuzzy membership degree. The paper positions new research directions on multi-task classification in the context of both supervised learning and semi-supervised learning.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130376900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974509
Jie Li, Huanming Liu, Tianzheng Wang, Min Jiang, Shuai Wang, Kang Li, Xiaoguang Zhao
Safety helmet wearing detection is very essential in power substation. This paper proposed a innovative and practical safety helmet wearing detection method based on image processing and machine learning. At first, the ViBe background modelling algorithm is exploited to detect motion object under a view of fix surveillant camera in power substation. After obtaining the motion region of interest, the Histogram of Oriented Gradient (HOG) feature is extracted to describe inner human. And then, based on the result of HOG feature extraction, the Support Vector Machine (SVM) is trained to classify pedestrians. Finally, the safety helmet detection will be implemented by color feature recognition. Compelling experimental results demonstrated the correctness and effectiveness of our proposed method.
在变电站中，安全帽佩戴检测是必不可少的。本文提出了一种基于图像处理和机器学习的创新实用的安全帽佩戴检测方法。首先，利用ViBe背景建模算法对变电站固定监控摄像机视域下的运动目标进行检测。在获得感兴趣的运动区域后，提取定向梯度直方图(Histogram of Oriented Gradient, HOG)特征来描述人体内部。然后，基于HOG特征提取结果，训练支持向量机(SVM)对行人进行分类。最后，通过颜色特征识别实现安全帽检测。实验结果证明了该方法的正确性和有效性。
{"title":"Safety helmet wearing detection based on image processing and machine learning","authors":"Jie Li, Huanming Liu, Tianzheng Wang, Min Jiang, Shuai Wang, Kang Li, Xiaoguang Zhao","doi":"10.1109/ICACI.2017.7974509","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974509","url":null,"abstract":"Safety helmet wearing detection is very essential in power substation. This paper proposed a innovative and practical safety helmet wearing detection method based on image processing and machine learning. At first, the ViBe background modelling algorithm is exploited to detect motion object under a view of fix surveillant camera in power substation. After obtaining the motion region of interest, the Histogram of Oriented Gradient (HOG) feature is extracted to describe inner human. And then, based on the result of HOG feature extraction, the Support Vector Machine (SVM) is trained to classify pedestrians. Finally, the safety helmet detection will be implemented by color feature recognition. Compelling experimental results demonstrated the correctness and effectiveness of our proposed method.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123005161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974480
Huiwei Wang, X. Liao, Tingwen Huang
This paper investigates a double-integrator consensus problem for multi-agent networks (MANs) with nonlinear dynamics, where each agent is governed by both time-varying position and velocity consensus terms. The following three cases are carefully analyzed: 1) networks with fixed topology; 2) networks with controlled switching topology; and 3) networks with random switching topology. Based on previous work [11], some sententious sufficient criteria are established for reaching consensus in MANs with fixed topology. With the help of consensus results under fixed topology, some criteria are also derived to achieve consensus for MANs with switching topology by utilizing average dwell time approach and a programmable switching signal. The next moment, in view of ergodic property and stationary distribution of Markov chain, some criteria are derived to reach consensus for MANs with random switching topology. It is worth noting that the MANs considered in the above two switching cases are composed of all or partial individual switching topologies which can be reached the desired consensus.
{"title":"Consensus in multi-agent networks with switching topology and nonlinear dynamics","authors":"Huiwei Wang, X. Liao, Tingwen Huang","doi":"10.1109/ICACI.2017.7974480","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974480","url":null,"abstract":"This paper investigates a double-integrator consensus problem for multi-agent networks (MANs) with nonlinear dynamics, where each agent is governed by both time-varying position and velocity consensus terms. The following three cases are carefully analyzed: 1) networks with fixed topology; 2) networks with controlled switching topology; and 3) networks with random switching topology. Based on previous work [11], some sententious sufficient criteria are established for reaching consensus in MANs with fixed topology. With the help of consensus results under fixed topology, some criteria are also derived to achieve consensus for MANs with switching topology by utilizing average dwell time approach and a programmable switching signal. The next moment, in view of ergodic property and stationary distribution of Markov chain, some criteria are derived to reach consensus for MANs with random switching topology. It is worth noting that the MANs considered in the above two switching cases are composed of all or partial individual switching topologies which can be reached the desired consensus.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117343437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974510
Xiaolin Xu, Lin Zhang
This paper aims to explore pushing service framework of the personalized learning resources in network learning platform. We use the data mining technology to acquire a series of data by combining with the content filtering push strategy and the collaborative filtering push strategy. Through the analysis of learners' registration information and browsing behavior, one can analyze learners' interest of learning and the learners will be pushed by the learning resources that they may be interested in. Finally, we design a new learning resource to improve the service system to achieve better learning performance on network learning platform.
{"title":"A study of pushing service framework of the personalized learning resources on network learning platform","authors":"Xiaolin Xu, Lin Zhang","doi":"10.1109/ICACI.2017.7974510","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974510","url":null,"abstract":"This paper aims to explore pushing service framework of the personalized learning resources in network learning platform. We use the data mining technology to acquire a series of data by combining with the content filtering push strategy and the collaborative filtering push strategy. Through the analysis of learners' registration information and browsing behavior, one can analyze learners' interest of learning and the learners will be pushed by the learning resources that they may be interested in. Finally, we design a new learning resource to improve the service system to achieve better learning performance on network learning platform.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133410150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974516
Kamran Shafi
Modern day autonomous systems are moving away form mere automation of manual tasks to true autonomy that require them to apply human-like judgment when dealing with uncertain situations in performing complex tasks. Trust in these systems is a key enabler to fully realize this dream. A lack of trust leads to inefficient use of these systems and increases the supervision workload for humans. Conversely, an over trust in these systems leads to increased risks and exposure to catastrophic events. This paper presents a high-level analytical model to study trust dynamics in supervised autonomous system environments. Trust, in this context, is defined as a function of machine competence and the level of human control required to achieve this competence. A parametric model of machine competence is presented that allows generating different machine competence behaviors based on the task difficulty, level of supervision and machine's learning ability. The notions of perceived and desired or optimal trust, computed based on perceived and observed machine competence respectively, are introduced. This allows treating trust calibration as an optimization or control problem. The presented models provide a formal framework for developing higher-fidelity simulation models to study trust dynamics in supervised autonomous systems and develop appropriate controllers for optimizing the trust between humans and machines in these systems.
{"title":"A machine competence based analytical model to study trust calibration in supervised autonomous systems","authors":"Kamran Shafi","doi":"10.1109/ICACI.2017.7974516","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974516","url":null,"abstract":"Modern day autonomous systems are moving away form mere automation of manual tasks to true autonomy that require them to apply human-like judgment when dealing with uncertain situations in performing complex tasks. Trust in these systems is a key enabler to fully realize this dream. A lack of trust leads to inefficient use of these systems and increases the supervision workload for humans. Conversely, an over trust in these systems leads to increased risks and exposure to catastrophic events. This paper presents a high-level analytical model to study trust dynamics in supervised autonomous system environments. Trust, in this context, is defined as a function of machine competence and the level of human control required to achieve this competence. A parametric model of machine competence is presented that allows generating different machine competence behaviors based on the task difficulty, level of supervision and machine's learning ability. The notions of perceived and desired or optimal trust, computed based on perceived and observed machine competence respectively, are introduced. This allows treating trust calibration as an optimization or control problem. The presented models provide a formal framework for developing higher-fidelity simulation models to study trust dynamics in supervised autonomous systems and develop appropriate controllers for optimizing the trust between humans and machines in these systems.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117350821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As it is known, computer users who notice the existence of electronic viruses will take active measures to defend against the viruses before they prevail on networks. However, the most of former computer virus epidemic models ignore the human vigilance completely. This paper aims to understand how the human awareness prohibits virus spreading. So a new computer virus propagation model where the viral prevalence is not quite high is developed. Under moderate assumptions, this model admits one equilibrium which is virus-free. And it is shown to be globally asymptotically stable. Some numerical examples are also given. The obtained result clearly exhibits that enough vigilance greatly benefits the containment of computer viruses.
{"title":"Toward understanding how the human vigilance contains the prevalence of computer viruses","authors":"Xianxiu Zhang, Chuandong Li, Wangshu Peng, Tingwen Huang","doi":"10.1109/ICACI.2017.7974478","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974478","url":null,"abstract":"As it is known, computer users who notice the existence of electronic viruses will take active measures to defend against the viruses before they prevail on networks. However, the most of former computer virus epidemic models ignore the human vigilance completely. This paper aims to understand how the human awareness prohibits virus spreading. So a new computer virus propagation model where the viral prevalence is not quite high is developed. Under moderate assumptions, this model admits one equilibrium which is virus-free. And it is shown to be globally asymptotically stable. Some numerical examples are also given. The obtained result clearly exhibits that enough vigilance greatly benefits the containment of computer viruses.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121134510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974515
A. Wadood, S. Anavatti, O. Hassanein
The control of Autonomous Underwater Vehicles (AUVs) is challenging because of its highly nonlinear and time-varying dynamics Fuzzy logic has the ability to model any nonlinear system. Recently/interval Type-2 Fuzzy logic (IT2FL) has gained interest due to its inherent ability to handle uncertainties. The purpose of this study is to employ IT2FLC for the control of an AUV Simulation experiments have been carried out. Results indicate that Interval Type-2 Fuzzy Logic Control (IT2FLC) has superior performance than Type-1 Fuzzy Logic Control in the presence of noise and parameter variations.
{"title":"Robust controller design for an autonomous underwater vehicle","authors":"A. Wadood, S. Anavatti, O. Hassanein","doi":"10.1109/ICACI.2017.7974515","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974515","url":null,"abstract":"The control of Autonomous Underwater Vehicles (AUVs) is challenging because of its highly nonlinear and time-varying dynamics Fuzzy logic has the ability to model any nonlinear system. Recently/interval Type-2 Fuzzy logic (IT2FL) has gained interest due to its inherent ability to handle uncertainties. The purpose of this study is to employ IT2FLC for the control of an AUV Simulation experiments have been carried out. Results indicate that Interval Type-2 Fuzzy Logic Control (IT2FLC) has superior performance than Type-1 Fuzzy Logic Control in the presence of noise and parameter variations.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133230558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974506
J. Tan, Chuandong Li
In this paper, we explore some aspect of the asymptotic stability of stochastic impulsive systems with variable-time impulses. At the beginning we consider the case that the trajectory of the stochastic system intersects each surface exactly once. Then we shall show that under the well-selected conditions the systems with variable-time impulsive can be changed to the systems with the fixed-time impulsive. Some criteria ensuring the stability in the p-th moment are obtained by using stochastic analysis theory. An illustrative example and simulations are given to show the effectiveness of our results.
{"title":"The P-th moment asymptotic stability of stochastic system with variable-time impulses","authors":"J. Tan, Chuandong Li","doi":"10.1109/ICACI.2017.7974506","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974506","url":null,"abstract":"In this paper, we explore some aspect of the asymptotic stability of stochastic impulsive systems with variable-time impulses. At the beginning we consider the case that the trajectory of the stochastic system intersects each surface exactly once. Then we shall show that under the well-selected conditions the systems with variable-time impulsive can be changed to the systems with the fixed-time impulsive. Some criteria ensuring the stability in the p-th moment are obtained by using stochastic analysis theory. An illustrative example and simulations are given to show the effectiveness of our results.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131329017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-02-01DOI: 10.1109/ICACI.2017.7974481
M. Kurdi, Alex K. Dadykin, I. Elzein
The simulation of a navigation heterogeneous group of robots; unmanned ground vehicle (UGV), unmanned aerial vehicle (UAV) through GPS, digital map and image processing using probabilistic roadmap method (PRM) are addressed throughout this paper. Having the capacitato navigate accurately is one of the major abilities of a mobile robot to effectively execute a variety of jobs including manipulation, docking, and transportation. To achieve the desired navigation accuracy, mobile robots are typically equipped with on-board sensors to observe persistent features in the environment, to estimate their pose from these observations, and to adjust tneir motion accordingly [1]. According to the scenario of the mission, UAV takes off from UGV, surveys the terrain and transmits Image terrestrial robot. UGV processes images, calculating the optimum trajectory method Probabilistic Roadmap with the help of GPS, and provide standalone navigate through the outdoor based on the calculated route. The group of robots is: UGV Belarus-132N and UAV Phantom-2 Vision quadcopter.
{"title":"Navigation of mobile robot with cooperation of quadcopter","authors":"M. Kurdi, Alex K. Dadykin, I. Elzein","doi":"10.1109/ICACI.2017.7974481","DOIUrl":"https://doi.org/10.1109/ICACI.2017.7974481","url":null,"abstract":"The simulation of a navigation heterogeneous group of robots; unmanned ground vehicle (UGV), unmanned aerial vehicle (UAV) through GPS, digital map and image processing using probabilistic roadmap method (PRM) are addressed throughout this paper. Having the capacitato navigate accurately is one of the major abilities of a mobile robot to effectively execute a variety of jobs including manipulation, docking, and transportation. To achieve the desired navigation accuracy, mobile robots are typically equipped with on-board sensors to observe persistent features in the environment, to estimate their pose from these observations, and to adjust tneir motion accordingly [1]. According to the scenario of the mission, UAV takes off from UGV, surveys the terrain and transmits Image terrestrial robot. UGV processes images, calculating the optimum trajectory method Probabilistic Roadmap with the help of GPS, and provide standalone navigate through the outdoor based on the calculated route. The group of robots is: UGV Belarus-132N and UAV Phantom-2 Vision quadcopter.","PeriodicalId":260701,"journal":{"name":"2017 Ninth International Conference on Advanced Computational Intelligence (ICACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114562549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：