Pub Date : 2018-11-01DOI: 10.1109/ICARCV.2018.8580636
F. Stoican, I. Prodan, D. Popescu, L. Ichim, Emilian Vlasceanu
In this paper we consider a multi-UAV formation whose goal is to efficiently gather data from sensors deployed in a cluttered environment while in the same time keeping communication with ground terminals. We formulate these requirements and constraints as a nonlinear constrained optimization problem and recast them in a mixed-integer form with the help of a hyperplane arrangement construction. Particular attention is given to line-of-sight constraints which ensure permanent communication between UAVs and ground terminals. Reference trajectories are generated in simulation over illustrative examples.
{"title":"Mixed-Integer Representations for Mission Constraints in a Multi-Agent Team","authors":"F. Stoican, I. Prodan, D. Popescu, L. Ichim, Emilian Vlasceanu","doi":"10.1109/ICARCV.2018.8580636","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8580636","url":null,"abstract":"In this paper we consider a multi-UAV formation whose goal is to efficiently gather data from sensors deployed in a cluttered environment while in the same time keeping communication with ground terminals. We formulate these requirements and constraints as a nonlinear constrained optimization problem and recast them in a mixed-integer form with the help of a hyperplane arrangement construction. Particular attention is given to line-of-sight constraints which ensure permanent communication between UAVs and ground terminals. Reference trajectories are generated in simulation over illustrative examples.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124370677","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}
Tracking the location of mobile manufacturing objects is essential for manufacturing execution system. This paper presents a review of recent RFID-based localization and tracking technologies. Based on the literature review, we studied the feasibility of indoor localization that locates items on the manufacturing shop-floor automatically using wireless signals and RF-based localization technologies. Although the real-time locating systems (RTLS) exist to provide real-time localization, these technologies are costly to implement on a large scale. In this feasibility study, we measured received signal strength and phase shift signals from commercial off-the-shelf (COTS) wireless devices for tracking the location of manufacturing objects.
{"title":"The Study on Indoor Localization for Manufacturing Execution System","authors":"Sheng Huang, Sudeep Mohanty, Andri Ashfahani, Mahardhika Pratama","doi":"10.1109/ICARCV.2018.8581192","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581192","url":null,"abstract":"Tracking the location of mobile manufacturing objects is essential for manufacturing execution system. This paper presents a review of recent RFID-based localization and tracking technologies. Based on the literature review, we studied the feasibility of indoor localization that locates items on the manufacturing shop-floor automatically using wireless signals and RF-based localization technologies. Although the real-time locating systems (RTLS) exist to provide real-time localization, these technologies are costly to implement on a large scale. In this feasibility study, we measured received signal strength and phase shift signals from commercial off-the-shelf (COTS) wireless devices for tracking the location of manufacturing objects.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116926503","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8580632
Yalong Jiang, Z. Chi
In this paper, we study an important factor that determines the capacity of a CNN model and propose a novel structure of convolutional layers with a higher performance-complexity ratio. Firstly, the relationship of the model capacity and the number of parameters versus segmentation performance is explored. Secondly, a mechanism is proposed to optimize the structure of a CNN model for a specific task. The mechanism also provides better convergence than current state-of-the-art methods for factorizing convolutional layers, such as MobileNet. Thirdly, we propose a measure based on the mutual information between hidden activations and inputs/outputs to compute the capacity of a CNN model. This measure is highly correlated with segmentation performance. Experimental results on the segmentation of the PASCAL Person Parts Dataset show that the linear dependency among convolutional kernels is an important factor determining the capacity of a CNN model. It is also demonstrated that our approach can successfully adjust the model capacity to best match to the complexity of a dataset. The optimized CNN model achieves the similar performance to Deeplab-V2 on the segmentation task with 100 × less parameters, resulting in a significantly improved performance-complexity ratio.
{"title":"A Novel Structure of Convolutional Layers with a Higher Performance-Complexity Ratio for Semantic Segmentation","authors":"Yalong Jiang, Z. Chi","doi":"10.1109/ICARCV.2018.8580632","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8580632","url":null,"abstract":"In this paper, we study an important factor that determines the capacity of a CNN model and propose a novel structure of convolutional layers with a higher performance-complexity ratio. Firstly, the relationship of the model capacity and the number of parameters versus segmentation performance is explored. Secondly, a mechanism is proposed to optimize the structure of a CNN model for a specific task. The mechanism also provides better convergence than current state-of-the-art methods for factorizing convolutional layers, such as MobileNet. Thirdly, we propose a measure based on the mutual information between hidden activations and inputs/outputs to compute the capacity of a CNN model. This measure is highly correlated with segmentation performance. Experimental results on the segmentation of the PASCAL Person Parts Dataset show that the linear dependency among convolutional kernels is an important factor determining the capacity of a CNN model. It is also demonstrated that our approach can successfully adjust the model capacity to best match to the complexity of a dataset. The optimized CNN model achieves the similar performance to Deeplab-V2 on the segmentation task with 100 × less parameters, resulting in a significantly improved performance-complexity ratio.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116966771","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581252
Guangyue Zhao, Weijie Sun, He Cai, Yunjian Peng
In this paper, a novel output feedback solution based on the Q-learning algorithm using the measured data is proposed for the linear quadratic tracking (LQT) problem of unknown discrete-time systems. To tackle this technical issue, an augmented system composed of the original controlled system and the linear command generator is first constructed. Then, by using the past input, output, and reference trajectory data of the augmented system, the output feedback Q-learning scheme is able to learn the optimal tracking controller online without requiring any knowledge of the augmented system dynamics. Learning algorithms including both policy iteration (PI) and value iteration (VI) algorithms are developed to converge to the optimal solution. Finally, simulation results are provided to verify the effectiveness of the proposed scheme.
{"title":"Output Feedback Reinforcement Q-learning for Optimal Quadratic Tracking Control of Unknown Discrete-Time Linear Systems and Its Application","authors":"Guangyue Zhao, Weijie Sun, He Cai, Yunjian Peng","doi":"10.1109/ICARCV.2018.8581252","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581252","url":null,"abstract":"In this paper, a novel output feedback solution based on the Q-learning algorithm using the measured data is proposed for the linear quadratic tracking (LQT) problem of unknown discrete-time systems. To tackle this technical issue, an augmented system composed of the original controlled system and the linear command generator is first constructed. Then, by using the past input, output, and reference trajectory data of the augmented system, the output feedback Q-learning scheme is able to learn the optimal tracking controller online without requiring any knowledge of the augmented system dynamics. Learning algorithms including both policy iteration (PI) and value iteration (VI) algorithms are developed to converge to the optimal solution. Finally, simulation results are provided to verify the effectiveness of the proposed scheme.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117133161","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581302
Lanlin Yu, J. Xiong
In this paper, the moment matching model reduction problem for negative imaginary systems is considered in the time-domain framework. For a given high order negative imaginary system with poles at the origin, our goal is to find a reduced-order negative imaginary system such that a prescribed number of the moments and the poles at the origin are preserved. The reduced-order negative imaginary systems was constructed by the parameterized reduced-order systems that match the moments. It shows that a desired reduced-order system can be obtained by using the unique solution of a Sylvester equation. Finally, the proposed model reduction method is illustrated by an RLC network and a train system.
{"title":"Time-domain moment matching model reduction for negative imaginary systems","authors":"Lanlin Yu, J. Xiong","doi":"10.1109/ICARCV.2018.8581302","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581302","url":null,"abstract":"In this paper, the moment matching model reduction problem for negative imaginary systems is considered in the time-domain framework. For a given high order negative imaginary system with poles at the origin, our goal is to find a reduced-order negative imaginary system such that a prescribed number of the moments and the poles at the origin are preserved. The reduced-order negative imaginary systems was constructed by the parameterized reduced-order systems that match the moments. It shows that a desired reduced-order system can be obtained by using the unique solution of a Sylvester equation. Finally, the proposed model reduction method is illustrated by an RLC network and a train system.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121021979","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581143
Sheng Huang, S. Shoaib, Andri Ashfahani, Mahardhika Pratama
One of the issues faced by manufacturing industry is a lack of automatic localization techniques. In this research, a Radio Frequency Identification (RFID) based localization system is proposed for resource tracking. In this study, we incorporated a RFID tag at each item to be tracked, and a RFID reference tag at each location zone. The encoded IDs are read to identify the names of items and location zones. At the same time, radio signals (received signal strength and phase) are measured as RFID fingerprints. Similarity measures are studied to compare fingerprints between RFID item tags and location reference tags to track the location of the items. The kernel-based learning method was implemented as similarity measure. Different cluster labelling methods were compared and it was found that the proximity method is more efficient. The clustering method is used to overcome the issues faced by traditional RFID based localization methods.
{"title":"Similarity Measures in Development of an Indoor Localization System","authors":"Sheng Huang, S. Shoaib, Andri Ashfahani, Mahardhika Pratama","doi":"10.1109/ICARCV.2018.8581143","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581143","url":null,"abstract":"One of the issues faced by manufacturing industry is a lack of automatic localization techniques. In this research, a Radio Frequency Identification (RFID) based localization system is proposed for resource tracking. In this study, we incorporated a RFID tag at each item to be tracked, and a RFID reference tag at each location zone. The encoded IDs are read to identify the names of items and location zones. At the same time, radio signals (received signal strength and phase) are measured as RFID fingerprints. Similarity measures are studied to compare fingerprints between RFID item tags and location reference tags to track the location of the items. The kernel-based learning method was implemented as similarity measure. Different cluster labelling methods were compared and it was found that the proximity method is more efficient. The clustering method is used to overcome the issues faced by traditional RFID based localization methods.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127050628","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}
Unmanned Air Vehicle (UAV) is an advanced automatic system. In the future, UAV will have an important role. In order to enhance the autonomous capability of UAV, The intelligent maneuver decision-making for UAV is studied. Firstly, a confrontation process based on Monte Carlo simulation is completed, and it is used to predict the maneuver behavior of UAV. Secondly, a multidimensional cloud model is used to access the situation of the UAV after different maneuver behavior. The final maneuver decision is chosen based on the evaluation results. A real-time simulation between UAV of our side and the opposite side under the pairwise confrontation is implemented. The aircraft model in SIMULINK of MATTLAB is used. The simulation result shows that maneuver action from decision making method which is based on Monte Carlo process simulation and multidimensional cloud model evaluation is validity and effective.
{"title":"Intelligent decision making for UAV based on Monte Carlo Simulation","authors":"Yun-hong Ma, Hao Liu, Yao-zhong Zhang, Q. He, Zhao Xu","doi":"10.1109/ICARCV.2018.8581333","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581333","url":null,"abstract":"Unmanned Air Vehicle (UAV) is an advanced automatic system. In the future, UAV will have an important role. In order to enhance the autonomous capability of UAV, The intelligent maneuver decision-making for UAV is studied. Firstly, a confrontation process based on Monte Carlo simulation is completed, and it is used to predict the maneuver behavior of UAV. Secondly, a multidimensional cloud model is used to access the situation of the UAV after different maneuver behavior. The final maneuver decision is chosen based on the evaluation results. A real-time simulation between UAV of our side and the opposite side under the pairwise confrontation is implemented. The aircraft model in SIMULINK of MATTLAB is used. The simulation result shows that maneuver action from decision making method which is based on Monte Carlo process simulation and multidimensional cloud model evaluation is validity and effective.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114907250","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581179
Hang Tian, Chenglin Liu, Guangbin Liu
This paper studies the bipartite consensus problem for second-order multi-agent systems with distinct disturbances. The interactions between agents are described by a signed directed graph. For structurally balanced networks, a generalized bipartite consensus algorithm with disturbances' observers is proposed. Necessary and sufficient conditions are obtained to achieve bipartite consensus with the well designed algorithm by using frequency-domain analysis and matrix theory. Finally, simulations are shown to verify the correctness of presented results.
{"title":"Bipartite Consensus Problem of Second-order Multi-agent Systems with Disturbances","authors":"Hang Tian, Chenglin Liu, Guangbin Liu","doi":"10.1109/ICARCV.2018.8581179","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581179","url":null,"abstract":"This paper studies the bipartite consensus problem for second-order multi-agent systems with distinct disturbances. The interactions between agents are described by a signed directed graph. For structurally balanced networks, a generalized bipartite consensus algorithm with disturbances' observers is proposed. Necessary and sufficient conditions are obtained to achieve bipartite consensus with the well designed algorithm by using frequency-domain analysis and matrix theory. Finally, simulations are shown to verify the correctness of presented results.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116124158","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581175
Fang Liu, Kee Jin Lee, Jihoon Hong
Online machine learning algorithm has attracted increasing attention especially in the era of Industry 4.0. The reason is that traditional batch learning algorithm cannot deal with the streaming data produced by sensorized machines and make real-time decisions. In this paper, we propose a Feature-aware online learning approach of Support Vector Machine (FSVM) for classification problem. Usually, online learning algorithm has limited access to streaming data due to resource and computation constraints. In FSVM, we introduced a feature vector selection method to reduce the size of training dataset without losing key information and maintain an acceptable classification accuracy. Here, such small set of selected feature vectors is able to represent the original dataset. What is more, we can detect feature drifting by checking whether or not a new input data can be represented by the current feature vectors. We evaluate the performance of FSVM based on several realworld datasets. The results show that even train the SVM model with around 10% data, an acceptable misclassification rate can be reached.
{"title":"A Feature-Aware Online Learning Approach for Support Vector Machine Classification","authors":"Fang Liu, Kee Jin Lee, Jihoon Hong","doi":"10.1109/ICARCV.2018.8581175","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581175","url":null,"abstract":"Online machine learning algorithm has attracted increasing attention especially in the era of Industry 4.0. The reason is that traditional batch learning algorithm cannot deal with the streaming data produced by sensorized machines and make real-time decisions. In this paper, we propose a Feature-aware online learning approach of Support Vector Machine (FSVM) for classification problem. Usually, online learning algorithm has limited access to streaming data due to resource and computation constraints. In FSVM, we introduced a feature vector selection method to reduce the size of training dataset without losing key information and maintain an acceptable classification accuracy. Here, such small set of selected feature vectors is able to represent the original dataset. What is more, we can detect feature drifting by checking whether or not a new input data can be represented by the current feature vectors. We evaluate the performance of FSVM based on several realworld datasets. The results show that even train the SVM model with around 10% data, an acceptable misclassification rate can be reached.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122417928","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 : 2018-11-01DOI: 10.1109/ICARCV.2018.8581157
A. Jamshidnejad, Emilio Frazzoli
We propose a novel optimal receding-horizon navigation approach for a robot in an unknown search environment, towards a known goal position. The search environment includes several obstacles that are distributed at unknown positions. The proposed approach considers multiple objectives, including reference path tracking, reduction of the energy consumption, restraining the robot's mission time, and asymptotic stability towards the goal position. The navigation policy is determined in the detection zone of the robot's detection sensor at particular update time steps for short time. This policy will be updated at the next update time steps. Moreover, we introduce a novel heuristic algorithm for determining the robot's tracking path trajectory that is simply implementable and fast in computations.
{"title":"Adaptive Optimal Receding-Horizon Robot Navigation via Short-Term Policy Development","authors":"A. Jamshidnejad, Emilio Frazzoli","doi":"10.1109/ICARCV.2018.8581157","DOIUrl":"https://doi.org/10.1109/ICARCV.2018.8581157","url":null,"abstract":"We propose a novel optimal receding-horizon navigation approach for a robot in an unknown search environment, towards a known goal position. The search environment includes several obstacles that are distributed at unknown positions. The proposed approach considers multiple objectives, including reference path tracking, reduction of the energy consumption, restraining the robot's mission time, and asymptotic stability towards the goal position. The navigation policy is determined in the detection zone of the robot's detection sensor at particular update time steps for short time. This policy will be updated at the next update time steps. Moreover, we introduce a novel heuristic algorithm for determining the robot's tracking path trajectory that is simply implementable and fast in computations.","PeriodicalId":395380,"journal":{"name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122459294","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：