Pub Date : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162598
Anthony Ngo, Max Paul Bauer, Michael M. Resch
Simulation-based testing is a promising approach to significantly reduce the validation effort of automated driving functions. Realistic models of environment perception sensors such as camera, radar and lidar play a key role in this testing strategy. A generally accepted method to validate these sensor models does not yet exist. Particularly radar has traditionally been one of the most difficult sensors to model. Although promising as an alternative to real test drives, virtual tests are time-consuming due to the fact that they simulate the entire radar system in detail, using computation-intensive simulation techniques to approximate the propagation of electromagnetic waves. In this paper, we introduce a sensitivity analysis approach for developing and evaluating a radar simulation, with the objective to identify the parameters with the greatest impact regarding the system under test. A modular radar system simulation is presented and parameterized to conduct a sensitivity analysis in order to evaluate a spatial clustering algorithm as the system under test, while comparing the output from the radar model to real driving measurements to ensure a realistic model behavior. The presented approach is evaluated and it is demonstrated that with this approach results from different situations can be traced back to the contribution of the individual sub-modules of the radar simulation.
{"title":"A Sensitivity Analysis Approach for Evaluating a Radar Simulation for Virtual Testing of Autonomous Driving Functions","authors":"Anthony Ngo, Max Paul Bauer, Michael M. Resch","doi":"10.1109/ACIRS49895.2020.9162598","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162598","url":null,"abstract":"Simulation-based testing is a promising approach to significantly reduce the validation effort of automated driving functions. Realistic models of environment perception sensors such as camera, radar and lidar play a key role in this testing strategy. A generally accepted method to validate these sensor models does not yet exist. Particularly radar has traditionally been one of the most difficult sensors to model. Although promising as an alternative to real test drives, virtual tests are time-consuming due to the fact that they simulate the entire radar system in detail, using computation-intensive simulation techniques to approximate the propagation of electromagnetic waves. In this paper, we introduce a sensitivity analysis approach for developing and evaluating a radar simulation, with the objective to identify the parameters with the greatest impact regarding the system under test. A modular radar system simulation is presented and parameterized to conduct a sensitivity analysis in order to evaluate a spatial clustering algorithm as the system under test, while comparing the output from the radar model to real driving measurements to ensure a realistic model behavior. The presented approach is evaluated and it is demonstrated that with this approach results from different situations can be traced back to the contribution of the individual sub-modules of the radar simulation.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115406286","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 : 2020-07-01DOI: 10.1109/acirs49895.2020.9162611
Wenjing Yang, Haiyan Zhao, Mingqian Wang, Jingzhou Ji
As the prototype or primary state of future brain computer interface, intelligent search engine is an important direction of artificial intelligence technology, which has become a field of high attention and continuous research in academia. In this paper, the performance evaluation index of intelligent search engine service is proposed in view of the unclear evaluation method and imperfect evaluation method. The calculation method of service performance evaluation of intelligent search engine is determined, and the service performance evaluation system of intelligent search engine is constructed, and the Chinese search engine A and B as an example of the experimental analysis, which provides theoretical support and technical support for the development of service performance evaluation of intelligent search engine.
{"title":"Design of Intelligent Search Engine Service Performance Evaluation System","authors":"Wenjing Yang, Haiyan Zhao, Mingqian Wang, Jingzhou Ji","doi":"10.1109/acirs49895.2020.9162611","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162611","url":null,"abstract":"As the prototype or primary state of future brain computer interface, intelligent search engine is an important direction of artificial intelligence technology, which has become a field of high attention and continuous research in academia. In this paper, the performance evaluation index of intelligent search engine service is proposed in view of the unclear evaluation method and imperfect evaluation method. The calculation method of service performance evaluation of intelligent search engine is determined, and the service performance evaluation system of intelligent search engine is constructed, and the Chinese search engine A and B as an example of the experimental analysis, which provides theoretical support and technical support for the development of service performance evaluation of intelligent search engine.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128323898","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162628
A. Cheraghi, Fabio Schloesser Vila, Kalman Graffi
In biology, phototaxing is one of the many forms of directed motions that organisms can exhibit. If stimulated by light, these organisms can move towards or away from the source. In this paper we present an algorithm that is reliably capable of moving a swarm of virtual robots away from a light source, all while the individual virtual robots are incapable of determining the direction and origin of the light source. The individual agents cannot generate phototactic behavior by themselves, instead this is realized through the overall, emergent behavior of the swarm. This paper explores an algorithm to produce phototactic movement in swarms of virtual robots. The algorithm is developed so that robots in a swarm of any size can execute it in a decentralized fashion, without the need for any globalized control or communication between them. We explore two different sets of virtual robots, one with self-charging and one with battery-powered characteristics. In a rigorous testing and evaluation we find that the swarms behavior and performance with regards to moving away from a light source varies strongly.
{"title":"Phototactic Movement of Battery-Powered and Self-Charging Robot Swarms","authors":"A. Cheraghi, Fabio Schloesser Vila, Kalman Graffi","doi":"10.1109/ACIRS49895.2020.9162628","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162628","url":null,"abstract":"In biology, phototaxing is one of the many forms of directed motions that organisms can exhibit. If stimulated by light, these organisms can move towards or away from the source. In this paper we present an algorithm that is reliably capable of moving a swarm of virtual robots away from a light source, all while the individual virtual robots are incapable of determining the direction and origin of the light source. The individual agents cannot generate phototactic behavior by themselves, instead this is realized through the overall, emergent behavior of the swarm. This paper explores an algorithm to produce phototactic movement in swarms of virtual robots. The algorithm is developed so that robots in a swarm of any size can execute it in a decentralized fashion, without the need for any globalized control or communication between them. We explore two different sets of virtual robots, one with self-charging and one with battery-powered characteristics. In a rigorous testing and evaluation we find that the swarms behavior and performance with regards to moving away from a light source varies strongly.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123737050","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 : 2020-07-01DOI: 10.1109/acirs49895.2020.9162602
Zhenzhen Zhou, Yunhai Song, Pengfei Xiang, Su Fang
The integration of big data analysis technology into the state monitoring of substation equipment can improve the utilization rate of state monitoring data, information sharing and data analysis ability. In this paper, three distributed data analysis schemes, namely Hive relational online analysis (ROLAP), Impala relational online analysis (ROLAP) and HBase multidimensional online analysis (MOLAP), were proposed based on the business development requirements of power system and the storage performance and analysis efficiency of traditional state monitoring platform. The experimental results show that the data loading speed is slower than the conventional model, but the roll-up performance and storage overhead are better than the conventional mathematical model. The load time is approximately 1.7 to 1.9 times that of the regular data model. The validity and feasibility of the model are verified by experiments.
{"title":"Research on Improving Intelligent Inspection Efficiency of Substation Based on Big Data Analysis","authors":"Zhenzhen Zhou, Yunhai Song, Pengfei Xiang, Su Fang","doi":"10.1109/acirs49895.2020.9162602","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162602","url":null,"abstract":"The integration of big data analysis technology into the state monitoring of substation equipment can improve the utilization rate of state monitoring data, information sharing and data analysis ability. In this paper, three distributed data analysis schemes, namely Hive relational online analysis (ROLAP), Impala relational online analysis (ROLAP) and HBase multidimensional online analysis (MOLAP), were proposed based on the business development requirements of power system and the storage performance and analysis efficiency of traditional state monitoring platform. The experimental results show that the data loading speed is slower than the conventional model, but the roll-up performance and storage overhead are better than the conventional mathematical model. The load time is approximately 1.7 to 1.9 times that of the regular data model. The validity and feasibility of the model are verified by experiments.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131706483","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162627
Zepeng Hao, Jingzhou Ji, Tao Xie, Bin Xue
Abstractive text summarization task is mainly through deep learning method to summarize one or more documents to produce a concise summary that can express the main meaning of the document. Most methods are mainly based on the traditional Seq2Seq structure, but the traditional Seq2Seq structure has limited ability to capture and store long-term features and global features, resulting in a lack of information in the generated summary. In our paper, we put forward a new abstractive summarization model based on feature-enhanced Seq2Seq structure for single document summarization task. This model utilizes two types of feature capture networks to improve the encoder and decoder in traditional Seq2Seq structure, to enhance the model’s ability to capture and store long-term features and global features, so that the generated summary more informative and more fluency. Finally, we verified the model we proposed on the CNN/DailyMail dataset. Experimental results demonstrate that the model proposed in this paper is more effective than the baseline model, and has improved by 5.6%, 5.3%, 6.2% on the three metrics R-1, R-2, and R-L.
{"title":"Abstractive Summarization Model with a Feature-Enhanced Seq2Seq Structure","authors":"Zepeng Hao, Jingzhou Ji, Tao Xie, Bin Xue","doi":"10.1109/ACIRS49895.2020.9162627","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162627","url":null,"abstract":"Abstractive text summarization task is mainly through deep learning method to summarize one or more documents to produce a concise summary that can express the main meaning of the document. Most methods are mainly based on the traditional Seq2Seq structure, but the traditional Seq2Seq structure has limited ability to capture and store long-term features and global features, resulting in a lack of information in the generated summary. In our paper, we put forward a new abstractive summarization model based on feature-enhanced Seq2Seq structure for single document summarization task. This model utilizes two types of feature capture networks to improve the encoder and decoder in traditional Seq2Seq structure, to enhance the model’s ability to capture and store long-term features and global features, so that the generated summary more informative and more fluency. Finally, we verified the model we proposed on the CNN/DailyMail dataset. Experimental results demonstrate that the model proposed in this paper is more effective than the baseline model, and has improved by 5.6%, 5.3%, 6.2% on the three metrics R-1, R-2, and R-L.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132789257","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162619
Yunhai Song, Zhenzhen Zhou, Pengfei Xiang, Su Fang
To improve the automatic operation of remote video monitoring equipment of substation, improve the operation efficiency of equipment, and realize the function of automatic self-check, the instrument identification system based on image recognition is studied. Firstly, the research significance of the application of image recognition in instrument recognition is analyzed. On the basis of previous studies, the structure of neuron network is introduced. Then, based on the Scale Invariant Feature Transform (SIFT), the instrument positioning is studied, the Gaussian difference model is constructed, and the reading method is determined, so that the instrument identification system can automatically read. Next, based on SIFT, the instrument identification system is established and the design scheme of the system is proposed. Finally, the experiment proves that the instrument recognition system based on image recognition is able to automatically recognize simple graphical interface and learn independently. This study has a great influence on the research field of image recognition instrument recognition.
{"title":"Instrument Recognition in Transformer Substation Base on Image Recognition Algorithm","authors":"Yunhai Song, Zhenzhen Zhou, Pengfei Xiang, Su Fang","doi":"10.1109/ACIRS49895.2020.9162619","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162619","url":null,"abstract":"To improve the automatic operation of remote video monitoring equipment of substation, improve the operation efficiency of equipment, and realize the function of automatic self-check, the instrument identification system based on image recognition is studied. Firstly, the research significance of the application of image recognition in instrument recognition is analyzed. On the basis of previous studies, the structure of neuron network is introduced. Then, based on the Scale Invariant Feature Transform (SIFT), the instrument positioning is studied, the Gaussian difference model is constructed, and the reading method is determined, so that the instrument identification system can automatically read. Next, based on SIFT, the instrument identification system is established and the design scheme of the system is proposed. Finally, the experiment proves that the instrument recognition system based on image recognition is able to automatically recognize simple graphical interface and learn independently. This study has a great influence on the research field of image recognition instrument recognition.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109999","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162618
C. Li, Dehua Zheng, Lizheng Liu, Xiaochen Zheng
Unmanned Aerial Vehicle (UAV) has overwhelming superiority on the completion of difficult missions in the industrial production or implementation scenarios. Its brilliant navigation and on-board perception abilities endow the aerial platform a considerable potential in the industrial applications. Since manipulation stability and computational capacity of UAVs are crucial for industrial missions, it is challenging to develop a reliable and safe UAV platform for indoor industrial operation. Focusing on the measurement of industrial-standard gauges, we propose a vision algorithm which is capable of fast detecting the industrial-standard gauges and the readings and integrate the algorithm into a quadrotor drone platform with indoor and outdoor navigation. In our work, we demonstrate how to improve the simplicity and efficiency of the UAV-based visual recognition by implementing and adjusting a YOLO v3 framework with Darknet [1]. Moreover, our vision algorithm is combined with the image geometric correction module and the gauge detecting and reading module to overcome the detection problems caused by the harsh industrial conditions, such as an obscure image and the under-exposure condition. And the results show that accuracy of detection in the experimentation is sufficient for industrial missions.
{"title":"A UAV-Based Machine Vision Algorithm for Industrial Gauge Detecting and Display Reading","authors":"C. Li, Dehua Zheng, Lizheng Liu, Xiaochen Zheng","doi":"10.1109/ACIRS49895.2020.9162618","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162618","url":null,"abstract":"Unmanned Aerial Vehicle (UAV) has overwhelming superiority on the completion of difficult missions in the industrial production or implementation scenarios. Its brilliant navigation and on-board perception abilities endow the aerial platform a considerable potential in the industrial applications. Since manipulation stability and computational capacity of UAVs are crucial for industrial missions, it is challenging to develop a reliable and safe UAV platform for indoor industrial operation. Focusing on the measurement of industrial-standard gauges, we propose a vision algorithm which is capable of fast detecting the industrial-standard gauges and the readings and integrate the algorithm into a quadrotor drone platform with indoor and outdoor navigation. In our work, we demonstrate how to improve the simplicity and efficiency of the UAV-based visual recognition by implementing and adjusting a YOLO v3 framework with Darknet [1]. Moreover, our vision algorithm is combined with the image geometric correction module and the gauge detecting and reading module to overcome the detection problems caused by the harsh industrial conditions, such as an obscure image and the under-exposure condition. And the results show that accuracy of detection in the experimentation is sufficient for industrial missions.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127295928","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 : 2020-07-01DOI: 10.1109/acirs49895.2020.9162614
A. Cheraghi, Julian Zenz, Kalman Graffi
This paper evaluates and compares two routing algorithms for message passing in opportunistic peer-to-peer networks in the swarm network simulator Swarm-Sim. The two considered algorithms, Epidemic Routing and PRoPHET Routing, are compared in terms of delivery rates, efficiency and overhead, while presenting different mobility models. By this, we combine a variation of mobility models and a set of communication protocols, measuring their impact on the swarm behavior. Message delivery rates for Epidemic routing are considerably and consistently better. However, PRoPHET generates less overhead than Epidemic Routing independent of mobility models and scenarios. The measured overhead of Epidemic exceeded that of PRoPHET by about 100%. Memory requirements for keeping delivery probabilities - used by PRoPHET to circumvent flooding - might be a limitation as they must be kept locally per peer, this detail offers aspects for further research in the future. Finally, this paper demonstrates Swarm-Sim to be a viable alternative to simulate routing protocols in opportunistic peer to peer networks without requiring great insight into the simulator’s architecture and thus establishing itself as an easy to use simulator. It achieves simplicity without yielding any of flexibility of application.
{"title":"Opportunistic Network Behavior in a Swarm: Passing Messages to Destination","authors":"A. Cheraghi, Julian Zenz, Kalman Graffi","doi":"10.1109/acirs49895.2020.9162614","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162614","url":null,"abstract":"This paper evaluates and compares two routing algorithms for message passing in opportunistic peer-to-peer networks in the swarm network simulator Swarm-Sim. The two considered algorithms, Epidemic Routing and PRoPHET Routing, are compared in terms of delivery rates, efficiency and overhead, while presenting different mobility models. By this, we combine a variation of mobility models and a set of communication protocols, measuring their impact on the swarm behavior. Message delivery rates for Epidemic routing are considerably and consistently better. However, PRoPHET generates less overhead than Epidemic Routing independent of mobility models and scenarios. The measured overhead of Epidemic exceeded that of PRoPHET by about 100%. Memory requirements for keeping delivery probabilities - used by PRoPHET to circumvent flooding - might be a limitation as they must be kept locally per peer, this detail offers aspects for further research in the future. Finally, this paper demonstrates Swarm-Sim to be a viable alternative to simulate routing protocols in opportunistic peer to peer networks without requiring great insight into the simulator’s architecture and thus establishing itself as an easy to use simulator. It achieves simplicity without yielding any of flexibility of application.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124724990","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162626
Sebastian Hoose, Daniel Sendzik, J. Jost, T. Kirks
This paper introduces a framework for behavior modeling of software agents using the Robot Operating System. We developed a framework to simplify behavior design and model conventional software agent design principles as known for example from belief desire intention BDI agents or adaptive agents. We provide a toolbox that is capable of supporting the developer with easy to implement methods written in python. Finally we present two brief example applications and evaluations in both simulation and using a social automated transport vehicle for intralogistical processes.
{"title":"A Flexible High and Low Level Multi Task Behavior Framework for Multi-agent Systems in Complex Environments","authors":"Sebastian Hoose, Daniel Sendzik, J. Jost, T. Kirks","doi":"10.1109/ACIRS49895.2020.9162626","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162626","url":null,"abstract":"This paper introduces a framework for behavior modeling of software agents using the Robot Operating System. We developed a framework to simplify behavior design and model conventional software agent design principles as known for example from belief desire intention BDI agents or adaptive agents. We provide a toolbox that is capable of supporting the developer with easy to implement methods written in python. Finally we present two brief example applications and evaluations in both simulation and using a social automated transport vehicle for intralogistical processes.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128057415","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 : 2020-07-01DOI: 10.1109/ACIRS49895.2020.9162613
A. Cheraghi, Abdelrahman Abdelgalil, Kalman Graffi
This research introduces the design and implementation of a universal systematic 2-dimensional terrain marking and coverage solution. Real world applications such as lawn mowing, mine detection, chemical spill clean-up, and humanitarian search and rescue missions can be automated by employing swarms of autonomous mobile robots to complete the task. In most of these real world applications, efficiency is of utmost importance especially when human lives are involved. The solution proposed builds up on two graph traversal algorithms; Depth First Search (DFS) and Breadth First Search (BFS), where the algorithms are adapted and modified to be utilized for coverage of 2-dimensional isometric grid-like representations of terrains. The solution is developed so that each robot in the swarm would be fully capable of covering and marking any terrain by itself. The efficiency of the solution is optimized by increasing the swarm size, as robots benefit from data sharing in their path planning and self organization within the terrain. Communication between robots enable them to perform on a higher level by benefiting from the collaborative distributed behavior of the swarm as a whole. The communication between particles is decentralized and is carried out at a local level with no need for a central guidance mechanism. Robot abilities in this research are limited, where a robot can see and move only to locations that are adjacent to its current location. A simulation based evaluation is conducted in this research to assess the robots’ area coverage and marking performance. The results show that the simulated robot swarm systems are suited for efficient flat area coverage, allowing for redundancy in data collection, and tolerating individual robot errors and shortcomings as the number of robots becomes more abundant.
{"title":"Universal 2-Dimensional Terrain Marking for Autonomous Robot Swarms","authors":"A. Cheraghi, Abdelrahman Abdelgalil, Kalman Graffi","doi":"10.1109/ACIRS49895.2020.9162613","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162613","url":null,"abstract":"This research introduces the design and implementation of a universal systematic 2-dimensional terrain marking and coverage solution. Real world applications such as lawn mowing, mine detection, chemical spill clean-up, and humanitarian search and rescue missions can be automated by employing swarms of autonomous mobile robots to complete the task. In most of these real world applications, efficiency is of utmost importance especially when human lives are involved. The solution proposed builds up on two graph traversal algorithms; Depth First Search (DFS) and Breadth First Search (BFS), where the algorithms are adapted and modified to be utilized for coverage of 2-dimensional isometric grid-like representations of terrains. The solution is developed so that each robot in the swarm would be fully capable of covering and marking any terrain by itself. The efficiency of the solution is optimized by increasing the swarm size, as robots benefit from data sharing in their path planning and self organization within the terrain. Communication between robots enable them to perform on a higher level by benefiting from the collaborative distributed behavior of the swarm as a whole. The communication between particles is decentralized and is carried out at a local level with no need for a central guidance mechanism. Robot abilities in this research are limited, where a robot can see and move only to locations that are adjacent to its current location. A simulation based evaluation is conducted in this research to assess the robots’ area coverage and marking performance. The results show that the simulated robot swarm systems are suited for efficient flat area coverage, allowing for redundancy in data collection, and tolerating individual robot errors and shortcomings as the number of robots becomes more abundant.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132976744","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：