An open, unified and loosely coupled service oriented software architecture of UAV Ground Control System (UGCS) based on container cloud platform is proposed in this paper, which is called “UCSAM”, and can support the collaborative control of UAV among multi-form ground control stations, such as portable, mobile and fixed stations. UCSAM establishes a kind of software computing environment based on the component framework conforming to the OSGi specifications on the client side, the container cloud platform on the server side, and the middleware conforming to the DDS and other transmission protocols between the two, so that the application software components on the client side and the FDSCs(Functional Domain Service Components) on the server side only rely on standardized APIs, so as to realize the architecture features of resource allocation on demand and cross platform portability. On the other hand, UCSAM defines PSM based on Open Application Model (OAM), including message model, service model and application model, which separates FDSC development from the operation and maintenance complexity of infrastructure software. Through a set of tool chains, it realizes the conversion from PIM based on XMI format to PSM based on OAM, code generation based on template and PSM, CI/CD based on GitOps, and dynamic deployment based on AppStore, so as to achieve the architectural goal of dynamic generation of capabilities, and the agile software development mode based on MDA and DevOps. Lastly, several study cases including UAV cooperative application, development of functional domain service components, and application deployment and operation are briefly discussed to verify this architecture's correctness and feasibility.
提出了一种开放、统一、松散耦合、基于容器云平台的无人机地面控制系统(UGCS)面向服务的软件体系结构，即UCSAM，可支持无人机在便携式、移动式、固定式多形式地面控制站之间的协同控制。UCSAM在客户端建立了一种符合OSGi规范的组件框架，在服务器端建立了容器云平台，在两者之间建立了一种符合DDS等传输协议的中间件的软件计算环境，使得客户端应用软件组件和服务器端功能域服务组件(fdsc, Functional Domain Service components)只依赖标准化的api。从而实现资源按需分配和跨平台可移植性的体系结构特点。另一方面，UCSAM基于开放应用模型(OAM)定义了PSM，包括消息模型、服务模型和应用模型，将FDSC开发与基础设施软件的运维复杂性分离开来。通过一套工具链，实现了从基于XMI格式的PIM到基于OAM的PSM、基于模板和PSM的代码生成、基于GitOps的CI/CD、基于AppStore的动态部署的转换，从而达到动态生成能力的架构目标，以及基于MDA和DevOps的敏捷软件开发模式。最后，简要讨论了无人机协同应用、功能领域服务组件开发、应用部署与运行等研究案例，验证了该体系结构的正确性和可行性。
{"title":"UCSAM: A UAV Ground Control System Architecture Supporting Cooperative Control Among Multi-form Stations based on MDA and Container Cloud Platform","authors":"Fengyi Jiang, Yongfei Ding, Hao Zhang, Zefan Li, Ruonan Rao","doi":"10.1109/ICUS55513.2022.9986525","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986525","url":null,"abstract":"An open, unified and loosely coupled service oriented software architecture of UAV Ground Control System (UGCS) based on container cloud platform is proposed in this paper, which is called “UCSAM”, and can support the collaborative control of UAV among multi-form ground control stations, such as portable, mobile and fixed stations. UCSAM establishes a kind of software computing environment based on the component framework conforming to the OSGi specifications on the client side, the container cloud platform on the server side, and the middleware conforming to the DDS and other transmission protocols between the two, so that the application software components on the client side and the FDSCs(Functional Domain Service Components) on the server side only rely on standardized APIs, so as to realize the architecture features of resource allocation on demand and cross platform portability. On the other hand, UCSAM defines PSM based on Open Application Model (OAM), including message model, service model and application model, which separates FDSC development from the operation and maintenance complexity of infrastructure software. Through a set of tool chains, it realizes the conversion from PIM based on XMI format to PSM based on OAM, code generation based on template and PSM, CI/CD based on GitOps, and dynamic deployment based on AppStore, so as to achieve the architectural goal of dynamic generation of capabilities, and the agile software development mode based on MDA and DevOps. Lastly, several study cases including UAV cooperative application, development of functional domain service components, and application deployment and operation are briefly discussed to verify this architecture's correctness and feasibility.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122215220","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}
In this paper, a novel image-based visual servoing (IBVS) approach is proposed for a fully-actuated hexacopter, which allows to maintain a stable attitude with the horizontal movement. In contrast to the existing methods, the key insight is to integrate the IBVS method to the fully-actuated hexacopter, which can alleviate the field of view (FOV) constraint. Specifically, the nonlinear hierarchical position and attitude controller is designed based on its dynamic characteristics. In the outer loop, an new IBVS method with perspective moments is employed to design the force input. The inner loop utilizes the quaternion to generate the torque input. Comparative simulations are conducted to verify that the proposed method can relax the FOV constraint greatly.
{"title":"Image-Based Visual Servoing of a Fully-Actuated Hexacopter","authors":"Xuetao Zhang, Zhicheng Li, Yisha Liu, Hanzhang Wang, Xuebo Zhang, Yan Zhuang","doi":"10.1109/ICUS55513.2022.9986822","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986822","url":null,"abstract":"In this paper, a novel image-based visual servoing (IBVS) approach is proposed for a fully-actuated hexacopter, which allows to maintain a stable attitude with the horizontal movement. In contrast to the existing methods, the key insight is to integrate the IBVS method to the fully-actuated hexacopter, which can alleviate the field of view (FOV) constraint. Specifically, the nonlinear hierarchical position and attitude controller is designed based on its dynamic characteristics. In the outer loop, an new IBVS method with perspective moments is employed to design the force input. The inner loop utilizes the quaternion to generate the torque input. Comparative simulations are conducted to verify that the proposed method can relax the FOV constraint greatly.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121767699","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9986967
Y. Huang, Jianing Zhao, Weiyao Lan, Xiao Yu
In this paper, the bearing-only leader-follower formation control problem for nonholonomic mobile agents in local reference frames is studied. The sensing/communication topology of multi-agent systems is modeled by an undirected graph. The target formation is specified by bearing constraints. The autonomous leaders are moving with a constant velocity which is known to only some followers. Each follower merely measures the bearings and relative orientations of its neighboring agents which are acquired in its local reference frame. To estimate the leaders' information, a distributed observer for each follower is designed. Then, we combine the observer and a developed bearing-only control law with the estimate into a dynamic control law, such that the target formation can be achieved. Finally, we present a simulation example to show the effectiveness of the proposed approach.
{"title":"Bearing-Only Formation Control of Nonholonomic Mobile Agents With Local Reference Frames","authors":"Y. Huang, Jianing Zhao, Weiyao Lan, Xiao Yu","doi":"10.1109/ICUS55513.2022.9986967","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986967","url":null,"abstract":"In this paper, the bearing-only leader-follower formation control problem for nonholonomic mobile agents in local reference frames is studied. The sensing/communication topology of multi-agent systems is modeled by an undirected graph. The target formation is specified by bearing constraints. The autonomous leaders are moving with a constant velocity which is known to only some followers. Each follower merely measures the bearings and relative orientations of its neighboring agents which are acquired in its local reference frame. To estimate the leaders' information, a distributed observer for each follower is designed. Then, we combine the observer and a developed bearing-only control law with the estimate into a dynamic control law, such that the target formation can be achieved. Finally, we present a simulation example to show the effectiveness of the proposed approach.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132105225","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9987158
Mingjia Zhang, Huawei Liang, Pengfei Zhou
Heterogeneous UGV-UAV system can efficiently complete large-scale tasks such as exploration and rescue by collaborative operation. This paper proposes a route planner based on a dynamic aggregation strategy to select the time-optimal routes for function-constrained UGV and fuel-constrained UAV to reach all the mission points. To reduce the time consumption of waiting at the take-off point, UGV and UAV are inclined to rendezvous at the next meeting point by no-wait operations. We present a two-step routing strategy to address this cooperative problem. First, the Voronoi diagram and greedy set cover method are used to determine meeting points and task areas. Then, solving a traveling salesman problem to find a UGV path by A-star and Lin-Kernighan heuristic. After that, an adaptive large neighborhood search heuristic is proposed to address vehicle routing problem with recharge for UAV among multiple task areas. The simulation and real experiment results demonstrate that our approach can effectively generate a time-optimal path for UGV-UAV Cooperative exploration.
{"title":"Cooperative Route Planning for Fuel-constrained UGV-UAV Exploration","authors":"Mingjia Zhang, Huawei Liang, Pengfei Zhou","doi":"10.1109/ICUS55513.2022.9987158","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987158","url":null,"abstract":"Heterogeneous UGV-UAV system can efficiently complete large-scale tasks such as exploration and rescue by collaborative operation. This paper proposes a route planner based on a dynamic aggregation strategy to select the time-optimal routes for function-constrained UGV and fuel-constrained UAV to reach all the mission points. To reduce the time consumption of waiting at the take-off point, UGV and UAV are inclined to rendezvous at the next meeting point by no-wait operations. We present a two-step routing strategy to address this cooperative problem. First, the Voronoi diagram and greedy set cover method are used to determine meeting points and task areas. Then, solving a traveling salesman problem to find a UGV path by A-star and Lin-Kernighan heuristic. After that, an adaptive large neighborhood search heuristic is proposed to address vehicle routing problem with recharge for UAV among multiple task areas. The simulation and real experiment results demonstrate that our approach can effectively generate a time-optimal path for UGV-UAV Cooperative exploration.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132122862","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9986777
Jianan Wang, Longze Zhao, Kewei Xia
This paper considers a team of unmanned aerial vehicle (UAV) carrying a capture net as an approach to intercept an aerial intruder. The center of the net is deemed as a virtual interceptor for maneuvering the net approach to the intruder. The UAV team tows the net tensioned so that the can orientate the net plane to an appropriate orientation during the guidance process by controlling the acceleration of each UAV. Simulation results are presented to verify the effectiveness of this intercepting strategy.
{"title":"A Discrete-time Intercepting Strategy for Net Capture Using Multiple Unmanned Aerial Vehicles","authors":"Jianan Wang, Longze Zhao, Kewei Xia","doi":"10.1109/ICUS55513.2022.9986777","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986777","url":null,"abstract":"This paper considers a team of unmanned aerial vehicle (UAV) carrying a capture net as an approach to intercept an aerial intruder. The center of the net is deemed as a virtual interceptor for maneuvering the net approach to the intruder. The UAV team tows the net tensioned so that the can orientate the net plane to an appropriate orientation during the guidance process by controlling the acceleration of each UAV. Simulation results are presented to verify the effectiveness of this intercepting strategy.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131713002","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}
With the intention of suppressing the aerodynamic/elasticity/control coupling of elastic hypersonic glide vehicles without adding new kinds of sensors and actuators, a kind of hierarchical sliding mode controller based on moving horizon estimation is proposed. In this controller, a kind of moving horizon estimation algorithm is utilized to obtain the full-state information online, based on which the hierarchical sliding mode controller is designed. The hierarchical sliding mode controller based on moving horizon estimation only uses elevator deflection to control the attitude and attenuate the elastic vibration simultaneously. Numerical simulations are carried out to demonstrate that the moving horizon estimation method can provide accurate full state information, and the hierarchical sliding mode control can control the attitude and suppress the elastic vibration simultaneously.
{"title":"Hierarchical Sliding Mode Control for Elastic Hypersonic Glide Vehicles Based on Moving Horizon Estimation","authors":"Erkang Chen, Liangcong Zhu, Wei Qiu, Chao Ren, Ding Zhou, Dongzheng Kuang","doi":"10.1109/ICUS55513.2022.9987017","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987017","url":null,"abstract":"With the intention of suppressing the aerodynamic/elasticity/control coupling of elastic hypersonic glide vehicles without adding new kinds of sensors and actuators, a kind of hierarchical sliding mode controller based on moving horizon estimation is proposed. In this controller, a kind of moving horizon estimation algorithm is utilized to obtain the full-state information online, based on which the hierarchical sliding mode controller is designed. The hierarchical sliding mode controller based on moving horizon estimation only uses elevator deflection to control the attitude and attenuate the elastic vibration simultaneously. Numerical simulations are carried out to demonstrate that the moving horizon estimation method can provide accurate full state information, and the hierarchical sliding mode control can control the attitude and suppress the elastic vibration simultaneously.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130791845","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9986554
Lingfei Su, Xiwang Dong, Yongzhao Hua, Jianglong Yu, Z. Ren
This paper presents the multi-target tracking (MTT) problem in decentralized large-scale sensor networks. A novel random finite set (RFS)-based framework is designed, including an improved Probability Hypothesis Density filter with Gaussian Mixture (GM-PHD) representation, and an improved Generalized Covariance Intersection (GCI) fusion algorithm. For the local GM-PHD filter, the intensity of new-born targets is initialized by pre-segmenting the measurement set to address the uncertainty of measurement origin and the computational burden of large-scale measurements. Then, a sensor node-dependent clutter model is established to deal with the cardinality overestimation problem brought by the decentralized structure. For the proposed fusion algorithm, i.e., fusing the posterior PHDs generated by the proposed GM-PHD filters in a distributed manner, it is based on the idea of compensating the severe missed detection problem of GCI in the case of large-scale fusing resources by arithmetic average (AA) fusion. In this way, GCI and AA can be fully utilized to guarantee the estimation accuracy for common targets and, respectively, the robustness for exclusive targets. A simulation of a decentralized large-scale network demonstrates the effectiveness of the proposed framework with respect to estimation accuracy and computational cost.
{"title":"Multi-target Tracking with Random Finite Set in Decentralized Large-scale Sensor Networks","authors":"Lingfei Su, Xiwang Dong, Yongzhao Hua, Jianglong Yu, Z. Ren","doi":"10.1109/ICUS55513.2022.9986554","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9986554","url":null,"abstract":"This paper presents the multi-target tracking (MTT) problem in decentralized large-scale sensor networks. A novel random finite set (RFS)-based framework is designed, including an improved Probability Hypothesis Density filter with Gaussian Mixture (GM-PHD) representation, and an improved Generalized Covariance Intersection (GCI) fusion algorithm. For the local GM-PHD filter, the intensity of new-born targets is initialized by pre-segmenting the measurement set to address the uncertainty of measurement origin and the computational burden of large-scale measurements. Then, a sensor node-dependent clutter model is established to deal with the cardinality overestimation problem brought by the decentralized structure. For the proposed fusion algorithm, i.e., fusing the posterior PHDs generated by the proposed GM-PHD filters in a distributed manner, it is based on the idea of compensating the severe missed detection problem of GCI in the case of large-scale fusing resources by arithmetic average (AA) fusion. In this way, GCI and AA can be fully utilized to guarantee the estimation accuracy for common targets and, respectively, the robustness for exclusive targets. A simulation of a decentralized large-scale network demonstrates the effectiveness of the proposed framework with respect to estimation accuracy and computational cost.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133600539","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9987212
Xianzhe Liu, Xuting Duan, Jianshan Zhou, Long Zhang
In this paper, we propose a platoon controller design approach for the vehicular platoon with bounded external disturbances. The vehicle communication between followers are bidirectional, and the leader can transmit its state to all followers. To make sure the platoon can converge to the leader's state with external disturbances, a distributed discontinuous controller is proposed. By introducing input-to-state string stability (ISSS), the states of all followers are proved to be convergent under the leader's bounded inputs and each follower's bounded external disturbances. After solving the linear matrix inequality (LMI) obtained from the convergence analysis, we get the feedback control gains which can make the vehicle platoon stabilized. Besides, with some minor changes to the theorem, the controller can also apply to the platoon system without disturbances. Finally, the effectiveness of the control scheme is confirmed by some numerical simulations.
{"title":"Distributed Platoon Control of Connected Vehicles Based on Input-to-state String Stability","authors":"Xianzhe Liu, Xuting Duan, Jianshan Zhou, Long Zhang","doi":"10.1109/ICUS55513.2022.9987212","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987212","url":null,"abstract":"In this paper, we propose a platoon controller design approach for the vehicular platoon with bounded external disturbances. The vehicle communication between followers are bidirectional, and the leader can transmit its state to all followers. To make sure the platoon can converge to the leader's state with external disturbances, a distributed discontinuous controller is proposed. By introducing input-to-state string stability (ISSS), the states of all followers are proved to be convergent under the leader's bounded inputs and each follower's bounded external disturbances. After solving the linear matrix inequality (LMI) obtained from the convergence analysis, we get the feedback control gains which can make the vehicle platoon stabilized. Besides, with some minor changes to the theorem, the controller can also apply to the platoon system without disturbances. Finally, the effectiveness of the control scheme is confirmed by some numerical simulations.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133640370","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9987020
Zhuming Nie, Ying Wang, Yuhan Shi
The intelligent marking technology can effectively improve and solve the problems existing in online manual marking due to its high efficiency, high accuracy, and high reliability. However, there are still many problems in the technology, process, function, and safety of intelligent marking of subjective questions, which need to be improved urgently. This research deeply excavates and investigates the cases and personnel related to bright marking and puts forward corresponding suggestions based on specific problems while obtaining first-hand information on intelligent marking of subjective questions. Existing issues in brilliancy marking of personal questions: insufficient text recognition accuracy, complex recognition model training process; philosophical algorithm logic are complicated to “override”, and data are not traceable; the intelligent marking model is single, lacking a replication mechanism. Based on three problems, the following solutions are proposed: text recognition model based on detection-recognition correction mechanism; intelligent sample selection mechanism based on text clustering analysis; new smart marking mode based on the fusion of manual marking and machine marking.
{"title":"Analysis of Subjective Question Correction Based on OM/QM Intelligent Marking System","authors":"Zhuming Nie, Ying Wang, Yuhan Shi","doi":"10.1109/ICUS55513.2022.9987020","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987020","url":null,"abstract":"The intelligent marking technology can effectively improve and solve the problems existing in online manual marking due to its high efficiency, high accuracy, and high reliability. However, there are still many problems in the technology, process, function, and safety of intelligent marking of subjective questions, which need to be improved urgently. This research deeply excavates and investigates the cases and personnel related to bright marking and puts forward corresponding suggestions based on specific problems while obtaining first-hand information on intelligent marking of subjective questions. Existing issues in brilliancy marking of personal questions: insufficient text recognition accuracy, complex recognition model training process; philosophical algorithm logic are complicated to “override”, and data are not traceable; the intelligent marking model is single, lacking a replication mechanism. Based on three problems, the following solutions are proposed: text recognition model based on detection-recognition correction mechanism; intelligent sample selection mechanism based on text clustering analysis; new smart marking mode based on the fusion of manual marking and machine marking.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133109018","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 : 2022-10-28DOI: 10.1109/ICUS55513.2022.9987014
Zhaohuang Zheng, Ting Yong, Jiaxin Li, Zhijin Wen
As a new type of mobile ad hoc network, UAANET (UAV Ad Hoc Network) provides a communication foundation for the realization of the ability of UAV swarm such as high coordination and intelligent control. However, the research on routing protocols is severely challenged by the characteristics of UAANET such as high-speed mobility and dynamic topology. The simulation research on the applicability of routing protocols for UAANET scene provides reference and guidance for solving related problems, which is of great significance. In this paper, the BATMNAN-ADV (Better Approach To Mobile Ad-Hoc Networking Advanced) simulation model is established based on the OPNET simulation tool, and simulation research is carried out for the scene of UAANET. The simulation results show that, compared with OLSR and AODV, BATMAN-ADV is more suitable for application in large-scale, high-dynamic, and high-load UAANET scenes.
UAANET (UAV ad hoc network)作为一种新型的移动自组网，为实现无人机群的高度协调和智能控制等能力提供了通信基础。然而，由于UAANET具有高速移动性和动态拓扑等特点，路由协议的研究面临着严峻的挑战。对路由协议在UAANET场景下的适用性进行仿真研究，为解决相关问题提供参考和指导，具有重要意义。本文基于OPNET仿真工具，建立了BATMNAN-ADV (Better Approach To Mobile Ad-Hoc Networking Advanced)仿真模型，并对UAANET场景进行了仿真研究。仿真结果表明，与OLSR和AODV相比，BATMAN-ADV更适合应用于大规模、高动态、高负载的UAANET场景。
{"title":"Simulation Research of UAANET Based on BATMAN-ADV Routing Protocol","authors":"Zhaohuang Zheng, Ting Yong, Jiaxin Li, Zhijin Wen","doi":"10.1109/ICUS55513.2022.9987014","DOIUrl":"https://doi.org/10.1109/ICUS55513.2022.9987014","url":null,"abstract":"As a new type of mobile ad hoc network, UAANET (UAV Ad Hoc Network) provides a communication foundation for the realization of the ability of UAV swarm such as high coordination and intelligent control. However, the research on routing protocols is severely challenged by the characteristics of UAANET such as high-speed mobility and dynamic topology. The simulation research on the applicability of routing protocols for UAANET scene provides reference and guidance for solving related problems, which is of great significance. In this paper, the BATMNAN-ADV (Better Approach To Mobile Ad-Hoc Networking Advanced) simulation model is established based on the OPNET simulation tool, and simulation research is carried out for the scene of UAANET. The simulation results show that, compared with OLSR and AODV, BATMAN-ADV is more suitable for application in large-scale, high-dynamic, and high-load UAANET scenes.","PeriodicalId":345773,"journal":{"name":"2022 IEEE International Conference on Unmanned Systems (ICUS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128906906","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：