Pub Date : 2021-07-10DOI: 10.1142/s2301385022500054
Sufal Chandra Swar, Suresh Manickam, D. Casbeer, K. Kalyanam, S. Darbha
Timely detection of intruders ensures the safety and security of high valued assets within a protected area. This problem takes on particular significance across international borders and becomes challenging when the terrain is porous, rugged and treacherous in nature. Keeping an effective vigil against intruders on large tracts of land is a tedious task; currently, it is primarily performed by security personnel with automatic detection systems in passive supporting roles. This paper discusses an alternate autonomous approach by utilizing one or more Unmanned Vehicles (UVs), aided by smart sensors on the ground, to detect and localize an intruder. To facilitate autonomous UV operations, the region is equipped with Unattended Ground Sensors (UGSs) and laser fencing. Together, these sensors provide time-stamped location information (node and edge detection) of the intruder to a UV. For security reasons, we assume that the sensors are not networked (a central node can be disabled bringing the whole system down) and so, the UVs must visit the vicinity of the sensors to gather the information therein. This makes the problem challenging in that pursuit must be done with local and likely delayed information. We discretize time and space by considering a 2D grid for the area and unit speed for the UV, i.e. it takes one time unit to travel from one node to an adjacent node. The intruder is slower and takes two time steps to complete the same move. We compute the min–max optimal, i.e. minimum number of steps to capture the intruder under worst-case intruder actions, for different number of rows and columns in the grid and for both one and two pursuers.
{"title":"Optimal Autonomous Pursuit of an Intruder on a Grid Aided by Local Node and Edge Sensors","authors":"Sufal Chandra Swar, Suresh Manickam, D. Casbeer, K. Kalyanam, S. Darbha","doi":"10.1142/s2301385022500054","DOIUrl":"https://doi.org/10.1142/s2301385022500054","url":null,"abstract":"Timely detection of intruders ensures the safety and security of high valued assets within a protected area. This problem takes on particular significance across international borders and becomes challenging when the terrain is porous, rugged and treacherous in nature. Keeping an effective vigil against intruders on large tracts of land is a tedious task; currently, it is primarily performed by security personnel with automatic detection systems in passive supporting roles. This paper discusses an alternate autonomous approach by utilizing one or more Unmanned Vehicles (UVs), aided by smart sensors on the ground, to detect and localize an intruder. To facilitate autonomous UV operations, the region is equipped with Unattended Ground Sensors (UGSs) and laser fencing. Together, these sensors provide time-stamped location information (node and edge detection) of the intruder to a UV. For security reasons, we assume that the sensors are not networked (a central node can be disabled bringing the whole system down) and so, the UVs must visit the vicinity of the sensors to gather the information therein. This makes the problem challenging in that pursuit must be done with local and likely delayed information. We discretize time and space by considering a 2D grid for the area and unit speed for the UV, i.e. it takes one time unit to travel from one node to an adjacent node. The intruder is slower and takes two time steps to complete the same move. We compute the min–max optimal, i.e. minimum number of steps to capture the intruder under worst-case intruder actions, for different number of rows and columns in the grid and for both one and two pursuers.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127498844","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 : 2021-06-10DOI: 10.1142/S2301385022500042
Linda Hachemi, M. Guiatni, A. Nemra
In this paper, we propose a new approach for fault tolerant localization using multi-sensors data fusion for a unicycle-type mobile robot. The main contribution of this paper is a new architecture proposal for fault diagnosis and reconfiguration for mobile robot localization using multi-sensors data fusion and the duplication/comparison approach. Four different sensors usually embedded in mobile robots (Camera, IMU, GPS, and Odometer) are considered, while six different sensors couples combinations are used for sensor data fusion and the duplication of the localization and estimation system. In order to reach this aim, three different filters (EKF, SVSF, and ASVSF) have been proposed and compared. For each selected filter, a comparison mechanism is then introduced to compute different residuals by comparing the estimated robot position for each sensor couples separately. Faults are then detected using the structural residual diagnosis method. This approach assumes the occurrence of a single fault at a given time. A reconfiguration mechanism is then applied by selected the healthy sensors couple and their corresponding fusion filter. Several scenarios are considered for navigation-based fault tolerant localization approaches. Simulation results are presented to illustrate the advantage and performance of the proposed architecture. The proposed solutions are implemented and validated successfully using the V-REP simulator.
{"title":"Fault Diagnosis and Reconfiguration for Mobile Robot Localization Based on Multi-Sensors Data Fusion","authors":"Linda Hachemi, M. Guiatni, A. Nemra","doi":"10.1142/S2301385022500042","DOIUrl":"https://doi.org/10.1142/S2301385022500042","url":null,"abstract":"In this paper, we propose a new approach for fault tolerant localization using multi-sensors data fusion for a unicycle-type mobile robot. The main contribution of this paper is a new architecture proposal for fault diagnosis and reconfiguration for mobile robot localization using multi-sensors data fusion and the duplication/comparison approach. Four different sensors usually embedded in mobile robots (Camera, IMU, GPS, and Odometer) are considered, while six different sensors couples combinations are used for sensor data fusion and the duplication of the localization and estimation system. In order to reach this aim, three different filters (EKF, SVSF, and ASVSF) have been proposed and compared. For each selected filter, a comparison mechanism is then introduced to compute different residuals by comparing the estimated robot position for each sensor couples separately. Faults are then detected using the structural residual diagnosis method. This approach assumes the occurrence of a single fault at a given time. A reconfiguration mechanism is then applied by selected the healthy sensors couple and their corresponding fusion filter. Several scenarios are considered for navigation-based fault tolerant localization approaches. Simulation results are presented to illustrate the advantage and performance of the proposed architecture. The proposed solutions are implemented and validated successfully using the V-REP simulator.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127977508","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 : 2021-05-14DOI: 10.1142/S2301385022500017
E. Altuğ, Abdullah Türkmen
Significant progress has been made in recent years on personal air vehicles (PAVs), which offer independent and autonomous urban transportation. On-demand parcel delivery drones and heavy-lift drones are gaining serious attention. Although various designs for these systems have been put forward, they still have not reached sufficient maturity. The current systems provide somehow satisfactory operation, but many of these systems are limited in payload capacity and flight duration, and not suitable for future operations. In this paper, we propose a novel thrust system that uses multiple mini jet engines. Unlike electric motors, the jet engine thrust cannot vary rapidly. This led us to design and develop a thrust vectoring system for each jet engine. This proposed system has the potential to enable drones to carry more payload and achieve longer flight times. This paper discusses the design and modeling of the system as well as the stabilization algorithms that satisfactorily stabilize the proposed system. We presented that due to motor lag, thrust variations cannot stabilize the vehicle. We showed that the use of a thrust vectoring mechanism with LQR-based controller can overcome the effects of motor lag and stabilize the vehicle, successfully.
{"title":"A Novel Mini Jet Engine Powered Unmanned Aerial Vehicle: Modeling and Control","authors":"E. Altuğ, Abdullah Türkmen","doi":"10.1142/S2301385022500017","DOIUrl":"https://doi.org/10.1142/S2301385022500017","url":null,"abstract":"Significant progress has been made in recent years on personal air vehicles (PAVs), which offer independent and autonomous urban transportation. On-demand parcel delivery drones and heavy-lift drones are gaining serious attention. Although various designs for these systems have been put forward, they still have not reached sufficient maturity. The current systems provide somehow satisfactory operation, but many of these systems are limited in payload capacity and flight duration, and not suitable for future operations. In this paper, we propose a novel thrust system that uses multiple mini jet engines. Unlike electric motors, the jet engine thrust cannot vary rapidly. This led us to design and develop a thrust vectoring system for each jet engine. This proposed system has the potential to enable drones to carry more payload and achieve longer flight times. This paper discusses the design and modeling of the system as well as the stabilization algorithms that satisfactorily stabilize the proposed system. We presented that due to motor lag, thrust variations cannot stabilize the vehicle. We showed that the use of a thrust vectoring mechanism with LQR-based controller can overcome the effects of motor lag and stabilize the vehicle, successfully.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141022","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 : 2021-04-29DOI: 10.1142/S2301385022500029
Shahbaz Khan, M. Tufail, Muhammad Tahir Khan, Z. Khan, J. Iqbal, Arsalan Wasim
Unmanned Aerial Vehicles (UAVs) have been recently used for different civilian applications such as remote sensing, search, and rescue (SAR), precision agriculture (PA), etc. A UAVs ability to sense and find targets remotely and, based on that, hover close to the target for a particular action makes it an ideal platform for the aforementioned applications. There has been extensive work carried out in the field of visual-based detection, navigation, and control, but the problem of detecting different ground targets and performing certain actions is still an open research area. This study proposes a novel framework for multiple target detection, recognition, and navigation of the UAV to the desired target and closely inspect it. This proposed framework can be deployed for accurately spot spraying in PA applications or SAR. The target detection and recognition in the framework are achieved through a computationally efficient Convolutional Neural Network (CNN) trained model, whereas the close inspection of the target is achieved through a PID-based tracking algorithm which ensures the UAV hover around the target for few seconds. The developed framework performed the desired objective in five stages employing Lawson’s control theory of sense, process, compare, decide and act. The target detection and recognition in the framework were validated with the field experiment, while the entire framework was validated through a variety of simulation flights conducted in Gazebo and PX4. The experiments’ results showed the versatility of the developed system to many complex missions where the targets are added or removed.
{"title":"A Novel Framework for Multiple Ground Target Detection, Recognition and Inspection in Precision Agriculture Applications Using a UAV","authors":"Shahbaz Khan, M. Tufail, Muhammad Tahir Khan, Z. Khan, J. Iqbal, Arsalan Wasim","doi":"10.1142/S2301385022500029","DOIUrl":"https://doi.org/10.1142/S2301385022500029","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) have been recently used for different civilian applications such as remote sensing, search, and rescue (SAR), precision agriculture (PA), etc. A UAVs ability to sense and find targets remotely and, based on that, hover close to the target for a particular action makes it an ideal platform for the aforementioned applications. There has been extensive work carried out in the field of visual-based detection, navigation, and control, but the problem of detecting different ground targets and performing certain actions is still an open research area. This study proposes a novel framework for multiple target detection, recognition, and navigation of the UAV to the desired target and closely inspect it. This proposed framework can be deployed for accurately spot spraying in PA applications or SAR. The target detection and recognition in the framework are achieved through a computationally efficient Convolutional Neural Network (CNN) trained model, whereas the close inspection of the target is achieved through a PID-based tracking algorithm which ensures the UAV hover around the target for few seconds. The developed framework performed the desired objective in five stages employing Lawson’s control theory of sense, process, compare, decide and act. The target detection and recognition in the framework were validated with the field experiment, while the entire framework was validated through a variety of simulation flights conducted in Gazebo and PX4. The experiments’ results showed the versatility of the developed system to many complex missions where the targets are added or removed.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117143250","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 : 2021-04-19DOI: 10.1142/S2301385022500030
Kai Feng, Weixing Li, Jun Han, Feng Pan
Visual-based object detection has large applications in security and surveillance for unmanned aerial vehicles (UAVs). Meanwhile, the object detectors are required of low-latency and easy to be deployed on embedded onboard platforms. Aiming to address these problems, we present a PA-YOLOv3 aerial images object detector based on YOLOv3 and PANet algorithms, which can be deployed on embedded platforms. The PA-YOLOv3 model uses the dual-tower structure to improve the feature extraction and expression capabilities in feature fusion stage of the network. Besides, we propose a balanced pruning method to reduce the model size and the imbalance of different feature layers during pruning. After balanced pruning, the latency and size of the model are significantly decreased. Finally, we deploy and quantify the model on the embedded platform with TensorRT technology and apply the model on the UAV system for testing. The comprehensive experiments are executed on VisDrone2018 dataset and real-world scenarios. The experimental results show the inference speed of PA-YOLOv3 boost of about [Formula: see text] model pruning and quantization, while maintaining high detection accuracy.
{"title":"Low-Latency Aerial Images Object Detection for UAV","authors":"Kai Feng, Weixing Li, Jun Han, Feng Pan","doi":"10.1142/S2301385022500030","DOIUrl":"https://doi.org/10.1142/S2301385022500030","url":null,"abstract":"Visual-based object detection has large applications in security and surveillance for unmanned aerial vehicles (UAVs). Meanwhile, the object detectors are required of low-latency and easy to be deployed on embedded onboard platforms. Aiming to address these problems, we present a PA-YOLOv3 aerial images object detector based on YOLOv3 and PANet algorithms, which can be deployed on embedded platforms. The PA-YOLOv3 model uses the dual-tower structure to improve the feature extraction and expression capabilities in feature fusion stage of the network. Besides, we propose a balanced pruning method to reduce the model size and the imbalance of different feature layers during pruning. After balanced pruning, the latency and size of the model are significantly decreased. Finally, we deploy and quantify the model on the embedded platform with TensorRT technology and apply the model on the UAV system for testing. The comprehensive experiments are executed on VisDrone2018 dataset and real-world scenarios. The experimental results show the inference speed of PA-YOLOv3 boost of about [Formula: see text] model pruning and quantization, while maintaining high detection accuracy.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114887430","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 : 2021-04-08DOI: 10.1142/S2301385022300013
S. H. Derrouaoui, Y. Bouzid, M. Guiatni, I. Dib
Recently, reconfigurable drones have gained particular attention in the field of automation and flying robots. Unlike the conventional drones, they are characterized by a variable mechanical structure in flight, geometric adaptability, aerial reconfiguration, high number of actuators and control inputs, and variable mathematical model. In addition, they are exploited to flight in more cluttered environments, avoid collisions with obstacles, transport and grab objects, cross narrow and small spaces, decrease different aerial damages, optimize the consumed energy, and improve agility and maneuverability in flight. Moreover, these new drones are considered as a viable solution to provide them with specific and additional functionalities. They are a promising solution in the near future, since they allow increasing considerably the capabilities and performance of classical drones in terms of multi-functionalities, geometric adaptation, design characteristics, consumed energy, control, maneuverability, agility, efficiency, obstacles avoidance, and fault tolerant control. This paper explores very interesting and recent research works, which include the classification, the main characteristics, the various applications, and the existing designs of this particular class of drones. Besides, an in-depth review of the applied control strategies will be presented. The links of the videos displaying the results of these researches will be also shown. A comparative study between the different types of flying vehicles will be established. Finally, several new challenges and future directions for reconfigurable drones will be discussed.
{"title":"A Comprehensive Review on Reconfigurable Drones: Classification, Characteristics, Design and Control Technologies","authors":"S. H. Derrouaoui, Y. Bouzid, M. Guiatni, I. Dib","doi":"10.1142/S2301385022300013","DOIUrl":"https://doi.org/10.1142/S2301385022300013","url":null,"abstract":"Recently, reconfigurable drones have gained particular attention in the field of automation and flying robots. Unlike the conventional drones, they are characterized by a variable mechanical structure in flight, geometric adaptability, aerial reconfiguration, high number of actuators and control inputs, and variable mathematical model. In addition, they are exploited to flight in more cluttered environments, avoid collisions with obstacles, transport and grab objects, cross narrow and small spaces, decrease different aerial damages, optimize the consumed energy, and improve agility and maneuverability in flight. Moreover, these new drones are considered as a viable solution to provide them with specific and additional functionalities. They are a promising solution in the near future, since they allow increasing considerably the capabilities and performance of classical drones in terms of multi-functionalities, geometric adaptation, design characteristics, consumed energy, control, maneuverability, agility, efficiency, obstacles avoidance, and fault tolerant control. This paper explores very interesting and recent research works, which include the classification, the main characteristics, the various applications, and the existing designs of this particular class of drones. Besides, an in-depth review of the applied control strategies will be presented. The links of the videos displaying the results of these researches will be also shown. A comparative study between the different types of flying vehicles will be established. Finally, several new challenges and future directions for reconfigurable drones will be discussed.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129121356","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 : 2021-03-24DOI: 10.1142/S2301385021410053
Mengzhen Huo, H. Duan, Xilun Ding
The heterogeneous pigeon flock showed higher leadership stability than the homogeneous flock. In this paper, a control model applied to manned aircraft and Unmanned Aerial Vehicle heterogeneous formation flight is designed. During the smoothing trajectory, the swarm employed the distributed communication network and event-triggered interactive mechanism. During the turning trajectory, the centralized and distributed communication networks were integrated. Simulation tests demonstrated that the proposed control algorithm was feasible to form a cohesive group and effectively avoid obstacles in unknown environment.
{"title":"Manned Aircraft and Unmanned Aerial Vehicle Heterogeneous Formation Flight Control via Heterogeneous Pigeon Flock Consistency","authors":"Mengzhen Huo, H. Duan, Xilun Ding","doi":"10.1142/S2301385021410053","DOIUrl":"https://doi.org/10.1142/S2301385021410053","url":null,"abstract":"The heterogeneous pigeon flock showed higher leadership stability than the homogeneous flock. In this paper, a control model applied to manned aircraft and Unmanned Aerial Vehicle heterogeneous formation flight is designed. During the smoothing trajectory, the swarm employed the distributed communication network and event-triggered interactive mechanism. During the turning trajectory, the centralized and distributed communication networks were integrated. Simulation tests demonstrated that the proposed control algorithm was feasible to form a cohesive group and effectively avoid obstacles in unknown environment.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127630808","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 : 2021-03-11DOI: 10.1142/S2301385021020015
H. Liu
{"title":"Editorial: Special Issue on Interactive Unmanned Systems and Intelligent Applications","authors":"H. Liu","doi":"10.1142/S2301385021020015","DOIUrl":"https://doi.org/10.1142/S2301385021020015","url":null,"abstract":"","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125662585","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 : 2021-03-06DOI: 10.1142/S2301385021410065
Zihao Wang, K. Qin, Te Zhang, Bo Zhu
In the future, heterogeneous robots are expected to perform more complex tasks in a cooperative manner, and the onboard navigation system is required to be capable of working safely and effectively in the area where GNSS signal is weak or even could not be received. To demonstrate this concept, we have developed a cooperative navigation system by the use of Ground-Aerial Vehicle Cooperation. The key innovations of the development lie in the following aspects: (1) a local scalable self-organizing network is constructed for data interaction between a small UAV and a reusable ground robot; (2) a new navigation framework is proposed to achieve visual simultaneous localization and mapping (SLAM) where carrying capacity of both the ground vehicle and UAV are systematically considered; (3) an octomap-based 3D environment reconstruction method is developed to achieve map pre-establishment in complex navigation environments, and the classic ORB-SLAM2 system is improved to be adaptive to actual environment exploration and perception. In-door flight experiments demonstrate the effectiveness of the proposed solution. More interestingly, by implementing a centroid tracking algorithm, the cooperative system is further capable of tracking a man moving in indoor environments.
{"title":"An Intelligent Ground-Air Cooperative Navigation Framework Based on Visual-Aided Method in Indoor Environments","authors":"Zihao Wang, K. Qin, Te Zhang, Bo Zhu","doi":"10.1142/S2301385021410065","DOIUrl":"https://doi.org/10.1142/S2301385021410065","url":null,"abstract":"In the future, heterogeneous robots are expected to perform more complex tasks in a cooperative manner, and the onboard navigation system is required to be capable of working safely and effectively in the area where GNSS signal is weak or even could not be received. To demonstrate this concept, we have developed a cooperative navigation system by the use of Ground-Aerial Vehicle Cooperation. The key innovations of the development lie in the following aspects: (1) a local scalable self-organizing network is constructed for data interaction between a small UAV and a reusable ground robot; (2) a new navigation framework is proposed to achieve visual simultaneous localization and mapping (SLAM) where carrying capacity of both the ground vehicle and UAV are systematically considered; (3) an octomap-based 3D environment reconstruction method is developed to achieve map pre-establishment in complex navigation environments, and the classic ORB-SLAM2 system is improved to be adaptive to actual environment exploration and perception. In-door flight experiments demonstrate the effectiveness of the proposed solution. More interestingly, by implementing a centroid tracking algorithm, the cooperative system is further capable of tracking a man moving in indoor environments.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124348758","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 : 2021-02-08DOI: 10.1142/S2301385021500187
Hemali Virani, Dahai Liu, Dennis A. Vincenzi
The effects of rewards on the ability of an autonomous UAV controlled by a Reinforcement Learning agent to accomplish a target localization task were investigated. It was shown that with an increase in the reward obtained by a learning agent upon correct detection, systems would become more risk-tolerant, efficient and have a tendency to locate targets faster with an increase in the sensor sensitivity after systems achieve steady-state performance.
{"title":"The Effects of Rewards on Autonomous Unmanned Aerial Vehicle (UAV) Operations Using Reinforcement Learning","authors":"Hemali Virani, Dahai Liu, Dennis A. Vincenzi","doi":"10.1142/S2301385021500187","DOIUrl":"https://doi.org/10.1142/S2301385021500187","url":null,"abstract":"The effects of rewards on the ability of an autonomous UAV controlled by a Reinforcement Learning agent to accomplish a target localization task were investigated. It was shown that with an increase in the reward obtained by a learning agent upon correct detection, systems would become more risk-tolerant, efficient and have a tendency to locate targets faster with an increase in the sensor sensitivity after systems achieve steady-state performance.","PeriodicalId":164619,"journal":{"name":"Unmanned Syst.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126514389","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：