Pub Date : 2022-09-19DOI: 10.1109/AUV53081.2022.9965924
Abu M. Fuad, Md. Nahidul Islam, Kazi Ramit Raihan, M. Talha, Md Maruf Hossain Tasin, Iftekhar Ahmed, Omar Farrok
The paper presents design and implementation of a multitasking autonomous underwater vehicle (AUV) named “Aqualung.” The motivation of this project is to construct the AUV which is going to be participated in the SAUVC-2022 competition. The conventional autonomous underwater vehicles are highly expensive (up to 10 thousand USD) and have complex mechanisms whereas the construction cost of the proposed AUV is under ${$}$ 300 USD with a simple structure. DC gear motors are used in this vehicle to drive the propeller, a pressure sensor is used to convert air pressure to calculate pressure underwater, advanced image processing technology is used that has increased the proper geo mapping process and identifying any particular object under water. A grabber can be attached with its body to grab a particular thing for carrying an object. Use of lightweight materials in Aqualung AUV results in weight reduction and enables the device to consume less amount of energy. The proposed AUV exhibits excellent features which are presented in the result section.
{"title":"Implementation of the AQUALUNG: A new form of Autonomous Underwater Vehicle","authors":"Abu M. Fuad, Md. Nahidul Islam, Kazi Ramit Raihan, M. Talha, Md Maruf Hossain Tasin, Iftekhar Ahmed, Omar Farrok","doi":"10.1109/AUV53081.2022.9965924","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965924","url":null,"abstract":"The paper presents design and implementation of a multitasking autonomous underwater vehicle (AUV) named “Aqualung.” The motivation of this project is to construct the AUV which is going to be participated in the SAUVC-2022 competition. The conventional autonomous underwater vehicles are highly expensive (up to 10 thousand USD) and have complex mechanisms whereas the construction cost of the proposed AUV is under ${$}$ 300 USD with a simple structure. DC gear motors are used in this vehicle to drive the propeller, a pressure sensor is used to convert air pressure to calculate pressure underwater, advanced image processing technology is used that has increased the proper geo mapping process and identifying any particular object under water. A grabber can be attached with its body to grab a particular thing for carrying an object. Use of lightweight materials in Aqualung AUV results in weight reduction and enables the device to consume less amount of energy. The proposed AUV exhibits excellent features which are presented in the result section.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129961352","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965934
Alberto Luvisutto, Aaesha Al Shehhi, N. Mankovskii, F. Renda, C. Stefanini, Giulia De Masi
Underwater exploration and monitoring are particularly challenging for the absence of GPS, limited communications, high hydrodynamic pressure and harsh environmental conditions. Autonomous swarms of underwater robots can play a crucial role for missions such as wide area underwater exploration, environmental monitoring and inspection of existing engineering infrastructures, like oil and gas, and archaeological or historical sites, given their properties of scalability, robustness, flexibility, adaptability, enlarged perception and tasks’ parallelization. Driven by the need to understand the state of art and develop new solutions within the realization of a new swarm of underwater fishes1, we provide here a critical review of past and current projects of underwater swarms, focusing on sensors, mission tasks, algorithms, simulation environments and real life proofs of concept. Moreover, we analyze the research directions that can improve the impact of autonomous underwater swarms on environmental preservation and marine sustainable development, also considering the limiting factors imposed on these prospects.1This work is part of a new project “Heterogeneous Swarm of Underwater Autonomous Vehicles” funded by the Technology Innovation Institute and developed with Khalifa University, UAE
{"title":"Robotic Swarm for Marine and Submarine Missions: Challenges and Perspectives","authors":"Alberto Luvisutto, Aaesha Al Shehhi, N. Mankovskii, F. Renda, C. Stefanini, Giulia De Masi","doi":"10.1109/AUV53081.2022.9965934","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965934","url":null,"abstract":"Underwater exploration and monitoring are particularly challenging for the absence of GPS, limited communications, high hydrodynamic pressure and harsh environmental conditions. Autonomous swarms of underwater robots can play a crucial role for missions such as wide area underwater exploration, environmental monitoring and inspection of existing engineering infrastructures, like oil and gas, and archaeological or historical sites, given their properties of scalability, robustness, flexibility, adaptability, enlarged perception and tasks’ parallelization. Driven by the need to understand the state of art and develop new solutions within the realization of a new swarm of underwater fishes1, we provide here a critical review of past and current projects of underwater swarms, focusing on sensors, mission tasks, algorithms, simulation environments and real life proofs of concept. Moreover, we analyze the research directions that can improve the impact of autonomous underwater swarms on environmental preservation and marine sustainable development, also considering the limiting factors imposed on these prospects.1This work is part of a new project “Heterogeneous Swarm of Underwater Autonomous Vehicles” funded by the Technology Innovation Institute and developed with Khalifa University, UAE","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117053608","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965928
Christian Mai, Malte von Benzon, F. Sørensen, Sigurd Klemmensen, Simon Pedersen, Jesper Liniger
Marine growth affects offshore structures, causing additional weight and roughened surfaces, increasing wave load. In order to reduce these issues, regular inspection and cleaning can be carried out using various methods, of which one is Remotely Operated Vehicle-based (ROV) operations. In the work presented here, the design of a task-specific ROV for marine-growth cleaning is described, which is differentiated from the normal general-purpose ROVs currently used for this purpose by specialized construction and the use of a simple yet flexible framework. Compared to existing solutions, the proposed framework requires limited low-level programming, which heavily simplifies the implementation and thus reduces the associated practical overhead. The presented ROV prototype design has been demonstrated in a test tank facility and will be validated in an offshore scenario in a future offshore campaign.
{"title":"Design of an Autonomous ROV for Marine Growth Inspection and Cleaning","authors":"Christian Mai, Malte von Benzon, F. Sørensen, Sigurd Klemmensen, Simon Pedersen, Jesper Liniger","doi":"10.1109/AUV53081.2022.9965928","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965928","url":null,"abstract":"Marine growth affects offshore structures, causing additional weight and roughened surfaces, increasing wave load. In order to reduce these issues, regular inspection and cleaning can be carried out using various methods, of which one is Remotely Operated Vehicle-based (ROV) operations. In the work presented here, the design of a task-specific ROV for marine-growth cleaning is described, which is differentiated from the normal general-purpose ROVs currently used for this purpose by specialized construction and the use of a simple yet flexible framework. Compared to existing solutions, the proposed framework requires limited low-level programming, which heavily simplifies the implementation and thus reduces the associated practical overhead. The presented ROV prototype design has been demonstrated in a test tank facility and will be validated in an offshore scenario in a future offshore campaign.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130778810","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965885
Louise Rixon Fuchs, A. Gällström, A. Maki
Robust feature correspondences between 2D sonar imagery are important for perception tasks in the underwater domain such as 3D reconstruction but involve open challenges, in particular, low-resolution as well as the fact that object appearance is view-dependent. Although sonars in the MHz range would allow for higher resolution imagery, in this paper we focus on scenarios with a lower frequency kHz sensor, in which the longer visual range is gained at the sacrifice of image resolution. To this end, we first propose to solve the correspondence task using the PatchMatch algorithm for the first time in sonar imagery, and then propose a method for feature extraction based on IC. We then compare the proposed methods against conventional methods from computer vision. We evaluate our method on data from a lake experiment with objects captured with an FLS sensor. Our results show that the proposed combination of IC together with PatchMatch is well-suited for point feature extraction and correspondence in sonar imagery. Further, we also evaluate the different methods for point correspondence with a 3D object reconstruction task.
{"title":"Towards Dense Point Correspondence with PatchMatch in Low-Resolution Sonar Images","authors":"Louise Rixon Fuchs, A. Gällström, A. Maki","doi":"10.1109/AUV53081.2022.9965885","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965885","url":null,"abstract":"Robust feature correspondences between 2D sonar imagery are important for perception tasks in the underwater domain such as 3D reconstruction but involve open challenges, in particular, low-resolution as well as the fact that object appearance is view-dependent. Although sonars in the MHz range would allow for higher resolution imagery, in this paper we focus on scenarios with a lower frequency kHz sensor, in which the longer visual range is gained at the sacrifice of image resolution. To this end, we first propose to solve the correspondence task using the PatchMatch algorithm for the first time in sonar imagery, and then propose a method for feature extraction based on IC. We then compare the proposed methods against conventional methods from computer vision. We evaluate our method on data from a lake experiment with objects captured with an FLS sensor. Our results show that the proposed combination of IC together with PatchMatch is well-suited for point feature extraction and correspondence in sonar imagery. Further, we also evaluate the different methods for point correspondence with a 3D object reconstruction task.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124484180","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965897
M. Bresciani, S. Tani, F. Ruscio, Leonardo Zacchini, L. Bartalucci, A. Ridolfi, F. Maurelli, R. Costanzi
Oceans preservation and protection have become increasingly relevant topics to tackle climate change. To this end, Autonomous Underwater Vehicles (AUVs) provide a useful means to carry out inspection and monitoring operations in full autonomy. A particular scenario in which AUVs are crucial involves the detection and mapping of underwater gas leaks, whether these are due to damaged offshore structures or naturally released from the seafloor. In this context, the proposed work investigates the effects of gas seeps on the navigation performance of AUVs. Indeed, the navigation of underwater vehicles mostly relies on acoustic sensors, as Doppler Velocity Log (DVL), which can be negatively affected by the presence of gas bubbles. The paper explores two solutions, based on two different acoustic sensors working at distinct frequencies: a DVL sensor and an Ultra-Short BaseLine (USBL) device. Both strategies have been implemented and tested during at-sea experiments, where gas leaks have been artificially reproduced. Results showed that both methods suffer from the presence of gas bubbles, causing erroneous DVL measurements and lost of USBL connectivity, respectively.
{"title":"Impact of Natural Gas Seeps on the Navigation of an Autonomous Underwater Vehicle","authors":"M. Bresciani, S. Tani, F. Ruscio, Leonardo Zacchini, L. Bartalucci, A. Ridolfi, F. Maurelli, R. Costanzi","doi":"10.1109/AUV53081.2022.9965897","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965897","url":null,"abstract":"Oceans preservation and protection have become increasingly relevant topics to tackle climate change. To this end, Autonomous Underwater Vehicles (AUVs) provide a useful means to carry out inspection and monitoring operations in full autonomy. A particular scenario in which AUVs are crucial involves the detection and mapping of underwater gas leaks, whether these are due to damaged offshore structures or naturally released from the seafloor. In this context, the proposed work investigates the effects of gas seeps on the navigation performance of AUVs. Indeed, the navigation of underwater vehicles mostly relies on acoustic sensors, as Doppler Velocity Log (DVL), which can be negatively affected by the presence of gas bubbles. The paper explores two solutions, based on two different acoustic sensors working at distinct frequencies: a DVL sensor and an Ultra-Short BaseLine (USBL) device. Both strategies have been implemented and tested during at-sea experiments, where gas leaks have been artificially reproduced. Results showed that both methods suffer from the presence of gas bubbles, causing erroneous DVL measurements and lost of USBL connectivity, respectively.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121197036","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965807
Justin Chang, M.J. Anderson, S. Merrifield, Andrew Nager, Robert Hess, Raymond Young, Sean Kitchen, E. Terrill
The power required to move an Autonomous Underwater Vehicle (AUV) depends on the body drag coefficient and the cube of the water velocity. This relationship suggests that the most efficient use of power is obtained at the slowest speed required to maintain steerage and level flight. However, AUVs also have hotel loads, which are independent of vehicle propulsion, leading to an optimization problem for the speed that allows for maximum distance traveled per unit energy. This paper documents a power-efficienct behavior for AUVs that considers this distance optimization and the impact of apparent ocean currents. Our approach is applicable to all propeller driven AUVs and is explored in detail with the REMUS 100 vehicle (Huntington Ingalls, MA USA) with the goal of maximizing transit distances for a given battery capacity. The REMUS 100, a two-person portable vehicle, is a convenient surrogate for larger AUVs. It allows for maturing autonomy in a rapid, build-testbuild design spiral that can be applied to larger variants of the REMUS system. The framework for our optimization problem is an accurate power model that includes the hotel load and the hydrodynamics of the AUV. The power model is validated against a series of ocean tests that involve transits through a tidally-forced harbor, and extended to show the gains that might be possible for a power efficiency behavior in realistic head/tail currents. An in-situ behavior is also developed that dynamically adjusts its speed for optimized power-efficiency given on-board apparent ocean currents, further demonstrating energy saving potentials for long duration transits.
自主水下航行器(AUV)移动所需的动力取决于船体阻力系数和水速度的立方。这种关系表明，最有效地利用动力是在最慢的速度下获得的，以保持操纵和水平飞行。然而，auv也有酒店负载，这与车辆推进无关，导致速度优化问题，允许每单位能量行驶的最大距离。本文记录了考虑距离优化和明显洋流影响的auv的功率效率行为。我们的方法适用于所有螺旋桨驱动的auv，并与REMUS 100车辆(Huntington Ingalls, MA USA)进行了详细的探讨，目标是在给定的电池容量下最大化运输距离。REMUS 100是一种双人便携式车辆，是大型auv的方便替代品。它允许在快速，构建-测试-构建设计螺旋中成熟的自主性，可以应用于REMUS系统的更大变体。我们的优化问题的框架是一个精确的功率模型，包括酒店负载和水下航行器的流体动力学。功率模型通过一系列海洋测试进行验证，这些测试包括通过潮汐迫使的港口，并扩展以显示在现实头/尾流中功率效率行为可能获得的增益。该系统还开发了一种原位特性，可以根据船上的明显洋流动态调整其速度，以优化功率效率，进一步展示了长时间过境的节能潜力。
{"title":"Power Efficiency Autonomy for Long Duration AUV Operation","authors":"Justin Chang, M.J. Anderson, S. Merrifield, Andrew Nager, Robert Hess, Raymond Young, Sean Kitchen, E. Terrill","doi":"10.1109/AUV53081.2022.9965807","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965807","url":null,"abstract":"The power required to move an Autonomous Underwater Vehicle (AUV) depends on the body drag coefficient and the cube of the water velocity. This relationship suggests that the most efficient use of power is obtained at the slowest speed required to maintain steerage and level flight. However, AUVs also have hotel loads, which are independent of vehicle propulsion, leading to an optimization problem for the speed that allows for maximum distance traveled per unit energy. This paper documents a power-efficienct behavior for AUVs that considers this distance optimization and the impact of apparent ocean currents. Our approach is applicable to all propeller driven AUVs and is explored in detail with the REMUS 100 vehicle (Huntington Ingalls, MA USA) with the goal of maximizing transit distances for a given battery capacity. The REMUS 100, a two-person portable vehicle, is a convenient surrogate for larger AUVs. It allows for maturing autonomy in a rapid, build-testbuild design spiral that can be applied to larger variants of the REMUS system. The framework for our optimization problem is an accurate power model that includes the hotel load and the hydrodynamics of the AUV. The power model is validated against a series of ocean tests that involve transits through a tidally-forced harbor, and extended to show the gains that might be possible for a power efficiency behavior in realistic head/tail currents. An in-situ behavior is also developed that dynamically adjusts its speed for optimized power-efficiency given on-board apparent ocean currents, further demonstrating energy saving potentials for long duration transits.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115413497","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965813
Martin Aubard, A. Madureira, L. Madureira, José Pinto
Accurate identification of an uncertain underwater environment is one of the challenges of underwater robotics. Autonomous Underwater Vehicle (AUV) needs to understand its environment accurately to achieve autonomous tasks. The method proposed in this paper is a real-time automatic target recognition based on Side Scan Sonar images to detect and localize a harbor’s wall. This paper explains real-time Side Scan Sonar image generation and compares three Deep Learning object detection algorithms (YOLOv5, YOLOv5-TR, and YOLOX) using transfer learning. The YOLOv5-TR algorithm has the most accurate detection with 99% during training, whereas the YOLOX provides the best accuracy of 91.3% for a recorded survey detection. The YOLOX algorithm realizes the flow chart validation’s real-time detection and target localization.
{"title":"Real-Time Automatic Wall Detection and Localization based on Side Scan Sonar Images","authors":"Martin Aubard, A. Madureira, L. Madureira, José Pinto","doi":"10.1109/AUV53081.2022.9965813","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965813","url":null,"abstract":"Accurate identification of an uncertain underwater environment is one of the challenges of underwater robotics. Autonomous Underwater Vehicle (AUV) needs to understand its environment accurately to achieve autonomous tasks. The method proposed in this paper is a real-time automatic target recognition based on Side Scan Sonar images to detect and localize a harbor’s wall. This paper explains real-time Side Scan Sonar image generation and compares three Deep Learning object detection algorithms (YOLOv5, YOLOv5-TR, and YOLOX) using transfer learning. The YOLOv5-TR algorithm has the most accurate detection with 99% during training, whereas the YOLOX provides the best accuracy of 91.3% for a recorded survey detection. The YOLOX algorithm realizes the flow chart validation’s real-time detection and target localization.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117104527","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965876
Christian Busse, Jan Erik Reich, Bernd-Christian Renner
In underwater vehicle navigation, accurate model parameters are crucial for the development of control and localization algorithms. However, the identification of hydrodynamic parameters is nontrivial, and experimental evaluation is usually required for accurate determination. Since the vehicle configuration is not unique and may change between missions, identification methods are needed that allow fast estimation of vehicle parameters in the field shortly before the start of a mission. In this work, we investigate the estimation of translational damping parameters for an underwater vehicle using onboard sensor measurements from self-propelled experiments. To improve the estimation of body forces, we have augmented the thruster model to consider decreasing battery voltage and hydrodynamic performance loss. Furthermore, we conducted field tests with an underwater vehicle equipped with an acoustic modem as well as an RTK-GNSS reference system to investigate the fast identification of surge damping parameters. The experimental results show that with the fitted damping model, the steady-state velocities in the range of 0. 4m/s to 0.85 m/s are predicted with an error less than 0.05 m/s.
{"title":"In Situ Damping Parameter Estimation for an Underwater Vehicle Using Onboard Sensors*","authors":"Christian Busse, Jan Erik Reich, Bernd-Christian Renner","doi":"10.1109/AUV53081.2022.9965876","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965876","url":null,"abstract":"In underwater vehicle navigation, accurate model parameters are crucial for the development of control and localization algorithms. However, the identification of hydrodynamic parameters is nontrivial, and experimental evaluation is usually required for accurate determination. Since the vehicle configuration is not unique and may change between missions, identification methods are needed that allow fast estimation of vehicle parameters in the field shortly before the start of a mission. In this work, we investigate the estimation of translational damping parameters for an underwater vehicle using onboard sensor measurements from self-propelled experiments. To improve the estimation of body forces, we have augmented the thruster model to consider decreasing battery voltage and hydrodynamic performance loss. Furthermore, we conducted field tests with an underwater vehicle equipped with an acoustic modem as well as an RTK-GNSS reference system to investigate the fast identification of surge damping parameters. The experimental results show that with the fitted damping model, the steady-state velocities in the range of 0. 4m/s to 0.85 m/s are predicted with an error less than 0.05 m/s.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114702911","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965853
Minsung Sung, Young-woon Song, Son-cheol Yu
Object detection is one of necessary techniques for autonomous underwater vehicles (AUVs) to automate their missions. However, underwater object detection requires a large number of data images of target object. This paper proposes a method to generate highly reliable training images through sonar simulator and background noise templates. Sonar simulator has been developed to generate ideal images of target by modeling imaging mechanism of sonar sensor. To make the image realistic, background noise acquired in the blank water tank are added to the simulated images. Finally, the AUV could detect the target objects at sea using a convolutional neural network trained with the generated images without any field data which is difficult to obtain.
{"title":"Underwater Object Detection of AUV based on Sonar Simulator utilizing Noise Addition","authors":"Minsung Sung, Young-woon Song, Son-cheol Yu","doi":"10.1109/AUV53081.2022.9965853","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965853","url":null,"abstract":"Object detection is one of necessary techniques for autonomous underwater vehicles (AUVs) to automate their missions. However, underwater object detection requires a large number of data images of target object. This paper proposes a method to generate highly reliable training images through sonar simulator and background noise templates. Sonar simulator has been developed to generate ideal images of target by modeling imaging mechanism of sonar sensor. To make the image realistic, background noise acquired in the blank water tank are added to the simulated images. Finally, the AUV could detect the target objects at sea using a convolutional neural network trained with the generated images without any field data which is difficult to obtain.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131494460","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 : 2022-09-19DOI: 10.1109/AUV53081.2022.9965937
D. Gomez-Ibanez, Moustafa Elkolali, Ahmed Al-Tawil, A. Alcocer
Design and testing of an epoxy-encapsulated planar L-band antenna for use in a small autonomous underwater vehicle is reported. Return loss testing with a reference radiative element is used to characterize two candidate polymer encapsulation materials, acrylic and epoxy. Planar radiative elements are iteratively scaled for accurate tuning after encapsulation.
{"title":"Design and Testing of a Low-Profile Pressure-Tolerant L-band Antenna","authors":"D. Gomez-Ibanez, Moustafa Elkolali, Ahmed Al-Tawil, A. Alcocer","doi":"10.1109/AUV53081.2022.9965937","DOIUrl":"https://doi.org/10.1109/AUV53081.2022.9965937","url":null,"abstract":"Design and testing of an epoxy-encapsulated planar L-band antenna for use in a small autonomous underwater vehicle is reported. Return loss testing with a reference radiative element is used to characterize two candidate polymer encapsulation materials, acrylic and epoxy. Planar radiative elements are iteratively scaled for accurate tuning after encapsulation.","PeriodicalId":148195,"journal":{"name":"2022 IEEE/OES Autonomous Underwater Vehicles Symposium (AUV)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121106654","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：