Shijie Su, Yushuo Chen, Cunjun Li, Kai Ni, Jian Zhang
The robotic manta has attracted significant interest for its exceptional maneuverability, swimming efficiency, and stealthiness. However, achieving efficient autonomous swimming in complex underwater environments presents a significant challenge. To address this issue, this study integrates Deep Deterministic Policy Gradient (DDPG) with Central Pattern Generators (CPGs) and proposes a CPG-based DDPG control strategy. First, we designed a CPG control strategy that can more precisely mimic the swimming behavior of the manta. Then, we implemented the DDPG algorithm as a high-level controller that adaptively modifies the CPG’s control parameters based on the real-time state information of the robotic manta. This adjustment allows for the regulation of swimming modes to fulfill specific tasks. The proposed strategy underwent initial training and testing in a simulated environment before deployment on a robotic manta prototype for field trials. Both further simulation and experimental results validate the effectiveness and practicality of the proposed control strategy.
{"title":"Intelligent Control Strategy for Robotic Manta via CPG and Deep Reinforcement Learning","authors":"Shijie Su, Yushuo Chen, Cunjun Li, Kai Ni, Jian Zhang","doi":"10.3390/drones8070323","DOIUrl":"https://doi.org/10.3390/drones8070323","url":null,"abstract":"The robotic manta has attracted significant interest for its exceptional maneuverability, swimming efficiency, and stealthiness. However, achieving efficient autonomous swimming in complex underwater environments presents a significant challenge. To address this issue, this study integrates Deep Deterministic Policy Gradient (DDPG) with Central Pattern Generators (CPGs) and proposes a CPG-based DDPG control strategy. First, we designed a CPG control strategy that can more precisely mimic the swimming behavior of the manta. Then, we implemented the DDPG algorithm as a high-level controller that adaptively modifies the CPG’s control parameters based on the real-time state information of the robotic manta. This adjustment allows for the regulation of swimming modes to fulfill specific tasks. The proposed strategy underwent initial training and testing in a simulated environment before deployment on a robotic manta prototype for field trials. Both further simulation and experimental results validate the effectiveness and practicality of the proposed control strategy.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141651471","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}
This paper applies federated reinforcement learning (FRL) in cellular vehicle-to-everything (C-V2X) communication to enable vehicles to learn communication parameters in collaboration with a parameter server that is embedded in an unmanned aerial vehicle (UAV). Different sensors in vehicles capture different types of data, contributing to data heterogeneity. C-V2X communication networks impose additional communication overhead in order to converge to a global model when the sensor data are not independent-and-identically-distributed (non-i.i.d.). Consequently, the training time for local model updates also varies considerably. Using FRL, we accelerated this convergence by minimizing communication rounds, and we delayed it by exploring the correlation between the data captured by various vehicles in subsequent time steps. Additionally, as UAVs have limited battery power, processing of the collected information locally at the vehicles and then transmitting the model hyper-parameters to the UAVs can optimize the available power consumption pattern. The proposed FRL algorithm updates the global model through adaptive weighing of Q-values at each training round. By measuring the local gradients at the vehicle and the global gradient at the UAV, the contribution of the local models is determined. We quantify these Q-values using nonlinear mappings to reinforce positive rewards such that the contribution of local models is dynamically measured. Moreover, minimizing the number of communication rounds between the UAVs and vehicles is investigated as a viable approach for minimizing delay. A performance evaluation revealed that the FRL approach can yield up to a 40% reduction in the number of communication rounds between vehicles and UAVs when compared to gross data offloading.
{"title":"Federated Reinforcement Learning for Collaborative Intelligence in UAV-Assisted C-V2X Communications","authors":"Abhishek Gupta, Xavier Fernando","doi":"10.3390/drones8070321","DOIUrl":"https://doi.org/10.3390/drones8070321","url":null,"abstract":"This paper applies federated reinforcement learning (FRL) in cellular vehicle-to-everything (C-V2X) communication to enable vehicles to learn communication parameters in collaboration with a parameter server that is embedded in an unmanned aerial vehicle (UAV). Different sensors in vehicles capture different types of data, contributing to data heterogeneity. C-V2X communication networks impose additional communication overhead in order to converge to a global model when the sensor data are not independent-and-identically-distributed (non-i.i.d.). Consequently, the training time for local model updates also varies considerably. Using FRL, we accelerated this convergence by minimizing communication rounds, and we delayed it by exploring the correlation between the data captured by various vehicles in subsequent time steps. Additionally, as UAVs have limited battery power, processing of the collected information locally at the vehicles and then transmitting the model hyper-parameters to the UAVs can optimize the available power consumption pattern. The proposed FRL algorithm updates the global model through adaptive weighing of Q-values at each training round. By measuring the local gradients at the vehicle and the global gradient at the UAV, the contribution of the local models is determined. We quantify these Q-values using nonlinear mappings to reinforce positive rewards such that the contribution of local models is dynamically measured. Moreover, minimizing the number of communication rounds between the UAVs and vehicles is investigated as a viable approach for minimizing delay. A performance evaluation revealed that the FRL approach can yield up to a 40% reduction in the number of communication rounds between vehicles and UAVs when compared to gross data offloading.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141652848","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}
This paper provides an in-depth analysis of the current research landscape in the field of UAV (Unmanned Aerial Vehicle) swarm formation control. This review examines both conventional control methods, including leader–follower, virtual structure, behavior-based, consensus-based, and artificial potential field, and advanced AI-based (Artificial Intelligence) methods, such as artificial neural networks and deep reinforcement learning. It highlights the distinct advantages and limitations of each approach, showcasing how conventional methods offer reliability and simplicity, while AI-based strategies provide adaptability and sophisticated optimization capabilities. This review underscores the critical need for innovative solutions and interdisciplinary approaches combining conventional and AI methods to overcome existing challenges and fully exploit the potential of UAV swarms in various applications.
{"title":"Advancement Challenges in UAV Swarm Formation Control: A Comprehensive Review","authors":"Yajun Bu, Ye Yan, Yueneng Yang","doi":"10.3390/drones8070320","DOIUrl":"https://doi.org/10.3390/drones8070320","url":null,"abstract":"This paper provides an in-depth analysis of the current research landscape in the field of UAV (Unmanned Aerial Vehicle) swarm formation control. This review examines both conventional control methods, including leader–follower, virtual structure, behavior-based, consensus-based, and artificial potential field, and advanced AI-based (Artificial Intelligence) methods, such as artificial neural networks and deep reinforcement learning. It highlights the distinct advantages and limitations of each approach, showcasing how conventional methods offer reliability and simplicity, while AI-based strategies provide adaptability and sophisticated optimization capabilities. This review underscores the critical need for innovative solutions and interdisciplinary approaches combining conventional and AI methods to overcome existing challenges and fully exploit the potential of UAV swarms in various applications.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141654399","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}
Loop closure detection is crucial for simultaneous localization and mapping (SLAM), as it can effectively correct the accumulated errors. Complex scenarios put forward high requirements on the robustness of loop closure detection. Traditional feature-based loop closure detection methods often fail to meet these challenges. To solve this problem, this paper proposes a robust and efficient deep-learning-based loop closure detection approach. We employ MixVPR to extract global descriptors from keyframes and construct a global descriptor database. For local feature extraction, SuperPoint is utilized. Then, the constructed global descriptor database is used to find the loop frame candidates, and LightGlue is subsequently used to match the most similar loop frame and current keyframe with the local features. After matching, the relative pose can be computed. Our approach is first evaluated on several public datasets, and the results prove that our approach is highly robust to complex environments. The proposed approach is further validated on a real-world dataset collected by a drone and achieves accurate performance and shows good robustness in challenging conditions. Additionally, an analysis of time and memory costs is also conducted and proves that our approach can maintain accuracy and have satisfactory real-time performance as well.
{"title":"A Robust and Lightweight Loop Closure Detection Approach for Challenging Environments","authors":"Yuan Shi, Rui Li, Yingjing Shi, Shaofeng Liang","doi":"10.3390/drones8070322","DOIUrl":"https://doi.org/10.3390/drones8070322","url":null,"abstract":"Loop closure detection is crucial for simultaneous localization and mapping (SLAM), as it can effectively correct the accumulated errors. Complex scenarios put forward high requirements on the robustness of loop closure detection. Traditional feature-based loop closure detection methods often fail to meet these challenges. To solve this problem, this paper proposes a robust and efficient deep-learning-based loop closure detection approach. We employ MixVPR to extract global descriptors from keyframes and construct a global descriptor database. For local feature extraction, SuperPoint is utilized. Then, the constructed global descriptor database is used to find the loop frame candidates, and LightGlue is subsequently used to match the most similar loop frame and current keyframe with the local features. After matching, the relative pose can be computed. Our approach is first evaluated on several public datasets, and the results prove that our approach is highly robust to complex environments. The proposed approach is further validated on a real-world dataset collected by a drone and achieves accurate performance and shows good robustness in challenging conditions. Additionally, an analysis of time and memory costs is also conducted and proves that our approach can maintain accuracy and have satisfactory real-time performance as well.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141653575","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 recent years, the widespread adaptation of Unmanned Aerial Vehicles (UAVs), commonly known as drones, among the public has led to significant security concerns, prompting intense research into drones’ classification methodologies. The swift and accurate classification of drones poses a considerable challenge due to their diminutive size and rapid movements. To address this challenge, this paper introduces (i) a novel drone classification approach utilizing deep convolution and deep transfer learning techniques. The model incorporates bypass connections and Leaky ReLU activation functions to mitigate the ‘vanishing gradient problem’ and the ‘dying ReLU problem’, respectively, associated with deep networks and is trained on a diverse dataset. This study employs (ii) a custom dataset comprising both audio and visual data of drones as well as analogous objects like an airplane, birds, a helicopter, etc., to enhance classification accuracy. The integration of audio–visual information facilitates more precise drone classification. Furthermore, (iii) a new Finite Impulse Response (FIR) low-pass filter is proposed to convert audio signals into spectrogram images, reducing susceptibility to noise and interference. The proposed model signifies a transformative advancement in convolutional neural networks’ design, illustrating the compatibility of efficacy and efficiency without compromising on complexity and learnable properties. A notable performance was demonstrated by the proposed model, with an accuracy of 100% achieved on the test images using only four million learnable parameters. In contrast, the Resnet50 and Inception-V3 models exhibit 90% accuracy each on the same test set, despite the employment of 23.50 million and 21.80 million learnable parameters, respectively.
{"title":"A New Approach to Classify Drones Using a Deep Convolutional Neural Network","authors":"Hrishi Rakshit, Pooneh Bagheri Zadeh","doi":"10.3390/drones8070319","DOIUrl":"https://doi.org/10.3390/drones8070319","url":null,"abstract":"In recent years, the widespread adaptation of Unmanned Aerial Vehicles (UAVs), commonly known as drones, among the public has led to significant security concerns, prompting intense research into drones’ classification methodologies. The swift and accurate classification of drones poses a considerable challenge due to their diminutive size and rapid movements. To address this challenge, this paper introduces (i) a novel drone classification approach utilizing deep convolution and deep transfer learning techniques. The model incorporates bypass connections and Leaky ReLU activation functions to mitigate the ‘vanishing gradient problem’ and the ‘dying ReLU problem’, respectively, associated with deep networks and is trained on a diverse dataset. This study employs (ii) a custom dataset comprising both audio and visual data of drones as well as analogous objects like an airplane, birds, a helicopter, etc., to enhance classification accuracy. The integration of audio–visual information facilitates more precise drone classification. Furthermore, (iii) a new Finite Impulse Response (FIR) low-pass filter is proposed to convert audio signals into spectrogram images, reducing susceptibility to noise and interference. The proposed model signifies a transformative advancement in convolutional neural networks’ design, illustrating the compatibility of efficacy and efficiency without compromising on complexity and learnable properties. A notable performance was demonstrated by the proposed model, with an accuracy of 100% achieved on the test images using only four million learnable parameters. In contrast, the Resnet50 and Inception-V3 models exhibit 90% accuracy each on the same test set, despite the employment of 23.50 million and 21.80 million learnable parameters, respectively.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141655653","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}
Bohao Wang, Yuehao Yan, Xingzhong Xiong, Qiang Han, Zhouguan Li
A combined control method integrating Linear Active Disturbance Rejection Control (LADRC) and Sliding Mode Control (SMC) is proposed to mitigate model uncertainty and external disturbances in the attitude control of fixed−wing unmanned aerial vehicles (UAVs). First, the mathematical and dynamic models of a small fixed−wing UAV are constructed. Subsequently, a Linear Extended State Observer (LESO) is designed to accurately estimate the model uncertainties and unidentified external disturbances. The LESO is then integrated into the control side to enable the SMC to enhance the control system’s anti−interference performance due to its insensitivity to variations in−system parameters. The system’s stability is proven using the Lyapunov stability theory. Finally, simulations comparing the classical LADRC and the newly developed SMC−LADRC reveal that the latter exhibits strong robustness and anti−interference capabilities in scenarios involving model uncertainty, external disturbances, and internal disturbances, confirming the effectiveness of this control method.
{"title":"Attitude Control of Small Fixed−Wing UAV Based on Sliding Mode and Linear Active Disturbance Rejection Control","authors":"Bohao Wang, Yuehao Yan, Xingzhong Xiong, Qiang Han, Zhouguan Li","doi":"10.3390/drones8070318","DOIUrl":"https://doi.org/10.3390/drones8070318","url":null,"abstract":"A combined control method integrating Linear Active Disturbance Rejection Control (LADRC) and Sliding Mode Control (SMC) is proposed to mitigate model uncertainty and external disturbances in the attitude control of fixed−wing unmanned aerial vehicles (UAVs). First, the mathematical and dynamic models of a small fixed−wing UAV are constructed. Subsequently, a Linear Extended State Observer (LESO) is designed to accurately estimate the model uncertainties and unidentified external disturbances. The LESO is then integrated into the control side to enable the SMC to enhance the control system’s anti−interference performance due to its insensitivity to variations in−system parameters. The system’s stability is proven using the Lyapunov stability theory. Finally, simulations comparing the classical LADRC and the newly developed SMC−LADRC reveal that the latter exhibits strong robustness and anti−interference capabilities in scenarios involving model uncertainty, external disturbances, and internal disturbances, confirming the effectiveness of this control method.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141655683","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}
Gang Huang, Min Hu, Xu Yang, Xun Wang, Yijun Wang, Feiyao Huang
UAV mission planning is one of the core problems in the field of UAV applications. Currently, mission planning needs to simultaneously optimize multiple conflicting objectives and take into account multiple mutually coupled constraints, and traditional optimization algorithms struggle to effectively address these difficulties. Constrained multi-objective evolutionary algorithms have been proven to be effective methods for solving complex constrained multi-objective optimization problems and have been gradually applied to UAV mission planning. However, recent advances in this area have not been summarized. Therefore, this paper provides a comprehensive overview of this topic, first introducing the basic classification of UAV mission planning and its applications in different fields, proposing a new classification method based on the priorities of objectives and constraints, and describing the constraints of UAV mission planning from the perspectives of mathematical models and planning algorithms. Then, the importance of constraint handling techniques in UAV mission planning and their advantages and disadvantages are analyzed in detail, and the methods for determining individual settings in multiple populations and improvement strategies in constraint evolution algorithms are discussed. Finally, the method from the related literature is presented to compare in detail the application weights of constrained multi-objective evolutionary algorithms in UAV mission planning and provide directions and references for future research.
{"title":"A Review of Constrained Multi-Objective Evolutionary Algorithm-Based Unmanned Aerial Vehicle Mission Planning: Key Techniques and Challenges","authors":"Gang Huang, Min Hu, Xu Yang, Xun Wang, Yijun Wang, Feiyao Huang","doi":"10.3390/drones8070316","DOIUrl":"https://doi.org/10.3390/drones8070316","url":null,"abstract":"UAV mission planning is one of the core problems in the field of UAV applications. Currently, mission planning needs to simultaneously optimize multiple conflicting objectives and take into account multiple mutually coupled constraints, and traditional optimization algorithms struggle to effectively address these difficulties. Constrained multi-objective evolutionary algorithms have been proven to be effective methods for solving complex constrained multi-objective optimization problems and have been gradually applied to UAV mission planning. However, recent advances in this area have not been summarized. Therefore, this paper provides a comprehensive overview of this topic, first introducing the basic classification of UAV mission planning and its applications in different fields, proposing a new classification method based on the priorities of objectives and constraints, and describing the constraints of UAV mission planning from the perspectives of mathematical models and planning algorithms. Then, the importance of constraint handling techniques in UAV mission planning and their advantages and disadvantages are analyzed in detail, and the methods for determining individual settings in multiple populations and improvement strategies in constraint evolution algorithms are discussed. Finally, the method from the related literature is presented to compare in detail the application weights of constrained multi-objective evolutionary algorithms in UAV mission planning and provide directions and references for future research.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141656232","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}
This paper investigates the target fencing control problem of fixed-wing Unmanned Aerial Vehicle (UAV) swarms with collision avoidance and connectivity maintenance in obstacle environments. A distributed cooperative fencing scheme for maneuvering targets is proposed without predefined accurate formation. Firstly, considering that not all states of the target can be obtained by UAVs, a differential state observer is developed to estimate the target’s unknown speed and control input. Secondly, by constructing potential functions with fewer parameter adjustments, corresponding negative gradient terms are calculated to guarantee the flight safety and communication connectivity of the swarm. A distributed cooperative controller is designed using the self-organized theory and consensus control. Additionally, the stability of the closed-loop system with the controller is analyzed based on Lyapunov stability theory. Finally, numerical simulations are performed to illustrate the effectiveness of the proposed scheme.
{"title":"Cooperative Target Fencing Control for Unmanned Aerial Vehicle Swarm with Collision, Obstacle Avoidance, and Connectivity Maintenance","authors":"Hao Yu, Xiuxia Yang, Yi Zhang, Zijie Jiang","doi":"10.3390/drones8070317","DOIUrl":"https://doi.org/10.3390/drones8070317","url":null,"abstract":"This paper investigates the target fencing control problem of fixed-wing Unmanned Aerial Vehicle (UAV) swarms with collision avoidance and connectivity maintenance in obstacle environments. A distributed cooperative fencing scheme for maneuvering targets is proposed without predefined accurate formation. Firstly, considering that not all states of the target can be obtained by UAVs, a differential state observer is developed to estimate the target’s unknown speed and control input. Secondly, by constructing potential functions with fewer parameter adjustments, corresponding negative gradient terms are calculated to guarantee the flight safety and communication connectivity of the swarm. A distributed cooperative controller is designed using the self-organized theory and consensus control. Additionally, the stability of the closed-loop system with the controller is analyzed based on Lyapunov stability theory. Finally, numerical simulations are performed to illustrate the effectiveness of the proposed scheme.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141658670","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}
The estimation of Unmanned Aerial Vehicle (UAV) poses using visual information is essential in Global Navigation Satellite System (GNSS)-denied environments. In this paper, we propose a UAV visual navigation algorithm based on visual-geography Bundle Adjustment (BA) to address the challenge of missing geolocation information in monocular visual navigation. This algorithm presents an effective approach to UAV navigation and positioning. Initially, Visual Odometry (VO) was employed for tracking the UAV’s motion and extracting keyframes. Subsequently, a geolocation method based on heterogeneous image matching was utilized to calculate the geographic pose of the UAV. Additionally, we introduce a tightly coupled information fusion method based on visual-geography optimization, which provides a geographic initializer and enables real-time estimation of the UAV’s geographical pose. Finally, the algorithm dynamically adjusts the weight of geographic information to improve optimization accuracy. The proposed method is extensively evaluated in both simulated and real-world environments, and the results demonstrate that our proposed approach can accurately and in real-time estimate the geographic pose of the UAV in a GNSS-denied environment. Specifically, our proposed approach achieves a root-mean-square error (RMSE) and mean positioning accuracy of less than 13 m.
{"title":"A Visual Navigation Algorithm for UAV Based on Visual-Geography Optimization","authors":"Weibo Xu, Dongfang Yang, Jieyu Liu, Yongfei Li, Maoan Zhou","doi":"10.3390/drones8070313","DOIUrl":"https://doi.org/10.3390/drones8070313","url":null,"abstract":"The estimation of Unmanned Aerial Vehicle (UAV) poses using visual information is essential in Global Navigation Satellite System (GNSS)-denied environments. In this paper, we propose a UAV visual navigation algorithm based on visual-geography Bundle Adjustment (BA) to address the challenge of missing geolocation information in monocular visual navigation. This algorithm presents an effective approach to UAV navigation and positioning. Initially, Visual Odometry (VO) was employed for tracking the UAV’s motion and extracting keyframes. Subsequently, a geolocation method based on heterogeneous image matching was utilized to calculate the geographic pose of the UAV. Additionally, we introduce a tightly coupled information fusion method based on visual-geography optimization, which provides a geographic initializer and enables real-time estimation of the UAV’s geographical pose. Finally, the algorithm dynamically adjusts the weight of geographic information to improve optimization accuracy. The proposed method is extensively evaluated in both simulated and real-world environments, and the results demonstrate that our proposed approach can accurately and in real-time estimate the geographic pose of the UAV in a GNSS-denied environment. Specifically, our proposed approach achieves a root-mean-square error (RMSE) and mean positioning accuracy of less than 13 m.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141661779","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}
Yahui Ren, Feng Zhu, Shuaishuai Sui, Zhengming Yi, Kai Chen
Deep reinforcement learning has demonstrated flexibility advantages in the control field of quadrotor aircraft. However, when there are sudden disturbances in the environment, especially special disturbances beyond experience, the algorithm often finds it difficult to maintain good control performance. Additionally, due to the randomness in the algorithm’s exploration of states, the model’s improvement efficiency during the training process is low and unstable. To address these issues, we propose a deep reinforcement learning framework guided by Multi-PID Self-Attention to tackle the challenges in the training speed and environmental adaptability of quadrotor aircraft control algorithms. In constructing the simulation experiment environment, we introduce multiple disturbance models to simulate complex situations in the real world. By combining the PID control strategy with deep reinforcement learning and utilizing the multi-head self-attention mechanism to optimize the state reward function in the simulation environment, this framework achieves an efficient and stable training process. This experiment aims to train a quadrotor simulation model to accurately fly to a predetermined position under various disturbance conditions and subsequently maintain a stable hovering state. The experimental results show that, compared with traditional deep reinforcement learning algorithms, this method achieves significant improvements in training efficiency and state exploration ability. At the same time, this study deeply analyzes the application effect of the algorithm in different complex environments, verifies its superior robustness and generalization ability in dealing with environmental disturbances, and provides a new solution for the intelligent control of quadrotor aircraft.
{"title":"Enhancing Quadrotor Control Robustness with Multi-Proportional–Integral–Derivative Self-Attention-Guided Deep Reinforcement Learning","authors":"Yahui Ren, Feng Zhu, Shuaishuai Sui, Zhengming Yi, Kai Chen","doi":"10.3390/drones8070315","DOIUrl":"https://doi.org/10.3390/drones8070315","url":null,"abstract":"Deep reinforcement learning has demonstrated flexibility advantages in the control field of quadrotor aircraft. However, when there are sudden disturbances in the environment, especially special disturbances beyond experience, the algorithm often finds it difficult to maintain good control performance. Additionally, due to the randomness in the algorithm’s exploration of states, the model’s improvement efficiency during the training process is low and unstable. To address these issues, we propose a deep reinforcement learning framework guided by Multi-PID Self-Attention to tackle the challenges in the training speed and environmental adaptability of quadrotor aircraft control algorithms. In constructing the simulation experiment environment, we introduce multiple disturbance models to simulate complex situations in the real world. By combining the PID control strategy with deep reinforcement learning and utilizing the multi-head self-attention mechanism to optimize the state reward function in the simulation environment, this framework achieves an efficient and stable training process. This experiment aims to train a quadrotor simulation model to accurately fly to a predetermined position under various disturbance conditions and subsequently maintain a stable hovering state. The experimental results show that, compared with traditional deep reinforcement learning algorithms, this method achieves significant improvements in training efficiency and state exploration ability. At the same time, this study deeply analyzes the application effect of the algorithm in different complex environments, verifies its superior robustness and generalization ability in dealing with environmental disturbances, and provides a new solution for the intelligent control of quadrotor aircraft.","PeriodicalId":507567,"journal":{"name":"Drones","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141660361","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：