An Efficient Sampling-Based Algorithms Using Active Learning and Manifold Learning for Multiple Unmanned Aerial Vehicle Task Allocation under Uncertainty

Recently, unmanned aerial vehicle (UAV) task allocation is a hot topic both in the civilian and military, while the research of considering uncertainty and multi-objective is still in its infancy. Firstly, based on the uncertainty theory, a mathematical model of the uncertain multi-objective UAV task allocation problem with uncertain variables in both objective function and constraint conditions is established. The expected value criterion and opportunity constraint are introduced to transform the model into a deterministic optimization model. Furthermore, because traditional fireworks algorithm (FWA) has the shortcomings of low solution accuracy and slow convergence speed in solving the UAV task allocation problem, a novel Tent-Levy FWA (TLFWA) based on discrete update process is designed by introducing integer coding, Tent chaotic mapping and Levy variation. Experimental results show that the mean cost calculated by TLFWA is 8.17% and 13.73% lower than that of FWA and particle swarm optimization algorithm respectively, which proves the effectiveness of TLFWA. This study provides a new way to solve multi-objective and uncertain decision-making problems.

In the rapidly evolving field of unmanned aerial vehicle (UAV) applications, the complexity of task planning and trajectory optimization, particularly in high-dimensional operational environments, is increasingly challenging. This study addresses these challenges by developing the Adaptive Distortion Suppression Correlation Filter Cooperative Optimization (ARCF-ICO) algorithm, designed for high-dimensional UAV task allocation and trajectory planning. The ARCF-ICO algorithm combines advanced correlation filter technologies with multi-objective optimization techniques, enhancing the precision of trajectory planning and efficiency of task allocation. By incorporating weather conditions and other environmental factors, the algorithm ensures robust performance at low altitudes. The ARCF-ICO algorithm improves UAV tracking stability and accuracy by suppressing distortions, facilitating optimal path selection and task execution. Experimental validation using the UAV123@10fps and OTB-100 datasets demonstrates that the ARCF-ICO algorithm outperforms existing methods in Area Under the Curve (AUC) and Precision metrics. Additionally, the algorithm’s consideration of battery consumption and endurance further validates its applicability to current UAV technologies. This research advances UAV mission planning and sets new standards for UAV deployment in both civilian and military applications, where adaptability and accuracy are critical.

Task allocation for Unmanned Aerial Vehicle (UAV) swarms is a complex challenge. Effective distribution of tasks among multiple UAVs necessitates the optimization of conflicting objectives, such as task balance, flight distance, cost, and target benefits. This multi-objective optimization problem is inherently intricate due to strong interdependencies, nonlinear relationships, and dynamic environments. Traditional methods, including heuristic algorithms, supervised machine learning, and basic reinforcement learning mechanisms, often suffer from low efficiency and strict requirements for data sources or supervision mechanisms. They also struggle to adapt to problems with large discrete action spaces. To address this challenge, this paper proposes a novel approach that integrates swarm intelligence simulation with reinforcement learning. The core of this approach is a reinforcement learning algorithm based on the Deep Deterministic Policy Gradient (DDPG) framework. A key innovation is a customized DDPG variant specifically designed to handle the large, discrete action spaces inherent in UAV task allocation. Additionally, a behavior tree model is employed to simulate UAV swarm interactions, providing a realistic and verifiable environment for evaluating task allocation strategies. This simulation generates a rich dataset for training and testing reinforcement learning algorithms. The combined approach efficiently addresses the multi-objective optimization problem, enabling optimal task distribution for numerous UAVs. Compared to existing heuristic methods, the proposed approach demonstrates superior computational efficiency and solution quality, while maintaining reasonable convergence stability and environmental adaptability. Simulation-based validation ensures the approach’s robustness in dynamic environments, a critical factor for practical applications. Overall, the integration of simulation and reinforcement learning provides a powerful framework for tackling the complex task allocation problem in UAV swarms.

As the application areas of unmanned aerial vehicles (UAVs) continue to expand, the importance of UAV task allocation becomes increasingly evident. A highly effective and efficient UAV task assignment method can significantly enhance the quality of task completion. However, traditional heuristic algorithms often perform poorly in complex and dynamic environments, and existing auction-based algorithms typically fail to ensure optimal assignment results. Therefore, this paper proposes a more rigorous and comprehensive mathematical model for UAV task assignment. By introducing task path decision variables, we achieve a mathematical description of UAV task paths and propose collaborative action constraints. To balance the benefits and efficiency of task assignment, we introduce a novel method: the Adaptive Sampling-Based Task Rationality Review Algorithm (ASTRRA). In the ASTRRA, to address the issue of high-value tasks being easily overlooked when the sampling probability decreases, we propose an adaptive sampling strategy. This strategy increases the sampling probability of high-value targets, ensuring a balance between computational efficiency and maximizing task value. To handle the coherence issues in UAV task paths, we propose a task review and classification method. This method involves reviewing issues in UAV task paths and conducting classified independent auctions, thereby improving the overall task assignment value. Additionally, to resolve the crossover problems between UAV task paths, we introduce a crossover path exchange strategy, further optimizing the task assignment scheme and enhancing the overall value. Experimental results demonstrate that the ASTRRA exhibits excellent performance across various task scales and dynamic scenarios, showing strong robustness and effectively improving task assignment outcomes.

The current research represents a first step towards developing a decentralized network of small autonomous, intelligent and inexpensive unmanned aerial vehicles (UAV), which could be used for a variety of scientific missions where measurements from a distributed network of nodes could significantly improve the assessment. The paper presents an adaptive airborne sensing platform (e.g., UAV) that could be used to fuse the information acquired through multiple sensing modalities (obtained from sensors located close to or inside the phenomena) to monitor environmental processes over space and time. The sensing platform is able to continuously reconfigure its trajectory according to the circumstances (e.g., continuously evolving scientific phenomena) to optimize the location of individual sensing waypoints. As proof of concept and validation, we will apply the proposed sensing approach to monitoring volcanic plumes. The paper focuses on (i) developing a Bayesian statistical method to create sensor fusion algorithms that is used to model the plume and guide the UAV in an optimal way (ii) implementing a distributed task allocation scheme which is able guide all the UAVs efficiently and optimize the UAV paths for various criteria.

One of the possible tasks for unmanned aerial vehicles (UAVs) is field capturing of object images. The field capturing of object images (scenes) is possible owing to the UAV equipped with photographic cameras, TV cameras, infrared camer-as or synthetic aperture radars (SAR). The result of the recognition is a metric mapping of space, i.e. 2D flat images. In order to increase the quality of image recognition, it is necessary to search for and develop stereoscopic visualization with the possibility of its mobile use. A pioneering approach presented in the research paper is using a UAV with an imagery intelligence system based on structured light technology for air reconnaissance of object over a selected area or in a given direction in the field. The outcome of imagery intelligence is a three-dimensional (3D imaging) information on the geometry of an observed scene. The visualization with a stereoscopic interface proposed in the work allows for a natural perception of the depth of the scene and mutual spatial relationships, as well as seeing which objects are closer and which are further. The essence of the article is to present the application of three-dimensional vision measurement technology on UAVs. The paper presents an analysis of the possibilities of using UAVs for image recognition and a method of image recognition based on the technology of structural lighting using the method of projection of Gray’a fringes and codes. The designed image recognition system based on the structural lighting technology is described. It also discusses task modules forming a measuring head, i.e., projection, detection and calculation modules, and the exchange of control or measurement data between imaging system components. It presents the results of tests on the possibility of rapidly acquiring images using a UAV. The test results and the analyses indicate that using a UAV with an imaging technology based on structural light can contribute to improving the abilities to detect, identify, locate and monitor objects at close range, within a selected direction outdoors or indoors.

To present and validate a manifold learning (ML)-based method that can estimate both cardiac and respiratory navigator signals from electrocardiogram (ECG)-free free-breathing cardiac magnetic resonance imaging (MRI) data to achieve self-gated retrospective CINE reconstruction. In this work the use of the ML method is demonstrated for 2D cardiac CINE to achieve both cardiac and respiratory self-gating without the need of an external navigator or ECG signal. This is achieved by sequentially applying ML to two sets of retrospectively reconstructed real-time images with differing temporal resolutions. A 1D cardiac signal is estimated by applying ML to high temporal resolution real-time images reconstructed from the acquired data. Using the estimated cardiac signal, a 1D respiratory signal was obtained by applying the ML method to low temporal resolution images reconstructed from the same acquired data for each cardiac cycle. Data were acquired in five volunteers with a 2D golden angle radial trajectory in a balanced steady-state free precession (b-SSFP) acquisition. The accuracy of the estimated cardiac signal was calculated as the standard deviation of the temporal difference between the estimated signal and the recorded ECG. The correlation between the estimated respiratory signal and standard pencil beam navigator signal was evaluated. Gated CINE reconstructions (20 cardiac phases per cycle, temporal resolution ∼30 msec) using the estimated cardiac and respiratory signals were qualitatively compared against conventional ECG-gated breath-hold CINE acquisitions. Accurate cardiac signals were estimated with the proposed method, with an error standard deviation in comparison to ECG lower than 20 msec. Respiratory signals estimated with the proposed method achieved a mean cross-correlation of 94% with respect to standard pencil beam navigator signals. Good quality visual scores of 2.80 ± 0.45 (scores from 0, bad, to 4, excellent quality) were observed for the proposed approach in comparison with the conventional ECG-gated breath-hold images (visual score: 3.00 ± 0.71). Accurate respiratory and cardiac navigator signals can be estimated using the proposed framework from the acquired data itself, resulting in retrospective self-gated CINE reconstruction with high spatial and temporal quality.

Active learning sensitivity analysis of γ'(L12) precipitate morphology of ternary co-based superalloys

In this paper, we consider the use of a team of multiple unmanned aerial vehicles (UAVs) to accomplish a search and rescue (SAR) mission in the minimum time possible while saving the maximum number of people. A novel technique for the SAR problem is proposed and referred to as the layered search and rescue (LSAR) algorithm. The novelty of LSAR involves simulating real disasters to distribute SAR tasks among UAVs. The performance of LSAR is compared, in terms of percentage of rescued survivors and rescue and execution times, with the max-sum, auction-based, and locust-inspired approaches for multi UAV task allocation (LIAM) and opportunistic task allocation (OTA) schemes. The simulation results show that the UAVs running the LSAR algorithm on average rescue approximately 74% of the survivors, which is 8% higher than the next best algorithm (LIAM). Moreover, this percentage increases with the number of UAVs, almost linearly with the least slope, which means more scalability and coverage is obtained in comparison to other algorithms. In addition, the empirical cumulative distribution function of LSAR results shows that the percentages of rescued survivors clustered around the [78%-100%] range under an exponential curve, meaning most results are above 50%. In comparison, all the other algorithms have almost equal distributions of their percentage of rescued survivor results. Furthermore, because the LSAR algorithm focuses on the center of the disaster, it finds more survivors and rescues them faster than the other algorithms, with an average of 55%~77%. Moreover, most registered times to rescue survivors by LSAR are bounded by a time of 04:50:02 with 95% confidence for a one-month mission time.

With the rapid advancement of unmanned aerial vehicle technology, the extensive application of multiple unmanned aerial vehicle systems in agriculture has led to significant innovations and benefits. Addressing the challenge of task allocation for multiple unmanned aerial vehicles, the primary objective is to minimize the total time required for unmanned aerial vehicles to return to their starting point after task completion. To tackle this issue, a mathematical model for the multi-constrained multiple unmanned aerial vehicle collaborative task allocation problem is developed. To efficiently solve this model, we propose an enhanced Seagull Optimization Algorithm, which integrates the Tent chaotic mapping strategy and the Lévy flight strategy. The Tent chaotic mapping helps the algorithm avoid becoming trapped in local optima, while the Lévy flight strategy, employed during the seagull attack phase, enhances the algorithm’s diversity and its ability to escape local optima. Additionally, the spiral coefficient is refined to balance the coordination between global and local searches. Simulation experiments demonstrate that the proposed algorithm can swiftly and effectively identify a reasonable task allocation scheme for solving the multi-constrained multi-UAV collaborative task allocation problem.

Imitation learning refers to an agent’s ability to mimic a desired behavior by learning from observations. A major challenge facing learning from demonstrations is to represent the demonstrations in a manner that is adequate for learning and efficient for real time decisions. Creating feature representations is especially challenging when extracted from high dimensional visual data. In this paper, we present a method for imitation learning from raw visual data. The proposed method is applied to a popular imitation learning domain that is relevant to a variety of real life applications; namely navigation. To create a training set, a teacher uses an optimal policy to perform a navigation task, and the actions taken are recorded along with visual footage from the first person perspective. Features are automatically extracted and used to learn a policy that mimics the teacher via a deep convolutional neural network. A trained agent can then predict an action to perform based on the scene it finds itself in. This method is generic, and the network is trained without knowledge of the task, targets or environment in which it is acting. Another common challenge in imitation learning is generalizing a policy over unseen situation in training data. To address this challenge, the learned policy is subsequently improved by employing active learning. While the agent is executing a task, it can query the teacher for the correct action to take in situations where it has low confidence. The active samples are added to the training set and used to update the initial policy. The proposed approach is demonstrated on 4 different tasks in a 3D simulated environment. The experiments show that an agent can effectively perform imitation learning from raw visual data for navigation tasks and that active learning can significantly improve the initial policy using a small number of samples. The simulated testbed facilitates reproduction of these results and comparison with other approaches.

Although the use of multiple unmanned aerial vehicles (UAVs) has great potential for fast autonomous exploration, it has received far too little attention. In this article, we present a RApid Collaborative ExploRation (RACER) approach using a fleet of decentralized UAVs. To effectively dispatch the UAVs, a pairwise interaction based on an online hgrid space decomposition is used. It ensures that all UAVs simultaneously explore distinct regions, using only asynchronous and limited communication. Furthermore, we optimize the coverage paths of unknown space and balance the workloads partitioned to each UAV with a capacitated vehicle routing problem formulation. Given the task allocation, each UAV constantly updates the coverage path and incrementally extracts crucial information to support the exploration planning. A hierarchical planner finds exploration paths, refines local viewpoints, and generates minimum-time trajectories in sequence to explore the unknown space agilely and safely. The proposed approach is evaluated extensively, showing high exploration efficiency, scalability, and robustness to limited communication. Furthermore, for the first time, we achieve fully decentralized collaborative exploration with multiple UAVs in the real world. We will release our implementation as an open-source package.

With the increasing demand for heterogeneous Unmanned Aerial Vehicle (UAV) swarms to perform complex tasks in urban environments, system design now faces major challenges, including efficient semantic understanding, flexible task planning, and the ability to dynamically adjust coordination strategies in response to evolving environmental conditions and continuously changing task requirements. To address the limitations of existing methods, this paper proposes CoordField, a coordination field agent system for coordinating heterogeneous drone swarms in complex urban scenarios. In this system, large language models (LLMs) is responsible for interpreting high-level human instructions and converting them into executable commands for the UAV swarms, such as patrol and target tracking. Subsequently, a Coordination field mechanism is proposed to guide UAV motion and task selection, enabling decentralized and adaptive allocation of emergent tasks. A total of 50 rounds of comparative testing were conducted across different models in a 2D simulation space to evaluate their performance. Experimental results demonstrate that the proposed system achieves superior performance in terms of task coverage, response time, and adaptability to dynamic changes.

Most of the existing methods for pedestrian detection work well, only when the following assumption is satisfied: the features extracted from the training dataset and the testing dataset have very similar distributions in the feature space. However, in practice, this assumption does not hold because of the scene complexity and variation. In this paper, a new method is proposed for detecting pedestrians in various scenes based on the transfer learning technique. Our proposed method employs the following two strategies for improving the pedestrian detection performance. First, a new sample screening method based on manifold learning is proposed. The basic idea is to choose samples from the training set, which may be similar to the samples from the unseen scene, and then merge the selected samples into the unseen set. Second, a new classification model based on transfer learning is proposed. The advantage of the classification model is that only a small number of samples need to be used from the unseen scenes. Most of the training samples are still obtained from the training scene, which take up to 90% of the entire training samples. Compared to the traditional pedestrian detection methods, the proposed algorithm can adapt to different scenes for detecting pedestrians. Experiments on two pedestrian detection benchmark datasets, DC and NICTA, showed that the method can obtain better performance as compared to other previous methods.

With the rise of the low-altitude economy and the rapid development of UAV autonomous navigation and blockchain intelligence, this paper proposes a HomePorts-based Unmanned Aerial Vehicle(UAV) logistics delivery system enabled by blockchain intelligence to address the “last-mile” delivery challenge. The proposed system encompasses UAV task allocation, user interaction networks, and real-time on-chain data recording. It enables full-process automation and end-to-end monitoring of parcel delivery, providing users with efficient and secure logistics services. Finally, simulation experiments are conducted to validate the system’s advantages in automation and security.