Multi-weather unmanned aerial vehicle remote sensing image restoration via scale-aware Trident Mamba

Study of the Earth’s surface objects reflectance characteristics with unmanned aerial vehicles is one of the most actual remote sensing trends. Aim of this work was to develop a method for obtaining of photospectral data using unmanned aerial spectrometry vehicle.An adaptation of the cameras spatial resolution evaluating technique based on a specialized target photographic fixation was proposed. A method for synchronizing of the camera and spectrometer of the videospectral device was also proposed. It was based on an experiment with spectra and screen images recording. Different colors were sequentially displayed on the screen. The percentage contribution of each of colors to the “mixed” spectra was calculated. So the out-of-sync time estimation became possible. In addition the work proposed the method for combining images and spectra with their merging into photospectral images. The method allows to consider the aircraft displacement when linking the spectrometer field of view to the RGB image. The way for photospectral images combining based on the images key points detectors was also proposed.Spatial resolutions for 3 aerial vehicle cameras were obtained. The study showed that the spatial resolution decrease of Zenmuse H20T caused by the device carrier movement with a speed of up to 5 m/s can be ignored. The videospectral device camera and spectrometer out-of-sync time was evaluated. An automatic merging of a set of images using key points detection was made. The spectrometry areas were linked to the panoramic image. The reflectance coefficients were obtained for each of the areas in the range of 350–900 nm. The areas to image linking accuracy was 84.9 ± 11.6 %.A discrepancy between the angular spatial resolution values got experimentally and theoretically was revealed as a result of the cameras spatial resolution evaluating. This indicates the importance of the imaging equipment spatial resolution experimental evaluation. The videospectral device spectrometer and observation camera out-of-sync time evaluation made it possible to correct the data recording time. This led to the timing error standard deviation reduction from 142 ms to 15 ms. The way for the unmanned aerial spectrometry vehicle data obtaining in a photospectral representation was developed. The proposed methods and techniques can be used in similar unmanned systems.

This paper presents the work being conducted at Cal Poly Pomona on the collaboration between unmanned aerial and ground vehicles for precision agriculture. The unmanned aerial vehicles (UAVs), equipped with multispectral/hyperspectral cameras and RGB cameras, take images of the crops while flying autonomously. The images are post processed or can be processed onboard. The processed images are used in the detection of unhealthy plants. Aerial data can be used by the UAVs and unmanned ground vehicles (UGVs) for various purposes including care of crops, harvest estimation, etc. The images can also be useful for optimized harvesting by isolating low yielding plants. These vehicles can be operated autonomously with limited or no human intervention, thereby reducing cost and limiting human exposure to agricultural chemicals. The paper discuss the autonomous UAV and UGV platforms used for the research, sensor integration, and experimental testing. Methods for ground truthing the results obtained from the UAVs will be used. The paper will also discuss equipping the UGV with a robotic arm for removing the unhealthy plants and/or weeds.

This paper explains the mathematical modelling and flight controller design for autonomous Vertical take-off and landing (VTOL) Tri-Tilt rotor hybrid Unmanned Aerial Vehicle (UAV). A tri Tilt rotor UAV is a combination of vertical flight performance of a helicopter and forward flight capability of an aircraft. The front two rotors are used to tilt from the horizontal position to the vertical and vice versa, and the third middle rotor is placed in the aft of centerline of fuselage with a lesser angle. UAVs can be classified into two main types, i.e., fixed-wing UAVs and VTOL UAVs. The mathematical model of the Tri Tilt rotor UAV using force and moment equations are derived for vertical take-off to horizontal flight and vice-versa using MATLAB/SIMULINK. The development of self-guided and fully autonomous UAVs would result in reducing the risk to human life. Civil applications include inspection of rescue teams, terrain, coasts, border patrol buildings, police, and pipelines. A Proportional-Derivative control approach is used to stabilize the altitude and attitude of the UAV. The results obtained from the simulation reveals that the proposed controller achieves robust stability, good adaptability and robust performance in the transition corridor.

In this paper, control laws are designed to achieve desired flight formations for a group of unmanned (uninhabited) aerial vehicles (UAVs). It is proposed that the formation is led and managed by a leader UAV, which determines desired (for instance, safe and achievable) flight trajectories for a group of follower UAVs. Having the desired trajectories, control laws are designed to achieve flight formations according to one of the following scenarios: (1) Each UAV takes off toward its corresponding trajectory and locks on to it in finite time; the UAVs take off independently of each other and one at a time; (2) all UAVs take off simultaneously towards their corresponding trajectories and lock on to them at the same instance of time. Examples are presented to illustrate the efficacy of the designed control laws.

В статті розглянуто питання щодо протиповітряної оборони кораблів (катерів) Військово-Морських Сил України від малорозмірних безпілотних засобів повітряного нападу (дронів). Проведений аналіз бойового застосування та порядок дій у сучасних військових конфліктах малорозмірних безпілотних літальних апаратів (БпЛА). Проведений узагальнений аналіз можливостей засобів протидії БпЛА провідних країн світу та України. Надані пропозиції щодо покращення протиповітряної оборони (можливості протидії) кораблів (катерів) ВМС України від малорозмірних БпЛА – дронів.

The recent experience of creating an unmanned combat aerial vehicle indicates that the main problems do not con- cern the development of an unmanned fighter an aerial vehicle. The greatest challenge lies in creating the algorithms, data sensors, control hardware, communications hardware, etc. necessary for utilization of an unmanned aerial vehicle (UAV). In this context it is important to highlight the problem of replacing the pilot a sensor and a flight operator on board of the UAV. This problem can be partially solved by introducing remote control, but there are some flight stages where it can only be executed under a fully independent control and data support due to various reasons, such tight time, short duration, lack of robust communication, etc. These stages include combat deployment (surface attack or air attack) which make the highest demands on the fighter's design, that is why the promising UAV are currently considered to be as autonomous possible. It is obvious that the efficiency of an autonomous UAV will be determined mostly by the effec- tiveness of its automated control algorithms, and this dependence will increase together with the level of UAV autonomy. On the other hand, the optimal control algorithms can only be synthesized based on the control object characteristics. It means the development of UAV external design and the synthesis of its control algorithms should occur simultaneously and interdependently. This article presents the content and gives an example of the use of the method of maneuverable UAV external design, the distinctive feature of which lies in the interdependent processes of UAV external design develop- ing and the synthesizing of its automated control algorithms.

Traditional incident management has dispatched resources to an immediate incident location without anticipation of near-future incidents. Previous distributed constraint optimization problem (DCOP) framework could allocate resources to highway incidents under static environments, simplifying dynamic behavior in distinct unconnected decisions. However, such an approach can not actively adapt to future changes in the environment and ignores dependencies between resource availability in near-future requests and the service time of each immediate incident request. The predictions of the environment and the resource availability in near-future requests should be considered through a look-ahead model when making decisions in the current time. This study develops a proactive, dynamic framework to overcome the above limitations and formulates the objective of the optimization problem to incorporate Unmanned Aerial Vehicles (UAVs). The UAVs’ role includes exploring uncertain traffic conditions and detecting unexpected events. Resources are relocated in anticipation of future highway incidents and dispatched in response to a highway incident request. The proposed model is solved using the Maximum Gain Method to determine the optimal vehicle assignment, which is then improved by incorporating exploration heuristics. Overall, our model reports a 5.26% improvement in response time compared to the DCOP strategy. Aside from UAVs’ assignment to incident locations, the UAVs provide enhanced transportation network coverage by reducing location assignments that result in overlapping observations.KeywordsIncident managementEmergency responseDistributed constraint optimizationUnmanned Aerial VehiclesLook-ahead optimization

In order to improve the characteristic of light-duty of space optical remote sensors and the quality of remote sensing images. A novel means was designed. It is used for remote sensing image restoration in-orbit that based on the modulation transfer function compensation (MTFC). The principle of the modulation transfer function compensation in-orbit was given, and the control system in-orbit of the modulation transfer function compensation was designed. The modulation transfer function curve was obtained by direct measurement in laboratory. The remote sensing image restoration was realized by constrained least square filter. The indexes including mean, standard deviation, edge intensity and others are used to evaluate the quality of remote sensing image restoration. The results show that the evaluation indicators of the restored image are better than the original image, and the MTF at Nyquist frequency is increased to 0.1635 from 0.1501. It totally satisfies the requirement for real-time remote sensing image restoration in-orbit, and significantly improves the image quality.

Neural network is widely used in remote sensing image restoration. To avoid huge time and space consumption of conventional neural network models, a novel remote sensing image restoration algorithm base on improved RBF (Radial Basis Function) neural network is proposed. The training data set could be organized by degrading the high-quality remote sensing images or promoting degraded images’ quality by other necessary methods. And the number of hidden layer is decided by the size of training data at the condition of small training sample scale. To accelerate convergence speed of RBF neural network during training process, conjugate gradient descent method is adopted to realize the weight parameters’ iterative correction. To further reduce calculating time, this paper proposes a matrix factorization algorithm to realize matrix's parallel arithmetic. Simulations and experiments indicate that the improved RBF neural network model could acquire relatively approving remote sensing image restoration results and time overhead.KeywordsRemote sensing image restorationRBF neural networkConjugate gradient descentMatrix factorization

A method for remote sensing image restoration based on the system degradation model

A complex system for control of swarms of micro aerial vehicles (MAV), in literature also called as unmanned aerial vehicles (UAV) or unmanned aerial systems (UAS), stabilized via an onboard visual relative localization is described in this paper. The main purpose of this work is to verify the possibility of self-stabilization of multi-MAV groups without an external global positioning system. This approach enables the deployment of MAV swarms outside laboratory conditions, and it may be considered an enabling technique for utilizing fleets of MAVs in real-world scenarios. The proposed visual-based stabilization approach has been designed for numerous different multi-UAV robotic applications (leader-follower UAV formation stabilization, UAV swarm stabilization and deployment in surveillance scenarios, cooperative UAV sensory measurement) in this paper. Deployment of the system in real-world scenarios truthfully verifies its operational constraints, given by limited onboard sensing suites and processing capabilities. The performance of the presented approach (MAV control, motion planning, MAV stabilization, and trajectory planning) in multi-MAV applications has been validated by experimental results in indoor as well as in challenging outdoor environments (e.g., in windy conditions and in a former pit mine).

This paper discusses the integration of Inertial measurements with measurements from a three-dimensional (3D) imaging sensor for position and attitude determination of unmanned aerial vehicles (UAV) and autonomous ground vehicles (AGV) in urban or indoor environments. To enable operation of UAVs and AGVs at any time in any environment a Precision Navigation, Attitude, and Time (PNAT) capability is required that is robust and not solely dependent on the Global Positioning System (GPS). In urban and indoor environments a GPS position capability may not only be unavailable due to shadowing, significant signal attenuation or multipath, but also due to intentional denial or deception. Although deep integration of GPS and Inertial Measurement Unit (IMU) data may prove to be a viable solution an alternative method is being discussed in this paper. The alternative solution is based on 3D imaging sensor technologies such as Flash Ladar (Laser Radar). Flash Ladar technology consists of a modulated laser emitter coupled with a focal plane array detector and the required optics. Like a conventional camera this sensor creates an "image" of the environment, but producing a 2D image where each pixel has associated intensity vales the flash Ladar generates an image where each pixel has an associated range and intensity value. Integration of flash Ladar with the attitude from the IMU allows creation of a 3-D scene. Current low-cost Flash Ladar technology is capable of greater than 100 x 100 pixel resolution with 5 mm depth resolution at a 30 Hz frame rate. The proposed algorithm first converts the 3D imaging sensor measurements to a point cloud of the 3D, next, significant environmental features such as planar features (walls), line features or point features (corners) are extracted and associated from one 3D imaging sensor frame to the next. Finally, characteristics of these features such as the normal or direction vectors are used to compute the platform position and attitude changes. These "delta" position and attitudes are then used calibrate the IMU. Note, that the IMU is not only required to form the point cloud of the environment expressed in the navigation frame, but also to perform association of the features from one flash Ladar frame to the next. This paper will discuss the performance of the proposed 3D imaging sensor feature extraction, position change estimator and attitude change estimator using both simulator data and data collected from a moving platform in an indoor environment. The former consists of data from a simulated IMU and flash Ladar installed on an aerial vehicle for various trajectories through an urban environment. The latter consists of measurements from a CSEM Swissranger 3D imaging sensor and a MicroStrain low-cost IMU. Data was collected on a manually operated aerial vehicle inside the Ohio University School of Electrical Engineering and Computer Science building.

This paper describes the Naval Air Systems Command (NAVAIR) unmanned aerial vehicle (UAV) / unmanned combat aerial vehicle (UCAV) distributed simulation infrastructure. This highly flexible and powerful infrastructure was exercised in a realistic interoperability demonstration. In this effort, the adopted scenario successfully ran as planned from beginning to end with a direct hit on the intended target. This demonstration established the value that NAVAIR brings, through the modeling and simulation tools offered in its facilities, to fully develop and exploit the capabilities and interoperability of UAVs and UCAVs. The exercise provided a baseline for a linked UAV infrastructure. However, some suggested modifications would greatly improve the fidelity and enhance the capabilities of the demonstration. The ultimate product would facilitate studying the interactions between UAVs and UCAVs to enhance our warfighters’ capabilities.

In modern warfare, Unmanned Aerial Vehicles (UAVs) prove to be a highly valuable asset for long and dangerous missions. Although UAVs are mostly used for Surveillance, Reconnaissance and Target Acquisition missions, so-called unmanned combat aerial vehicles (UCAVs) are under development, carrying missiles as payload. Recent evolutions in computer technology and artiflcial intelligence (AI) enable UAVs to operate more autonomously. This reduces the UAV operator workload, enables covert operations and may, in the long term, reduce the number of operators on the ground. This paper is based on an MSc study on advanced UAV autonomy. It presents the results of the application of a greedy heuristic approach to enable a swarm of UCAVs to completely autonomously execute a Suppression of Enemy Air Defence (SEAD) mission. Trajectory generation was done using visibility graphs. For task assignment, Network Flow Programming was used. The algorithms are computationally e‐cient, which enables the swarm to update the mission plan, during the mission. Although the resulting mission plans are sub-optimal, test runs have shown that approach successfully generates feasible missions that meet fuel and time constraints.

Theory and experiment on distributed output formation tracking of unmanned aerial and ground vehicle swarm systems over jointly connected digraphs