3D UAV Research Articles

Multiple elite strategy enhanced RIME algorithm for 3D UAV path planning

With the wave of artificial intelligence sweeping the world in recent years, UAVs is widely used in various fields. UAV path planning has attracted much attention from scientists as an essential part of UAV work. In order to design an efficient and reasonable 3D UAV path planning program, recent researchers have invented and improved many algorithms. This paper proposes an elite RIME algorithm for 3D UAV path planning. First, we propose an elite reverse learning population selection strategy based on piecewise mapping to enhance the population diversity of the algorithm for better exploration. Second, this paper proposes a stochastic factor-controlled elite pool exploration strategy so that the algorithm is difficult to enter the local optimum and can better explore the global optimum. Then, this paper proposes a hard frost puncture exploitation strategy based on the sine–cosine function so that the algorithm can find the global optimum faster during the exploitation process. Meanwhile, in order to test the performance of the algorithm proposed in this paper, we compare it with 13 other intelligent optimization algorithms that are classical and popular nowadays on 52 test functions in three test sets, CEC2017, CEC2020, and CEC2022, and obtain competitive results. Finally, we applied it to the 3D UAV path planning problem in three different terrain scenarios, and the ELRIME algorithm achieved good results in all of them. Especially in the 7-peak model, the ELRIME algorithm improves the performance of the RIME algorithm by a factor of two. In the 9-peak model, the average value aspect also reduce the cost by 91 compared to the RIME algorithm, and more importantly, it has the smallest fluctuation in 30 runs, which is among the most stable of all the compared algorithms. In the 12-peak model, its stability is also significantly enhanced, and in terms of worst-case cost, it improves the cost by 340 compared to RIME.

Deep Reinforcement Learning-Based Distributed 3D UAV Trajectory Design

Deep Reinforcement Learning-Based Distributed 3D UAV Trajectory Design

Three-dimensional unmanned aerial vehicle path planning utilizing artificial gorilla troops optimizer incorporating combined mutation and quadratic interpolation operators

In real terrain and dynamic obstacle scenarios, the complexity of the 3D UAV path planning problem greatly increases. Thus, to procure the optimal flight path for UAVs in such scenarios, an augmented Artificial Gorilla Troops Optimizer, denoted as OQMGTO, is proposed. The proposed OQMGTO algorithm introduces three strategies: combination mutation, quadratic interpolation, and random opposition-based learning, aiming to enhance the ability to timely escape from local optimal path areas and rapidly converge to the global optimal path. Given the flight distance, smoothness, terrain collision, and other five realistic factors of UAVs, specific constraint conditions are proposed to address complex scenarios, aiming to construct a path planning model. By optimizing this model, OQMGTO algorithm solves the path planning problem in complex scenarios. The extensive validation of OQMGTO algorithm on CEC2017 test suite enhances its credibility as a powerful optimization tool. Comparison experiments are conducted in simulated terrain scenarios, including six multi-obstacle terrain scenarios and three dynamic obstacle scenarios. The experimental findings validate OOMGTO algorithm can assist UAV in searching for excellent flight paths, featuring high safety and reliability characteristics, which confirms the superiority of OOMGTO algorithm for path planning in simulated terrain scenarios. Furthermore, in four flight missions carried out in real terrains, OQMGTO algorithm demonstrates superior search performance, planning smooth trajectories without mountain collision.

Modeling the hotspot effect for vegetation canopies based on path length distribution

The hotspot effect, which refers to the increased reflectance in the solar direction, relies on the canopy structure. Numerous bi-directional reflectance distribution function (BRDF) models have been developed with careful attention to the hotspot effect. However, different assumptions may lead to very different shapes of BRDF, especially in the hotspot direction. With the development of high-resolution remote sensing satellites and three-dimensional (3D) mapping technologies, abundant 3D structural vegetation canopy information is available. However, traditional analytical models might not fully use these kinds of information. As a result, most of them are still very limited by their assumptions, such as the shape and spatial distribution of crowns. One BRDF model may do well only for one vegetation type and shows significant errors under other scenarios. We propose a new model named PATH_RT, which can model the hotspot effect at both the leaf and crown levels using the path length distribution (PLD). PLD can be easily obtained with the 3D information of the canopy at given remote sensing geometries. We validated the bi-directional reflectance factor (BRF) predicted by the PATH_RT model with the simulated scenes and field measurements which were produced by a 3D radiative transfer model LESS and UAV observations respectively. Compared to traditional analytical models SAILH, 4SAIL2, GORT, and 5SCALE, the PATH_RT model exhibits the highest accuracy, reducing the average RMSE by 86%, 66%, 52%, and 58% for the hotspot region respectively. PATH_RT accurately depicts the hotspot effects at the canopy and leaf levels and is highly efficient (99%, 75%, 86%, 99%, and 99% less time spent for one repeat run compared to LESS, SAILH, 4SAIL2, GORT, and 5SCALE models, respectively). Considering its high accuracy and efficiency, PATH_RT is expected to improve the accuracy and efficiency of remote sensing inversion.

A Tree-based Next-best-trajectory Method for 3D UAV Exploration

A Tree-based Next-best-trajectory Method for 3D UAV Exploration

Assessing canopy structure in Andean (agro)forests using 3D UAV remote sensing

Assessing canopy structure in Andean (agro)forests using 3D UAV remote sensing

SGGTSO: A Spherical Vector-Based Optimization Algorithm for 3D UAV Path Planning

The application of 3D UAV path planning algorithms in smart cities and smart buildings can improve logistics efficiency, enhance emergency response capabilities as well as provide services such as indoor navigation, thus bringing more convenience and safety to people’s lives and work. The main idea of the 3D UAV path planning problem is how to plan to get an optimal flight path while ensuring that the UAV does not collide with obstacles during flight. This paper transforms the 3D UAV path planning problem into a multi-constrained optimization problem by formulating the path length cost function, the safety cost function, the flight altitude cost function and the smoothness cost function. This paper encodes each feasible flight path as a set of vectors consisting of magnitude, elevation and azimuth angles and searches for the optimal flight path in the configuration space by means of a metaheuristic algorithm. Subsequently, this paper proposes an improved tuna swarm optimization algorithm based on a sigmoid nonlinear weighting strategy, multi-subgroup Gaussian mutation operator and elite individual genetic strategy, called SGGTSO. Finally, the SGGTSO algorithm is compared with some other classical and novel metaheuristics in a 3D UAV path planning problem with nine different terrain scenarios and in the CEC2017 test function set. The comparison results show that the flight path planned by the SGGTSO algorithm significantly outperforms other comparison algorithms in nine different terrain scenarios, and the optimization performance of SGGTSO outperforms other comparison algorithms in 24 CEC2017 test functions.

Feature selection-based decision model for UAV path planning on rough terrains

Path planning and obstacle avoidance in 3D terrain have been identified as a monumental challenge for a UAV in a variety of autonomous missions, such as disaster management, and search and rescue operations. In large terrain areas, it is a key problem for traditional approaches to search within the point-cloud maps to find a global path for a UAV considering the flight safety, maneuverability, weather constraints, and fuel cost. Hence, this paper proposes a trajectory planning technique for global and local path planning of a fixed-wing UAV above 3D terrain under static and dynamic constraints. For global path generation, a novel feature selection-based decision model has been proposed to select the features of a point-cloud map and transform them into the feature set. The feature set is utilized by an A* multi-directional planner with an extensive search area to deliver an optimal global path. The global path is assumed as the UAV’s reference waypoints. The motion of the UAV on reference waypoints is simplified with two coordinates (R,d), where R is the cumulative distance covered by the UAV along the reference waypoints and d is its offset distance from the reference line segment in time t. For the local path planning, offset trajectories are generated along with reference waypoints to avoid collisions. Cost functions have been added so that the best global and local path can be chosen, taking into account altitude, weather, and fuel constraints. The simulation results and comparison show that the proposed approach outperforms various other 3D UAV path planning techniques in complex terrain.

Research on Real-time and High-precision Positioning Method of Ground Target through UAV Stereo Vision and Spatial Information Fusion

Background: Positioning accuracy is the most important index of the reconnaissance positioning system. Positioning accuracy involves many factors, such as the position, attitude and motion state of the flight platform, the pointing accuracy of the stable platform, and various coordinate transformations. A reasonable fusion strategy can guarantee stable positioning accuracy, so it is very important to study the precise fusion of machine vision, 3D geographic data and UAV airborne positioning information to realize the optimal combination of positioning data and complete the accurate and rapid positioning of the ground target. Methods: In this paper, a location model based on stereo vision and spatial information fusion method is proposed. It fully integrates visual information, satellite positioning information and spatial geographic information, greatly improves positioning accuracy, and through a real-time processing algorithm, significantly improves real-time positioning. Results: Through the related experiments, positioning accuracy and real-time ability of positioning could reach about three meters. Conclusion: The proposed real-time and high-precision positioning method of the ground target through UAV stereo vision and spatial information fusion is proposed showing significant improvement compared to other traditional methods.

Reinforcement learning-based multi-strategy cuckoo search algorithm for 3D UAV path planning

Unmanned aerial vehicles are applied extensively in various fields due to their advantages of low-cost, high-maneuverability, and easy-operation. However, the path planning problem of unmanned aerial vehicles, which directly determines the flight safety and efficiency, still remains challenging when building and optimizing the path model. To further study the path planning problem, we firstly construct it as a constrained optimization problem. The objective function considers the costs of path length and threat, and the constraints involve the collision and turning angle. Additionally, we employ the theory of B-Spline curve to represent the planned paths to facilitate the optimization of established model. Then, aiming at the poor searchability and slow convergence speed of current optimization methods, we propose a reinforcement learning-based multi-strategy cuckoo search algorithm. Specifically, we establish an innovative reinforcement learning-based multi-strategy mechanism and a reinforced switch parameter based on the theory of reinforcement learning. To verify the effectiveness of the proposed algorithm, extensive experiments are carried out on the CEC’17 benchmark test and different three-dimensional path planning problems. Detailed statistical analysis of the experimental results confirm the superiority of our proposed algorithm to the other well-established algorithms.

Multi-Sensor Data Fusion for 3D Reconstruction of Complex Structures: A Case Study on a Real High Formwork Project

As the most comprehensive document types for the recording and display of real-world information regarding construction projects, 3D realistic models are capable of recording and displaying simultaneously textures and geometric shapes in the same 3D scene. However, at present, the documentation for much of construction infrastructure faces significant challenges. Based on TLS, GNSS/IMU, mature photogrammetry, a UAV platform, computer vision technologies, and AI algorithms, this study proposes a workflow for 3D modeling of complex structures with multiple-source data. A deep learning LoFTR network was used first for image matching, which can improve matching accuracy. Then, a NeuralRecon network was employed to generate a 3D point cloud with global consistency. GNSS information was used to reduce search space in image matching and produce an accurate transformation matrix between the image scene and the global reference system. In addition, to enhance the effectiveness and efficiency of the co-registration of the two-source point clouds, an RPM-net was used. The proposed workflow processed the 3D laser point cloud and UAV low-altitude multi-view image data to generate a complete, accurate, high-resolution, and detailed 3D model. Experimental validation on a real high formwork project was carried out, and the result indicates that the generated 3D model has satisfactory accuracy with a registration error value of 5 cm. Model comparison between the TLS, image-based, data fusion 1 (using the common method), and data fusion 2 (using the proposed method) models were conducted in terms of completeness, geometrical accuracy, texture appearance, and appeal to professionals. The results denote that the generated 3D model has similar accuracy to the TLS model yet also provides a complete model with a photorealistic appearance that most professionals chose as their favorite.

AUTOMATIC EXTRACTION OF CONTROL POINTS FROM 3D LIDAR MOBILE MAPPING AND UAV IMAGERY FOR AERIAL TRIANGULATION

Abstract. Installing targets and measuring them as ground control points (GCPs) are time consuming and cost inefficient tasks in a UAV photogrammetry project. This research aims to automatically extract GCPs from 3D LiDAR mobile mapping system (L-MMS) measurements and UAV imagery to perform aerial triangulation in a UAV photogrammetric network. The L-MMS allows to acquire 3D point clouds of an urban environment including floors and facades of buildings with an accuracy of a few centimetres. Integration of UAV imagery, as complementary information enables to reduce the acquisition time of measurement as well as increasing the automation level in a production line. Therefore, a higher quality measurements and more diverse products are obtained. This research hypothesises that the spatial accuracy of the L-MMS is higher than that of the UAV photogrammetric point clouds. The tie points are extracted from the UAV imagery based on the well-known SIFT method, and then matched. The structure from motion (SfM) algorithm is applied to estimate the 3D object coordinates of the matched tie points. Rigid registration is carried out between the point clouds obtained from the L-MMS and the SfM. For each tie point extracted from the SfM point clouds, their corresponding neighbouring points are selected from the L-MMS point clouds, and then a plane is fitted and then a tie point was projected on the plane, and this is how the LiDAR-based control points (LCPs) are calculated. The re-projection error of the analyses carried out on a test data sets of the Glian area in Iran show a half pixel size accuracy standing for a few centimetres range accuracy. Finally, a significant increasing of speed up in survey operations besides improving the spatial accuracy of the extracted LCPs are achieved.

Cooperative Threat Engagement Using Drone Swarms

The ability of multiple manned and unmanned aircraft systems to cooperatively engage and disable an aerial threat plays a decisive role in modern warfare scenarios. In this paper, we apply key methods to enable the so-called cooperative threat engagement capability among multiple networked agents, e.g., a swarm of drones, with combat and communication capabilities. In particular, this research combines AI-based decision-making and control techniques for a swarm of loyal wingman drones to coordinate efficient defense actions in a cooperative and autonomous manner. We apply these concepts in a defense scenario that is modeled to analyze the loyal wingman concept, which we consider an interesting testbed for cooperative decision-making and low-level control techniques. The investigated methods were implemented in a realistic 3D UAV simulator for demonstration and evaluation.

FlyingLoRa: Towards energy efficient data collection in UAV-assisted LoRa networks

Energy efficiency is an increasingly crucial consideration due to the battery-powered end devices in LoRa networks. With the adoption of chirp spread spectrum modulation, end devices far apart from the gateway have to use a high spreading factor and transmit power to send uplink packets, which causes longer transmission time and higher energy consumption compared to the end devices near the gateway, and further causes unfairness issues on energy efficiency. To tackle this problem, we investigate a novel energy-efficient data collection scheme named FlyingLoRa, where an unmanned aerial vehicle carrying one gateway is dispatched to harvest packets from end devices. The goal of FlyingLoRa is to minimize the energy consumption of end devices for packet transmission by jointly optimizing the 3D UAV trajectory, scheduling strategies, and transmission parameters of end devices. We formulate our design as a mixed-integer non-convex optimization problem and propose an efficient iterative algorithm to find a sub-optimal solution. The proposed approach is numerically simulated and the results show that FlyingLoRa improves energy efficiency by 16.13× on average compared with the existing fixed gateway schemes. In addition, we realize FlyingLoRa in real scenarios and evaluate its performance by presenting the actual packet reception rate (PRR) and transmission energy consumption, which shows its effectiveness.

Discontinuity Recognition and Information Extraction of High and Steep Cliff Rock Mass Based on Multi-Source Data Fusion

It is fundamental to acquire accurate point cloud information on rock discontinuities efficiently and comprehensively when evaluating the stability of rock masses. Taking a high and steep cliff as an example, we combined 3D laser scanning and UAV photogrammetry technology to collect rock data, and proposed an intelligent identification method for rock discontinuities based on the multi-source fusion of point clouds. First, the 3D-laser-collected point cloud data were used as the basis to fuse with the UAV-photogrammetry-collected data, and the unified coordinate system and improved ICP algorithm were used to obtain the complete 3D point cloud in the study area. Secondly, we used neighborhood information entropy to achieve adaptive neighborhood-scale selection and to obtain the optimal neighborhood radius for the KNN search, to effectively calculate the point cloud normal vector and rock mass orientation information. Finally, the KDE algorithm and DBSCAN algorithm were combined for rock discontinuity clustering to achieve intelligent identification and information extraction of the rock structural plane. The clustering results were imported into the DSE program developed based on Matlab to calculate the discontinuity spacing and continuity of the rock mass structure, and to efficiently obtain the parameters of rock mass occurrence. The research results showed that this method can effectively solve the problem of incomplete-data-acquisition ground 3D laser scanning in complex geological conditions, and UAV photogrammetry prone to blurred images in depressed areas. When the extraction results were compared with the field-measured rock occurrence, the average dip angle error was about 2°, the average dip direction error was 1°, and the recognition results met the accuracy requirements. The research results provide a feasible scheme for the identification and extraction of discontinuities of high and steep rock masses.

3D MODEL OF BUILDING BASED ON MULTI-SOURCE DATA FUSION

Abstract. The process of building a digital city is the construction of a three-dimensional city model. The construction of 3 d data model is the process of multi-source spatial information collection and fusion. The current means of spatial information collection are mainly divided into three-dimensional laser technology and UAV photogrammetry technology. The three-dimensional laser technology is mainly based on ground laser, which has high acquisition accuracy for the bottom part of the building, but it is insufficient for the information collection at the top of the building. UAV photogrammetry has a large area and high efficiency spatial information collection method. At the same time, a large three-dimensional city model of the building can also be constructed. However, due to practical problems such as flight height and ground occlusion, the model constructed by UAV photogrammetry has a perfect top and poor bottom quality. The two methods are combined to build a more perfect point cloud model. Aiming at the above problems, a three-dimensional modeling method of buildings under multi-source data fusion is proposed. Firstly, the point cloud data and image data obtained by 3D laser scanner and UAV are preprocessed, and the two data forms are transformed into high-precision point cloud data. Then two sets of point cloud data are fused to generate the whole point cloud data. Finally, based on the patch generated by the whole point cloud, the point cloud model is reverse modeled. Get the corresponding building entity model, in order to get a more perfect 3D city model.

Correction to: Deep Neural Network Routing with Dynamic Space Division for 3D UAV FANETs

Correction to: Deep Neural Network Routing with Dynamic Space Division for 3D UAV FANETs

Expected Length of the Shortest Path of the Traveling Salesman Problem in 3D Space

Finding the shortest path of the traveling salesman problem (TSP) is a typical NP-hard problem and one of the basic optimization problems. TSP in three-dimensional space (3D-TSP) is an extension of TSP. It plays an important role in the fields of 3D path planning and UAV inspection, such as forest fire patrol path planning. Many existing studies have focused on the expected length of the shortest path of TSP in 2D space. The expected length of the shortest path in 3D space has not yet been studied. To fill this gap, this research focuses on developing models to estimate the expected length of the shortest path of 3D-TSP. First, different experimental scenarios are designed by combining different service areas and the number of demand points. Under each scenario, the specified number of demand points is randomly generated, and an improved genetic algorithm and Gurobi are used to find the shortest path. A total of 500 experiments are performed for each scenario, and the average length of the shortest path is calculated. The models to estimate the expected length of the shortest path are proposed. Model parameters are estimated and k-fold cross-validation is used to evaluate the goodness of fit. Results show that all the models fit the data well and the best model is selected. The developed models can be used to estimate the expected length of the shortest path of 3D-TSP and provide important references for many applications.

Deep Neural Network Routing with Dynamic Space Division for 3D UAV FANETs

Deep Neural Network Routing with Dynamic Space Division for 3D UAV FANETs

Robust 3D-Trajectory and Time Switching Optimization for Dual-UAV-Enabled Secure Communications

This paper investigates a dual-unmanned aerial vehicle (UAV)-enabled secure communication system, in which, a UAV moves around to send confidential messages to a mobile user while another cooperative UAV transmits artificial noise signals to confuse malicious eavesdroppers. Both UAVs have energy constraints and the location information of eavesdroppers is imperfect. We consider a worst-case secrecy rate maximization problem of the mobile user over all time slots. This optimization problem is solved by jointly designing the three-dimensional (3D) trajectory of UAVs and the time allocation (recharging and service or jamming) under practical constraints including maximum UAV speed, UAV collision avoidance, UAV positioning error, and UAV energy harvesting. Specifically, we adopt a more practical UAV-ground channel model with both large-scale and small-scale fading components. Due to the non-convex feasible region constructed by the complicated constraints, directly finding the optimal solution of the original problem is intractable. To address this issue, we decouple the original optimization problem into three subproblems and develop an iterative algorithm to find its suboptimal solution by using the block coordinate descent technique. To solve each subproblem, certain advanced optimization tools, such as integer relaxation, S-procedure, and successive convex approximation techniques, are utilized. Numerical simulation results are provided to corroborate the theoretical derivations and to evaluate the performance of the proposed algorithm. Additionally, the numerical results assist to draw new insights on the 3D UAV trajectory by comparing the performance with conventional two-dimensional (2D) schemes.