Drone Localization Research Articles

UAV Geo-Localization Dataset and Method Based on Cross-View Matching.

The stable flight of drones relies on Global Navigation Satellite Systems (GNSS). However, in complex environments, GNSS signals are prone to interference, leading to flight instability. Inspired by cross-view machine learning, this paper introduces the VDUAV dataset and designs the VRLM network architecture, opening new avenues for cross-view geolocation. First, to address the limitations of traditional datasets with limited scenarios, we propose the VDUAV dataset. By leveraging the virtual-real mapping of latitude and longitude coordinates, we establish a digital twin platform that incorporates 3D models of real-world environments. This platform facilitates the creation of the VDUAV dataset for cross-view drone localization, significantly reducing the cost of dataset production. Second, we introduce a new baseline model for cross-view matching, the Virtual Reality Localization Method (VRLM). The model uses FocalNet as its backbone and extracts multi-scale features from both drone and satellite images through two separate branches. These features are then fused using a Similarity Computation and Feature Fusion (SCFF) module. By applying a weighted fusion of multi-scale features, the model preserves critical distinguishing features in the images, leading to substantial improvements in both processing speed and localization accuracy. Experimental results demonstrate that the VRLM model outperforms FPI on the VDUAV dataset, achieving an accuracy increase to 83.35% on the MA@20 metric and a precision of 74.13% on the RDS metric.

Impact of hardware impairments and BS antenna tilt on 3D drone localization and tracking

Today, GPS-free drone localization is increasingly gaining attention in various applications, but it faces significant accuracy challenges in three-dimensional (3D) space due to various impairments. This study investigates the effects of carrier frequency offset (CFO), phase noise (PN), and down-tilted base station (BS) antennas on drone positioning and tracking. Additionally, we explore the impact of inter-site distance (ISD) and BS density on drone position estimation accuracy. In our methodology, we consider a flying drone equipped with a single transmission antenna and BSs configured with 4 × 4 antennas under specific impairments. We first analyze the effects of these impairments on the signal’s covariance matrix. Then, using the MUSIC algorithm, we estimate the azimuth and elevation angles, which serve as the basis for drone localization using the Least Squares (LS) method across all BSs. Finally, the estimated positions feed into an Extended Kalman Filter (EKF) for tracking. Our results present a sequential analysis of the impact of all impairments on the off-diagonal covariance matrix, on the Angle of Arrival (AOA) estimation and 3D drone localization. We use simulations to demonstrate how hardware impairments affect 3D drone localization accuracy under varying ISD and BS densities.

Dual Free-Size LS-SVM Assisted Maximum Correntropy Kalman Filtering for Seamless INS-Based Integrated Drone Localization

Dual Free-Size LS-SVM Assisted Maximum Correntropy Kalman Filtering for Seamless INS-Based Integrated Drone Localization

Precise acoustic drone localization and tracking via drone noise: Steered response power - phase transform around harmonics

This study introduces a new method for precise acoustic drone localization and tracking via the noise generated by the drone. Drone noises include harmonic frequency components which are related to the rotational speed of the propeller and the number of blades. This study integrates utilization of the frequency components around harmonics into Steered Response Power - Phase Transform (SRP-PHAT). First, a custom discrete Fourier transform (namely DFT-Harmonics) is defined which concentrates only on the vicinities of harmonics to capture the frequency components possibly related to the drone sound. Then, DFT-Harmonics is integrated into SRP-PHAT, which is named SRP-Harmonics. The benefits of SRP-Harmonics are explained and illustrated via SRP maps and videos. Experiments with real microphone array data show that SRP-Harmonics is precise in localizing and tracking a drone, while the ordinary SRP-PHAT can not be reasonably successful. Moreover, SRP-Harmonics after Kaiser window can maintain its performance even when significant level of artificial white noise or natural wind noise exists in the data.

Indoor Drone Localization and Tracking Based on Acoustic Inertial Measurement

Indoor Drone Localization and Tracking Based on Acoustic Inertial Measurement

Autonomous Full 3D Coverage Using an Aerial Vehicle, Performing Localization, Path Planning, and Navigation Towards Indoors Inventorying for the Logistics Domain

Over the last years, a rapid evolution of unmanned aerial vehicle (UAV) usage in various applications has been observed. Their use in indoor environments requires a precise perception of the surrounding area, immediate response to its changes, and, consequently, a robust position estimation. This paper provides an implementation of navigation algorithms for solving the problem of fast, reliable, and low-cost inventorying in the logistics industry. The drone localization is achieved with a particle filter algorithm that uses an array of distance sensors and an inertial measurement unit (IMU) sensor. Navigation is based on a proportional–integral–derivative (PID) position controller that ensures an obstacle-free path within the known 3D map. As for the full 3D coverage, an extraction of the targets and then their final succession towards optimal coverage is performed. Finally, a series of experiments are carried out to examine the robustness of the positioning system using different motion patterns and velocities. At the same time, various ways of traversing the environment are examined by using different configurations of the sensor that is used to perform the area coverage.

Experimental Evaluation of an SDR-Based UAV Localization System.

UAV communications have seen a rapid rise in the last few years. The drone class of UAV has particularly become more widespread around the world, and illicit behavior using drones has become a problem. Therefore, localization, tracking, and even taking control of drones have also gained interest. Knowing the frequency of a target signal, its position can be determined (as the angle of arrival with respect to a fixed receiver point) using radio frequency-based localization techniques. One such technique is represented by the subspace-based algorithms that offer highly accurate results. This paper presents the implementation of the MUSIC algorithm on an SDR-based system using a uniform circular antenna array and its experimental evaluation in relevant outdoor environments for drone localization. The results show the capability of the system to indicate the AoA of the target signal. The results are compared with the actual direction computed from the log files of the drone application and validated with a professional direction-finding solution (i.e., Narda SignalShark equipped with the automatic direction-finding antenna).

OPTILOD: Optimal Beacon Placement for High-Accuracy Indoor Localization of Drones.

For many applications, drones are required to operate entirely or partially autonomously. In order to fly completely or partially on their own, drones need to access location services for navigation commands. While using the Global Positioning System (GPS) is an obvious choice, GPS is not always available, can be spoofed or jammed, and is highly error-prone for indoor and underground environments. The ranging method using beacons is one of the most popular methods for localization, especially for indoor environments. In general, the localization error in this class is due to two factors: the ranging error, and the error induced by the relative geometry between the beacons and the target object to be localized. This paper proposes OPTILOD (Optimal Beacon Placement for High-Accuracy Indoor Localization of Drones), an optimization algorithm for the optimal placement of beacons deployed in three-dimensional indoor environments. OPTILOD leverages advances in evolutionary algorithms to compute the minimum number of beacons and their optimal placement, thereby minimizing the localization error. These problems belong to the Mixed Integer Programming (MIP) class and are both considered NP-hard. Despite this, OPTILOD can provide multiple optimal beacon configurations that minimize the localization error and the number of deployed beacons concurrently and efficiently.

Detection and Localization of Drones in MIMO CW Radar

Detection and Localization of Drones in MIMO CW Radar

RIS-Assisted Three-Dimensional Drone Localization and Tracking Under Hardware Impairments

RIS-Assisted Three-Dimensional Drone Localization and Tracking Under Hardware Impairments

Acoustic Localization of Drones in Precise Landing: The Research and Practice with MicNest

Delivery drones have the potential to revolutionize transportation and distribution of goods. With their autonomous navigation capabilities, they offer an efficient solution to bypass the challenges posed by complex urban traffic and enable instant package delivery. Many industrial firms are actively exploring the commercial feasibility of instant drone deliveries. Meituan, one of the largest companies in this area, devised a systematic approach to instant delivery using drones. The process begins with loading the package onto the drone, which then takes off, ascends to cruising altitude, and sets a direct course towards the designated destination. Typically, this destination is a Meituan-operated self-collection station located near the customer.

A Multi-model Framework for Tether-based Drone Localization

A Multi-model Framework for Tether-based Drone Localization

PILOT: High-Precision Indoor Localization for Autonomous Drones

In many scenarios, unmanned aerial vehicles (UAVs), aka drones, need to have the capability of autonomous flight to carry out their missions successfully. In order to fly autonomously, drones need to know their location constantly. Then, based on their current position and the final destination, navigation commands will be generated and drones will be guided to their destination. Localization can be easily carried out in outdoor environments using GPS signals and drone inertial measurement units (IMUs). However, such an approach is not feasible in indoor environments or GPS-denied areas. In this paper, we propose a localization scheme for drones called PILOT (High-Precision Indoor Localization for Autonomous Drones), which is specifically designed for indoor environments. PILOT relies on ultrasonic acoustic signals to estimate the target drone's location. To obtain a precise final estimation of the drone's location, PILOT deploys a three-stage localization scheme. The first two stages provide robustness against the multi-path fading effect of indoor environments and mitigate the ranging error. Then, in the third stage, PILOT deploys a simple yet effective technique to reduce the localization error induced by the relative geometry between transmitters and receivers, which significantly reduces the height estimation error. The performance of PILOT was assessed in different scenarios, and the results indicate that it achieves centimeter-level accuracy for three-dimensional drone localization.

Low-rank approximation for underwater drone localization

We herein propose a low-approximated least-squares method for underwater drone localization that does not require depth information. On the basis of error analysis, we propose a rule to deploy a set of surface drones that minimizes the impact of measurement errors such as GPS or distance measurement errors. The Evaluation results indicate that the proposed method outperforms the least-squares method when depth information is not provided.

Drone Detection and Localization Using Enhanced Fiber-Optic Acoustic Sensor and Distributed Acoustic Sensing Technology

In recent years, the widespread use of drones has led to serious concerns about safety and privacy. Drone detection using microphone arrays has proven to be a promising method. However, it is challenging for microphones to serve large-scale applications due to the issues of synchronization, complexity, and data management. Moreover, distributed acoustic sensing (DAS) using optical fibers has demonstrated its advantages in monitoring vibrations over long distances but does not have the necessary sensitivity for weak airborne acoustics. In this work, we present, to the best of our knowledge, the first fiber-optic quasi-distributed acoustic sensing demonstration for drone surveillance. We develop enhanced fiber-optic acoustic sensors (FOASs) for DAS to detect drone sound. The FOAS shows an ultra-high measured sensitivity of −101.21 re. 1rad/μPa, as well as the capability for high-fidelity speech recovery. A single DAS can interrogate a series of FOASs over a long distance via optical fiber, enabling intrinsic synchronization and centralized signal processing. We demonstrate the field test of drone detection and localization by concatenating four FOASs as a sensing array and capturing the airborne sound remotely through DAS. Both the waveforms and spectral features of the drone sound are recognized. With acoustic field mapping and data fusion, accurate drone localization is achieved with a root-mean-square error (RMSE) of 1.47 degrees. This approach holds great potential in large-scale sound detection applications, such as drone detection or city event monitoring.

Comparison and Improvement of 3D-Multilateration for Solving Simultaneous Localization of Drones and UWB Anchors

Drone fleets have attracted a lot of attention from the research community in recent years. One of the biggest challenges in deploying such systems is localization. While GNSS localization systems can only be effective in open outdoor environments, new solutions based on radio sensors (e.g., ultra-wideband) are increasingly being used for localization in various situations and environments. However, self-localization without prior knowledge of anchor positions remains an open problem, which, for example, makes it impossible to track a moving target. In this article, we provide a comparison of different variants of gradient descent-based algorithms, with a new improved variant, for solving the localization problem using relative distance measurements and multilateration. Extensive simulation results are provided, varying the number of neighboring nodes for multilateration, algorithm initialization, and cost functions, in addition to accounting for node positioning errors and ultra-wideband sensor noise. They help set the adequate rate for fixed step descent when used and produce a damping effect in the variable step rate, which will otherwise diverge. In particular, we consider three scenarios: (i) self-localization of anchors; (ii) tracking moving targets using ultra-wideband range sensors; and (iii) simultaneously estimating unknown positions of ultra-wideband anchors and mobile agents (drones). The latter shows a great improvement in localization accuracy.

UAV's Status Is Worth Considering: A Fusion Representations Matching Method for Geo-Localization.

Visual geo-localization plays a crucial role in positioning and navigation for unmanned aerial vehicles, whose goal is to match the same geographic target from different views. This is a challenging task due to the drastic variations in different viewpoints and appearances. Previous methods have been focused on mining features inside the images. However, they underestimated the influence of external elements and the interaction of various representations. Inspired by multimodal and bilinear pooling, we proposed a pioneering feature fusion network (MBF) to address these inherent differences between drone and satellite views. We observe that UAV's status, such as flight height, leads to changes in the size of image field of view. In addition, local parts of the target scene act a role of importance in extracting discriminative features. Therefore, we present two approaches to exploit those priors. The first module is to add status information to network by transforming them into word embeddings. Note that they concatenate with image embeddings in Transformer block to learn status-aware features. Then, global and local part feature maps from the same viewpoint are correlated and reinforced by hierarchical bilinear pooling (HBP) to improve the robustness of feature representation. By the above approaches, we achieve more discriminative deep representations facilitating the geo-localization more effectively. Our experiments on existing benchmark datasets show significant performance boosting, reaching the new state-of-the-art result. Remarkably, the recall@1 accuracy achieves 89.05% in drone localization task and 93.15% in drone navigation task in University-1652, and shows strong robustness at different flight heights in the SUES-200 dataset.

Sensing spectrum sharing based massive MIMO radar for drone tracking and interception.

Radar sensors are becoming crucial for environmental perception in a world with the tremendous growth of unmanned aerial vehicles (UAVs) or drones. When public safety is a concern, the localization of drones are of great significance. However, a drone used for a wrong motive can cause a serious problem for the environment and public safety, given the fact that the dynamic movement of a drone’s emission signal and location tracking is different from existing positioning. This study proposes a safety zone characterized by the presence of N radars sensors with a goal to track and destabilized rogue drones attending to penetrate safety zones (stadium and school). Specifically, a new joint estimation based on a Gaussian filter has been introduced for spectrum sharing and detection awareness. The profit of this novel sensing method can be clearly seen when the two joint hidden states are taken into consideration. Therefore, the drone’s emission state is analyzed by estimating its movement jointly. Considering the drone’s unknown states and actual positioning, an algorithm is developed based on dynamic states space model. Where Bernoulli filter model is designed to estimate recursively the unknown stages of the drone and its changing location based on time. Meanwhile a power control acted from the radar to the targeted drones so that rogue drones are optimally tracked and destabilized over time. Furthermore, an expanding mechanism has been generated to accurately track the drone and enhance detection. A thoughtful result of the experimentation shows clearly that, even when the drone is moving, spectral detection can be performed accurately by chasing its positions. Its demonstrates at 90% of credibility that the original signal has a direct effect on the propagated signal. Therefore, the magnitude of the Doppler shift increases with frequency. And the clue of its positioning can be used for cognitive radio optimization.

Combined RF-Based Drone Detection and Classification

Despite several beneficial applications, unfortunately, drones are also being used for illicit activities such as drug trafficking, firearm smuggling or to impose threats to security-sensitive places like airports and nuclear power plants. The existing drone localization and neutralization technologies work on the assumption that the drone has already been detected and classified. Although we have observed a tremendous advancement in the sensor industry in this decade, there is no robust drone detection and classification method proposed in the literature yet. This paper focuses on radio frequency (RF) based drone detection and classification using the frequency signature of the transmitted signal. We have created a novel drone RF dataset using commercial drones and presented a detailed comparison between a two-stage and combined detection and classification framework. The detection and classification performance of both frameworks are presented for a single-signal and simultaneous multi-signal scenario. With detailed analysis, we show that You Only Look Once (YOLO) framework provides better detection performance compared to the Goodness-of-Fit (GoF) spectrum sensing for a simultaneous multi-signal scenario and good classification performance comparable to Deep Residual Neural Network (DRNN) framework.

Ultralow-Power Localization of Insect-Scale Drones: Interplay of Probabilistic Filtering and Compute-in-Memory

We propose a novel compute-in-memory (CIM)-based ultralow-power framework for probabilistic localization of insect-scale drones. Localization is a critical subroutine for path planning and rotor control in drones, where a drone is required to continuously estimate its pose (position and orientation) in flying space. The conventional probabilistic localization approaches rely on the 3-D Gaussian mixture model (GMM)-based representation of a 3-D map. A GMM model with hundreds of mixture functions is typically needed to adequately learn and represent the intricacies of the map. Meanwhile, localization using complex GMM map models is computationally intensive. Since insect-scale drones operate under extremely limited area/power budget, continuous localization using GMM models entails much higher operating energy, thereby limiting flying duration and/or size of the drone due to a larger battery. Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3-D map representation using a harmonic mean of the “Gaussian-like” mixture (HMGM) model. We show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">short-circuit current</i> of a multiinput floating-gate CMOS-based inverter follows the harmonic mean of a Gaussian-like function. Therefore, the likelihood function useful for drone localization can be efficiently implemented by connecting many multiinput inverters in parallel, each programmed with the parameters of the 3-D map model represented as HMGM. When the depth measurements are projected to the input of the implementation, the summed current of the inverters emulates the likelihood of the measurement. We have characterized our approach on an RGB-D scenes dataset. The proposed localization framework is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 25\times $ </tex-math></inline-formula> energy-efficient than the traditional, 8-bit digital GMM-based processor paving the way for tiny autonomous drones.