We are on the cusp of a new era of connected autonomous vehicles with unprecedented user experiences, tremendously improved road safety and air quality, highly diverse transportation environments and ...use cases, and a plethora of advanced applications. Realizing this grand vision requires a significantly enhanced vehicle-to-everything (V2X) communication network that should be extremely intelligent and capable of concurrently supporting hyperfast, ultrareliable, and low-latency massive information exchange. It is anticipated that the sixth-generation (6G) communication systems will fulfill these requirements of the next-generation V2X. In this article, we outline a series of key enabling technologies from a range of domains, such as new materials, algorithms, and system architectures. Aiming for truly intelligent transportation systems, we envision that machine learning (ML) will play an instrumental role in advanced vehicular communication and networking. To this end, we provide an overview of the recent advances of ML in 6G vehicular networks. To stimulate future research in this area, we discuss the strength, open challenges, maturity, and enhancing areas of these technologies.
Viewing stationary targets with priority order in an uncertain environment, the cooperative strike decision of distributed unmanned aerial vehicle (UAV) cluster is explored in this article. With ...regard to the decision for UAV cluster in dynamic environments, it has always been a difficult problem. In this article, a Q-learning-based attack decision method is proposed, and a two-layer Q-network is designed, aiming at solving the decision problem of UAVs in cruise in terms of attack time and attack plan. The upper Q network is used to find the time to attack the target during the cruise, while the lower Q network is used to determine the attack plan based on the current position of the UAV and the target after the attack time is determined. Ultimately, the effectiveness of our proposed method is validated through simulation, with comparative simulations against the dual-layer crayfish optimization algorithm (Dual-COA) demonstrating the superiority of our approach. This provides a reference for future operational endeavors of UAV clusters.
The problem of neural adaptive distributed formation control is investigated for quadrotor multiple unmanned aerial vehicles (UAVs) subject to unmodeled dynamics and disturbance. The quadrotor UAV ...system is divided into two parts: the position subsystem and the attitude subsystem. A virtual position controller based on backstepping is designed to address the coupling constraints and generate two command signals for the attitude subsystem. By establishing the communication mechanism between the UAVs and the virtual leader, a distributed formation scheme, which uses the UAVs' local information and makes each UAV update its position and velocity according to the information of neighboring UAVs, is proposed to form the required formation flight. By designing a neural adaptive sliding mode controller (SMC) for multi-UAVs, the compound uncertainties (including nonlinearities, unmodeled dynamics, and external disturbances) are compensated for to guarantee good tracking performance. The Lyapunov theory is used to prove that the tracking error of each UAV converges to an adjustable neighborhood of zero. Finally, the simulation results demonstrate the effectiveness of the proposed scheme.
Large-scale visual geolocation is a meaningful task that involves locating a query image by comparing it with images in a database and predicting the most similar image. However, the widely used ...training framework based on contrastive learning cannot fully utilize all data and is difficult to adapt to larger scales. At the same time, the traditional convolutional neural networks (CNNs) and vector of locally aggregated descriptors (VLADs) using aggregated features cannot fully reflect the relationship between the local features of the image. Therefore, a graph neural network (GNN) is designed as the feature extraction network, and then a training framework based on image classification is constructed. Specifically, a data grouping strategy and special loss function are designed for better training results. After training, we adopt an image retrieval strategy based on kNN for position. In addition, considering that existing datasets cannot be adapted to our requirements, two datasets are constructed for experiments, that one contains large-scale satellite images and the other fuses satellite and unmanned aerial vehicle (UAV) images. Results demonstrate that our method outperforms other common methods in both the datasets. The results demonstrate the effectiveness of our approach for UAV visual geolocation and provide ideas for future research in this field.
Reinforcement learning (RL) has been proven to enable the automation of tasks involving complex sequential decision-making. The simulation to reality (sim2real) gap, however, poses a major challenge ...in most engineering applications. In this work, we propose a learning approach combining RL-based navigation and collision avoidance scheme with low-level advanced control to bridge the sim2real gap for unmanned aerial vehicle (UAV) applications. The proposed approach puts the RL agent at the top of the control hierarchy to focus on behavioral intelligence. We demonstrate the transferability of the RL policy trained in simulation to a real UAV without randomization of the system's dynamic parameters. The direct transfer is enabled by: 1) the use of deep neural networks with the modified relay feedback test (DNN-MRFT) to identify the parameters of the UAV; and 2) formulating a reward function to penalize excessive actor actions. Particularly, the RL agent generates high-level velocity actions to achieve the sought task, while the low-level controller minimizes any unwanted disturbances and model discrepancies. The proposed approach has been tested and validated using computer simulations and real-world experiments. The real-world experimental results demonstrated the agent's capability to achieve the navigation task with a 90 \% success rate.
Due to their flexibility and low cost deployment, unmanned aerial vehicles (UAV) will most likely act as base stations and backhaul relays in the next generation of wireless communication systems. ...However, these UAVs-in the untethered mode-can only operate for a finite time due to limited energy they carry in their batteries. In free-space optical communications, one solution is to transport both data and energy from the source to the UAV through the laser beam-a concept known as simultaneous lightwave information and power transfer (SLIPT). In this study, we have analyzed the SLIPT scheme for laser-powered decode-and-forward UAV relays in an optical wireless backhaul. The major goal of this study is to optimally allocate the received beam energy between the decoding circuit, the transmitting circuit and the rotor block of the relay in order to maximize a quality-of-service metric such as maximum achievable rate, outage or error probabilities. As expected, we note that the optimal power allocation depends heavily on the source-relay and relay-destination channel conditions. In the final part of this study, we have maximized the operational time of the UAV relay given that the maximum achievable rate stays above a certain threshold in order to meet a minimum quality-of-service requirement.
In this paper, we consider a scenario where an unmanned aerial vehicle (UAV) collects data from a set of sensors on a straight line. The UAV can either cruise or hover while communicating with the ...sensors. The objective is to minimize the UAV's total flight time from a starting point to a destination while allowing each sensor to successfully upload a certain amount of data using a given amount of energy. The whole trajectory is divided into non-overlapping data collection intervals, in each of which one sensor is served by the UAV. The data collection intervals, the UAV's speed, and the sensors' transmit powers are jointly optimized. The formulated flight time minimization problem is difficult to solve. We first show that when only one sensor is present, the sensor's transmit power follows a water-filling policy and the UAV's speed can be found efficiently by bisection search. Then, we show that for the general case with multiple sensors, the flight time minimization problem can be equivalently reformulated as a dynamic programming (DP) problem. The subproblem involved in each stage of the DP reduces to handle the case with only one sensor node. Numerical results present the insightful behaviors of the UAV and the sensors. Specifically, it is observed that the UAV's optimal speed is proportional to the given energy of the sensors and the inter-sensor distance, but it is inversely proportional to the data upload requirement.
Emerging applications of quadrotor vertical take-off and landing (VTOL) unmanned aerial vehicles in various fields have created a need for demanding controllers that are able to counter several ...challenges, inter alia, nonlinearity, underactuated dynamics, lack of modeling, and uncertainties in the working environment. This study compares and contrasts type-1 and type-2 fuzzy neural networks (T2FNNs) for the trajectory tracking problem of quadrotor VTOL aircraft in terms of their tracking accuracy and control efforts. A realistic trajectory consisting of both straight lines and curvatures for a surveillance operation with minimum snap property, which is feasible regarding input constraints of the quadrotor, is generated to evaluate the proposed controllers. In order to imitate the outdoor noisy and time-varying working conditions, realistic uncertainties, such as wind and gust disturbances, are fed to the real-time experiment in the laboratory environment. Furthermore, a cost function based on the integral of the square of the sliding surface, which gives the optimal parameter update rules, is used to train the consequent part parameters of the T2FNN. Thanks to the learning capability of the proposed controllers, experimental results show the efficiency and efficacy of the learning algorithms that the proposed T2FNN-based controller with the optimal tuning algorithm is 50% superior to a conventional proportional-derivative (PD) controller in terms of control accuracy but requires more control effort. T2FNN structures are also shown to possess better noise reduction property as compared to their type-1 counterparts in the presence of unmodeled noise and disturbances.
Considering the user mobility and unpredictable mobile edge computing (MEC) environments, this paper studies the intelligent task offloading problem in unmanned aerial vehicle (UAV)-enabled MEC with ...the assistance of digital twin (DT). We aim at minimizing the energy consumption of the entire MEC system by jointly optimizing mobile terminal users (MTUs) association, UAV trajectory, transmission power distribution and computation capacity allocation while respecting the constraints of mission maximum processing delays. Specifically, double deep Q-network (DDQN) algorithm stemming from deep reinforcement learning is first proposed to effectively solve the problem of MTUs association and UAV trajectory. Then, the closed-form expression is employed to handle the problem of transmission power distribution and the computation capacity allocation problem is further addressed via an iterative algorithm. Numerical results show that our proposed scheme is able to converge and significantly reduce the total energy consumption of the MEC system compared to the benchmark schemes.
PDF
