Collision Avoidance For Unmanned Aerial Vehicles Research Articles

Adaptive Neuroevolution With Genetic Operator Control and Two-Way Complexity Variation

Topology and weight evolving artificial neural network (TWEANN) algorithms optimize the structure and weights of artificial neural networks (ANNs) simultaneously. The resulting networks are typically used as policy models for solving control and reinforcement learning (RL) type problems. This paper presents a neuroevolution algorithm that aims to address the typical stagnation and sluggish convergence issues present in other neuroevolution algorithms. These issues are often caused by inadequacies in population diversity preservation, exploration/exploitation balance, and search flexibility. This new algorithm, called the Adaptive Genomic Evolution of Neural-Network Topologies (AGENT), builds on the neuroevolution of augmenting topologies (NEAT) concept. Novel mechanisms for adapting the selection and mutation operations are proposed to favorably control population diversity and exploration/exploitation balance. The former is founded on a fundamentally new way of quantifying diversity by taking a graph-theoretic perspective of the population of genomes and inter-genomic differences. Further advancements to the NEAT paradigm occur through the incorporation of variable neuronal properties and new mutation operations that uniquely allow both the growth and pruning of ANN topologies during evolution. Numerical experiments with benchmark control problems adopted from the OpenAI Gym illustrate the competitive performance of AGENT against standard RL methods and adaptive HyperNEAT, and superiority over the original NEAT algorithm. Further parametric analysis provides key insights into the impact of the new features in AGENT. This is followed by evaluation on an unmanned aerial vehicle collision avoidance problem where maneuver planning models are learnt by AGENT with 33% reward improvement over 15 generations.

Vehicle-to-Vehicle Based Autonomous Flight Coordination Control System for Safer Operation of Unmanned Aerial Vehicles

The exponential growth of unmanned aerial vehicles (UAVs) or drones in recent years has raised concerns about their safe operation, especially in beyond-line-of-sight (BLOS) scenarios. Existing unmanned aircraft system traffic management (UTM) heavily relies on commercial communication networks, which may become ineffective if network infrastructures are damaged or disabled. For this challenge, we propose a novel approach that leverages vehicle-to-vehicle (V2V) communications to enhance UAV safety and efficiency in UAV operations. In this study, we present a UAV information collection and sharing system named Drone Mapper®, enabled by V2V communications, so that UAVs can share their locations with each another as well as with the ground operation station. Additionally, we introduce an autonomous flight coordination control system (AFCCS) that augments UAV safety operations by providing two essential functionalities: UAV collision avoidance and UAV formation flight, both of which work based on V2V communications. To evaluate the performance of the developed AFCCS, we conducted comprehensive field experiments focusing on UAV collision avoidance and formation flight. The experimental results demonstrate the effectiveness of the proposed system and show seamless operations among multiple UAVs.

Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments

In some military application scenarios, Unmanned Aerial Vehicles (UAVs) need to perform missions with the assistance of on-board cameras when radar is not available and communication is interrupted, which brings challenges for UAV autonomous navigation and collision avoidance. In this paper, an improved deep-reinforcement-learning algorithm, Deep Q-Network with a Faster R-CNN model and a Data Deposit Mechanism (FRDDM-DQN), is proposed. A Faster R-CNN model (FR) is introduced and optimized to obtain the ability to extract obstacle information from images, and a new replay memory Data Deposit Mechanism (DDM) is designed to train an agent with a better performance. During training, a two-part training approach is used to reduce the time spent on training as well as retraining when the scenario changes. In order to verify the performance of the proposed method, a series of experiments, including training experiments, test experiments, and typical episodes experiments, is conducted in a 3D simulation environment. Experimental results show that the agent trained by the proposed FRDDM-DQN has the ability to navigate autonomously and avoid collisions, and performs better compared to the FR-DQN, FR-DDQN, FR-Dueling DQN, YOLO-based YDDM-DQN, and original FR output-based FR-ODQN.

Game-Theoretic Decision-Making and Payoff Design for UAV Collision Avoidance in a Three-Dimensional Airspace

Safety and efficiency are primary goals of air traffic management. With the integration of unmanned aerial vehicles (UAVs) into the airspace, UAV traffic management (UTM) has attracted significant interest in the research community to maintain the capacity of three-dimensional (3D) airspace, provide information, and avoid collisions. We propose a new decision-making architecture for UAVs to avoid collision by formulating the problem into a multi-agent game in a 3D airspace. In the proposed game-theoretic approach, the Ego UAV plays a repeated two-player normal-form game, and the payoff functions are designed to capture both the safety and efficiency of feasible actions. An optimal decision in the form of Nash equilibrium (NE) is obtained. Simulation studies are conducted to demonstrate the performance of the proposed game-theoretic collision avoidance approach in several representative multi-UAV scenarios.

Genetic Fuzzy Inference System-Based Three-Dimensional Resolution Algorithm for Collision Avoidance of Fixed-Wing UAVs

Fixed-wing Unmanned Aerial Vehicles (UAVs) cannot fly at speeds lower than critical stall speeds. As a result, hovering during a potential collision scenario, like with rotary-wing UAVs, is impossible. Moreover, hovering is not an optimal solution for Collision Avoidance (CA), as it increases mission time and is innately fuel-inefficient. This work proposes a decentralized Fuzzy Inference System (FIS)-based resolution algorithm that modulates the point-to-point mission path while ensuring the continuous motion of UAVs during CA. A simplified kinematic guidance model with coordinated turn conditions is considered to control the UAVs. The model employs a proportional-derivative control of commanded airspeed, bank angle, and flight path angle. The commands are derived from the desired path, characterized by airspeed, heading, and altitude. The desired path is, in turn, obtained using look-ahead points generated for the target point. The FIS aims to mimic human behavior during collision scenarios, generating modulation parameters for the desired path to achieve CA. Notably, it is also scalable, which makes it easy to adjust the algorithm parameters, as per the required missions, and factors specific to a given UAV. A genetic algorithm was used to optimize FIS parameters so that the distance traveled during the mission was minimized despite path modulation. The proposed algorithm was optimized using a pairwise conflict scenario. The effectiveness of the algorithm was evaluated through a Monte Carlo simulation of random conflict scenarios involving multiple UAVs operating in a confined space.

Adaptive Collision Avoidance for Multiple UAVs in Urban Environments

The increasing number of unmanned aerial vehicles (UAVs) in low-altitude airspace is seriously threatening the safety of the urban environment. This paper proposes an adaptive collision avoidance method for multiple UAVs (mUAVs), aiming to provide a safe guidance for UAVs at risk of collision. The proposed method is formulated as a two−layer resolution framework with the considerations of speed adjustment and rerouting strategies. The first layer is established as a deep reinforcement learning (DRL) model with a continuous state space and action space that adaptively selects the most suitable resolution strategy for UAV pairs. The second layer is developed as a collaborative mUAV collision avoidance model, which combines a three-dimensional conflict detection and conflict resolution pool to perform resolution. To train the DRL model, in this paper, a deep deterministic policy gradient (DDPG) algorithm is introduced and improved upon. The results demonstrate that the average time required to calculate a strategy is 0.096 s, the success rate reaches 95.03%, and the extra flight distance is 26.8 m, which meets the real-time requirements and provides a reliable reference for human intervention. The proposed method can adapt to various scenarios, e.g., different numbers and positions of UAVs, with interference from random factors. The improved DDPG algorithm can also significantly improve convergence speed and save training time.

Deep reinforcement learning-based model-free path planning and collision avoidance for UAVs: A soft actor–critic with hindsight experience replay approach

In this paper, we propose a soft actor–critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.

A Novel Collision Avoidance Strategy with D2D Communications for UAV Systems

In recent years, safety operation issues related to the autonomous flight of unmanned aerial vehicles (UAVs) have become popular research and development topics worldwide. Among all UAV applications, multiple UAV-related applications are emerging due to the integration of UAVs into 6G networks, which is an important topic for next-generation wireless communication systems. For multiple UAV applications, flight safety among UAVs is the most significant issue. Therefore, collision avoidance for UAVs has become an emerging topic in UAV-related research. In the past, although many UAV collision avoidance methods have been proposed, there is still a probability of other problems, such as no possible avoidance route and unmanaged UAVs that are without centralized control, which both result in an unpredictable risk of collisions. In this study, we investigate the current existing methods and propose novel collision avoidance methods based on the elastic collision principle. To verify the performance of the proposed methods, we also conduct simulations in this paper to demonstrate their effectiveness. From the simulation results, it can be seen that the proposed methods can effectively perform collision avoidance for multiple UAVs. Specifically, using the proposed methods, all UAVs can reach their destination points within reasonable time resources without any collision, validating the effectiveness of the proposed methods.

An ADS-B Information-Based Collision Avoidance Methodology to UAV

A collision avoidance method that is specifically tailored for UAVs (unmanned aerial vehicles) operating in converging airspace is proposed. The method is based on ADS-B messages and it aims to detect and resolve conflicts between UAVs. The proposed method involves two main steps. First, a UAV conflict-sensing scheme is developed, which utilizes ADS-B information flow path and analyzes the message format information. Second, an unscented Kalman filter is used to predict UAV trajectories based on the acquired ADS-B information. The predicted information is then used to determine potential conflict scenarios, and different deconfliction strategies are selected accordingly. These strategies include speed regulation, direction regulation, and compound deconfliction, and are mathematically validated using the velocity obstacle method. The feasibility and effectiveness of the proposed method are evaluated through simulation, and it is concluded that the method can significantly improve the conflict resolution capability of UAV flights. This research provides a valuable contribution to the field of UAV collision avoidance, and can serve as a theoretical foundation for further advancements in this area.

A Comparison of Deep Neural Networks for Monocular Depth Map Estimation in Natural Environments Flying at Low Altitude

Currently, the use of Unmanned Aerial Vehicles (UAVs) in natural and complex environments has been increasing, because they are appropriate and affordable solutions to support different tasks such as rescue, forestry, and agriculture by collecting and analyzing high-resolution monocular images. Autonomous navigation at low altitudes is an important area of research, as it would allow monitoring parts of the crop that are occluded by their foliage or by other plants. This task is difficult due to the large number of obstacles that might be encountered in the drone's path. The generation of high-quality depth maps is an alternative for providing real-time obstacle detection and collision avoidance for autonomous UAVs. In this paper, we present a comparative analysis of four supervised learning deep neural networks and a combination of two for monocular depth map estimation considering images captured at low altitudes in simulated natural environments. Our results show that the Boosting Monocular network is the best performing in terms of depth map accuracy because of its capability to process the same image at different scales to avoid loss of fine details.

Cooperative path planning optimization for multiple UAVs with communication constraints

Path planning is a complicated optimization problem that is crucial for the safe flight of unmanned aerial vehicles (UAVs). Especially in the scenarios involving multiple UAVs, this problem is highly challenging due to the constraints of complex environments, various tasks and inherent UAV maneuverability. In this paper, a cooperative path planning model for multiple UAVs is presented. In addition to common limitations such as the path length minimization, UAV maneuverability limitation and collision avoidance, the communication requirements between UAVs and the impact of obstacles in the flight environment on the quality of communication are also taken into account in the presented path planning model. On this basis, the corresponding objective function is designed. Then, an improved particle swarm optimization (PSO) algorithm is proposed to solve the above path planning problem. Utilizing the ideas of the dynamic multi-swarm PSO (DMSPSO) algorithm and the comprehensive learning PSO (CLPSO) algorithm, the proposed algorithm, denoted as CL-DMSPSO, further improves the performance of both algorithms. The effectiveness and superiority of the novel CL-DMSPSO algorithm is verified on benchmark functions, especially for complex multimodal functions. Finally, we present an effective path planning method using CL-DMSPSO to generate optimized flyable paths for multiple UAVs. And simulation and comparison results on the designed scenario indicate the proposed UAV path planning method can efficiently plan high-quality paths for UAVs and demonstrate the advantages of the proposed CL-DMSPSO algorithm compared with other PSO algorithms in UAV path planning.

Variational Quantum Algorithm Applied to Collision Avoidance of Unmanned Aerial Vehicles.

Mission planning for multiple unmanned aerial vehicles (UAVs) is a complex problem that is expected to be solved by quantum computing. With the increasing application of UAVs, the demand for efficient conflict management strategies to ensure airspace safety continues to increase. In the era of noisy intermediate-scale quantum (NISQ) devices, variational quantum algorithms (VQA) for optimizing parameterized quantum circuits with the help of classical optimizers are currently one of the most promising strategies to gain quantum advantage. In this paper, we propose a mathematical model for the UAV collision avoidance problem that maps the collision avoidance problem to a quadratic unconstrained binary optimization (QUBO) problem. The problem is formulated as an Ising Hamiltonian, then the ground state is solved using two kinds of VQAs: the variational quantum eigensolver (VQE) and the quantum approximate optimization algorithm (QAOA). We select conditional value-at-risk (CVaR) to further promote the performance of our model. Four examples are given to validate that with our method the probability of obtaining a feasible solution can exceed 90% based on appropriate parameters, and our method can enhance the efficiency of a UAVs' collision avoidance model.

Distributed UAV Swarm Formation and Collision Avoidance Strategies Over Fixed and Switching Topologies.

This article proposes a controlling framework for multiple unmanned aerial vehicles (UAVs) to integrate the modes of formation flight and swarm deployment over fixed and switching topologies. Formation strategies enable UAVs to enjoy key collective benefits including reduced energy consumption, but the shape of the formation and each UAV's freedom are significantly restrained. Swarm strategies are thus proposed to maximize each UAV's freedom following simple yet powerful rules. This article investigates the integration and switch between these two strategies, considering the deployment environment factors, such as poor network conditions and unknown and often highly mobile obstacles. We design a distributed formation controller to guide multiple UAVs in orderless states to swiftly reach an intended formation. Inspired by starling birds and similar biological creatures, a distributed collision avoidance controller is proposed to avoid unknown and mobile obstacles. We further illustrated the stability of the controllers over both fixed and switching topologies. The experimental results confirm the effectiveness of the framework.

UAV path planning and collision avoidance in 3D environments based on POMPD and improved grey wolf optimizer

Due to the complexity and uncertain factors of the environment, a 3D path planning algorithm is urgently needed. This paper presents a 3D optimal feasible flight path generation and collision avoidance algorithms based on partially observable Markov decision process (POMDP) and improved grey wolf optimizer (GWO) for an unmanned aerial vehicle (UAV). Firstly, a novel algorithm based on the GWO is proposed to deal with constrained optimization problem (COP) and utilized to plan a flyable path. The designed variant is called improved GWO with level comparison (GWOLC), which combines the communication mechanism and the ε-level comparison method at the same time. Secondly, aircraft collision avoidance is modeled as a Partially Observable Markov Decision Process (POMDP) and the Monte-Carlo tree search (MCTS) algorithm is used to solve it. We introduce a novel algorithm, Information Particle Filter Tree (IPFT), to solve the problem of belief update in continuous domain. Thirdly, simulation experiments are conducted in 3D environment, and numerical results showed the proposed algorithm offers good performance as measured by effectiveness, robustness, convergence, and constraint handling capabilities.

Reinforcement Learning Training Environment for Fixed Wing UAV Collision Avoidance

In recent years, Unmanned Aerial Vehicles (UAVs) are emerging as a key technology with possible uses for several applications. To fully exploit their potential, UAVs needs to be able to be fully automatized and they need to be allowed to go Beyond Visual Line of Sight (BVLOS). Nowadays, autopilots and Detect and Avoid (DAA) systems, essential components for BVLOS operations, are developed with classical control approaches and classical algorithm for identification and avoidance of collision in the airspace. However, new methods based on Artificial Intelligence and, in particular, on Reinforcement Learning are attracting scientific interest. In order to train an agent with Reinforcement Learning methods, the development of the training environment is of utmost importance. This paper aims to present the development of a training environment to train an agent to avoid collisions in the airspace by setting desired values of roll, pitch and throttle. It will describe the developed training environment and the PID controllers implemented for allowing the own aircraft to receive the roll, pitch and throttle commands and to control the intruders’ trajectory.

Navigation of a UAV Team for Collaborative Eavesdropping on Multiple Ground Transmitters

Thanks to excellent mobility and high probability of a Line-of-Sight (LoS) to ground objects, unmanned aerial vehicles (UAVs) have been widely used in surveillance. This paper considers the use of UAVs to covertly and collaboratively eavesdrop on suspicious wireless transmitters on the ground. We focus on the trajectory planning of the UAVs. To avoid the UAVs being visually noticed by the ground transmitters, we propose a new measure to quantify the disguising performance of the UAVs. The trajectories of the UAVs are planned to maximize the disguising performance, subject to an uninterrupted eavesdropping requirement, UAV collision avoidance and UAV aeronautic maneuverability. A new randomized method based on the Rapidly-exploring Random Tree (RRT) is developed to efficiently construct the trajectories of the UAVs. Computer simulations confirm that the proposed method outperforms the random movement method in eavesdropping performance, while achieving with comparable disguising performance.

On Unmanned Aerial Vehicles Light Show Systems: Algorithms, Software and Hardware

Unmanned aerial vehicle (UAV) light shows (UAV-LS) have a wow factor due to their advantages in terms of environment friendliness and controllability compared to traditional fireworks. In this paper, a UAV-LS system is developed including a collision-free formation transformation trajectory planning algorithm, a software package that facilitates animation design and real-time monitoring and control, and hardware design and realization. In particular, a dynamic task assignment algorithm based on graph theory is proposed to reduce the impact of UAV collision avoidance on task assignment and the frequency of task assignment in the formation transformation. In addition, the software package consists of an animation interface for formation drawing and 3D animation simulation, which helps the monitoring and control of UAVs through a real-time monitoring application. The developed UAV-LS system hardware consists of subsystems of decision-making, real-time kinematic (RTK) global positioning system (GPS), wireless communication, and UAV platforms. Outdoor experiments using six quadrotors are performed and details of implementations of high-accuracy positioning, communication, and computation are presented. Results show that the developed UAV-LS system can successfully complete a light show and the proposed task assignment algorithm performs better than traditional static ones.

Distributed Multi-Agent Target Tracking: A Nash-Combined Adaptive Differential Evolution Method for UAV Systems

Multi-agent cooperative target tracking plays a significant role in distributed artificial intelligence for unmanned aerial vehicle (UAV) systems. Most existing tracking solutions using online path planning focus on general target trajectories. Such trajectories have strong regularity and are smooth with minimal fluctuations. However, in real UAV applications a target will change its trajectory frequently to prevent from being tracked, and thus its trajectory will fluctuate greatly and randomly. To this end, in this paper we consider a realistic scenario where the UAV target trajectory is changeable and random. For real-time target tracking, we formulate the tracking task as a distributed model predictive control (DMPC) problem, the objective of which is to optimize tracking performance under various constraints. To do so, we innovatively combine the adaptive differential evolution (ADE) algorithm with Nash optimization, and then propose a Nash-combined ADE method. Specifically, we use ADE to adaptively adjust the predicted trajectory of each UAV agent and Nash optimization to efficiently solve DMPC formulation for global optimization, which can improve the tracking accuracy and simultaneously reduce the computational complexity. The simulation results show that the proposed method performs well in terms of tracking accuracy, UAV collision avoidance and tracking stability for realistic target trajectories.

Hierarchical task-based formation control and collision avoidance of UAVs in finite time

This work addresses the problem of distributedly controlling the position of a group of Unmanned Aerial Vehicles (UAVs), that are considered as holonomic three-dimensional agents, to achieve a desired formation while collisions are avoided. We propose a generic control scheme computed by the adaptive convex combination of two control laws dealing with two, possibly conflicting, tasks, which are formation control and obstacle avoidance. The main contributions of the paper are threefold: First, the whole proposed scheme is distributed by nature, since the formation control is formulated as a consensus problem of virtual agents and the collision avoidance strategy is reactive, valid for unknown environments. Second, two control protocols are proposed to guarantee convergence to the desired formation in finite or predefined time; in the last case, the formation is achieved in a constant time independently of the initial UAVs positions. And finally, the control scheme generates continuous control signals in spite of activation and deactivation of the obstacle avoidance task, and stability is proved even in the transition of tasks. The effectiveness of the proposed approach is shown through realistic simulations and real experiments for a group of quadrotors.

Optimal trajectory planning for cinematography with multiple Unmanned Aerial Vehicles

This paper presents a method for planning optimal trajectories with a team of Unmanned Aerial Vehicles (UAVs) performing autonomous cinematography. The method is able to plan trajectories online and in a distributed manner, providing coordination between the UAVs. We propose a novel non-linear formulation for this challenging problem of computing multi-UAV optimal trajectories for cinematography; integrating UAVs dynamics and collision avoidance constraints, together with cinematographic aspects like smoothness, gimbal mechanical limits and mutual camera visibility. We integrate our method within a hardware and software architecture for UAV cinematography that was previously developed within the framework of the MultiDrone project; and demonstrate its use with different types of shots filming a moving target outdoors. We provide extensive experimental results both in simulation and field experiments. We analyze the performance of the method and prove that it is able to compute online smooth trajectories, reducing jerky movements and complying with cinematography constraints.