No abstract

In recent years, the use of multiple unmanned aerial vehicles (UAVs) in various applications has progressively increased thanks to advancements in multi-agent system technology, which enables the accomplishment of complex tasks that require cooperative and coordinated abilities. In this article, multi-UAV applications are grouped into five classes based on their primary task: coverage, adversarial search and game, computational offloading, communication, and target-driven navigation. By employing a systematic review approach, we select the most significant works that use deep reinforcement learning (DRL) techniques for cooperative and scalable multi-UAV systems and discuss their features using extensive and constructive critical reasoning. Finally, we present the most likely and promising research directions by highlighting the limitations of the currently held assumptions and the constraints when dealing with collaborative DRL-based multi-UAV systems. The suggested areas of research can enhance the transfer of knowledge from simulations to real-world environments and can increase the responsiveness and safety of UAV systems.

We design a multi-purpose environment for autonomous UAVs offering different communication services in a variety of application contexts (e.g., wireless mobile connectivity services, edge computing, data gathering). We develop the environment, based on OpenAI Gym framework, in order to simulate different characteristics of real operational environments and we adopt the Reinforcement Learning to generate policies that maximize some desired performance. The quality of the resulting policies are compared with a simple baseline to evaluate the system and derive guidelines to adopt this technique in different use cases. The main contribution of this paper is a flexible and extensible OpenAI Gym environment, which allows to generate, evaluate, and compare policies for autonomous multidrone systems in multi-service applications. This environment allows for comparative evaluation and benchmarking of different approaches in a variety of application contexts.

Unmanned aerial vehicles (UAVs) are supposed to be used to provide different services from video surveillance to communication facilities during critical and high-demanding scenarios. Augmented reality streaming services are especially demanding in terms of required throughput, computing resources at the user device, as well as user data collection for advanced applications, for example, location-based or interactive ones. This work is focused on the experimental utilization of a framework adopting reinforcement learning (RL) approaches to define the paths crossed by UAVs in delivering resources for augmented reality services. We develop an OpenAI Gym-based simulator that is tuned and tested to study the behavior of UAVs trained with RL to fly around a given area and serve augmented reality users. We provide abstractions for the environment, the UAVs, the users, and their requests. A reward function is then defined to encompass several quality-of-experience parameters. We train our agents and observe how they behave as a function of the number of UAVs and users at different hours of the day.