Drones are expected to be used extensively for delivery tasks in the future. In the absence of obstacles, satellite based navigation from departure to the geo-located destination is a simple task. When obstacles are known to be in the path, pilots must build a flight plan to avoid them. However, when they are unknown, there are too many or they are in places that are not fixed positions, then to build a safe flight plan becomes very challenging. Moreover, in a weak satellite signal environment, such as indoors, under trees canopy or in urban canyons, the current drone navigation systems may fail. Artificial intelligence, a research area with increasing activity, can be used to overcome such challenges. Initially focused on robots and now mostly applied to ground vehicles, artificial intelligence begins to be used also to train drones. Reinforcement learning is the branch of artificial intelligence able to train machines. The application of reinforcement learning to drones will provide them with more intelligence, eventually converting drones in fully-autonomous machines. In this work, reinforcement learning is studied for drone delivery. As sensors, the drone only has a stereo-vision front camera, from which depth information is obtained. The drone is trained to fly to a destination in a neighborhood environment that has plenty of obstacles such as trees, cables, cars and houses. The flying area is also delimited by a geo-fence; this is a virtual (non-visible) fence that prevents the drone from entering or leaving a defined area. The drone has to avoid visible obstacles and has to reach a goal. Results show that, in comparison with the previous results, the new algorithms have better results, not only with a better reward, but also with a reduction of its variance. The second contribution is the checkpoints. They consist of saving a trained model every time a better reward is achieved. Results show how checkpoints improve the test results.

The continuous development of technical innovations provides the opportunity to create new economic markets and a wealth of new services. However, these innovations sometimes raise concerns, notably in terms of societal, safety, and environmental impacts. This is the case for services related to the operation of unmanned aerial vehicles (UAV), which are emerging rapidly. Unmanned aerial vehicles, also called drones, date back to the first third of the twentieth century in aviation industry, when they were mostly used for military purposes. Nowadays, drones of various types and sizes are used for many purposes, such as precision agriculture, search and rescue missions, aerial photography, shipping and delivery, etc. Starting to operate in areas with low population density, drones are now looking for business in urban and suburban areas, in what is called urban air mobility (UAM). However, this rapid growth of the drone industry creates psychological fear of the unknown in some parts of society. Reducing this fear will play an important role in public acceptance of drone operations in urban areas. This paper presents the main concerns of society with regard to drone operations, as already captured in some public surveys, and proposes a list of mitigation measures to reduce these concerns. The proposed list is then analyzed, and its applicability to individual, urban, very large demonstration flights is explained, using the feedback from the CORUS-XUAM project. CORUS-XUAM will organize a set of very large drone flight demonstrations across seven European countries to investigate how to safely integrate drone operations into airspace with the support of the U-space.

Unmanned aerial vehicles (UAV) specifically drones have been used for surveillance, shipping and delivery, wildlife monitoring, disaster management etc. The increase on the number of drones in the airspace worldwide will lead necessarily to full autonomous drones. Given the expected huge number of drones, if they were operated by human pilots, the possibility to collide with each other could be too high. In this paper, deep reinforcement learning (DRL) architecture is proposed to make drones behave autonomously inside a suburb neighborhood environment. The environment in the simulator has plenty of obstacles such as trees, cables, parked cars and houses. In addition, there are also another drones, acting as moving obstacles, inside the environment while the learner drone has a goal to achieve. In this way the drone can be trained to detect stationary and moving obstacles inside the neighborhood and so the drones can be used safely in a public area in the future. The drone has a front camera and it can capture continuously depth images. Every depth image is part of the state used in DRL architecture. Also, another part of the state is the distance to the geo-fence (a virtual barrier on the environment) which is added as a scalar value. The agent will be rewarded negatively when it tries to overpass the geo-fence limits. In addition, angle to goal and elevation angle between the goal and the drone will be used as information to be added to the state. It is considered that these scalar values will improve the DRL performance and also the reward obtained. The drone is trained using Q-Network and its convergence and final reward are evaluated. The states containing image and several scalars are processed by a neural network that joints the two state parts into a unique flow. This neural network is named as Joint Neural Network (JNN) [1]. The training and test results show that the agent can successfully learn to avoid any obstacle in the environment. The results for three scenarios are very promising and the learner drone reaches the destination with a success rate 100% in first two tests and with a success rate 98% in the last test, this one with a total of three drones.

The number of unmanned aerial vehicles (UAVs, also known as drones) has increased dramatically in the airspace worldwide for tasks such as surveillance, reconnaissance, shipping and delivery. However, a small number of them, acting maliciously, can raise many security risks. Recent Artificial Intelligence (AI) capabilities for object detection can be very useful for the identification and classification of drones flying in the airspace and, in particular, are a good solution against malicious drones. A number of counter-drone solutions are being developed, but the cost of drone detection ground systems can also be very high, depending on the number of sensors deployed and powerful fusion algorithms. We propose a low-cost counter-drone solution composed uniquely by a guard-drone that should be able to detect, locate and eliminate any malicious drone. In this paper, a state-of-the-art object detection algorithm is used to train the system to detect drones. Three existing object detection models are improved by transfer learning and tested for real-time drone detection. Training is done with a new dataset of drone images, constructed automatically from a very realistic flight simulator. While flying, the guard-drone captures random images of the area, while at the same time, a malicious drone is flying too. The drone images are auto-labelled using the location and attitude information available in the simulator for both drones. The world coordinates for the malicious drone position must then be projected into image pixel coordinates. The training and test results show a minimum accuracy improvement of 22% with respect to state-of-the-art object detection models, representing promising results that enable a step towards the construction of a fully autonomous counter-drone system.

Counter-drone technology by using artificial intelligence (AI) is an emerging technology and it is rapidly developing. Considering the recent advances in AI, counter-drone systems with AI can be very accurate and efficient to fight against drones. The time required to engage with the target can be less than other methods based on human intervention, such as bringing down a malicious drone by a machine-gun. Also, AI can identify and classify the target with a high precision in order to prevent a false interdiction with the targeted object. We believe that counter-drone technology with AI will bring important advantages to the threats coming from some drones and will help the skies to become safer and more secure. In this study, a deep reinforcement learning (DRL) architecture is proposed to counter a drone with another drone, the learning drone, which will autonomously avoid all kind of obstacles inside a suburban neighborhood environment. The environment in a simulator that has stationary obstacles such as trees, cables, parked cars, and houses. In addition, another non-malicious third drone, acting as moving obstacle inside the environment was also included. In this way, the learning drone is trained to detect stationary and moving obstacles, and to counter and catch the target drone without crashing with any other obstacle inside the neighborhood. The learning drone has a front camera and it can capture continuously depth images. Every depth image is part of the state used in DRL architecture. There are also scalar state parameters such as velocities, distances to the target, distances to some defined geofences and track, and elevation angles. The state image and scalars are processed by a neural network that joints the two state parts into a unique flow. Moreover, transfer learning is tested by using the weights of the first full-trained model. With transfer learning, one of the best jump-starts achieved higher mean rewards (close to 35 more) at the beginning of training. Transfer learning also shows that the number of crashes during training can be reduced, with a total number of crashed episodes reduced by 65%, when all ground obstacles are included.

Police tasks related with law enforcement and citizen protection have gained a very useful asset in drones. Crowded demonstrations, large sporting events, or summer festivals are typical situations when aerial surveillance is necessary. The eyes in the sky are moving from the use of manned helicopters to drones due to costs, environmental impact, and discretion, resulting in local, regional, and national police forces possessing specific units equipped with drones. In this paper, we describe an artificial intelligence solution developed for the Castelldefels local police (Barcelona, Spain) to enhance the capabilities of drones used for the surveillance of large events. In particular, we propose a novel methodology for the efficient integration of deep learning algorithms in drone avionics. This integration improves the capabilities of the drone for tasks related with capacity control. These tasks have been very relevant during the pandemic and beyond. Controlling the number of persons in an open area is crucial when the expected crowd might exceed the capacity of the area and put humans in danger. The new methodology proposes an efficient and accurate execution of deep learning algorithms, which are usually highly demanding for computation resources. Results show that the state-of-the-art artificial intelligence models are too slow when utilised in the drone standard equipment. These models lose accuracy when images are taken at altitudes above 30 m. With our new methodology, these two drawbacks can be overcome and results with good accuracy ($96\%$ correct segmentation and between $20\%$ and $35\%$ mean average proportional error) can be obtained in less than 20 s.