Counter a Drone in a Complex Neighborhood Area by Deep Reinforcement Learning

Abstract

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.

Counter a Drone and the Performance Analysis of Deep Reinforcement Learning Method and Human Pilot

“…In this paper, DDQN algorithm is chosen for DRL training. The best performance of DDQN algorithm have already been presented in previous studies [22], [6]. DRL model have been changed and the improvements are included considering the new image state which is improved by using the state of the art object detection algorithm and fences on the image state, new reward function and drone actions, updated geo-fence locations.…”

“…The image is an input of a convolutional neural network (CNN), followed by a flatten layer and then a concatenation layer joints the flatten output of the CNN with scalar inputs. Neural network model is explained in detail in our previous research [6].…”

“…Wyder et al [5], presented a UAV platform to detect and counter a small UAV in an indoor environment without GPS information. In a study presented in MDPI Sensors journal [6], DRL architecture is proposed to counter a drone with another drone. In this study, drone is a quadcopter and it can catch the target drone and it can also autonomously avoid all kind of obstacles inside a suburban neighborhood environment.…”

DRONET: Multi-Tasking Framework for Real-Time Industrial Facility Aerial Surveillance and Safety

“…On the other hand, drone identification is concerned with determining the legality or illegality, harmfulness or otherwise of a drone in sight which invariably determines the neutralization strategy to adopt (jamming, hunting, or re-assembling to overwrite control) through flexible secured authentications to counter and keep the illegal drone or its derivatives within the authorized area [11,12] as depicted in Figure 1. These concepts are the integral components of an anti-drone system, which is a multi-tasking, multi-modal, and complex hard real-time critical mission networkcontrolled system used in engaging drones and other aerial vehicles in the airspace [13]. This suggests that attempting to address the detection concerns in isolation without considering the other components of the anti-drone system is counterproductive-hence a multi-tasking approach.…”

Improving real-time drone detection for counter-drone systems

“…A full counter-drone system using several types of sensors and several levels of prediction and fusion was also presented by Samaras et al (5) . A Deep Reinforcement Learning (DRL) solution was proposed by Çetin et al (6) to counter a drone by using another drone. The countering drone can autonomously avoid all kinds of obstacles (trees, cars, houses, etc.)…”