The proliferation of small uncrewed aerial systems (UAS) poses many threats to airspace systems and critical infrastructures. In this paper, we apply deep reinforcement learning (DRL) to intercept rogue UAS in urban airspaces. We train a group of homogeneous friendly UAS, in this paper referred to as agents, to pursue and intercept a faster UAS evading capture while navigating through crowded airspace with several moving non-cooperating interacting entities (NCIEs). The problem is formulated as a multi-agent Markov Decision Process, and we develop the Proximal Policy Optimization based Advantage ActorCritic (PPO-A2C) method to solve it, where the actor and critic networks are trained in a centralized server and the derived actor network is distributed to the agents to generate the optimal action based their observations. The simulation results show that, as compared to the traditional method, PPO-A2C fosters collaborations among agents to achieve the highest probability of capturing the evader and maintain the collision rate with other agents and NCIEs in the environment.
Borrowing from nature, neural-inspired interception algorithms were implemented onboard a vehicle. To maximize success, work was conducted in parallel within a simulated environment and on physical hardware. The intercept vehicle used only optical imaging to detect and track the target. A successful outcome is the proof-of-concept demonstration of a neural-inspired algorithm autonomously guiding a vehicle to intercept a moving target. This work tried to establish the key parameters for the intercept algorithm (sensors and vehicle) and expand the knowledge and capabilities of implementing neural-inspired algorithms in simulation and on hardware.
Sensors continue to decrease in size and power. This report presents results of a market survey conducted in February 2020 for commercial off-the-self sensors with optimal size, weight, and power to be carried onboard a small unmanned aircraft system. For this report, Sandia National Laboratories considered sensors that can detect an object in three dimensions. The sensors that were researched are broken into three categories: radio detection and ranging sensors, stereo camera sensors, and light detection and ranging sensors.
Unmanned aircraft systems (UASs) have grown significantly within the private sector with ease of acquisition and platform capabilities far outstretching what previously existed. Where once the operation of these platforms was limited to skilled individuals, increased computational power, manufacturing techniques, and increased autonomy allows inexperienced individuals to skillfully maneuver these devices. With this rise in consumer use of UAS comes an increased security concern regarding their use for malicious intent.The focus area of counter UAS (CUAS) remains a challenging space due to a small cross-sectioned UAS's ability to move in all three dimensions, attain very high speeds, carry payloads of notable weight, and avoid standard delay techniques.We examine frequency analysis of pixel fluctuation over time to exploit the temporal frequency signature present in UAS imagery. This signature allows for lower pixels-on-target detection [1]. The methodology also acts as a method of assessment due to the distinct frequency signatures of UAS when examined against the standard nuisance alarms such as birds. The temporal frequency analysis (TFA) method demonstrates a UAS detection and assessment method. In this paper we discuss signal processing and Fourier filter optimization methodologies that increase UAS contrast.
Using internal investment funds within Sandia National Laboratories’ (SNL) Division 6000, JUBA was a collaborative exercise between SNL Orgs. 6533 & 6913 (later 8863) to demonstrate simultaneous flights of tethered balloons and UAS on the North Slope of Alaska. JUBA UAS and tethered balloon flights were conducted within the Restricted Airspace associated with the ARM AMF3 site at Oliktok Point, Alaska. The Restricted Airspace occupies a 2 nautical mile radius around Oliktok Point. JUBA was conducted at the Sandia Arctic Site, which is approximately 2 km east-southeast of the AMF3. JUBA activities occurred from 08/08/17 – 08/10/17. Atmospheric measurements from tethered balloons can occur for a long duration, but offer limited spatial variation. Measurements from UAS could offer increased spatial variability.