We present an approach for learning a reactive maneuver policy for a UAV involved in a close-quarters one-on-one aerial engagement. Specifically, UAVs with behaviors learned through reinforcement learning can match or improve upon simple, but effective behaviors for intercept. In this paper, a framework for developing reactive policies that can learn to exploit behaviors is discussed. In particular, the A3C algorithm with a deep neural network is applied to the aerial combat domain. The efficacy of the learned policy is demonstrated in Monte Carlo experiments. An architecture that can transfer the learned policy from simulation to an actual aircraft and its effectiveness in live-flight are also demonstrated.

On Developing a UAV Pursuit-Evasion Policy Using Reinforcement Learning

We seek to review recent and current research efforts by the US military in the field of robotics. We present background on research arms and current overall strategy in developing autonomous and robotic systems. We also discuss specific projects undertaken by the different research arms and service branches. The US military has widely used remote piloted systems for 25 years. That has shifted to systems that are capable of autonomous deployment and navigation but are overseen by human operators. Current research thrusts include increasing the amount of decision-making these systems are capable of and allowed to make. Recent research also focuses on developing new and novel tactics enabled by autonomous systems and ensuring that these systems can work well with each other and with human teammates. Robotics and autonomous systems are central to the long-term plans of the U.S. Military. Each service branch is pursuing research according to its mission and culture. Multirobot systems and increased levels of autonomy are key research thrusts, though human oversight will remain for the near future.

https://link.springer.com/content/pdf/10.1007/s43154-020-00039-w.pdf

Cooperative Multirobot Systems for Military Applications

This paper proposes a system for autonomous aerial combat of next generation unmanned combat aerial vehicles(UVACs). The system includes a decision making scheme, positional prediction of targets, an aircraft model analysis, and a basic fighter maneuvering (BFM)-based combat guidance law designed to generate effective combat maneuvers. A oneon-one combat simulation environment is set up, and the virtual fighter pilot (VFP) combat simulation results are addressed. The VFP proposed in this paper follows the mindset of an real human pilot, and all the subcomponents that reflect the thought processes are modularized. The designed BFM-based aerial combat guidance law conducts suboptimal combat maneuvers in real time. In order for a fighter jet to attain advantageous positions in aerial combat, it must have the ability to carry out high agility maneuvers. Therefore, a V-n diagram and an energy-maneuverability chart analysis are used to determine the limits of the aircraft’s flight operable regions and to find the corner velocity of the aircraft model for the maximum rate of turn. Based on the measured combat geometry, the VFP carries out decision making processes and assesses situations in terms of scoring functions. In order to preoccupy advantageous geometry in combat, the system estimates the future positions of the target using velocity estimation-based target prediction. The modularized VFP is designed using a MATLAB/Simulink, and its simulation environment is designed based on an F-16 model. The performance of the designed VFP is verified, and through animation, the maneuvers of the UCAVs are visualized in real time.

/pdf/design-of-a-virtual-fighter-pilot-and-simulation-environment-3v9z597sgr.pdf

Design of a Virtual Fighter Pilot and Simulation Environment for Unmanned Combat Aerial Vehicles

In 2015, a group of Naval Postgraduate School (NPS) professors and students set the record for largest fixed-wing unmanned aerial vehicle (UAV) swarm flown at one time. The swarm had 50 vehicles flying simultaneously and successfully demonstrated distributed decision-making with all processing occurring on swarm vehicles rather than a centralized control station. Much of the decision-making is based on telemetry data that is continuously streamed from all the nodes. At that time all telemetry data was broadcast in a single-hop radio environment using 802.11n in infrastructure mode. In the future, drone swarm distribution and mobility patterns will necessitate multi-hop communications for this telemetry data. This paper models the network currently used by the NPS drone swarm as well as potential future topologies and evaluates candidate multihop routing protocols for this application.

Multihop routing of telemetry data in drone swarms

SUMMARY This paper proposes and evaluates swarming mechanisms of patrolling unmanned aerial vehicles (UAVs) that can collectively search a region for intruding UAVs. The main contributions include the development of multi-objective searching strategies and investigation of the required sensor configurations for the patrolling UAVs. Numerical results reveal that it is sometimes better to search through a region with a single swarm rather than multiple swarms deployed over sub-regions. Moreover, a large communication range does not necessarily improve search performances, and the patrolling swarm must have a speed close to the speed of the intruding UAVs to maximize the search performances.

Search Strategies and Specifications in a Swarm versus Swarm Context

Autonomous unmanned aerial vehicles (UAVs) present an increasingly viable threat vector to the Defense com- munity. Existing response systems are vulnerable to saturation attacks of large swarms of low-cost autonomous vehicles. One method of reducing this threat is the use of an intelligent counter swarm with tactics, navigation and planning capabilities for engaging the adversarial swarm. Though previous studies exist that have produced libraries of basic fighter tactics employable by unmanned fixed-wing aircraft, we are aware of little prior work that explores close-in tactical engagements at a large scale (teams of at least size 10). We examine existing technologies that can be applied in fixed-wing swarm-versus-swarm engagement, including classic pursuit-evasion strategies and the application of Lanchester's laws for attrition calculations. Our recent studies center on lever- aging existing manned fighter combat doctrine, and on the benefits of collaboration. We consider experiments in close-air combat against adversaries capable of destroying aerial targets. The following work employs both a Monte Carlo analysis in a simulation environment to measure the effectiveness of several autonomous tactics, as well as an analysis of live flight experiments in swarm competitions with up to 10 vs. 10 scenarios.

Responding to unmanned aerial swarm saturation attacks with autonomous counter-swarms

This paper builds on previous Naval Postgraduate School success with large, autonomous swarms of fixed-wing unmanned aerial vehicles (UAV) to provide infrastructure for the simultaneous operation of multiple swarms. Developed in support of an event fostering swarm capability development through competition, the online referee, or Arbiter, monitors and evaluates multiple independent but interacting swarms. This Arbiter provides sensor modeling for both swarms, evaluation of inter-swarm interaction, scoring and enforcement of competition rules, and graphical display of game status. Arbiter capability is demonstrated through live-fly experiments and software-in-the-loop simulation. The Arbiter is also used to evaluate swarm behaviors that are developed for air-to-air pursuit of an opposing swarm with results provided in this paper.

Multi-swarm Infrastructure for Swarm Versus Swarm Experimentation

A potential approach for engaging an adversarial force of fixed-wing UAVs is to counter it with a similar force. There are open questions, however, regarding the numbers and characteristics necessary for the defending UAV team in such a scenario. In this paper, we consider the importance of coordination in such a mutli-UAV aerial engagement. We introduce a legacy-tactic-inspired autonomous UAV behavior that uses simple coordination between team members for targeting opponents, and test it in simulated engagements against a team of non-coordinating UAVs that use simple nearest-enemy guidance logic. Extensive simulations were performed, varying tactical behavior, team size, and weapon effectiveness. Results show that both relative team size and autonomous behavior are significant factors in engagement outcome.

On Coordination in Multiple Aerial Engagement

This paper describes research performed in pursuit of autonomous swarm tactics for unmanned aerial vehicles (UAVs) as part of an internally funded effort at the Georgia Tech Research Institute (GTRI). Human engineered swarming tactics, reinforcement learned tactics, and aggressive flight maneuvers are explored. Aggressive flight maneuvers included autonomous descents, rolls, and an Immelmann maneuver. These efforts expand on preliminary control capabilities and are intended to enable groups of UAVs to act as a defensive swarm to counter aggressor swarms. All tactics have been validated in simulation using the GTRI-developed SCRIMMAGE [1], [2] simulation engine and were further proven in live-fly experiments throughout the duration of the ACTION effort, which ran from 2017-2019.

Aerial Combat Tactics In Overwhelming Numbers

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Michael A. Day

Author Tools

Chat about Author

Papers

Responding to unmanned aerial swarm saturation attacks with autonomous counter-swarms

Multi-swarm Infrastructure for Swarm Versus Swarm Experimentation

On Coordination in Multiple Aerial Engagement

Aerial Combat Tactics In Overwhelming Numbers