2017 · 13 citations · 13 references
EngineeringAerospace EngineeringAutonomous SystemsAerial RoboticsAutonomous VehiclesMachine LearningAircraft ControlFlight SimulationAutonomous Flight ControlFlightFlight TestingUnmanned Aerial Vehicle Control
Contemporary models of Unmanned Aerial Vehicles (UAVs) are largely developed using simulators. In a typical scheme, a flight simulator is dovetailed with a machine learning (ML) algorithm. A good simulator provides a realistic environment for simulated aircraft. It also provides the ability to invoke and fly various models of aircraft. The ML algorithm, in turn, allows to find an appropriate set of control inputs that can be useful in flying the aircraft autonomously. Creating UAVs in this way has certain obvious benefits. The process of development can be accelerated largely by employing a testbed that allows a seamless dovetailing between the flight simulator and an ML algorithm of choice. However, an extensive testbed is largely missing from the academic landscape both in terms of implementation and technical details. This papers proposes a new testbed for the development of fully autonomous UAVs. The proposed system allows researchers to simulate UAVs for various scenarios.
13
Neural networks for pattern recognition
Choice Reviews Online · 1994 · 18.7K citations
The Complexity of Decentralized Control of Markov Decision Processes
Daniel S. Bernstein, Robert Givan, Neil Immerman et al. · Mathematics of Operations Research · 2002 · 1.2K citations
The GRASP Multiple Micro-UAV Testbed
Nathan Michael, Daniel Mellinger, Quentin Lindsey et al. · IEEE Robotics & Automation Magazine · 2010 · 771 citations
Engineering, Aerospace Engineering, Mechanical Engineering +5