Policy Analysis of Safe Vertical Manoeuvring using Reinforcement Learning: Identifying when to Act and when to stay Idle

The number of unmanned aircraft operating in the airspace is expected to grow exponentially during the next decades. This will likely lead to traffic densities that are higher than those currently observed in civil and general aviation, and might require both a different airspace structure compared to conventional aviation, as well as different...

Spinning-off the AI: Defining the Value Proposition of an Artificial Intelligence solution

Artificial Intelligence technology offers computational, decision-making, and optimizing abilities that surpass every previously established traditional computation method. By being able to navigate across large amounts of data, the realized solutions learn on their own and provide results that would be unattainable with other ways. The complex...

Lateral and Vertical Air Traffic Control Under Uncertainty Using Reinforcement Learning

Air traffic demand has increased at an unprecedented rate in the last decade (albeit interrupted by the COVID pandemic), but capacity has not increased at the same rate. Higher levels of automation and the implementation of decision-support tools for air traffic controllers could help increase capacity and catch up with demand. The air traffic...

Reinforcement Learning for Quadcopter Fault Tolerance: Analyzing Hierarchical and Online Deep Reinforcement Learning for Quadcopter Fault Tolerant Control

The demand of adding fault tolerance to quadcopter control systems has significantly increased with the rise of adoption of UAVs in numerous sectors. This work proposes and demonstrates the use of Hierarchical Reinforcement Learning to control a quadcopter subject to severe actuator fault. State-of-the-art algorithms are implemented, and a...

Deep Reinforcement Learning with Feedback-based Exploration

Deep Reinforcement Learning enables us to control increasingly complex and high-dimensional problems. Modelling and control design is longer required, which paves the way to numerous in- novations, such as optimal control of evermore sophisticated robotic systems, fast and efficient scheduling and logistics, effective personal drug dosing...

Deep Reinforcement Learning - Pretraining actor-critic networks using state representation learning

In control, the objective is to find a mapping from states to actions that steer a system to a desired reference. A controller can be designed by an engineer, typically using some model of the system or it can be learned by an algorithm. Reinforcement Learning (RL) is one such algorithm. In RL, the controller is an agent that interacts with the...