Tilt-rotor Tailsitter Global Acceleration Control: Behavioural Cloning of a Nonlinear Model Predictive Controller

Capable of both vertical take-off and landing and forward flight, tail-sitters are a versatile class of UAVs with a large range of potential applications. A variant of tailsitters using tilt-rotors instead of ailerons for pitch and roll control has been proposed to mitigate the reduced control authority at low to zero velocities. The control of...

Integrated Torque Vectoring and Path Following using Nonlinear Model Predictive Control

This thesis introduces a novel model predictive controller (MPC) that integrates both torque vectoring and path following into one controller. Due to a need to improve vehicle safety, systems are being developed in order to improve vehicle handling. One system that is able to improve the vehicle handling is torque vectoring (TV). With torque...

Nonlinear Incremental Optimal Control for Underactuated Mechanical Systems: Robust Tightly-Coupled NMPC and INDI applied to Underactuated Mechanical Systems

Underactuated mechanical systems (UMS) feature prominently in robotics and aerospace, with aircraft, unmanned air vehicles, and aeroelastic wings as prime examples. These systems present multifaceted control challenges, ranging from inherent underactuation and stability concerns to state and control saturation and an overarching need for...

Game-Theoretic Intention-Aware Planning for Autonomous Vehicles

As Autonomous Vehicles (AVs) navigate through dynamic and constantly changing environments, it is crucial that they take into account the impact of their actions on the decisions of others for safe and efficient interaction with humans. In doing so, they need to anticipate how humans will behave in different situations based on their intentions....

Safer reinforcement learning for robotics

Reinforcement learning is an active research area in the fields of artificial intelligence and machine learning, with applications in control. The most important feature of reinforcement learning is its ability to learn without prior knowledge about the system. However, in the real world, reinforcement learning actions may lead to serious damage...