In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...
This doctoral thesis navigates the complex landscape of motion coordination and formation control within teams of rotary-wing Micro Aerial Vehicles (MAVs). Prompted by the intricate demands of real-world applications such as search and rescue or surveillan ...
Model-based reinforcement learning for robot control offers the advantages of overcoming concerns on data collection and iterative processes for policy improvement in model-free methods. However, both methods use exploration strategy relying on heuristics ...
Shape-changing robots adapt their own morphology to address a wider range of functions or environments than is possible with a fixed or rigid structure. Akin to biological organisms, the ability to alter shape or configuration emerges from the underlying m ...
The design of an oil free turbocharger supported on herringbone grooved gas bearing was formulated as a multi-objective problem, which was solved by coupling a reduced order parametric model for gas bearing supported rotors with an evolutionary algorithm. ...
Order, regularities, and patterns are ubiquitous around us. A flock of birds maneuvering in the sky, the self-organization of social insects, a global pandemic or a traffic jam are examples of complex systems where the macroscopic patterns arise from the m ...
Quadratic Programming (QP)-based controllers allow many robotic systems, such as humanoids, to successfully undertake complex motions and interactions. However, these approaches rely heavily on adequately capturing the underlying model of the environment a ...
Programming intelligent robots requires robust controllers that can achieve desired tasks while adapting to the changes in the task and the environment. In this thesis, we address the challenges in designing such adaptive and anticipatory feedback controll ...
Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms but also to a drastic increase in computational power used to train them.|S ...
