Reinforcement Learning for Flight Control: Hybrid Offline-Online Learning for Robust and Adaptive Fault-Tolerance

Recent advancements in fault-tolerant flight control have involved model-free offline and online Reinforcement Learning algorithms in order to provide robust and adaptive control to autonomous systems. Inspired by recent work on Incremental Dual Heuristic Programming (IDHP) and Soft Actor-Critic (SAC), this research proposes a hybrid SAC-IDHP...

Increasing data sustainability: a behavioural approach

In a matter of decades, information technologies have become omni-present in the lives of more than a billion people. Whilst holding many promises for more efficient and therefore seemingly more sustainable practices, this fast-growing industry is expanding its footprint rapidly. Exponential advancements in hardware and software are kept in...

Explainable Artificial Intelligence Techniques for the Analysis of Reinforcement Learning in Non-Linear Flight Regimes

Reinforcement Learning is being increasingly applied to flight control tasks, with the objective of developing truly autonomous flying vehicles able to traverse highly variable environments and adapt to unknown situations or possible failures. However, the development of these increasingly complex models and algorithms further reduces our...

Beauty Ideals

If 10 people would answer the question “What falls into the category grooming and what is beautification?” there would be 10 different answers. For some, grooming does not go beyond taking a shower and brushing your teeth. But what about shaving? Or make-up? And a question that arose during quarantine: how important are hairdressers? Most people...

Smart Bench: A Speculative Design to Create Critical Awareness of Data-driven Nudging in the Smart City

The Smart Bench is a speculative design aiming to create critical awareness about the social implications of Data-driven Nudging in the Smart City. The project originated from a critical perspective on Smart City as a leading urban development paradigm. Many cities labelling themselves as smart cities competitively implemented advanced...

Longitudinal Flight Control by Reinforcement Learning: Online Adaptive Critic Design Approach to Altitude Control

Reinforcement learning is used as a type of adaptive flight control. Adaptive Critic Design (ACD) is a popular approach for online reinforcement learning control due to its explicit generalization of the policy evaluation and the policy improvement elements. A variant of ACD, Incremental Dual Heuristic Programming (IDHP) has previously been...

Me and My Smartphone - The influence smartphones have on our lives: Using critical designs as a tool to raise awareness for our societal issues related to smartphones

Smartphones have become an inseparable gadget and beneficial tool in our lives. Imagining a future without them would truly be impossible. When a new technology arrives, society needs time to adjust and become aware of the impact products have on people and our ways of behaving.. This always takes time. In the case of smartphones, the last few...

Online Reinforcement Learning for Flight Control: An Adaptive Critic Design without prior model knowledge

Online Reinforcement Learning is a possible solution for adaptive nonlinear flight control. In this research an Adaptive Critic Design (ACD) based on Dual Heuristic Dynamic Programming (DHP) is developed and implemented on a simulated Cessna Citation 550 aircraft. Using an online identified system model approximation, the method is independent...

Design for fairness in AI: Cooking a fair AI Dish

Artificial intelligence (AI) is an emerging field which unleashes massive new (business) opportunities. The potential growth and broad application of the AI technology has great economic benefits however also severe societal implications. Simultaneously, ethical challenges arise with its development. Questions of values and ethics are becoming...

Reinforcement Learning for Flight Control: Learning to Fly the PH-LAB

In recent years Adaptive Critic Designs (ACDs) have been applied to adaptive flight control of uncertain, nonlinear systems. However, these algorithms often rely on representative models as they require an offline training stage. Therefore, they have limited applicability to a system for which no accurate system model is available, nor readily...

Escape the Smart City: Critical pervasive game to question the AI-surveillance infrastructure in the smart city

Escape the Smart City is a critical pervasive game for creating awareness about the implications of AI-surveillance technology in the smart city. It responds to growing concerns over the mass deployment of surveillance cameras that are enhanced with artificial intelligence (AI) which are turning the cities into digital panopticons (Sadowski &amp...

Experiencing the City: Towards a more pigeon inclusive Smart City

This graduation thesis critically reflects on the Smart City. It critiques certain values embedded in the technology used to source and analyse data, and manage the city, when it comes to the world of human experience. The theoretical critique is eventually expressed in a critical design. Applying the values of the Smart City to the feral pigeon.

Speculative (food) design histories: A critical look at the history of (Western) food

In this project I demonstrate how the world could have been different by portraying alternate historical realities, centered around food, to stimulate my audience to think about the choices they have in the present. The objective is to empower my audience to make mindful food choices today. The final outcome of this project is four stories and...

Adaptive-Critic Designs For Aircraft Control: A comparative study between Heuristic Dynamic Programming and Dual Heuristic Programming

The Variable Camber Continuous Trailing Edge Flap (VCCTEF) is a novel aircraft control system that intents to prevent undesired aeroelastic deflections by precise lift tailoring along the wing span. However, the unknown dynamics and increased complexity of the new hardware imposes difficulties to establish an optimal controller. One approach is...

An explorative study on business models for sustainability using STOF and stress-testing

A decision support system for balancing critical design issues in new service development for the TomTom Mapshop service platform

A case study research in which a decision support system is designed for balancing critical design issues that stem from the technology part of a business case.