Hospitals worldwide are under increasing pressure as patient intake rises while fewer staff are available to provide care. These challenges are particularly evident in Intensive Care Units (ICUs), where patients rely on one-to-one care. In the ICU, monitoring and frequent manual therapy adjustments lead to high workloads among clinical staff. (Semi-)closed-loop therapy systems, which automatically adjust or recommend therapy actions based on physiological data, offer the potential to reduce this workload while also improving the accuracy and consistency of care.
Despite growing evidence regarding the technical feasibility of these systems, limited research addresses how they should be designed for integration into the complex socio-technical context of the ICU. This thesis addresses this gap by developing a design framework aimed at overcoming adoption barriers and supporting their implementation within clinical workflows. Using blood pressure management as a case study, the research combined ICU observations, semi-structured interviews with ICU nurses, and a co-creation session involving clinical stakeholders and designers.
The findings resulted in nine guiding design principles: (1) Trust and confidence, (2) Regulation and legislation, (3) Reliable and safe functioning, (4) Context-aware automation, (5) System transparency, (6) Authority and control boundaries, (7) Critical clinical supervision, (8) Cognitive load management, and (9) Proven effectiveness. Each principle consists of underlying concerns, design challenges, and guiding questions to support practical application. Additionally, a structured design approach was developed to translate these principles into practice. By adapting the Systems Engineering Initiative for Patient Safety (SEIPS) model and integrating it with the Double Diamond process, this approach provides a step-by-step method for designers to move from analyzing today’s clinical reality to building a vision for future integration.
Together, the design principles and structured methodology demonstrate that successful implementation of (semi-)closed-loop therapy systems depends on carefully balancing technological capabilities with human and organizational needs. In doing so, this thesis offers both practical insights and a structured method for integrating (semi-)closed-loop therapy systems into intensive care practice.

Visitors of public security facilities (i.e. detention centres, courthouses, penitentiaries and customs) often experience anxiousness and low mood during their time in the waiting room, while staff have limited capacity to attend to visitors. To address this, we explore the design of a social robot that engages visitors through socially appropriate interactions intended to support a positive mood, while simultaneously providing staff with remote situation awareness. Simultaneously, social robots have been deployed as reception agents and mood-intervention tools in public settings (e.g., healthcare[1] and retail[2]). Usually, social robots in public buildings handle welcoming and giving information; this thesis will test what happens when a reception robot also provides visitors a mood-intervention activity. A social robot could therefore provide a friendlier atmosphere in the emotionally fraught visitor area of public security constrained facilities. Here we identify three complementary robot roles – receptionist, storyteller, and playmate – combined with a monitoring function for staff. Receptionist and storyteller roles were lab-evaluated using a local LLM powered social robot as a mood-intervention agent in two iterations with a Before-After Control-Impact (BACI) study. In the lab, the design was implemented with a Softbank Pepper-robot, a pre-post study indicated that interaction effectiveness depends on turn-taking level: high turn-taking activities produce larger immediate mood gains than low turn-taking storytelling. The playmate role was field-tested in a security-constrained public service waiting room. Beyond visitor surveys, semi-structured interviews explored staff acceptance. In the real-world evaluation, the design was implemented with an Enchanted Tools Miroki robot. The results indicate that visitors particularly value the playmate role, the guessing game agent was well accepted: 89% of visitors self-reported that the robot improved their visit(t(9) = 4.0, p < .005). Staff interviews underline acceptance rests on sociotechnical framing, perceived operational usefulness and minimizing of operational overhead. The results advance understanding of social robots in high-consequence domains and other affectively complex (anxiety-laden) public places, suggesting that rapid, reciprocal interaction designs improve mood-intervention outcomes for security constrained facility visitors. Overall, the study findings inform the iterative design of social robots for sensitive, high-security public environments. Our findings suggest further elaborating the waiting room robot with a (1) time-aware conversation system to offer activities suited to visitors’ time-frames and (2) multilingual functionality for visitors without Dutch proficiency. Additionally, the other areas of the security constrained facility provide possibilities where robots may help reduce staff burden; (3) as a multilingual interpreter and as a (4) supporting buddy to reflect on accidents during visit to the facility.

Clinical communication and information management are essential to healthcare, yet they remain challenged by fragmented documentation, fast-paced exchanges, data loss and burdensome administrative processes with Electronic Health Record (EHR) systems. Meanwhile, Artificial Intelligence (AI) shows strong potential to address these challenges by enhancing workflow efficiency and supporting real-time information documentation.

This graduation project, guided by TU Delft and Accenture IXID, investigates how AI can be integrated into healthcare communication processes. Literature review, comparative case studies of intensive care units (ICU) and nursing homes, and user research identified six shared pain points. These insights informed key design opportunities and criteria.

The final design proposes an AI-driven companion system, consisting of an online platform and a wearable voice-enabled pin. The pin enables privacy-conscious real-time voice capture and seamless authentication, while the platform supports transcription, classification, OCR-based digitization of handwritten notes, and AI-assisted report generation with traceable data sources. Together, they serve as a bridge between HCPs and EHR systems, reducing information loss and clerical burden.

Evaluation sessions with HCPs, patient families, and design experts confirmed the concept’s value and feasibility, while highlighting opportunities for refinement. This project contributes practice-based insights into designing AI systems that embed naturally into healthcare workflows, enhancing efficiency, reducing administrative strain, and supporting better communication outcomes.

This research project explores how emerging AI-powered collaboration technologies may influence visibility and impression management in remote workspaces. As remote work has shifted visibility practices from in-person interactions to digital spaces, collaboration tools have become central to how remote workers maintain their professional presence. The integration of AI into these tools introduces new socio-ethical challenges that affect trust, privacy, fairness, and overall workplace dynamics. Using speculative design methods, the project envisions possible near-future scenarios of AI-powered workplace visibility and develops diegetic prototypes to provoke reflection on the value tensions that arise in remote, AI-powered professional impression management. The outcomes include a set of speculative prototypes presented through an interactive storyboard, empirical insights on workplace AI-powered visibility, and implications for the design of responsible AI-powered workplace tools.
The link to the speculative prototype (The interactive storyboard):
https://www.figma.com/proto/QuW9xm6sK53FooepH4Qpsi/User-study?page-id=0%3A1&node-id=1-1493&viewport=261%2C177%2C0.02&t=abw0cNBqdcTwl4JJ-1&scaling=min-zoom&content-scaling=fixed&starting-point-node-id=1%3A1493

This thesis investigates how optimisation logics embedded in Urban Digital Twins (UDTs) shape the tension between efficiency and inclusivity within the contemporary and future cities. To do this I question: What happens when optimisation becomes the driving logic behind urban inclusion? Who is at risk of not being represented within an urban algorithm? And how can speculative design help bring to light and open these tensions to surface critical discussion?
Drawing on theories of algorithmic bias, data feminism and design ambiguity, I analyse how UDTs rely on binary classifications (such as high vs low demand, and predictable vs unpredictable), and how these simplify complexity to shape reality while determining who is recognised and who remains unseen in the process. To explore these dynamics, I looked into the binary logics within a specific urban algorithm (the Advier Hub Algorithm). The shortcomings of these binary logics were then extrapolated into a context where a fully Autonomous Urban Digital Twin (AUDT) would have control of the city. This speculation led to the formation of a scenario on which the final speculative artefact, The Behavioural Mirror, was formed.
This artefact was created for within the municipal context to help start the conversation around algorithmic justice within the urban environment, specifically in relation to Urban Digital Twins. The Behavioural Mirror, invites users to encounter a fictional interface that calculates a “visibility score” based on the legibility of their behavioural patterns rather than on identity alone; through the scenario of Sem, a nurse whose irregular hours fall outside optimisation models, participants are prompted to confront how systems silently sort populations according to behavioural norms.
In my research through design process, I combined theoretical framing, design exploration and iterative testing with municipal professionals, mobility experts and designers; in facilitated sessions, participants used the mirror to provoke dialogue, policy reflection and ethical awareness. Within this process questions were raised about data invisibility’s complexity, the trade-offs between opting out and the limits of rigid logics in public systems.
In the facilitated evaluation sessions, I observed the Behavioural Mirror effectively prompted participants to question their own assumptions and discuss the hidden rules of optimisation. Municipal professionals and mobility experts engaged deeply with the video within the artefact, often remarked on their discomfort and curiosity. Discussions ranged from technical concerns about data completeness to ethical debates on agency and refusal. Many participants suggested that the mirror could serve as a primer in team workshops, policy labs and ethical training days by creating a shared reference point for challenging binary logics in Urban Digital Twins. Overall, the testing confirmed that speculative artefacts can be effective in opening space for critical dialogue.
Future work could explore artefacts that foreground the choice of invisibility. What if you would like to choose not to be visible? Aside from this, it could be interesting to iterate and develop this artefact further to test its and other artefacts’ potential in influencing the urban decision making over time.

The post-pandemic period was a critical point for the aviation industry; the shortage of workforce meant difficulties in keeping up with tight aircraft maintenance schedules. To deal with this, KLM Royal Dutch Airlines designed the Back-on-Track program, which emphasized introducing automation as a long-term goal to deal with labour shortages. While there is an attempt to gradually introduce autonomous technologies into the workflow, the opinions and inputs of the employees meant to collaborate with said technologies are not often considered. This gives the impression of a technology push, persuading the employees to collaborate with them. That is where this project comes in; it focuses on technological pull, using the employees’ feedback as input in introducing an autonomous system.

This project is performed at the MRO Lab and aims to aid the aircraft towing operations at KLM’s Hangar 12. KLM uses a remote-controlled towing vehicle called the Mototok to tow an aircraft into and out of the hangar for maintenance. The MRO Lab intends to make this towing process more autonomous, making this project their first attempt to do so.

The project starts with establishing a main research question and sub-research questions, followed by understanding the towing process, specifically its phases, its people, and the interactions occurring between them. To visualize the towing process, a scaled-down, 3D printed version of the setup was created with all towing-relevant infrastructure. An experimental interview arranged with two Mototok drivers helped visualize the towing procedure through the setup, resulting in the development of a process map, containing every step of the towing process, and an interaction map, linking every interaction between operators with the process map.

The first novel aspect of this thesis is a custom framework developed to identify that the safety verification role of the walkers is an ideal starting point to introduce autonomy. This required structuring the flow of information through the Rational Agent Model and breaking the process into functional clusters, followed by the consideration of key inputs from a safety and compliance perspective. Research indicated that the Rational Agent Model matched closely with the Parasuraman, Sheridan, and Wickens framework, which also provides a scale for autonomous system levels. Using its scale as a reference, a Level 2 autonomous system was chosen to replace the safety verification role of the walkers.

Before using the technology in towing, it must be tested. A system-level test was chosen over a product-level test to ensure the autonomy can be evaluated in a context-specific manner. Since the information perceived by the autonomous system would directly impact the decision-making of the drivers, this decision-making was chosen as the test area for the system. However, it was decided to first test the decision-making with the walkers, so that the natural decision-making behaviour could be revealed, along with more specific factors that could be used to test the decision-making of the drivers.

The Critical Decision Method was used to set up the decision-making experiment, which involved an experiment followed by an interview with the driver. The test was based on the driver’s decision-making under certain worst-case scenarios, which they are not trained for, but could occur in towing conditions. A specific situation of the driver receiving multiple inputs was incorporated into the experiment to further understand worst-case decision-making. The scaled-down setup involved simulating the driver and walker’s vision via cameras to maintain a more realistic vision of the towing environment. Results from the scaled-down experiments revealed a decision-making model.

The interview revealed that the driver’s ability to make decisions was heavily reliant on his trust in the walker’s inputs. Thus, the challenge for the perception system test would be to understand if the driver trusts the inputs provided. Guidelines were provided to design this test while addressing any possible limitations.

Finally, the project is concluded and reflected on by answering the main research question and discussing its implications for academia and KLM. The next possible steps to take this project forward are also discussed.

We have an increasingly unsettled relationship with home (Lauzon, 2017) our environment is changing, affecting the places we live, technology allows us to move more and more into our homes, artificially creating the world outside (Urry, 2002), and essentially we are the most lonely we have ever been (DAZED & SPACE10,2022). This exclusivity of the home is contrasted by an emptying of public space, in short, we lack a proper balance between public and private life.

This is one of the sixteen directions, described in this thesis that defines a possible future of home, conditioning us in our understanding and experience of home. Through proposing 3 concepts, inviting people to think about how to balance between public and private and opening up possibilities for different interactions in public space, I attempt to restore the balance between public and private. The three concepts, Noise Collecting Culture, Namebag, and The Mirroring ublic react to current behaviour and create possibilities for different behaviour, being more public and enjoying the possibilities public space has to offer.

The sixteen home conditions are an outcome of the exploration of the future of home through use of the ViP method (Hekkert & van Dijk, 2011). 236 context factors, stable and changing building blocks of the future context, create a framework from which these 16 home conditions emerged. All these sixteen future directions open up a possibility for intervening and designing.

To make a just decision about how to intervene, the ViP method relies heavily on the values of the designer. As a means to find a compass in relying on these values different experiments with the method are created and tested. These experiments try to integrate other perspectives in the design process. The experiments resulted in additions to the ViP method. The first involves the activity of stating one’s preconceptions before engaging in a certain domain, so that designers can be aware of their biases and try to look for other perspectives during their process. The second is the activity of defending the mission statement, the design goal and vision the design has for the future. Through incorporating other entities in this defence: Gaia, The Other and The Things, the effects of the desired proposition are evaluated.

This thesis set out to explore the meaning of autonomy and use this knowledge to create a tool for designers to communicate the complexity of the concept with their clients. In today’s society, we value autonomy and we strive to ensure that everyone can lead their life as autonomous as possible. In fact, we view autonomy as ultimate independence and freedom from outside influence. But by insisting so hard on independence and personal responsibility, it can feel like failing if you do not manage to do everything on your own. From the research done in this project, it was found that autonomy is more than being able to do everything yourself. Autonomy actually means making decisions and doing things in a way that you like or need. This can also mean that you do not want, can or should do it alone and that you need or want to be supported by the world around you. You decide yourself, as an individual, who or what can provide that support. The relationships you are part of are part of the context you are in and which can support you the way you want. The insights gained throughout the project are boiled down into a comprehensible framework explaining the different components of autonomy: the individual, important relationships, boundaries of support, and the context. Exploring the framework with designers revealed that the framework could be implemented throughout the design process in different capacities. As the first step to designing with autonomy is understanding what autonomy is, the choice was made to come up with a design for the first phase of the design process. The framework has served as the foundation for the development of a toolkit for designers. The Autonomie voor/in/met/en Design toolkit supports designers in communicating the importance and complexity of autonomy with their clients at the start of a project, by providing tools to uncover assumptions the client might have regarding the autonomy of their target group. While the toolkit is designed for the first phase of the design process, it is the first step in putting autonomy higher on the priority list of designers and clients.

Domestic kitchens are the heart of modern households, a space that embraces social gatherings and most importantly, where pleasures associated with interacting with food arise while cooking and eating. Nevertheless, the way technology is being introduced in this context moves away from this ritual aspect of kitchens as it focuses on a rather rational side, focused on efficiency and functionality to fix undesired problems.

The goal of this project has been approaching the introduction of autonomous agents in domestic kitchens in a celebratory way, emphasising the positive aspects of Human-Food interaction with a special focus on culinary creativity. Speculative design has served as a means to set the mindset in the near future and design according to a scenario where kitchen appliances will be smarter and capable of gathering more information from the cooking process. The project has been executed with a strong focus on research, both on a theoretical and user-context level, resulting in the design of a concept that conveys a potential solution for the above-mentioned challenge.

Sous, the cooking assistant designed in this thesis responds to the following Design Goal “Gaggenau users should feel like Home Chefs when cooking in their kitchens”. Feeling like a Home Chef involves being the leader of the (domestic) kitchen, feeling in control, exploring creative opportunities, and having a certain level of culinary knowledge. The design revolves around celebratory technologies based on principles of autonomy and embodied interactions, the theoretical background from this project. Sous is a wearable that allows Home Chefs to have a deeper understanding of the preparations being cooked by providing real-time feedback about doneness or sensory aspects among other information. With this, the aim is that Home Chefs would be able to enjoy more the cooking process while ensuring the best result for the dishes they cook.

The collaboration that is created when Home Chefs cook with Sous aims to maximise human capacities while maximising the possibilities of technology in a way that ensures both entities’ autonomy and richness of interactions.