This paper proposes a novel framework that combines both planning and learning-based trajectory generation methods to handle complex robotic assembly tasks. The framework utilizes MoveIt! for planning large-scale reaching motions and Dynamic Movement Primitives (DMPs) for precise grasping and placing movements, with both methods integrated into a single system controlled by a behavior tree. An impedance controller is employed to ensure smooth and safe execution of the generated trajectories, particularly in scenarios that involve human interaction.

The proposed framework was evaluated within the context of the European Space Agency-funded Rhizome project, which focuses on off-earth habitat construction. The project involves assembling habitats using custom-designed Voronoi-shaped building blocks, which were also utilized in experiments to test the framework. The results showed that combining planning for large-reaching motions with DMPs for detailed movements effectively addressed the limitations of each individual method, delivering a flexible and robust solution to the challenges of robotic assembly.

Hospitals fulfill an important function within the healthcare systems, providing complex and specialized care. Healthcare continues to evolve into more effective forms of care and thus benefiting those in need. While care changes the physical hospital rarely does, resulting in hospital architecture which leaks the quality to contribute to and improve the users wellbeing. This design thesis explores a large scale architectural intervention strategy that improves the hospital architecture of the AMC Amsterdam through means parametric and computational design. The intervention focuses on spatial redistribution of function based on trends and innovations in healthcare. Resulting in vacant space available for spatial interventions. In order to increase wellbeing the intervention focusses on the themes of nature, exercises, sight and daylight. Creating an biophilic experiential structure that connects vertically and horizontally on the various floors. Enabling patients to move, stay and experience the intervention each on their own manner, while simultaneously creating an healing environment that improves patients wellbeing.

In a quest to breathe new life into public spaces and engage with its today’s increasingly (inter-)connected users, robotic architectural components seem to open up possibilities to give agency to building component. A new field of research has been involving multi-agent robotic systems in the architectural design and/or fabrication process. They require a new understand the built environment as an “adaptive ecology” composed of autonomous agents that interact with each other and their nearby environment (users and context). I am proposing the examination of a multi-agent system composed of unmanned aerial vehicles (UAVs, or drones) that can collaborate together to self-assemble into structures that are user-interactive and responsive to the local climate conditions. These structures are composed of a many of these ‘drone-bricks’ that form shelters that can grow and morph to accommodate users’ changing positions and movements through time. They are able to modulate environmental conditions such as wind and rain shelters, daylight penetration and the acoustic resonance of the space. This architecture is directly informed by the users’ activities, environmental conditions, and other information flows. It relies on principles of emergence, indeterminacy and generative design. This architecture has no blueprint but is self-organising; it is processual, indeterminate and continuously in formation, as opposed to the dominance of static, predetermined forms and functions in the organisation of the environment today. How to translate these architectural intents (performative and qualitative metrics) to a swarm of UAVs in an attempt to create a robotic architectural ‘species’ where autonomous agents collaborate to form temporary shelters that respond to local environmental conditions and human interactions? The research, simulation and prototyping rely on a behavioural and praxiological approach to architectural design that establishes a feedback loop between the algorithmically-encoded robotic capacities (behaviours), the material properties (morphogenetic processes) and sensing capabilities (neurological processes) of the agents and the emergent interactions and their self-organization in the environment in real-time. This project attempts to look at the ways these behaviours are digitally coded and physically expressed, as well as evaluate the overall agency granted to the system through the implementation of these behaviours with the overarching aim of developing new relationships between space and users through multi-agent robotic systems.