This graduation project explores how a user-in-the-loop approach can improve the usability and reliability of robot-generated maps in domestic environments. While Simultaneous Localization and Mapping (SLAM) allows robots to autonomously create maps of new environments, they are often imperfect due to sensor noise, environmental complexity, and localization errors. Such map errors can negatively impact navigation performance and reduce user trust, particularly when errors are difficult to interpret or correct.

The research phase focused on understanding how humans perceive and interact with robot-generated maps and identifying opportunities for a human-robot collaborative mapping approach. Through literature research and iterative robotics prototyping, insights were gathered and used to create a prototype interface that enables users to interpret, adjust, and refine robot-generated maps. The proposed concept views the user as an active collaborator in the mapping process, combining human spatial reasoning with algorithmic map generation. The design was evaluated through user testing, in which both map understanding and navigation performance were assessed.

The results show that users are able to identify and correct structural inconsistencies in robot-generated maps, leading to more visually consistent representations. Although no statistically significant improvements in navigation performance were found, the robot was able to successfully navigate using refined maps, and the results indicate a positive trend. This suggests that the approach is feasible and does not negatively impact system performance.

This project demonstrates that integrating users into the mapping process can enhance transparency and support more intuitive interactions with robotic systems. While further research is required to validate the effectiveness of the approach, the concept provides a promising direction for collaborative human-robot interaction, contributing to the development of more understandable and user-centered domestic robotics.
... Read more

Labour shortages in the restaurant sector have increased interest in the use of service robots to support daily operations. While autonomous delivery robots can reduce physical workload, they struggle to operate effectively in socially complex environments. Fully tele operated robots,
including systems controlled remotely by human operators, have shown limited efficiency, as operators spend a significant amount of time monitoring robots that do not require direct human input.
This creates a need for shared control systems in which multiple semi autonomous robots operate independently, while a single human operator is supported in identifying situations where human intervention adds the most value. Such systems should provide both an overview of robot
activity and the means to selectively intervene through remote control, allowing human and robotic strengths to be combined more effectively.
This thesis presents a simulated restaurant environment designed as a research platform for studying shared control of semi autonomous service robots. The simulation enables the use of multiple visualisation methods to guide operator attention, primarily based on machine vision
derived metrics, and supports a range of tele operation control strategies. The platform is designed to be modular, allowing additional visualisations, control methods, and evaluation metrics to be integrated for future research.
The secondary goal was to kickstart this research by testing a set of visualisation methods against each other in an automated testing setup. This allows automatic data collection, such as
a total human obstruction score, movement analysis, and a secondary task in the form of math questions to determine the cognitive load of every method. However, due to some unreliability in the data caused by inaccuracies in the human obstruction calculation, none of the options
showed a clear numerical advantage over the others.
Thus, the primary contribution of this work is a configurable simulation environment that enables systematic investigation of shared control strategies for service robots in socially complex spaces. The platform provides researchers with tools to prototype, test, and evaluate human robot
collaboration methods under controlled yet realistic conditions.
... Read more

Despite the rapid growth of research on socially aware robot navigation, mobile robots still struggle to navigate smoothly through crowded environments, often disrupting both human and robot motion. One major gap to their successful integration into real-world shared environments is our limited understanding of how humans perceive and predict mobile robot intent. Prior work demonstrated that intent-expressive trajectory modulation improves legibility for point robots and manipulator arms, but this has not been validated for mobile robots using Dragan and Srinivasa’s defining metrics: correctness and speed of human goal inference. This study provides the first empirical test of whether legibility-optimizing trajectory modulation enhances mobile robot legibility, as measured by these metrics. In a within-subjects laboratory experiment (N = 40), participants observed a physical mobile robot navigating toward one of two goals. We varied a parameter, λ, that controls the trajectory’s lateral deviation from the efficient path. Increasing λ improved prediction accuracy (from 77.1% at λ = 0 to 99.2%at λ = 4; p < .001) and reduced reaction time to correct inference (from 2.08 s to 0.97 s; p < .001). These effects persisted after controlling for MPC trajectory tracking deviation, with effect sizes increasing when this noise source was accounted for. These results provide empirical evidence that legibility-optimizing trajectory modulation enhances mobile robot legibility, extending prior video-based findings to a physical, non-holonomic platform. Future work should address the real-time implementation of such trajectory modulations in motion planners and their evaluation in dynamic multi-agent environments. ... Read more

Healthcare systems increasingly rely on robotic technologies to address workforce shortages, yet asignificant disconnect remains between the technical logic of efficiency and the relational requirementsof care. While standard Value Sensitive Design (VSD) provides a method for value integration, it lacksspecific normative content. Care Centered VSD (CCVSD) resolves this by anchoring design in careethics, yet it remains a theoretical model that lacks the practical tools required for engineering implementation.This thesis posits that this failure stems not from a deficit of moral will (practitioner apathy),but from a deficit of moral skill: the lack of intermediate-level knowledge (operational artifacts thatbridge the divide between high-level theory and concrete implementation) to translate abstract valuesinto concrete technical implementations.Adopting a Research through Design (RtD) approach, this study operationalized the CCVSD frameworkthrough a case study within a commercial robotics company, focusing on the development of a socialnavigation module (interaction-aware motion planning that respects human proximity and social cues)for the PAL Tiago robot. The investigation revealed three structural barriers. First, semi-structured interviewswith 19 stakeholders (comprising robotics engineers and caregivers) identified a semantic gapwhere groups held divergent interpretations of care values; this was bridged by the Prospective ValueHierarchy, which translated care values into technical constraints. Second, the technical implementationof the navigation algorithm revealed a normative void, caused by the original framework structurallyskipping the technical development process. This phase was made explicit and operationalizedby integrating standard engineering workflows, providing the necessary structure to document technicaltrade-offs as ethical decisions rather than implicit defaults. Third, the integration phase of theframework, executed through comparative evaluations with 20 stakeholders (spanning care receivers,caregivers, and management) uncovered contextual instability, demonstrating that identical robotic behaviorselicited divergent value judgments across different care settings.The findings from this case study suggest that the operationalized framework offers practical utility forengineering teams. Feedback from the participating engineers indicated that the translational artifactshelped structure their tacit knowledge into a formalized process. These results indicate that providingengineers with tools to convert ethical mandates into actionable constraints can support a shift frompost-hoc ethical critique to continuous design input within such collaborative environments. ... Read more

With the increasing integration of Automated Vehicles (AVs) into our daily traffic, validating their performance poses a significant challenge. Virtual testing, where simulated AVs operate in a simulated environment, has become a widely adopted approach for efficient and cost-effective validation. However, the lack of realistic human behaviour models hinders the realism of these simulations, particularly in simulating reciprocal driver interactions. In this research, I introduce a discretionary lane change model based on the Communication-Enabled Interaction (CEI) framework, which simulates reciprocal driver interactions through implicit communication and belief modelling. These reciprocal interactions involve mutual behaviours, where individual drivers contribute through high-level decisions and low-level control actions. By employing the CEI framework, decision-making and control actions are integrated into a unified model. The proposed model is validated against naturalistic driving data in discretionary lane change scenarios to assess its validity. Results demonstrate that the model successfully reproduces qualitative and quantitative characteristics of human driving behaviour, reflecting both individual behaviours and the collective contributions of multiple drivers. Moreover, it reflects how varied tactical decisions yield distinct, human-like operational execution characteristics. Thereby improving the realism of interactive traffic simulations and posing a step towards improving virtual testing environments for AVs. ... Read more

As autonomous vehicle (AV) technology progresses, the necessity for a comprehensive understanding of interactions between AVs and human-driven vehicles (HVs) becomes paramount, particularly in critical manoeuvres such as merging. Mastering merging interactions is essential for enhancing road safety. Existing research in this field focuses on how the AV performs the merging manoeuvre but often fails to assess how they influence these interactions. By drawing inspiration from Human-Robot Interaction and Human Aware Navigation, this study aims to bridge this gap by examining how these interactions influence driver workload, measured through fixations duration, perceived safety and drivers’ subjective perception during merging scenarios. We employed a Virtual Reality environment to simulate realistic driving conditions and measure driver responses. We conducted an experiment where participants engaged in merging manoeuvres with each other and, subsequently and without being informed, with the AV described in “Planning for cars that coordinate with people” [1]. This approach allowed for an unbiased assessment of natural driver reactions to AV behaviours. Our findings reveal significant increases in driver workload and decreases in perceived safety during HV-AV interactions, compared to HV-HV interactions. These results suggest that current AV algorithms may not fully account for the complexity of human-AV interactions, highlighting a need for interaction evaluation in the AV development. Participants’ subjective feedback indicates a recognition of and negative reaction to AV driving behaviours, emphasizing the importance of designing AVs that are both efficient and intuitive for human drivers. The study’s implications suggest improving AV controllers’ evaluations by including their interactions with human drivers. By integrating interaction evaluation, AV technologies can achieve smoother and more successful integration into existing road systems, enhancing predictability and driver acceptance. This study marks a step towards understanding the interactions between AVs and HVs, offering insights that could steer future research and development in autonomous driving technologies.
... Read more

Autonomy in traffic (e.g., autonomous vehicles) could potentially benefit mobility, safety, accessibility and sustainability. However, the realisation of these advancements is highly dependent on how effective these autonomous vehicles interact with vulnerable road users such as pedestrians. Before we can understand how pedestrians will interact with autonomous vehicles, it is essential to understand how pedestrians interact among themselves in interactive traffic scenarios. Previous studies have focused on describing these scenarios with probabilistic trajectory prediction methods such as TrajFlow. However, these approaches often fall short in capturing the nuances of mutual interactions. Simple interaction models have been proposed that can describe these interactions, but neglect the influence of another person's intentions. To address this issue, in existing work the Communication-Enabled-Interaction (CEI) framework was proposed that describes interactions by modelling communication and a belief of another person's intentions. The idea of using beliefs in interaction modelling is based on the concept that people have a general but uncertain idea about the plans of other people. These beliefs are one of the fundamental aspects of the CEI framework and must therefore contain valuable information about possible decisions. That is why this study investigates the use of the probabilistic trajectory prediction method TrajFlow for the belief construction of the CEI framework. TrajFlow is trained on the belief-based Forking Paths dataset, integrated into the CEI framework, and tested in four simulated pedestrian interaction scenarios. The analysis shows that the framework is able to simulate plausible interaction behaviour, dealing with conflicting goals and trajectories in multiple simulations. By doing so, this study takes a positive step towards modelling pedestrian interactions and contributes to the broader goal of realising the benefits linked to autonomy in traffic. ... Read more

Fleet Cleaner B.V. is a Dutch company which deploys a wheeled hull-fixed Remotely Operated Vehicle (ROV) to clean biofouling off the Vertical Sides (VSs) and the Flat Bottom (FB) of the hull of seagoing cargo vessels, while berthed at the harbour. To ensure maximal cleaning coverage, accurate localization to keep track of the robot trajectory on the ship hull is essential, but also challenging. Contrary to the VS case, drift-free localization from motion sensors is not applicable on the FB. Instead, the current system relies heavily on operator input, who in turn relies on features (such as the quay wall, a line feature) appearing on imagery from a Forward Looking Sonar (FLS) to determine the robot pose. Human inattentiveness caused by the high workload of cleaning operations makes this method error-prone and sensitive to drift. In the future, Fleet Cleaner aims to develop an autonomous robot to relieve the operators from the task of localization and improve cleaning performance. As no previous work was performed on this matter, this thesis is a contribution to this vision, by developing a sonar-based framework enabling drift-free localization of a ship hull cleaning robot on FBs. Before the conceptual phase, two objectives are formulated to achieve the thesis goal. The first is to provide a sonar-based algorithm measuring the line parameters of the quay wall, as lateral and heading reference. The second objective seeks to fuse the FLS-based measurements with motion sensors to achieve drift-free localization. From there, the operating conditions relevant to the systems are defined, and both functional and performance requirements are formulated, where the latter define metrics that measure the accuracy of the systems w.r.t. manually defined ground truths.
For the first objective, three candidate solutions for tracking the quay wall line parameters are selected. These are first implemented with recorded data in an iterative tuning procedure, then validated where the Total Least-Squares (TLS)-based line tracker with Gaussian filtering arises as a proof of concept. Although the algorithm is fast enough to function for each incoming sonar image, it does not fulfill the requirements for accuracy and robustness, a problem solvable by tuning with better data and the use of filters. For the second objective, also three sensor fusion algorithms are selected. Analysis of their properties with regards to performance revealed the Extended Kalman Filter (EKF) as the most suitable solution, where tuning was performed heuristically. Validation tests again showed partial success, with fast computation times and greatly improved but still insufficient accuracy of the FLS measurements, although localization drift was reduced within the required limits. Mainly, the poor predictions from auxiliary sensors degrade performance, but also the imperfect nature of manually defined ground truths exaggerate the errors. To improve and complete the localization system, it is recommended to implement trajectory optimization for an improved fit of estimated poses with sensory data, and Simultaneous Localization And Mapping (SLAM) based on weld line detection to reduce longitudinal drift. ... Read more