Large Language Models (LLMs) possess significant semantic knowledge about the world, making them valuable for high level control for robots through Vision-Language-Action (VLA) models. These models integrate an LLM to deduce semantic knowledge from a robot’s vision and natural language inputs, facilitating real-world actions. Despite their potential, VLA models are a relatively new research area, with applications mostly limited to simulations or household tasks and insufficient validation in broader contexts. This study aims to develop a LLM-Enhanced Robotic Affordance and Control System (LERACS) for robotic manipulation in applied cases such as the management and maintenance of electrical grid infrastructure. LERACS is designed to visually ground manipulable objects and decompose tasks based on user instructions within a human-robot interaction chat interface, using ChatGPT. A system validation and an AI user experiment were conducted to evaluate its effectiveness in interpreting and performing actions based on pre-made and synthetically generated user instructions. These assessed LERACS’ performance across various settings and instructions. Results indicate high success rates in environmental interpretation and task execution, with robust labeling accuracy, especially in complex settings. Feedback from the AI user experiment highlighted LERACS’ adaptability, identified areas for improvement, and demonstrated its practical utility across diverse settings and task complexities.

This study investigates the influence of synthetic data on the accuracy of 6D pose estimation in RGB images compared to RGB-Depth image-based methods. Additionally, it aims to examine how this performance varies across different types of small chess pieces during a picking task with a robotic arm. The methodology involves 3D scanning the chess pieces and generating a dataset of 61,910 synthetic images with diverse domain randomization. Using this synthetic dataset, six unique 6D pose estimation models were trained for each type of chess piece. The models were validated using a real-world 6D pose estimation dataset, and the obtained results were compared with those from the estimations on a synthetic dataset. It was observed that synthetic data can be used for bridging the visual simulation to reality gap. However there is superior performance on synthetic data compared to real-world data. This implies that results obtained in a synthetic environment cannot be directly projected to real-world scenarios. Also a noticeable decrease in accuracy in both object detection and 6D pose estimation was observed with respect to camera distance for real-world images, primarily linked to the reduced size of chess pieces in the images. Notably, each chess piece exhibited improvement after depth refinement, with accuracy closely linked to the performance of the depth camera. A picking experiment was also conducted, revealing that models relying solely on RGB data achieved a positive grasping rate of approximately 52%, while RGB-Depth-based methods reached around 70%. The findings underscore the potential for successfully picking chess pieces with and without depth refinement, emphasizing the feasibility of bridging the visual simulation to reality gap. Additionally, the study suggests several avenues for future research, including comparing synthetic data with real-world data, further exploring the training process, and introducing domain randomization in the picking experiment, such as background changes or different distractors. Furthermore, it suggests investigating diverse approaches to improve depth accuracy.

Understanding individual differences in manual control cybernetics plays a principal role in personalizing human-machine systems. While much of the work in cybernetics utilizes models for the average controller, individualized models have also been explored, albeit constrained by data availability and the effectiveness of identification techniques. It has previously been theorized that human controller behavior may be defined by a cost function that the controller minimizes for a given control task. This cost function comprises weighted performance and effort terms, and the weightings have been connected to cybernetic models before, but not on an individualized basis. A proposed connection is through the equalization component of the cybernetic model, which has also been outlined as an indicator of individual differences. This claim was reinforced by the analysis of previously collected experiment data in this paper: Across three independent experiments, the equalization parameters, on average, showed 33.84% higher variation than the others and a greater impact on the cost function. Thus, this paper presents a human-controller-cost-function-centered approach to predict and generate individualized sets of cybernetic parameters. Individual cost function weightings were determined using the identified equalization parameters from earlier human-in-the-loop experiments. This process exhibited clear groupings in participants, as clusters of participants with similar equalization were not identified adequately. Individual cost function weightings were then employed to predict full sets of cybernetic parameters. The results indicated that the utilized cost function is incapable of reflecting the physical limitations of the human controller, as these parameters (time delay, neuromuscular natural frequency, and neuromuscular damping coefficient) showed 56.06%, -94.43%, and -170.34% deviation compared to the experimental values. Hence, a hybrid cybernetic data augmentation method was devised, yielding signal values within 15% of experimental data.

Robots can aid in post-stroke motor function recovery and motor learning through the use of haptic feedback during collaborative training. A clear objective in robotic-assisted motor learning is to adapt the haptic feedback to individual users, but personal characteristics are not yet considered in this adaptation.

We investigated the suitability of a haptic guidance feedback strategy, based on participants’ locus of control character trait, compared to training without haptic guidance. For this purpose, a motor learning experiment was conducted on 42 healthy participants, where the internal dynamics of a pendulum had to be learned in order to hit upcoming targets. For two groups, training either with or without haptic guidance, we assessed motor learning and its generalization to similar tasks through target hitting performance, as well as behavior during training and perceived user experience.

Evidence was found of a relatively better performance improvement in both training and long-term (generalization of) motor learning for participants with a more internal compared to external locus of control. Lower observed interaction force during training and increasingly better performance throughout training
in these participants may have caused these motor learning differences. More positive user experience in these individuals through a higher perceived control over the pendulum and lower perceived frustration with haptic guidance may have also contributed.

Combined, this suggests an intrinsically better compatibility
with haptic guidance for people with a more internal rather than
external locus of control, for motor learning, during training and
in user experience

As the global population continues to increase, so does its dependance on food, which has led to the development of more efficient food production methods. Greenhouse horticulture and genetically modified seeds have increased crop yield and decreased water and energy consumption. However, delicate greenhouse-grown vegetables continue to necessitate manual labour. The purpose of this thesis is to design and evaluate a vision system capable of detecting the spatial structure of greenhouse vegetation in order to automate plant repositioning, pruning, and leaf removal. The system employs a robotic arm and a single camera to generate custom plant features, match them, and generate a 3D model of the plant’s structure. The thesis discusses the system’s requirements, design, and evaluation, including the segmentation of plant outlines using deep learning networks, the construction of a 2D plant structure using constrained Delaunay triangulation, and triangulation-based depth calculation. Analysis of three-dimensional precision reveals a correlation between camera positional errors and the algorithm’s depth estimation. The findings support the viability of using a vision system to automate greenhouse duties if certain modifications are made. Contributing to ongoing efforts to increase greenhouse agriculture’s efficiency and reduce manual labour.

Autonomous vehicles are becoming increasingly prevalent in society, but the transition from active driver to passive passenger is known to increase the risk and severity of motion sickness. Motion anticipation is a critical factor in this difference, and visual information is known to be a major contributor to motion anticipation. However, the underlying mechanisms of how visual information influences motion sickness remain largely unknown. This study aims to investigate the effect of visual translation on motion sickness development. To accomplish this, a proposal was made to extend an existing motion sickness prediction model with visual translational components. A human-out-of-the-loop experiment was conducted in a moving-base simulator to test the proposed model's reliability and determine whether visual translation influences motion sickness. The experiment simulated an urban ride that featured repetitive accelerating and breaking maneuvers on a straight road. Eighteen participants were subjected to three different visual conditions that varied in the amount of global optical flow, while the simulator's motion was identical. The results suggest that congruent visual translation may lead to a minor, non-significant reduction of motion sickness, while the amount of optical flow does not seem to affect it. The proposed motion sickness model was able to predict a slight decrease in motion sickness for conditions with visual optical flow, as demonstrated by the experiment. Nonetheless, it is still debatable whether congruent visual translation may influence the onset and severity of motion sickness, as the results of this study could not confirm this.

When a person makes a decision, it is automatically accompanied by a subjective probability judgement of the decision being correct, in other words, a (local) confidence judgement. Confidence judgements have, among other things, an
effect on justifications of future decisions and behaviour. A better understanding of the metacognitive processes responsible for these confidence judgements could improve behaviour models. To date, confidence judgements are mostly studied in a fundamental manner. Little to no research has been done into confidence in more dynamic tasks. Such applied research could render insights on whether fundamental principles also hold for real-life tasks. It could also have practical relevance for several applications. Driving is amongst the areas for which an improved understanding of the decision making and accompanied confidence judgements can be useful, for instance in order to improve driving assistance systems. However, current studies on driving behaviour are merely focused on decision making and do not take confidence into account.
In this study, we made a first attempt of connecting these two fields of research by investigating the confidence of drivers in left-turn gap acceptance decisions in a driver simulator experiment (N=17). The study showed that confidence can be related to the gap size with respect to the oncoming vehicle, described by the time-to-arrival and the distance gap. Confidence increases with the gap size for gap accepting decisions and decreases with the gap size for gap rejecting decisions. In addition, we concluded that confidence can be related to the driving behaviour, and that confidence is negatively related to the decision response time. Moreover, we found that confidence judgements can best be captured with the use of an extended dynamic drift diffusion decision model of which the drift rate of the evidence accumulator as well as the decision boundaries are functions of the time-to-arrival and distance gap. Furthermore, we demonstrated that allowing for post-decision evidence accumulation in the model increases its ability to describe confidence judgements in gap rejecting decisions. Overall, the study confirmed that principles known from fundamental confidence research can be used to describe confidence judgements in a dynamic and applied task.

This study explored several anticipatory interfaces as motion sickness mitigation tool in autonomously driving vehicles. The interfaces were designed to lower the mismatch between the expected motion and the sensory input in a moving body, by providing anticipatory information on upcoming vehicle motion. The two proposed interfaces were a Light only interface and a Combined interface featuring both light and sound. The interfaces present information on the direction and magnitude proportional to the upcoming vehicle accelerations, 0.9s before the actual event. The interfaces were tested in separate trials and compared to a Baseline trial. The comparison was done by a mixed-order, within-participants experiment (n=18), performed in the SIMONA Research Simulator, with identical 30-minute driving conditions. To test the interfaces’ effectiveness in the most motion sickness-triggering setting, subjects got a reading task on a handheld tablet. The results were quantified on an 11-point motion sickness scale and subjective survey questions. Improvements in motion sickness and subjective experience were found with both interfaces. However, only the Combined interface trial showed significant improvements compare to the Baseline. Neither of the interfaces was considered intrusive, while only the Combined interface was considered comfortable. The survey also clearly favored the Combined interface in scores on timing cor- rectness, intuitiveness, and subjective cue correctness. Although the Combined interface had the best results, strong individual preferences were reported for both interfaces, a hypothetical sound interface, or no interface. Further research is advised to focus on the Combined interface while considering optional light and/or sound disengagement in line with personal preference.

Different paradigms can be used to evoke brainwaves. These brainwaves can be interpreted as commands that can be used to control different applications. These frameworks that interpret the brainwaves are called brain-computer interfaces. Steady-state visually evoked potentials is one of these paradigms that uses external stimuli flickering at fixed frequencies to evoke brainwaves. This paradigm is fast to issue, is reliable, and needs no training time of the user. However, to be able to distinguish multiple commands it is important to distinguish between multiple commands reliably. The fundamental metric that determines the signal quality is the signal-to-noise ratio. The signal-to-noise ratio is measured in decibels and is the ratio in power between the signal that is evoked around the stimulus frequency and the power of some baseline, referred to as noise.
To extract the power the discrete Fourier transform is calculated from the measured brainwaves. The brainwaves are measured in millivolts over time. These brainwaves can be recorded using implants in the head named intracortical or external, such as electroencephalography. External methods such as electroencephalography are much safer for the user.

Important to recognize is that one of the contributing factors to signal-to-noise ratio are the characteristics of the external stimuli displayed. Research is still trying to figure out the exact relationship between stimuli characteristics and signal-to-noise ratio. However, the experiments of previous research lack the context of the gaze of the subjects to explain the electroencephalography recordings. In this research, this is attempted to be solved using eye tracking. Furthermore, there is a research gap in the
the scientific field surrounding signal-to-noise ratio and stimuli characteristics as the effect of surrounding
stimuli on the measured signal-to-noise ratio of the target stimulus has never been investigated.

This research attempted to solve these problems by performing 2 experiments with 6 participants. One experiment shows a single stimulus across various shapes (triangles, squares, and circles), colors (red, green, and white), frequencies (9, 13, 19, and 25Hz), and sizes (10.000, 20.000, 30.000 pixels). The other experiment simulates the natural environment of the external stimuli across the same frequencies, colors, and shapes. The natural environment of a single stimulus is actually surrounding stimuli at different frequencies, as applications often require the ability to distinguish between multiple different commands. Thus, to state the main research question: "What is the relationship between the stimuli characteristics and the measured SNR?".
This question is answered by dissecting the effect that color, shape, size, frequency, and surrounding stimuli have on the signal-to-noise ratio.

The identification of time-varying, adaptive behaviour of a human operator in basic manual control tasks is undoubtedly under development since most methodologies only account for time-invariant systems. Previous authors have proved that estimation techniques based on ARX structures can generally identify the HO model parameters. Nonetheless, ARX methods present several problems, such as the persistent bias in estimates that may increase due to coupled noise and system models. Therefore, a novel identification technique based on Box Jenkins models is proposed to achieve a more adequate match between the estimator structure and the HO model. The identification process can be conducted offline by the Ordinary Least Squares and Prediction Error Method, or online, when Recursive Least Squares and Recursive PEM are employed, respectively, in ARX and BJ models. The BJ estimator has excellent potential as an identification tool due to its bias reduction capabilities, as clearly shown in batch-fitting, although non-linear optimization processes decrease its convergence speed by 500%. An RPEM algorithm with forgetting factor @ = 0.99609 and first-order remnant BJ structure is implemented and tested under Monte Carlo simulation and experimental data. Recursive BJ algorithms could help to achieve the ideal identification method by diminishing the Neuro-Muscular parameter bias in ARX.

This study investigated the human-robot interaction of three different augmented reality interfaces that enabled an operator to control a robot arm. The first control methods gives the operator complete manual control by moving a holographic object which the robot arm copies (Direct control). The second control method allows the operator to manually set holographic waypoints which the robot arm autonomously tries to execute (Waypoint control). And the third control method, gives the operator the capability to specify a target location which the robot autonomously moves towards (Command control). An experiment was designed to give 30 participants the capability to control a Franka Emika Research 3 robot arm with a Hololens. During the experiment, the participant had to use each control method to move the end-effector of the robot arm from a starting position to a goal position in 9 different environments. The 9 environments were divided into three manually created complexity levels (Easy, Medium, and Hard), which were based upon the performance of an informed RRT* path planner that was simulated in 67.500 unique environments. The experiment results showed that Command control outperformed the other two methods in the success rate, path length, and operation time. In terms of number of routes Command control had in general a lower number compared to Direct control, showcasing that Direct control has more flexibility in route selection. Furthermore, Direct control required more skill to get a similar performances in path length, operation time, and number of collisions as Command control. The design of Waypoint control made this method too unpredictable for the participants to use proficiently, which was underscored by the very low success rate, the long operation time, and large path length of this method. Comparing the performance of the control methods against the complexity levels did not show many significant differences, except for the success rate that decreased with a more complex environment. In summary, each control method will require unique features to completely unlock the possibilities of an augmented reality interface. The three control methods show different performances, each with their own strengths and weaknesses. And the choice of a control method is therefore dependent on the task at hand.

Electrovibration offers potential to enrich virtual touch experiences with authentic tactile sensations on touchscreens. In controlled environments, responses to tactile stimuli may be anticipated, yet this predictability becomes uncertain in unconstrained settings due to dynamic factors like varied applied force, finger scanning speed, and sensory adaptation. To address this issue, we conducted a psychophysical study with 21 participants to investigate the effect of tactile
rendering parameters on user exploratory behaviour and perception during unconstrained exploration of artificial textures, aiming to discern a predominant tendency of interaction. Our results revealed, signal amplitude shapes human tactile
perception considerably during unconstrained exploration. We also observed, higher signal amplitudes were associated with lower finger scanning speeds, a trend tempered by significant individual differences, thereby affecting its practical effect. In contrast, the measured applied normal force and obtained finger movement pattern remained consistent and were not affected by different tactile rendering parameters. Notably, the rate of change of measured lateral force was found
to be a better metric for the perceived tactile dimensions than the lateral force magnitude. These findings enhance our understanding of perception and physics of such interactions, that could be vital for designing and delivering improved
haptic feedback on electrovibration-based tactile interfaces.

In order to design safe and effective interactions between autonomous vehicles (AVs) and human road users, it is essential to understand the mechanisms underlying human-human merging behavior. Driving simulator experiments can be used to study these mechanisms, but previous research has primarily focused on the behavior of individual drivers rather than the dynamics of interactions. In addition, current experimental scenarios and data analysis tools do not adequately capture interactive humanhuman merging behavior. To address these issues, I propose an experimental framework featuring a simplified highway-merging scenario that can facilitate human factors research on merging interactions. In a case study with fourteen participants, I used the framework in a coupled virtual reality driving simulator to show a relation between participants’ interactive behavior and fixation behavior. This work shows how to better understand human-human merging interactions, which is essential for developing AVs that can safely and successfully interact with other road users.

Percutaneous needle procedures (PNPs) are minimally invasive procedures that use imaging guidance to diagnose or treat medical conditions. In the treatment of liver cancer, PNPs are becoming increasingly used due to their shorter recovery times and lower complication rates. However, needle placement during PNPs can be challenging due to a lack of direct visualization of the target and liver tissue deformation caused by respiratory motion, patient (re)positioning, and needle insertion. Currently, no imaging modality provides continuous, qualitative visualization while maintaining acceptable radiation levels. Continuous feedback during PNPs could improve needle placement accuracy by enabling real-time adjustments in response to tissue deformation. Previous studies have used external- and internal markers for continuous feedback, but these markers have not been able to fully capture tumor displacement and the underlying causes of deformation. Endovascular insertion is a potential solution to this problem - it involves placing the marker close to the tumor by inserting it through the blood vessels. Here, we present exploratory research that aims to investigate the possibility of using an endovascular marker to capture the displacement of a liver tumor during a PNP.

An ex-vivo porcine liver with artificially created tumors and endovascular catheter markers was used. In the first experiment, robotic-assisted needle insertion was performed on seven tumors with a 13-gauge ablation needle. The second experiment involved simulating respiratory motion with an inflatable sachet to mimic the lungs and create a representable blow zone (the area affected by the inflated sachet). The displacement of the tumor- and endovascular catheter markers were tracked in the x-, y-, and z-directions using a C-arm system making Cone Beam Computed Tomography (CBCT). The x- and y-directions represents the horizontal plane within the liver, and the z-direction is the vertical plane (the direction of the ablation needle). The average offset in millimeters was calculated to quantify the error between the tumor- and catheter marker displacement.

The results of needle insertion showed that catheter markers placed 8-28 mm from the tumor could deduce tumor displacement in the x-direction, with a maximum offset of 1.23 mm. The catheter markers placed 8-13 mm from the tumor were also able to deduce displacement in the z-direction with a maximum offset of 0.23 mm and in Euclidean distance (total path length as measured using Pythagoras' theorem) with a maximum offset of 0.73 mm. Furthermore, the results indicated that, on average, catheter markers placed 8-28 mm from the tumor were able to accurately deduce tumor displacement for needle insertion depths of 0-15 mm. During respiratory motion simulation, tumor- and catheter marker displacement was influenced more by blow zone location than the distance between them. To apply these findings to the human body, it is recommended that the endovascular marker will be positioned in the same sagittal (longitudinal) and coronal (frontal) plane as the tumor. In this study, catheter markers could be used to deduce tumor displacement for inflation volumes of 0-500 ml, which is the typical resting breathing volume.

In conclusion, this study demonstrated that the ability to use endovascular catheter markers to deduce tumor displacement during a percutaneous needle procedure is influenced by the distance between the tumor- and the catheter marker, the depth of the needle, the inflation volume of simulated lungs, and whether the marker is positioned in the same sagittal and coronal plane in relation to the tumor. Future research should focus on determining the optimal number and location of endovascular markers, including a bigger variation and spread of tumor locations, and adjusting insertion techniques, to further realize the clinical applicability of endovascular catheter markers in percutaneous needle procedures.

Future human-machine control tasks with preview (e.g., car driving) are expected to include automation for safety, but keep operators in charge for liability. Such shared control applications require time-varying human identification because the control feedback should be compatible with the operator's variable behavior. A promising time-domain identification algorithm is the Dual Extended Kalman Filter (DEKF), estimating human operator parameters from Van der El's preview model. In this article, the DEKF's time-varying identification performance is studied with realistic simulations, followed by human operator experiments in a fixed-base simulator. The investigation focuses on look-ahead time, indicating how much future information the operator uses for control. Compared to other parameters, look-ahead time is adapted most considerably with preview. The results suggest that this parameter should be initialized in a 0.25 s proximity of its actual value to make the DEKF converge within 30 s. Although only estimating look-ahead time while fixing the other parameters, the DEKF is capable of identifying time variations in preview. Based on the sigmoid results, the estimation bias increases linearly to 0.35 s at the largest 0.75 s steps in look-ahead time. For sine variations, the DEKF estimations are in phase with the look-ahead time until 0.03 rad/s. Between 0.03 rad/s and 0.4 rad/s the DEKF behaves as a lag function, and for higher frequencies the estimation response is decayed. For the first time, it is quantified how well the DEKF can identify variations in look-ahead time during preview tracking tasks. With further research, the DEKF might become capable of real-time identification, bringing the cybernetics community one step closer to intuitive shared control applications.

A vehicle that is travelling at high sideslip angles can still be controlled by drifting. Implemented into a vehicle, this phenomenon could lead to increased vehicle safety and performance. Additionally, it could lead to higher acceptance rates of autonomous driving.
In this work a three state vehicle model is used. Using this model, simulations are performed with varying vehicle parameters and tyre models. First, the mathematical descriptions of all used models are stated, after which phase plane representations for the identification of drift equilibria are elaborated on. Next, different steering characteristics and their influence on the drift equilibrium points are considered. These characteristics are achieved by varying the lateral rear tyre stiffness. The effect of
three different types of tyre models on the drift equilibria is discussed. The models that are considered are the linear tyre model, Dugoff tyre model and Magic Formula model.
In addition to this, the effects of the location of the centre of gravity, the vehicle mass and the cornering stiffness are investigated. Finally the outcome of the Dugoff tyre model and the Magic Formula model for construction of drift equilibria is shown and discussed.
Contrary to the Dugoff and Magic Formula model, no drift equilibria were found using the linear tyre model. Using the Dugoff model, drift equilibrium points were found for the understeering and neutral steering vehicle, whereas the oversteering vehicle showed drift equilibrium ranges. Finally, drift equilibria depend on vehicle parameters, showing change in behaviour when the latter are varied.

Food-evoked emotions are essential for consumers’ food choice prediction and market success. These food-evoked emotions are predominantly measured by explicit self-reports. Yet in certain situations such as social desirability, explicit measures might not reflect one’s true emotional experience. The additional use of implicit measures can be beneficial.
The present study investigated whether social pressure truly changes food experience by means of explicit and implicit measures of food liking. Explicit ratings were EmojiGrid valence and arousal ratings in response to familiar and unfamiliar food images and soups. Implicit measures consisted of frontal alpha asymmetry during pre-selected scenes of a movie about Japanese soy sauce as well as sip size of the soup. Explicit and implicit measures were compared to assess the effect of social pressure on Japanese and Dutch food liking.
No differences between the social pressure (n = 19) and control group (n = 23) emerged in any of the measures. Explicit ratings and the implicit measure sip size, but not frontal alpha asymmetry during watching the movie, showed differences between participants with high and low food neophobia. The insensitivity of frontal alpha asymmetry to food neophobia groups could be explained by the movie scenes showing rather familiar foods. BMI grouping similarly showed no effect on frontal alpha asymmetry during watching the movie, but also explicit measures were unaffected.
It was concluded that the social pressure intervention itself was not effective in inducing increased liking of Japanese food, since there was no increase in neither reported liking nor ‘true’ liking. Additional ways to induce social pressure, e.g., observation during rating, are advisable if the study was repeated. Furthermore, the use of stronger stimuli to induce approach or avoidance motivation as measured by frontal alpha asymmetry, is recommended. It cannot be concluded whether social pressure truly affects food experience.

Understanding human perception of haptic feedback is critical when designing and regulating these control systems. In recent years, experiments have been conducted to determine the Just-Noticeable Difference (JND) in mass-spring-damper dynamics using a hydraulic admittance display in the form of a side-stick. These experiments have resulted in a model of JNDs when interacting with linear second-order dynamics. In real-world applications, however, control force dynamics also commonly include nonlinearities like friction. This research extends the current understanding of JNDs in linear systems by including the nonlinear case, where friction is also present. Experiments were conducted to determine JNDs in friction when combined with second-order system dynamics. Initial results suggest that friction JND can be independent of linear system dynamics as long as its value compared to the linear system’s impedance is sufficiently large. This means, friction JND follows Weber’s law, also when it is combined with mass-spring-damper dynamics, unless the level of friction approaches the detection threshold, which in turn can be influenced by the linear system dynamics. Based on the findings presented, it is possible to conduct more focused experiments to confirm and add to these initial results.

Abstract— Visual occlusion can cause object detection and classification systems to fail due to swift movement or a soiled, moist or dusty environment. Hence, this asks for a ’blind’ collision detection and classification method. This paper presents a novel blind collision detection and classification scheme for a
heavyweight, low-speed, wheeled mobile robot. By recognizing the target signal pattern in phase current data, the robot can detect whether the wheels are blocked caused by overload (G1). After this, using acceleration and phase current data, the robot will be able to differentiate between a collision against a wall
or a collision with an object between the wall, or no collision of interest (G2). Additionally, an algorithm based on the pitch angle can detect if the robot slides on top of a soft object (G3). Three different algorithms are developed that address these goals. Finally, the developed algorithms are validated in
dynamic and soiled environment (G4). The first two goals are reached by training machine learning classifiers that identify the signal pattern of its target event and place uneventful data in a separate class (open-world classification). During training the classifiers Random Forest, Multi-layered Perceptron, Decision
Tree and Logistic Regression are compared, and the two best perfoming classifiers are subsequently tested for a time-series open-world classification task. The third goal is reached with the development of a heuristic algorithm based on the running mean of the pitch angle.
Experiments were performed in a controlled environment, creating collisions with varying floor conditions, robot weight and collision objects. The best performing algorithm for blind collision overload detection has achieved 98.6% detection accuracy. The object classification algorithm can differentiate
between two types of soft objects, a wall or no event with an accuracy of 93.3%. The algorithm based on the deviating pitch angle can detect events with 100% detection rate and 0% false positive rate. Detailed implementation schemes are provided for real-time implementation, illustrating a robust framework in soiled environments. The proposed solutions can be used to improve collision detection on blind mobile robots, as well as mapping the environment using the object classification model.

According to the WHO, falls are responsible for over 38 million disability-adjusted life years lost each year, globally. Additionally, an estimated 684.000 individuals die of falling each year, making it the second leading cause of unintentional death. One of the most effective physical activity interventions to reduce the risk of falling, is targeted exercise that safely challenges balance. One tool, that is currently
being developed, which can aid physical therapists with these interventions is the GyBAR. A wearable device that uses gyroscopes to apply moments to the patient. This can be used to either provide balance assistance or challenge balance by applying perturbations. The goal of this research was to develop an interface for the GyBAR. The interface should contribute to the acceptance of the GyBAR. This can be achieved by an excellent perceived ease of use, which combined with perceived usefulness
are indicators for the Technology Acceptance Model (TAM). The interface inspired by a Voodoo-doll was developed by going through the following design process steps; the creation of a list of requirements; a brainstorm to generate ideas; the development of three concepts; and the selection and development of one concept into a prototype. The Voodoo Doll controls the GyBAR by a handheld model of the patient, which can be manipulated and translates the movements of the model to the actual patient. User tests were performed to validate the design. With a SUS-score of 82.81 (SD=7.48), which is within the 90-95 percentile, it can be concluded that the interface has an excellent perceived ease of use. Further development is encouraged are several recommendations for points of improvement are given.