In this thesis, we focus on developing behaviours for socially interactive agents (SIAs). The context in which the agent is used is a self-regulated learning system for children. We focus on personalising learning objectives and interaction content within an intelligent tutoring system (ITS). We envision a system where children can train diabetes selfmanagement knowledge and skills independent of space and time and in collaboration with the health care professional, legal caretakers, and a SIA. To facilitate long-term interaction with such a system, relevant learning content and appropriate ‘intelligent’ social behaviour of the SIA are necessary. The envisioned system was developed within the Horizon 2020 PAL-project and evaluated in an iterative design process. The main contributions of the research described in this thesis are: insights into the behaviour design for a NAO robot and its virtual avatar, and the formalisation of learning objectives facilitating personalised learning content.
Most studies on SIA behaviour focus on the design of emotional expressions or implement roles (e.g., peer or tutor) that were not validated for perception. We argue that strategical pedagogical interaction style (i.e., style purposefully selected based on knowledge about the user, task and context such as done by teachers in traditional classroom settings) is necessary but not yet sufficiently studied to design meaningful interactions that surpass the initial novelty and fun. Further, we argue that learning content must be relevant to the child’s needs and developmental stage. These two challenges are the subjects of study in the two parts of this thesis.

The main research question addressed in part I is: How to design SIA behaviours that express different pedagogical styles and what is the effect on learning outcomes? We answer this question in the four included chapters.
In a systematic review we focus on non-verbal expressions by parameter-based manipulations of bodily shape and motion of humanoid robots and virtual agents, and how these manipulations are perceived by humans. We present a comprehensive review of peer-reviewed published articles and analyse and summarise the available work. Research in this field is multidisciplinary and shows a large variety in concept definitions, behavioural manipulations and evaluation methodologies. We developed the TAXMOD taxonomy as a starting point to develop a shared understanding and interpretation of research
objectives and outcomes, and to formulate a road-map. We applied TAXMOD to position and compare research, and to explicate progress in this area. We found structural support for the fact that some social signals can be displayed by behaviour manipulation in the form of posture- or motion modulation or designed key expressions (fixed behaviours with a specific target expression). Key findings include: 1) the expression of personality traits using virtual or robot bodies is limited to the trait extraversion; 2) the expression of social dimensions such as warmth, competence and dominance is possible, but only when using the whole body, and more research is needed to disentangle individual effects on friendliness, competence and dominance; 3) the expression
of emotion is restricted to generic positive versus negative signals; and 4) context seems important for users for the correct interpretation of the expressive behaviour.
In a first perception study we evaluate an educational robot displaying non-verbal behaviours expressing high or low warmth and competence with children at primary schools and a camp. We show that style expression by a humanoid robot is possible. Bodily posture, hand gestures and paralinguistic cues were manipulated to evoke an expression of a specific level of warmth and competence. The competence dimension in our model was successful. Warmth manipulations were perceived as intended only in combination with high-competence. Moreover, context influenced children’s perceptions:
at school the robot was perceived warmer and more competent than at camp.
In a second perception study we evaluate an educational robot displaying non-verbal behaviours expressing high or low dominance. We modulate bodily posture and movement, specifically by manipulating body expansiveness. We show the validity of body expansiveness modulation for dominance expression in both postures and gestures and showthat with a limited set of parameterswe can moderate dominance expression. Specific postures and gestures have a natural tendency towards being perceived as more or less dominant. Further, the manipulation effect is consistent for a variety of behaviours except a sitting pose. This study provides evidence that body expansiveness is an important factor for dominance expression and that this effect is independent of specific behaviours and view angle.
We study the effect of stylised behaviours on children’s learning approach and learning gain by having a NAO robot guide children while performing an inquiry-based science learning task where children roll rollers down a slope to discover laws ofmovement, friction and gravity. Robot style is implemented as variations in verbal strategy and nonverbal style expression, resulting in an expert or facilitator interaction style. No effect of robot interaction style on children’s learning approach or gain is reported. Based on only verbal behaviour variations children perceive the explaining robot (either the expert
style or explaining verbal strategy with neutral non-verbal behaviour) as more competent than the robot giving evidence descriptions (either the facilitator style or evidence descriptions verbal strategy with neutral non-verbal behaviour). These perception differences did not impact the learning approach or gain in the present study. We did not find perception differences based on the variation of non-verbal behaviour. We did find that the presence of a robot giving feedback on children during rolling trials did cause children to play longer and do more informative experiments compared to no feedback. However, this difference in learning approach did not impact learning gain.

The main research question addressed in part II is: How to personalise learning content based on personal learning objectives?
First, we look into how learning goals are formulated in pedagogy and ontologies for education: effective learning goals must attune to the appropriate and desired difficulty level. A way to structure this is Bloom’s taxonomy. A learning goal must also have attributes presenting relations between and descriptions of goals. Then, we model educational objectives (i.e., achievements, learning goals and accompanying tasks) in an ontology. The upper ontology structures the classes and relations and defines domain independent constructs (i.e., level and topic). The domain model specifies diabetes self-management training objectives for young children based on current checklists and expert input. The resulting knowledge base was considered relevant to, and covering,
the diabetes domain to a considerable extent. From this we conclude that our upper model adequately supports the formalisation of implicit knowledge of health care professionals on diabetes self-management training. A field study with children with type 1 diabetes in the Netherlands and Italy showed that an SIA-ITS offering tasks based on our model to support basic needs for autonomy, competence, and relatedness of children with diabetes. For the formalisation of domain specific learning goals, achievements, tasks and materials in the knowledge structure we recommend the following design
guidelines: work in a multidisciplinary team (to define an inventory of important learning goals and define learning activities include domain- and pedagogic experts next to knowledge engineers); formulate achievements from logical learning units (e.g., daily challenges) that require a subset of the knowledge and skills encapsulated in the goals to improve relevance; formulate achievements and goals from the perspective of the child to facilitate ownership and increase experienced relevance; and, define user characteristics relevant to goal and/or task selection. For the integration of the knowledge structure in a multi-modal intelligent tutoring system we recommend the following design guidelines: provide instruction and explanation to the child on how achievements, goals and tasks are selected and can be attained (i.e., that progress on a goal is gained by task completion, and benefits earned by this); embed the objectives in the ITS application to make them easily accessible to the (child) user and integrate them in other system functionality such as feedback on progress provided by a SIA; and offer sufficient learning content such as games and quizzes to maintain interest and engagement.
We developed an authoring tool with a tree-based interface adapted from game design for collaborative personal goal setting and monitoring that implements the ontology of diabetes self-management education, and we co-evaluated this interface with health care professionals. We propose the following design guidelines for an authoring tool: provide clear, visual feedback on goal structure, and active state and progress; consistently use a different representation (e.g., shape) for different concepts of the model (e.g., goal and achievement); cover the full domain and different skill levels with the finite
set of goals; and, support assessment of current abilities next to goal setting, progress monitoring and goal attainment registration.
We developed an mHealth dashboard as interface for personal goal and task selection and monitoring, and co-evaluated this interface with children with diabetes. The interface implements our ontology of diabetes self-management education. The following design elements were understandable for all children: colouring indicating status, and navigation between layers of information. Children experienced difficulties interpreting the meaning conveyed in iconic presentations, understanding of the layered information, and navigation. Based on reported usability issues, we present guidelines for
the design of a dashboard for children: provide descriptive labels next to visual elements because children lack experience using apps and thus understanding of icons and such; connect elements accordingly by placing them in close proximity and in boxes with appropriate labels; ease navigation between layers when hiding detailed information to avoid cognitive overload; and avoid cluttering elements such as navigation bars.

The work in this thesis shows that robots can express different pedagogical styles perceivable by young children. Dominance expression is mainly dependent on body expansiveness. Warmth and competence expression rely on a complex set of behaviour modulations. However, current style variations are too subtle to impact learning approach and gain. With respect to content personalisation, we show that a structure for and selection of learning objectives provide both a personalised learning path as well as personalised content.
Overall we conclude that to impact learning approach and gain not only SIA behaviour must be modulated, it must be noticed by the learner as well. Learning objectives and content should be formalised within a structure and a user-friendly interface is needed to select objectives and tasks with accompanying content, and monitor progress. The success of an SIA-ITS depends on the amount of available content and social interaction
capabilities of the SIA.@en

Programming robots with verbal commands is limited by the capabilities of the utilized natural language parser. A simple natural language parser which can understand only keywords and small phrases may be easy to use, but limited in what it can interpret and convey. Alternatively, a natural language parser which understands more complex commands can be used to convey more nuance, but can be more difficult to use and create. It is unclear when having complex verbal commands available is preferable to having only simple verbal commands available. Here we show that using natural language parsers which understand more complex commands are preferable when teaching a robot, both in terms of user preference and objective metrics such as completion time and accuracy, but only when the task is complex as well. During a preliminary wizard of oz experiment, we observed what types of phrases users use to correct the robot during a pose imitation learning task, in order to create multiple natural language parsers which allowed for different levels of complexity in given verbal feedback. In a follow up experiment, in which 24 users utilized these parsers in a similar task, the users reported finding the more complex ones to be more useful and satisfying to use. Additionally, the more complex parsers also led to a higher objective similarity between the pose that the user wanted to convey and the final attained pose by the robot. However, this last result was only found for poses which required a comparably high effort on part of the user.

The gaming industry is growing larger every year. Video games are useful for many applications but are also a reason for worry. Games are starting to affect the lives of people negatively. Nowadays, this is defined as Internet Gaming Disorder (IGD). We relate the players' motivations to game addiction through a survey and test our findings by using a game. The survey (n-106) showed that playtime could indicate addiction, six motivation types could be extracted, and two motivational factors correlated with addiction. By analyzing 16 games, we found that the most implemented game mechanics match these two factors. This indicates that games are developed with addictive mechanics. We test the found factors by creating a two versioned game, one with, and one without these mechanics.
Because of limited player data, we could not yet confirm the found motivational factors.

Biologically plausible representations have been found to emerge in particular recurrent neural networks when training on path-integration [1, 2]. This report explores factors influencing the occurrence of entorhinal-like representations in recurrent neural networks. Reproducing simplified models from existing studies and created a hybrid model to explore additional factors, including the input features, structural properties, and regularization techniques in recurrent neural networks. Additional experiments evaluate the difference in training performance when entorhinal-like representations are introduced to a recurrent neural network. This report also assesses existing and experimental visualization techniques in their ability to visualize the performance and representation of recurrent neurons. While some experiments show specialized representations, mostly due to regularization; none of the experiments showed typical entorhinal-like representation. These results show how sensitive the emergence of biologically-plausible representations is to network conditions and training procedure,
casting some doubt on the generality of the conclusions proposed in earlier work.

Speech recognition systems can be found all around us. From personal assistants in mobile phones and smart speakers to robots, we use speech recognition systems everyday. However, communicating with them can be troublesome in noisy environments because they only use audio signals for speech recognition. This problem can be solved by using visual speech recognition or lipreading systems. Research on lipreading systems has been going on since the 1980s but such systems are not being used in real-time systems yet. This can be attributed to the fact they need to process significantly higher amounts of data than audio speech processing which takes a lot of time and hence, they cannot be used in real-time. This thesis aims at finding out if frame rate, jpeg compression or presence of noise have any impact on the performance of lipreading system. The LipNet system is used for this thesis and the Lip Reading in the Wild (LRW) dataset is used for the purpose of experiments. The frame rate of videos of the dataset is varied from 11 to 25, with an increment of 2 for each experiment. Also, compression ratio is varied between no compression and 30 % quality, to find out how compression affects the performance of lipreading systems. Also, salt and pepper noise is artificially added to the dataset for the purpose of experiments. The results from the experiments showed that performance is not affected till frame rate 21, but it starts degrading gradually from frame rate 19 to 13 and after that there is sudden drop in the accuracy of LipNet. With compression of frames to 30 percent of their original quality, there is only a slight decrease in accuracy. However, there is a huge reduction in data size, which makes it easier to transmit data for cloud processing. We found substantial degradation in performance with the presence of noise with a probability of only 3 percent.
This means that if we decrease frame rate to 21 and compress the frames to 30 % quality, memory usage can be decreased to 25 % without much impact on performance of the system. However, quality of video capturing cameras and data transmission to cloud needs to be monitored to avoid noise.

Personality modeling is important in order to create character variation in
games. Character variation favors replayability and is an important aspect
of game design. The eect of articial personalities through the expression of
emotions is evaluated in this research. To do so, a prototype game is developed
in the context of training in bad news conversations. Replayability through
character modeling is important in a game in which people can train to deliver
bad news. By training with multiple personalities one can learn to deal with
the dierent reactions that people can give. In this thesis, the eect of arti-
cial personalities through the expression of emotions on the replayability of the
game, believability of the non-playing character and immersion of the player is
researched. It is expected that articial personalities have a positive eect on
the replayability of the game and believability of the non-playing character, but
not on the immersion of the player. Experiments show that there is a positive
trend in the replayability of the game and the believability of the non-playing
character.

The use of social robots increased in the past few years. Current technology, however, lacks in deploying a single robot for different applications without the help of a human being. Current solutions are time-consuming, labour intensive and hard to generalize. Being aware of its surroundings, in terms of environment and context, the robot can select the appropriate application that the situation needs. We propose a multi-modal, knowledge-based hybrid scene classification method for applying awareness to the robot. As scene we refer to the combination of the environment and the context of the surroundings; a study on how to describe a scene has been done through knowledge-engineering methods that comprehend an anonymous online questionnaire and observations. The method inputs features of the type of objects, audio, and human detection and understanding; and outputs the probabilities of the possible social roles for the robot (Receptionist, Tutor and Waiter). The classification is based on a hybrid approach and trained and validated on a real-time multi-modal data-set collected by a mobile robot. The training experiment aimed to collect the data-set, to select the features that describe different roles and to calculate their weights. The validation experiments aimed to measure the performance and the generalization of the method. Results show that the robot was able to successfully classify the Receptionist role with an accuracy of 83.4%; the Tutor role with 82.7%; and finally, the Waiter role with 55.9%. On average, the method generalizes for 74% of unseen data.

Enabling mobile robots to autonomously navigate complex environments is essential for real-world deployment in commercial, industrial, military, health care, and domestic settings. Prior methods approach this problem by having the robot maintain an internal map of the world and then use a localization and planning method to navigate through the internal map. However, these approaches often include a variety of assumptions, are computationally intensive, and do not learn from failures. Recent work in deep reinforcement learning shows that navigational abilities could emerge as the by-product of an agent learning a policy that maximizes reward. Deep Q-Networks (DQN), a reinforcement learning algorithm, uses experience replay to remember and reuse experiences from the past. A sampling technique determents how to sample the experiences that are to be replayed from the experience replay buffer. Here we studied the effect of different sampling techniques on the learning behavior of an agent using DQN in partially observable navigation tasks. In this work five sampling techniques are proposed and compared to the original random sampling technique. We found that sampling techniques focusing on surprising experiences learn faster than random sampling techniques. Secondly, we found that the final performance of all sampling techniques usually converge to the same policy. Finally, we found the correct use of importance sampling is essential when using prioritized techniques.

An important challenge in developing a social robot is making the interaction between human and robot to be more pleasant and convenient. It could be obtained by making the robot to develop, i.e. change its behavior over the course of time. Here we study two aspects of development: behavioral adaptation and behavioral complexity to which we refer as growth. In this study, the adaptive behavior was implemented as a finite state machine with probability state transitions shaped by human feedback, while the behavioral growth was implemented as an unlocking behavior stages approach which was inspired by the development capability theory. The goal of this study is to examine if there is a significant effect of the adaptation and growth mechanism on human perceptions of aliveness, learning ability, and the behavior shaping control; and moreover how these perceptions influence interaction experience. We used a NAO robot for our studies. There were four conditions experimented from combination of adaptive and growing behavior. Twenty four (24) participants joined to interact with the robot in a within-subject experiment design where each participant interacted in two different conditions. As a result, we did not find a significant effect of the behavior manipulation in the experiment towards the measured perceptions. However, there is a significant positive correlation between the perception of learning ability and interaction experience.

Tata Steel IJmuiden, een bedrijf gespecialiseerd in het produceren van kwalitatief staal, is bezig met het digitaliseren van meerdere componenten van hun productieproces. Aan het eind van dat productie proces controleren menselijke inspecteurs of de geproduceerde rollen staal kwalitatief voldoen aan de eisen van de klant. Om dit werk te standaardiseren hanteren deze inspecteurs een aantal kwaliteitsniveau die specificeren welke productiefouten al dan niet aanwezig mogen zijn voor de toepassing van de klant. De inspecteurs worden opgeleid om te weten welke staalfouten al dan niet acceptabel zijn voor elk kwaliteitsniveau en hoe deze staalfouten eruit zien. Deze kennis wordt elk jaar getest door middel van een zogenaamde Measurement System Analysis (MSA) test. Tata Steel heeft het ontwikkelteam gevraagd om deze test te digitaliseren en te gamificeren. De grootste voorwaarde aan deze digitale versie is dat hij statistisch equivalent blijft aan het uitvoeren van een fysieke MSA. Deze thesis bespreekt hoe het onderzoek is verlopen naar zowel de digitalisatie als de gamificatie van de test. Als onderdeel hiervan wordt uiteen gezet welke opties zijn overwogen om de test zo goed mogelijk te vertalen naar een digitale versie. Bij deze digitalisatie is zowel gekeken naar de inspecteurs die de test maken als de begeleiders die de test opzetten. Daarnaast is er onderzoek gedaan naar het gamificeren van de test en zijn er 2 brede richtingen gevonden die het bedrijf kan volgen qua gamificatie: gamificeren en serious games. Ook is er onderzocht of er een patroon te vinden is karakter van de inspecteurs en of het ontwikkelteam hier gebruik van kan maken in het evalueren van mogelijke spelelementen die als toevoeging kunnen dienen. Dit patroon bleek te bestaan, aangezien het grootste deel van de inspecteurs hetzelfde Keirsey temperament hadden. Dit temperament is vervolgens terug geleid naar het Achiever spelerstype van Bartle. Deze termen en de consequenties hiervan worden uitgelegd in 2.3. Na het onderzoek bespreekt dit rapport welke uiteindelijke implementatie het team heeft gekozen. Hierbij is afleiding van het keuren zelf zoveel mogelijk vermeden. Daarom heeft het ontwikkelteam gekozen voor een oplossing die een spel creëert rondom het keuren, in plaats van het keuren zelf vermakelijker te maken. Hiermee wordt bedoelt dat het beoordelen van een plaat wordt gedaan in een omgeving waar het spel geen externe druk probeert te leggen op de inspecteur. Hiervoor is gekozen met het oog op de statistische equivalentie die de digitale test moest behouden. Het systeem is getest op deze statistische equivalentie door de resultaten van inspecteurs op de digitale test te vergelijken met die van de fysieke test. Hieruit is geconcludeerd dat het digitale systeem een bruikbaar alternatief is voor het uitvoeren van een fysieke MSA. Hierbij dient wel vermeld te worden dat dit onderzoek gelimiteerd is qua omvang. Het uitvoeren van verdere testen wordt dan ook geadviseerd. Ten slotte behandelt dit rapport de lessen die het ontwikkelteam heeft geleerd van dit project en doet het team aanbevelingen voor verdere ontwikkeling van het programma. Door middel van het toevoegen van enkele elementen kan Tata Steel op basis van dit werk een aantal interessante richtingen uit. Het eindproduct van deze thesis wordt dan ook voornamelijk beschouwd als een prototype waarop latere evolutie van het programma kan voortbouwen.

The subject of this thesis is to find a way to manipulate the bodily dominant / submissive expressions of robotic behaviors. The expression of emotion is an important part of the development of Socially Interactive Robots. Previously, studies about the robotic emotions usually focus on single behaviors. Because the generation and testing of new behaviors are time consuming, this kind of emotional manipulation procedure requires a lot of work when applied in practical use. The innovation of this thesis is to explore a solution that can modify the dominance level of a wide range of robotic behaviors without the re-creation of new behaviors.
The results of this work can be used for the design of the robotic movements and the development of robotic applications.