Human-robot interaction (HRI) programmers often struggle with operating older robot hardware due to the short support period provided by manufacturers and difficulties integrating modern software solutions. This paper introduces the ZTL Task Library (ZTL), a lightweight communication framework and protocol designed to decouple robot hardware from the operating platform via socket communication, thereby increasing robot lifetime. We present a task-based communication protocol facilitating the co-design of robot behaviours with non-programming experts. Our approach has been shown across different platforms to effectively mitigate incompatibilities between middlewares, simplifying control and usability, allowing for simultaneous addressing of multiple devices.

Adapting to novel tasks in human-robot interaction (HRI) is crucial for long-term autonomy, yet remains a major challenge for autonomous agents deployed in unpredictable open-world settings. This paper introduces CAPA-AI, a novel framework that integrates probabilistic novelty detection with continual post-deployment adaptation achieved via transfer learning to address this challenge. The framework’s novelty detection component employs conditional probability and the Jaccard Index to identify unfamiliar tasks by quantifying their deviation from the agent’s knowledge base of previously learned tasks. Upon detecting a novel task, the agent utilises transfer learning to repurpose prior knowledge and update its models without retraining from scratch. We detail the design of CAPA-AI, including an isolated learning phase for initial skill acquisition and the construction of a dynamic knowledge base. The complete system was deployed on a social robot in real-world HRI scenarios to evaluate its performance. Experimental results demonstrated that the agent accurately detects novel tasks and adapts to them, achieving adaptation and novelty detection accuracies of 80% and 89%, respectively. These findings underscore the efficacy of the proposed approach and highlight a significant step towards robust open-world deployment of AI agents in HRI, where continuous adaptation and the safe handling of unforeseen tasks are essential.

This paper presents an investigation into the effectiveness of introducing explicit causal explanations in a child-robot interaction setting to help children with autism improve their Visual Perspective Taking (VPT) skills. A sample of ten children participated in three sessions with a social robot on different days, during which they played several games consisting of VPT tasks. In some of the sessions, the robot provided constructive feedback to the children by giving causal explanations related to VPT; other sessions were control sessions without explanations. An analysis of the children’s learning progress revealed that they improved their VPT abilities faster when the robot provided causal explanations. However, both groups ultimately reach a similar ratio of correct answers in later sessions. These findings suggest that providing causal explanations using a social robot can be effective to teach VPT to children with autism. This study paves the way for further exploring a robot’s ability to provide causal explanations in other educational scenarios.

The research presented in this paper investigates the feasibility of using humanoid robots like Kaspar as assistive tools in Speech, Language and Communication (SLC) therapy for children with learning disabilities. The study aims to answer two research questions: RQ1. Can a social robot be used to improve SLC skills of children with learning disabilities? RQ2. What is the measurable impact of interacting with a humanoid robot on children with learning disability and SLC needs? A co-creation approach was followed, three therapeutic educational games were developed and implemented on the Kaspar robot in collaboration with experienced SLC experts. Twenty children from two different special educational needs schools participated in the games in 9 sessions over a period of 3 weeks. Results showed significant improvement in participants’ SLC skills – i.e. language comprehension and production skills– over the intervention. Findings of this research affirms feasibility, suggesting that this type of robotic interaction is the right path to follow to help the children improve their SLC skills.

Robot-assisted rehabilitation often makes use of virtual environments to present the therapy tasks. Virtual reality has the ability of providing valuable visual feedback and enjoyable interaction to the patients; therefore, the way they are displayed to users becomes crucial. Is the monitor size an important feature that influences how the task is perceived and thus affects patients’ performance?This study on healthy participants investigates the influence of displays in perceiving haptic effects. The participants performed an experiment using an end-effector robot, where they followed a moving target around a trajectory while disturbed by a simulated perturbation and assisted by an adaptive algorithm. The experiment was presented on two different monitors to assess whether a different size affects their performance. Statistically significant results show that the performance achieved with the large monitor features lower error compared to the small monitor, implying that large monitors might be a better solution for rehabilitation with virtual tasks and assistive robots.

Children with Autism Spectrum Disorder (ASD) often struggle with visual perspective taking (VPT) skills and the understanding that others might have viewpoints and perspectives that are different from their own; i.e., the ability to understand that two or more people looking at the same object from different positions might not see the same thing. The understanding of VPT can be improved by introducing explicit causal explanations in the interactions involving autistic children. Moreover, the use of social robots can help autistic children improve their social skills. We present a retrospective study with Kaspar, a humanoid social robot specifically designed to interact with children with ASD, which aims to define the initial protocol for a study on the effect of causal explanation in VPT provided by Kaspar. To this end, we investigate in which scenarios causal explanations, provided either by researchers or by Kaspar, contribute substantially to the child’s understanding of VPT. The results have helped us identify multiple interaction categories that benefit from causal explanation. We have used these results in order to define new interaction games that benefit from causal explanations. These are now progressing through usability assessment experiments.

Humans need to understand and trust the robots they are working with. We hypothesize that how a robot moves can impact people's perception and their trust. We present a methodology for a study to explore people's perception of a robot using the animation principle of slow in, slow out-to change the robot's velocity profile versus a robot moving using a linear velocity profile. Study participants will interact with the robot within a home context to complete a task while the robot moves around the house. The participants' perceptions of the robot will be recorded using the Godspeed Questionnaire. A pilot study shows that pilot participants notice the difference between the linear and the slow in, slow out velocity profiles, so the full experiment planned with participants will allow us to compare their perceptions based on the two observable behaviors.

We investigated how a robot moving with different velocity profiles affects a person's perception of it when working together on a task. The two profiles are the common linear profile and a profile based on the animation principles of slow in, slow out. The investigation was accomplished by running an experiment in a home context where people and the robot cooperated on a clean-up task. We used the Godspeed series of questionnaires to gather people's perception of the robot. Average scores for each series appear not to be different enough to reject the null hypotheses, but looking at the component items provides paths to future areas of research. We also discuss the scenario for the experiment and how it may be used for future research into using animation techniques for moving robots and improving the legibility of a robot's locomotion.

This research paper explores the possibility of using Electromyogram (EMG) signals for classifying point to point upper limb movements during dynamic muscle contraction in the context of human-robot interactions. Previous studies have mostly focused on classifiers for gesture recognition using steady state EMG. Only few studies have used non-steady-state EMG classifier when gross upper arm muscles are in motion. To investigate it further, our study was designed to take EMG measurements from 4 upper limb muscles of 10 participants while interacting with HapticMaster robot in assisting mode. The participants were asked to move the robotic arm in a rectangular path consisting of 4 segments named S1 to S4. The EMG signals were analyzed by splitting them into non-overlapping windows of 100 milliseconds width. The initial windows within the initial 1 seconds of each segment iteration were considered to train and test a Support Vector Machine classifier. Various EMG features were calculated for different number of windows and used for classifying different segments. For the different combinations of features and muscles, it was noticed that the near-the-body segments S1 and S4 displayed the highest median accuracy for the feature combination (Waveform Length + Mean Average Value + Zero Crossing Count + Signal Slope Change) which were 100% each. For the same feature combination, it was also noticed that the segments S2 and S3 had the least accuracy, 76.2% and 73.8% respectively, possibly due to the away-from-body movements. In general, the accuracy was found to be more stable and higher for S1 and S4 segments. Considering 700 milliseconds (so 7 windows) for classification provided the best accuracy and the best muscle combination was Trapezius + Deltoid + Biceps Brachii + Triceps Brachii.

How do mistakes made by a robot affect its trustworthiness and acceptance in human-robot collaboration? We investigate how the perception of erroneous robot behavior may influence human interaction choices and the willingness to cooperate with the robot by following a number of its unusual requests. For this purpose, we conducted an experiment in which participants interacted with a home companion robot in one of two experimental conditions: (1) the correct mode or (2) the faulty mode. Our findings reveal that, while significantly affecting subjective perceptions of the robot and assessments of its reliability and trustworthiness, the robot's performance does not seem to substantially influence participants' decisions to (not) comply with its requests. However, our results further suggest that the nature of the task requested by the robot, e.g. whether its effects are revocable as opposed to irrevocable, has a significant impact on participants' willingness to follow its instructions.

Rehabilitation robots are useful tools to objectively quantify and treat post-stroke impairments. The SCRIPT Passive Orthosis (SPO) is an passively actuated hand orthosis that can be used for interactive therapy at home. In the last year the SPO was used independently by 24 patients in three EU countries. In this paper we report on the technical challenges this has presented and the feedback we were given by therapists and patients. This includes the range-of-motion of the device, the assistive characteristics, the potential for grasp detection, and the user acceptance.

Severely impaired children with Physical and Neurological Impairments (PNI) often have erratic test responses because of impairments. Very often even the binary (YES/NO) intention of a PNI child cannot be determined because responses are made at the wrong time and conflicting signals are sent. We propose that it is possible to determine intention using significant streaks of successful responses found in the noisy responses. We can use two measures among others to determine intention; the maximum streak size attained in a test run with a device, and the sum of the significant streaks in the test run. The maximum streak size measures consecutive successes and the sum of streaks gives an indication measure of re-attempts. This work is part of a larger study to increase accessibility of PNI children to a cognitive test through the use of new non-hand held devices that interact with a computer. Using the proposed two measures, we are able to compare more closely the performance of the less capable and the more capable PNI children. The results show that the children who are more capable re-attempt in that test when they fail to achieve a target. Conversely the less able children divide into two groups: those that do re-attempt the target and those that do not re-attempt the target dependent however on the device being used. These results provide two measures that are potentially useful for determining the intention of the child undertaking the cognitive test.

Motivation plays in important role in rehabilitation after stroke. Multi-modal games can provide an engaging and interactive platform to motivate people to actively participate in the therapy. Designing games for rehabilitation requires input from both multiple stakeholders such as the medical, bioengineering and game design fields. In order to bridge this gap, we implemented and tested games specifically designed for upper limb rehabilitation and observed their effects on players. This paper presents the design process for three rehabilitation games and their effects on motivation of a single stroke patient. These results indicate that engagement and enjoyment vary for the three different games while managing to achieve repetitive number of hand and wrist gestures in the background. In our summative evaluation planned to be conducted in patients' homes, 9 different games, including the three presented here, are provided to allow for providing a better range and a wider choice. Use-logs as well as the questionnaire trialed in this study will be used to assess preference and motivation, and to explore if current feedback will be repeated by a larger number of stroke patients and a wider range of impairments and preferences. These will further inform the process of game design for rehabilitation and personal well-being.

With changes in life expectancy across the world, technologies enhancing well-being of individuals, specifically for older people, are subject to a new stream of research and development. In this paper we present the ACCOMPANY project, a pan-European project which focuses on home companion technologies. The projects aims to progress beyond the state of the art in multiple areas such as empathic and social human-robot interaction, robot learning and memory visualisation, monitoring persons and chores at home, and technological integration of these multiple approaches on an existing robotic platform, Care-O-Bot®3 and in the context of a smart-home environment utilising a multitude of sensor arrays. The resulting prototype from integrating these developments undergoes multiple formative cycles and a summative evaluation cycle towards identifying acceptable behaviours and roles for the robot for example role as a butler or a trainer. Furthermore, the evaluation activities will use an evaluation grid in order to assess achievement of the identified user requirements, formulated in form of distinct scenarios. Finally, the project considers ethical concerns and by highlighting principles such as autonomy, independence, enablement, safety and privacy, it embarks on providing a discussion medium where user views on these principles and the existing tension between some of these principles for example tension between privacy and autonomy over safety, can be captured and considered in design cycles and throughout project developments.

In this work we present three interaction algorithms developed under the EU project SCRIPT in order to evaluate stroke patients' capabilities, evaluate their performance during robot-assisted exercise and consequently adapt the difficulty of the exercise to each individual. The first procedure assesses movement amplitude and duration with the subject making only a few repetitions of the motion. The second algorithm, aimed at evaluation of subject performance, is based on whether that the subject is lagging or leading with respect to a target reference trajectory. Finally, the third procedure aims at modifying the task difficulty (time allowed to reach the target, in this case) based on a performance indicator. The proposed mechanisms are completely independent from each other and could thus be exploited as single units. Furthermore, all of them are generalizable to any movement. These components have been adopted in the SCRIPT system, which is currently being tested in patients' home.

For able-bodied people within the art and design discipline, access to Computer Aided Design (CAD) and visual graphic interface is a well-defined iterative process. However for non-sighted people or people with impaired vision, this is a difficult process to facilitate. Often this issue excludes and/or limits access for people with vision impairments to fully utilise CAD systems, web interface, and any other visually led interface which mainly communicates through graphical or pictorial cues and image-based metaphors. This paper presents an ongoing inclusively designed multimodal system. Whereby the use of digitally adapted haptic technology is explored via a clinically established and valid fine motor skills test: 'Wade's Nine-Hole-Peg-Test' (NHPT). Particular attention is paid to assess whether non-sighted participants can gain a level of speed and efficacy of NHPT task by using the haptic technology together with their own tacit haptic perceptions compared to a subject group of healthy sighted participants. The results indicate better performance of non-sighted participants when compared to the sighted, while also showing that implemented multimodal cues assist the performance of both participant groups based on insertion time. Given these results, future work will focus on analysing collision data from haptic insertion of the pegs in holes to compare performance based on recorded error. Additionally, these findings will be used towards providing tools for more inclusive interfaces to be used in pedagogic practices.

The main target of this work is to improve human-robot interaction capabilities, by adding a new modality of sense, touch, to KASPAR, a humanoid robot. Large scale distributed skin-like sensors are designed and integrated on the robot, covering KASPAR at various locations. One of the challenges is to classify different types of touch. Unlike digital images represented by grids of pixels, the geometrical structure of the sensor array limits the capability of straightforward application of well-established approaches for image patterns. This paper introduces a novel histogram-based classification algorithm, transforming tactile data into histograms of local features termed as codebook. Tactile pattern can be invariant at periodical locations, allowing tactile pattern classification using a smaller number of training data, instead of using training data from everywhere on the large scale skin sensors. To generate the codebook, this method uses a two-layer approach, namely local neighbourhood structures and encodings of pressure distribution of the local neighbourhood. Classification is performed based on the constructed features using Support Vector Machine (SVM) with the intersection kernel. Real experimental data are used for experiment to classify different patterns and have shown promising accuracy. To evaluate the performance, it is also compared with the SVM using the Radial Basis Function (RBF) kernel and results are discussed from both aspects of accuracy and the location invariance property.

Summary form only given. Scaled technologies continue to exhibit variability, driven by both random process effects and systematic structural effects. Process and design rule actions can be taken to reduce, or even eliminate, sources of systematic variability. Random variability is more difficult to combat, but architectural decisions can be made to limit the device sensitivity to specific random effects. A review of several current sources of technology variability is presented, and the impacts to the overall technology offering are assessed.

The work presented in this paper is part of our investigation in the ROBOSKIN project. The project aims to develop and demonstrate a range of new robot capabilities based on the tactile feedback provided by a robotic skin. One of the project's objectives is to improve human-robot interaction capabilities in the application domain of robot-assisted play. This paper presents design challenges in augmenting a humanoid robot with tactile sensors specifically for interaction with children with autism. It reports on a preliminary study that includes requirements analysis based on a case study evaluation of interactions of children with autism with the child-sized, minimally expressive robot KASPAR. This is followed by the implementation of initial sensory capabilities on the robot that were then used in experimental investigations of tactile interaction with children with autism.

Smooth trajectories are essential for safe interaction in between human and a haptic interface. Different methods and strategies have been introduced to create such smooth trajectories. This paper studies the creation of human-like movements in haptic interfaces, based on the study of human arm motion. These motions are intended to retrain the upper limb movements of patients that lose manipulation functions following stroke. We present a model that uses higher degree polynomials to define a trajectory and control the robot arm to achieve minimum jerk movements. It also studies different methods that can be driven from polynomials to create more realistic human-like movements for therapeutic purposes.