Personalizing interactions in socially assistive robot (SAR) tutoring has shown promise with a wide variety of learners, especially when using multiple interaction modalities. Many of those interactions, however, focus on seated learning contexts, creating a need for multimodal personalization measures in kinesthetic (i.e., embodied) learning contexts. This paper proposes a multimodal measure of student kinesthetic curiosity ( $$KC^S$$ ) that combines a student's movement and curiosity measures into a single, personalized measure. This work evaluates the efficacy of $$KC^S$$ in a SAR tutor interaction by conducting a within-subjects ( $$n=9$$ ) pilot study where participants completed kinesthetic mixed reality coding exercises alongside a curious robot tutor whose actions were determined by $$KC^S$$ . The study results indicate that the stationarity assumptions needed for $$KC^S$$ were met and that the robot tutor was able to successfully use $$KC^S$$ to personalize its action policy, thereby positively affecting short term $$KC^S$$ . However, no significant results were found for longer state changes for each student. The mixed reality visual programming language (MoveToCode) created for this work has been made open-source. This work aims to inform future online features and measures for mixed reality human-robot interactions.

The field of Socially Assistive Robot (SAR) tutoring has extensively explored both subjective and objective usability metrics for seated tablet-based human-robot interactions. As SAR tutoring introduces kinesthetic mixed reality environments where students can move around and physically manipulate virtual objects, usability metrics for such interactions need to be re-evaluated. This paper applies standard usability metrics from seated 2D interactions to a kinesthetic mixed reality environment and validates those metrics with post-interaction survey data. Using data from a pilot study ( $$n=9$$ ) conducted with a mixed reality SAR tutor, three commonly-used metrics of usability for seated 2D tutoring interfaces were collected: performance, manipulation time, and gaze. The strength of each usability metric was compared to subjective survey-based scores measured with the System Usability Scale (SUS). The results show that usability scores were correlated with the gaze metric but not with the manipulation time or performance metrics. The findings provide interesting implications for the design and evaluation of kinesthetic mixed reality robot tutoring environments.

Robot tutors have great potential for supporting personalized learning, in both home and classroom settings. To be effective, robot tutors must encourage users to seek help as needed during the learning process. We conducted a between-subjects study with N = 45 participants to compare different types of learner help-seeking behaviors-pressing an on-screen button, pressing a physical button, and raising a hand- and assess how help-seeking behavior preferences relate to perceptions of the robot tutor. The results indicate that hand raising was seen as the hardest method for a user to perform but the most useful and beneficial, with positive trends in students' intention to use a robot.

This ongoing study delves into an autonomous swarm of unmanned aerial vehicles (UAVs) that takes mission requirements and moves in formations based on user input. We utilize commercial off-the-shelf (COTS) hardware and open source software to create a low-cost accessible platform for the potential use in commercial and research applications. The system is scalable, with the capability of swarm formation in both static and dynamic configurations using real-time path planning and optimized target assignment. The group of UAVs used in this study consists of multiple quadcopters, each equipped with an on-board computer, a flight controller, and COTS telemetry and GPS modules. Commands are sent to the swarm via a ground station. The ground station and UAVs communicate via a WiFi datalink. The system has demonstrated path-planning with collision avoidance capabilities through simulations. This study shows via simulation and partially through experimentation that swarm autonomy can be implemented effectively and cost-efficiently. This creates an ease of access for the use of a swarm of UAVs for a variety of applications including 3D mapping, and search and rescue across a variety of terrains with increasing difficulty. By integrating other sensors and instruments, this swarm can be used to measure a variety of parameters, locating targets and creating formations around them to best study the targets in areas where ground navigation and viewpoints are non-optimal.

Expressivity--the use of multiple modalities to convey internal state and intent of a robot--is critical for interaction. Yet, due to cost, safety, and other constraints, many robots lack high degrees of physical expressivity. This paper explores using mixed reality to enhance a robot with limited expressivity by adding virtual arms that extend the robot's expressiveness. The arms, capable of a range of non-physically-constrained gestures, were evaluated in a between-subject study ($n=34$) where participants engaged in a mixed reality mathematics task with a socially assistive robot. The study results indicate that the virtual arms added a higher degree of perceived emotion, helpfulness, and physical presence to the robot. Users who reported a higher perceived physical presence also found the robot to have a higher degree of social presence, ease of use, usefulness, and had a positive attitude toward using the robot with mixed reality. The results also demonstrate the users' ability to distinguish the virtual gestures' valence and intent.

Socially assistive robotics (SAR) research has shown great potential for supplementing and augmenting therapy for children with autism spectrum disorders (ASD). However, the vast majority of SAR research has been limited to short-term studies in highly controlled environments. The design and development of a SAR system capable of interacting autonomously in situ for long periods of time involves many engineering and computing challenges. This paper presents the design of a fully autonomous SAR system for long-term, in-home use with children with ASD. We address design decisions based on robustness and adaptability needs, discuss the development of the robot's character and interactions, and provide insights from the month-long, in-home data collections with children with ASD. This work contributes to a larger research program that is exploring how SAR can be used for enhancing the social and cognitive development of children with ASD.

Socially assistive robots (SAR) have shown great potential to augment the social and educational development of children with autism spectrum disorders (ASD). As SAR continues to substantiate itself as an effective enhancement to human intervention, researchers have sought to study its longitudinal impacts in real-world environments, including the home. Computational personalization stands out as a central computational challenge as it is necessary to enable SAR systems to adapt to each child's unique and changing needs. Toward that end, we formalized personalization as a hierarchical human robot learning framework (hHRL) consisting of five controllers (disclosure, promise, instruction, feedback, and inquiry) mediated by a meta-controller that utilized reinforcement learning to personalize instruction challenge levels and robot feedback based on each user's unique learning patterns. We instantiated and evaluated the approach in a study with 17 children with ASD, aged 3–7 years old, over month-long interventions in their homes. Our findings demonstrate that the fully autonomous SAR system was able to personalize its instruction and feedback over time to each child's proficiency. As a result, every child participant showed improvements in targeted skills and long-term retention of intervention content. Moreover, all child users were engaged for a majority of the intervention, and their families reported the SAR system to be useful and adaptable. In summary, our results show that autonomous, personalized SAR interventions are both feasible and effective in providing long-term in-home developmental support for children with diverse learning needs.