When designing socially assistive robots, HRI researchers often focus on robot personality as a means of increasing a person’s engagement, enjoyment, and trust. In this work, we argue that using only trait-based personality models is often limited in its ability to capture the nuance that matches end users’ desires, experiences, and cultural backgrounds. To address this gap, we introduce the concept of a robot character , a holistic framing of robot personality that extends the trait-based approach to include external factors, such as shared interests between the user and robot, as sociocultural and environmental factors. We introduced and validated the Robot Role Character Creation (R2C2) tool, an accessible scaffolding tool to co-design robot characters with end users in order to support more nuanced and personalized robots. R2C2 highlights the voices of end users and enables them to easily ideate and communicate their unique robot characters, particularly for populations often underrepresented in robot design. Through a cross-cultural study (the U.S. and Mexico), we validated the R2C2 tool in eliciting rich design insights for robot characters from people with mild cognitive impairment (MCI) and dementia (PwD). We report our findings, enabled by the R2C2 tool, on the role participants envisioned for their desired robot characters, the multidimensionality and adaptability of these robot characters, and how participants’ socio-cultural backgrounds influenced their characters. Our findings demonstrate that R2C2 can facilitate the creation of nuanced and personalized robot characters that resonate with user experiences, needs, and preferences. We analyze how participants envisioned the roles, multidimensionality, and cultural influences shaping their ideal robot characters, highlighting R2C2’s ability to capture these diverse perspectives. This work will serve as a basis for HRI designers to create more effective robot interactions, enhance acceptance and trust, and promote engagement with robot characters while centering the wisdom and personhood of people with cognitive impairments.

Many HRI researchers have engaged in participatory research to include users in robot design processes. However, to our knowledge, people with mild cognitive impairment (PwMCI) and early stage dementia have yet to be included in developing and programming robots, and the HRI community lacks tools to facilitate their inclusion. We bridge this gap by introducing PODER (PrOgramming framework to Develop Robot behaviors), which enables a lived technology experience for PwMCI via scaffolding, peer programming, and development tools to support them as key developers of social robots. We conducted a study where PwMCI and early stage dementia used PODER to program robot interactions, and found that participants were highly engaged and deeply enjoyed their experience, creating programs for robots that reflected their interests, experiences, and needs. Our results show the impact of including participants with MCI and early stage dementia in robot programming, including an increased understanding of technology, shifting their perceived role from technology users to programmers, and desire to be involved with the end-to-end process. By releasing PODER to the community, we hope this work can facilitate the intentional inclusion of people with cognitive impairments in further HRI research.

Gait rehabilitation is a critical aspect of post-stroke recovery, and emerging technologies such as virtual reality and wearables are playing a pivotal role in facilitating this process. However, despite the potential benefits, there is a significant gap in robot-based rehabilitative systems that facilitate repeated use by maintaining users' attention long-term. Our research aims to bridge this gap by creating a comprehensive system that utilizes different feedback types and robotic assistance to support users' gait rehabilitation outcomes. In this paper, we introduce GARRY (Gait Rehabilitation Robotic System), a new robotic system that provides interactive feedback during locomotor training. It promotes engagement by gamifying the rehabilitation process, offering a fun means for the user to meet their rehabilitation goals defined and set by physical therapists. GARRY also incorporates behavioral feedback to introduce a sense of companionship during a session. We make GARRY open-source to other researchers in hopes of encouraging accessibility and to promote research in the field. Our code can be found here: https://github.com/UCSD-RHC-Lab/GARRY

Cognitively assistive robots (CARs) have great potential to extend the reach of clinical interventions to the home. Due to the wide variety of cognitive abilities and rehabilitation goals, these systems must be flexible to support rapid and accurate implementation of intervention content that is grounded in existing clinical practice. To this end, we detail the system architecture of CARMEN (Cognitively Assistive Robot for Motivation and Neurorehabilitation), a flexible robot system we developed in collaboration with our key stakeholders: clinicians and people with mild cognitive impairment (PwMCI). We implemented a well-validated compensatory cognitive training (CCT) intervention on CARMEN, which it autonomously delivers to PwMCI. We deployed CARMEN in the homes of these stakeholders to evaluate and gain initial feedback on the system. We found that CARMEN gave participants confidence to use cognitive strategies in their everyday life, and participants saw opportunities for CARMEN to exhibit greater levels of autonomy or be used for other applications. Furthermore, elements of CARMEN are open source to support flexible home-deployed robots. Thus, CARMEN will enable the HRI community to deploy quality interventions to robots, ultimately increasing their accessibility and extensibility.

Many robot-delivered health interventions aim to support people longitudinally at home to complement or replace in-clinic treatments. However, there is little guidance on how robots can support collaborative goal setting (CGS). CGS is the process in which a person works with a clinician to set and modify their goals for care; it can improve treatment adherence and efficacy. However, for home-deployed robots, clinicians will have limited availability to help set and modify goals over time, which necessitates that robots support CGS on their own. In this work, we explore how robots can facilitate CGS in the context of our robot CARMEN (Cognitively Assistive Robot for Motivation and Neurorehabilitation), which delivers neurorehabilitation to people with mild cognitive impairment (PwMCI). We co-designed robot behaviors for supporting CGS with clinical neuropsychologists and PwMCI, and prototyped them on CARMEN. We present feedback on how PwMCI envision these behaviors supporting goal progress and motivation during an intervention. We report insights on how to support this process with home-deployed robots and propose a framework to support HRI researchers interested in exploring this both in the context of cognitively assistive robots and beyond. This work supports designing and implementing CGS on robots, which will ultimately extend the efficacy of robot-delivered health interventions.

Much research in healthcare robotics explores extending rehabilitative interventions to the home. However, for adults, little guidance exists on how to translate human-delivered, clinic-based interventions into robot-delivered, home-based ones to support longitudinal interaction. This is particularly problematic for neurorehabilitation, where adults with cognitive impairments require unique styles of interaction to avoid frustration or overstimulation. In this paper, we address this gap by exploring the design of robot-delivered neurorehabilitation interventions for people with mild cognitive impairment (PwMCI). Through a multi-year collaboration with clinical neuropsychologists and PwMCI, we developed robot prototypes which deliver cognitive training at home. We used these prototypes as design probes to understand how participants envision long-term deployment of the intervention, and how it can be contextualized to the lives of PwMCI. We report our findings and specify design patterns and considerations for translating neurorehabilitation interventions to robots. This work will serve as a basis for future endeavors to translate cognitive training and other clinical interventions onto a robot, support longitudinal engagement with home-deployed robots, and ultimately extend the accessibility of longitudinal health interventions for people with cognitive impairments.

JESSIE is a robotic system that enables novice programmers to program social robots by expressing high-level specifications. We employ control synthesis with a tangible front-end to allow users to define complex behavior for which we automatically generate control code. We demonstrate JESSIE in the context of enabling clinicians to create personalized treatments for people with mild cognitive impairment (MCI) on a Kuri robot, in little time and without error. We evaluated JESSIE with neuropsychologists who reported high usability and learnability. They gave suggestions for improvement, including increased support for personalization, multi-party programming, collaborative goal setting, and re-tasking robot role post-deployment, which each raise technical and sociotechnical issues in HRI. We exhibit JESSIE's reproducibility by replicating a clinician-created program on a TurtleBot~2. As an open-source means of accessing control synthesis, JESSIE supports reproducibility, scalability, and accessibility of personalized robots for HRI.

In safety-critical environments, robots need to reliably recognize human activity to be effective and trust-worthy partners. Since most human activity recognition (HAR) approaches rely on unimodal sensor data (e.g. motion capture or wearable sensors), it is unclear how the relationship between the sensor modality and motion granularity (e.g. gross or fine) of the activities impacts classification accuracy. To our knowledge, we are the first to investigate the efficacy of using motion capture as compared to wearable sensor data for recognizing human motion in manufacturing settings. We introduce the UCSD-MIT Human Motion dataset, composed of two assembly tasks that entail either gross or fine-grained motion. For both tasks, we compared the accuracy of a Vicon motion capture system to a Myo armband using three widely used HAR algorithms. We found that motion capture yielded higher accuracy than the wearable sensor for gross motion recognition (up to 36.95%), while the wearable sensor yielded higher accuracy for fine-grained motion (up to 28.06%). These results suggest that these sensor modalities are complementary, and that robots may benefit from systems that utilize multiple modalities to simultaneously, but independently, detect gross and fine-grained motion. Our findings will help guide researchers in numerous fields of robotics including learning from demonstration and grasping to effectively choose sensor modalities that are most suitable for their applications.

In this work, we present a novel non-visual HAR system that achieves state-of-the-art performance on realistic SCE tasks via a single wearable sensor. We leverage surface electromyography and inertial data from a low-profile wearable sensor to attain performant robot perception while remaining unobtrusive and user-friendly. By capturing both convolutional and temporal features with a hybrid CNN-LSTM classifier, our system is able to robustly and effectively classify complex, full-body human activities with only this single sensor. We perform a rigorous analysis of our method on two datasets representative of SCE tasks, and compare performance with several prominent HAR algorithms. Results show our system substantially outperforms rival algorithms in identifying complex human tasks from minimal sensing hardware, achieving F1-scores up to 84% over 31 strenuous activity classes. To our knowledge, we are the first to robustly identify complex full-body tasks using a single, unobtrusive sensor feasible for real-world use in SCEs. Using our approach, robots will be able to more reliably understand human activity, enabling them to safely navigate sensitive, crowded spaces.

Patient safety errors account for over 400,000 preventable deaths annually in US in hospitals alone, 70% of which are caused by team communication breakdowns, stemming from hierarchical structures and asymmetrical power dynamics between physicians, nurses, patients, and others. Nurses are uniquely positioned to identify and prevent these errors, but they are often penalized for speaking up, particularly when physicians are responsible. Nevertheless, empowering nurses and building strong interdisciplinary teams can lead to improved patient safety and outcomes. Thus, our group has been developing a series of intelligent systems that support teaming in safety critical settings, Robot-Centric Team Support System (RoboTSS), and recently developed a group detection and tracking system for collaborative robots. In this paper, we explore how RoboTSS can be used to empower nurses in interprofessional team settings, through a three month long, collaborative design process with nurses across five US-based hospitals. The main findings and contributions of this paper are as follows. First, we found that participants envisioned using a robotic crash cart to guide resuscitation procedures to improve efficiency and reduce errors. Second, nurses discussed how RoboTSS can generate choreography for efficient spatial reconfigurations in co-located clinical teams, which is particularly important in time-sensitive situations such as resuscitation. Third, we found that nurses want to use RoboTSS to "stop the line," and disrupt power dynamics by policing unsafe physician behavior, such as avoiding safety protocols using a robotic crash cart. Fourth, nurses envisioned using our system to support real-time error identification, such as breaking the sterile field, and then communicating those errors to physicians, to relieve them of responsibility. Finally, based on our findings, we propose robot design implications that capture how nurses envision utilizing RoboTSS. We hope this work promotes further exploration in how to design technology to challenge authority in asymmetrical power relationships, particularly in healthcare, as strong teams save lives.