A Socially Assistive Robot for Long-Term Cardiac Rehabilitation in the Real World

Closing the loop in minimally supervised human-robot interaction: formative and summative feedback

Human instructors fluidly communicate with hand gestures, head and body movements, and facial expressions, but robots rarely leverage these complementary cues. A minimally supervised social robot with such skills could help people exercise and learn new activities. Thus, we investigated how nonverbal feedback from a humanoid robot affects human behavior. Inspired by the education literature, we evaluated formative feedback (real-time corrections) and summative feedback (post-task scores) for three distinct tasks: positioning in the room, mimicking the robot's arm pose, and contacting the robot's hands. Twenty-eight adults completed seventy-five 30-s-long trials with no explicit instructions or experimenter help. Motion-capture data analysis shows that both formative and summative feedback from the robot significantly aided user performance. Additionally, formative feedback improved task understanding. These results show the power of nonverbal cues based on human movement and the utility of viewing feedback through formative and summative lenses.

Long-Term Exercise Assistance: Group and One-on-One Interactions between a Social Robot and Seniors

For older adults, regular exercises can provide both physical and mental benefits, increase their independence, and reduce the risks of diseases associated with aging. However, only a small portion of older adults regularly engage in physical activity. Therefore, it is important to promote exercise among older adults to help maintain overall health. In this paper, we present the first exploratory long-term human–robot interaction (HRI) study conducted at a local long-term care facility to investigate the benefits of one-on-one and group exercise interactions with an autonomous socially assistive robot and older adults. To provide targeted facilitation, our robot utilizes a unique emotion model that can adapt its assistive behaviors to users’ affect and track their progress towards exercise goals through repeated sessions using the Goal Attainment Scale (GAS), while also monitoring heart rate to prevent overexertion. Results of the study show that users had positive valence and high engagement towards the robot and were able to maintain their exercise performance throughout the study. Questionnaire results showed high robot acceptance for both types of interactions. However, users in the one-on-one sessions perceived the robot as more sociable and intelligent, and had more positive perception of the robot’s appearance and movements.

Personalised socially assistive robot for cardiac rehabilitation: Critical reflections on long-term interactions in the real world

Lack of motivation and low adherence rates are critical concerns of long-term rehabilitation programmes, such as cardiac rehabilitation. Socially assistive robots are known to be effective in improving motivation in therapy. However, over longer durations, generic and repetitive behaviours by the robot often result in a decrease in motivation and engagement, which can be overcome by personalising the interaction, such as recognising users, addressing them with their name, and providing feedback on their progress and adherence. We carried out a real-world clinical study, lasting 2.5 years with 43 patients to evaluate the effects of using a robot and personalisation in cardiac rehabilitation. Due to dropouts and other factors, 26 patients completed the programme. The results derived from these patients suggest that robots facilitate motivation and adherence, enable prompt detection of critical conditions by clinicians, and improve the cardiovascular functioning of the patients. Personalisation is further beneficial when providing high-intensity training, eliciting and maintaining engagement (as measured through gaze and social interactions) and motivation throughout the programme. However, relying on full autonomy for personalisation in a real-world environment resulted in sensor and user recognition failures, which caused negative user perceptions and lowered the perceived utility of the robot. Nonetheless, personalisation was positively perceived, suggesting that potential drawbacks need to be weighed against various benefits of the personalised interaction.

Socially Assistive Robots for Parkinson's Disease: Needs, Attitudes and Specific Applications as Identified by Healthcare Professionals

To explore how socially assistive robots (SARs) may assist the specific needs of individuals with Parkinson's disease (IwPD), we conducted three focus groups with 12 clinicians who treat IwPD. We present a thematic analysis of their perceptions of the needs of the patients, and their own expectations, perceived advantages, disadvantages and concerns regarding the use of SARs for IwPD. Clinicians were positive towards using SARs for IwPD, if used in the patient's home, for motor, communication, emotional, and cognitive needs, especially for practice and for help with activities of daily living. They were concerned that a SAR might be used to replace clinicians’ work, and stressed it should only augment the clinicians’ work. They thought a SAR may relieve some of the burden experienced by informal caregivers, and identified specific applications for SARs for PD. We asked 18 stakeholders (nine IwPD, nine family members) to rate their level of agreement with the clinicians’ statements. The greatest divergence between their views and those of the clinicians was on the topic of using a SAR as a companion, or as a feeding assistant, to which they objected. This work may be used as a basis for future studies designing SARs for IwPD.

A Socially Assistive Robot for Stroke Patients: Acceptance, Needs, and Concerns of Patients and Informal Caregivers

Stroke patients often contend with long-term physical challenges that require treatment and support from both formal and informal caregivers. Socially Assistive Robots (SARs) can assist patients in their physical rehabilitation process and relieve some of the burden on the informal caregivers, such as spouses and family members. We collected and analyzed information from 23 participants (11 stroke patients and 12 informal caregivers) who participated in a total of six focus-group discussions. The participants responded to questions regarding using a SAR to promote physical exercises during the rehabilitation process: (a) the advantages and disadvantages of doing so; (b) specific needs that they wish a SAR would address; (c) patient-specific adaptations they would propose to include; and (d) concerns they had regarding the use of such technology in stroke rehabilitation. We found that the majority of the participants in both groups were interested in experiencing the use of a SAR for rehabilitation, in the clinic and at home. Both groups noted the advantage of having the constant presence of a motivating entity with whom they can practice their rehabilitative exercises. The patients noted how such a device can assist formal caregivers in managing their workload, while the informal caregivers indicated that such a system could ease their own workload and sense of burden. The main disadvantages that participants noted related to the robot not possessing human abilities, such as the ability to hold a conversation, to physically guide the patient's movements, and to express or understand emotions. We anticipate that the data collected in this study-input from the patients and their family members, including the similarities and differences between their points of view-will aid in improving the development of SARs for rehabilitation, so that they can better suit people who have had a stroke, and meet their individual needs.

A Meta-Analysis on Remote HRI and In-Person HRI: What Is a Socially Assistive Robot to Do?

Recently, due to the COVID-19 pandemic and the related social distancing measures, in-person activities have been significantly reduced to limit the spread of the virus, especially in healthcare settings. This has led to loneliness and social isolation for our most vulnerable populations. Socially assistive robots can play a crucial role in minimizing these negative affects. Namely, socially assistive robots can provide assistance with activities of daily living, and through cognitive and physical stimulation. The ongoing pandemic has also accelerated the exploration of remote presence ranging from workplaces to home and healthcare environments. Human-robot interaction (HRI) researchers have also explored the use of remote HRI to provide cognitive assistance in healthcare settings. Existing in-person and remote comparison studies have investigated the feasibility of these types of HRI on individual scenarios and tasks. However, no consensus on the specific differences between in-person HRI and remote HRI has been determined. Furthermore, to date, the exact outcomes for in-person HRI versus remote HRI both with a physical socially assistive robot have not been extensively compared and their influence on physical embodiment in remote conditions has not been addressed. In this paper, we investigate and compare in-person HRI versus remote HRI for robots that assist people with activities of daily living and cognitive interventions. We present the first comprehensive investigation and meta-analysis of these two types of robotic presence to determine how they influence HRI outcomes and impact user tasks. In particular, we address research questions regarding experience, perceptions and attitudes, and the efficacy of both humanoid and non-humanoid socially assistive robots with different populations and interaction modes. The use of remote HRI to provide assistance with daily activities and interventions is a promising emerging field for healthcare applications.

Interaction Matters: The Effect of Touching the Social Robot PARO on Pain and Stress is Stronger When Turned ON vs. OFF

Social touch between humans, as well as between humans and animals, was previously found to reduce pain and stress. We previously reported that touching a social robot can also induce a reduction in pain ratings. However, it is unclear if the effect that touching a robot has on pain perception is due to its appearance and its pleasant touch, or due to its ability to socially interact with humans. In the current experiment, we aimed to assess the contribution of the interactive quality to pain perception. We assessed the effect of touching the social robot PARO on mild and strong pain ratings and on stress perception, on a total of 60 healthy young participants. The robot either interacted with participants (ON group, n = 30) or was turned off (OFF group, n = 30). Touching the robot induced a decrease in mild pain ratings (compared to baseline) only in the ON group while strong pain ratings decreased similarly in both the ON and the OFF groups. The decrease in mild pain ratings in the ON group was significantly greater in participants with a higher positive perception of the interaction with PARO. We conclude that part of the effect that touching the robot has on pain stems from its interactive features.

Multi-modal Open World User Identification

User identification is an essential step in creating a personalised long-term interaction with robots. This requires learning the users continuously and incrementally, possibly starting from a state without any known user. In this article, we describe a multi-modal incremental Bayesian network with online learning, which is the first method that can be applied in such scenarios. Face recognition is used as the primary biometric, and it is combined with ancillary information, such as gender, age, height, and time of interaction to improve the recognition. The Multi-modal Long-term User Recognition Dataset is generated to simulate various human-robot interaction (HRI) scenarios and evaluate our approach in comparison to face recognition, soft biometrics, and a state-of-the-art open world recognition method (Extreme Value Machine). The results show that the proposed methods significantly outperform the baselines, with an increase in the identification rate up to 47.9% in open-set and closed-set scenarios, and a significant decrease in long-term recognition performance loss. The proposed models generalise well to new users, provide stability, improve over time, and decrease the bias of face recognition. The models were applied in HRI studies for user recognition, personalised rehabilitation, and customer-oriented service, which showed that they are suitable for long-term HRI in the real world.

A Data-Driven Approach to Physical Fatigue Management Using Wearable Sensors to Classify Four Diagnostic Fatigue States

Physical exercise contributes to the success of rehabilitation programs and rehabilitation processes assisted through social robots. However, the amount and intensity of exercise needed to obtain positive results are unknown. Several considerations must be kept in mind for its implementation in rehabilitation, as monitoring of patients' intensity, which is essential to avoid extreme fatigue conditions, may cause physical and physiological complications. The use of machine learning models has been implemented in fatigue management, but is limited in practice due to the lack of understanding of how an individual's performance deteriorates with fatigue; this can vary based on physical exercise, environment, and the individual's characteristics. As a first step, this paper lays the foundation for a data analytic approach to managing fatigue in walking tasks. The proposed framework establishes the criteria for a feature and machine learning algorithm selection for fatigue management, classifying four fatigue diagnoses states. Based on the proposed framework and the classifier implemented, the random forest model presented the best performance with an average accuracy of ≥98% and F-score of ≥93%. This model was comprised of ≤16 features. In addition, the prediction performance was analyzed by limiting the sensors used from four IMUs to two or even one IMU with an overall performance of ≥88%.

A Survey on Socially Assistive Robotics: Clinicians' and Patients' Perception of a Social Robot within Gait Rehabilitation Therapies

A growing interest in Socially Assistive Robotics in Physical Rehabilitation is currently observed; some of the benefits highlight the capability of a social robot to support and assist rehabilitation procedures. This paper presents a perception study that aimed to evaluate clinicians’ and patients’ perception of a social robot that will be integrated as part of Lokomat therapy. A total of 88 participants were surveyed, employing an online questionnaire based on the Unified Theory of Acceptance and Use of Technology (UTAUT). The participants belong to two health care institutions located in different countries (Colombia and Spain). The results showed an overall positive perception of the social robot (>60% of participants have a positive acceptance). Furthermore, a difference depending on the nature of the user (clinician vs. patient) was found.