Personal Robots Research Articles

User-centered Social Interaction Design in Intelligent Personal Assistants and Social Robots

User-centered design practices are used to develop the social interaction characteristics of intelligent personal assistants and social robots. In this approach, developers establish characteristics favored by the majority of users. However, catering to target users may negate the benefits in user experience and use intention achieved from matching a product’s characteristics to the preferences of individual users. The present study examines differences between target versus individual user based approaches to user-centered design. Specifically, a framework is presented on how to develop a product to meet individual user preferences. Results show that individual user preferences, while similar to the target user preferences, can vary significantly from the baseline. Machine learning and artificial intelligence approaches should be employed to help adjust social interaction approaches from a baseline to individual user preferences.

Effect of a Group-Based Personal Assistive RObot (PARO) Robot Intervention on Cognitive Function, Autonomic Nervous System Function, and Mental Well-being in Older Adults with Mild Dementia: A Randomized Controlled Trial

ObjectivesPersonal Assistive RObot (PARO) interventions have been used to treat agitation and mood symptoms of dementia effectively. However, the effects of a PARO intervention on physiological and cognitive function are unclear. To examine the effects of a group-based PARO intervention for older adults with mild dementia. DesignUsing a group-based PARO intervention randomized controlled trial with 2-arm parallel groups. Setting and ParticipantsOlder adults with mild dementia aged 65 years or older from 4 dementia day care centers were recruited. MethodsPhysiological parameters were assessed using the finger tapping test (FTT) and heart rate variability (HRV). The Mini-Mental State Examination (MMSE), Geriatric Depression Scale–Short Form (GDS-SF), University of California Los Angeles loneliness scale–version 3 (UCLA-3), and Warwick-Edinburgh Mental Well-being Scale (WEMWBS) were assessed before the intervention, end of the intervention, and 1-month after the intervention. ResultsUsing a repeated-measures generalized linear model, significant time × group interactions were found in the MMSE [F(2, 115) = 19.54, P < .001], FTT [F(2, 115) = 4.87, P = .01], HRV high-frequency [F(2, 115) = 3.57, P = .03], and high-frequency/low-frequency ratio [F(2, 115) = 0.96, P = .01], UCLA-3 [F(2, 115) = 54.7, P < .001], GDS-SF [F(2, 115) = 3.36, P = .04], and WEMWBS [F(2, 115) = 5.93, P < .001]. Furthermore, psychological parameters improved significantly and continuously even 1 month after the PARO intervention was finished. Physiological parameters significantly improved at week 6, but the effects had diminished by week 10. Conclusions and ImplicationsA PARO intervention may effectively improve the physiological and psychological responses of people with mild dementia.

Customer service chatbot enhancement with attention-based transfer learning

Customer service is an important and expensive aspect of business, often being the largest department in most companies. With growing societal acceptance and increasing cost efficiency due to mass production, service robots are beginning to cross from the industrial domain to the social domain. Currently, customer service robots tend to be digital and emulate social interactions through on-screen text, but state-of-the-art research points towards physical robots soon providing customer service in person. This article explores the feasibility of Transfer Learning different customer service domains to improve chatbot models. In our proposed approach, transfer learning-based chatbot models are initially assigned to learn one domain from an initial random weight distribution. Each model is then tasked with learning another domain by transferring knowledge from the previous domains. To evaluate our approach, a range of 19 companies from domains such as e-Commerce, telecommunications, and technology are selected through social interaction with X (formerly Twitter) customer support accounts. The results show that the majority of models are improved when transferring knowledge from at least one other domain, particularly those more data-scarce than others. General language transfer learning is observed, as well as higher-level transfer of similar domain knowledge. For each of the 19 domains, the Wilcoxon signed-rank test suggests that 16 have statistically significant distributions between transfer and non-transfer learning. Finally, feasibility is explored for the deployment of chatbot models to physical robot platforms including “Pepper”, a semi-humanoid robot manufactured by SoftBank Robotics, and “Temi”, a personal assistant robot.

Stiffness-switchable hydrogel composite for transformable exo-suit

Transformable exo-suits, which are soft and wearable under normal conditions and could increase stiffness dramatically on demand, are significant in personal protection and robotics and also a dream of science-fiction fans. Herein, an ideal candidate material based on a carbon fabric reinforced thermal-hardening hydrogel (CFRTH) composite is proposed for developing transformable exo-suits. The introduction of carbon fabric significantly enhances the mechanical performance of thermal-hardening hydrogel, and empowers the CFRTH composite with an active, rapid and repeatable stiffness switchability. At ambient temperature, the CFRTH composite developed is soft and wearable with excellent flexibility and shape adaptability, while the composite becomes hard and rigid instantaneously as temperature rises. The flexural modulus of the CFRTH composite increases from 2.3 MPa to 539.7 MPa (about 232 times) by applying an electro-thermal stimulus, which endows the composite with good energy absorption/dissipation performance. Compared with the untransformed CFRTH composite, the transformed CFRTH composite under the electro-thermal stimulus exhibits a giant improvement (200%) in the peak force attenuation ratio under dropping ball test and excellent puncture resistance under penetration test and knife stab. Finally, the transformable CFRTH composite demonstrates a high effectiveness in fragile product protection from the impact of steel ball. This study offers a novel and versatile strategy for developing transformable exo-suits which have wearable conformability under normal circumstances and exhibit enhanced stiffness and impact protection performance on-demand through an electro-thermal stimulus.

Designing Socially Assistive Robots Exploring Israeli and German Designers’ Perceptions

Socially assistive robots (SARs) are becoming more prevalent in everyday life, emphasizing the need to make them socially acceptable and aligned with users’ expectations. Robots’ appearance impacts users’ behaviors and attitudes toward them. Therefore, product designers choose visual qualities to give the robot a character and to imply its functionality and personality. In this work, we sought to investigate the effect of cultural differences on Israeli and German designers’ perceptions of SARs’ roles and appearance in four different contexts: a service robot for an assisted living/retirement residence facility, a medical assistant robot for a hospital environment, a COVID-19 officer robot, and a personal assistant robot for domestic use. The key insight is that although Israeli and German designers share similar perceptions of visual qualities for most of the robotics roles, we found differences in the perception of the COVID-19 officer robot’s role and, by that, its most suitable visual design. This work indicates that context and culture play a role in users’ perceptions and expectations; therefore, they should be taken into account when designing new SARs for diverse contexts.

Mechanical Survey on Wheeled Mobile Robot Platform for Industrial and Personal Service Robots

Mechanical Survey on Wheeled Mobile Robot Platform for Industrial and Personal Service Robots

Personal assistant robot using reinforcement learning: DARWIN-OP2 as a case study

Personal assistant robot using reinforcement learning: DARWIN-OP2 as a case study

J.A.R.V.I.S: A Personal Assistant Robot

Abstract: Personal assistant robots are becoming increasingly popular as versatile devices that can assist individuals in various aspects of daily life. These robots are designed to be small and portable, with user-friendly interaction features that allow them to navigate tight spaces and interact closely with users. Equipped with sensors, cameras, and AI algorithms, personal assistant robots can perceive and respond to their environment, recognize faces and voices, and perform tasks such as setting reminders, providing information, and controlling smart home devices. They offer a range of benefits in different settings, including smart homes, healthcare facilities, and public spaces, where they can serve as personal assistants, health monitors, and information guides. The ability of personal assistant robots to learn and adapt to users' preferences and behaviors over time enables them to provide personalized and intuitive assistance, making them suitable for individuals of all ages. As advancements in their design and capabilities continue, personal assistant robots are expected to have an even greater impact on enhancing daily life in the future

Development of a Personal Guide Robot That Leads a Guest Hand-in-Hand While Keeping a Distance.

This paper proposes a novel tour guide robot, "ASAHI ReBorn", which can lead a guest by hand one-on-one while maintaining a proper distance from the guest. The robot uses a stretchable arm interface to hold the guest's hand and adjusts its speed according to the guest's pace. The robot also follows a given guide path accurately using the Robot Side method, a robot navigation method that follows a pre-defined path quickly and accurately. In addition, a control method is introduced that limits the angular velocity of the robot to avoid the robot's quick turn while guiding the guest. We evaluated the performance and usability of the proposed robot through experiments and user studies. The tour-guiding experiment revealed that the proposed method that keeps distance between the robot and the guest using the stretchable arm enables the guests to look around the exhibits compared with the condition where the robot moved at a constant velocity.

Exploring mobility and transportation technology futures for people with ambulatory disabilities: A science fiction prototype

Although a number of studies have explored science fiction prototyping as a method for new product development, no study has ever used the method to examine the mobility and transportation technology needs of people with disabilities. The current research created a science fiction prototype, based on expert opinion expressed during an imagination workshop, which the authors then presented to a sample of people with ambulatory disabilities. Through a conjoint analysis, the sample members delineated the elements of the prototype they regarded as most important. The participants considered personal mobility assistive technology (either an automated wheelchair or an exoskeleton) the most important, followed by personal automation (autonomous [driverless] vehicle or personal robot) and thirdly by personal assistance technologies (real-time response versus augmented metaverse planning systems). Outputs to the conjoint analysis were clustered and three categories of individual emerged (i) more innovatively minded people who occupied the first cluster and preferred an exoskeleton, a personal robot and a subscription to the metaverse, (ii) people who appeared to be less technologically inclined and preferred an automated wheelchair, an autonomous vehicle and a subscription to a real-time assistive system, and (iii) a group with members favouring an AV but with few other predilections.

Flexible temperature-pressure dual sensor based on 3D spiral thermoelectric Bi2Te3 films

Dual-parameter pressure-temperature sensors are widely employed in personal health monitoring and robots to detect external signals. Herein, we develop a flexible composite dual-parameter pressure-temperature sensor based on three-dimensional (3D) spiral thermoelectric Bi2Te3 films. The film has a (000l) texture and good flexibility, exhibiting a maximum Seebeck coefficient of −181 μV K–1 and piezoresistance gauge factor of approximately −9.2. The device demonstrates a record-high temperature-sensing performance with a high sensing sensitivity (−426.4 μV K−1) and rapid response time (~0.95 s), which are better than those observed in most previous studies. In addition, owing to the piezoresistive effect in the Bi2Te3 film, the 3D-spiral deviceexhibits significant pressure-response properties with a pressure-sensing sensitivity of 120 Pa–1. This innovative approach achieves high-performance dual-parameter sensing using one kind of material with high flexibility, providing insight into the design and fabrication of many applications, such as e-skin.

Robot Ethics

Robot Ethics

Robot Ethics

Robot Ethics

Exploring the Role of Sociability, Ownership, and Affinity for Technology in Shaping Acceptance and Intention to Use Personal Assistance Robots.

Personal assistance robots are making inroads into our private and public life. At the same time, most humans are still unfamiliar with this technology and hesitate to accept and use it for daily tasks. Fortunately, the designs of robots can be adjusted to yield greater acceptance, subsequently enabling their utilization across various tasks. Using a scenario-based online experiment, we explored how sociability (low vs. high), ownership (private vs. public), and affinity for technology influence the acceptance and intention to use a robot for grocery shopping. Moreover, to assess users’ preference for robots’ morphology, participants were asked to choose a robot (technical vs. anthropomorphic design) that they would prefer to use in a supermarket. We found that low sociability of the service robot and a higher affective affinity for technology led to a higher level of acceptance. For more sociable robots, higher levels of anthropomorphism were preferred. Our results point to the importance of task-specific robot design that exceeds functional considerations.

Personalized robots for long-term telerehabilitation after stroke: a perspective on technological readiness and clinical translation.

Stroke rehabilitation, which demands consistent, intensive, and adaptable intervention in the long term, faced significant challenges due to the COVID-19 pandemic. During this time, telerehabilitation emerged as a noteworthy complement to traditional rehabilitation services, offering the convenience of at-home care delivery and overcoming geographical and resource limitations. Self-help rehabilitation robots deliver repetitive and intensive physical assistance, thereby alleviating the labor burden. However, robots have rarely demonstrated long-term readiness for poststroke telerehabilitation services. The transition from research trials to general clinical services presents several challenges that may undermine the rehabilitative gains observed in these studies. This perspective discusses the technological readiness of personal use robots in the context of telerehabilitation and identifies the potential challenges for their clinical translation. The goal is to leverage technology to seamlessly integrate it into standard clinical workflows, ultimately enhancing the outcomes of stroke rehabilitation.

A Brain-Controlled Quadruped Robot: A Proof-of-Concept Demonstration.

Coupling brain-computer interfaces (BCIs) and robotic systems in the future can enable seamless personal assistant systems in everyday life, with the requests that can be performed in a discrete manner, using one's brain activity only. These types of systems might be of a particular interest for people with locked-in syndrome (LIS) or amyotrophic lateral sclerosis (ALS) because they can benefit from communicating with robotic assistants using brain sensing interfaces. In this proof-of-concept work, we explored how a wireless and wearable BCI device can control a quadruped robot-Boston Dynamics' Spot. The device measures the user's electroencephalography (EEG) and electrooculography (EOG) activity of the user from the electrodes embedded in the glasses' frame. The user responds to a series of questions with YES/NO answers by performing a brain-teaser activity of mental calculus. Each question-answer pair has a pre-configured set of actions for Spot. For instance, Spot was prompted to walk across a room, pick up an object, and retrieve it for the user (i.e., bring a bottle of water) when a sequence resolved to a YES response. Our system achieved at a success rate of 83.4%. To the best of our knowledge, this is the first integration of wireless, non-visual-based BCI systems with Spot in the context of personal assistant use cases. While this BCI quadruped robot system is an early prototype, future iterations may embody friendly and intuitive cues similar to regular service dogs. As such, this project aims to pave a path towards future developments in modern day personal assistant robots powered by wireless and wearable BCI systems in everyday living conditions.

Gaze-Cues of Humans and Robots on Pedestrian Ways

Delivery robots and personal cargo robots are increasingly sharing space with incidentally co-present persons (InCoPs) on pedestrian ways facing the challenge of socially adequate and safe navigation. Humans are able to effortlessly negotiate this shared space by signalling their skirting intentions via non-verbal gaze cues. In two online-experiments we investigated whether this phenomenon of gaze cuing can be transferred to human–robot interaction. In the first study, participants (n = 92) watched short videos in which either a human, a humanoid robot or a non-humanoid delivery robot moved towards the camera. In each video, the counterpart looked either straight towards the camera or did an eye movement to the right or left. The results showed that when the counterpart gaze cued to their left, also participants skirted more often to the left from their perspective, thereby walking past each other and avoiding collision. Since the participants were recruited in a right-hand driving country we replicated the study in left-hand driving countries (n = 176). Results showed that participants skirted more often to the right when the counterpart gaze cued to the right, and to the left in case of eye movements to the left, expanding our previous result. In both studies, skirting behavior did not differ regarding the type of counterpart. Hence, gaze cues increase the chance to trigger complementary skirting behavior in InCoPs independently of the robot morphology. Equipping robots with eyes can help to indicate moving direction by gaze cues and thereby improve interactions between humans and robots on pedestrian ways.

“It Brings the Good Vibes”: Exploring Biomorphic Aesthetics in the Design of Soft Personal Robots

The flexible bodies of soft robots provide exciting new possibilities for interaction with humans. In this paper, we propose a novel design paradigm, Soft Biomorphism, for soft robots centered on the idea of amplifying their inherent biomorphic aesthetic qualities and activating these as affordances for human interaction. Following this approach, we developed a set of biomorphic soft robotic prototypes and conducted two studies to understand the effects of biomorphic design aesthetics on people’s impressions of these prototypes. Based on qualitative data collected through five workshop sessions, the first exploratory study (n = 10) sought to investigate the envisioned uses and types of interactions that prototypes elicited within the context of personal robots. We found that various uses were considered and that most participants associated the biomorphic aesthetic design with soft robots contributing to emotional and physical well-being. Building on these results, we conducted a second study (n = 32) to investigate if soft robots with enhanced biomorphic qualities are perceived as more appealing and appropriate for physical human–robot interaction aimed at supporting well-being. We did not find any statistically significant preference for biomorphic soft robots. However, we found statistically significant differences in appeal ratings post-interaction for some prototypes, suggesting that physical interaction with soft robots can impact the perceived appeal. Based on our findings, we highlight key issues to bear in mind when considering biomorphic aesthetics in soft personal robot designs and provide tentative design recommendations to combine biomorphic and geometric elements and align visual appearance, tactility, and movement in future robot designs.

How can ISO 13482:2014 account for the ethical and social considerations of robotic exoskeletons?

This paper analyzes and classifies regulatory gaps and inconsistencies in ISO 13482:2014 (‘Safety Requirements for Personal Care Robots'), specifically regarding robotic lower-limb exoskeletons, being personal care robots, for everyday activities. Following a systematic literature review, our findings support the conclusion that, even though ISO 13482:2014 has proven to be a substantial step towards regulating that type of wearable robot, it fails to address safety sufficiently and comprehensively. That failure results in a general overlook of critical legal, ethical, and social considerations when designing robots, with the consequence that seemingly safe systems might nonetheless harm end-users. Notwithstanding those limitations and impediments to the development of safe technologies, to date, there has been no thorough assessment of how the standard regulates the development of exoskeletons and whether it requires any improvement in light of ethical, legal, and societal considerations. To bridge this gap, we compile relevant areas for improvement concerning ISO 13482:2014 fueled by these considerations. We do so in an accessible manner and provide concrete recommendations to help decision-makers overcome the standard's drawbacks.

Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment

PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realistically simulated environments, under the assumptions with noiseless actuation and most importantly, perfect localization with GPS and compass sensors. However, accurate GPS signalis difficult to be obtained in real indoor environment. To improve the PointGoal navigation accuracy without GPS signal, we use visual odometry (VO) and propose a novel action integration module (AIM) trained in unsupervised manner. Sepecifically, unsupervised VO computes the relative pose of the agent from the re-projection error of two adjacent frames, and then replaces the accurate GPS signal with the path integration. The pseudo position estimated by VO is used to train action integration which assists agent to update their internal perception of location and helps improve the success rate of navigation. The training and inference process only use RGB, depth, collision as well as self-action information. The experiments show that the proposed system achieves satisfactory results and outperforms the partially supervised learning algorithms on the popular Gibson dataset.