Learning Based Intelligence For Socially Assistive Robots

Assistive robots are categorized as robots that share their area of work and interact with humans. Their main goals are to help, assist, and monitor humans, especially people with disabilities. To achieve these goals, it is necessary that these robots possess a series of characteristics, namely the abilities to perceive their environment from their sensors and act consequently, to interact with people in a multimodal manner, and to navigate and make decisions autonomously. This complexity demands computationally expensive algorithms to be performed in real time. The advent of high-end embedded processors has enabled several such algorithms to be processed concurrently and in real time. All these capabilities involve, to a greater or less extent, the use of machine learning techniques. In particular, in the last few years, new deep learning techniques have enabled a very important qualitative leap in different problems related to perception, navigation, and human understanding. In this Special Issue, several works are presented involving the use of machine learning techniques for assistive technologies, in particular for assistive robots.

Due to the world's rapidly growing elderly population, dementia is becoming increasingly prevalent. This poses considerable health, social, and economic concerns as it impacts individuals, families and healthcare systems. Current research has shown that cognitive interventions may slow the decline of or improve brain functioning in older adults. This research investigates the use of intelligent socially assistive robots to engage individuals in person-centered cognitively stimulating activities. Specifically, in this thesis, a novel learning-based control architecture is developed to enable socially assistive robots to act as social motivators during an activity. A hierarchical reinforcement learning approach is used in the architecture so that the robot can learn appropriate assistive behaviours based on activity structure and personalize an interaction based on the individual's behaviour and user state. Experiments show that the control architecture is effective in determining the robot's optimal assistive behaviours for a memory game interaction and a meal assistance scenario.

This book constitutes the refereed proceedings of the 6th International Conference on Social Robotics, ICSR 2014, held in Sydney, NSW, Australia, in October 2014. The 41 revised full papers presented in this book were carefully reviewed and selected from numerous submissions. Amongst others, topics covered are such as interaction and collaboration among robots, humans, and environments; robots to assist the elderly and persons with disabilities; socially assistive robots to improve quality of life; affective and cognitive sciences for socially interactive robots; personal robots for the home; social acceptance and impact in the society; robot ethics in human society and legal implications; context awareness, expectation, and intention understanding; control architectures for social robotics; socially appealing design methodologies; safety in robots working in human spaces; human augmentation, rehabilitation, and medical robots; robot applications in education, entertainment, and gaming; knowledge representation and reasoning frameworks for robot social intelligence; cognitive architectures that support social intelligence for robots; robots in the workplace; human-robot interaction; creative and entertaining robots.

Emotional intelligence has emerged as an important area of research in the artificial intelligence field as it covers a wide range of real-life domains. Though machines may never need all the emotional skills that people need, there is evidence to suggest that machines require at least some of these skills to appear intelligent when interacting with people. To understand how deep learning-based emotional intelligence can be applied and utilized across industries, further study on its opportunities and future directions is required. Multidisciplinary Applications of Deep Learning-Based Artificial Emotional Intelligence explores artificial intelligence applications, such as machine and deep learning, in emotional intelligence and examines their use towards attaining emotional intelligence acceleration and augmentation. It provides research on tools used to simplify and streamline the formation of deep learning for system architects and designers. Covering topics such as data analytics, deep learning, knowledge management, and virtual emotional intelligence, this reference work is ideal for computer scientists, engineers, industry professionals, researchers, scholars, practitioners, academicians, instructors, and students.

Caregivers play a crucial role in assisting seniors having difficulty accomplishing activities of daily living (ADLs) due to physical or cognitive limitations. A global decline in the caregiver-to-senior ratio is making it increasingly more difficult to care for these seniors. Socially assistive robots are promising alternative technologies for supporting seniors in living independently. However, limited research has gone into developing a learning-based method for designing assistive robot behaviors. This thesis aims to: (1) identify the key features necessary for assistive robots supporting seniors with cognitive impairments in completing ADLs; and (2) develop a novel behavior-learning architecture to teach robots how to display assistive behaviors using expert demonstrations and personalize these learned behaviors to the seniorâ s cognition using reinforcement learning to increase task performance. Experiments with a socially assistive robot validated the robotâ s ability to learn and personalize new behaviors to a userâ s cognition from expert demonstration using the proposed architecture.

The population of the world is rapidly aging and there is presently an increasing demand for residential care facilities to provide care for older adults. Understimulation can be a major concern in such facilities due to high resident-to-staff ratios and a decreasing number of healthcare staff to facilitate cognitive, social, and physical activities for older adults. Currently, socially assistive robots are being developed to assist in providing such stimulation. However, the existing robots are limited to only facilitating a set of activities that have been pre-programmed on the robot and cannot be customized to the needs of a facility. Furthermore, the majority consider only one-on-one activities, rather than providing stimulation to groups of users at the same time. This thesis focused on developing a learning based interaction system for socially assistive robots to: 1) autonomously facilitate multi-user activities while providing individualized assistance; 2) learn new customized activities from caregivers; and 3) personalize robot assistive behaviours to obtain user compliance. Numerous human-robot interaction experiments were conducted with the system integrated into the socially assistive robot Tangy for the multi-user activity of Bingo. The participants for the experiments consisting of caregivers and older adults. The results showed that: 1) participants had positive attitudes towards interacting with the robot and found it easy to use, 2) older adults were engaged during the activity and complied with the robotâ s behaviours, and 3) caregivers were able to successfully teach a new activity to the robot with moderately low perceived workload.

The two-volume set LNAI 14453 and 14454 constitutes the refereed post-conference proceedings of the 15th International Conference on Social Robotics, ICSR 2023, held in Doha, Qatar, during December 4–7, 2023. The 68 revised full papers presented in these proceedings were carefully reviewed and selected from 83 submissions. They deal with topics around the interaction between humans and intelligent robots and on the integration of robots into the fabric of society. This year the special topic is "Human-Robot Collaboration: Sea; Air; Land; Space and Cyberspace”, focusing on all physical and cyber-physical domains where humans and robots collaborate.

The book's content is designed to provide practical guidance and insights for conducting experiments in Human-Robot Interaction (HRI) and publishing the results in scientific journals. It includes a detailed explanation of how to conduct HRI experiments and what to do and what not to do to get an article accepted for publication. It is tailored to those seeking to deepen their understanding of HRI methodologies, statistical measurements, and research design. The case studies and examples featured in the book focus on interactions between social robots and specific demographics such as children and older adults, making it relevant for individuals working in healthcare, education, and related domains.Also covered are common statistical measurements used in HRI research and quantitative, qualitative, and meta-analyses. The concepts are illustrated with several international case studies of interactions between social robots and children and older adults and robot learning instead of programming. The final chapter explores current trends in HRI and provides insights into what to look for in the coming years. It includes an extensive reference section to help HRI researchers in all these areas.This book will appeal to an international audience of advanced students, researchers, industry, and others who are actively engaged or interested in the field of HRI.

Learning from Demonstration (LfD) explores techniques for learning a task policy from examples provided by a human teacher. The field of LfD has grown into an extensive body of literature over the past 30 years, with a wide variety of approaches for encoding human demonstrations and modeling skills and tasks. Additionally, we have recently seen a focus on gathering data from non-expert human teachers (i.e., domain experts but not robotics experts). In this book, we provide an introduction to the field with a focus on the unique technical challenges associated with designing robots that learn from naive human teachers. We begin, in the introduction, with a unification of the various terminology seen in the literature as well as an outline of the design choices one has in designing an LfD system. Chapter 2 gives a brief survey of the psychology literature that provides insights from human social learning that are relevant to designing robotic social learners. Chapter 3 walks through an LfD interaction, surveying the design choices one makes and state of the art approaches in prior work. First, is the choice of input, how the human teacher interacts with the robot to provide demonstrations. Next, is the choice of modeling technique. Currently, there is a dichotomy in the field between approaches that model low-level motor skills and those that model high-level tasks composed of primitive actions. We devote a chapter to each of these. Chapter 7 is devoted to interactive and active learning approaches that allow the robot to refine an existing task model. And finally, Chapter 8 provides best practices for evaluation of LfD systems, with a focus on how to approach experiments with human subjects in this domain.