Personal Assistants: Emerging Computational Technologies

Cognitive Assistants is a subset area of Personal Assistants focused on ubiquitous and pervasive platforms and services. They are aimed at elderly people’s needs, habits, and emotions by being dynamic, adaptive, sensitive, and responsive. These advances make cognitive assistants a true candidate of being used in real scenarios and help elderly people at home and outside environments. This survey will discuss the cognitive assistants’ emergence in order to provide a list of new projects being developed on this area. We summarize and enumerate the state-of-the-art projects. Moreover, we discuss how technology support the elderly affected by physical or mental disabilities or chronic diseases.

Personal assistants may help the elderly population to live independently and improve their welfare in ambient assisted living environments. However, although there are current proposals already developed both in academic and commercial domains, these systems are still far from being established on the daily lives of the general population. Argumentation technologies can help to deal with open challenges in this domain. In this chapter, we explore the connection between the related areas of argumentation, recommendation, decision-making and persuasion, and we review related work that can play an important role on the development of the next generation of personal assistants for ambient assisted living.

A cognitive disability is a medical condition that, despite all technological progress, still does not have a cure, i.e., there are cases where the physician may use medication, but the only purpose is to decrease the progression of the disease, not its cure. This is the case in many situations, and in particular in kidney illnesses, which have a dominant impact on a person well being, i.e., the assistance to an individual to whom was diagnosed cognitive disabilities is essential, where the location of the individual is not decisive or important. Hence, the presence of a Personal Assistance Service can become a cornerstone in achieving independence and quality of life. Therefore, the objective of this work is to present an intelligent system aimed at an endless individuals monitoring and alerting system, based on a Logical Programming approach to Knowledge Representation and Reasoning, and centre on RapidMiner, a software platform that provides an integrated environment for machine learning, predictive analysis or application development and deployment. It undergoes a Case Based approach to computing that tracks patient’s performance, learn and deliver content when it is needed, and assures that patient’s key information is changed into the indispensable ongoing knowledge.

Personal assistants using emerging technologies are showing a great potential to provide an important impact in different aspects of daily human life currently and during the near future. They are usually intended to help people with especial needs. The one presented in this chapter, called VIRTRAEL, is especially designed to assess, stimulate and train several cognitive skills that experience a decline as people age, reason why its target public is the elderly, as well as the therapists who treat them. VIRTRAEL is made up of different types of exercises, each of them specifically designed to evaluate and stimulate a different cognitive function. After presenting an overview of our tool, we focus on one of its exercises, the one devoted to the classification and memorization of images, which is intended to train the visual working memory. We also present a configuration tool that allows the therapists to customize and adapt each exercise to the preferences and needs of a given user. Moreover, we show some results of a pilot study carried out with a sample of elderly people.

The world’s population is ageing and, with that, new social issues arise, especially in terms of healthcare and daily activities. Despite the preference for human professional healthcare, the new socio-economic situation and the decrease in care personnel make necessary to give support to the process of caregiving. In this context, Robotics can be considered as a solution since it can provide healthcare support, help in performing daily tasks, and/or increase the feeling of autonomony and self management. This paper is an overview of the existing robotic technologies for elderly care, analysing their benefits for the elderly.

During the last few years, deep learning has led to an astonishing advancement in visual recognition. Computers now reach near-human accuracy in visually recognizing characters, physical objects and human faces. This will certainly allow us to build more intelligent personal assistants that can help users better understand their surrounding environments. However, most visual recognition systems have been designed for user-independent recognition (e.g., Google reverse image search), and not for an individual user. We believe this practice is restricting the technology from helping people who have individual needs. For example, a person with memory problems may want to have a computer that accurately recognizes a few close friends, rather than hundreds of celebrities. To address this issue, we propose a novel wearable system that enables users to create their own visual recognition system with minimal effort. A client running on Google Glass collects images of objects a user is interested in, and sends them to the server with a request for a specific machine learning task: training or classification. The server performs deep learning according to the request and returns the result to Glass. Regarding the training task, our system not only aims to build deep learning models with user generated image data, but also to update the models whenever new data is added by the user. Experiments show that our system is able to train the custom deep learning models in an efficient manner, in terms of the required amount of computing power and training data. Based on the customized deep learning model, the system classifies an image into one of 10 different user-defined categories with 97% accuracy.

Personal assistants are focused on helping users with various tasks in the daily management, as they anticipate their needs and learn with their interaction. An intelligent personal assistant is a software agent that can perform actions requested by a user and can access to information from remote sources, based on requirements or user profile. Moreover, intelligence personal assistants can be considered as a special case of recommendation systems since they are used in web searches. Thus, the personal assistant interacts and represents users to choose relevant items according to their needs and preferences. This work proposes an intelligent personal assistant aimed to support users for selecting educational material from learning objects repositories. In this regard, a recommendation system was implemented based on the artificial intelligence technique known as CBR. The possibility of taking advantage of previous results of students with similar characteristics allows to improve the relevance of the materials for each particular student. The results of the functional tests are satisfactory.

In the last years, the development of robots is entering a new stage where the focus is placed on interaction with people in their daily environments. With the improvement of more and more complex robots to be used in rehabilitation, heath care, service or other applications, robot-human interaction is a rapidly growing area of research. This chapter explores the topic of human-robot interaction. Finally, we presented a proposed framework design that will operate with a person. The system considers the person attitudes level while interact with. The goal is to propose an architecture that monitoring person attitudes in real scenario, and detect patterns of behavior in different occasions. The robot will interact with a person and its training a decision support system that in a real scenario that provide the robot to makes interactions with a person.

Two human-like intelligent artificial characters (agents) of heterogeneous realities (a humanoid robot and a virtual human) are developed with similar intelligence and functionalities. Operations of the characters are integrated through a unified platform. The characters are separately deployed in a homely environment to provide personal assistance to a physically disabled human in finding a missing household object. Human’s trust in the characters as well as bilateral trust between the characters for the collaboration are separately modeled, and real-time trust measurement methods are developed. A collaboration scheme between the characters based on the bilateral trust is developed. A comprehensive evaluation scheme is developed to evaluate the performance of the characters in assisting the human. The performance levels of the individual characters and their collaboration toward providing personal assistance to the human are compared. The results show that the individual characters and their collaboration can assist the disabled human successfully, but with varying capabilities. For example, the collaboration partly outperforms the individual characters, and the physical character (robot) partly outperforms the virtual character. The results are novel that broaden the horizon of humanoid robots and virtual humans and open a new paradigm of collaboration between physical (robot) and virtual (virtual human) characters. The results are useful to develop artificial characters of heterogeneous realities and their social collaborations to provide personal assistance to disabled humans in their daily living that may improve the quality of life and produce positive economic and societal impacts.

This paper introduces a proposal for integrating personal assistant robots with social capacities in smart environments. The personal robot will be a fundamental element for the detection and healthy regulation of the affect of the environment’s inhabitants. A full description of the main features of the proposed personal assistant robot are introduced. Also, the multi-modal emotion detection and emotion regulation modules are fully described. Machine learning techniques are employed for emotion recognition from voice and images and both outputs are merged to achieve the detected emotion.

Electronic Data Interchange has been around for more than 20 years but it is now on the verge of transition to the new environments of the Networked Society, along with Personal Assistants, the Internet of Things and Ambient Intelligence, all aimed at relations with consumers. The commercial relationships will have to be rethought and reshaped, and Privacy and Data Protection will be at stake. It is the moment to look at the right to be forgotten from a perspective of the B2C commercial relationship.

In this chapter, we will study the problem of civil liability resultant from the use of intelligent personal assistants and the most appropriate legal means to resolve disputes in this area. Thus, starting from a preliminary analysis with regard to the protection of personal rights, we will analyse the different illicit behaviours that may occur as a result of the use of intelligent personal assistants, as well as the legal requirements for the liability that have to be verified and the possible need to implement new legislation on this area. In the second part of our study, we will examine the different legal means that can be used to resolve civil liability disputes arising from the use of intelligent personal assistants, with a particular focus on alternative means of dispute resolution.