This paper presents an exploratory study conducted to understand how audio-visual prompts are understood by people on an emotional level as a first step towards the more challenging task of designing emotionally aligned prompts for persons with cognitive disabilities such as Alzheimer’s disease and related dementias (ADRD). Persons with ADRD often need assistance from a caregiver to complete daily living activities such as washing hands, making food, or getting dressed. Artificially intelligent systems have been developed that can assist in such situations. This paper presents a set of prompt videos of a virtual human ‘Rachel’, wherein she expressively communicates prompts at each step of a simple hand washing task, with various human-like emotions and behaviors. A user study was conducted for 30 such videos with respect to three basic and important dimensions of emotional experience: evaluation, potency, and activity. The results show that, while people generally agree on the evaluation (valence: good/bad) of a prompt, consensus about power and activity is not as socially homogeneous. Our long term aim is to enhance such systems by delivering automated prompts that are emotionally aligned with individuals in order to help with prompt adherence and with long-term adoption.

In (Bouchard, Bouchard, and Bouzouane 2012), guidelines While the design of smart environments dedicated to people to build the software architecture of a smart home system with disabilities involves many challenges, like blending are presented. Such a software follows a loop-based execution, unobtrusively into the home environment (Novak, Binas, depicting the same execution principle, allowing the and Jakab 2012), recognizing the ongoing inhabitant activity use of a Reconfiguration controller task.

We present a Companion-based Ambient Robust INtelliGence (CARING) system, for communication with, and support of, clients with Traumatic brain injury (TBI) or Amyotrophic Lateral Sclerosis (ALS). A central component of this system is an artificial companion, combined with a range of elements for ambient intelligence. The companion acts as a personalized intermediary for multi-party communication between the client, the environment (e.g. a Smart Home), caregivers and health professionals. CARING is based on tightly coupled systems drawing from natural language processing, speech recognition and adaptation, deep language understanding and constraint-based knowledge representation and reasoning. A major innovation of the system is its ability to adapt and accommodate different interfaces associated with different client capabilities and needs. The system will use, as a proxy, different interaction requirements of clients (e.g., Brain-Computer Interfaces) at different stages of ALS progression and with different types of TBI impairments. Ultimately, this technology is expected to improve the quality of life for clients through conversation with a computer.

Learning to provide appropriate assistance to people indifferent situations is an extremely important, but insufficientlyinvestigated machine learning task. Applications includehuman-robot and human-computer interactions settings to maximizing the benefits of assistive technologies. Three key challenges must be overcome to appropriately address this task: Complexity: the space of possible assistive policies can be very large, making many existing methods (e.g., fromreinforcement learning) too data inefficient to be practical. Noise and misspecification: observed human behavior is often noisy and parametric formulations that reduce complexity will typically suffer from model misspecification,leading to unboundedly sub-optimal assistance. Biasedness: data available for learning a model is biased by previously provided assistive actions, violating the typical assumptions of supervised learning. We develop a general framework for learning to assist in single intervention settings. The framework narrows the search for effective assistance by viewing previous behavior under assistance through a restricted set of statistics. Assistive policies for the worst-case context-assistance-outcome relationships satisfying these statistics are obtained. We embed the problem of learning how to assist users in cursor based target pointing tasks into this framework and outline its usage.

As artificially intelligent systems grow in intelligence and capability, some of their available options may allow them to resist intervention by their programmers. We call an AI system "corrigible" if it cooperates with what its creators regard as a corrective intervention, despite default incentives for rational agents to resist attempts to shut them down or modify their preferences. We introduce the notion of corrigibility and analyze utility functions that attempt to make an agent shut down safely if a shutdown button is pressed, while avoiding incentives to prevent the button from being pressed or cause the button to be pressed, and while ensuring propagation of the shutdown behavior as it creates new subsystems or self-modifies. While some proposals are interesting, none have yet been demonstrated to satisfy all of our intuitive desiderata, leaving this simple problem in corrigibility wide-open.

Under the auspices of “being green,” we have given our printed word over to a cyber-medium that cannot be touched or felt or folded. Our information is as volatile as the authority protecting our storage devices. Eliminating a book or changing its text can be done by literally pressing a button -- without a fire or an erasure marking, without smoke, without evidence. Our data is ephemeral along with the web in which we weave it. This paper considers the current ease of censorship, and that the non-permanence of data and links can wreak havoc on our societal infra-structure if the wrong entities (human or machine) with the wrong motives have the control to determine its fate.

Hutter's universal artificial intelligence (AI) showed how to define future AI systems by mathematical equations. Here we adapt those equations to define a self-modeling framework, where AI systems learn models of their own calculations of future values. Hutter discussed the possibility that AI agents may maximize rewards by corrupting the source of rewards in the environment. Here we propose a way to avoid such corruption in the self-modeling framework. This paper fits in the context of my book Ethical Artificial Intelligence.

Given the fast rise of increasingly autonomous artificial agents and robots, a key acceptability criterion will be the possible moral implications of their actions. In particular, intelligent persuasive systems (systems designed to influence humans via communication) constitute a highly sensitive topic because of their intrinsically social nature. Still, ethical studies in this area are rare and tend to focus on the output of the required action. Instead, this work focuses on the persuasive acts themselves (e.g. “is it morally acceptable that a machine lies or appeals to the emotions of a person to persuade her, even if for a good end?”). Exploiting a behavioral approach, based on human assessment of moral dilemmas – i.e. without any prior assumption of underlying ethical theories – this paper reports on a set of experiments. These experiments address the type of persuader (human or machine), the strategies adopted (purely argumentative, appeal to positive emotions, appeal to negative emotions, lie) and the circumstances. Findings display no differences due to the agent, mild acceptability for persuasion and reveal that truth-conditional reasoning (i.e. argument validity) is a significant dimension affecting subjects’ judgment. Some implications for the design of intelligent persuasive systems are discussed.

Autonomy and agency are a central property in robotic systems, human-machine interfaces, e-business, ambient intelligence and assisted living applications. As the complexity of the situations the autonomous agents may encounter in such contexts is increasing, the decisions those agents make must integrate new issues, e.g. decisions involving contextual ethical considerations. Consequently contributions have proposed recommendations, advice or hard-wired ethical principles for systems of autonomous agents. However, socio-technical systems are more and more open and decentralized, and involve autonomous artificial agents interacting with other agents, human operators or users. For such systems, novel and original methods are needed to address contextual ethical decision-making, as decisions are likely to interfere with one another. This paper aims at presenting the ETHICAA project (Ethics and Autonomous Agents) whose objective is to define what should be an autonomous entity that could manage ethical conflicts. As a first proposal, we present various practical case studies of ethical conflicts and highlight what their main system and decision features are.

Coding values (or preferences) directly into an artificial agent is a very challenging task, while value selection (or value-learning, or value-loading) allows agents to learn values from their programmers, other humans or their environments in an interactive way. However, there is a conflict between agents learning their future values and following their current values, which motivates agents to manipulate the value selection process. This paper establishes the conditions under which motivated value selection is an issue for some types of agents, and presents an example of an `indifferent' agent that avoids it entirely. This poses and solves an issue which has not to the author's knowledge been formally addressed in the literature.