External factors are hard to model using a Markovian state in several real-world planning domains. Although planning can be difficult in such domains, it may be possible to exploit long-term dependencies between states of the environment during planning. We introduce weighted state scenarios to model long-term sequences of states, and we use a model based on a Partially Observable Markov Decision Process to reason about scenarios during planning. Experiments show that our model outperforms other methods for decision making in two real-world domains.

Hand-coded finite-state machines and behavior trees are the go-to techniques for artificial intelligence (AI) developers that want full control over their character's bearing. However, manually crafting behaviors for computer-controlled agents is a tedious and parameter-dependent task. From a high-level view, the process of designing agent AI by hand usually starts with the determination of a suitable set of action sequences. Once the AI developer has identified these sequences he merges them into a complete behavior by specifying appropriate transitions between them. Automated techniques, such as learning, tree search and planning, are on the other end of the AI toolset's spectrum. They do not require the manual definition of action sequences and adapt to parameter changes automatically. Yet AI developers are reluctant to incorporate them in games because of their performance footprint and lack of immediate designer control. We propose a method that, given the symbolic definition of a problem domain, can automatically extract a transparent behavior model from Goal-Oriented Action Planning (GOAP). The method first observes the behavior exhibited by GOAP in a Monte-Carlo simulation and then evolves a suitable behavior tree using a genetic algorithm. The generated behavior trees are comprehensible, refinable and as performant as hand-crafted ones.

This article describes the MultiAgent Decision Process (MADP) toolbox, a software library to support planning and learning for intelligent agents and multiagent systems in uncertain environments. Some of its key features are that it supports partially observable environments and stochastic transition models; has unified support for single- and multiagent systems; provides a large number of models for decision-theoretic decision making, including one-shot decision making (e.g., Bayesian games) and sequential decision making under various assumptions of observability and cooperation, such as Dec-POMDPs and POSGs; provides tools and parsers to quickly prototype new problems; provides an extensive range of planning and learning algorithms for single-and multiagent systems; and is written in C++ and designed to be extensible via the object-oriented paradigm.

In typical human interactions, nonverbal behaviors such as eye gazes and gestures serve to augment and reinforce spoken communication. To use similar nonverbal behaviors in human-robot interactions, researchers can apply artificial intelligence techniques such as machine learning, cognitive modeling, and computer vision. But knowledge of nonverbal behavior can also benefit artificial intelligence: because nonverbal communication can reveal human mental states, these behaviors provide additional input to artificial intelligence problems such as learning from demonstration, natural language processing, and motion planning. This article describes how nonverbal communication in HRI can benefit from AI techniques as well as how AI problems can use nonverbal communication in their solutions.

Emotions are a key element in all human interactions. It is well documented that individual- and group-level interactions have different emotional expressions and humans are by nature extremely competent in perceiving, adapting and reacting to them. However, when developing social robots, emotions are not so easy to cope with. In this paper we introduce the concept of emotional climate applied to human-robot interaction (HRI) to define a group-level emotional expression at a given time. By doing so, we move one step further in developing a new tool that deals with group emotions within HRI.

This paper explores the concept of Continuation Desire further by investigating the behavioral intent of players’ desire to keep playing. User experience is a complex, multifaceted topic, which is commonly studied through different aspects namely engagement, continuation desire, immersion, flow experience, motivation and enjoyment — yet it is difficult to measure. These concepts were conceptualized into different factors and thereby it was identified which of them are related. This resulted in a synthesized model that was based on the Theory of Planned Behavior model. This model takes into account the perceived user experience factors relevant for Continuation Desire and then attempts to predict players’ intention to continue playing. Structural Equation Modeling analysis was performed to validate the model and to predict the intention of continuation desire. At the same time, exploring why people continue playing, based on experiments using Candy Crush Saga, one of the most popular Free-to-Play mobile games worldwide. The findings indicate that motivation is an important factor of Continuation Desire in Free-to-Play mobile games, with engagement, enjoyment and flow being less important. This paper contributes an early work of a factor-based exploration of measuring user experience and their continuation desire.

An ongoing goal at the intersection of artificial intelligence In this paper, we briefly present initial work that has (AI), robotics, and human-robot interaction (HRI) is to create been done in the DIARC/ADE cognitive robotic architecture autonomous agents that can assist and interact with human (Schermerhorn et al. 2006; Kramer and Scheutz 2006) to enable teammates in natural and humanlike ways. This is a such a rejection and explanation mechanism. First we multifaceted challenge, involving both the development of discuss the theoretical considerations behind this challenge, an ever-expanding set of capabilities (both physical and algorithmic) specifically the conditions that must be met for a directive to such that robotic agents can autonomously engage be appropriately accepted. Next, we briefly present some of in a variety of useful tasks, as well as the development the explicit reasoning mechanisms developed in order to facilitate of interaction mechanisms (e.g.

Is it possible to conduct player modeling without any players? In this paper we use Monte-Carlo Tree Search-controlled procedural personas to simulate a range of decision making styles in the puzzle game MiniDungeons 2. The purpose is to provide a method for synthetic play testing of game levels with synthetic players based on designer intuition and experience. Five personas are constructed, representing five different decision making styles archetypal for the game. The personas vary solely in the weights of decision-making utilities that describe their valuation of a set affordances in MiniDungeons 2. By configuring these weights using designer expert knowledge, and passing the configurations directly to the MCTS algorithm, we make the personas exhibit a number of distinct decision making and play styles.

Natural language dialogue provides the opportunity for truly natural human-robot interaction. A robot participating in natural language dialogue must identify or create new representations for referenced entities if it is to discuss, reason about, or perform actions involving that entity, a capability known as reference resolution. In previous work we presented algorithms for resolving references occurring in definite noun phrases. In this paper we propose an algorithm for resolving references in a wider array of linguistic forms, using the Givenness Hierarchy.

With advancements in technology, smartphones can already serve as memory aids. Electronic calendars are of great use in time-based memory tasks. In this project, we enter the mixed reality realm for helping dementia patients. Dementia is a general term for a decline in mental ability severe enough to interfere with daily life. Memory loss is an example. Here, mixed reality refers to the merging of real and virtual worlds to produce new episodic memory visualisations where physical and digital objects co-exist and interact in real-time. Cognitive models are approximations of a patient's mental abilities and limitations involving conscious mental activities (such as thinking, understanding, learning, and remembering). External representations of episodic memory help patients and caregivers coordinate their actions with one another. We advocate distributed cognition, which involves the coordination between individuals, artefacts and the environment, in four main implementations of artificial intelligence technology in the Kognit storyboard: (1) speech dialogue and episodic memory retrieval; (2) monitoring medication management and tracking an elder's behaviour (e.g., drinking water); (3) eye tracking and modelling cognitive abilities; and (4) serious game development towards active memory training. We discuss the storyboard, use cases and usage scenarios, and some implementation details of cognitive models and mixed reality hardware for the patient. The purpose of future studies is to determine the extent to which cognitive enhancement technology can be used to decrease caregiver burden.