In this demonstration, we present a system that automates regression testing for video games using automated planning techniques. Traditional test scripts are a common method for testing both video games and software in general. While effective, they require manual creation and frequent updates throughout development, making the process labor-intensive. Our system eliminates this burden by automatically generating and maintaining test scripts. The test engineer only needs to define the game's rules using the Planning Domain Definition Language (PDDL) and specify initial states and goals for individual test cases. This significantly reduces human effort while ensuring test scripts remain up to date. Additionally, our system integrates with game engine editors- supporting both Unity and Unreal to execute and evaluate test cases directly within the game. It collects detailed logs, telemetry data, and video recordings, allowing users to review test results efficiently.

Previous STRIPS domain model acquisition approaches that learn from state traces start with the names and parameters of the actions to be learned. Therefore their only task is to deduce the preconditions and effects of the given actions. In this work, we explore learning in situations when the parameters of learned actions are not provided. We define two levels of trace quality based on which information is provided and present an algorithm for each. In one level (L1), the states in the traces are labeled with action names, so we can deduce the number and names of the actions, but we still need to work out the number and types of parameters. In the other level (L2), the states are additionally labeled with objects that constitute the parameters of the corresponding grounded actions. Here we still need to deduce the types of the parameters in the learned actions. We experimentally evaluate the proposed algorithms and compare them with the state-of-the-art learning tool FAMA on a large collection of IPC benchmarks. The evaluation shows that our new algorithms are faster, can handle larger inputs and provide better results in terms of learning action models more similar to reference models.

In this paper, we propose a method and workflow for automating regression testing of certain video game aspects using automated planning and incremental action model learning techniques. The basic idea is to use detailed game logs and incremental action model learning techniques to maintain a formal model in the planning domain description language (PDDL) of the gameplay mechanics. The workflow enables efficient cooperation of game developers without any experience with PDDL or other formal systems and a person experienced with PDDL modeling but no game development skills. We describe the method and workflow in general and then demonstrate it on a concrete proof-of-concept example – a simple role-playing game provided as one of the tutorial projects in the popular game development engine Unity. This paper presents the first step towards minimizing or even eliminating the need for a modeling expert in the workflow, thus making automated planning accessible to a broader audience.

Previous STRIPS domain model acquisition approaches that learn from state traces start with the names and parameters of the actions to be learned. Therefore their only task is to deduce the preconditions and effects of the given actions. In this work, we explore learning in situations when the parameters of learned actions are not provided. We define two levels of trace quality based on which information is provided and present an algorithm for each. In one level (L1), the states in the traces are labeled with action names, so we can deduce the number and names of the actions, but we still need to work out the number and types of parameters. In the other level (L2), the states are additionally labeled with objects that constitute the parameters of the corresponding grounded actions. Here we still need to deduce the types of the parameters in the learned actions. We experimentally evaluate the proposed algorithms and compare them with the state-of-the-art learning tool FAMA on a large collection of IPC benchmarks. The evaluation shows that our new algorithms are faster, can handle larger inputs and provide better results in terms of learning action models more similar to reference models.

COGLE (COmmon Ground Learning and Explanation) is an explainable artificial intelligence (XAI) system for autonomous drones that deliver supplies in mountainous areas to field units. The drone missions have risks that vary with topography, flight decisions, and mission goals in a simulated environment. Users must determine which AI-controlled drone is better for a mission. Narrative explanations identify the advantages of a drone’s plan (“What?”) and reasons that the better drone is able to do them (“Why?”). Visual explanations highlight risks from obstacles that users may have overlooked (“Where?”). A model induction user study showed that post-decision explanations produced a small effect on the participants’ abilities to identify the better of two imperfect drones and their plans for a mission, but they did not teach participants to judge the multiple success factors in complex missions as well as the AI pilots. In a decision support variation of the task, users would receive pre-decision explanations to help them to decide when to trust the XAI’s decision. In a fielded XAI application, every drone available for a mission may lack some competencies. We created a proof-of-concept demonstration of automatic ways to combine knowledge from multiple imperfect AIs to get better solutions that the individual AIs do not find on their own. This paper reports on the research challenges, technical approach, and findings of the project and also reflects on the multidisciplinary journey that we took.

This editorial introduces several of the deployed applications that were described at the 2018 Innovative Applications of Artificial Intelligence conference, held in New Orleans, Louisiana, in February 2018.

Automatically staging characters in order to facilitate the performance and blocking of a scene in a virtual environment is a difficult task today. There is only a limited set of techniques used in practice. Some general methods include Behavior Markup Language (BML) and motion capture replay (the most popular); however they require either detailed technical knowledge or are not adaptable to different environmental configurations. In this work, we block and perform scenes with synthetic actors utilizing only a text-based, standard play-script as the primary input to the positioning of these characters in an environment. Using natural language processing techniques, we extract the annotated movements from the script, then add additional movements and adjustments from our rules engine built with theater, stage performance, and human interaction spatiotemporal relationships. In addition, we incorporate force-directed graph algorithms to adjust positions of the artificially intelligent (AI)-driven characters based on human-controlled character movements for interaction. These techniques have been quantitatively and qualitatively evaluated, revealing both similar blocking, and indistinguishably good performances from a human's perspective, when compared to an actual human performance.

A navigation mesh is composed of a listing of regions, which are well-defined convex groupings of traversable space and an additional listing describing connectivity. Traditionally, navigation meshes have been created either by hand or using some form of automated spatial decomposition algorithm that examines the obstructions present in the environment and then breaks down the area between them into as few regions as possible. Existing growth-based spatial decomposition algorithms took advantage of a postprocessing step to improve the quality of the resulting navigation mesh. The Wavefront algorithm generates fast, high-quality decompositions for use as navigation meshes via a quad-based expansion algorithm. Such decompositions have fewer small and degenerate regions that can interfere with character navigation. Additionally, since wavefront algorithm only grows one region at a time, there is less post processing that would normally be caused by multiple regions competing to fill the same convex area.

We present a series of mHealth applications and studies pursued as part of the Fittle+ project. This program of research has the dual aims of (1) bringing scalable evidence-based behavior-change interventions to mHealth and evaluating them and (2) developing theoretically based predictive models to better understand the dynamics of the impact of these interventions on achieving behavior-change goals. Our approach in the Fittle+ systems rests on the idea that to master the complex fabric of a new healthy lifestyle, one must weave together a new set of healthy habits that over-ride the old unhealthy habits. To achieve these aims, we have developed a series of mHealth platforms that provide scaffolding interventions: Behavior-change techniques and associated mHealth interactions (e.g., SMS reminders; chatbot dialogs; user interface functionality; etc.) that provide additional support to the acquisition and maintenance of healthy habits. We present experimental evidence collected so far for statistically significant improvements in behavior change in eating, exercise, and physical activity for the following scaffolding interventions: guided mastery, teaming, self-affirmation, and implementation intentions. We also present predictive computational ACT-R models of daily individual behavior goal success for data collected in guided mastery and implementation intention studies that address goal-striving and habit formation mechanisms.

Growing interest in eXplainable Artificial Intelligence (XAI) aims to make AI and machine learning more understandable to human users. However, most existing work focuses on new algorithms, and not on usability, practical interpretability and efficacy on real users. In this vision paper, we propose a new research area of eXplainable AI for Designers (XAID), specifically for game designers. By focusing on a specific user group, their needs and tasks, we propose a human-centered approach for facilitating game designers to co-create with AI/ML techniques through XAID. We illustrate our initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users' needs, and we identify key open challenges.

The 2018 AAAI Conference on Artificial Intelligence, the 2018 Innovative Applications of Artificial Intelligence, and the 2018 Symposium on Educational Advances in Artificial Intelligence were held February 2–7, 2018, at the Hilton New Orleans Riverside, New Orleans, Louisiana. This report, based on the prefaces contained in the AAAI‐18 proceedings and program, summarizes the events of the conference.

Although undergraduate enrollment in Computer Science has remained strong and seen substantial increases in the past decade, retention of majors remains a significant concern, particularly for students at the freshman and sophomore level that are tackling foundational courses on algorithms and data structures. In this work, we present BRIDGES, a software infrastructure designed to enable the creation of more engaging assignments in introductory data structures courses by providing students with a simplified API that allows them to populate their own data structure implementations with live, real-world, and interesting data sets, such as those from popular social networks (e.g., Twitter, Facebook). BRIDGES also provides the ability for students to create and explore {\em visualizations} of the execution of the data structures that they construct in their course assignments, which can promote better understanding of the data structure and its underlying algorithms; these visualizations can be easily shared via a weblink with peers, family, and instructional staff. In this paper, we present the BRIDGES system, its design, architecture and its use in our data structures course over two semesters.

This paper details the work of a seldom studied but growing population of members of grassroots, offline-project based groups. We aim to understand how these groups self-organize to enable a large number of volunteers to gather and "get things done," and identify design opportunities for technologies to support such work. By studying the work structure, we identified two types of members, regular and episodic participants, who differ in structural role, motivation, and type of work they do. We studied two key tasks: 1) project management, which is mostly done collaboratively by the regular participants; and 2) organization of work events-the project implementation, which involve many episodic participants. For both tasks, we report on common practices and tools that are currently used. We then discuss design implications and user requirements for developing specialized tools to support these tasks.

BACKGROUND:Novel methods of promoting self-monitoring and social support are needed to ensure long-term maintenance of behavior change. In this paper, we directly investigate the effects of group support in an exercise and nutrition program delivered by an mHealth application called Fittle.OBJECTIVE:Our first specific study aim was to explore whether social support improved adherence in wellness programs. Our second specific study aim was to assess whether media types (ePaper vs mobile) were associated with different levels of compliance and adherence to wellness programs. The third aim was to assess whether the use of an mHealth application led to positive changes to participants' eating behavior, physical activity, and stress level, compared to traditional paper-based programs.METHODS:A 2 × 2 (eg, Media: Mobile vs ePaper × Group Type: Team vs Solo) factorial design feasibility study was conducted. A sample of 124 volunteers who were interested in improving eating behavior, increasing physical activity, or reducing stress participated in this study. The study duration was 8 weeks. All groups were self-directed with no ongoing human input from the research team.RESULTS:Participants in ePaper conditions had higher attrition rates compared to participants in Mobile conditions, χ3(2)=9.96, P=.02 (N=124). Participants in Mobile conditions reported their compliance with a much higher frequency closer to the time of challenge activity completion (2-sample Kolmogorov-Smirnov test comparing distributions was highly significant-KS=0.33, P<.001 [N=63]). Participants in ePaper conditions had a much higher frequency of guessing while reporting as compared with those in Mobile conditions-χ1(2)=25.25, P<.001 (N=63). Together, these findings suggest that the mobile app allowed a more accurate method to report and track health behaviors over a longer period than traditional ePaper-based diaries or log books. There was a significant difference in the overall compliance score for Mobile-Solo (Mean [SD] 0.30 [0.39]) and Mobile-Team (Mean [SD] 0.49 [0.35]) conditions (t50.82=1.94, P=.05). This suggests that working in a team increased participants' overall compliance within Fittle. Survival analysis showed that participants assigned to Team conditions are 66% more likely to engage longer with mHealth app-based intervention than those assigned to the Solo condition. Overall, participants across all groups reported some positive changes in eating behavior, physical activity, and stress level; however, participants in the Mobile-Solo condition reported higher perceived stress levels at the end of the study.CONCLUSIONS:The team-based Fittle app is an acceptable and feasible wellness behavior change intervention and a full randomized controlled trial to investigate the efficacy of such an intervention is warranted.

FittleBot is virtual coach provided as part of a mobile application named Fittle that aims to provide users with social support and motivation for achieving the user's health and wellness goals. Fittle's wellness challenges are based around teams, where each team has its own FittleBot to provide personalized recommendations, support team building and provide information or tips. Here we present a quantitative analysis from a 2-week field study where we test new FittleBot strategies to increase FittleBot's effectiveness in building team community. Participants using the enhanced FittleBot improved compliance over the two weeks by 8.8% and increased their sense of community by 4%.

Positioning characters in virtual environments currently requires manual work and human intervention to complete. Many applications focus primarily on producing nonverbal behaviors and interacting one-on-one with humans. The problem is that most applications, especially games, are very interactive experiences. They introduce a human factor where a character (the human) may choose not to follow a predefined script, yet an author needs to be able to accommodate the unexpected movements when blocking their AI characters. Here, we look to our prior work on positioning characters in these types of virtual environments to create an AI Director to pre-block a play-script. In addition, we incorporate a force-directed graph component to assist with positioning the AI characters when there is a human-controlled character involved. Forcedirected graphs have been shown to position objects aesthetically for large and complex graphs. We rely upon this feature to assist with adjusting pre-defined play-script blocking to include the human-controlled character, making the human appear to be moving correctly even when they are not. Finally, we evaluate this approach based on occlusion and clustering analysis to show its effectiveness in balancing a production and incorporating a human-controlled character.