The national computing curriculum in Czechia was revised in 2021 to incorporate various topics, including fundamental principles of the internet and computer networks at the ISCED level 2 (age \sim11-15). However, schools face a shortage of age-appropriate teaching materials on this subject. To address this gap, we developed four model lessons and corresponding materials tailored for ISCED 2 students and teachers at two levels of difficulty. The primary objective of these lessons is to elucidate the structure and fundamental principles of the internet, building on prevalent student preconceptions. This work is grounded in the constructivist instructional framework known as Evocation - Realisation of Meaning - Reflection (ERR). The lessons were created and validated through design-based research conducted across six schools, involving 13 classes and a total of approximately 270 students. Pre-post-delayed testing revealed very large immediate improvements following the intervention ( d = 1.72, p < 0.001, n = 204) as well as large, sustained effects months later ( d = 1.10, p < 0.001, n = 59). This paper details the development, implementation, and evaluation of these lessons, providing a valuable resource for educators in various contexts.

Teaching the principles of how digital technologies work at the K-5 level is underexplored. We created six model lessons for children covering this topic as part of the newly updated Czech national computing curriculum. Here, we introduce these lessons. They can be viewed through the lenses of a constructivist educational framework, Evocation - Realization of Meaning - Reflection. Four lessons target younger learners (Grades ~2-4) and include topics such as storing and deleting data, data size and computer viruses, among others. Two lessons target older children (Grade ~4-5) and focus on the structure and functioning of the internet and digital footprints. The lessons are organized around probing child preconceptions about the lesson topics, showing brief animated videos, and introducing new concepts through instructional analogies, discussions and unplugged activities. The paper describes how the lessons were created and evaluated; discusses their structure along with sample activities and analogies; and presents lessons learnt and how our approach can be used by others. Altogether, the paper contributes by complementing existing reports on primary computing education.

Computer science education in the Czech Republic's primary school curriculum (ISCED 1) is now, similar to other countries, undergoing a transformation to respond current needs. This includes principles of how the Internet functions. Little is known about how prepared novice primary school teachers are for teaching this topic. Here, we have taken one step in addressing this issue by examining what preconceptions novice Czech primary school teachers have about how the Internet functions (N = 62; semi-structured interviews). Data are analysed using thematic and frequency analyses. Preliminary results suggest that teachers have many misconceptions about how the Internet works.

The revised Czech national computing curriculum for grades 6-9 entails the topic of how digital devices work. Up to date materials for teaching this topic are lacking in the Czech context. Our goal is to create such materials. As a first step, we mapped preconceptions of children from grades 6-9 about how a digital devices work and what hardware parts they comprise of (N = 53, semi-structured interviews). Preliminary analysis uncovered some preconceptions not discovered by existing literature. This poster presents these preconceptions.

The quality of high-level AI of nonplayer characters (NPCs) in commercial open-world games (OWGs) has been increasing during the past years. However, due to constraints specific to the game industry, this increase has been slow and it has been driven by larger budgets rather than adoption of new complex AI techniques. Most of the contemporary AI is still expressed as hard-coded scripts. The complexity and manageability of the script codebase is one of the key limiting factors for further AI improvements. In this paper, we address this issue. We presentbehavior objects(BO)—a general approach to development of NPC behaviors for large OWGs. BOs are inspired by object-oriented programming and extend the concept of smart objects. Our approach promotes encapsulation of data and code for multiple related behaviors in one place, hiding internal details and embedding intelligence in the environment. BOs are a natural abstraction of five different techniques that we have implemented to manage AI complexity in an upcoming AAA OWG. We report the details of the implementations in the context of behavior trees and the lessons learned during development. Our study should serve as an inspiration for AI architecture designers from both the academia and the industry.

A variety of agent programming languages have been proposed but only few comparative studies have been performed to evaluate the strengths and weaknesses of these languages. In order to gain a better understanding of features in and their use by programmers of these languages, we perform a study which compares the two languages GOAL and POSH. The study aims at advancing our knowledge of the benefits of using agentoriented languages and at contributing to the evolution of these languages. The main focus of the study is on the usability of both languages and the differences between novice and more advanced programmers that use either language. As POSH requires Java programming experience, we expected novice POSH programmers to perform better on the tasks than novice GOAL programmers whereas we hypothesized this difference would not be observed between more advanced programmers. However, results suggest that there is no significant difference. The study does suggest that general experience and tooling support can make a difference. Analysis of the tasks and the observations made about the use of the languages, moreover, suggests ways to improve the experimental design in such a way that differences in usability of the frameworks could be established.

Many contemporary computer games, notably action and role‐playing games, represent an interesting class of navigation‐intensive dynamic real‐time simulations inhabited by autonomous intelligent virtual agents (IVAs). Although higher level reasoning of IVAs in these domains seems suited for action planning, planning is not widely adopted in existing games and similar applications. Moreover, statistically rigorous study measuring performance of planners in decision making in a game‐like domain is missing. Here, five classical planners were connected to the virtual environment of Unreal Development Kit along with a planner for delete‐free domains (only positive preconditions and positive effects). Performance of IVAs employing those planners and IVAs with reactive architecture was measured on a class of game‐inspired test environments of various sizes and under different levels of external interference. The analysis has shown that planning agents outperform reactive agents if (i) the size of the problem is small or if (b) the environment changes are either hostile to the agent or infrequent. In delete‐free domains, specialized approaches are inferior to classical planners because the lower expressivity of delete‐free domains results in lower plan quality. These results can help to determine when planning is advantageous in games and for IVAs control in other dynamic real‐time environments.

As the graphical representation of computer games gradually becomes comparable to cinema, previously neglected non-graphical game aspects start to play an important role in maintaining believability of the game world. One such aspect is the behavior of non-player characters (NPCs), which should appear intelligent and purposeful in the ideal case or not completely stupid at the very least. A good and fast language to express the behaviors is vital for success. We present a visual agent language inspired by behavior trees that was approved for deployment at the core of AI system for an upcoming high-budget open world game.

Constructing beliavable behavior of non-player characters (NPCs) for large open worlds in computer games is a challenging application of AI. One of the greatest obstacles for practical game applications lie in managing the complexity of individual behaviors and in managing their development cycle. We propose the use of ``Smart areas'' to overcome these obstacles and allow for realistic simulation of NPCs day-to-day life and describe a particular implementation for an upcoming AAA game. For practical applications it is also vital to resolve usability issues and assess the productivity of the technology. We have conducted a qualitative study with 8 subjects that compares performance of working with Smart Areas as opposed to using the default AI tools. The study indicates that Smart areas are not difficult to understand, allow for substantial code reuse resulting in speedup in modification of existing behaviors and force good structuring of behavior code.

The autonomous agents community has been developing specific agent-oriented programming languages for more than two decades. Some of the languages have been considered by academia as possible tools for developing artificial intelligence (AI) for non-player characters in computer games. However, as most of the research related to the development of new AI languages within the agent community does not reach production quality, they are seldom adopted by the games industry. As our experience has shown, it is not only the actual language that matters. The toolchain supporting the language and its integration (or lack thereof) with a development environment can make or break the success of the language in practical applications. In this paper, we describe our methodology for evaluating AI languages and associated tools in practice based on controlled experiments with programmers and/or game designers. The methodology is demonstrated on our development and evaluation of SPOSH and yaPOSH high level agent behavior languages. We show that incomplete development support may prevent the tool from giving any benefit to developers at all. We also present our experience from transferring knowledge gained during yaPOSH development to actual AI design for an upcoming AAA game.