Stefan J. Johansson

Blekinge Institute of Technology | BTH · School of Computing (COM)

Inventeringar av fladdermöss utförs på många olika sätt, av en mängd olika aktörer. Metoderna som används varierar, så även syftena med inventeringarna. Det finns ett mindre antal fastställda och dokumenterade metoder, tex. artkartering och linjetaxering, som fyller vissa roller i arbetet med systematiska inventeringar, och de får betraktas som til...

The aim of the PsyIntEC project is to explore affective and cognitive modeling of humans in human-robot interaction (HRI) as a basis for behavioral adaptation. To achieve this we have explored human affective perception of relevant modalities in human-human and human-robot interaction on a collaborative problem-solving task using psychophysiologica...

The Turing Test Track of the Mario AI Championship focused on developing human-like controllers for a clone of the popular game Super Mario Bros. Competitors participated by submitting AI agents that imitate human playing style. This paper presents the rules of the competition, the software used, the voting interface, the scoring procedure, the sub...

Ms. Pac-Man, one of the classic arcade games has recently gained attention in the field of game AI through the yearly competitions of various kinds held at e.g. CIG. We have implemented an Influence Map-based controller for Ms. Pac-Man as well as for the ghosts within the game. We show that it is able to handle a number of various situations throug...

The Car Racing championship initiative is a platform for evaluating different car control solutions under competitive conditions. We introduce the novel combination of using artificial potential fields as the major control paradigm, and a multi-agent system to deal with the coordination of the different control interests. By combining fields for sh...

Computer controlled characters (NPCs) are important in any video game to make the game world interesting, give more depth to a game and make the game playable. In almost any game the player has to cooperate with, fight against or interact with NPCs. This is especially true for single-player games but NPCs are also important in most multi-player gam...

Real-time strategy games (RTS) are an active area of research as well as a popular branch of industrial game production, with high commercial interest. Although player satisfaction is the ultimate goal also for these games, they are usually too complex to come up with human-level AI that is not cheating. In consequence, for RTS games it is as desir...

We have developed a multi-agent platform as a complement to the existing healthcare system in a children's diabetic healthcare setting. It resolves problems related to the difficulty of collaboration between the stakeholders of the problem domain. In addition, it gives us an opportunity to support the decision-making of the stakeholders using multi...

Computer games in general, and Real Time Strategy games in particular is a challenging task for both AI research and game AI programmers. The player, or AI bot, must use its workers to gather resources. They must be spent wisely on structures such as barracks or factories, mobile units such as soldiers, workers and tanks. The constructed units...

Do players find it more enjoyable to win, than to play even matches? We have made a study of what a number of players expressed after playing against computer opponents of different kinds in an RTS game. There were two static computer opponents, one that was easily beaten, and one that was hard to beat, and three dynamic ones that adapted their str...

Bots for real time strategy (RTS) games provide a rich challenge to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. It is often the case that RTS AIs cheat in the sense that they get perfect information abou...

Bots for real-time strategy (RTS) games may be very challenging to implement. A bot controls a number of units that will have to navigate in a partially unknown environment, while at the same time avoid each other, search for enemies, and coordinate attacks to fight them down. Potential fields are a technique originating from the area of roboti...

Commercial computer games has become one of the largest industries in the area of entertainment. Real Time Strategy (Rts) based games is one of the most important among different types of computer games and is also considered to be a good research platform within Artificial Intelligence (Ai). There exists a number of algorithms that can deal with t...

Online Collectible Card Games is a relatively new genre of games that allow the players to collect cards, com-bine them into decks, and play the decks against oppo-nents through the Internet. Players get engaged in all these three levels of the game, and we relate these levels to the theories of what makes a computer game fun to play. The Eye of Ju...

Diabetic healthcare is characterized by the collaboration problem, which is manifested by problems of accessibility and interoperability. To improve the problem situation, we propose a Multi-agent Systems approach. The interactions among the diabetic healthcare actors are categorized on three levels: collaboration, coordination, and communication....

Bots for Real Time Strategy (RTS) games provide a rich challenge to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. Potential fields is a technique originating from the area of robotics where it is used in c...

Bots for Real Time Strategy (RTS) games provide a rich challenge to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. Potential fields is a technique originating from the area of robotics where it is used in c...

Bots for Real Time Strategy (RTS) games are challenging to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. Potential fields is a technique originating from the area of robotics where it is used in controllin...

A virtual plague is a process in which a behavior-affecting property spreads among characters in a Massively Multiplayer Online Game (MMOG). The MMOG individuals constitute a synthetic population, and the game can be seen as a form of interactive executable model for studying disease spread, albeit of a very special kind. To a game developer mainta...

Based on a classification of artificial societies and the identification of four different types of stakeholders in such societies, we investigate the potential of norm-governed behavior in different types of artificial societies. The basis of the analysis is the preferences of the stakeholders and how they influence the state of the society. A gen...

Several barriers to turn innovative ideas into growth-oriented businesses with a global outlook are identified. The Plug and Play Business concept is suggested to lower these barriers by making it possible for the inno- vator to plug into a network of actors or potential collaborators with automated entrepreneurial functions. A P2P paradigm with in...

We present a multi-agent architecture for playing the game of Risk which is a multi-player board game in which the players control armies and try to conquer the world through attacking each others territories. Our solution puts an agent in every territory, and let them negotiate about what actions to priori- tize in the phases of placing armies, at...

Computer programs able to play different kinds of games (aka bots) is a growing area of interest for the computer game industry as the demand for better skilled computerized opponents increase. We propose a general architecture of a Multi-agent System (Mas) based bot able to play complex board games and show that this solution is able to outperform...

Agent technology has not been accepted by software developers to the extent and rate anticipated. We believe that the lack of clarity and consistency regarding the terminology and its use may be a contributing cause for this. The dissemination of research results both to industry and related research disciplines becomes difficult. In addition, a ty...

While there is a broad theoretic foundation for creating computational players for two-player games, such as Chess, the multi-player domain is not as well explored. We make an attempt to apply a multi-agent approach to a multi-player game with huge search spaces and multiple adversaries, namely no-press Diplomacy. We tested our solution against oth...

We present a multi-agent architecture for playing the game of Risk which is a multi-player game where the players control armies and try to conquer the world through attacking each others territories. Our solution puts an agent in every territory, and let them negotiate about what actions to prioritize in the phases of placing armies, attack, and f...

Team Chaos" (formerly Team Sweden) is a multi-university team which has been competing in the 4-legged robot league of RoboCup since 1999. This paper shortly describes the Team Chaos entry for RoboCup 2004. The most distinctive points of our team are: (i) a general, prin- cipled architecture for autonomous systems, (ii) hierarchical fuzzy be- havio...

The strengths and weaknesses of agent-based approaches and mathematical optimization techniques are analyzed and compared. Their appropriateness for dynamic distributed resource allocation is evaluated. We conclude that their properties are complementary and that it seems fruitful to try to combine the approaches. Some suggestions of such hybrid sy...

Team Sweden" is a multi-university team competing in the Sony legged robot league of RoboCup since 1999. This paper shortly describes the preparation of the Team Sweden entry for RoboCup 2003. The main innovations with respect to the previous year are: (i) higher-stance walking style, (ii) cooperative ball perception, and (iii) dynamic role assignm...

We introduce the notion of Characteristic Distributions which is a way of representing information about the payoffs of different behaviors in a Multi-Agent System. We discuss how they can be used to simplify and structure the analysis of strategies and prove the existence of optimal environments, given a certain behavior, and that all behaviors pa...

Four different multi-agent system architectures for a dynamic resource allocation problem are presented and evaluated. Although all the architectures use three types of agents, i.e., quantifiers that act on the behalf the providers, alloca- tors that act on the behalf of the customers, and distributors that decide how the available resources should...

“Team Sweden” is the Swedish national team that entered the Sony legged robot league at the RoboCup2001 competition. The work was distributed over three universities in Sweden. This nationwide character has made the project organization particularly demanding, but has resulted in a rewarding cooperation experience, both scientific and human. The Te...

We introduce the notion of Characteristic Distributions which is a way of representing information about the payoffs of different behaviors in a Multi-agent System. We discuss how they can be used to simplify and structure the analysis of strategies and prove i) the existence of optimal environments, given a certain behavior, and ii) that all behav...

Introduction The notions of coalitions, norms and agents raise a lot of interesting questions. What makes agents form coalitions? When are new agents in a Multi-Agent System (mas) considered to be members in a coalition? And when does a coalition think it might be time for certain agents to leave? Can we design agents in such a way that they will c...

In game theory, iterated strategic games are considered harder to analyze than repeated ones. However, iterated games are in many cases more fit to describe the situation of artificial agents than repeated games. The reason being that they take into account previous actions of others, rather than just assigning each possible action a certain probab...

Introduction One important issue of agency is control. We must not be enticed to believe that the agents live in social and environmental isolation. They have been designed to ful ll the goals of their creators by interacting with its environment and other agents. Central to our point of view are the following concepts: De nition 1 An agent owner,...

Introduction The notions of norms, coalitions and agents raise a lot of interesting questions. What makes agents form coalitions? When are new agents in a MAS considered to be members in a coalition? And when does a coalition think it might be time for certain agents to leave? Can we design agents in such a way that they will continuously improve a...

A fundamental problem in multi agent systems is conflict resolution. A conflict occurs in general when the agents have to deal with conflicting goals, such as demands for shared, but limited resources. We investigate how game theory may be a helpful and efficient tool for examining a class of conflicts in multi agent systems and argue that paramete...

Stock markets to an ever-increasing extent allow for trading controlled by artificial agents, or more generally, program trading. For instance, the Swedish Securities Dealers Association finds that it has no objections to program trading, and already in 1992 declared that only the means to exploiting unlawful quotes manipulation, resulting from pro...

this paper, plus eight undergraduate students: M. Karlstrom and K. LeBlanc from Orebro University; M. Broberg, I. Bergmann, J. Johansson, P. Johnsson, R. Krejstrup, B.M. Lindberg, and B. Smeds from Blekinge Institute of Technology

Introduction "Team Sweden" is the Swedish national team that entered the Sony legged robot league at the RoboCup 2001 competition. The work was distributed over three universities in Sweden. This nationwide character has made the project organization particularly demanding, but has resulted in a rewarding cooperation experience, both scientific and...

“Team Sweden” is the Swedish national team that entered the Sony legged robot league at the RoboCup ’99 and RoboCup 2000 competitions. We had two main requirements in mind when preparing our entries: 1. The entry should effectively address the specific challenges present in this domain; in particular, it should be able to tolerate errors and imprec...

In autonomous robotics, so-called artificial potential fields are often used to plan and control the motion of a physical robot. In this paper, we propose to use an artificial electric field to address the problem or real time action selection in embodied, autonomous agents. We attach positive and negative electric charges to the relevant objects i...

We introduce generous, even-matched, and greedy strategies as concepts for analyzing games. A two person prisoner's dilemma game is described by the four outcomes (C,D), (C,C), (D,C), and (D,D). In a generous strategy the proportion of(C,D) is larger than that of (D,C), i.e. the probability of facing a defecting agent is larger than the probability...

A fundamental problem in multi agent systems is conflict resolution. A conflict occurs in general when the agents have to deal with inconsistent goals, such as a demand for shared resources. We investigate some theoretical game approaches as efficient methods to examine a class of conflicts in multi agent systems. In the first part of the paper, we...

A new approach to how to evolve integer recurrences using Genetic Programming (GP) is taken where the recurrences fix their base cases in accordance with the set of test cases instead of evolving them. A number of experiments indicate that this approach outperforms the old one as well as random search in finding non-trivial recurrences.

This report addresses the problem of synthesizing integer recurrences by genetic programming (GP). A number of alternative approaches were proposed and tested by running thousands of experiments. In particular the following aspects were investigated: approaches to base cases, population size, different fitness measures and superiority of GP over ra...

While there is a broad theoretic foundation for creating artificial intelligence based solutions for two-player games, such as Chess, the multi-player domain is not as well explored. We make an attempt to apply a multi-agent approach to a multi-player game with huge search spaces and multiple adversaries, namely no-press Diplomacy. We tested our so...

Bots for Real Time Strategy (RTS) games provide a rich challenge to implement. A bot controls a number of units that may have to navigate in a partially unknown environment, while at the same time search for enemies and coordinate attacks to fight them down. Potential fields is a technique originating from the area of robotics where it is used in c...

Agent technology enables the designers of computer based systems to construct software agents that are able to model attitudes. We present a frame-work in which these artifacts aim to express the preferences of both their designers and their owners. Just like human societies need rules, regula-tions, norms and social laws, in order to function,...