Papers by Karel van den Bosch
Serious games allow for adaptive and personalised forms of training; the nature and timing of lea... more Serious games allow for adaptive and personalised forms of training; the nature and timing of learning activities can be tailored to the trainee's needs and interests. Autonomous game-based training requires for the automatic selection of appropriate exercises for an individual trainee. This paper presents a framework for an automated scenario generation system. The underlying notion is that a learning experience is defined by the objects and agents that inhabit the training environment. Our system uses automated planning to assess the behaviour required to achieve the (personalised) training objective. It then generates a scenario by selecting semantically annotated (or 'smart') objects and by assigning goals to the virtual characters. The resulting situations trigger the trainee to execute the desired behaviour. To test the framework, a prototype has been developed to train the First Aid treatment of burns. Experienced instructors evaluated scenarios written by three types of authors: the prototype, first-aid experts, and laymen. The prototype produced scenarios that were at least as good as laymen scenarios. First-aid experts seemed the best scenario writers, although differences were not significant. It is concluded that combining automated planning, smart objects, and virtual agent behaviour, is a promising approach to automated scenario generation.
Serious games allow for adaptive and personalised forms of training; the nature and timing of lea... more Serious games allow for adaptive and personalised forms of training; the nature and timing of learning activities can be tailored to the trainee’s needs and interests. Autonomous game-based training requires for the automatic selection of appropriate exercises for an individual trainee. This paper presents a framework for an automated scenario generation system. The underlying notion is that a learning experience is defined by the objects and agents that inhabit the training environment. Our system uses automated planning to assess the behaviour required to achieve the (personalised) training objective. It then generates a scenario by selecting semantically annotated (or ‘smart’) objects and by assigning goals to the virtual characters. The resulting situations trigger the trainee to execute the desired behaviour. To test the framework, a prototype has been developed to train the First Aid treatment of burns. Experienced instructors evaluated scenarios written by three types of auth...
International Journal of Technology Enhanced Learning, 2014
ABSTRACT An intelligent system for automated scenario-based training (SBT) needs knowledge about ... more ABSTRACT An intelligent system for automated scenario-based training (SBT) needs knowledge about the training domain, events taking place in the simulated environment, the behaviour of the participating characters, and teaching strategies for effective learning. This knowledge base should be theoretically sound and should represent the information in a generic, consistent, and unambiguous manner. Currently, there is no such knowledge base. This paper investigates the declarative knowledge needed for a system to reason about training and to make intelligent teaching decisions. A frame-based approach was used to model the identified knowledge in an ontology. The ontology specifies the core concepts of SBT and their relationships, and is applicable across training domains and applications. The ontology was used to develop a critical component of SBT: the scenario generator. It was found that the ontology enabled the scenario generator to develop scenarios that fitted the learning needs and skill level of the trainee. The presented work is an important step towards automated scenario-based training systems.
Computers & Education, 2014
ABSTRACT
Cognitive models can be used to generate the behavior of virtual players in simulation-based trai... more Cognitive models can be used to generate the behavior of virtual players in simulation-based training systems. To learn from such training, the virtual players must display realistic human behavior, and trainees need to understand why the other players behave the way they do. This understanding can be achieved by explaining the underlying reasons for the virtual players' behavior. In this paper, it is discussed how to design cognitive models in such a way that they are able to explain the behavior they generate. Three users studies were carried out to assess what type of explanations are useful for training, and how that relates to cognitive model design. Several guidelines for developing explainable cognitive models are proposed.
Cognitive biases and heuristics are pervasive simplifications and distortions in judgement and re... more Cognitive biases and heuristics are pervasive simplifications and distortions in judgement and reasoning that systematically affect human decision making. Knowledge in this area may enable us to foresee and reduce detrimental effects of biases or to influence others more effectively. We therefore performed a literature study to assess the influence of personal characteristics (cognitive abilities, expertise, personality, cultural background) on the occurrence of cognitive biases. We found that each of the aforementioned factors can affect cognitive biases, though not much is known about the effects of culture. Also, factors that appear to reduce a cognitive bias may in fact mitigate (suppress or override) its behavioral effect rather than preventing the bias from occurring at all. The general picture that arises is that bias susceptibility and the occurrence of biases depend on thinking style (heuristic versus deliberate), where thinking style is associated with an individual " s personal characteristics. In general, biases are reduced when a deliberate (analytical) thinking style is applied. However, whether a specific (heuristic or deliberate) thinking style actually reduces or enhances a given type of bias also depends on the context.
Expert Opinion on Drug Safety, 2012
Serious games enable trainees to practice independently of school, staff, and fellow students. Th... more Serious games enable trainees to practice independently of school, staff, and fellow students. This is important as amount of practice directly relates to training efficacy. It is also known that personalized guidance elevates the benefits of training. How to achieve automated guidance, for example to be used in serious games, is a yet unsolved issue. This paper uses the situated
Communications in Computer and Information Science, 2008
Ambient systems that explain their actions promote the user's understanding as they give the user... more Ambient systems that explain their actions promote the user's understanding as they give the user more insight in the effects of their behavior on the environment. In order to provide individualized intelligent explanations, we need not only to evaluate a user's observable behavior, but we also need to make sense of the underlying beliefs, intentions and strategies. In this paper we argue for the need of intelligent explanations, identify the requirements of such explanations, propose a method to achieve generation of intelligent explanations, and report on a prototype in the training of naval situation assessment and decision making. We discuss the implications of intelligent explanations in training and set the agenda for future research.
Public reporting burden for this collection of information is estimated to average 1 hour per res... more Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing this collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188), 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS.
Nakano Y Et Al Proceedings of the Inteligent Virtual Agents Held at Santa Cruz Ca 218 230, Sep 12, 2012
In this paper we test the hypothesis that Virtual Reality (VR) negotiation training positively in... more In this paper we test the hypothesis that Virtual Reality (VR) negotiation training positively influences negotiation skill and knowledge. We discuss the design of the VR training. Then, we present the results of a between subject experiment (n=42) with three experimental conditions (control, training once, repeated training) investigating learning effects on subjects' negotiation skill and knowledge. In our case negotiation skill consists of negotiation outcome (final bid utility) and conversation skill (exploratory conversational choices in VR scenario), and negotiation knowledge is the subjects' quality of reflection upon filmed behavior of two negotiating actors. Our results confirm the hypothesis. We found significant effects of training on conversation skill and negotiation knowledge. We found a marginally significant effect of training on negotation outcome. As the effect of training on negotiation outcome was marginally significant and only present when controlling for overshadowing effects of the act of reflecting, we postulate that other learning approaches (e.g., instruction) are needed for trainees to use the information gained during the joint exploration phase of a negotiation for the construction of a bid. Our results are particularly important given the sparse availability of experimental studies that show learning effects of VR negotiation training, and gives additional support to those studies that do report possitive effects such as with the BiLAT system.
Web Intelligence and Agent Systems, Jul 1, 2012
Virtual training systems with intelligent agents provide an effective means to train people for c... more Virtual training systems with intelligent agents provide an effective means to train people for complex, dynamic tasks like crisis management or firefighting. For successful training, intelligent virtual agents should be able to show believable behavior, adapt their behavior to the trainee's performance and give useful explanations about their behavior. Agents can provide more believable behavior and explanations if they, besides their own, take the assumed knowledge and intentions of other players in the scenario into account. This paper proposes two ways to model agents with a theory of mind, i.e. equip them with the ability to ascribe mental concepts such as knowledge and intentions to others. The first theory of mind model is based on theory-theory (TT) and the second on simulation theory (ST). In a simulation study, agents with no theory of mind, a TT-based theory of mind, and an ST-based theory of mind are compared. The results show that agents with a theory of mind are preferred over agents with no theory of mind, and that, regarding agent development, the ST model has advantages over the TT model.
The aim of the studies undertaken for this dissertation was to investigate: (a) whether critical ... more The aim of the studies undertaken for this dissertation was to investigate: (a) whether critical thinking instruction benefits transfer of complex judgment skills, (b) the effects of random and blocked practice schedules on learning, retention and transfer of complex judgment skills and (c) the effects of critical thinking prompts in random and blocked practice schedules. The studies Two field experiments (N=16, N=16) were undertaken to determine whether critical thinking instruction (critical thinking, control) yields better performance in complex judgment tasks. In six exercises of one hour, students were taught military command and control. During near and far transfer test, students judgment performance was evaluated by experts who were not informed of the experimental manipulation. The results showed a benefit of critical thinking instruction, especially for the far transfer test. The effects of practice schedule (random, blocked) on retention (study 1) and near transfer (study 2) of complex judgment skills were studied in two laboratory experiments (N=54, N=64). Random practice yielded better retention and improved transfer performance, without having a detrimental effect of performance during learning. The final study involved a 2 x 3 factorial experiment (N = 120) with the factors practice schedule (random, blocked) and critical thinking prompts (proactive, retrospective, none). Here, a blocked schedule led to better performance than random practice during learning, but not on the transfer test, where a random schedule was beneficial. An interaction effect was also found: whereas retrospective critical thinking prompts have surplus value in a random schedule, transfer test performance following a blocked schedule is enhanced through proactive critical thinking prompts. Conclusion Critical thinking instruction teaches students a better judgment strategy and enhances understanding of the domain. Furthermore, with a correct timing of critical thinking prompts, not only random but also blocked practice schedules can greatly enhance learning and transfer performance.
To understand emergent processes in multi-agent-based simulations it is important to study the gl... more To understand emergent processes in multi-agent-based simulations it is important to study the global processes in a simulation as well as the processes on the agent level. The behavior of individual agents is easier to understand when they are able to explain their own behavior. In this paper, a theoretical framework for explaining agent behavior is proposed. By distinguishing different types and contexts of explanations, the framework aims to support the development of explainable agents. The framework is based on an examination of explanation literature, and experiences with developing explainable agents for virtual training. The use of the framework is illustrated by an example about the development of a negotiation agent.
Journal of Artificial Societies and Social Simulation, 2010
Several strategies are used to explain emergent interaction patterns in agent-based simulations. ... more Several strategies are used to explain emergent interaction patterns in agent-based simulations. A distinction can be made between simulations in which the agents just behave in a reactive way, and simulations involving agents with also pro-active (goal-directed) behavior. Pro-active behavior is more variable and harder to predict than reactive behavior, and therefore it might be harder to explain. However, the approach presented in this paper tries to make advantage of the agents' pro-activeness by using it to explain their behavior. The aggregation of the agents' explanations form a basis for explaining the simulation as a whole. In this paper, an agent model that is able to generate (pro-active) behavior and explanations about that behavior is introduced, and the implementation of the model is discussed. Examples show how the link between behavior generation and explanation in the model can contribute to the explanation of a simulation.
Military missions are more and more focused upon peace enforcing operations in regional conflicts... more Military missions are more and more focused upon peace enforcing operations in regional conflicts. There is often uncertainty about the intentions, capabilities and strategies of the parties involved. Successful operations under such unstable and complex conditions require competent commanders and staff personnel.
Helsdingen, A. S., & Van den Bosch, K. (2009). Learning to make sense. Paper presented at the Cog... more Helsdingen, A. S., & Van den Bosch, K. (2009). Learning to make sense. Paper presented at the Cognitive Systems with Interactive sensors conference in Paris. November, 16-18, 2009, Paris, France.
Explanation-aware Computing, 2008
Instructors play a major role in many of the current vir- tual training systems. Consequently, ei... more Instructors play a major role in many of the current vir- tual training systems. Consequently, either many instructors per trainee are needed, which is expensive, or single instructors perform highly de- manding tasks, which might lead to suboptimal training. To solve this problem, this paper proposes a cognitive model that not only generates the behaviour of virtual characters, but also
Virtual training systems with intelligent agents are often used to prepare people who have to act... more Virtual training systems with intelligent agents are often used to prepare people who have to act in incidents or crisis situations. Literature tells that typical human mistakes in incidents and crises involve situations in which people make false assumptions about other people's knowledge or inten- tions. To develop a virtual training system in which cor- rectly estimating others' knowledge and
Uploads
Papers by Karel van den Bosch