Naturalistic decision making

OBJECTIVE: This article describes the origins and contributions of the naturalistic decision making (NDM) research approach. BACKGROUND: NDM research emerged in the 1980s to study how people make decisions in real-world settings. Method: The findings and methods used by NDM researchers are presented along with their implications. RESULTS: The NDM framework emphasizes the role of experience in enabling people to rapidly categorize situations to make effective decisions. CONCLUSION: The NDM focus on field settings and its interest in complex conditions provide insights for human factors practitioners about ways to improve performance. APPLICATION: The NDM approach has been used to improve performance through revisions of military doctrine, training that is focused on decision requirements, and the development of information technologies to support decision making and related cognitive functions.     

Team situation assessment and information distribution

Described is the cooperative work of constructing team situation awareness within two teams of a military command and control unit. Specifically discussed is how the distributed cognitive and cooperative work of decision-making of the two teams is structured. The situation enabled two different ways of distributing information within the team: one serial and one parallel. One team chose the parallel information transfer, the other the serial one. Discussed is the interaction patterns that emerge in the respective teams and their consequences for situation assessment and situation awareness. The differences are then discussed in terms of means of sharing information. Some hypotheses for future research are also offered.     

Team situation assessment and information distribution

Described is the cooperative work of constructing team situation awareness within two teams of a military command and control unit. Specifically discussed is how the distributed cognitive and cooperative work of decision-making of the two teams is structured. The situation enabled two different ways of distributing information within the team: one serial and one parallel. One team chose the parallel information transfer, the other the serial one. Discussed is the interaction patterns that emerge in the respective teams and their consequences for situation assessment and situation awareness. The differences are then discussed in terms of means of sharing information. Some hypotheses for future research are also offered.     

The role of project management in ineffective decision making within Agile software development projects

Decision making in traditional software development lies with the project manager. In contrast, Agile software development teams are empowered to make decisions, while the role of project manager has changed from one of command and control (i.e. to make decisions and ensure they are implemented) to one of a facilitator. This article argues that decision making in software development is not characterised by a sequence of isolated or exclusive decisions; rather, decisions are inter-related, with each decision leading to further decisions, the chain of which often spans the entire duration of a project. Over this extended period, there are several potential factors that can negatively affect the efficacy of decision making by Agile teams. One of the findings of this exploratory longitudinal study is that the high level of empowerment of a cohesive software development team undertaking an Agile project may be one of these negative factors, as empowered, cohesive teams can exhibit problems such as groupthink or the Abilene Paradox. This article therefore argues that the role of project manager in Agile development initiatives needs to be reassessed, with project managers taking on the role of devil's advocate in the decision-making process.     

Decision-Making in Driver-Automation Shared Control: A Review and Perspectives

Shared control schemes allow a human driver to work with an automated driving agent in driver-vehicle systems while retaining the driver’s abilities to control. The human driver, as an essential agent in the driver-vehicle shared control systems, should be precisely modeled regarding their cognitive processes, control strategies, and decision-making processes. The interactive strategy design between drivers and automated driving agents brings an excellent challenge for human-centric driver assistance systems due to the inherent characteristics of humans. Many open-ended questions arise, such as what proper role of human drivers should act in a shared control scheme? How to make an intelligent decision capable of balancing the benefits of agents in shared control systems? Due to the advent of these attentions and questions, it is desirable to present a survey on the decision making between human drivers and highly automated vehicles, to understand their architectures, human driver modeling, and interaction strategies under the driver-vehicle shared schemes. Finally, we give a further discussion on the key future challenges and opportunities. They are likely to shape new potential research directions.      

Unanimously acceptable agreements for negotiation teams in unpredictable domains

A negotiation team is a set of agents with common and possibly also conflicting preferences that forms one of the parties of a negotiation. A negotiation team is involved in two decision making processes simultaneously, a negotiation with the opponents, and an intra-team process to decide on the moves to make in the negotiation. This article focuses on negotiation team decision making for circumstances that require unanimity of team decisions. Existing agent-based approaches only guarantee unanimity in teams negotiating in domains exclusively composed of predictable and compatible issues. This article presents a model for negotiation teams that guarantees unanimous team decisions in domains consisting of predictable and compatible, and alsounpredictable issues. Moreover, the article explores the influence of using opponent, and team member models in the proposing strategies that team members use. Experimental results show that the team benefits if team members employ Bayesian learning to model their teammates’ preferences.     

“Where’s Farah?”: Knowledge silos and information fusion by distributed collaborating teams

The Cognitively-Based Rapid Assessment Methodology (C-RAM) system manages multiple-user interactions as users work with multiple information sources. Further, it allows users to view, exchange, organize, and combine the information available and it facilitates group decision-making. Three-member teams, randomly assigned in either the (a) view others’ whiteboards or (b) cannot view others’ whiteboards conditions, completed an intelligence analysis and mission planning task. Each team member was given access to a virtual whiteboard populated with decision cards (DCards) containing intelligence information constrained to a specific area of expertise. DCards can be assessed (rated) for decision impact and importance and team members have access to all DCards regardless of experimental condition. Team members who can view their teammates’ whiteboards during collaborative activities achieve significantly higher performance. When compared to teams unable to view others’ whiteboards, they move their own DCards less frequently, add fewer additional DCards to their own whiteboards, and rate others’ DCards less frequently. Additionally, rating one’s own DCards is the only process positively related team performance.     

Control sharing in human-robot team interaction

The interaction between humans and robot teams is highly relevant in many application domains, for example in collaborative manufacturing, search and rescue, and logistics. It is well-known that humans and robots have complementary capabilities: Humans are excellent in reasoning and planning in unstructured environments, while robots are very good in performing tasks repetitively and precisely. In consequence, one of the key research questions is how to combine human and robot team decision making and task execution capabilities in order to exploit their complementary skills. From a controls perspective this question boils down to how control should be shared among them. This article surveys advances in human-robot team interaction with special attention devoted to control sharing methodologies. Additionally, aspects affecting the control sharing design, such as human behavior modeling, level of autonomy and human-machine interfaces are identified. Open problems and future research directions towards joint decision making and task execution in human-robot teams are discussed.     

Non-communicative multi-robot coordination in dynamic environments

Within a group of cooperating agents the decision making of an individual agent depends on the actions of the other agents. In dynamic environments, these dependencies will change rapidly as a result of the continuously changing state. Via a context-specific decomposition of the problem into smaller subproblems, coordination graphs offer scalable solutions to the problem of multiagent decision making. In this work, we apply coordination graphs to a continuous (robotic) domain by assigning roles to the agents and then coordinating the different roles. Moreover, we demonstrate that, with some additional assumptions, an agent can predict the actions of the other agents, rendering communication superfluous. We have successfully implemented the proposed method into our UvA Trilearn simulated robot soccer team which won the RoboCup-2003 World Championship in Padova, Italy.     

Using emotions for the development of human-agent societies

Human-agent societies refer to applications where virtual agents and humans coexist and interact transparently into a fully integrated environment. One of the most important aspects in this kind of applications is including emotional states of the agents (humans or not) in the decision-making process. In this sense, this paper presents the applicability of the JaCalIVE (Jason Cartago implemented intelligent virtual environment) framework for developing this kind of society. Specifically, the paper presents an ambient intelligence application where humans are immersed into a system that extracts and analyzes the emotional state of a human group. A social emotional model is employed to try to maximize the welfare of those humans by playing the most appropriate music in every moment.     

A general computational recognition primed decision model with multi-agent rescue simulation benchmark

Analytical decision making strategies rely on weighing pros and cons of multiple options in an unbounded rationality manner. Contrary to these strategies, recognition primed decision (RPD) model which is a primary naturalistic decision making (NDM) approach assumes that experienced and professional decision makers when encounter problems in real operating conditions are able to use their previous experiences and trainings in order to diagnose the problem, recall the appropriate solution, evaluate it mentally, and implement it to handle the problem in a satisficing manner. In this paper, a computational form of RPD, now called C-RPD, is presented. Unified Modeling Language was used as a modeling language to represent the proposed C-RPD model in order to make the implementation easy and obvious. To execute the model, RoboCup Rescue agent simulation environment, which is one of the best and the most famous complex and multi-agent large-scale environments, was selected. The environment simulates the incidence of fire and earthquakes in urban areas where it is the duty of the police forces, firefighters and ambulance teams to control the crisis. Firefighters of SOS team are first modeled and implemented by utilizing C-RPD and then the system is trained using an expert’s experience. There are two evaluations. To find out the convergence of different versions developed during experience adding, some of the developed versions are chosen and evaluated on seven maps. Results show performance improvements. The SOS team ranked first in an official world championship and three official open tournaments.     

Human factors in the guidance of uninhabited vehicles: oxymoron or tautology?

Today’s automation is typically tied into work processes as tools actively supporting the human operator in fulfilling certain well-defined sub-tasks. The human operator is in the role of the high-end decision component determining and supervising the work process. With emergent technology highly automated work systems can be beneficial on the one hand, but automation may as well cause problems on its own. A new way of introducing automation into work systems shall be advocated by this article overcoming the classical pitfalls of automation and simultaneously taking the benefit as wanted. This shall be achieved by so-called cognitive automation, i.e. providing human-like problem-solving, decision-making and knowledge processing capabilities to machines in order to obtain goal-directed behaviour and effective operator assistance. A key feature of cognitive automation is the ability to create its own comprehensive representation of the current situation and to provide reasonable action. By additionally providing full knowledge of the prime work objectives to the automation it will be enabled to co-operate with the human operator in supervision and decision tasks, then being intelligent machine assistants for the human operator in his work place. Such assistant systems understand the work objective and will be heading for the achievement of the overall desired work result. They will understand the situation (e.g. opportunities, conflicts) and actions of team members—whether humans or assistant systems—and will pursue goals for co-operation and co-ordination (e.g. task coverage, avoidance of redundancy or team member overcharge). On the other hand, cognitive automation can be emerged towards being highly automated intelligent agents in charge of certain supportive tasks to be performed in a semi-autonomous mode. These cognitive semi-autonomous systems and the cognitive assistants shall be denoted as the two faces of dual-mode cognitive automation (Onken and Schulte, in preparation).     

基于影响图的传球训练策略的实现

影响图是决策问题的图形表示,利用影响图可以有效地解决智能Agent的行为选择,而传球问题就是球员Agent选择传球速度和角度的问题。建立了一个基于影响图的传球模型,并根据该模型创建一个评价传球效果的效用函数;然后利用由教练程序改写的记录员程序来记录数据,并进行统计得到效用函数中的概率值;最后通过训练得到效用函数中系数的值,并利用此效用函数作传球训练。训练结果表明该效用函数是可信的。     

Adaptive learning algorithm of self-organizing teams

In order to improve the ability of achieving good performance in self-organizing teams, this paper presents a self-adaptive learning algorithm for team members. Members of the self-organizing teams are simulated by agents. In the virtual self-organizing team, agents adapt their knowledge according to cooperative principles. The self-adaptive learning algorithm is approached to learn from other agents with minimal costs and improve the performance of the self-organizing team. In the algorithm, agents learn how to behave (choose different game strategies) and how much to think about how to behave (choose the learning radius). The virtual team is self-adaptively improved according to the strategies’ ability of generating better quality solutions in the past generations. Six basic experiments are manipulated to prove the validity of the adaptive learning algorithm. It is found that the adaptive learning algorithm often causes agents to converge to optimal actions, based on agents’ continually updated cognitive maps of how actions influence the performance of the virtual self-organizing team. This paper considered the influence of relationships in self-organizing teams over existing works. It is illustrated that the adaptive learning algorithm is beneficial to both the development of self-organizing teams and the performance of the individual agent.     

伦理智能体及其设计:现状和展望

智能体一直是人工智能的主要研究领域之一,任何独立的能够同环境交互并自主决策的实体都可以抽象为智能体.随着人工智能从计算智能到感知智能,再到认知智能的发展,智能体已逐步渗透到无人驾驶、服务机器人、智能家居、智慧医疗、战争武器等人类生活密切相关的领域.这些应用中,智能体与环境、尤其是与人类和社会的交互愈来愈突出,其中的伦理...     

Effects of sleep loss on team decision making: motivational loss or motivational gain?

OBJECTIVE: To examine the effects of 30 hr of sleep loss and continuous cognitive work on performance in a distributed team decision-making environment. BACKGROUND: To date, only a few studies have examined the effect of sleep loss on distributed team performance, and only one other to our knowledge has examined the relationship between sleep loss and social-motivational aspects of teams (Hoeksema-van Orden, Gaillard, & Buunk, 1998). METHOD: Sixteen teams participated; each comprised 4 members. Three team members made threat assessments on a military surveillance task and then forwarded their judgments electronically to a team leader, who made a final assessment on behalf of the team. RESULTS: Sleep loss had an antagonistic effect on team decision-making accuracy and decision time. However, the performance loss associated with fatigue attributable to sleep loss was mediated by being part of a team, as compared with performing the same task individually - that is, we found evidence of a "motivational gain" effect in these sleepy teams. We compare these results with those of Hoeksema-van Orden et al. (1998), who found clear evidence of a "social loafing" effect in sleepy teams. CONCLUSION: The divergent results are discussed in the context of the collective effort model (Karau & Williams, 1993) and are attributable in part to a difference between independent and interdependent team tasks. APPLICATION: The issues and findings have implications for a wide range of distributed, collaborative work environments, such as military network-enabled operations.     

Supporting decision making process with “ideal” software agents - What do business executives want?

According to Simon’s (1977) decision making theory, intelligence is the first and most important phase in the decision making process. With the escalation of information resources available to business executives, it is becoming imperative to explore the potential and challenges of using agent-based systems to support the intelligence phase of decision-making. This research examines UK executives’ perceptions of using agent-based support systems and the criteria for design and development of their “ideal” intelligent software agents. The study adopted an inductive approach using focus groups to generate a preliminary set of design criteria of “ideal” agents. It then followed a deductive approach using semi-structured interviews to validate and enhance the criteria. This qualitative research has generated unique insights into executives’ perceptions of the design and use of agent-based support systems. The systematic content analysis of qualitative data led to the proposal and validation of design criteria at three levels. The findings revealed the most desirable criteria for agent based support systems from the end users’ point view. The design criteria can be used not only to guide intelligent agent system design but also system evaluation.     

The effects of agent activeness and cooperativeness on team decision efficiency: A computational simulation study using Team-Soar

Within an organizational context, an agent type reflects the behavioral tendency that a member might employ across tasks. Until now, however, the impacts of agent types on team performance are not well understood. To address this issue, this study examines the relationships of agent activeness and cooperativeness with team decision efficiency at different degrees of information redundancy by using a team model consisting of four AI agents. This study presents the team model called “Team-Soar” and describes how the model implements agent activeness at two levels (active and passive) and agent cooperativeness at three levels (cooperative, neutral, and selfish). Then a computational simulation experiment is described. Results of the simulation indicate that the impacts of the agent type depend on the amount of information to be processed and active style boosts the effects of agent cooperativeness on team efficiency. The results also indicate that active agents do not always contribute team efficiency more than passive agents.