An Explainable Artificial Intelligence System for Small-unit Tactical Behavior

By Michael van Lent, W. Fisher, Michael Mancuso. 2004

301 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, methodology): “In addition, several research groups have applied many of the explanation approaches of the earlier expert systems to agent-based systems (Johnson, 1994; Van Lent et al., 2004).”
Metrics for Explainable AI: Challenges and Prospects (2018, background): “In discussing early medical diagnosis systems, van Lent et al (2004) stated, “Early on the developers of these systems realized that doctors weren’t willing to accept the expert system’s diagnosis on faith” (p. 904), which led to development of the first explanation-based AI systems.”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “[20], to describe the ability of their system to explain the behavior of AI-controlled entities in simulation games application.”
Multimodal Explanations: Justifying Decisions and Pointing to the Evidence (2018, background): “, medical [31] and feedback for teaching programs [19, 32, 9]).”
Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations (2017, background): “Explainable AI has been explored in the context of ad-hoc techniques for transforming simulation logs to explanations [17], intelligent tutoring systems [3], transforming AI plans into natural language [16], and translating multiagent communication policies into natural language [1].”
Grounding Visual Explanations (2018, methodology): “Early textual explanation models are applied to medical images [25] and developed as a feedback for teaching programs [12,27,3].”
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (2016, background): “Early textual explanation models span a variety of applications (e.g., medical [32] and feedback for teaching programs [19, 33, 10]) and are generally template based.”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, methodology): “The abbreviation XAI for the term explainable artificial intelligence was first used in 2004 in [132] (see [23, Sec.”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “[260]: “Ideally, this Explainable AI can present the user with an easily understood chain of reasoning from the user’s order, through the AI’s knowledge and inference, to the resulting behavior”.”
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey (2019, methodology): “Another example is the early use of explainable AI [29] which was developed as a simulator game for the commercial platform training aid Full Spectrum Command motivated by previous work such as [30].”
Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach (2019, background): “XAI has been particularly studied in the military domain [13,14].”
Explainable Artificial Intelligence: Objectives, Stakeholders, and Future Research Opportunities (2020, unknown): “Two years later, FSC was presented by their developers in an article at the computer science conference on Innovative Applications of Artificial Intelligence, in which FSC was described as an “XAI System” for small-unit tactical behavior (Van Lent et al., 2004).”
Building Explainable Artificial Intelligence Systems (2006, background): “Related Work In this section, we discuss two pieces of previous work on generating explanations of entity actions during a simulation: Debrief (Johnson 1994) and explainable artificial intelligence (XAI) for Full Spectrum Command (FSC) (van Lent, Fisher, & Mancuso 2004).”