Human-AI Testing: State-of-the-Art and Research Needs

Description

Although artificial intelligence (AI) has many potential benefits, it has also been shown to suffer from a number of challenges for successful performance in complex real-world environments such as military operations, including brittleness, perceptual limitations, hidden biases, and lack of a model of causation important for understanding and predicting future events. These limitations mean that AI will remain inadequate for operating on its own in many complex and novel situations for the foreseeable future, and that AI will need to be carefully managed by humans to achieve their desired utility. Human-AI Teaming: State-of-the-Art and Research Needs examines the factors that are relevant to the design and implementation of AI systems with respect to human operations. This report provides an overview of the state of research on human-AI teaming to determine gaps and future research priorities and explores critical human-systems integration issues for achieving optimal performance. FrontMatter Preface Acknowledgment of Reviewers Contents Summary 1 Introduction 2 Human-AI Teaming Methods and Models 3 Human-AI Teaming Processes and Effectiveness 4 Situation Awareness in Human-AI Teams 5 AI Transparency and Explainability 6 Human-AI Team Interaction 7 Trusting AI Teammates 8 Identification and Mitigation of Bias in Human-AI Teams 9 Training Human-AI Teams 10 HSI Processes and Measures of Human-AI Team Collaboration and Performance 11 Conclusions References Appendixes Appendix A: Committee Biographies Appendix B: Human-AI Teaming Workshop Agenda Appendix C: Definitions