A computational theory of strategic deception. This artificial project aims to develop a theory of strategic deception and test it through an Artificial Intelligence model. The project will combine computational Theory-of-Mind concepts with recent scientific findings to allow us to better understand whether and how intelligent technologies of the future might deceive humans. The findings will provide new insights into how Artificial Intelligence technologies of the future will impact applied are ....A computational theory of strategic deception. This artificial project aims to develop a theory of strategic deception and test it through an Artificial Intelligence model. The project will combine computational Theory-of-Mind concepts with recent scientific findings to allow us to better understand whether and how intelligent technologies of the future might deceive humans. The findings will provide new insights into how Artificial Intelligence technologies of the future will impact applied areas of computing, where simulating advanced forms of social behaviour and cognition, including deception, will become increasingly significant.Read moreRead less
Explanation in artificial intelligence: a human-centred approach. This project aims to produce validated methods for creating human-centred explanations of decisions made by artificial intelligence (AI). Trial deployment of AI devices has resulted in the requirement for explanations of how AI makes decisions, where developed AI systems gave insufficient consideration of how decision logic would be explained to people. This project positions 'explainable AI' within the intersection of human-compu ....Explanation in artificial intelligence: a human-centred approach. This project aims to produce validated methods for creating human-centred explanations of decisions made by artificial intelligence (AI). Trial deployment of AI devices has resulted in the requirement for explanations of how AI makes decisions, where developed AI systems gave insufficient consideration of how decision logic would be explained to people. This project positions 'explainable AI' within the intersection of human-computer interaction, computer science and cognitive psychology. The expected outcomes of this project are new methods, models and algorithms for explaining different types of AI models to people. This project should result in improved understanding and trust of decisions made by AI systems, mitigating some societal concerns about AI-based decision making.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210100858
Funder
Australian Research Council
Funding Amount
$344,896.00
Summary
Human-Centred Robot Training. This project aims to address the challenge of effectively enabling novice users to train robots on complex tasks using instructional methods and gamification. With the recent advances of AI research, robots have now better cognitive and functional skills, research in robot training also now allows them to learn interactively from human. Since these robots are expected to provide assistance in different domains including education and healthcare, it is crucial to eff ....Human-Centred Robot Training. This project aims to address the challenge of effectively enabling novice users to train robots on complex tasks using instructional methods and gamification. With the recent advances of AI research, robots have now better cognitive and functional skills, research in robot training also now allows them to learn interactively from human. Since these robots are expected to provide assistance in different domains including education and healthcare, it is crucial to effectively engage human in robot’s instruction. Expected outcomes include new methods for trainers to assess robot learning, and to improve their engagement and feedback. This should provide significant human-robot interaction benefits for accessibility of learning robots.Read moreRead less
Foundations of human-agent collaboration: situation-relevant information sharing. As automated systems become more sophisticated in their capabilities, the design of effective interaction with human operators becomes more demanding. Outcomes from this project will support the development of human-automation teams that can coordinate and collaborate in fast changing task environments.