Rethinking Safe Control in the Presence of Self-Seeking Humans
Zixuan Zhang, Maitham AL-Sunni, Haoming Jing, Hirokazu Shirado, Yorie Nakahira
Abstract
Safe control methods are often designed to behave safely even in worst-case human uncertainties. Such design can cause more aggressive human behaviors that exploit its conservatism and result in greater risk for everyone. However, this issue has not been systematically investigated previously. This paper uses an interaction-based payoff structure from evolutionary game theory to model humans’ short-sighted, self-seeking behaviors. The model captures how prior human-machine interaction experience causes behavioral and strategic changes in humans in the long term. We then show that deterministic worst-case safe control techniques and equilibrium-based stochastic methods can have worse safety and performance trade-offs than a basic method that mediates human strategic changes. This finding suggests an urgent need to fundamentally rethink the safe control framework used in human-technology interaction in pursuit of greater safety for all.
BibTeX
@article{Zhang_AL-Sunni_Jing_Shirado_Nakahira_2023, title={Rethinking Safe Control in the Presence of Self-Seeking Humans}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26788}, DOI={10.1609/aaai.v37i12.26788}, abstractNote={Safe control methods are often designed to behave safely even in worst-case human uncertainties. Such design can cause more aggressive human behaviors that exploit its conservatism and result in greater risk for everyone. However, this issue has not been systematically investigated previously. This paper uses an interaction-based payoff structure from evolutionary game theory to model humans’ short-sighted, self-seeking behaviors. The model captures how prior human-machine interaction experience causes behavioral and strategic changes in humans in the long term. We then show that deterministic worst-case safe control techniques and equilibrium-based stochastic methods can have worse safety and performance trade-offs than a basic method that mediates human strategic changes. This finding suggests an urgent need to fundamentally rethink the safe control framework used in human-technology interaction in pursuit of greater safety for all.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zhang, Zixuan and AL-Sunni, Maitham and Jing, Haoming and Shirado, Hirokazu and Nakahira, Yorie}, year={2023}, month={Jun.}, pages={15331-15339} }