Safe Handover in Mixed-Initiative Control for Cyber-Physical Systems
This addresses safety and trust issues in human-machine interactions for cyber-physical systems, but it is incremental as it builds on existing methods from AI and HCI.
The paper tackles the problem of safely handing over control from cyber-physical systems to humans in mixed-initiative settings by proposing a concept that uses formal AI methods to predict handover needs and increase advance notice, combined with HCI and NLG for smooth transitions, illustrated in an autonomous driving scenario.
For mixed-initiative control between cyber-physical systems (CPS) and its users, it is still an open question how machines can safely hand over control to humans. In this work, we propose a concept to provide technological support that uses formal methods from AI -- description logic (DL) and automated planning -- to predict more reliably when a hand-over is necessary, and to increase the advance notice for handovers by planning ahead of runtime. We combine this with methods from human-computer interaction (HCI) and natural language generation (NLG) to develop solutions for safe and smooth handovers and provide an example autonomous driving scenario. A study design is proposed with the assessment of qualitative feedback, cognitive load and trust in automation.