CAREER: Provably Correct Shared Control for Human-Embedded Autonomous Systems
| Establishing provable trust is one of the most pressing bottlenecks in deploying autonomous systems at scale. Embedding a human as a user, information source or decision aid into the operation of autonomous systems amplifies the difficulty. While humans offer cognitive capabilities that complement machine implementable functionalities, the impact of this synergy is contingent on the system’s ability to infer the intent, preferences and limitations of the human and the imperfections imposed by the interfaces between the human and the autonomous system.
This project targets a major gap in theory and tools for the design of human-embedded autonomous systems. Its objective is to develop languages, algorithms and demonstrations for the formal specification and automated synthesis of shared control protocols. It identifies three key needs, and addresses them in three thrusts: