Shared Control with Human Trust and Workload Models

We synthesize shared control protocols subject to probabilistic temporal logic specifications. Specifically, we develop a framework in which a human and an autonomy protocol can issue commands to carry out a certain task. We blend these commands as a joint input into a robot. We model the interaction between the human and the robot as a Markov decision process representing the shared control scenario. Using inverse reinforcement learning, we obtain an abstraction of the human's behavior. We use randomized strategies to account for randomness in human's decisions, caused by factors such as the complexity of the task specifications or imperfect interfaces. We design the autonomy protocol to ensure that the resulting robot behavior satisfies given safety and performance specifications in probabilistic temporal logic. Additionally, the resulting strategies generate a behavior that is similar to the behavior induced by the human's commands as possible. We solve the underlying problem efficiently using sequential convex programming. In the case studies involving experiments in a high‐fidelity Unity simulator, we demonstrate the applicability of our approach.