Asking for Help Effectively via Modeling of Human Beliefs

摘要: Autonomous robots deployed around humans must be able to ask for help when problems arise. However, people may have incorrect mental models of the robots» capabilities or task, making them unable help. We propose a data-driven method estimate humans» beliefs after hearing task-related utterances and build sets that influence towards useful in expectation. present an example show our selects effective desired is much different than person expects.