Inferring user intent with Bayesian inverse planning: Making sense of multi-UAS mission management

摘要: The goal of intent inference is to use observed behavior predict underlying mental states and causal processes that are likely have generated the behavior. A potentially powerful technique for inferring uses Bayesian in structured generative models planning. We describe our adaptation inverse planning framework multi-unmanned systems mission domain. three experiments elucidate space priorities domain, infer users’ goals given their actions with a user interface, next using inferences about priorities.