Learning and Reasoning for Robot Sequential Decision Making under Uncertainty

摘要: Robots frequently face complex tasks that require more than one action, where sequential decision-making (SDM) capabilities become necessary. The key contribution of this work is a robot SDM framework, called LCORPP, supports the simultaneous supervised learning for passive state estimation, automated reasoning with declarative human knowledge, and planning under uncertainty toward achieving long-term goals. In particular, we use hybrid paradigm to refine estimator, provide informative priors probabilistic planner. experiments, mobile tasked estimating intentions using their motion trajectories, contextual human-robot interaction (dialog-based motion-based). Results suggest that, in efficiency accuracy, our framework performs better its no-learning no-reasoning counterparts office environment.