Semantic Task Planning for Service Robots in Open Worlds

This paper presents a planning system based on semantic reasoning for general-purpose service robot, which is aimed at behaving more intelligently in domains that contain incomplete information, under-specified goals, and dynamic changes. First, Two kinds of data are generated by Natural Language Processing module from the speech: (i) action frames their relationships; (ii) modifier used to indicate some property or characteristic variable frame. Next, task’s goals these modifiers. These represented as AI symbols, combining world state domain knowledge, generate plans an Answer Set Programming solver. Finally, plan’s actions executed one one, continuous sensing grounds useful makes robot use contingent knowledge adapt changes faults. For each plan, planner gets its preconditions effects so during execution task, environmental changes, especially those conflict with actions, not only being performed but also subsequent can be detected handled early possible. A series case studies evaluate verify ability acquire through dialogue users, solve problems acquired causal plan complex tasks autonomously open world.