Semantic Task Planning for Service Robots in Open World

TL;DR

This paper introduces a semantic reasoning planning system for service robots that handles incomplete information, dynamic environments, and under-specified goals by integrating natural language understanding, AI symbolic planning, and adaptive execution.

Contribution

It presents a novel integrated framework combining NLP, symbolic AI planning, and real-time sensing for autonomous service robots in open, unpredictable environments.

Findings

Successfully plans and executes complex tasks in dynamic settings.

Acquires and utilizes causal knowledge through dialogue.

Adapts plans in real-time to environmental changes and faults.

Abstract

In this paper, we present a planning system based on semantic reasoning for a 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 and their relationships; (ii) the modifier used to indicate some property or characteristic of a variable in the action frame. Next, the goals of the task are generated from these action frames and modifiers. These goals are represented as AI symbols, combining world state and domain knowledge, which are used to generate plans by an Answer Set Programming solver. Finally, the actions of the plan are executed one by one, and continuous sensing grounds useful information, which make the robot to use contingent knowledge to adapt to dynamic changes and faults. For each action in the plan, the planner gets its preconditions and effects from domain knowledge, so during the execution of the task, the environmental changes, especially those conflict with the actions, not only the action being performed, but also the subsequent actions, can be detected and handled as early as possible. A series of case studies are used to evaluate the system and verify its ability to acquire knowledge through dialogue with users, solve problems with the acquired causal knowledge, and plan for complex tasks autonomously in the open world.