A Robotic Context Query-Processing Framework Based on Spatio-Temporal Context Ontology

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Service robots require real-time environmental awareness, including dynamic changes and historical context.
• Existing systems often struggle with efficient processing of spatio-temporal information for robots.

Purpose of the Study:

• To propose a novel context query-processing framework for service robots.
• To enable robots to query both current and past contextual information efficiently.

Main Methods:

• Development of a spatio-temporal robotic context query language (ST-RCQL) and a query-processing system (ST-RCQP).
• Design based on spatio-temporal context ontology, incorporating time operators and constants.
• Implementation of a perception handler, working memory, and backward reasoner within ST-RCQP.
• Utilizing a spatio-temporal index in working memory to accelerate query processing.

Main Results:

• ST-RCQL allows efficient querying of historical and current context.
• ST-RCQP demonstrates real-time query processing capabilities.
• The spatio-temporal index significantly speeds up query processing.
• Experiments confirm the high efficiency and performance of the framework.

Conclusions:

• The proposed framework effectively addresses the need for context-aware service robots.
• This approach enhances robot's ability to understand and react to dynamic environments.
• The system offers a significant advancement in robotic context awareness and query processing.