Tenorth, MoritzWinkler, JanBeßler, DanielBeetz, Michael2018-01-082018-01-0820152015https://dl.gi.de/handle/20.500.12116/11493We present Open-EASE, a cloud-based knowledge base of robot experience data that can serve as episodic memory, providing a robot with comprehensive information for autonomously learning manipulation tasks. Open-EASE combines both robot and human activity data in a common, semantically annotated knowledge base, including robot poses, object information, environment models, the robot’s intentions and beliefs, as well as information about the actions that have been performed. A powerful query language and inference tools support reasoning about the data and retrieving information based on semantic queries. In this paper, we focus on applications of Open-EASE in the context of autonomous learning.Text/Journal Article1610-1987