Translating Universal Scene Descriptions into Knowledge Graphs for Robotic Environment
This work addresses the need for robots to access extensive environmental knowledge for human-like manipulation, though it appears incremental as it builds on existing USD standards.
The paper tackles the problem of enabling robots to understand their surroundings for manipulation tasks by translating Universal Scene Description (USD) scene graphs into knowledge graphs, resulting in a technique that facilitates semantic querying and integration with other knowledge sources.
Robots performing human-scale manipulation tasks require an extensive amount of knowledge about their surroundings in order to perform their actions competently and human-like. In this work, we investigate the use of virtual reality technology as an implementation for robot environment modeling, and present a technique for translating scene graphs into knowledge bases. To this end, we take advantage of the Universal Scene Description (USD) format which is an emerging standard for the authoring, visualization and simulation of complex environments. We investigate the conversion of USD-based environment models into Knowledge Graph (KG) representations that facilitate semantic querying and integration with additional knowledge sources.