Abstract
Human-robot teaming is inevitable in various applications ranging from manufacturing to field robotics because of the advantages of adaptability and high flexibility. To become an effective team, knowledge regarding plan execution needs to be shared by verbalization. In this respect, semantic scene understanding in natural language is one of the most fundamental components for information sharing between humans and heterogeneous robots, as robots can perceive the surrounding environment in a form that both humans and other robots can understand. In this paper, we introduce semantic scene understanding methods for verbalization of plan execution. We generate sentences and scene graphs, which is a natural language grounded graph over the detected objects and their relationships, with the graph map generated using a robot mapping algorithm. Experiments were performed to verify the effectiveness of the proposed methods.
| Original language | English |
|---|---|
| Title of host publication | SDMM19 : 1st International Workshop on the Semantic Descriptor, Semantic Modeling and Mapping for Humanlike Perception and Navigation of Mobile Robots toward Large Scale Long-Term Autonomy |
| Place of Publication | Germany |
| Pages | 58-64 |
| Number of pages | 7 |
| Volume | 2487 |
| Publication status | Published - 8 Nov 2019 |
| Event | International Workshop on the Semantic Descriptor, Semantic Modeling and Mapping for Humanlike Perception and Navigation of Mobile Robots toward Large Scale Long-Term Autonomy - Macau, China Duration: 8 Nov 2019 → … http://ceur-ws.org/Vol-2487/ |
Workshop
| Workshop | International Workshop on the Semantic Descriptor, Semantic Modeling and Mapping for Humanlike Perception and Navigation of Mobile Robots toward Large Scale Long-Term Autonomy |
|---|---|
| Abbreviated title | SDMM |
| Country/Territory | China |
| City | Macau |
| Period | 8/11/19 → … |
| Internet address |
Keywords
- human-robot teaming
- robotics
- Artificial Intelligence (AI)
- plan execution