Semantic Representation of Robot Manipulation with Knowledge Graph
Autonomous indoor service robots are affected by multiple factors when they are directly involved in manipulation tasks in daily life, such as scenes, objects, and actions. It is of self-evident importance to properly parse these factors and interpret intentions according to human cognition and sema...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/25/4/657 |
| _version_ | 1797605573107122176 |
|---|---|
| author | Runqing Miao Qingxuan Jia Fuchun Sun Gang Chen Haiming Huang Shengyi Miao |
| author_facet | Runqing Miao Qingxuan Jia Fuchun Sun Gang Chen Haiming Huang Shengyi Miao |
| author_sort | Runqing Miao |
| collection | DOAJ |
| description | Autonomous indoor service robots are affected by multiple factors when they are directly involved in manipulation tasks in daily life, such as scenes, objects, and actions. It is of self-evident importance to properly parse these factors and interpret intentions according to human cognition and semantics. In this study, the design of a semantic representation framework based on a knowledge graph is presented, including (1) a multi-layer knowledge-representation model, (2) a multi-module knowledge-representation system, and (3) a method to extract manipulation knowledge from multiple sources of information. Moreover, with the aim of generating semantic representations of entities and relations in the knowledge base, a knowledge-graph-embedding method based on graph convolutional neural networks is proposed in order to provide high-precision predictions of factors in manipulation tasks. Through the prediction of action sequences via this embedding method, robots in real-world environments can be effectively guided by the knowledge framework to complete task planning and object-oriented transfer. |
| first_indexed | 2024-03-11T05:03:00Z |
| format | Article |
| id | doaj.art-4fcccc9115324b4f9bdffda5376a17ce |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-11T05:03:00Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-4fcccc9115324b4f9bdffda5376a17ce2023-11-17T19:09:13ZengMDPI AGEntropy1099-43002023-04-0125465710.3390/e25040657Semantic Representation of Robot Manipulation with Knowledge GraphRunqing Miao0Qingxuan Jia1Fuchun Sun2Gang Chen3Haiming Huang4Shengyi Miao5School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaInstitute for Artificial Intelligence, Tsinghua University, Beijing 100084, ChinaSchool of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, ChinaAutonomous indoor service robots are affected by multiple factors when they are directly involved in manipulation tasks in daily life, such as scenes, objects, and actions. It is of self-evident importance to properly parse these factors and interpret intentions according to human cognition and semantics. In this study, the design of a semantic representation framework based on a knowledge graph is presented, including (1) a multi-layer knowledge-representation model, (2) a multi-module knowledge-representation system, and (3) a method to extract manipulation knowledge from multiple sources of information. Moreover, with the aim of generating semantic representations of entities and relations in the knowledge base, a knowledge-graph-embedding method based on graph convolutional neural networks is proposed in order to provide high-precision predictions of factors in manipulation tasks. Through the prediction of action sequences via this embedding method, robots in real-world environments can be effectively guided by the knowledge framework to complete task planning and object-oriented transfer.https://www.mdpi.com/1099-4300/25/4/657robot manipulationknowledge graphrepresentation learninggraph neural network |
| spellingShingle | Runqing Miao Qingxuan Jia Fuchun Sun Gang Chen Haiming Huang Shengyi Miao Semantic Representation of Robot Manipulation with Knowledge Graph Entropy robot manipulation knowledge graph representation learning graph neural network |
| title | Semantic Representation of Robot Manipulation with Knowledge Graph |
| title_full | Semantic Representation of Robot Manipulation with Knowledge Graph |
| title_fullStr | Semantic Representation of Robot Manipulation with Knowledge Graph |
| title_full_unstemmed | Semantic Representation of Robot Manipulation with Knowledge Graph |
| title_short | Semantic Representation of Robot Manipulation with Knowledge Graph |
| title_sort | semantic representation of robot manipulation with knowledge graph |
| topic | robot manipulation knowledge graph representation learning graph neural network |
| url | https://www.mdpi.com/1099-4300/25/4/657 |
| work_keys_str_mv | AT runqingmiao semanticrepresentationofrobotmanipulationwithknowledgegraph AT qingxuanjia semanticrepresentationofrobotmanipulationwithknowledgegraph AT fuchunsun semanticrepresentationofrobotmanipulationwithknowledgegraph AT gangchen semanticrepresentationofrobotmanipulationwithknowledgegraph AT haiminghuang semanticrepresentationofrobotmanipulationwithknowledgegraph AT shengyimiao semanticrepresentationofrobotmanipulationwithknowledgegraph |