Research Papers - Dept of Information Technology

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593

Browse

Filters

2013 - 201912020 - 20212

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Semantic

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationEmbargo
    Semantic Self Learning And Teaching Agent (SESLATA)
    (IEEE, 2013-04-26) Koggalahewa, D. N; Amararachchi, J. L; Pilapitiya, S. U; Geegange, D. T. K
    Semantic Self Learning And Teaching Agent (SESLATA) is a self learning software which is capable of learning from a natural language source. It identifies language complexity, ambiguity and influence of diverse writing styles to extract and decipher. The specialty herein the system is, usage of its acquired knowledge to perform teaching and explaining activities to its end users. The agent is capable of updating its own knowledge and it interacts with learner through intelligent response and using own experiences in the process of teaching according to learner's knowledge. Simply it learns somewhat like a human and teaches what it has learnt as a human does. The software is endowed with inventions involving in Natural Language Processing, machine learning, explanation and knowledge representation and ontology, which are still under research. Self learning from natural language (acquiring the domain knowledge to model ontology), automate the ontology creation from natural language, the teaching and explaining capability of an agent, updating the knowledge via ontology, knowledge representation and sharing, a new methodology of online learning, teaching according to the depth of user's knowledge are the major findings of the system.
  • Thumbnail Image
    PublicationEmbargo
    ROS Based Multiple Service Robots Control and Communication with High Level User Instruction with Ontology
    (IEEE, 2021-08-11) Rajapaksha, S. K
    Human Robot Interaction (HRI) is one of the biggest research field in the Robotics research world. Understanding the semantic meaning of the user instruction is very important to establish the communication between user and robot. When a user instructs to all heterogeneous service Robots with high level instructions who are working at different locations in smart house, all robots need to operate by understanding the semantic of the instruction and complete the task uniformly without considering underline software and hardware implementations. Ontology is used to extract the semantic meaning of the instructions. Each robot is assigned a specific task for specific time period for each day. User can issue commands to all robots at different time slots but the same command can be issued with different sentence by different users. We have used ontology to represents the semantic of the sentence with different commands. We have used three robots (TurtleBot, TiaGo and Husky) for our experiment in Gazebo simulator. Robot Operating System (ROS) is the middleware which is hiding more complex implementation of different functions for different robots and provide the interoperability for heterogeneous robot operations. The ROS nodes and topics can be different for different robots, therefore our implementation can solve this issue by autonomous robot registration algorithm which is working with Robot ontology.
  • Thumbnail Image
    PublicationEmbargo
    ROS Based Multiple Service Robots Control and Communication with High Level User Instruction with Ontology
    (IEEE, 2021-08-11) Rajapaksha, U. U. S; Jayawardena, C; MacDonald, B. A
    Human Robot Interaction (HRI) is one of the biggest research field in the Robotics research world. Understanding the semantic meaning of the user instruction is very important to establish the communication between user and robot. When a user instructs to all heterogeneous service Robots with high level instructions who are working at different locations in smart house, all robots need to operate by understanding the semantic of the instruction and complete the task uniformly without considering underline software and hardware implementations. Ontology is used to extract the semantic meaning of the instructions. Each robot is assigned a specific task for specific time period for each day. User can issue commands to all robots at different time slots but the same command can be issued with different sentence by different users. We have used ontology to represents the semantic of the sentence with different commands. We have used three robots (TurtleBot, TiaGo and Husky) for our experiment in Gazebo simulator. Robot Operating System (ROS) is the middleware which is hiding more complex implementation of different functions for different robots and provide the interoperability for heterogeneous robot operations. The ROS nodes and topics can be different for different robots, therefore our implementation can solve this issue by autonomous robot registration algorithm which is working with Robot ontology.