Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Filters

2020 - 20223

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Instructions

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationEmbargo
    Adding Common Sense to Robots by Completing the Incomplete Natural Language Instructions
    (IEEE, 2022-07-18) De Silva, G. W. M. H. P.; Rajapaksha, S; Jayawardena, C
    This system is developed to identify and complete the human’s instructions or incomplete sentences given by a user as a command. It would facilitate the interaction between the human and mobile service robots. However, when humans give the instruction, there can be incompleteness or else missing the information related to the environment. That is because humans, generally based on common sense, depending on the environment. Then the human brain can complete all those incomplete sentences by using common sense knowledge. This paper itself introduced a model of a service robot who can compete with the given incomplete instructions, display the related sentences or words, and finally move to the related objects in the environment. First, it will consider and identify the objects in the environment and then consider the given natural language instruction by humans. As a first step of the approach, complete the incomplete sentences. Those sentences are coming as natural language instructions. By parsing it into as the frame can identify the related words by using the created model or can call as language model and here used some identify words from the human common sense also, then the service robot will learn about the commonsense knowledge automatically from the parsing sentences as a speaker. Considering all the parsing sentences, it calculates and measures the accuracy of this service robot model. Simply this is a commonsense reasoning model. The result of the provided solution can enable the robot model that works in a ROS environment to identify and automatically perform the tasks.
  • Thumbnail Image
    PublicationEmbargo
    ROS Based Heterogeneous Multiple Robots Control Using High Level User Instructions
    (IEEE, 2021-12-07) Rajapaksha, S. K; Jayawardena, C; MacDonald, B. A
    Heterogeneous Multiple Robots(HMR) can be used in daily life for smart homes and industry. The differences in implementing different HMR can be minimized using middle-ware like Robot Operating System (ROS). However, the ROS topics, nodes, and message formats to subscribe and publish can differ from one robot to another. When a user expresses high-level instructions through the Web interface, all multiple robots must understand instructions uniformly and take the actions accordingly without considering each robot's internal software and hardware implementation. This paper represents an optimized ontology-based algorithm for HMR registration and control for high-level instructions. Autonomous robot registration was achieved using an ontology-based optimized algorithm. User-level high-level instructions are processed using an ontology-based algorithm to determine the corresponding actions for each robot. Finally, autonomous publication and subscription to different ROS topics were implemented using another optimized algorithm. The evaluation of the proposed algorithms was completed with Turtlebot, Husky and TiaGo robots using gazebo.
  • Thumbnail Image
    PublicationEmbargo
    Methodology for coping with uncertain information contained in natural language instructions in a robotic system
    (IEEE, 2020-12-10) Bandara, H. M. Y. L. W; Wijesekera, D. S; Bandara Herath, H. M. T. D; Kodagoda, D. L; Rajapaksha, S, K
    Intelligent service robots are currently being developed to provide services and assistance in different sectors including domestic and household context. Typically, the service tasks of a domestic service robot involve direct interaction with humans. Humans typically express their ideas through voice communication. However, communication through natural language is imprecise because it tends to contain uncertain and unknown information. Therefore, understanding uncertain terms contained in natural language is a crucial capability that an intelligent service robot should possess. Hence, this project which is named as IntelBot is aimed at developing a methodology to cope with uncertain and unknown words contained in a natural language command given to a domestic service robot. In brief, the proposed system can interpret uncertain commands related to speed such as “go very fast” and the uncertain commands related to time such as “go later”. Additionally, if the robot is instructed to identify an object which is regarded to be unknown, as an example “cup” it can interpret and identify that particular object. And for the entire system, a user-friendly interface is developed for the easy control of the robot and the demonstration of the functionalities.