Ontology-based framework for cooperative learning of 3d object recognition | |
| Author | Parkpoom Chaisiriprasert |
| Call Number | AIT Diss no.CS-22-01 |
| Subject(s) | Ontology Three-dimensional imaging Robotics |
| Note | A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | Advanced service robots are not, as of yet, widely adopted in homes, partly due to the in effectiveness of robots’ object recognition capabilities, issues around object heterogeneity, a lack of knowledge sharing between robots, and the difficulty of knowledge management for a collective of networked robots. To encourage the usage of service robots on a larger scale, we present an ontology-based framework for cooperative robot learning that begins to address these issues. We demonstrate how the system can be used to offload compute-intensive machine vision workloads to cloud infrastructure using numerous service robots. With the use of ontologies, the framework can recognize heterogeneous 3D objects. The main contribution of the proposal is a new ontology-based system incorporating the Unified Robot Description Format (URDF) to represent robots and a new Robotic Object Description (ROD) ontology to represent the world of objects known by the collective. We use the WordNet database to provide common semantics for objects across various robots and robotic applications. With this framework, we aim to give a widely distributed group of robots the ability to cooperatively learn to recognize a variety of 3D objects. Different robots and different robotic applications could share knowledge and benefit from the experience of the collective via this framework. The framework was validated and then evaluated using a proof of concept, including a Web application integrated with the ROD ontology and the WordNet API for semantic analysis. The evaluation demonstrates the feasibility of using an ontology-based framework and the Ontology Web Language (OWL) as a basis for improved knowledge management while enabling cooperative learning between multiple robots. |
| Year | 2022 |
| Type | Dissertation |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Mathew N. |
| Examination Committee(s) | Chutiporn Anutariya;Mongkol Ekpanyapong |
| Degree | Thesis (Ph.D.) - Asian Institute of Technology, 2022 |