Knowledge representation and reasoning for perception-based manipulation planning

This thesis develops a series of modeling and reasoning tools for knowledge-oriented manipulation planning in semi/unstructured environments. The main idea is to use high-level knowledge-based reasoning to capture a rich semantic description of the scene, knowledge about the physical behavior of the...

Descripción completa

Detalles Bibliográficos
Autor: Diab, Mohammed
Tipo de recurso: tesis doctoral
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/345316
Acceso en línea:https://hdl.handle.net/2117/345316
https://dx.doi.org/10.5821/dissertation-2117-345316
Access Level:acceso abierto
Palabra clave:Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:This thesis develops a series of modeling and reasoning tools for knowledge-oriented manipulation planning in semi/unstructured environments. The main idea is to use high-level knowledge-based reasoning to capture a rich semantic description of the scene, knowledge about the physical behavior of the objects, and inference mechanism to reason about the potential manipulation actions. Moreover, a multi-model sensory module is proposed to perceive the objects in the environment and build the ontological knowledge. The first part of the thesis is focused on the techniques to provide useful knowledge to guide and facilitate the planning process within a classical-based manipulation planning framework. This planning framework facilitates the combination of task and motion planning approaches which includes Fast Forward (FF), a classical symbolic planning approach to compute the sequence of actions to be done in a certain task, and physics-based motion planning which deals with motions and possible interactions with the objects. The tool proposed to provide useful knowledge to the planning process is called Perception and Manipulation Knowledge (PMK). It provides, on the one hand, a standardized formalization under several foundations, such as the Suggested Upper Merged Ontology (SUMO), and the Core Ontology for Robotics and Automation (CORA), in order to facilitate the shareability and reusability when the interaction between humans and/or robots is done. On the other hand, it provides the inference mechanism to reason about TAMP requirements, such as robot capabilities, action constraints, action feasibility, and manipulation behaviors. Moreover, PMK allows breaking the closed-world assumption of classical-based manipulation planning approaches. This proposal has been tested for a serving task in a table-top manipulation problem.