RT Dissertation/Thesis
T1 Multi-Layered Architectures for Autonomous Systems
A1 González Dorado, José Carlos
AB Deliberation is a key feature to endow advanced intelligence to autonomous agents.Complex use cases, specially robotic applications which require a considerable degreeof autonomy, have to be coordinated by some kind of control architecture. However,reusing existing architectures can be difficult because use cases are very heterogeneous.The main goal of this thesis is to ease the use of standard deliberative techniques in usecaseoriented cognitive architectures for autonomous systems. This thesis contributeswith new declarative languages to model use cases, new control architectures, new softwaredevelopments and new methodological guidelines of how to apply these conceptsin engineering processes. To justify the contributions, this thesis presents the designof NAOTherapist, an autonomous social robot for upper-limb pediatric rehabilitation.Its control architecture is a prototype that maximizes its generalization capabilities.However, several limitations arose when reusing this architecture in other projects asthe Clarc robot (geriatric assessment) and a CoBot robot (office delivery tasks). Thediscussion about NAOTherapist is used to highlight these limitations and determinehow to overcome them. The main implementation after all these approaches is Mlaras(Multi-Layered ARchitecture for Autonomous Systems), which is a generic architectureto ease the development of autonomous intelligent systems. It also allows non-expertusers to directly modify it to refine the use-case definition. Mlaras is focused on automatedplanning as the core of its deliberative processes, which are separated intoseveral layers to take advantage of the hierarchical abstraction levels present in manyuse cases. An instance of Mlaras has been developed for the autonomous agents of asimulated logistics competition use case to further evaluate the capabilities of the newarchitecture. The experimentation concludes that the contributions help to fill the gapbetween the use case definitions and the actual developed applications.
YR 2020
FD 2020-02
LK https://hdl.handle.net/10016/31368
UL https://hdl.handle.net/10016/31368
LA eng
NO Mención Internacional en el título de doctor
NO - Arquitecturas para Capacitación Social Basadas en Planificación Automática. Funding Entity: MICINN, RTI2018-099522-B-C43.- Lifelong Technologies for Social Robots in Smart Homes. Funding Entity: MINECO, TIN2015-65686-C5-1-R- European Clearing House for Open Robotics Development Plus Plus (ECHORD++).Sub-project smart CLinic Assistant Robot for CGA (CLARK). Funding Entity: European Union Seventh Framework Programme for Research (FP7),Grant Agreement No. FP7-ICT-601116- Diseño, Planificacion Automática Y Evaluación De Terapias De Neuro-Rehabilitación Dirigidas Por Un Robot Social E Interactivo. Funding Entity: MINECO, TIN2012-38079-C03-02
DS e-Archivo
RD 19 may. 2024