Learning-based planner for unknown object dexterous manipulation using ANFIS

Dexterous manipulation of unknown objects performed by robots equipped with mechanical hands represents a critical challenge. The difficulties arise from the absence of a precise model of the manipulated objects, unpredictable environments, and limited sensing capabilities of the mechanical hands co...

Descripción completa

Detalles Bibliográficos
Autores: Sheikhsamad, Mohammad, Suárez Feijóo, Raúl|||0000-0002-3853-7095, Rosell Gratacòs, Jan|||0000-0003-4854-2370
Tipo de recurso: artículo
Fecha de publicación:2024
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:2117/414140
Acceso en línea:https://hdl.handle.net/2117/414140
https://dx.doi.org/10.3390/machines12060364
Access Level:acceso abierto
Palabra clave:Robotics
Robots -- Control systems
Dexterous manipulation
Motion planning
ANFIS planner
Allegro hand
Robòtica
Robots -- Sistemes de control
Àrees temàtiques de la UPC::Informàtica::Robòtica
Descripción
Sumario:Dexterous manipulation of unknown objects performed by robots equipped with mechanical hands represents a critical challenge. The difficulties arise from the absence of a precise model of the manipulated objects, unpredictable environments, and limited sensing capabilities of the mechanical hands compared to human hands. This paper introduces a data-driven approach that provides a learning-based planner for dexterous manipulation employing an Adaptive Neuro-Fuzzy Inference System (ANFIS) fed by data obtained from an analytical manipulation planner. ANFIS captures the complex relationships between inputs and optimal manipulation parameters. Moreover, during a training phase, it is able to fine-tune itself on the basis of its experiences. The proposed planner enables a robot to interact with objects of various shapes, sizes, and material properties while providing an adaptive solution for increasing robotic dexterity. The planner is validated in a real-world environment, applying an Allegro anthropomorphic robotic hand. A link to a video of the experiment is provided in the paper.