RT Journal Article
T1 Deep robot sketching: an application of deep Q-learning networks for human-like sketching
A1 Fernandez Fernandez, Raul
A1 G. Victores, Juan
A1 Balaguer, Carlos
AB The current success of Reinforcement Learning algorithms for its performance in complex environments has inspired many recent theoretical approaches to cognitive science. Artistic environments are studied within the cognitive science community as rich, natural, multi-sensory, multi-cultural environments. In this work, we propose the introduction of Reinforcement Learning for improving the control of artistic robot applications. Deep Q-learning Neural Networks (DQN) is one of the most successful algorithms for the implementation of Reinforcement Learning in robotics. DQN methods generate complex control policies for the execution of complex robot applications in a wide set of environments. Current art painting robot applications use simple control laws that limits the adaptability of the frameworks to a set of simple environments. In this work, the introduction of DQN within an art painting robot application is proposed. The goal is to study how the introduction of a complex control policy impacts the performance of a basic art painting robot application. The main expected contribution of this work is to serve as a first baseline for future works introducing DQN methods for complex art painting robot frameworks. Experiments consist of real world executions of human drawn sketches using the DQN generated policy and TEO, the humanoid robot. Results are compared in terms of similarity and obtained reward with respect to the reference inputs.
PB Elsevier
SN 1389-0417
YR 2023
FD 2023-09
LK https://hdl.handle.net/20.500.14352/72355
UL https://hdl.handle.net/20.500.14352/72355
LA eng
NO © 2023 The Authors. Published by Elsevier B.V.This research has been financed by ALMA, ‘‘Human Centric Algebraic Machine Learning’’, H2020 RIA under EU grant agreement 952091; ROBOASSET, ‘‘Sistemas robóticos inteligentes de diagnóstico y rehabilitación de terapias de miembro superior’’, PID2020-113508RBI00, financed by AEI/10.13039/501100011033; ‘‘RoboCity2030-DIHCM, Madrid Robotics Digital Innovation Hub’’, S2018/NMT-4331, financed by ‘‘Programas de Actividades I+D en la Comunidad de Madrid’’; ‘‘iREHAB: AI-powered Robotic Personalized Rehabilitation’’, ISCIIIAES-2022/003041 financed by ISCIII and UE; and EU structural funds
NO Unión Europea. H2020
NO Ministerio de Ciencia e Innovación (MICINN)/ AEI/10.13039/501100011033;
NO Comunidad de Madrid
NO Instituto de Salud Carlos III (ISCIII)/UE
NO ROBOTICSLAB
DS Docta Complutense
RD 2 may 2024