PolyDexFrame: Deep Reinforcement Learning-Based Pick-and-Place of Objects in Clutter
Machines · 11.08.2024 · 12 (8) · 547
DOI: 10.3390/machines12080547 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 11.08.2024. Verfasst von Muhammad Babar Imtiaz und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland (SFI), European Regional Development Fund, Higher Education Authority (HEA) on behalf of the Department of Further and Higher Education, Research, Innovation, and Science (DFHERIS), and the Shared Islan….
Abstract (Originalsprache)
This research study represents a polydexterous deep reinforcement learning-based pick-and-place framework for industrial clutter scenarios. In the proposed framework, the agent tends to learn the pick-and-place of regularly and irregularly shaped objects in clutter by using the sequential combination of prehensile and non-prehensile robotic manipulations involving different robotic grippers in a completely self-supervised manner. The problem was tackled as a reinforcement learning problem; after the Markov decision process (MDP) was designed, the off-policy model-free Q-learning algorithm was deployed using deep Q-networks as a Q-function approximator. Four distinct robotic manipulations, i.e., grasp from the prehensile manipulation category and inward slide, outward slide, and suction grip from the non-prehensile manipulation category were considered as actions. The Q-function comprised four fully convolutional networks (FCN) corresponding to each action based on memory-efficient DenseNet-121 variants outputting pixel-wise maps of action-values jointly trained via the pixel-wise parametrization technique. Rewards were awarded according to the status of the action performed, and backpropagation was conducted accordingly for the FCN generating the maximum Q-value. The results showed that the agent learned the sequential combination of the polydexterous prehensile and non-prehensile manipulations, where the non-prehensile manipulations increased the possibility of prehensile manipulations. We achieved promising results in comparison to the baselines, differently designed variants, and density-based testing clutter.
Förderung
- Science Foundation Ireland (SFI)
- European Regional Development Fund
- Higher Education Authority (HEA) on behalf of the Department of Further and Higher Education, Research, Innovation, and Science (DFHERIS), and the Shared Islan…
Zitieren
APA
Imtiaz, M. B., Qiao, Y., & Lee, B. (2024). PolyDexFrame: Deep Reinforcement Learning-Based Pick-and-Place of Objects in Clutter. Machines, 12(8), 547. https://doi.org/10.3390/machines12080547
Vancouver
Imtiaz MB, Qiao Y, Lee B. PolyDexFrame: Deep Reinforcement Learning-Based Pick-and-Place of Objects in Clutter. Machines. 2024;12(8):547. doi:10.3390/machines12080547
BibTeX
@article{Imtiaz2024,
author = {Imtiaz, Muhammad Babar and Qiao, Yuansong and Lee, Brian},
title = {PolyDexFrame: Deep Reinforcement Learning-Based Pick-and-Place of Objects in Clutter},
journal = {Machines},
year = {2024},
volume = {12},
number = {8},
pages = {547},
doi = {10.3390/machines12080547}
}
EUVIMED