Verlagslink DOI: 10.1007/s00791-020-00327-0
arXiv ID: 1912.05958v2
Titel: Parareal with a learned coarse model for robotic manipulation
Sprache: Englisch
Autor/Autorin: Agboh, Wisdom 
Grainger, Oliver 
Ruprecht, Daniel  
Dogar, Mehmet R, 
Schlagwörter: Learning; Manipulation; Model-predictive control; Neural network; Parallel-in-time; Parareal; Planning; Robotics; Computer Science - Robotics; Computer Science - Robotics; Computer Science - Learning
Erscheinungs­datum: 23-Sep-2020
Verlag: Springer
Quellenangabe: Computing and Visualization in Science 1-4 (23): 8 (2020-09-23)
Zusammenfassung (englisch): 
A key component of many robotics model-based planning and control algorithms is physics predictions, that is, forecasting a sequence of states given an initial state and a sequence of controls. This process is slow and a major computational bottleneck for robotics planning algorithms. Parallel-in-time integration methods can help to leverage parallel computing to accelerate physics predictions and thus planning. The Parareal algorithm iterates between a coarse serial integrator and a fine parallel integrator. A key challenge is to devise a coarse model that is computationally cheap but accurate enough for Parareal to converge quickly. Here, we investigate the use of a deep neural network physics model as a coarse model for Parareal in the context of robotic manipulation. In simulated experiments using the physics engine Mujoco as fine propagator we show that the learned coarse model leads to faster Parareal convergence than a coarse physics-based model. We further show that the learned coarse model allows to apply Parareal to scenarios with multiple objects, where the physics-based coarse model is not applicable. Finally, we conduct experiments on a real robot and show that Parareal predictions are close to real-world physics predictions for robotic pushing of multiple objects. Videos are at https://youtu.be/wCh2o1rf-gA.
URI: http://hdl.handle.net/11420/7444
DOI: 10.15480/882.2954
ISSN: 1433-0369
Zeitschrift: Computing and visualization in science 
Institut: Mathematik E-10 
Dokumenttyp: Artikel/Aufsatz
Lizenz: CC BY 4.0 (Attribution) CC BY 4.0 (Attribution)
Enthalten in den Sammlungen:Publications with fulltext

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat
Agboh2020_Article_PararealWithALearnedCoarseMode.pdfVerlagsversion1,48 MBAdobe PDFÖffnen/Anzeigen
Miniaturbild
Zur Langanzeige

Seitenansichten

211
Letzte Woche
1
Letzten Monat
3
checked on 06.10.2022

Download(s)

117
checked on 06.10.2022

SCOPUSTM   
Zitate

2
Letzte Woche
0
Letzten Monat
0
checked on 11.07.2022

Google ScholarTM

Prüfe

Feedback zu diesem Datensatz

Diesen Datensatz zitieren

Export

Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons