Antoine Mahé
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Antoine Mahé has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Antoine Richard
SnT-SpaceR, University of Luxembourg, Luxembourg, Luxembourg
3 shared publications - Cédric Pradalier
CNRS IRL2958 GeorgiaTech- CNRS, 2 rue Marconi, Metz, 57050, France
3 shared publications - Matthieu Geist
Google DeepMind
3 shared publications - Benjamin Mouscadet1 shared publication
- Stéphanie Aravecchia
GeorgiaTech EuropeIRL2958 GT-CNRS, Metz, France
1 shared publication
Latest Publications
- 30 March 2021
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 101 (4) , 1-19
Evaluation of Prioritized Deep System Identification on a Path Following Task
- 30 March 2021
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 101 (4) , 1-19
Evaluation of Prioritized Deep System Identification on a Path Following Task
- Open Access
A Comprehensive Benchmark of Neural Networks for System Identification
This paper compares a wide variety of neural network architectures applied in the context of black-box modeling for robotics and control. We compare six different architectural concepts and four activation functions, with over three hundred different models. Those models were applied to three robotics datasets to show the differences in performance between the architectures along with their limitations.
Open AccessA Comprehensive Benchmark of Neural Networks for System Identification
This paper compares a wide variety of neural network architectures applied in the context of black-box modeling for robotics and control. We compare six different architectural concepts and four activation functions, with over three hundred different models. Those models were applied to three robotics datasets to show the differences in performance between the architectures along with their limitations.
- Open Access
Importance Sampling for Deep System Identification
This paper revisit the methodology of system identification and shows how new paradigms from machine learning can be used to improve the model identification performance in the case of non-linear systems observed with noisy and unbalanced dataset. We prove that using importance sampling schemes in system identification can provide significant performance boost on a wide variety of systems, in particular when some of the system dynamic is only exhibited by relatively rare events. The performance of the approaches is evaluated on a real and simulated drone and two standard datasets from real robotic systems. Our approach consistently outperforms baseline approaches on these datasets, all the more when the datasets are noisy and unbalanced.
Open AccessImportance Sampling for Deep System Identification
This paper revisit the methodology of system identification and shows how new paradigms from machine learning can be used to improve the model identification performance in the case of non-linear systems observed with noisy and unbalanced dataset. We prove that using importance sampling schemes in system identification can provide significant performance boost on a wide variety of systems, in particular when some of the system dynamic is only exhibited by relatively rare events. The performance of the approaches is evaluated on a real and simulated drone and two standard datasets from real robotic systems. Our approach consistently outperforms baseline approaches on these datasets, all the more when the datasets are noisy and unbalanced.