Authors:
Ashley Hill
1
;
Eric Lucet
1
and
Roland Lenain
2
Affiliations:
1
CEA, LIST, Interactive Robotics Laboratory, Gif-sur-Yvette, F-91191, France
;
2
Université Clermont Auvergne, Inrae, UR TSCF, Centre de Clermont-Ferrand, F-63178 Aubière, France
Keyword(s):
Machine Learning, Neural Network, Robotics, Mobile Robot, Control Theory, Gain Tuning, Adaptive Control, Explainable Artificial Intelligence.
Abstract:
This paper proposes a new approach for feature importance of neural networks and subsequently a methodology using the novel feature importance to determine useful sensor information in high performance controllers, using a trained neural network that predicts the quasi-optimal gain in real time. The neural network is trained using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm, in order to lower a given objective function. The important sensor information for robotic control are determined using the described methodology. Then a proposed improvement to the tested control law is given, and compared with the neural network’s gain prediction method for real time gain tuning. As a results, crucial information about the importance of a given sensory information for robotic control is determined, and shown to improve the performance of existing controllers.