Showing 2023Show all
3 papers · 1 filter
cs.RO2023
Forward Dynamics Estimation from Data-Driven Inverse Dynamics Learning
Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli +2
In this paper, we propose to estimate the forward dynamics equations of mechanical systems by learning a model of the inverse dynamics and estimating individual dynamics components…
eess.SY2023
A Learning-based Nonlinear Model Predictive Controller for a Real Go-Kart based on Black-box Dynamics Modeling through Gaussian Processes
Enrico Picotti, Enrico Mion, Alberto Dalla Libera +5
Lately, Nonlinear Model Predictive Control (NMPC)has been successfully applied to (semi-) autonomous driving problems and has proven to be a very promising technique. However, accu…
cs.RO2023
Learning Control from Raw Position Measurements
Fabio Amadio, Alberto Dalla Libera, Daniel Nikovski +2
We propose a Model-Based Reinforcement Learning (MBRL) algorithm named VF-MC-PILCO, specifically designed for application to mechanical systems where velocities cannot be directly…