US 11,886,782 B2
Dynamics model for globally stable modeling of system dynamics
Gaurav Manek, Pittsburgh, PA (US); Jeremy Zieg Kolter, Pittsburgh, PA (US); and Julia Vinogradska, Stuttgart (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE); and Carnegie Mellon University, Pittsburgh, PA (US)
Filed on Jul. 20, 2020, as Appl. No. 16/933,245.
Claims priority of application No. 19190105 (EP), filed on Aug. 5, 2019.
Prior Publication US 2021/0042457 A1, Feb. 11, 2021
Int. Cl. G06F 30/27 (2020.01); G06N 20/00 (2019.01); G05B 13/02 (2006.01); G05B 13/04 (2006.01); G06N 3/08 (2023.01); G06N 5/046 (2023.01)
CPC G06F 30/27 (2020.01) [G05B 13/027 (2013.01); G05B 13/048 (2013.01); G06N 3/08 (2013.01); G06N 5/046 (2013.01); G06N 20/00 (2019.01)] 13 Claims
OG exemplary drawing
 
1. A machine learning system for training a dynamics model to learn dynamics of a physical system by learning to infer a future state of the physical system and/or its environment based on a current state of the physical system and/or its environment, the machine learning system comprising:
an input interface configured for accessing:
training data representing a time-series of states of the physical system and/or its environment; and
model data defining a machine learnable dynamics model which includes a machine learnable Lyapunov function; and
a processor subsystem configured to learn the dynamics model based on time- sequential pairs of states so as to learn to infer a future state of the physical system and/or its environment based on the current state, wherein the learning is constrained to provide a globally stable modelling of dynamics of the physical system by jointly learning the dynamics model and the Lyapunov function so that values of the learned Lyapunov function decrease along all trajectories of states inferred by the learned dynamics model;
wherein the processor subsystem is configured to jointly learn the dynamics model and the Lyapunov function by learning, as the dynamics model, a projection of nominal dynamics of the physical system, which are learned based on the time-series of states, onto a function that fulfills a Lyapunov condition as defined by the Lyapunov function; and
wherein the projection is an orthogonal projection onto a halfspace.