The invention relates to a computer-implemented prediction method (900) of making time-series predictions for controlling and/or monitoring a computer-controlled system, e.g., a semi-autonomous vehicle. The method uses a time series of one or more observed states. A state comprises values of measurable quantities of multiple interacting objects. Based on the observed states, values of time-invariant latent features for the multiple objects are determined, for example, according to an encoder model. A decoder model is then used to predict at least one next state. This involves applying a trained graph model to obtain a first prediction contribution based on an object's interactions with other objects, and applying a trained function to obtain a second prediction contribution based just on information about the object itself. Based on the predicted next state, output data is generated for use in controlling and/or monitoring the computer-controlled system.
MAKING TIME-SERIES PREDICTIONS USING A TRAINED DECODER MODEL
TREFFEN VON ZEITREIHENVORHERSAGEN UNTER VERWENDUNG EINES TRAINIERTEN DECODIERERMODELLS
ÉTABLISSEMENT DE PRÉVISIONS CHRONOLOGIQUES À L'AIDE D'UN MODÈLE DE DÉCODEUR FORMÉ
2021-12-29
Patent
Electronic Resource
English
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V |
MAKING TIME-SERIES PREDICTIONS USING A TRAINED DECODER MODEL
European Patent Office | 2021
|European Patent Office | 2016
|European Patent Office | 2016
|Predictions of Urban Volumes in Single Time Series
Online Contents | 2010
|