Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020068895 - ADAPTABLE ON-DEPLOYMENT LEARNING PLATFORM FOR DRIVER ANALYSIS OUTPUT GENERATION

Publication Number WO/2020/068895
Publication Date 02.04.2020
International Application No. PCT/US2019/052821
International Filing Date 25.09.2019
IPC
B60W 50/08 2020.01
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
50Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
08Interaction between the driver and the control system
B60W 40/09 2012.01
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
40Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit
08related to drivers or passengers
09Driving style or behaviour
B60W 50/14 2020.01
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
50Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
08Interaction between the driver and the control system
14Means for informing the driver, warning the driver or prompting a driver intervention
CPC
G06N 3/0445
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0445Feedback networks, e.g. hopfield nets, associative networks
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 7/005
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
005Probabilistic networks
H04L 67/10
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
67Network-specific arrangements or communication protocols supporting networked applications
10in which an application is distributed across nodes in the network
H04L 67/12
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
67Network-specific arrangements or communication protocols supporting networked applications
12adapted for proprietary or special purpose networking environments, e.g. medical networks, sensor networks, networks in a car or remote metering networks
H04W 76/10
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
WWIRELESS COMMUNICATION NETWORKS
76Connection management
10Connection setup
Applicants
  • ALLSTATE INSURANCE COMPANY [US]/[US]
Inventors
  • ARAGON, Juan Carlos
  • MADIGAN, Regina
Agents
  • ALMETER, Elizabeth A.
  • BERGHAMMER, Joseph J.
Priority Data
16/580,35324.09.2019US
62/736,78326.09.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) ADAPTABLE ON-DEPLOYMENT LEARNING PLATFORM FOR DRIVER ANALYSIS OUTPUT GENERATION
(FR) PLATEFORME D'APPRENTISSAGE ADAPTABLE SUR DÉPLOIEMENT PERMETTANT LA GÉNÉRATION DE SORTIE D'ANALYSE DE CONDUCTEUR
Abstract
(EN)
Aspects of the disclosure relate to enhanced processing systems for providing dynamic driving metric outputs using improved machine learning methods. A computing platform may receive sensor data from vehicle sensors. The computing platform may generate a pattern deviation output corresponding to an output of a sensor data analysis model, an actual outcome associated with a lowest TTC value, and driving actions that occurred over a prediction horizon corresponding to the pattern deviation output. The computing platform may cluster the pattern deviation outputs to maximize a ratio of inter-cluster variance to intra-cluster variance. The computing platform may train a long short term memory (LSTM) for each cluster, and may verify consistency of the pattern deviation outputs in the respective clusters. After verifying the consistency of the pattern deviation outputs in each cluster, the computing platform may modify the sensor data analysis model to reflect pattern deviation outputs associated with verified consistency.
(FR)
Des aspects de l'invention concernent des systèmes de traitement améliorés permettant de fournir des sorties métriques de conduite dynamique au moyen de procédés d'apprentissage automatique améliorés. Une plateforme informatique peut recevoir des données de capteur provenant de capteurs de véhicule. La plateforme informatique peut générer une sortie d'écart de schéma correspondant à une sortie d'un modèle d'analyse de données de capteur, un résultat réel associé à une valeur de TTC la plus faible et des actions d'entraînement qui se sont produites sur un horizon de prédiction correspondant à la sortie d'écart de schéma. La plateforme informatique peut regrouper les sorties d'écart de schéma afin de développer au maximum un rapport entre une variance inter-grappe et une variance intra-grappe. La plateforme informatique peut entraîner une longue mémoire à court terme (LSTM) correspondant à chaque grappe et peut vérifier la cohérence des sorties d'écart de schéma dans les grappes respectives. Après vérification de la cohérence des sorties d'écart de schéma dans chaque grappe, la plateforme informatique peut modifier le modèle d'analyse de données de capteur afin de refléter des sorties d'écart de schéma associées à une cohérence vérifiée.
Also published as
Latest bibliographic data on file with the International Bureau