公开(公告)号：US12061965B2

公开(公告)日：2024-08-13

申请号：US17687720

申请日：2022-03-07

Applicant: Cognata Ltd.

Inventor： Dan Atsmon ,  Eran Asa ,  Ehud Spiegel

IPC: G06V10/82 ,  G06F18/20 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2415 ,  G06N3/006 ,  G06N5/043 ,  G06N20/00 ,  G06T7/00 ,  G06V10/74 ,  G06V10/774 ,  G06V10/776 ,  G06V10/80 ,  G06V20/56 ,  G06V20/70

CPC classification number: G06N3/006 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/2415 ,  G06F18/285 ,  G06N5/043 ,  G06N20/00 ,  G06T7/0002 ,  G06V10/761 ,  G06V10/774 ,  G06V10/776 ,  G06V10/809 ,  G06V10/82 ,  G06V20/56 ,  G06V20/70 ,  G06T2207/30168

Abstract: A method for training a model for generating simulation data for training an autonomous driving agent, comprising: analyzing real data, collected from a driving environment, to identify a plurality of environment classes, a plurality of moving agent classes, and a plurality of movement pattern classes; generating a training environment, according to one environment class; and in at least one training iteration: generating, by a simulation generation model, a simulated driving environment according to the training environment and according to a plurality of generated training agents, each associated with one of the plurality of agent classes and one of the plurality of movement pattern classes; collecting simulated driving data from the simulated environment; and modifying at least one model parameter of the simulation generation model to minimize a difference between a simulation statistical fingerprint, computed using the simulated driving data, and a real statistical fingerprint, computed using the real data.

公开(公告)号：US11270165B2

公开(公告)日：2022-03-08

申请号：US17286526

申请日：2019-10-15

Applicant: Cognata Ltd.

Inventor： Dan Atsmon ,  Eran Asa ,  Ehud Spiegel

IPC: G06K9/62 ,  G06N20/00 ,  G06N5/04 ,  G06T7/00

Abstract: A method for training a model for generating simulation data for training an autonomous driving agent, comprising: analyzing real data, collected from a driving environment, to identify a plurality of environment classes, a plurality of moving agent classes, and a plurality of movement pattern classes; generating a training environment, according to one environment class; and in at least one training iteration: generating, by a simulation generation model, a simulated driving environment according to the training environment and according to a plurality of generated training agents, each associated with one of the plurality of agent classes and one of the plurality of movement pattern classes; collecting simulated driving data from the simulated environment; and modifying at least one model parameter of the simulation generation model to minimize a difference between a simulation statistical fingerprint, computed using the simulated driving data, and a real statistical fingerprint, computed using the real data.

公开(公告)号：US11694388B2

公开(公告)日：2023-07-04

申请号：US17383465

申请日：2021-07-23

Applicant: Cognata Ltd.

Inventor： Dan Atsmon ,  Eran Asa ,  Ehud Spiegel

IPC: G06T15/10 ,  G06T7/55 ,  G06T7/579 ,  G06N3/08 ,  G06V20/56 ,  G06F18/21 ,  G06F18/24 ,  G06F18/28 ,  G05D1/00 ,  G05D1/02 ,  G06N3/04 ,  G06T3/00 ,  G06F18/214

CPC classification number: G06T15/10 ,  G05D1/0088 ,  G05D1/0246 ,  G06F18/217 ,  G06F18/2148 ,  G06F18/24 ,  G06F18/28 ,  G06N3/04 ,  G06N3/08 ,  G06T3/0018 ,  G06T7/55 ,  G06T7/579 ,  G06V20/56 ,  G05D2201/0213 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30252 ,  G06V2201/07

Abstract: A system for creating synthetic data for testing an autonomous system, comprising at least one hardware processor adapted to execute a code for: using a machine learning model to compute a plurality of depth maps based on a plurality of real signals captured simultaneously from a common physical scene, each of the plurality of real signals are captured by one of a plurality of sensors, each of the plurality of computed depth maps qualifies one of the plurality of real signals; applying a point of view transformation to the plurality of real signals and the plurality of depth maps, to produce synthetic data simulating a possible signal captured from the common physical scene by a target sensor in an identified position relative to the plurality of sensors; and providing the synthetic data to at least one testing engine to test an autonomous system comprising the target sensor.

公开(公告)号：US12260489B2

公开(公告)日：2025-03-25

申请号：US18202970

申请日：2023-05-29

Applicant: Cognata Ltd.

Inventor： Dan Atsmon ,  Eran Asa ,  Ehud Spiegel

IPC: G06T15/10 ,  G05D1/00 ,  G06F18/21 ,  G06F18/214 ,  G06F18/24 ,  G06F18/28 ,  G06N3/04 ,  G06N3/08 ,  G06T3/047 ,  G06T7/55 ,  G06T7/579 ,  G06V20/56

Abstract: A system for creating synthetic data for testing an autonomous system, comprising at least one hardware processor adapted to execute a code for: using a machine learning model to compute a plurality of depth maps based on a plurality of real signals captured simultaneously from a common physical scene, each of the plurality of real signals are captured by one of a plurality of sensors, each of the plurality of computed depth maps qualifies one of the plurality of real signals; applying a point of view transformation to the plurality of real signals and the plurality of depth maps, to produce synthetic data simulating a possible signal captured from the common physical scene by a target sensor in an identified position relative to the plurality of sensors; and providing the synthetic data to at least one testing engine to test an autonomous system comprising the target sensor.

公开(公告)号：US11100371B2

公开(公告)日：2021-08-24

申请号：US16594200

申请日：2019-10-07

Applicant: Cognata Ltd.

Inventor： Dan Atsmon ,  Eran Asa ,  Ehud Spiegel

IPC: G06K9/62 ,  G06T7/55 ,  G06T7/579 ,  G06D1/02 ,  G06N3/04 ,  G06N3/08 ,  G05D1/00 ,  G06K9/00 ,  G06T3/00 ,  G05D1/02

Abstract: A system for creating synthetic data for testing an autonomous system, comprising at least one hardware processor adapted to execute a code for: using a machine learning model to compute a plurality of depth maps based on a plurality of real signals captured simultaneously from a common physical scene, each of the plurality of real signals are captured by one of a plurality of sensors, each of the plurality of computed depth maps qualifies one of the plurality of real signals; applying a point of view transformation to the plurality of real signals and the plurality of depth maps, to produce synthetic data simulating a possible signal captured from the common physical scene by a target sensor in an identified position relative to the plurality of sensors; and providing the synthetic data to at least one testing engine to test an autonomous system comprising the target sensor.