公开(公告)号：US20230228863A1

公开(公告)日：2023-07-20

申请号：US18155735

申请日：2023-01-18

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Omer Jackobson ,  Kessem Meir ,  Tomer Livne ,  Oz Sharlin ,  Kirill Diagilev ,  Roman Shklyar ,  Yarden Zohar ,  Matan Ron ,  Michael Cohen

IPC: G01S13/42 ,  G05D1/00 ,  G05D1/02

CPC classification number: G01S13/426 ,  G05D1/0088 ,  G05D1/0257

Abstract: A method for fusion of radar and visual information, the method comprises: obtaining visual information and radar information about a three dimensional (3D) space located within a field of view of a camera that acquired the visual information and within a field of view of a radar that acquired the radar information; finding, based on the visual information, estimated visual-detection-based (VDB) objects and estimated VDB locations of the estimated VDB objects within the 3D space; wherein the estimated VDB locations exhibit a distance ambiguity; determining hybrid-detection-based (HDB) objects and HDB locations of the HDB objects, based on (i) the radar information, (ii) the estimated VDB objects, and (iii) the estimated VDB locations of the VDB objects.

公开(公告)号：US11700356B2

公开(公告)日：2023-07-11

申请号：US16544942

申请日：2019-08-20

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: G05D1/02 ,  G05D1/00 ,  G08G1/16 ,  G06K9/00 ,  G06T7/73 ,  H04N7/18 ,  G06T7/246 ,  G06N3/04 ,  H04W4/48 ,  H04W4/46 ,  G06N3/08 ,  G06V20/58 ,  G06V40/10 ,  G06F18/23 ,  G06F18/25 ,  G06F18/28 ,  G06F18/211 ,  G06F18/214 ,  G06V10/762 ,  G06V10/764 ,  G06V10/82 ,  G06V10/20 ,  G06V20/56 ,  H04L67/12

CPC classification number: H04N7/183 ,  G05D1/0061 ,  G05D1/0088 ,  G05D1/0094 ,  G05D1/0238 ,  G05D1/0253 ,  G05D1/0276 ,  G05D1/0287 ,  G06F18/211 ,  G06F18/214 ,  G06F18/23 ,  G06F18/25 ,  G06F18/28 ,  G06N3/04 ,  G06N3/08 ,  G06T7/246 ,  G06T7/74 ,  G06V10/255 ,  G06V10/762 ,  G06V10/764 ,  G06V10/82 ,  G06V20/56 ,  G06V20/58 ,  G06V40/103 ,  G08G1/166 ,  H04N7/185 ,  H04W4/46 ,  H04W4/48 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30261 ,  G06V2201/08 ,  G08G1/162 ,  G08G1/165 ,  H04L67/12

Abstract: A method for finding at least one trigger for human intervention in a control of a vehicle, the method may include receiving, from a plurality of vehicles, and by an I/O module of a computerized system, visual information acquired during situations that are suspected as situations that require human intervention in the control of at least one of the plurality of vehicles; determining, based at least on the visual information, the at least one trigger for human intervention; and transmitting to one or more of the plurality of vehicles, the at least one trigger.

公开(公告)号：US11673583B2

公开(公告)日：2023-06-13

申请号：US16731398

申请日：2019-12-31

Applicant: AUTOBRAINS TECHNOLOGIES LTD.

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: G08G1/16 ,  G08G1/056 ,  G06N20/00 ,  B60W60/00 ,  G06V20/59 ,  G06V20/58 ,  G06F18/23 ,  G06F18/23213 ,  G06V10/44 ,  G06V10/20 ,  G05D1/00 ,  G08G1/048 ,  B60W40/06 ,  B60W30/095 ,  B60W50/14 ,  G08G1/0962 ,  B60W40/08 ,  G05D1/02 ,  B60W40/02 ,  H04W4/46 ,  B60W30/09 ,  G05B13/02 ,  G06N3/08 ,  G07C5/02 ,  G06N5/04 ,  G06V20/56 ,  G06F18/22 ,  G06F18/2431 ,  G06N3/042

CPC classification number: B60W60/0025 ,  G06F18/23 ,  G06F18/23213 ,  G06V10/255 ,  G06V10/454 ,  G06V20/58 ,  G06V20/597 ,  G08G1/056 ,  G08G1/162 ,  G08G1/165 ,  G08G1/166 ,  B60W30/09 ,  B60W30/0956 ,  B60W40/02 ,  B60W40/06 ,  B60W40/08 ,  B60W50/14 ,  B60W60/0011 ,  B60W60/0016 ,  B60W60/0017 ,  B60W60/0051 ,  B60W2040/0872 ,  B60W2540/10 ,  B60W2540/12 ,  B60W2540/18 ,  B60W2554/00 ,  B60W2554/4023 ,  B60W2554/4046 ,  B60W2556/65 ,  G05B13/029 ,  G05D1/0044 ,  G05D1/0061 ,  G05D1/0088 ,  G05D1/0214 ,  G05D1/0293 ,  G05D2201/0213 ,  G06F18/22 ,  G06F18/2431 ,  G06N3/042 ,  G06N3/08 ,  G06N5/04 ,  G06N20/00 ,  G06T2207/30261 ,  G06V20/56 ,  G06V20/584 ,  G07C5/02 ,  G08G1/048 ,  G08G1/09626 ,  H04W4/46

Abstract: Using a read sensor to sense wrong-way driving. A method may include sensing, by a rear sensor of a vehicle, an environment of the vehicle to provide rear sensed information; processing the rear sensed information to provide at least one rear-sensed vehicle progress direction indications; generating or receiving at least one front-sensed vehicle progress direction indications; wherein the at least one front-sensed vehicle progress direction indications is generated by processing front-sensed information acquired during right-way progress; comparing at least one rear-sensed vehicle progress direction indications to the at least one front-sensed vehicle progress direction indications to determine whether the vehicle is wrong-way driving; and responding to the finding of the wrong-way driving.

公开(公告)号：US20230162512A1

公开(公告)日：2023-05-25

申请号：US18052555

申请日：2022-11-03

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Omer Jackobson ,  Oz Sharlin ,  Tomer Livne

IPC: G06V20/56 ,  G06V10/20 ,  G06V10/44 ,  G06V10/764 ,  G06V10/80

CPC classification number: G06V20/588 ,  G06V10/255 ,  G06V10/44 ,  G06V10/764 ,  G06V10/809 ,  B60W60/0013

Abstract: A method for detecting a road-boundary based on radar information and visual information, the method may include (a) estimating, based on the visual information obtained by a visual sensor, locations of road-boundary points up to a first distance from the visual sensor; wherein a distance ambiguity of visual based location determination of road-boundary points with the first distance range does not exceed a predefined ambiguity threshold; wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds a predefined ambiguity threshold; (b) estimating, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; and (c) determining the shape and position of the road-boundary based on the locations of the road-boundary points within the first range distance.

公开(公告)号：US20230119374A1

公开(公告)日：2023-04-20

申请号：US18045820

申请日：2022-10-11

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Tom TABAK

IPC: G06T7/10 ,  G06N3/08

Abstract: A method for neural network based image processing, the method may include obtaining multiple two dimensional (2D) segments of a sensed information unit, each 2D segment has a segment location within the sensed information unit; converting each 2D segments to a segment vector; generating multiple segments intermediate results by repeating, for each segment vector: (a) concatenating the segment vector with associated segment location information to provide a first segment concatenated vector; and (b) multiplying the first segment concatenated vector by a learnable embedding matrix to provide a segment intermediate result; concatenating the multiple segments intermediate results with associated segment identifiers to provide a sensed information unit result; and feeding the sensed information unit result to a second layer of a neural network.

公开(公告)号：US11613261B2

公开(公告)日：2023-03-28

申请号：US16729309

申请日：2019-12-28

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: B60W40/09 ,  B60W30/08 ,  G06N20/00 ,  G06N5/025 ,  B60W60/00

Abstract: A method for detecting an improperly driven vehicle, that may include detecting, based on information sensed by at least one sensor of a monitoring vehicle, a behavior of a monitored vehicle; determining whether the behavior of the monitored vehicle is an improper behavior; generating, by a processing unit of the monitoring vehicle, an improper vehicle label that comprises a unique vehicle identifier that identifies the monitored vehicle, when the behavior of the monitored vehicle is determined to be improper; and sending the improper vehicle label to at least one shared database accessible to other vehicles.

公开(公告)号：US20230059047A1

公开(公告)日：2023-02-23

申请号：US17821145

申请日：2022-08-19

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: B60W30/12 ,  G06V20/56

Abstract: A method for lane departure assistance, the method may include obtaining sensed information about an environment of the first vehicle, by one of more vehicle sensors of a first vehicle; wherein the environment of the first vehicle comprises a passing lane and a current lane in which the first vehicle is positioned; determining, by a computer of the first vehicle, whether the first vehicle can successfully and lawfully bypass a second vehicle; wherein the determining is executed before starting the bypass of the second vehicle and is based on the sensed information, one or more driving laws, and one or more first vehicle mechanical parameters; generating a driver perceivable indicator that is indicative of the determining; sensing that the driver initiates a bypass of the second vehicle; evaluating, following the start of the bypass of the second vehicle and during at least a majority of the bypass, whether the first vehicle can successfully and lawfully complete the bypass of the second vehicle; and generating another driver perceivable indicator that is indicative of the evaluating.

公开(公告)号：US20230045885A1

公开(公告)日：2023-02-16

申请号：US17805847

申请日：2022-06-07

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Tom TABAK

IPC: G06V20/56 ,  G06V10/82

Abstract: A method for context based lane prediction, the method may include obtaining sensed information regarding an environment of the vehicle; providing the sensed information to a second trained machine learning process; and locating one or more lane boundaries by the second trained machine learning process. The second trained machine learning process is generated by: performing a self-supervised training process, using a first dataset, of a first machine learning process to provide a first trained machine learning process; wherein the first trained machine learning process comprises a first encoder portion and a first decoder portion; replacing the first decoder portion by a second decoder portion to provide a second machine learning process; and performing an additional training process, using a second dataset that is associated with lane boundary metadata, of the second machine learning process to provide a second trained machine learning process.

公开(公告)号：US20220388538A1

公开(公告)日：2022-12-08

申请号：US17805852

申请日：2022-06-07

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: B60W60/00 ,  B60H1/00 ,  B60Q3/80 ,  B60R16/037 ,  B60W10/30

Abstract: A method that may include receiving driving information and environmental metadata indicative of information sensed by the vehicle; detecting multiple driving events encountered during the driving over the path; determining driving events; for each driving event, determining a comfort based autonomous driving pattern information; for each driving event, determining an driving event identifier; and storing in at least one data structure a driving event identifier for each one of the multiple types of driving events, and a comfort based autonomous driving pattern information.

公开(公告)号：US20220388479A1

公开(公告)日：2022-12-08

申请号：US17805851

申请日：2022-06-07

Applicant: AUTOBRAINS TECHNOLOGIES LTD

Inventor： Igal Raichelgauz ,  Karina Odinaev

IPC: B60R25/25 ,  B60R25/24 ,  B60R25/102 ,  G07C9/37 ,  G06V40/16 ,  G06V10/70

Abstract: A method for face recognition based vehicle access control. The method may include acquiring one or more images of at least a face of a person that is positioned outside the vehicle and accesses a door of the vehicle in order to determine, based on the one or more images, whether the person is allowed to enter the vehicle. The determination may include matching the face of the person to a database of faces of allowed persons. The database is generated during a machine learning process that involves monitoring persons within the vehicle; and then granting access to the vehicle when determining that the person is allowed to enter the vehicle.