IP Library Granted Patent US 11,613,261
Granted Patent B2
US 11,613,261 · App. 16/729,309 · Granted Mar 28, 2023

Generating a database and alerting about improperly driven vehicles

Inventors: Igal Raichelgauz (Tel Aviv, IL); Karina Odinaev (Tel Aviv, IL)
Assignee: AUTOBRAINS TECHNOLOGIES LTD
B60W40/09B60W30/08B60W60/007G06N5/025G06N20/00B60W2556/65
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,613,261
App. No.
16/729,309
Granted
Mar 28, 2023
Kind
B2
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.

Claims (32)

1. A method for detecting an improperly driven vehicle, the method comprises:

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; wherein the determining is based on reactions of a driver of the monitored vehicle that are indicative that the driver is stressed;

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; wherein a storage of improper vehicle labels in the at least one shared database is limited by a limitation learnt by a machine learning process.

2. The method according to claim 1 , wherein the determining comprises applying, by the processing unit, a machine learning process that was trained on vehicle behaviors that led to accidents.

3. The method according to claim 1 , wherein the determining comprises applying, by the processing unit, another machine learning process that was trained on vehicle behaviors that led to at least one out of accidents and near accidents.

4. The method according to claim 1 , wherein the determining comprises applying, by the processing unit, a rule based process that comprises traffic rules and regulations.

5. The method according to claim 1 , wherein the determining comprises monitoring a response of a driver of the monitored vehicle to the behavior of the monitored vehicle.

6. The method according to claim 1 , wherein the monitoring vehicle is an autonomous vehicle having an autonomous driving policy that defines at least one monitored vehicle behavior as improper, and wherein the determining is responsive to the autonomous driving policy.

7. The method according to claim 1 , wherein the monitoring vehicle is an autonomous vehicle having an autonomous driving policy that imposes at least one limit on autonomous driving of the monitoring vehicle, wherein the determining is responsive to the at least one limit.

8. The method according to claim 1 , comprising sending the improper vehicle label via a vehicle to vehicle communication link.

9. The method according to claim 1 , wherein the improper vehicle label comprise information about at least one out of the improper behavior, a time of occurrence of the improper behavior, a type of improper behavior or a severity of the improper behavior.

10. The method according to claim 1 , wherein a storage of improper vehicle labels in the at least one shared database is limited by a limitation regarding an overall number of improper vehicle labels within the at least one shared database.

11. The method according to claim 1 , wherein a storage of improper vehicle labels in the at least one shared database is limited by a limitation regarding an overall number of improper vehicle labels of a certain type of improper behavior within the at least one shared database.

12. The method according to claim 1 comprising defining a behavior of the monitored vehicle as a proper behavior when the behavior is a normal behavior of vehicles, even when the behavior brakes a traffic rule.

13. The method according to claim 1 , wherein the improper vehicle label does not include information about the improper behavior.

14. A non-transitory computer readable medium for detecting an improperly driven vehicle, the non-transitory computer readable medium stores instructions for:

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; wherein a storage of improper vehicle labels in the at least one shared database is limited by a limitation learnt by a machine learning process.

15. The non-transitory computer readable medium according to claim 14 , wherein the determining comprises applying, by the processing unit, a machine learning process that was trained on vehicle behaviors that led to accidents.

16. The non-transitory computer readable medium according to claim 14 , wherein the determining comprises applying, by the processing unit, another machine learning process that was trained on vehicle behaviors that led to at least one out of accidents and near accidents.

17. The non-transitory computer readable medium according to claim 14 , wherein the improper vehicle label comprise information about at least one out of the improper behavior, a time of occurrence of the improper behavior, a type of improper behavior or a severity of the improper behavior.

18. The non-transitory computer readable medium according to claim 14 , wherein the determining is based on reactions of a driver if the monitored vehicle that are indicative that the drive is stressed.

19. A method for detecting an improperly driven vehicle, the method comprises:

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; wherein the determining is based on reactions of a driver of the monitored vehicle that are indicative that the driver is stressed;

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;

sending the improper vehicle label to at least one shared database accessible to other vehicles; and

defining a behavior of the monitored vehicle as a proper behavior when the behavior is a normal behavior of vehicles, even when the behavior brakes a traffic rule.

Assignments (2)
CHANGE OF NAME Recorded Jan 3, 2023
From: CARTICA AI LTD
To: AUTOBRAINS TECHNOLOGIES LTD
Reel/Frame 062266/0553 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 10, 2020
From: RAICHELGAUZ, IGAL; ODINAEV, KARINA
To: CARTICA AI LTD
Reel/Frame 052132/0600 →
Continuity (5)
Continuation PCTIB2019058207 · Sep 27, 2019
Provisional Application 62750822 · Oct 26, 2018
Provisional Application 62747147 · Oct 18, 2018
Provisional Application 62727112 · Sep 5, 2018
Related Publication 20210053573A1 · Feb 25, 2021
Cited By (3)
US 12,271,200 US 12,606,158 US 12,680,817