Combination alerts

Patent metadata

Field	Value
Publication number	US-12444305-B2
Application number	US-202117796287-A
Country	US
Kind code	B2
Filing date	Jan 29, 2021
Priority date	Jan 29, 2020
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

Systems and methods are provided for intelligent driving monitoring systems, advanced driver assistance systems and autonomous driving systems, and providing alerts to the driver of a vehicle. Combinations of co-occurring driving events may be detected and used to warn on anomalies, prevent accidents, provide feedback to the driver, and in general provide a safer driver experience.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, by a computer, sensor data of a vehicle and/or visual data of an environment outside the vehicle;
detecting, by the computer in the vehicle, a combination driving event, wherein detecting the combination driving event comprises:
detecting, by the computer, from the sensor data and/or visual data that a first driving event occurred at a first time;
detecting, by the computer, from the sensor data and/or visual data that a second driving event occurred at a second time, wherein the second time is within a predetermined time interval of the first time; wherein the first driving event belongs to a first class of driving events, and wherein the second driving event belongs to a second class of driving events;
recognizing, by the computer, an appropriate braking response to a detected hazard based on the detected first driving event and second driving event; and
modifying, by the computer and in response to the detection of the combination driving event, a valance parameter affecting a report to a remote device, wherein the report comprises an indication that the second driving event was detected at the second time, wherein the valence parameter is modified to be positive and corresponds to positive feedback for the combination driving event, and wherein the valence parameter affects a data transmission likelihood; and

determining, based on a modified value of the data transmission likelihood parameter, whether to transmit the sensor data and/or visual data of the second driving event to the remote device based on the modified value of the data transmission likelihood parameter satisfying a threshold value.

2. The method of claim 1 , wherein the sensor data and/or visual data comprises video data of the second driving event.

3. The method of claim 2 , wherein the modified value of the data transmission likelihood parameter is higher than a value of a predetermined data transmission likelihood of driving events belonging to the second class of driving events.

4. The method of claim 2 , wherein the modified value of the data transmission likelihood parameter is lower than a value of a predetermined data transmission likelihood of driving events belonging to the second class of driving events.

5. The method of claim 4 , wherein, based on the modified value of the data transmission likelihood parameter, transmission, by the computer and to the remote device, of the sensor data and/or visual data corresponding the second driving event is suppressed.

6. The method of claim 2 , wherein the data transmission likelihood parameter is modified from an initial value to the modified value based on the detection of the combination event, and wherein the initial value is a predetermined throttling parameter corresponding to the second class of driving events.

7. The method of claim 2 , wherein the data transmission likelihood parameter is modified by selecting a first throttling parameter from a plurality of throttling parameters, the first throttling parameter corresponding to a class of combination driving events to which the combination driving event belongs, and wherein the plurality further comprises a second throttling parameter corresponding to the second class of driving events.

8. The method of claim 1 , wherein the second class of driving events is a hard-braking event class; and wherein the method further comprises:
determining, by the computer, that a driver of the vehicle engaged in a risk mitigating maneuver based on the detection of the second driving event.

9. The method of claim 8 , wherein detecting that the first driving event occurred comprises:
determining that the vehicle is travelling on a road and approaching an intersection with a second road;
receiving, by the computer, the visual data from a road-facing camera on the vehicle;
detecting, by the computer and based on the visual data, an intersection stop line corresponding to a second road;
detecting, by the computer, a second vehicle travelling on the second road; and
determining, by the computer, that the second vehicle failed to come to a complete stop before the intersection stop line based on the visual data.

10. The method of claim 1 , wherein the valence parameter affects at least one of:
a summary driving score for the driver; or
a likelihood that data corresponding to the combination driving event will be incorporated into:
a positive recognition report for the driver.

11. The method of claim 1 , wherein the valence parameter affects a likelihood that data corresponding to the combination driving event will be incorporated into a training set comprising video of risk mitigating human driving actions.

12. The method of claim 1 , further comprising:
transmitting, by the computer, the report to the remote device, wherein the report further comprises an indication of the detected combination driving event; and
determining, at the remote device, whether to request corresponding the sensor data and/or visual data from the computer in the vehicle, based at least in part on the report.

13. The method of claim 1 , further comprising:
receiving, by the computer, the visual data from a camera on the vehicle, wherein the visual data comprises video data of the second driving event.

14. The method of claim 13 , wherein a first duration of transmitted videos for driving events of the first class is characterized by a first context interval, a second typical duration of transmitted videos for driving events of the second class is characterized by a second context interval, and wherein the method further comprises:
determining a duration of the video data based on the first time, the second time, the first context interval and the second context interval.

15. The method of claim 14 , wherein the duration of the video data comprises a union of the first context interval and the second context interval, and further comprises any gap between the first context interval and the second context interval.

16. The method of claim 14 , wherein the duration of the video data comprises an interval when the first context interval and the second context interval overlap.

17. The method of claim 1 , wherein detecting the first driving event comprises:
determining, by the computer, a position of the vehicle; and
determining, by the computer and based on the position, that the vehicle has entered a location where the sensor data and/or visual data corresponding to the combination driving event should be processed.

18. The method of claim 17 , further comprising:
querying, by the computer and based on the position of the vehicle, a map of positions at which driving events of the second class tend to occur; and
determining, by the computer and based on the query, a likelihood that the second driving behavior will be observed within the predetermined time interval, wherein the determination that the sensor data and/or visual data should be processed is based on the likelihood that the second driving behavior will be observed.

19. The method of claim 17 , wherein detecting the second driving event comprises:
receiving, by the computer, the visual data from a camera on the vehicle; and
processing, by the computer, the visual data to detect the second driving event.

20. The method of claim 17 , wherein the position is associated with a traffic sign or a traffic light.

21. The method of claim 1 , wherein the first driving event comprises the vehicle approaching

Assignees

• Netradyne Inc

Inventors

• Agrawal Avneesh
• Annapureddy Venkata Sreekanta Reddy
• Julian David Jonathan
• Yedla Arvind
• Rai Vinay Kumar
• Campos Michael

Classifications

• G08G1/096791

  where the origin of the information is another vehicle · CPC title

• G08G1/096775

  where the origin of the information is a central station · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G06V10/82

  using neural networks · CPC title