Vehicle accident avoidance system

• US 9,868,393 B2
• Filed: 12/10/2015
• Issued: 01/16/2018
• Est. Priority Date: 12/10/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bahgat, Mohamed A., Emam, Ossama, Hanafy, Ayman S., Noeman, Sara A.
• Primary Examiner(s): SMALL, NAOMI J
• Application Number:
  US14/965,072
• Publication Number:
  US 20170166123A1
• Time in Patent Office: 768 Days
• Field of Search: 340436
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• CPC Class Codes: B60W 2050/0029 Mathematical model of the driver
• CPC Class Codes: B60W 2540/20 Direction indicator values
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/804 Relative longitudinal speed
• CPC Class Codes: B60W 2900/00 Indexing codes relating to the purpose of, or problem solved of road vehicle drive control systems not otherwise provided for in groups B60W30/00
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 50/0097 Predicting future conditions

Abstract

Method and system are provided for vehicle accident avoidance carried out with respect to a host vehicle by modeling behavior. The method includes: monitoring a surrounding environment of the host vehicle and detecting other vehicles in a vicinity of the host vehicle by at least one visual sensor. The method further includes: estimating a speed and direction of each of the detected vehicles; calculating one or more projected paths of each of the detected vehicles based on their current estimated speed and direction, the current monitored surrounding environment, and other vehicle projected paths; estimating a probability of intersection of each projected path with the host vehicle; and providing an alert or action to the host vehicle if there is a high probability of intersection.

Claims

1. A computer-implemented method for vehicle accident avoidance carried out with respect to a host vehicle, comprising:

monitoring a surrounding environment of the host vehicle;

detecting other vehicles in the surrounding environment of the host vehicle by at least one visual sensor;

estimating a speed and direction of each of the detected vehicles;

calculating one or more projected paths of each of the detected vehicles based on their current estimated speed and direction, the monitored surrounding environment, and other detected vehicle projected paths, wherein the calculating further comprises;

uniquely identifying a detected vehicle;

retrieving a historical-data-based model for the uniquely identified, detected vehicle, the historical-data-based model comprising historical vehicle travel route data and historical vehicle-moving behavioral data along those routes for the uniquely identified, detected vehicle; and

generating one or more projected paths for the uniquely identified, detected vehicle based, at least in part, on the historical-data-based model for the uniquely identified, detected vehicle, including the historical vehicle travel route data and the historical vehicle-moving behavioral data along those routes;

estimating a probability of intersection of each projected path with the host vehicle; and

providing an alert or action to the host vehicle if there is a high probability of intersection.

2. The method as claimed in claim 1, further including:

converting the estimated speed and direction of each of the detected vehicles into a canonical form;

comparing the canonical form with known patterns of vehicles with known paths;

identifying a match for the canonical form with a known pattern of vehicles with known paths; and

generating one or more projected paths based on the known paths.

3. The method as claimed in claim 1, further including:

classifying a type of each detected vehicle;

retrieving an appropriate model for the type of each of the detected vehicles; and

generating one or more projected paths based on the appropriate models.

4. The method as claimed in claim 1, wherein monitoring a surrounding environment of the host vehicle includes one or more of the group of:

monitoring the road using the one or more visual sensors for hazards;

monitoring route parameters based on map resources;

monitoring weather and/or visibility conditions.

5. The method as claimed in claim 1, wherein estimating a speed and direction of each of the detected vehicles includes:

obtaining a current speed of the host vehicle;

at regular time intervals, calculating and storing the distance between the host vehicle and the detected vehicles;

referencing stored distances; and

estimating motion of each detected vehicle in horizontal and vertical directions.

6. The method as claimed in claim 1, including:

providing an alert or action to the host vehicle if there is an extreme hazard is detected.

7. The method of claim 1, wherein the uniquely identifying comprises uniquely identifying one or more physical characteristics of the detected vehicle.

8. The method of claim 1, wherein the uniquely identifying comprises reading a license plate of the detected vehicle.

9. A system for vehicle accident avoidance, comprising:

a memory; and

a processor communicatively coupled to the memory, wherein the system performs a method comprising;

monitoring a surrounding environment of a host vehicle;

detecting other vehicles in the surrounding environment of the host vehicle by at least one visual sensor;

estimating a speed and direction of each of the detected vehicles;

calculating one or more projected paths of each of the detected vehicles based on their current estimated speed and direction, the monitored surrounding environment, and other detected vehicle projected paths, wherein the calculating further comprises;

uniquely identifying a detected vehicle;

retrieving a historical-data-based model for the uniquely identified, detected vehicle, the historical-data-based model comprising historical vehicle travel route data and historical vehicle-moving behavioral data along those routes for the uniquely identified, detected vehicle; and

generating one or more projected paths for the uniquely identified, detected vehicle based, at least in part, on the historical-data-based model for the uniquely identified, detected vehicle, including the historical vehicle travel route data and the historical vehicle-moving behavioral data along those routes;

estimating a probability of intersection of each projected path with the host vehicle; and

providing an alert or action to the host vehicle if there is a high probability of intersection.

10. The system as claimed in claim 9, further including:

converting the estimated speed and direction of each of the detected vehicles into a canonical form;

comparing the canonical form with known patterns of vehicles with known paths;

identifying a match for the canonical form with a known pattern of vehicles with known paths; and

generating one or more projected paths based on the known paths.

11. The system as claimed in claim 9, further including:

classifying a type of each detected vehicle;

retrieving an appropriate model for the type of each of the detected vehicles; and

generating one or more projected paths based on the appropriate models.

12. The system as claimed in claim 9, wherein estimating the speed and direction of each of the detected vehicles comprises:

obtaining a current speed of the host vehicle;

at regular time intervals, calculating and storing the distance between the host vehicle and the detected vehicles;

referencing stored distances; and

estimating motion of each detected vehicle in horizontal and vertical directions.

13. The system as claimed in claim 9, wherein the system is provided as an onboard system for the host vehicle, and further:

accesses a remote storage for the historical-data-based model, and caches a retrieved subset of the historical-data-based model.

14. The system as claimed in claim 13, further including checking for required data before accessing the remote storage for retrieval of the required data.

15. The system as claimed in claim 13, wherein the accessing uses a mobile communication network.

16. The system as claimed in claim 13, further including providing access to local storage of the historical-data-based-model at the onboard system and updating the local storage periodically from the remote storage via a local area network communication.

17. The system as claimed in claim 9, wherein the system includes a remote modeling system in which monitored vehicle information is used to model vehicle behavior for types and individual identifications of vehicles.

18. The system as claimed in claim 9, wherein the system is provided remotely to the host vehicle.

19. The system as claimed in claim 9, providing an alert or action to the host vehicle if there is an extreme hazard is detected.

20. A computer program product for vehicle accident avoidance, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

monitor a surrounding environment of a host vehicle;

detect other vehicles in the surrounding environment of the host vehicle by at least one visual sensor;

estimate a speed and direction of each of the detected vehicles;

calculate one or more projected paths of each of the detected vehicles based on their current estimated speed and direction, the monitored surrounding environment, and other detected vehicle projected paths, wherein the calculating further comprises;

uniquely identifying a detected vehicle;

retrieving a historical-data-based model for the uniquely identified, detected vehicle, the historical-data-based model comprising historical vehicle travel route data and historical vehicle-moving behavioral data along those routes for the uniquely identified, detected vehicle; and

generating one or more projected paths for the uniquely identified, detected vehicle based, at least in part, on the historical-data-based model for the uniquely identified, detected vehicle, including the historical vehicle travel route data and the historical vehicle-moving behavioral data along those routes;

estimate a probability of intersection of each projected path with the host vehicle; and

provide an alert or action to the host vehicle if there is a high probability of intersection.