US-12620319-B2 - Apparatuses, computer-implemented methods, and computer program products for predicting vehicle collision

Abstract

Embodiments of the disclosure provide for predicting collisions between vehicles and environment objects based at least in part on user input from a computing entity. Some embodiments receive, at a cloud computing environment, a user input from a computing entity, where the user input comprises an approximate location of an environment object. Some embodiments generate, using a machine learning model, a collision prediction involving the environment object and a vehicle based at least in part on the approximate location of the environment object and a trusted location of the vehicle. Some embodiments generate traffic data based at least in part on the collision prediction. Some embodiments provide a notification indicative of the traffic data to the vehicle and the computing entity.

Inventors

• Anil Kumar Sati Jayaramaiah
• Chandrashekar Shankarappa

Assignees

• HONEYWELL INTERNATIONAL INC.

Dates

Publication Date

20260505

Application Date

20240506

Priority Date

20231107

Claims (20)

1. 1 . A computer-implemented method, comprising: receiving, at a cloud computing environment, a user input from a computing entity, wherein the user input is obtained using a graphical user interface (GUI) of the computing entity and comprises an approximate location of an environment object; generating, at the cloud computing environment and using a machine learning model, at least one collision prediction involving the environment object and at least one vehicle based at least in part on the approximate location of the environment object and a trusted location of the at least one vehicle; generating traffic data based at least in part on the at least one collision prediction; and providing a notification indicative of the traffic data to the at least one vehicle and the computing entity.
2. 2 . The method of claim 1 , wherein: the computing entity embodies a device onboard an aerial vehicle.
3. 3 . The method of claim 1 , wherein: the user input originates from a user-controlled device in an environment external to the at least one vehicle.
4. 4 . The method of claim 1 , wherein: the user input further comprises an approximate speed of the environment object; and the method further comprises generating the at least one collision prediction further based at least in part on the approximate speed of the environment object.
5. 5 . The method of claim 1 , further comprising: generating the at least one collision prediction further based at least in part on a predefined collision boundary.
6. 6 . The method of claim 5 , further comprising: receiving, at the cloud computing environment, the predefined collision boundary from a computing entity associated with the at least one vehicle.
7. 7 . The method of claim 1 , wherein: the trusted location of the at least one vehicle is based at least in part on an upload of primary radar data to the cloud computing environment from a primary radar system; and the primary radar data is associated with a geozone comprising the approximate location of the environment object and comprises vehicle position data associated with the at least one vehicle.
8. 8 . The method of claim 1 , wherein: the trusted location of the at least one vehicle is based at least in part on an upload of secondary radar data to the cloud computing environment from a secondary radar system; and the secondary radar data is associated with a geozone comprising the approximate location of the environment object and comprises: an identifier for the at least one vehicle; and vehicle position data associated with the at least one vehicle.
9. 9 . The method of claim 1 , wherein: the at least one vehicle is an unmanned vehicle remotely controlled by a control station located within a predetermined proximity of a geozone comprising the approximate location of the environment object; and the trusted location of the at least one vehicle is based at least in part on unmanned vehicle tracking data received at the cloud computing environment from the control station.
10. 10 . The method of claim 1 , wherein: the trusted location of the at least one vehicle is based at least in part on vehicle position data received at the cloud computing environment from a traffic collision avoidance system (TCAS) of the at least one vehicle.
11. 11 . The method of claim 1 , wherein: the at least one vehicle is without a TCAS; and the trusted location of the at least one vehicle is based at least in part on simple vehicle location data received at the cloud computing environment.
12. 12 . The method of claim 11 , wherein: the cloud computing environment receives the simple vehicle location data from a satellite-based position system of the at least one vehicle.
13. 13 . The method of claim 1 , wherein: the trusted location of the at least one vehicle is based at least in part on vehicle position data received at the cloud computing environment from an automatic dependent surveillance broadcast (ADS-B) system of the at least one vehicle.
14. 14 . The method of claim 1 , further comprising: generating a training dataset based at least in part on the at least one collision prediction; and retraining the machine learning model using the training dataset.
15. 15 . An apparatus comprising at least one processor and at least one non-transitory memory having computer-coded instructions stored thereon that, in execution with at least one processor, cause the apparatus to: receive, at a cloud computing environment, a user input from a computing entity, wherein the user input is obtained using a graphical user interface (GUI) of the computing entity and comprises an approximate location of an environment object; generate, at the cloud computing environment and using a machine learning model, at least one collision prediction involving the environment object and at least one vehicle based at least in part on the approximate location of the environment object and a trusted location of the at least one vehicle; generate traffic data based at least in part on the at least one collision prediction; and provide a notification indicative of the traffic data to the at least one vehicle and the computing entity.
16. 16 . The apparatus of claim 15 , wherein: the computer-coded instructions, in execution with the at least one processor, further cause the apparatus to: determine a plurality of vehicles located within a geozone comprising the approximate location of the environment object; and provide a respective notification indicative of the traffic data to the plurality of vehicles.
17. 17 . The apparatus of claim 16 , wherein: the computer-coded instructions, in execution with the at least one processor, further cause the apparatus to: obtain a subscriber list comprising a plurality of vehicle identifiers; determine a subset of the plurality of vehicles based at least in part on the subscriber list and respective vehicle identifiers for the plurality of vehicles, wherein the providing of the respective notification is limited to the subset of the plurality of vehicles.
18. 18 . The apparatus of claim 17 , wherein: the computer-coded instructions, in execution with the at least one processor, further cause the apparatus to: receive the respective vehicle identifiers for the plurality of vehicles from a vehicle traffic control system.
19. 19 . The apparatus of claim 15 , wherein: the computer-coded instructions, in execution with the at least one processor, further cause the apparatus to: cause rendering of a graphical user interface (GUI) on a display of a computing device associated with the at least one vehicle; and the GUI comprises the notification and a three-dimensional mapping of a geozone comprising at least one indicia indicative of the at least one collision prediction.
20. 20 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, is configured to: receive, at a cloud computing environment, a user input from a computing entity, wherein the user input is obtained using a graphical user interface (GUI) of the computing entity and comprises an approximate location of an environment object; generate, at the cloud computing environment and using a machine learning model, at least one collision prediction involving the environment object and at least one vehicle based at least in part on the approximate location of the environment object and a trusted location of the at least one vehicle; generate traffic data based at least in part on the at least one collision prediction; and provide a notification indicative of the traffic data to the at least one vehicle and the computing entity.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application claims the benefit of and priority to India Provisional Application No. 202311075999, filed Nov. 7, 2023, entitled “APPARATUSES, COMPUTER-IMPLEMENTED METHODS, AND COMPUTER PROGRAM PRODUCTS FOR PREDICTING VEHICLE COLLISION,” the disclosure of which is incorporated herein by reference in its entirety. TECHNOLOGICAL FIELD Embodiments of the present disclosure are generally directed to predicting vehicle based at least in part on vehicle data uploaded to a cloud computing environment. BACKGROUND The increased density and diversity of vehicle traffic presents challenges to ensuring air and ground safety. For example, typical approaches to vehicle traffic control rely on radar systems and vehicles equipped with transponders that broadcast vehicle position data. However, there exists an increasing volume of vehicles that are unequipped with transponder-based systems, which may result in reduced capacity to monitor vehicle traffic and accurately predict vehicle collisions. For example, smaller vehicles (e.g., unmanned vehicles, small engine craft and/or the like) may have insufficient carrying capacity to support onboard position-broadcasting systems, such as traffic collision avoidance system (TCAS) or automatic dependent surveillance-broadcast (ADS-B). Even in instances where such equipment may be provisioned to a vehicle, exchange of vehicle position data between different vehicle types may be unsupported due to design differences in the position-broadcasting systems. Additionally, reduced vehicle dimensions may reduce vehicle radar detectability due in part to reduced radar signatures and/or increased vehicle traffic density that obfuscates smaller vehicles. Applicant has discovered various technical problems associated with predicting collisions between vehicles and environment objects. Through applied effort, ingenuity, and innovation, Applicant has solved many of these identified problems by developing the embodiments of the present disclosure, which are described in detail below. BRIEF SUMMARY In general, embodiments of the present disclosure herein provide for prediction of collisions between vehicles and other environment objects based at least in part on aggregated vehicle position data indicative of vehicle and object locations. For example, embodiments of the present disclosure provide for prediction of collisions between a vehicle and an environment object based at least in part on a trusted location of the vehicle and an approximate location of the environment object, where the approximate location of the environment object may be generated based at least in part on one or more user inputs describing a position of the environment object. Other implementations for predicting collisions will be, or will become, apparent to one with skill in the art upon examination of the following figures and detailed description. It is intended that all such additional implementations be included within this description be within the scope of the disclosure, and be protected by the following claims. In accordance with a first aspect of the disclosure, a computer-implemented method for collision prediction is provided. The computer-implemented method is executable utilizing any of a myriad of computing device(s) and/or combinations of hardware, software, firmware. In some example embodiments an example computer-implemented method includes receiving, at a cloud computing environment, a user input from a computing entity, where the user input includes an approximate location of an environment object. In some embodiments, the method includes generating, at the cloud computing environment and using a machine learning model, at least one collision prediction involving the environment object and at least one vehicle based at least in part on the approximate location of the aerial object and a trusted location of the at least one vehicle. In some embodiments, the method includes generating traffic data based at least in part on the at least one collision prediction and providing a notification indicative of the traffic data to the at least one vehicle and the computing entity. In some embodiments, the computing entity embodies a device onboard an aerial vehicle. In some embodiments, the user input originates from a user-controlled device in an environment external to the at least one vehicle. the user input further includes an approximate speed of the environment object. In some embodiments, the method includes generating the at least one collision prediction further based at least in part on the approximate speed of the environment object. In some embodiments, the method includes generating the at least one collision prediction further based at least in part on a predefined collision boundary. In some embodiments, the method includes receiving, at the cloud computing environment, the predefined collision boundary from a computing entity associated with the at least on