System and method for collision avoidance

• US 9,836,661 B2
• Filed: 12/04/2014
• Issued: 12/05/2017
• Est. Priority Date: 12/04/2014
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Zhou, Zhi, Joshi, Narendra Digamber, Zhou, Rui, Hoover, Craig
• Primary Examiner(s): CASS, JEAN PAUL
• Application Number:
  US14/560,311
• Publication Number:
  US 20160163208A1
• Time in Patent Office: 1,097 Days
• Field of Search: None
• CPC Class Codes: B64F 1/228 remotely controlled; operating autonomously
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G08G 5/0026 located on the ground
• CPC Class Codes: G08G 5/0082 for monitoring traffic from a ground station radar or analogous systems specially adapted for traffic control G01S13/91
• CPC Class Codes: G08G 5/045 Navigation or guidance aids, e.g. determination of anti-collision manoeuvers radar or analogous systems specially adapted for anti-collision between aircraft G01S13/933
• CPC Class Codes: G08G 5/065 Navigation or guidance aids, e.g. for taxiing or rolling
• CPC Class Codes: Y02T 50/80 Energy efficient operational measures, e.g. ground operations or mission management

Abstract

A method implemented using at least one processor includes receiving a plurality of images acquired from a plurality of image sensors disposed on a vehicle configured to engage an aircraft for ground operations. The method further includes determining at least one parameter about a potential obstacle based on the plurality of images and a machine vision algorithm. The method also includes generating an alert signal based on the at least one parameter, useful for avoiding collision of the aircraft.

Claims

1. A collision avoidance system comprising:

at least one processor and a memory communicatively coupled to the at least one processor via a communications link;

a plurality of sensors disposed at a plurality of locations on a taxi vehicle taxiing an aircraft, wherein the plurality of sensors comprises a plurality of image sensors and the taxi vehicle is configured to engage an aircraft for ground operations;

a data acquisition module communicatively coupled to the plurality of sensors that receives a plurality of images from the plurality of image sensors;

a supervisory control module communicatively coupled to the data acquisition module and configured to;

receive environmental data from at least one of a gate, a service vehicle, a taxi vehicle, another aircraft, and a control center;

determine a plurality of environmental parameters based on the environmental data and a discretized model, wherein the plurality of environmental parameters are used to perform supervisory control and monitoring operations and wherein the discretized model is based on architecture and specifications of a ground management system, components and layout of an airport, specifications on vehicle dynamics, specifications of vehicle controllers, uncertainty in communications, and safety requirements; and

a collision avoidance module configured to determine a signal indicative of a collision condition, wherein the collision avoidance module is communicatively coupled to the data acquisition module and that;

determines at least one parameter about an obstacle based on the plurality of images, the plurality of environmental parameters and a machine vision algorithm, wherein the obstacle is a stationary or a moving object disposed near the taxi vehicle; and

generates an alert signal based on the at least one parameter, wherein the alert signal is indicative of the collision condition, and wherein the alert signal is used for avoiding collision of the aircraft with the obstacle;

wherein at least one of the data acquisition module and the collision avoidance module is stored in the memory and executable by the at least one processor.

2. The system of claim 1, wherein the plurality of sensors comprises at least one of a proximity sensor and a radio frequency sensor.

3. The system of claim 1, wherein the data acquisition module acquires a real time video at a plurality of frame rates.

4. The system of claim 1, wherein the collision avoidance module determines a distance value, a velocity value, an acceleration value and a direction parameter as the at least one parameter.

5. The system of claim 1, wherein the collision avoidance module identifies at least one of a gate, a service vehicle, and another aircraft as the obstacle.

6. The system of claim 1, wherein the collision avoidance module performs at least one of registration, segmentation, motion analysis, edge detection, and pattern recognition operation.

7. The system of claim 1, wherein the collision avoidance module identifies a blocking condition.

8. The system of claim 1, wherein the alert signal comprises at least one of an audible signal, a visual signal, a tactile signal, an electrical signal indicative of the collision condition.

18. The system of claim 1, wherein the discretized model employs discretization of time, discretization of a vehicle velocity, and discretization of a vehicle position.

9. A method for collision avoidance comprising:

receiving a plurality of images acquired from a plurality of sensors disposed on a taxi vehicle taxiing the aircraft, wherein the taxi vehicle is configured to engage an aircraft for ground operations;

receiving environmental data from at least one of a gate, a service vehicle, a taxi vehicle, another aircraft, and a control center;

a plurality of environmental parameters based on the environmental data and discretization of time, discretization of a vehicle velocity, and discretization of a vehicle position, wherein discretization of time, discretization of the vehicle velocity, and discretization of the vehicle position is based on architecture and specifications of a ground management system, components and layout of an airport, specifications on vehicle dynamics, specifications of vehicle controllers, uncertainty in communications, and safety requirements; and

determining at least one parameter about an obstacle by a processor communicatively coupled to the plurality of image sensors, based on the plurality of images, the plurality of environmental parameters and a machine vision algorithm, wherein the obstacle is a stationary or moving object disposed near the vehicle; and

generating an alert signal based on the at least one parameter by the processor, wherein the alert signal is indicative of the collision condition, and wherein the alert signal is used for avoiding collision of the aircraft with the obstacle near the vehicle.

10. The method of claim 9, wherein the plurality of sensors includes at least one of proximity sensor and a radio frequency sensor.

11. The method of claim 9, wherein receiving comprises acquiring a video in real time with a plurality frame rates.

12. The method of claim 9, wherein determining comprises computing at least one of a distance value, a velocity value, an acceleration value, a direction parameter.

13. The method of claim 9, wherein determining comprises computing the at least one parameter corresponding to at least one of a gate, a service vehicle, and another aircraft.

14. The method of claim 9, wherein determining comprises performing at least one of registration, segmentation, motion analysis, edge detection, and pattern recognition operations.

15. The method of claim 9, wherein determining comprises identifying a collision condition of the vehicle.

16. The method of claim 15, wherein the collision condition comprises a blocking condition.

17. The method of claim 15, wherein generating comprises determining at least one of an audible signal, a visual signal, a tactile signal and an electrical signal indicative of the collision condition.