PROBABILISTIC SAFE LANDING AREA DETERMINATION

• US 20160114905A1
• Filed: 06/10/2015
• Published: 04/28/2016
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: Sikorsky Aircraft Corporation (Martin Marietta Corporation)
• Original Assignee: Sikorsky Aircraft Corporation (Martin Marietta Corporation)
• Inventors: Derenick, Jason C., Cherepinsky, Igor, Stathis, Christopher
• Granted Patent: US 9,617,011 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B64D 45/04 Landing aids; Safety measures to prevent collision with earth's surface
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/17 taken from planes or by drones
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft
• CPC Class Codes: G08G 5/0086 for monitoring terrain radar or analogous systems specially adapted for terrain avoidance G01S13/935
• CPC Class Codes: G08G 5/025 Navigation or guidance aids radar or analogous systems specially adapted for landing purposes G01S13/913

Abstract

According to an aspect of the invention, a method of probabilistic safe landing area determination for an aircraft includes receiving sensor data indicative of current conditions at potential landing areas for the aircraft. Feature extraction on the sensor data is performed. A processing subsystem of the aircraft updates a probabilistic safe landing area map based on comparing extracted features of the sensor data with a probabilistic safe landing area model. The probabilistic safe landing area model defines probabilities that terrain features are suitable for safe landing of the aircraft. A list of ranked landing areas is generated based on the probabilistic safe landing area map.

Claims

1. A method of performing a probabilistic safe landing area determination for an aircraft, the method comprising:

receiving sensor data indicative of current conditions at potential landing areas for the aircraft;

performing feature extraction on the sensor data;

updating, by a processing subsystem of the aircraft, a probabilistic safe landing area map based on comparing extracted features of the sensor data with a probabilistic safe landing area model, the probabilistic safe landing area model defining probabilities that terrain features are suitable for safe landing of the aircraft; and

generating a list of ranked landing areas based on the probabilistic safe landing area map.

2. The method of claim 1, wherein generating the list of ranked landing areas further comprises performing a mission-level optimization to order the list of ranked landing areas according to one or more of a mission model and constraints.

3. The method of claim 2, wherein the mission-level optimization further comprises identifying a target based on one or more of the mission model and constraints, and adjusting the list of ranked landing areas to give a greater preference to a safe landing area in closer proximity to the target.

4. The method of any of claims 1-3, further comprising:

performing geospatial partitioning of the sensor data to subdivide processing of the sensor data into a plurality of cells.

5. The method of claim 4, further comprising:

distributing processing of the cells between a plurality of processing resources.

6. The method of any of claims 4-5, further comprising:

collecting sensor data for the cells over a period of time; and

computing slope and variance feature values of the cells based on the sensor data that are collected over the period of time.

7. The method of any of claims 4-6, further comprising:

associating each of the cells with a feature vector computed over a time interval; and

based on computing a new feature value for a cell, performing recursive integration of the new feature value into the probabilistic safe landing area map using a Bayesian update.

8. The method of any of claims 1-7, further comprising:

receiving position data for the aircraft;

determining positions of the potential landing areas and the aircraft based on the position data; and

correlating the sensor data to the position data.

9. The method of any of claims 1-8, further comprising:

comparing probability values in the probabilistic safe landing area map to a threshold level indicative of a safe landing area; and

identifying safe landing areas for the list of ranked landing areas based on extracting cells from the probabilistic safe landing area map that exceed the threshold level.

10. The method of any of claims 1-8, further comprising:

sorting probability values in the probabilistic safe landing area map; and

selecting most likely candidates for the list of ranked landing areas based on the sorting of the probability values.

11. A system for performing a probabilistic safe landing area determination for an aircraft, the system comprising:

a processing subsystem; and

memory having instructions stored thereon that, when executed by the processing subsystem, cause the system to;

receive sensor data indicative of current conditions at potential landing areas for the aircraft;

perform feature extraction on the sensor data;

update a probabilistic safe landing area map based on comparing extracted features of the sensor data with a probabilistic safe landing area model, the probabilistic safe landing area model defining probabilities that terrain features are suitable for safe landing of the aircraft; and

generate a list of ranked landing areas based on the probabilistic safe landing area map.

12. The system of claim 11, wherein generation of the list of ranked landing areas further comprises performance of a mission-level optimization to order the list of ranked landing areas according to one or more of a mission model and constraints.

13. The system of any of claims 11-12, wherein geospatial partitioning of the sensor data is performed to subdivide processing of the sensor data into a plurality of cells and distribute processing of the cells between a plurality of processing resources of the processing subsystem.

14. The system of claim 13, wherein the memory further comprises instructions stored thereon that, when executed by the processing subsystem, cause the system to:

collect sensor data for the cells over a period of time; and

compute slope and variance feature values of the cells based on the sensor data that are collected over the period of time.

15. The system of any of claims 13-14, wherein the memory further comprises instructions stored thereon that, when executed by the processing subsystem, cause the system to:

associate each of the cells with a feature vector computed over a time interval; and

based on computing a new feature value for a cell, recursive integration of the new feature value into the probabilistic safe landing area map is performed using a Bayesian update.