Method and apparatus for providing dynamic obstacle data for a collision probability map

Patent metadata

Field	Value
Publication number	US-11550340-B2
Application number	US-201916709513-A
Country	US
Kind code	B2
Filing date	Dec 10, 2019
Priority date	Dec 10, 2019
Publication date	Jan 10, 2023
Grant date	Jan 10, 2023

Abstract

An approach is provided for dynamic obstacle data in a collision probability map. The approach, for example, involves monitoring a flight of an aerial vehicle through a three-dimensional (3D) space that is partitioned into 3D shapes of varying resolutions. The approach also involves detecting an entry of the aerial vehicle into one 3D shape of the plurality of 3D shapes. The approach further involves, on detecting an exit of the aerial vehicle form the one 3D shape, recording a 3D shape identifier (ID) of the one 3D shape and at least one of a first timestamp indicating the entry, a second timestamp indicating the exit, a duration of stay in the one 3D shape, dimensions of the aerial vehicle, or a combination thereof as a dynamic obstacle observation record. The approach further involves transmitting the dynamic obstacle observation record to another device (e.g., a server for creating the collision probability map).

First claim

What is claimed is:

1. A method comprising:
monitoring a flight of an aerial vehicle through a three-dimensional (3D) space, wherein the 3D space is partitioned into a plurality of 3D shapes of varying resolutions;
detecting an entry of the aerial vehicle into one 3D shape of the plurality of 3D shapes, wherein the one 3D shape represents a bounded volume of the 3D space;
on detecting an exit of the aerial vehicle from the one 3D shape, recording a 3D shape identifier (ID) of the one 3D shape and at least one of a first timestamp indicating the entry, a second timestamp indicating the exit, a duration of stay in the one 3D shape, dimensions of the aerial vehicle, or a combination thereof as a dynamic obstacle observation record; and
transmitting the dynamic obstacle observation record to a server, wherein the server aggregates the dynamic obstacle observation record with at least one additional dynamic obstacle observation record of at least one additional aerial vehicle to calculate a dynamic obstacle collision probability in the one 3D shape.

2. The method of claim 1 , further comprising:
determining that the one 3D shape is not on an aerial route calculated for the aerial vehicle; and
selecting a resolution of the one 3D shape.

3. The method of claim 2 , wherein the dynamic obstacle observation record is reported at the selected resolution while the aerial vehicle is off the aerial route.

4. The method of claim 1 , wherein the one 3D shape is on an aerial route calculated for the aerial vehicle.

5. The method of claim 4 , wherein the aerial route comprises a list of the plurality of 3D shapes forming the aerial route.

6. The method of claim 1 , wherein the plurality of 3D shapes is a plurality of cubes.

7. A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:
monitoring a flight of an aerial vehicle through a three-dimensional (3D) space, wherein the 3D space is partitioned into a plurality of 3D shapes of varying resolutions;
detecting an entry of the aerial vehicle into one 3D shape of the plurality of 3D shapes, wherein the one 3D shape represents a bounded volume of the 3D space;
on detecting an exit of the aerial vehicle from the one 3D shape, recording a 3D shape identifier (ID) of the one 3D shape and at least one of a first timestamp indicating the entry, a second timestamp indicating the exit, a duration of stay in the one 3D shape, dimensions of the aerial vehicle, or a combination thereof as a dynamic obstacle observation record; and
transmitting the dynamic obstacle observation record to a server, wherein the server aggregates the dynamic obstacle observation record with at least one additional dynamic obstacle observation record of at least one additional aerial vehicle to calculate a dynamic obstacle collision probability in the one 3D shape.

8. The non-transitory computer-readable storage medium of claim 7 , wherein the one 3D shape is on an aerial route calculated for the aerial vehicle.

Assignees

• Here Global Bv

Inventors

• Cajias Raul
• Rolf Daniel

Classifications

• B64U2201/10

  autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS] · CPC title

• G06V20/64

  Three-dimensional [3D] objects · CPC title

• G06T3/4053

  based on super-resolution, i.e. the output image resolution being higher than the sensor resolution · CPC title

• G05D1/106 Primary

  Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones · CPC title

• G08G5/003

  Physics · mapped topic