# US 2022/0035382 A1 · Systems and methods for coordinating device actions

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0035382 A1
- Document ID: US20220035382A1
- Status: Published application
- Kind: A1
- Application number: 17/449,174
- Filed: 2021-09-28
- Published: 2022-02-03
- Earliest claimed: 2018-11-13
- Assignees: Sz Dji Technology Co., Ltd.
- Applicants: Sz Dji Technology Co., Ltd
- Inventors: You ZHOU; Xuyang FENG; Cong ZHAO; Jiaqi YAN
- Web page: https://patentgrep.com/patent/US20220035382A1

## CPC

- G05D 1/104: {involving a plurality of aircrafts, e.g. formation flying (traffic control systems for aircraft G08G5/00)}
- G05D 1/0094: {involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target}
- G05D 1/689: Pointing payloads towards fixed or moving targets (positioning towed, pushed or suspended implements G05D1/672)
- B64U 2101/32: for cartography or topography
- B64U 2201/102: adapted for flying in formations
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR

## Abstract

Systems, methods, and computer-readable storage devices for obstacle detection may include an exemplary method of obstacle detection by a computing device. The method includes receiving a first dataset indicating a first surrounding with a first perspective; receiving a second dataset indicating a second surrounding with a second perspective; and generating a composite dataset from the first and second datasets. The method additionally includes identifying an obstacle using the composite dataset.

## Claims

### Claim at position 1

-19. (canceled)

### Claim 20

A method of obstacle detection by a computing device, the method comprising:
receiving a first dataset indicating a first surrounding with a first perspective;
receiving a second dataset indicating a second surrounding with a second perspective;
generating a composite dataset from the first dataset and the second dataset; and
identifying an obstacle using the composite dataset.

### Claim 21 (depends on 20)

The method of claim 20, wherein the first dataset includes a first image taken by a first movable object and the second dataset includes a second image taken by a second movable object.

### Claim 22 (depends on 20)

The method of claim 20, wherein the composite dataset contains three-dimensional information indicating at least one of a size or a location of at least one object.

### Claim 23 (depends on 20)

The method of claim 20, wherein identifying the obstacle includes:
determining a location of an object in the composite dataset relative to a moving path of a movable object; and
classifying the object as an obstacle if the moving path of the movable object intersects the location of the object.

### Claim 24 (depends on 20)

The method of claim 20, further comprising:
causing a movable object to avoid the obstacle by altering a moving path of the movable object.

### Claim at position 7

-30. (canceled)

### Claim 31 (depends on 20)

The method of claim 20, wherein the computing device is coupled to an unmanned aerial vehicle.

### Claim at position 9

-71. (canceled)

### Claim 72

A non-transitory computer-readable medium storing instructions that, when executed, cause a computing device to perform a method of obstacle detection, the method comprising:
receiving a first dataset indicating a first surrounding with a first perspective;
receiving a second dataset indicating a second surrounding with a second perspective;
generating a composite dataset from the first dataset and the second dataset; and
identifying an obstacle using the composite dataset.

### Claim 73 (depends on 72)

The non-transitory computer-readable medium of claim 72, wherein the first dataset includes a first image taken by a first movable object and the second dataset includes a second image taken by a second movable object.

### Claim 74 (depends on 72)

The non-transitory computer-readable medium of claim 72, wherein the composite dataset contains three-dimensional information indicating at least one of a size or a location of at least one object.

### Claim 75 (depends on 72)

The non-transitory computer-readable medium of claim 72, wherein identifying the obstacle includes:
determining a location of an object in the composite dataset relative to a moving path of a movable object; and
classifying the object as an obstacle if the moving path of the movable object intersects the location of the object.

### Claim 76 (depends on 72)

The non-transitory computer-readable medium of claim 72, the method further comprising:
causing a movable object to avoid the obstacle by altering a moving path of the movable object.

### Claim at position 15

-82. (canceled)

### Claim 83 (depends on 72)

The non-transitory computer-readable medium of claim 72, wherein the computing device is coupled to an unmanned aerial vehicle.

### Claim at position 17

-91. (canceled)

### Claim 92

A system of obstacle detection by a computing device comprising:
one or more processors; and
a detector running on the one or more processors, the detector configured to:
receive a first dataset indicating a first surrounding with a first perspective;
receive a second dataset indicating a second surrounding with a second perspective;
generate a composite dataset from the first dataset and the second dataset; and
identify an obstacle using the composite dataset.

### Claim at position 19

-113. (canceled)

### Claim 114 (depends on 92)

The system of claim 92, wherein the first dataset includes a first image taken by a first movable object and the second dataset includes a second image taken by a second movable object.

### Claim 115 (depends on 92)

The system of claim 92, wherein the composite dataset contains three-dimensional information indicating at least one of a size or a location of at least one object.

### Claim 116 (depends on 92)

The system of claim 92, wherein identifying the obstacle includes:
determining a location of an object in the composite dataset relative to a moving path of a movable object; and
classifying the object as an obstacle if the moving path of the movable object intersects the location of the object.

### Claim 117 (depends on 92)

The system of claim 92, wherein the detector running on the one or more processors is further configured to cause a movable object to avoid the obstacle by altering a moving path of the movable object.

### Claim at position 24

-123. (canceled)

### Claim 124 (depends on 92)

The system of claim 92, wherein the computing device is coupled to an unmanned aerial vehicle.

### Claim at position 26

-134. (canceled)

### Claim 135 (depends on 20)

The method of claim 20, wherein generating the composite dataset from the first dataset and the second dataset includes:
generating the composite dataset by combining the first dataset and the second dataset using a structure from motion (SfM) algorithm.

### Claim 136 (depends on 92)

The system of claim 92, wherein the detector is configured to generate the composite dataset from the first dataset and the second dataset by combining the first dataset and the second dataset using a structure from motion (SfM) algorithm.
