# US 2026/0169479 A1 · Method for detecting obstacle, self-moving robot, and non-transitory computer readable storage medium

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

- Number: US 2026/0169479 A1
- Document ID: US20260169479A1
- Status: Published application
- Kind: A1
- Application number: 19/532,575
- Filed: 2026-02-06
- Published: 2026-06-18
- Earliest claimed: 2020-08-26
- Assignees: Beijing Roborock Innovation Technology Co., Ltd.
- Applicants: Beijing Roborock Innovation Technology Co., Ltd.
- Inventors: Haojian XIE
- Web page: https://patentgrep.com/patent/US20260169479A1

## CPC

- G05D 1/024: {in combination with a laser (lasers per se H01S)}
- G05D 1/0251: {extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision (stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593)}
- A47L 9/2805: {Parameters or conditions being sensed}
- A47L 9/2852: {Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles}
- G05D 1/0214: {in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13)}
- G05D 1/2435: {Extracting 3D information}
- G05D 1/622: Obstacle avoidance (predicting or avoiding probable or impending collision of road vehicles B60W30/08)
- G06T 1/0014: {Image feed-back for automatic industrial control, e.g. robot with camera (robots B25J19/023)}
- G06T 7/11: Region-based segmentation
- G06T 7/50: Depth or shape recovery
- G06T 7/62: of area, perimeter, diameter or volume
- G06T 7/85: {Stereo camera calibration}
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- 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
- A47L 2201/04: Automatic control of the travelling movement; Automatic obstacle detection
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/30261: Obstacle
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- A47L: DOMESTIC WASHING OR CLEANING (brushes A46B; cleaning quantities of bottles or of other hollow articles of one kind B08B9/00; laundry D06F); SUCTION CLEANERS IN GENERAL (cleaning in general B08)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for detecting an obstacle, applied to a self-moving robot, including: transforming obstacle information into depth information; converting the depth information into a point cloud map, and determining coordinate data of a reference point on the obstacle; determining a valid analysis range in a height direction in the point cloud map; and determining, based on the coordinate data of the reference point, whether an obstacle is present within the valid analysis range.

## Claims

### Claim 1

A method for detecting an obstacle, performed by a self-moving robot, comprising:
acquiring obstacle information;
transforming the obstacle information into depth information;
converting the depth information into a point cloud map;
obtaining a probability map formed in a traveling process of the self-moving robot, wherein at least one location in the probability map is marked with a probability value that the location is an obstacle; and
determining, based on the point cloud map and the probability map, whether an obstacle is present.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising:
determining coordinate data of a reference point on the obstacle;
determining a valid analysis range in a height direction in the point cloud map; and
wherein the determining, based on the point cloud map and the probability map, whether the obstacle is present comprises:
determining, based on the coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the probability map is formed by, in a historical moving track process of the self-moving robot, determining whether the obstacle is present at the location by using multiple historical experiences.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the determining, based on the coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range comprises:
transforming 3D coordinate data of the reference point within the valid analysis range into 2D coordinate data; and
determining, based on the 2D coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the determining, based on the 2D coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range, further comprises:
filtering out coordinate data of a noise point in the 2D coordinate data of each reference point based on the probability map.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the filtering out the coordinate data of the noise point in the 2D coordinate data of the reference point based on the probability map comprises:
obtaining location coordinate data of the obstacle in the probability map, wherein a probability value of the obstacle in the probability map is greater than a preset probability threshold; and
comparing the location coordinate data of the obstacle with the 2D coordinate data of the reference point, and filtering out the 2D coordinate data in response to determining that a distance between the location coordinate data of the obstacle and the 2D coordinate data of the reference point is greater than a first preset value.

### Claim 7 (depends on 2)

The method according to claim 2, wherein the determining, based on the coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range comprises:
clustering the reference point within the valid analysis range, and determining all reference points with a distance from coordinate data of an adjacent reference point less than a second preset value as a region; and
determining a size of the region respectively, and in response to the size of the region being greater than or equal to a third preset value, determining that the obstacle is present within the valid analysis range.

### Claim 8 (depends on 7)

The method according to claim 7, wherein the size of the region comprises at least one of the following:
an area/volume of the region, a diameter of the region, or a minimum distance across a geometric center of the region.

### Claim 9 (depends on 2)

The method according to claim 2, further comprising:
in response to the obstacle being present within the valid analysis range, determining whether a size of the obstacle is less than a preset threshold; and
in response to the size of the obstacle being less than the preset threshold, controlling the self-moving robot to reduce a rotation speed within a preset distance range from the obstacle.

### Claim 10 (depends on 8)

The method according to claim 8, further comprising:
in response to the obstacle being present within the valid analysis range, performing navigation according to a size of the obstacle.

### Claim 11 (depends on 10)

The method according to claim 10, wherein performing the navigation according to the size of the obstacle comprises:
determining an obstacle avoidance distance according to the size of the obstacle or a range of the size, and controlling the self-moving robot to start to perform an obstacle avoidance strategy at the obstacle avoidance distance.

### Claim 12 (depends on 10)

The method according to claim 10, wherein the size of the region further comprises a height of the region.

### Claim 13 (depends on 12)

The method according to claim 12, wherein, performing the navigation according to the size of the obstacle comprises:
in response to determining that the height of the region is greater than a preset height, performing an obstacle avoidance strategy.

### Claim 14

A self-moving robot, comprising a processor and a memory, wherein the memory stores with a computer program instruction executable by the processor, and when the processor executes the computer program instruction, the processor is configured to:
acquire obstacle information;
transform the obstacle information into depth information;
convert the depth information into a point cloud map;
obtain a probability map formed in a traveling process of the self-moving robot, wherein at least one location in the probability map is marked with a probability value that the location is an obstacle; and
determine, based on the point cloud map and the probability map, whether an obstacle is present.

### Claim 15 (depends on 14)

The self-moving robot according to claim 14, wherein the processor is further configured to:
determine coordinate data of a reference point on the obstacle;
determine a valid analysis range in a height direction in the point cloud map; and
determine, based on the coordinate data of the reference point in the valid analysis range and the probability map, whether an obstacle is present within the valid analysis range.

### Claim 16 (depends on 15)

The self-moving robot according to claim 15, wherein the processor is further configured to:
transform 3D coordinate data of the reference point within the valid analysis range into 2D coordinate data; and
determine, based on the 2D coordinate data of the reference point in the valid analysis range and the probability map, whether the obstacle is present within the valid analysis range.

### Claim 17 (depends on 16)

The self-moving robot according to claim 16, wherein the processor is further configured to:
obtain location coordinate data of the obstacle in the probability map, wherein the probability value of the obstacle in the probability map is greater than a preset probability threshold; and
compare the location coordinate data of the obstacle with the 2D coordinate data of the reference point, and filter out the 2D coordinate data in response to determining that a distance between the location coordinate data of the obstacle and the 2D coordinate data of the reference point is greater than a first preset value.

### Claim 18 (depends on 15)

The self-moving robot according to claim 15, the processor is further configured to:
cluster the reference point within the valid analysis range, and determine all reference points with a distance from coordinate data of an adjacent reference point less than a second preset value as a region; and
determine a size of the region respectively, and in response to a size of the region being greater than or equal to a third preset value, determine that the obstacle is present within the valid analysis range.

### Claim 19 (depends on 15)

The self-moving robot according to claim 15, the processor is further configured to:
in response to the obstacle being present within the valid analysis range, determine whether a size of the obstacle is less than a preset threshold; and
in response to the size of the obstacle being less than the preset threshold, control the self-moving robot to reduce a rotation speed within a preset distance range from the obstacle.

### Claim 20

A non-transitory computer readable storage medium, wherein a computer program instruction is stored, and when the computer program instruction is invoked and executed by a processor of a self-moving robot, a method for detecting an obstacle is performed, and the method comprises:
acquiring obstacle information;
transforming the obstacle information into depth information;
converting the depth information into a point cloud map;
obtaining a probability map formed in a traveling process of the self-moving robot, wherein at least one location in the probability map is marked with a probability value that the location is an obstacle; and
determining, based on the point cloud map and the probability map, whether an obstacle is present.
