Method of identifying unexpected obstacle and robot implementing the method

Patent metadata

Field	Value
Publication number	US-2018239355-A1
Application number	US-201815892589-A
Country	US
Kind code	A1
Filing date	Feb 9, 2018
Priority date	Feb 20, 2017
Publication date	Aug 23, 2018
Grant date	—

Abstract

The present disclosure relates to a method of identifying an unexpected obstacle and a robot implementing the method. The method includes: by a sensing module of a robot, sensing a blind spot located in a traveling path of the robot; by a control unit of the robot, calculating a probability that a moving object appears in the sensed blind spot; and, by the control unit, controlling the speed or direction of a moving unit of the robot based on the calculated probability.

First claim

What is claimed is:

1 . A method of controlling a robot, the method comprising:
identifying, by a sensor of the robot, a bond spot located along a traveling path of the robot through a space; calculating, by a controller of the robot, a probability that a moving object is present in the blind spot; and managing, by the controller, at least one of a speed or a direction of the robot based on the calculated probability that the moving object is present in the blind spot.

2 . The method of claim 1 , wherein the sensor includes a LiDAR sensor and a depth sensor, and identifying the blind spot includes:
determining, by the LiDAR sensor, a distance to an object located along the traveling path; and when the distance to the object changes irregularly as the robot moves through a location on the traveling path, collecting, by the depth sensor, depth information on the location where the distance to the object changes irregularly.

3 . The method of claim 1 , wherein further comprising:
generating the traveling path of the robot based on a map of the space; and updating the map to identify the blind spot on the traveling path.

4 . The method of claim 1 , further comprising:
moving the robot toward the blind spot after managing the at least one of the direction or the speed of the robot; and sensing an object in the blind spot after the robot moves toward the blind spot.

5 . The method of claim 4 , wherein the sensor further includes at least one of a depth sensor or an infrared sensor, and sensing the object includes:
detecting, by the at least one of the depth sensor or the infrared sensor, an attribute of the object; calculating a probability that the object is a person based on the detected attribute of the object; and when the probability that the object is a person is higher than a reference value, outputting by the robot, at least one of auditory information or visual information toward the moving object.

6 . The method of claim 4 , further comprising:
forwarding sensing data about the blind spot to another robot.

7 . The method of claim 1 , wherein identifying the blind spot includes:
identifying a portion of the space along the traveling path that is at least partially blocked from the sensor; and identifying the portion of the space as the blind spot when the portion of the space is sufficiently large to receive the moving object.

8 . The method of claim 1 , wherein calculating the probability that the moving object is located in the blind spot includes:
identifying a size and a shape of the blind spot; and calculating the probability that the moving object is located in the blind spot based on at least the size and the shape of the blind spot.

9 . The method of claim 1 , wherein managing the at least one of the speed or the direction of the robot based on the calculated probability that the moving object is located in the blind spot includes:
causing the robot to move away from the blind spot when the calculated probability that the moving object is located in the blind spot is greater than a reference value.

10 . A method of controlling a robot, the method comprising:
identifying, by a controller of the robot, a blind spot located along a traveling path the robot through a space; detecting, by a sensor of the robot, an attribute of an object in the blind spot when the robot approaches the blind spot; determining, by the controller, whether the object is a fixed object or a moving object based on the detected attribute; and modifying, by the controller, at least one of a speed or a direction of the robot when the object is determined to be a moving object.

11 . The method of claim 10 , wherein the sensor includes a LiDAR sensor and a depth sensor, and detecting the attribute the object in the blind spot includes:
detecting, by the LiDAR sensor, a distance to a particular object located along the traveling path; and when the distance to the particular object changes irregularly or the particular object is sensed in an empty space of the blind spot, detecting, by the depth sensor, depth information on a spot where the distance changes irregularly or the particular object is sensed.

12 . The method of claim 10 , further comprising:
moving the robot toward the blind spot in a blind spot traveling mode after modifying the at least one of the speed or the direction of the robot; and sensing a moving object in the blind spot after the robot moves toward the blind spot.

13 . The method of claim 12 , wherein the sensor further includes at least one of a depth sensor or an infrared sensor, and sensing the moving object includes:
detecting, by the at least one of the depth sensor or the infrared sensor, an attribute of the moving object; calculating a probability that the moving object is a person based on the attribute; and when the probability that the moving object is a person is higher than a reference value, outputting at least one of auditory information or visual information toward the moving object.

14 . The method of claim 10 , wherein modifying the at least one of the speed or the direction of the robot includes modifying a movement of the robot to avoid a collision with the moving object.

15 . A robot, comprising:
a sensor that detects data about a space in which the robot travels; a memory that stores a map identifying a position of a fixed object in the space where the robot travels and a fixability value of the fixed object; a controller that generates a traveling path of the robot through the space based on data sensed by the sensor and the stored map; and a motor that selectively applies a driving force to move the robot, wherein the controller further identifies a moving object in a blind spot located along the traveling path of the robot and controls at least one of a speed or a direction of driving force applied by the motor to avoid a collision with the moving object.

16 . The robot of claim 15 , wherein the sensor includes:
a LiDAR sensor that senses a distance to an object located on the traveling path; and a depth sensor that generates depth information for a spot at which the LIDAR sensor detects that the distance to the object changes irregularly.

17 . The robot of claim 15 , wherein the controller updates the map to identify the blind spot along the traveling path, the sensor collects data about an object in the blind spot, and the controller determines whether the object is still or moving.

18 . The robot of claim 15 , further comprising:
a user interface that selectively outputs at least one of visual information or auditory information, wherein the sensor includes at least one of a depth sensor or an infrared sensor that detects an attribute of the moving object, the controller calculates a probability that the moving object is a person based on the attribute, and when the probability that the moving object is a person is higher than a reference value, the controller directs the user interface to output the visual information or the auditory information.

19 . The robot of claim 15 , further comprising:
a cleaning head coupled to the main body to perform a cleaning function.

20 . The robot of claim 15 , further comprising:
a communication interface that forwards data collected by the sensor to at least one of another robot or a computer.

Assignees

• Lg Electronics Inc

Inventors

• Lee Changhyeon
• Sohn Byungkon

Classifications

• G01S17/931

  of land vehicles · CPC title

• G01C21/005

  with correlation of navigation data from several sources, e.g. map or contour matching (G01C21/30 takes precedence) · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G01C3/08 Primary

  Use of electric radiation detectors · CPC title

• G08G1/161

  Decentralised systems, e.g. inter-vehicle communication · CPC title