Robot and method for controlling thereof
AssigneeSamsung Electronics Co., Ltd.
InventorsSeongmin Kang, Heungwoo Han
Life of this patent
Estimating the term…
Abstract
A robot is provided. The robot includes an image sensor, a driving part, a memory configured to store at least one instruction, and a processor, and the processor is configured to obtain a first image captured by the image sensor, obtain first information on an object included in the first image, control the driving part for the robot to approach the object, obtain a second image while the robot is approaching the object, obtain second information on an object based on the second image, determine whether an error is present in first information or second information based on the first information and the second information, and control an operation of the robot based on a determination result.
Claims15
A robot comprising:
- an image sensor;
- a driving part;
- a memory configured to store at least one instruction;
- and
- a processor,
- wherein the processor, when executing the at least one instruction, is configured to:
- obtain a first image captured by the image sensor,
- input the first image to an object recognition model and obtain first information comprising first identification information on an object comprised in the first image and a first reliability of the first identification information,
- control the driving part for the robot to approach the object,
- obtain a second image captured by the image sensor while the robot is approaching the object,
- input the second image to the object recognition model and obtain second information comprising second identification information on the object and a second reliability of the second identification information,
- determine whether an error is present in the first information by comparing the first information and the second information,
- control an operation of the robot based on the determination result,
- obtain a third image captured by the image sensor, and
- input the third image to the object recognition model and obtain third information comprising third identification information on an object in the third image and a third reliability of the third identification information,
- wherein a pre-set value is increased based on a determination that the object in the third image is an object other than a human, and
- wherein the increase of the pre-set value is configured to decrease a likelihood that the robot will approach the object of the third image.
A method for controlling a robot comprising an image sensor, the method comprising:
- obtaining a first image captured by the image sensor;
- inputting the first image to an object recognition model and obtaining first information comprising first identification information on an object comprised in the first image and a first reliability of the first identification information;
- controlling the robot to approach the object;
- obtaining a second image captured by the image sensor while the robot approaches the object;
- inputting the second image to the object recognition model and obtaining second information comprising second identification information on the object and a second reliability of the second identification information;
- determining whether an error is present in the first information by comparing the first information and the second information;
- controlling an operation of the robot based on the determination result;
- obtaining a third image captured by the image sensor;
- and
- inputting the third image to the object recognition model and obtain third information comprising third identification information on an object in the third image and a third reliability of the third identification information,
- wherein a pre-set value is increased based on a determination that the object in the third image is an object other than a human, and
- wherein the increase of the pre-set value is configured to decrease a likelihood that the robot will approach the object of the third image.
Dependencies are inferred from the claim text.