Method of controlling mobile robot, apparatus for supporting the method, and delivery system using mobile robot

1. A method of controlling a mobile robot, the method being performed by a control apparatus, the method comprising:

acquiring a first control value for the mobile robot, which is input through a remote control apparatus;

acquiring a second control value for the mobile robot, which is generated by an autonomous driving module;

determining a weight for each control value based on a delay between the mobile robot and the remote control apparatus; and

generating a target control value of the mobile robot in combination of the first control value and the second control value based on the determined weights,

wherein a first weight for the first control value and a second weight for the second control value are inversely proportional to each other.

2. The method of claim 1 , further comprising adjusting the target control value so that a difference between the target control value and the first control value is less than or equal to a threshold value in response to determination that the difference is greater than or equal to the threshold value.

3. The method of claim 1 , wherein the determining the weight for each control value comprises:

determining whether the delay is greater than or equal to a threshold value;

determining the first weight as a maximum value within a designated range in response to determination that the delay is greater than or equal to the threshold value; and

determining the second weight as a minimum value within the designated range in response to determination that the delay is greater than or equal to the threshold value.

4. The method of claim 3 , wherein the threshold value is determined based on a current speed of the mobile robot.

5. The method of claim 1 , wherein the determining the weight for each control value comprises:

determining a risk of collision with an object near the mobile robot based on sensing data of the mobile robot; and

determining the weight for each control value further based on the risk of collision.

6. The method of claim 1 , wherein the determining the weight for each control value comprises:

determining a level of complexity of surrounding environments of the mobile robot based on sensing data of the mobile robot; and

determining the weight for each control value further based on the level of complexity.

7. The method of claim 6 ,

wherein the sensing data of the mobile robot includes image data, and

wherein the determining the level of complexity of surrounding environments comprises:

acquiring a result of recognizing the object near the mobile robot from the image data; and

determining the level of complexity based on the recognition result.

8. The method of claim 1 , further comprising acquiring a third control value for the mobile robot, which is generated based on a machine learning model that learns a driving pattern of a user who controls the remote control apparatus, wherein the generating the target control value of the mobile robot comprises generating the target control value further based on the third control value.

9. The method of claim 1 , further comprising acquiring a third control value for the mobile robot, which is generated based on a machine learning model that learns a driving pattern of a plurality of users, wherein the generating the target control value of the mobile robot comprises generating the target control value further based on the third control value.