Artificial intelligence robot for determining cleaning route using sensor data and method for the same

1. An artificial intelligence (AI) robot for determining a cleaning route using sensor data, comprising:

a sensor device including at least one of an image sensor, a depth sensor or a shock sensor;

a cleaning device including at least one of a suction device or a mopping device;

a driving device configured to drive the AI robot; and

a processor configured to:

acquire the sensor data from the sensor device,

determine a complex area having adjacent complex areas using the acquired sensor data,

create a virtual wall for blocking an entry into the determined complex area,

determine the cleaning route in consideration of the created virtual wall, and

control the cleaning device and the driving device based on the determined cleaning route,

wherein the processor is further configured to create the virtual wall based on determining whether the adjacent complex areas include specific rule-based complex areas that are adjacent to one another within a predetermined distance,

wherein the complex area is at least one of an area with a predetermined number of obstacles or an area having a predetermined width relative to access by the AI robot.

2. The AI robot of claim 1 , wherein the processor is configured to:

determine the complex area in an around map by using the acquired sensor data and the around map with regard to a predetermined radius around the AI robot, and

create the virtual wall in the around map.

3. The AI robot of claim 2 , wherein the processor is configured to determine the cleaning route by avoiding the virtual wall.

4. The AI robot of claim 3 , wherein the processor is configured to create the virtual wall by including the complex area.

5. The AI robot of claim 3 , wherein the processor is configured to create the virtual wall only in a passage entering into the complex area.

6. The AI robot of claim 1 , wherein the processor is configured to determine the complex area from the acquired sensor data by using a complex area determination model learned using a machine learning algorithm or a deep learning algorithm.

7. The AI robot of claim 6 , wherein the processor is configured to create the virtual wall from the determined complex area by using a first virtual wall creation model learned using the machine learning algorithm or the deep learning algorithm.

8. The AI robot of claim 1 , wherein the processor is configured to create the virtual wall from the acquired sensor data by using a second virtual wall creation model learned using a machine learning algorithm or a deep learning algorithm.

9. The AI robot of claim 1 , further comprising a memory for storing a Simultaneous Localization And Mapping (SLAM) map with regard to an operating space of the AI robot,

wherein the processor is configured to:

map the created virtual wall on the SLAM map, and

determine the cleaning route using the SLAM map which includes the virtual wall.

10. The AI robot of claim 9 , wherein the processor is configured to determine a new cleaning route by excluding the virtual wall, if the cleaning along the cleaning route determined in consideration of the virtual wall is completed.

11. A method for determining a cleaning route using sensor data, the method performed by an artificial intelligence (AI) robot that includes a sensor, a cleaning device and a driving device, the method comprising:

acquiring the sensor data from the sensor, the sensor comprising at least one of an image sensor, a depth sensor or a shock sensor,

determining a complex area having adjacent complex areas using the acquired sensor data,

creating a virtual wall for blocking an entry into the determined complex area,

determining the cleaning route in consideration of the created virtual wall, and

controlling the cleaning device and the driving device based on the determined cleaning route,

wherein the method further comprises creating the virtual wall based on determining whether the adjacent complex areas include specific rule-based complex areas that are adjacent to one another within a predetermined distance,

wherein the complex area is at least one of an area with a predetermined number of obstacles or an area having a predetermined width relative to access by the AI robot.

12. A non-transitory computer readable recording medium containing a program for causing an artificial intelligence (AI) robot that includes a sensor, a cleaning device and a driving device to determine a cleaning route using sensor data, the method comprising:

acquiring the sensor data from the sensor, the sensor comprising at least one of an image sensor, a depth sensor or a shock sensor,

determining a complex area having adjacent complex areas using the acquired sensor data,

creating a virtual wall for blocking an entry into the determined complex area,

determining the cleaning route in consideration of the created virtual wall, and

controlling the cleaning device and the driving device based on the determined cleaning route,

wherein the method further comprises creating the virtual wall based on determining whether the adjacent complex areas include specific rule-based complex areas that are adjacent to one another within a predetermined distance,

wherein the complex area is at least one of an area with a predetermined number of obstacles or an area having a predetermined width relative to access by the AI robot.