Method and/or apparatus for navigating mobile robot using virtual sensor

• US 20050187678A1
• Filed: 02/18/2005
• Published: 08/25/2005
• Est. Priority Date: 02/19/2004
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Myeong, Hyeon, Hong, Youngjin
• Granted Patent: US 8,712,588 B2
• Time in Patent Office: Days
• US Class Current: 701/27
• CPC Class Codes: G05D 1/0255 using acoustic signals, e.g. ultra-sonic singals sonar systems designed for anti-collision purposes G01S15/93
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A method and apparatus of improving the navigation performance of robot are provided. The navigation method using a virtual sensor includes: generating information on positions of obstacles, the information which is estimated to be generated by virtual sensors that are virtually present, based on information on positions of the obstacles, which is generated by physical sensors; and controlling a movement of a robot according to the information on the positions of the obstacles. It is possible to overcome limits in the number and arrangement of previously installed physical sensors.

Claims

1. A navigation method using a virtual sensor, comprising:

(a) generating information on positions of obstacles, the information which is estimated to be generated by virtual sensors that are virtually present, based on information on positions of the obstacles, which is generated by physical sensors; and

(b) controlling a movement of a robot according to the information on the positions of the obstacles.

2. The navigation method of claim 1, wherein the process (a) generates information on distances between the obstacles and the robot, the information which is estimated to be generated by the virtual sensors, using the difference between information on positions of obstacles, which are present in direction angles of the virtual sensors, and information on a current position of the robot.

3. The navigation method of claim 1, wherein the process (b) controls the movement using methods such as a fuzzy rule-based control method, a neural network based control method, or a proportional integral derivative (PID) control method, which is a sensor-based control method.

4. The navigation method of claim 1, further comprising (c) receiving a predetermined selected sensor arrangement type, wherein the process (a) generates information on positions of obstacles, the information which is estimated to be generated by virtual sensors that are virtually present at positions determined according to the selected sensor arrangement type.

5. The navigation method of claim 1, wherein the process (a) comprises:

(a1) generating IDs of the virtual sensors based on direction angles of the virtual sensors and a current direction angle of the robot; and

(a2) generating information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors having the IDs, using difference between information on positions of obstacles that are present at the direction angles of the virtual sensors and information on a current position of the robot.

6. The navigation method of claim 1, further comprising (d) updating presence probability values of the obstacles, which are recorded on cells of a map representing a predetermined area, according to the information on the positions of the obstacles, which is generated by the physical sensors, wherein the process (a) generates information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors, using the difference between information on positions of cells, which have probability values greater than a predetermined threshold value among the cells having the updated probability values, and information on a current position of the robot.

7. The navigation method of claim 6, wherein the process (a) comprises:

(a1) generating IDs of the virtual sensors using the difference between the direction angles of the virtual sensors and a current direction angle of the robot; and

(a2) generating information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors having the IDs, using the difference between information on positions of cells, which have probability values greater than the predetermined threshold value among the cells having updated probability values, and the information on the current position of the robot.

8. A navigation apparatus using a virtual sensor, comprising:

a virtual sensor information generating part which generates information on position(s) of obstacle(s), the information which is estimated to be generated by virtual sensors that are virtually present, based on information on position(s) of the obstacle(s), which is generated by physical sensors; and

a control part which controls a movement of a robot according to the information on the positions of the obstacle(s).

9. The navigation apparatus of claim 8, wherein the virtual sensor information generating part generates information on distances between the obstacles and the robot, the information which is estimated to be generated by the virtual sensors, using difference between information on positions of obstacles, which are present in direction angles of the virtual sensors, and information on a current position of the robot.

10. The navigation apparatus of claim 8, wherein the control part controls the movement using methods such as a fuzzy rule-based control method, a neural network-based control method, or a proportional integral derivative (PID) control method, which is a sensor-based control method.

11. The navigation apparatus of claim 8, further comprising a sensor arrangement type selecting part which receives a predetermined selected sensor arrangement type, wherein the virtual sensor information generating part generates information on positions of obstacles, the information which is estimated to be generated by virtual sensors that are virtually present at positions determined according to the selected sensor arrangement type.

12. The navigation apparatus of claim 8, wherein the virtual sensor information generating part comprises:

a virtual sensor ID generating unit which generates IDs of the virtual sensors based on direction angles of the virtual sensors and a current direction angle of the robot; and

a virtual sensor distance generating unit which generates information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors having the IDs, using difference between information on positions of obstacles that are present at the direction angles of the virtual sensors and information on a current position of the robot.

13. The navigation apparatus of claim 8, further comprising a map value updating part which updates presence probability values of the obstacles, which are recorded on cells of a map representing a predetermined area, according to the information on the positions of the obstacles, which is generated by the physical sensors, wherein the virtual sensor information generating part generates information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors, using the difference between information on positions of cells, which have probability values greater than a predetermined threshold value among the cells having updated probability values, and information on a current position of the robot.

14. The navigation apparatus of claim 13, wherein the virtual sensor information generating part comprises:

a virtual sensor ID generating unit which generates IDs of the virtual sensors using difference between the direction angles of the virtual sensors and a current direction angle of the robot; and

a virtual sensor distance information generating unit which generates information on distances between obstacles and the robot, the information which is estimated to be generated by the virtual sensors having the IDs, using difference between information on positions of cells, which have probability values greater than the predetermined threshold value among the cells having the updated probability values, and the information on the current position of the robot.

15. A computer readable recording medium encoded with processing instructions for implementing a navigation method using a virtual sensor, the method comprising:

(a) generating information on positions of obstacles, the information which is estimated to be generated by virtual sensors that are virtually present, based on information on positions of the obstacles, which is generated by physical sensors; and

(b) controlling a movement of a robot according to the information on the positions of the obstacles.

16. A method of controlling a robot, comprising:

generating a map of object position probabilities as the robot moves using actual sensor information;

generating virtual sensor information using the map; and

moving the robot responsive to the virtual sensor information.