Auto-recharging of robot

• US 10,585,437 B1
• Filed: 04/26/2019
• Issued: 03/10/2020
• Est. Priority Date: 09/25/2018
• Status: Active Grant

• Current Assignee: NextVPU (Shanghai) Co., Ltd.
• Original Assignee: NextVPU (Shanghai) Co., Ltd.
• Inventors: Zhou, Ji, Feng, Xinpeng
• Primary Examiner(s): Holloway, Jason
• Application Number:
  US16/396,613
• Publication Number:
  US 20200097017A1
• Time in Patent Office: 319 Days
• CPC Class Codes: A47L 11/4011 Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
• CPC Class Codes: A47L 2201/00 Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
• CPC Class Codes: A47L 2201/022 Recharging of batteries
• CPC Class Codes: A47L 2201/04 Automatic control of the travelling movement; Automatic obstacle detection
• CPC Class Codes: A47L 9/2873 Docking units or charging stations for autonomous or robotic vacuum cleaners A47L2201/02
• CPC Class Codes: B25J 9/0003 Home robots, i.e. small robots for domestic use
• CPC Class Codes: B25J 9/1661 characterised by task planning, object-oriented languages
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: B60L 2200/40 Working vehicles
• CPC Class Codes: G05D 1/0225 involving docking at a fixed facility, e.g. base station or loading bay parking aids B62D15/027
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means

Abstract

The present disclosure provides a robot, an auto-recharging method therefor and a storage medium. The auto-recharging method for a robot comprises: the robot moving from an initial position to a docking position, wherein the docking position faces a charging interface of a charging pile; the robot traveling from the docking position to a charging position along a first path such that the robot is docked to the charging pile at the charging position, wherein the first path is a straight-line or approximately straight-line path, and the robot maintains a docking pose during the course of traveling along the first path and the charging pile is identified in the images captured by the robot in real time. The present disclosure may achieve auto-recharging of the robot without guidance of active light source, thereby reducing the cost of the robot and meanwhile offering a high flexibility to the equipment.

Claims

1. A computer-implemented method, comprising:

moving a robot from an initial position to a docking position in an environment map that is generated by the robot, wherein the robot captures images of surroundings of the robot when generating the environment map, wherein the robot at the docking position faces a charging interface of a charging pile, and the docking position is determined based on a position of the charging pile identified by means of images captured by the robot in real time; and

moving the robot from the docking position to a charging position along a first path such that the robot is docked to the charging pile at the charging position, wherein the first path is a straight-line or approximately straight-line path, and wherein, during the course of traveling along the first path, the robot maintains a docking pose and the charging pile is identifiable in the images captured by the robot in real time, and

wherein the operation of moving the robot from the initial position to the docking position further comprises,

moving the robot from the initial position to a boundary of a transit area along a second path, wherein the second path is planned by the robot at the initial position, wherein the transit area is preset in the environment map when the environment map is generated, and the transit area is defined as an area in which each image captured by the robot when generating the environment map has the charging pile; and

moving the robot from the boundary of the transit area to the docking position along a third path, wherein the third path is adjusted in real time based on the images captured by the robot in real time.

2. The computer-implemented method according to claim 1, wherein the operation of moving the robot from the boundary of the transit area to the docking position along the third path further comprises:

determining whether the charging pile is identified in the images captured by the robot in real time when the robot moves to the boundary of the transit area;

when positive, taking the current position of the robot as a transit position, and moving the robot from the transit position to the docking position along the third path;

when negative, moving the robot according to a predetermined mode or an adaptive mode until the charging pile is identified in the images captured by the robot in real time, and taking the position of the robot at which the charging pile is identified in the images captured by the robot as the transit position.

3. The computer-implemented method according to claim 2, wherein when the charging pile still fails to be identified in the images captured by the robot in real time after moving the robot according to the predetermined mode or the adaptive mode, an alert indicating a failure to find the charging pile is generated.

4. The computer-implemented method according to claim 2, wherein the docking position is located in the transit area, and the docking position is determined at the transit position on the basis of the position of the charging pile identified by means of images captured by the robot in real time at the transit position.

5. The computer-implemented method according to claim 1, wherein the operation of moving the robot from the docking position to the charging position along the first path comprises:

adjusting, by the robot, the first path based on an auxiliary pattern identified in images captured by the robot in real time, wherein the auxiliary pattern is provided on the charging pile.

6. The computer-implemented method according to claim 1, wherein the initial position of the robot is determined based on a motion trajectory of the robot in the environment map before recharging, and/or a position, in the environment map, of an identification feature in the images captured by the robot in real time, wherein the identification feature comprises a feature of the charging pile, or a feature of an object or a label in the environment map, wherein the object or the label has a fixed positional relationship with respect to the charging pile.

7. A robot, characterized in that the robot comprises:

a sensor at least configured to capture images of surroundings of the robot in real time;

a motor configured to drive the robot;

a processor configured to;

cause the robot to move from an initial position to a docking position in an environment map that is generated by the robot, wherein the robot captures images of surroundings of the robot when generating the environment map, wherein the robot at the docking position faces a charging interface of a charging pile, and the docking position is determined based on a position of the charging pile identified by means of images captured by the robot in real time; and

cause the robot to travel along a first path from the docking position to a charging position so as to be docked with the charging pile at the charging position, wherein the first path is a straight-line or approximately straight-line path, and wherein, during the course of traveling along the first path, the robot maintains a docking pose and the charging pile is identifiable in the images captured by the robot in real time, and

wherein the processor is configured to;

cause the robot to move from the initial position to a boundary of a transit area along a second path, wherein the second path is planned by the robot at the initial position, wherein the transit area is preset in the environment map when the environment map is generated, and the transit area is defined as an area in which each image captured by the robot when generating the environment map has the charging pile, and

cause the robot to move from the boundary of the transit area to the docking position along a third path, wherein the third path is adjusted in real time based on the images captured by the robot in real time.

8. The robot according to claim 7, wherein the processor is configured to:

determine whether the charging pile is identified in the images captured by the robot in real time when the robot moves to the boundary of the transit area;

when positive, take the current position of the robot as a transit position, and cause the robot to move from the transit position to the docking position along the third path;

when negative, cause the robot to move according to a predetermined mode or an adaptive mode until the charging pile is identified in the images captured by the robot in real time, and take the position of the robot at which the charging pile is identified in the images captured by the robot as the transit position.

9. The robot according to claim 8, wherein the processor is configured to generate an alert indicating a failure to find the charging pile, when the charging pile still fails to be identified in the images captured by the robot in real time after moving the robot according to the predetermined mode or the adaptive mode.

10. The robot according to claim 8, wherein the docking position is located in the transit area, and the docking position is determined at the transit position on the basis of the position of the charging pile identified by means of images captured by the robot in real time at the transit position.

11. The robot according to claim 7, wherein the processor is configured to:

adjust the first path based on an auxiliary pattern identified in images captured by the robot in real time, wherein the auxiliary pattern is provided on the charging pile.

13. The robot according to claim 7, wherein the initial position of the robot is determined based on a motion trajectory of the robot in the environment map before recharging, and/or a position, in the environment map, of an identification feature in the images captured by the robot in real time, wherein the identification feature comprises a feature of the charging pile, or a feature of an object or a label in the environment map, wherein the object or the label has a fixed positional relationship with respect to the charging pile.

12. A non-transitory storage medium comprising a computer program which, when executed by a processor, causes the processor to perform the operations as follows:

moving a robot from an initial position to a docking position in an environment map that is generated by the robot, wherein the robot captures images of surroundings of the robot when generating the environment map, wherein the robot at the docking position faces a charging interface of a charging pile, and the docking position is determined based on a position of the charging pile identified by means of images captured by the robot in real time; and

moving the robot from the docking position to a charging position along a first path so as to be docked with the charging pile at the charging position, wherein the first path is a straight-line or approximately straight-line path, and wherein, during the course of traveling along the first path, the robot maintains a docking pose and the charging pile is identifiable in the images captured by the robot in real time, and

wherein the operation of moving the robot from the initial position to the docking position further comprises;

moving the robot from the initial position to a boundary of a transit area along a second path, wherein the second path is planned by the robot at the initial position, wherein the transit area is preset in the environment map when the environment map is generated, and the transit area is defined as an area in which each image captured by the robot when generating the environment map has the charging pile; and

moving the robot from the boundary of the transit area to the docking position along a third path, wherein the third path is adjusted in real time based on the images captured by the robot in real time.