SEMI-AUTONOMOUS ROBOT THAT SUPPORTS MULTIPLE MODES OF NAVIGATION

• US 20120215380A1
• Filed: 02/23/2011
• Published: 08/23/2012
• Est. Priority Date: 02/23/2011
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Clinton, Nathaniel T., Voss, Chad Aron, Fouillade, Jean Sebastien, Olivier, Charles F. III, Chalabi, Malek M., Sanchez, Russ
• Application Number:
  US13/032,661
• Publication Number:
  US 20120215380A1
• Time in Patent Office: Days
• US Class Current: 701/2
• CPC Class Codes: G05D 1/0038 by providing the operator with simple or augmented images from one or more cameras located onboard the vehicle, e.g. tele-operation images analyzed by a computer and used for automatic navigation G05D1/0246
• CPC Class Codes: G05D 1/0044 by providing the operator with a computer generated representation of the environment of the vehicle, e.g. virtual reality, maps maps used for automatic navigation G05D1/0274; flight directors G01C23/005
• CPC Class Codes: G05D 1/0238 using obstacle or wall sensors G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS

Abstract

Described herein are technologies pertaining to robot navigation. The robot includes a video camera that is configured to transmit a live video feed to a remotely located computing device. A user interacts with the live video feed, and the robot navigates in its environment based upon the user interaction. In a first navigation mode, the user selects a location, and the robot autonomously navigates to the selected location. In a second navigation mode, the user causes the point of view of the video camera on the robot to change, and thereafter causes the robot to semi-autonomously drive in a direction corresponding to the new point of view of the video camera. In a third navigation mode, the user causes the robot to navigate to a selected location in the live video feed.

Claims

1. A method that is executable by a processor residing in a mobile robot, the method comprising:

causing video data captured by a video camera resident upon the robot to be transmitted to a remote computing device by way of a communications channel established between the robot and the remote computing device, wherein the video camera is capturing video data at a first point of view;

receiving a first command by way of the communications channel from the remote computing device to alter a point of view of the video camera from the first point of view to a second point of view;

responsive to receiving the first command, causing the point of view of the video camera to be altered from the first point of view to the second point of view while continuing to transmit video data to the remote computing device by way of the communications channel;

subsequent to the point of view of the robot being altered from the first point of view to the second point of view, receiving a second command by way of the communications channel to drive the robot in a direction that corresponds to a center of the second point of view;

causing a motor to drive the robot in the direction that corresponds to the second point of view until either

     1) a command is received from the remote computing device to discontinue driving the robot in the direction that corresponds to the center of the second point of view;

or

     2) data is received from a sensor on the robot that indicates that the robot is unable to continue travelling in the direction that corresponds to the center of the second point of view, wherein the robot travels autonomously in the direction that corresponds to the second point of view.

2. The method of claim 1, wherein the communications channel established between the robot and the remote computing device is over the Internet.

3. The method of claim 1, wherein the communications channel established between the robot and the remote computing device is over a cellular telephone network.

4. The method of claim 1, wherein the video camera is moveable by a different motor than the motor utilized to drive the robot.

5. The method of claim 1, further comprising:

receiving the command from the remote computing device to discontinue driving the robot in the direction that corresponds to the center of the second point of view, wherein the command identifies a predefined location; and

causing the robot to autonomously travel to the predefined location.

6. The method of claim 1, further comprising:

receiving the command from the remote computing device to discontinue driving the robot in the direction that corresponds to the center of the second point of view, wherein the command identifies a particular location that is in the second point of view of the video camera; and

causing the robot to autonomously travel to the location in the second point of view of the video camera.

7. The method of claim 1, wherein the sensor in the robot is an infrared depth sensor.

8. The method of claim 1, further comprising:

receiving a third command from the remote computing device to alter the point of view of the video camera from the second point of view to a third point of view; and

responsive to receiving the third command, causing the point of view of the video camera to be changed from the second point of view to the third point of view; and

causing the motor to drive the robot in another direction that corresponds to a center of the third point of view.

9. The method of claim 1, further comprising causing a display on the robot to display data pertaining to the second command on a display of the robot while the robot is travelling in the direction that corresponds to the center of the second point of view.

10. The method of claim 1, further comprising:

receiving data from the sensor on the robot that indicates that the robot is unable to continue travelling in the direction that corresponds to the center of the second point of view, wherein the data from the sensor indicates existence of an obstacle in the direction that corresponds to the center of the second point of view; and

automatically causing a travel direction of the robot to alter to a new travel direction to avoid the obstacle.

11. The method of claim 10, further comprising:

receiving data from the sensor on the robot that indicates that the obstacle has been passed by the robot; and

automatically causing the travel direction of the robot to alter such that the robot travels in the direction that corresponds to the center of the second point of view.

12. A robot, comprising:

a processor; and

a memory, wherein the memory comprises a plurality of components that are executable by the processor, the components comprising;

a direct and drive component that is configured to direct the robot along a path in a first direction based at least in part upon commands received from a remote computing device, wherein the remote computing device is in communication with the robot by way of a network, wherein the commands comprise;

a first command that causes the direct and drive component to change a point of view of a video camera on the robot to change from a first point of view to a second point of view; and

a second command that causes the direct and drive component to drive the robot to drive along the path in the first direction subsequent to the point of view of the video camera changing from the first point of view to the second point of view, wherein the first direction corresponds to a center point of the second point of view;

an obstacle detector component that receives data from a sensor that indicates that an obstacle resides in the path of the robot and outputs an indication that the obstacle resides in the path of the robot; and

a direction modifier component that receives the indication, and responsive to receipt of the indication, causes the robot to automatically change direction from the first direction to a second direction to avoid the obstacle.

13. The robot of claim 12, wherein the network is the Internet.

14. The robot of claim 12, wherein the robot is configured to receive the commands from a mobile computing device.

15. The robot of claim 12, wherein the components further comprise an audio/video transmitter component that is configured to transmit live audio/video captured from the video camera in the robot to the remote computing device.

16. The robot of claim 12, wherein the memory further comprises a map of an environment, wherein the map of the environment comprises a plurality of tagged locations, and wherein the plurality of components further comprise:

a location direction component that receives a third command that comprises an indication of a selection of a tagged location from amongst the plurality of tagged locations in the map in the memory of the robot, wherein the location direction component causes the robot to travel from a current position to the tagged location, wherein the obstacle detector component receives second data from the sensor that indicates that another obstacle is in a path taken by the robot to reach the tagged location, and wherein the direction modifier component causes the robot to autonomously avoid the obstacle and reaching the tagged location.

17. The robot of claim 16, wherein the robot is configured to output data on a display of the robot to indicate the location to which the robot is travelling.

18. The robot of claim 12, wherein the plurality of components further comprise:

a drag and direct component that is configured to direct the robot to a particular specified location that is in a portion of video captured by the video camera based at least in part upon additional commands received from the remote computing device, wherein the additional commands comprises;

a third command that causes the point of view of the video camera to change from the second point of view to a third point of view; and

a fourth command that specifies a particular location in the third point of view of the video camera subsequent to the point of view of the video camera changing from the third point of view to the fourth point of view, wherein the obstacle, wherein detector component receives second data from the sensor that indicates that another obstacle resides between the robot and the specified location, and wherein the direction modifier component causes the robot to autonomously avoid the obstacle and reach the specified location.

19. The robot of claim 12, wherein the direct and drive component causes the point of view of the video camera to change from the first point of view to the second point of view without altering an orientation of a body of the robot.

20. A robot, comprising:

a processor; and

a memory that comprises a plurality of components that are executable by the processor, wherein the plurality of components comprises;

a drive and direct component that is configured to drive a robot in a direction specified by way of a first command from a remote computing device, wherein the drive and direct component is configured to autonomously cause the robot to avoid obstacles while driving in the direction specified in the first command;

a location direction component that is configured to drive the robot to a tagged location in a map of an environment that is being experienced by the robot, wherein the map is retained in the memory of the processor, wherein the location direction component is configured to drive the robot to the tagged location responsive to receipt of a second command from the remote computing device, wherein the second command indicates the tagged location,

and wherein the location direction component is configured to autonomously cause the robot to avoid obstacles while driving to the tagged location; and

a drag and direct component that is configured to drive the robot to a particular location that is in a field of view of a video camera in the robot responsive to a third command from the remote computing device, wherein the third command indicates the location in the field of view of the video camera, and wherein the drag and direct component is configured to autonomously cause the robot to avoid obstacles while driving to the particular location.