Robotic creature and method of operation

• US 10,120,386 B2
• Filed: 11/17/2017
• Issued: 11/06/2018
• Est. Priority Date: 11/18/2016
• Status: Active Grant

• Current Assignee: Robert Bosch Start-Up Platform North America LLC (Robert Bosch GmbH)
• Original Assignee: Robert Bosch Start-Up Platform North America LLC (Robert Bosch GmbH)
• Inventors: Lee, Stephanie, Dooley, Douglas, Osentoski, Sarah, Hsiao, Kaijen
• Primary Examiner(s): Oh, Harry Y
• Application Number:
  US15/817,035
• Publication Number:
  US 20180143645A1
• Time in Patent Office: 354 Days
• Field of Search: 700253
• CPC Class Codes: B25J 11/001 with emotions simulating means
• CPC Class Codes: B25J 11/0015 Face robots, animated artificial faces for imitating human expressions
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• 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 robotic creature system includes an actuatable head defining eyes, an eyelid mechanism, a body, a drivetrain, and a set of sensors. A method for robotic creature operation includes: detecting an event associated with a technological imperfection and automatically performing a set of expressive actions associated with the event.

Claims

1. A method for responding to a technological imperfection associated with a task of a robot, comprising:

receiving a command to perform a first action;

sampling sensor signals associated with the first action from a sensor;

attempting performance of the first action based on the sensor signals;

in response to failure to perform the first action;

performing a data-acquiring action associated with the failure, comprising sampling auxiliary signals with an on-board sensor;

performing an expressive action, associated with the failure, according to instructions determined based on a technical requirement of the data-acquiring action; and

performing the first action, wherein the first action is performed based on the auxiliary signals.

2. The method of claim 1, wherein:

the sensor comprises an audio sensor;

failure to perform the first action comprises receiving a voice command omitted from a library of known commands;

the expressive action comprises a head actuation; and

the data-acquiring action comprises movement toward a user.

3. The method of claim 2, wherein the head actuation comprises a side-to-side movement performed at a predetermined frequency.

4. The method of claim 1, wherein:

the sensor comprises a location sensor;

failure to perform the first action comprises detecting a delocalization event;

the data-acquiring action comprises sampling a feature of an ambient environment using an on-board mapping system over a predetermined time period; and

the expressive action comprises a head actuation animation having a duration substantially equal to the predetermined time period.

5. The method of claim 4, wherein detecting the delocalization event comprises detecting a pickup event, comprising detecting wheel unloading and re-loading.

6. The method of claim 1, wherein:

the sensor comprises a contact sensor arranged in a front bumper of the robot;

the first action comprises traversal along a navigation route, wherein failure to perform the first action comprises detecting a collision between the front bumper and an external obstacle;

the expressive action comprises a head actuation downward toward the obstacle; and

the data-acquiring action comprises movement away from the obstacle.

7. The method of claim 6, wherein the front bumper is mounted to the robot at a predetermined height relative to the ground.

8. The method of claim 6, further comprising:

concurrently sampling an image of the external obstacle with a camera arranged within the head while the head is actuated downward; and

determining an obstacle dimension based on the image;

wherein performing the first action based on the auxiliary signals comprises;

generating a second navigation route based on the navigation route and the obstacle dimension; and

controlling the robot to traverse along the second navigation route.

9. The method of claim 1, wherein the data-acquiring action and the expressive action are performed concurrently.

10. The method of claim 1, wherein the expressive action comprises a string of non-verbal sounds.

11. The method of claim 10, wherein the robot determines a pitch of the non-verbal sounds based on the failure to perform the first action, wherein the robot subsequently plays the non-verbal sounds with said pitch to a user.

12. The method of claim 1, further comprising:

receiving a user input, wherein the user input is assigned a positivity score based on a predetermined positivity scale;

determining a robot mood score based on the positivity score; and

performing the first action based on the robot mood score, wherein the first action is associated with a set of operation parameters, wherein a magnitude of an operation parameter within the set of operation parameters is determined based on the robot mood score.

13. The method of claim 12, wherein the robot mood score degrades with time.

14. The method of claim 13, wherein the user input comprises a touch received by a capacitive touch sensor on a head of the robot.

15. The method of claim 14, further comprising identifying a specific user, wherein the robot mood score is further determined based on a history of user interactions associated with the specific user.