Incidental robot-human contact detection

• US 9,868,213 B2
• Filed: 08/11/2015
• Issued: 01/16/2018
• Est. Priority Date: 08/11/2015
• Status: Active Grant

• Current Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Fine, Kevin S, Kruglick, Ezekiel
• Primary Examiner(s): RINK, RYAN J
• Application Number:
  US14/823,500
• Publication Number:
  US 20170043483A1
• Time in Patent Office: 889 Days
• Field of Search: None
• CPC Class Codes: B25J 9/1676 Avoiding collision or forbidden zones
• CPC Class Codes: G05B 2219/40201 Detect contact, collision with human
• CPC Class Codes: Y10S 901/09 Closed loop, sensor feedback controls arm movement
• CPC Class Codes: Y10S 901/15 Jointed arm
• CPC Class Codes: Y10S 901/46 Sensing device

Abstract

Technologies are generally described for detection of incidental robot-human contact. In some examples, a robotic actuator movement may generate a feedback signal, such as a haptic signal, a proprioreceptive signal, an optical signal, and/or an infrared signal. A tremor detector may determine whether the feedback signal contains a tremor signal characteristic of a human, for example by determining whether frequency components in the feedback signal fall within particular frequency ranges. Upon determining that the feedback signal does contain a tremor signal characteristic of a human, the tremor detector may conclude that the robotic actuator has come into contact with a human, and may cause the actuator to halt its movement.

Claims

1. A method to guide actuator movement, the method comprising:

receiving a feedback signal associated with a movement of an actuator;

filtering the received feedback signal to remove frequency components that have a frequency less than 7 Hz or greater than 12 Hz;

monitoring a power spectral density of the filtered feedback signal, wherein the filtered feedback signal includes information representative of a characteristic of at least one of a human or an animal;

detecting whether there is an increase in the power spectral density of the filtered feedback signal;

determining that the actuator has come into contact with the at least one of the human or the animal, based on a detection of the increase in the power spectral density of the filtered feedback signal; and

in response to the determination that the actuator has come into contact with the at least one of the human or the animal, halting the movement of the actuator.

2. The method of claim 1, wherein detecting whether there is the increase in the power spectral density of the filtered feedback signal comprises:

detecting whether there is an increase in the power spectral density of the filtered feedback signal with respect to at least one other frequency component of the received feedback signal, wherein the at least one other frequency component has a frequency less than 7 Hz or greater than 12 Hz.

3. The method of claim 1, wherein receiving the feedback signal includes receiving a haptic signal associated with a pressure detected on the actuator.

4. The method of claim 1, wherein receiving the feedback signal includes receiving a proprioreceptive signal associated with at least one of a force and a torque applied at a joint of the actuator.

5. The method of claim 4, wherein receiving the proprioreceptive signal comprises detecting the proprioreceptive signal from at least one of a motor driver current and a stress signal.

6. The method of claim 1, wherein receiving the feedback signal comprises receiving a remote signal from a remote sensor that generates the remote signal in response to the movement of the actuator.

7. The method of claim 6, wherein receiving the remote signal includes receiving at least one of optical image data and infrared data.

8. The method of claim 1, wherein detecting whether there is the increase in the power spectral density of the filtered feedback signal comprises initially evaluating the filtered feedback signal with a first change point detector and subsequently evaluating the filtered feedback signal with a second change point detector, and wherein the first change point detector reacts more quickly than the second change point detector.

9. A tremor detection system, comprising:

a sensor signal processor configured to receive a feedback signal associated with a movement of a robotic actuator; and

a processor block, operatively coupled to the sensor signal processor, configured to;

determine that the feedback signal includes a frequency component that has a first frequency that is at least 7 Hz and at most 12 Hz, and that includes information representative of a characteristic of at least one of a human or an animal;

monitor a power spectral density of the frequency component;

detect whether there is an increase in the power spectral density of the frequency component with respect to at least one other frequency component of the feedback signal, wherein the at least one other frequency component has a second frequency less than 7 Hz or greater than 12 Hz;

determine that the robotic actuator has come into contact with the at least one of the human or the animal, based on a detection of the increase in the power spectral density of the frequency component; and

in response to the determination that the robotic actuator has come into contact with the at least one of the human or the animal, transmit a control signal to cause the robotic actuator to halt the movement.

10. The system of claim 9, wherein the processor block is configured to:

detect an increase in an amplitude of the frequency component with respect to the at least one other frequency component of the feedback signal; and

determine that the robotic actuator has come into contact with the at least one of the human or the animal, based on the detection of the increase in the amplitude of the frequency component.

11. The system of claim 9, wherein the feedback signal includes a haptic signal associated with a pressure detected on the robotic actuator.

12. The system of claim 9, wherein the feedback signal includes a proprioreceptive signal associated with at least one of a force and a torque applied at a joint of the robotic actuator.

13. The system of claim 12, wherein the proprioreceptive signal is based on at least one of a motor driver current and a stress signal.

14. The system of claim 9, wherein the feedback signal includes a remote signal from a remote sensor that generates the remote signal in response to the movement of the robotic actuator.

15. The system of claim 14, wherein the remote signal includes at least one of optical image data and infrared data.

16. The system of claim 9, wherein to detect whether there is the increase in the power spectral density of the frequency component, the processor block is configured to:

initially evaluate the frequency component with a first change point detector; and

subsequently evaluate the frequency component with a second change point detector,

wherein the first change point detector reacts more quickly than the second change point detector.

17. A robotic actuator system, comprising:

an actuator configured to;

perform a physical action in response to a control signal; and

stop the physical action in response to a stop signal;

a controller operatively coupled to the actuator and configured to transmit the control signal and the stop signal to the actuator; and

a tremor detector operatively coupled to the controller and configured to;

receive a feedback signal associated with the physical action from at least one of the actuator and the controller;

determine that the feedback signal includes a tremor signal, wherein the tremor signal includes a frequency component that has a first frequency between 7 Hz and 12 Hz, and wherein the tremor signal includes information representative of a characteristic of at least one of a human or an animal;

monitor a power spectral density of the tremor signal;

detect whether there is an increase in the power spectral density of the tremor signal with respect to at least one other frequency component of the feedback signal, wherein the at least one other frequency component has a second frequency less than 7 Hz or greater than 12 Hz;

determine that the actuator has come into contact with at least one of the human or the animal, based on a detection of the increase in the power spectral density of the tremor signal; and

in response to s determination that the actuator has come into contact with the at least one of the human or the animal, cause the controller to transmit the stop signal to the actuator.

18. The system of claim 17, wherein the tremor detector is configured to determine that the actuator has come into contact with the at least one of the human or the animal, in response to a detection of an increase in an amplitude of the tremor signal with respect to the at least one other frequency component.

19. The system of claim 17, wherein the feedback signal includes at least one of:

a haptic signal associated with a pressure detected on the actuator during the performance of the physical action; and

a proprioreceptive signal associated with at least one of a force and a torque applied at a joint of the actuator during the performance of the physical action.

20. The system of claim 19, wherein the proprioreceptive signal is based on at least one of a motor driver current and a stress signal.

21. The system of claim 17, wherein the feedback signal includes a remote signal from a remote sensor that generates the remote signal in response to a movement of the actuator.

22. The system of claim 21, wherein the remote signal includes at least one of optical image data and infrared data.

23. The system of claim 17, wherein to detect whether there is the increase in the power spectral density of the tremor signal, the tremor detector is configured to:

initially evaluate the tremor signal with a first change point detector; and

subsequently evaluate the tremor signal with a second change point detector,

wherein the first change point detector reacts more quickly than the second change point detector.