Self-calibrating sensors and actuators for unmanned vehicles

• US 10,012,981 B2
• Filed: 08/30/2017
• Issued: 07/03/2018
• Est. Priority Date: 11/07/2014
• Status: Active Grant

• Current Assignee: Clearpath Robotics, Inc. (Rockwell Automation, Inc.)
• Original Assignee: Clearpath Robotics, Inc. (Rockwell Automation, Inc.)
• Inventors: Gariepy, Ryan Christopher, Shehata, Kareem, Mukherjee, Prasenjit, Tod, Anthony, Thomas, Teyvonia, Ma, Yan
• Primary Examiner(s): Dager, Jonathan M
• Application Number:
  US15/691,643
• Publication Number:
  US 20180004200A1
• Time in Patent Office: 307 Days
• Field of Search: None
• CPC Class Codes: G05D 1/0011 associated with a remote control arrangement
• 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 1/223 Command input arrangements on the remote controller, e.g. joysticks or touch screens
• CPC Class Codes: G05D 1/247 using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
• CPC Class Codes: G05D 1/249 from positioning sensors located off-board the vehicle, e.g. from cameras

Abstract

An apparatus, method, and system of self-calibrating sensors and actuators for unmanned vehicles is provided, which includes an unmanned vehicle comprising: a chassis; a propulsion system; one or more sensors configured to sense features around the chassis; a memory; a communication interface; and a processor configured to: operate the propulsion system in a guided calibration mode; automatically switch operation of the propulsion system to an autonomous calibration mode when a degree of certainty on a calibration of one or more of sensor data and a position of the chassis is above a first threshold value associated with safe operation of the propulsion system in the autonomous calibration mode; thereafter, operate the propulsion system in the autonomous calibration mode; and, automatically switch operation of the propulsion system to an operational mode when the degree of certainty is above a second threshold value greater than the first threshold value.

Claims

1. An unmanned vehicle comprising:

a communication interface; and

a processor for controlling a propulsion system of the unmanned vehicle and receiving sensor data from one or more sensors mounted on a chassis of the unmanned vehicle, the processor configured to;

in a guided calibration mode, while controlling the propulsion system according to commands received via the communications interface from an external guided control system, process the sensor data to determine at least one degree of certainty on a calibration of one or more of the sensor data and a position of the chassis;

automatically switch operation of the propulsion system to an autonomous calibration mode when the degree of certainty is above a first threshold value associated with safe operation of the propulsion system in the autonomous calibration mode;

thereafter, operate the propulsion system in the autonomous calibration mode by;

while automatically controlling the propulsion system to move the chassis, collecting the sensor data from the one or more sensors; and

,

further processing the sensor data using one or more uncertainty propagation models to determine at least one further degree of certainty on the calibration; and

,

automatically switch operation of the propulsion system to an operational mode when the further degree of certainty is above a second threshold value greater than the first threshold value.

2. The unmanned vehicle of claim 1, wherein the processor is further configured to, prior to entering the guided calibration mode, enumerate unmanned vehicle capabilities, by one or more of:

receiving, using the communication interface, a weight of the unmanned vehicle;

receiving, with the weight, an indication of accuracy of the weight;

receiving, using the communication interface, dimensions of the unmanned vehicle;

receiving, with the dimensions, a respective indication of accuracy of the dimensions of the unmanned vehicle;

autodetecting each of the one or more sensors;

receiving, using the communication interface, a list of the one or more sensors; and

using a scanner to scan one or more graphical identifiers of the one or more sensors.

3. The unmanned vehicle of claim 2, wherein the processor is further configured to automatically switch to the guided calibration mode when an enumeration of the unmanned vehicle capabilities supports a performance level threshold.

4. The unmanned vehicle of claim 1, wherein the processor is further configured to automatically switch to one or more of an error mode and an autorecovery mode when an error is detected in the operational mode, by:

stopping, using the propulsion system, movement of the chassis; and

, automatically switching to one or more of an enumerate capability mode and the guided calibration mode.

5. The unmanned vehicle of claim 4, wherein the error is based on one or more of:

a boundary of an estimated parameter; and

, a rate of change of the estimated parameter.

6. The unmanned vehicle of claim 1, wherein the processor is further configured to process the sensor data using one or more uncertainty propagation models to determine the at least one degree of certainty and the at least one further degree of certainty to determine one or more of:

a respective calibration of a relationship between uncertainty on sensor measurements with respect to the position of the chassis;

a respective location of each of the one or more sensors with respect to the chassis;

a respective orientation of each of the one or more sensors with respect to the chassis; and

, one or more of respective shapes and respective locations of sensed features.

7. The unmanned vehicle of claim 1, wherein the first threshold value and the second threshold value each comprise a respective constraint on one or more of:

a control algorithm, a mapping algorithm, a localization algorithm, at least one performance capability, and at least one current probability distribution.

8. The unmanned vehicle of claim 1, wherein the one or more sensors comprise one or more of:

one or more cameras, one or more LIDAR (Light Detection and Ranging) devices, one or more laser sensing devices, one or more radar devices, one or more accelerometers, and one or more magnetometers.

9. The unmanned vehicle of claim 1, wherein the calibration of the sensor data comprises a respective calibration of a respective position of each of the one or more sensors with respect to the chassis.

10. A method comprising:

while controlling, using a processor of an unmanned vehicle, a propulsion system of the unmanned vehicle according to commands received via a communications interface from an external guided control system in a guided calibration mode;

processing sensor data received at the processor from one or more sensors mounted on a chassis of the unmanned vehicle to determine at least one degree of certainty on a calibration of one or more of the sensor data and a position of the chassis;

automatically switching, using the processor, operation of the propulsion system to an autonomous calibration mode when the degree of certainty is above a first threshold value associated with safe operation of the propulsion system in the autonomous calibration mode;

thereafter, operating, using the processor, the propulsion system in the autonomous calibration mode by;

while automatically controlling the propulsion system to move the chassis, collecting the sensor data from the one or more sensors; and

, further processing the sensor data using one or more uncertainty propagation models to determine at least one further degree of certainty on the calibration; and

,

automatically switching, using the processor, operation of the propulsion system to an operational mode when the further degree of certainty is above a second threshold value greater than the first threshold value.

11. The method of claim 10, further comprising, prior to entering the guided calibration mode, enumerating, using the processor, unmanned vehicle capabilities, by one or more of:

receiving, using the communication interface, a weight of the unmanned vehicle;

receiving, with the weight, an indication of accuracy of the weight;

receiving, using the communication interface, dimensions of the unmanned vehicle;

receiving, with the dimensions, a respective indication of accuracy of the dimensions of the unmanned vehicle;

autodetecting each of the one or more sensors;

receiving, using the communication interface, a list of the one or more sensors; and

using a scanner to scan one or more graphical identifiers of the one or more sensors.

12. The method of claim 11, further comprising automatically switching, using the processor, to the guided calibration mode when an enumeration of the unmanned vehicle capabilities supports a performance level threshold.

13. The method of claim 10, further comprising automatically switching, using the processor, to one or more of an error mode and an autorecovery mode when an error is detected in the operational mode, by:

stopping, using the propulsion system, movement of the chassis; and

, automatically switching to one or more of an enumerate capability mode and the guided calibration mode.

14. The method of claim 13, wherein the error is based on one or more of:

a boundary of an estimated parameter; and

, a rate of change of the estimated parameter.

15. The method of claim 10, further comprising processing, using the processor, the sensor data using one or more uncertainty propagation models to determine the at least one degree of certainty and the at least one further degree of certainty to determine one or more of:

a respective calibration of a relationship between uncertainty on sensor measurements with respect to the position of the chassis;

a respective location of each of the one or more sensors with respect to the chassis;

a respective orientation of each of the one or more sensors with respect to the chassis; and

, one or more of respective shapes and respective locations of sensed features.

16. The method of claim 10, wherein the first threshold value and the second threshold value each comprise a respective constraint on one or more of:

a control algorithm, a mapping algorithm, a localization algorithm, at least one performance capability, and at least one current probability distribution.

17. The method of claim 10, wherein the one or more sensors comprise one or more of:

one or more cameras, one or more LIDAR (Light Detection and Ranging) devices, one or more laser sensing devices, one or more radar devices, one or more accelerometers, and one or more magnetometers.

18. The method of claim 10, wherein the calibration of the sensor data comprises a respective calibration of a respective position of each of the one or more sensors with respect to the chassis.

19. A computer program product, comprising a non-transitory computer usable medium having a computer readable program code adapted to be executed to implement a method comprising:

while controlling, using a processor of an unmanned vehicle, a propulsion system of the unmanned vehicle according to commands received via a communications interface from an external guided control system in a guided calibration mode;

processing sensor data received at the processor from one or more sensors mounted on a chassis of the unmanned vehicle to determine at least one degree of certainty on a calibration of one or more of the sensor data and a position of the chassis;

automatically switching, using the processor, operation of the propulsion system to an autonomous calibration mode when the degree of certainty is above a first threshold value associated with safe operation of the propulsion system in the autonomous calibration mode;

thereafter, operating, using the processor, the propulsion system in the autonomous calibration mode by;

while automatically controlling the propulsion system to move the chassis, collecting the sensor data from the one or more sensors; and

, further processing the sensor data using one or more uncertainty propagation models to determine at least one further degree of certainty on the calibration; and

,

automatically switching, using the processor, operation of the propulsion system to an operational mode when the further degree of certainty is above a second threshold value greater than the first threshold value.