Machine positioning system utilizing position error checking

Patent metadata

Field	Value
Publication number	US-9234758-B2
Application number	US-201213721958-A
Country	US
Kind code	B2
Filing date	Dec 20, 2012
Priority date	Dec 20, 2012
Publication date	Jan 12, 2016
Grant date	Jan 12, 2016

Abstract

A system and method for estimating position of a machine is disclosed. The method may include receiving, from a perception sensor, scene data describing an environment in a vicinity of the machine and estimating a first position of the machine based on the scene data. The method may include determining whether a first signal indicative of a location of the machine is received by the machine and estimating a second position of the machine when it is determined that the first signal is received. The method may include comparing the second position with the first position and estimating a third position of the machine using at least one of the first position and the second position.

First claim

What is claimed is:

1. A method of estimating position of a machine, comprising:
receiving, from a perception sensor, scene data describing an environment in a vicinity of the machine;
estimating, by a controller of the machine, a first position of the machine based on the received scene data and a map of the environment of the machine;
determining, by the controller of the machine, whether a global positioning system (GPS) signal indicative of a location of the machine is received by the machine;
estimating, by the controller of the machine, a second position of the machine using the GPS signal when it is determined that the GPS signal is received;
comparing, by the controller of the machine, the second position and the first position; and
estimating, by the controller of the machine, a third position of the machine using at least one of the first position and the second position,
wherein:
estimating the third position is performed based on a result of the comparison between the second position and the first position.

2. The method of claim 1 , wherein the scene data is generated by the perception sensor by scanning for physical objects in the vicinity of the machine.

3. The method of claim 1 , further comprising estimating a fourth position of the machine, wherein:
the fourth position is estimated in a propagation stage of a Kalman filter;
the third position is estimated in a measurement update stage of the Kalman filter; and
the third position is estimated based on the fourth position and at least one of the first position and the second position.

4. The method of claim 1 , wherein the third position is estimated using a combination of the first position and the second position when an uncertainty of the second position in comparison to an uncertainty of the first position is within a predetermined range.

5. The method of claim 1 , wherein the third position is estimated using one of the first position and the second position based on uncertainties associated with the first position and the second position.

6. The method of claim 1 , further comprising:
comparing the third position and the first position; and
declaring a fault with respect to the third position if the third position is not within a predetermined range of the first position.

7. The method of claim 1 , wherein estimating the first position includes:
estimating a current position of the machine on the map,
determining a plurality of particles based on the estimated current position on the map, each of the particles describing a scene of the environment of the machine as viewed from the estimated current position,
selecting one or more of the plurality of particles based on a comparison of the received scene data with the plurality of particles, and
estimating the first position of the machine based on the selected one or more particles.

8. A system for estimating position of a machine, comprising:
a perception sensor configured to generate scene data describing an environment in a vicinity of the machine;
a locating device configured to receive a global positioning system (GPS) signal indicative of a location of the machine; and
a controller in communication with the perception sensor and the locating device, the controller configured to:
estimate a first position of the machine based on the scene data and a map of the environment of the machine;
determine whether the GPS signal is received by the machine;
estimate a second position of the machine using the GPS signal when it is determined that the GPS signal is received;
compare the second position with the first position; and
estimate a third position of the machine using at least one of the first position and the second position,
wherein:
the controller is configured to estimate the third position based on a result of the comparison between the second position and the first position.

9. The system of claim 8 , wherein the perception sensor is configured to generate the scene data by scanning for physical objects in the vicinity of the machine.

10. The system of claim 8 , wherein the controller is further configured to estimate a fourth position of the machine, wherein:
the fourth position is estimated in a propagation stage of a Kalman filter;
the third position is estimated in a measurement update stage of the Kalman filter; and
the third position is estimated based on the fourth position and at least one of the first position and the second position.

11. The system of claim 8 , wherein the controller is configured to estimate the third position using a combination of the first position and the second position when an uncertainty of the second position in comparison to an uncertainty of the first position is within a predetermined range.

12. The system of claim 8 , wherein the controller is configured to estimate the third position using one of the first position and the second position based on uncertainties associated with the first position and the second position.

13. The system of claim 8 , wherein the controller is further configured to:
compare the third position and the first position; and
declare a fault with respect to the third position if the third position is not within a predetermined range of the first position.

14. The system of claim 8 , wherein the controller is configured to estimate the first position by:
estimating a current position of the machine on the map,
determining a plurality of particles based on the estimated current position on the map, each of the particles describing a scene of the environment of the machine as viewed from the estimated current position,
selecting one or more of the plurality of particles based on a comparison of the received scene data with the plurality of particles, and
estimating the first position of the machine based on the selected one or more particles.

15. A non-transitory computer-readable storage medium storing instructions for enabling a processor to execute a method of estimating position of a machine, the method comprising:
receiving, from a perception sensor, scene data describing an environment in a vicinity of the machine;
estimating, by a controller of the machine, a first position of the machine based on the scene data and a map of the environment of the machine;
determining, by the controller, whether a first signal indicative of a location of the machine is received by the machine;
estimating, by the controller, a second position of the machine using the first signal when it is determined that the first signal is received;
comparing, by the controller, the second position with the first position; and
estimating, by the controller, a third position of the machine using at least one of the first position and the second position,
wherein:
estimating the third position is performed based on a result of the comparison between the second position and the first position.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the scene data is generated by the perception sensor by scanning for physical objects in the vicinity of the machine.

17. The non-transitory computer-readable storage medium of claim 15 , wherein:
the method further comprises estimating a fourth position of the machine;
the fourth position is estimated in a propagation stage of a Kalman filter;
the third position is estimated in a measurement update stage of the Kalman filter; and
the third position is estimated based on the fourth position and at least one of the first position and the second position.

18

Assignees

• Caterpillar Inc

Inventors

• Friend Paul Russell
• Chen Qi
• Willis Frank Arthur

Classifications

• G01S17/89

  for mapping or imaging · CPC title

• G01B11/00

  Measuring arrangements characterised by the use of optical techniques · CPC title

• E02F9/264

  Sensors and their calibration for indicating the position of the work tool · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01C21/1656

  with passive imaging devices, e.g. cameras · CPC title