Map localizing with partially obstructed ranging devices for autonomous robots and vehicles

• US 9,943,959 B2
• Filed: 04/25/2016
• Issued: 04/17/2018
• Est. Priority Date: 04/25/2016
• Status: Active Grant

• Current Assignee: Disney Enterprises Incorporated (The Walt Disney Company)
• Original Assignee: Disney Enterprises Incorporated (The Walt Disney Company)
• Inventors: Freeman, Kyle G.
• Primary Examiner(s): Jen, Ian
• Application Number:
  US15/137,735
• Publication Number:
  US 20170305013A1
• Time in Patent Office: 722 Days
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/47 Optical

Abstract

A method for localizing robots and other objects when ranging devices are partially obstructed. The method includes retrieving a digital map of the space and then identifying potential locations for the object in the space. The method involves generating a prediction of expected ranges between the object and surfaces in the space at each of the potential locations. The method includes operating a ranging device to measure ranges to the surfaces in the space and comparing, for each of the predictions, the measured ranges with the expected ranges to identify the most accurate prediction. The comparing includes weighting ranges that are too small neutrally as these are strikes on obstructions, weighting ranges that provide matches positively, and weighting ranges that are too large negatively, and the comparing then involves summing the weighted ranges to identify a most accurate one of the predictions and associated current location for the object.

Claims

1. A method of localizing an autonomous object in a space, comprising:

retrieving from data storage a digital map of the space;

with a localizing module run by a controller, identifying a plurality of potential locations for the autonomous object in the space;

with the localizing module based on the digital map, generating a prediction of expected ranges between the autonomous object when at each of the potential locations and surfaces in the space, wherein the generating of the predictions includes generating a ray casting prediction from the autonomous object to the surfaces in the space;

operating a ranging device to measure ranges between the autonomous object and the surfaces in the space; and

comparing, for each of the predictions, the measured ranges with the expected ranges to identify one of the predictions as an accurate prediction,

wherein the comparing includes weighting each of the measured ranges based on results of the comparing.

2. The method of claim 1, further comprising generating localizing data including a current position of the autonomous object in the space from the one of the predictions identified as the accurate prediction.

3. The method of claim 1, wherein the weighting includes treating neutrally the measured ranges that are smaller than the corresponding ones of the expected ranges, whereby strikes from the ranging devices with obstructions in the space are identified for the comparing.

4. The method of claim 1, wherein the comparing includes summing the weighted measured ranges and wherein the weighting includes positively weighting the measured ranges when the expected range matches the corresponding one of the measured ranges.

5. The method of claim 4, wherein the weighting further includes negatively weighting the measured ranges when the corresponding one of the measured ranges is greater than the expected range.

6. The method of claim 5, wherein the negative weighting is greater than the positive weighting.

7. The method of claim 1, wherein the expected ranges and the measured ranges are provided using polar coordinates.

8. A localizing method, comprising:

determining a plurality of potential locations of an autonomous object;

from each of the potential locations, generating a ray casting prediction defining predicted ranges from the autonomous object to surfaces in a space based on a digital map of the space;

measuring ranges to the surfaces in the space;

identifying the measured ranges corresponding with obstructions in the space;

for each of the ray casting predictions, summing all of the measured ranges except the measured ranges identified as corresponding with the obstructions;

selecting one of the ray casting predictions as most accurate based on the summing; and

determining localizing data for the autonomous object in the space using the selected one of the ray casting predictions.

9. The method of claim 8, further including, prior to the summing, positively weighting the measured ranges matching corresponding ones of the predicted ranges and negatively weighting the measured ranges that are greater than corresponding ones of the predicted ranges.

10. The method of claim 9, wherein the measured ranges that are greater than corresponding ones of the predicted ranges are weighted more heavily negative than the measured ranges that match the corresponding ones of the predicted ranges are weighted in a positive manner.

11. The method of claim 8, wherein the measuring of the ranges is performed 360 degrees about the autonomous object by at least two LIDAR devices.

12. The method of claim 10, wherein the ray casting predictions are performed from locations of the LIDAR devices on the autonomous object.

13. The method of claim 8, further comprising determining a seed location for the autonomous object and wherein the determining of the potential locations is performed using the seed location and wherein the digital map includes the seed location.

14. An autonomous object configured for accurate localizing, comprising:

a controller;

a localizing module run by the controller, wherein the localizing module determines a plurality of potential locations for the autonomous object in a space and wherein the localizing module generates a prediction of expected ranges between the object and surfaces in the space for each of the potential locations; and

a ranging assembly collecting ranging data about the autonomous object,

wherein the localizing module compares, for each of the predictions, the ranging data with the expected ranges to identify one of the predictions as an accurate prediction, and

wherein the comparing by the localizing module includes weighting measured ranges in the ranging data based on a comparison with a corresponding one of the expected ranges.

15. The object of claim 14, wherein the weighting includes treating neutrally the measured ranges that are smaller than the corresponding ones of the measured ranges, whereby strikes from the ranging devices with obstructions in the space are identified for the comparing.

16. The object of claim 14, wherein the comparing includes summing the weighted measured ranges and wherein the weighting includes positively weighting the measured ranges when the expected range matches the corresponding one of the measured ranges.

17. The object of claim 16, wherein the weighting further includes negatively weighting the measured ranges when the corresponding one of the measured ranges is greater than the expected range.

18. The object of claim 16, wherein the autonomous object comprises a robot or a vehicle and wherein the ranging assembly includes at least one LIDAR device.