Using planar sensors for pallet detection

Patent metadata

Field	Value
Publication number	US-10007266-B2
Application number	US-201715629343-A
Country	US
Kind code	B2
Filing date	Jun 21, 2017
Priority date	Sep 19, 2016
Publication date	Jun 26, 2018
Grant date	Jun 26, 2018

Abstract

Example implementations may relate to a mobile robotic device that is operable to detect pallets using a distance sensor. According to these implementations, the robotic device causes the distance sensor to scan a horizontal coverage plane in an environment of the robotic device. Then, the robotic device receives from the distance sensor, sensor data indicative of the horizontal coverage plane. The robotic device compares the sensor data to a pallet identification signature. Based on the comparison, the robotic device detects a pallet located in the environment. Further, based on the sensor data, the robotic device determines a location and an orientation of the detected pallet.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
receiving first sensor data indicative of a horizontal coverage plane in an environment;
detecting a pallet located in the environment by identifying a first portion and a second portion of the first sensor data, wherein the first portion of the first sensor data is indicative of a first pallet support member of the pallet, wherein the second portion is indicative of a second pallet support member, wherein identifying the first portion and the second portion of the first sensor data comprises comparing the first sensor data to a pallet identification signature, and wherein the pallet identification signature is indicative of two pallet support members of a pallet type; and
based on the first sensor data, determining a location and an orientation of the pallet.

2. The computer-implemented method of claim 1 , wherein identifying the first portion of the first sensor data that is indicative of the first pallet support member comprises:
comparing the first sensor data to a pallet identification signature, wherein the pallet identification signature is indicative of a pallet support member of a pallet type.

3. The computer-implemented method of claim 1 , wherein the first sensor data comprises a plurality of points each indicative of a position of a respective surface in the environment.

4. The computer-implemented method of claim 1 , wherein the method further comprises:
identifying a first corner pattern indicative of a first corner of the first pallet support member, wherein the first corner pattern comprises a substantially 90 degree change in a slope of a first set of points within the first portion of the first sensor data;
identifying a first discontinuity and a second discontinuity in the first set of points, wherein the first discontinuity and the second discontinuity are indicative of a second corner and a third corner of the first pallet support member respectively; and
based on respective locations of the first, second, and third corners, determining a first and second dimension of the first pallet support member.

5. The computer-implemented method of claim 1 , wherein the method further comprises:
determining that a distance between the first pallet support member and the second pallet support member corresponds to a pallet pocket width; and
based on determining that the distance corresponds to the pallet pocket width, determining that the first pallet support member and the second pallet support member are support members of the detected pallet.

6. The method of claim 1 , further comprising:
determining the pallet type of the pallet based on the first sensor data, wherein the pallet type is indicative of: (i) a number of support members of the pallet type, (ii) dimensions of the pallet type, and (iii) a number and location of tine openings of the pallet type.

7. The method of claim 6 , further comprising:
based on the pallet type of the detected pallet, determining (i) a location and orientation of each support member of the detected pallet, and (ii) respective locations of each tine opening of the detected pallet.

8. The method of claim 7 , wherein determining the location and the orientation of the pallet is further based on the determined location and orientation of each support member of the detected pallet.

9. The method of claim 1 , further comprising:
operating a robotic device to insert a tine into a tine pocket of the detected pallet;
after inserting the tine, receiving second sensor data indicative of an area surrounding the tine;
analyzing the second sensor data to identify data indicative of a front corner of the detected pallet;
analyzing the second sensor data to identify data indicative of an inflection point, wherein the inflection point is indicative of a back corner of the pallet; and
based on a location of the front corner and a location of the back corner of the pallet, determining a positioning of the tine with respect to the detected pallet.

10. The method of claim 9 , the method further comprising:
based on the positioning of the tine with respect to the pallet, adjusting the robotic device to center the tine within the tine pocket.

11. A forklift robotic device comprising:
a control system operable to:
receive sensor data indicative of a horizontal coverage plane in an environment in which the forklift robotic device is deployed;
identify, in the sensor data, (i) first sensor data indicative of a first candidate corner of a first candidate pallet support member, (ii) second sensor data indicative of a second candidate corner of the first candidate pallet support member, and (iii) third sensor data indicative of a third candidate corner of the first candidate pallet support member;
based on a location of the first candidate corner, the second candidate corner, and the third candidate corner, determine (i) a width of the first candidate pallet support member, and (ii) a length of the first candidate pallet support member;
compare the length and width to dimensions of a pallet support member indicated in a pallet identification signature;
determine that the length and the width correspond to the dimensions of the pallet support member indicated by the pallet identification signature; and
based on determining that the length and the width correspond to the dimensions of the pallet support member indicated by the pallet identification signature, detect a pallet located in the environment.

12. The forklift robotic device of claim 11 , wherein the sensor data comprises a plurality of points each indicative of a position of a respective surface in the environment.

13. The forklift robotic device of claim 11 , further comprising:
a distance sensor configured to generate the sensor data.

14. The forklift robotic device of claim 13 , further comprising:
a camera, wherein the distance sensor and the camera are oriented in one of a horizontal coplanar orientation and a vertical coplanar orientation.

15. The forklift robotic device of claim 11 , further comprising:
a camera mounted on a backrest of the forklift robotic device, wherein the camera is orientated such that a coverage area of the camera covers at least front edge of a pallet when the pallet is carried by tines of the forklift robotic device.

16. The forklift robotic device of claim 15 , wherein the control system is further operable to:
monitor the coverage area of the camera in order to detect a movement of the pallet when the pallet is carried by tines of the forklift robotic device.

17. The forklift robotic device of claim 11 , further comprising:
one or more sensors, wherein an orientation of each of the one or more sensors is adjustable, wherein the one or more sensors are oriented in a first direction when the forklift robotic device is searching for the pallet, and wherein the one or more sensors are oriented in a second direction when the forklift robotic device is carrying the pallet.

18. A non-transitory computer readable medium having stored therein instructions executable by one or more processors to perform functions comprising:
receiving sensor data indicative of a horizontal coverage plane in an environment;
detecting a pallet located in the environment by identifying a first portion of the sensor data, wherein the first portion of the first sensor data is indicative of a first pallet support member of the pallet; and
based on the sensor data, determining a pallet type of the pallet, wherein the pallet type is indicative of: (i) a number of supp

Assignees

• X Dev Llc

Inventors

• Fischer Mark
• Zevenbergen John

Classifications

• G01S17/08

  for measuring distance only (indirect measurement G01S17/46; active triangulation systems G01S17/48) · CPC title

• Y10S901/01

  Mobile robot · CPC title

• G05D1/0231 Primary

  using optical position detecting means (position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16) · CPC title

• G05D2201/0216

  Physics · mapped topic

• B66F9/063

  Automatically guided · CPC title