AUTONOMOUS WORK VEHICLE OBSTACLE DETECTION SYSTEM

• US 20170357267A1
• Filed: 06/10/2016
• Published: 12/14/2017
• Est. Priority Date: 06/10/2016
• Status: Abandoned Application

• Current Assignee: Autonomous Solutions, Inc., CNH Industrial America LLC (CNH Industrial N.V.)
• Original Assignee: Autonomous Solutions, Inc., CNH Industrial America LLC (CNH Industrial N.V.)
• Inventors: Foster, Christopher Alan, Debide, Bonoit, Baillio, Brad Abram, Bybee, Taylor Chad
• Application Number:
  US15/178,805
• Publication Number:
  US 20170357267A1
• Time in Patent Office: Days
• CPC Class Codes: A01B 69/008 automatic
• CPC Class Codes: A01B 79/005 Precision agriculture
• CPC Class Codes: G01C 21/005 with correlation of navigation data from several sources, e.g. map or contour matching G01C21/30 takes precedence
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0219 ensuring the processing of the whole working surface
• 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

Abstract

A work vehicle includes at least one sensor configured to detect at least one property of a work area. The work vehicle includes a controller comprising a processor operatively coupled to a memory, wherein the controller is configured to receive a first signal from an at least one sensor indicative of the at least one property of the work area, to determine whether an obstacle occupies one or more locations of the work area by creating or updating a map having one or more cells that correspond to the one or more locations of the work area, wherein each of the one or more cells indicate whether the obstacle occupies the respective locations of the work area based on the at least one property, and to send a second signal based on the map.

Claims

1. A work vehicle, comprising:

at least one sensor configured to detect at least one property of a work area; and

a controller comprising a processor operatively coupled to a memory, wherein the controller is configured to receive a first signal from at least one sensor indicative of the at least one property of the work area, to determine whether an obstacle occupies one or more locations on a two dimensional (2D) surface of the work area by creating or updating a map having a plurality of cells that cover the 2D surface of the work area, one or more cells of the plurality of cells correspond to the locations on the 2D surface of the work area, wherein each cell of the plurality of cells indicates whether the obstacle occupies the cell based on the at least one property, and to output a second signal based on the map.

2. The vehicle of claim 1, wherein the controller is configured to output a third signal indicative of instructions to control the vehicle based on the map.

3. The vehicle of claim 1, wherein the controller is configured to output a fourth signal to a user interface to alert an operator of the obstacle.

4. The vehicle of claim 1, wherein the controller is configured to determine a probability of the obstacle occupying the one or more locations by using Bayes'"'"' Theorem in which the probability is based on the true positive and true negative rates, prior grid cell probability of an obstacle occupying the one or more locations, and lidar and radar sensor data.

5. The vehicle of claim 1, wherein the controller is configured to determine whether the obstacle occupies the one or more locations by comparing a probability of the obstacle occupying the one or more locations to a threshold probability.

6. The vehicle of claim 1, wherein the at least one sensor comprises a lidar sensor configured to output the first signal indicative of a distance and a direction of the obstacle based on light reflecting from the obstacle.

7. The vehicle of claim 6, wherein the controller is configured to create or update a point cloud of each distance and direction from the light reflecting from the obstacle to be used in creating or updating the map.

8. A work vehicle, comprising:

a lidar sensor; and

a controller comprising a processor and a memory, wherein the controller is configured to receive a first signal from the lidar sensor indicating distances and directions to an obstacle in a work area, to create or update a point cloud having a set of points based on the distance and directions, to create or update a map of a plurality of cells that cover a two dimensional (2D) surface of the work area, one or more cells of the plurality of cells correspond to one or more locations on the 2D surface of the work area, wherein each cell of the plurality of cells indicate whether the obstacle occupies the cell based on the points of the point cloud, to output a second signal indicative of the map to a control system of the vehicle.

9. The vehicle of claim 8, wherein the lidar sensor and radar sensor are mounted to a front of the vehicle.

10. The vehicle of claim 8, wherein the lidar sensor is positioned in a downward direction toward the work area to provide a greater resolution of scanning patterns detected by the lidar detector by utilizing a larger percentage of the field of view of the lidar sensor as compared to a lidar sensor positioned level to the work area.

11. The vehicle of claim 10, wherein the lidar sensor is positioned at an angle positioned aiming downward in the range of zero to fifteen degrees below level.

12. The vehicle of claim 8, comprising a radar sensor, wherein the controller is configured to determine the map by weighing probabilities of presence of the object based on radar sensor data and lidar sensor data according to the radar sensor accuracy and the lidar sensor accuracy.

13. The vehicle of claim 8, wherein the controller is configured to create or update the map based at least in part on a prior probability of presence of the obstacle in each cell.

14. A control system for a work vehicle, comprising:

a controller comprising a processor and a memory, wherein the memory is operatively coupled to the processor, wherein the processor is configured to receive a first signal from a first sensor indicating distances and directions to an obstacle in an agricultural field, to create or update a map of a plurality of cells that cover a two dimensional (2D) surface of the agricultural field, each cell of the plurality of cells corresponding to one or more locations on the 2D surface of the agricultural field, wherein each cell of the plurality of cells indicate whether the obstacle occupies the respective locations of the agricultural field, and to output a second signal indicative of instructions to control the vehicle based on the map.

15. The control system of claim 14, wherein the controller is configured to send the second signal indicative of instructions to control the vehicle based on the map.

16. The control system of claim 14, wherein the controller is configured to stop the vehicle to await further instructions from an operator.

17. The control system of claim 14, wherein the controller is configured to create or update a point cloud of points based on the distances and directions of light reflecting on the obstacle to be used in creating or updating the map.

18. The control system of claim 14, wherein the controller is configured to create or update the map based at least in part on a prior probability of presence of the obstacle in each cell.

19. The control system of claim 14, wherein the controller is configured to determine a probability of the obstacle occupying the one or more locations by using Bayes'"'"' Theorem in which the probability is based on the true positive and true negative rates, prior grid cell probability of an obstacle occupying the one or more locations, and the Lidar and Radar sensor data.

20. The control system of claim 14, wherein the controller is configured to determine whether the obstacle occupies the one or more locations by comparing a probability of the obstacle occupying the one or more locations to a threshold probability.