System and method of control for autonomous or remote-controlled vehicle platform

Patent metadata

Field	Value
Publication number	US-11420652-B2
Application number	US-202016917862-A
Country	US
Kind code	B2
Filing date	Jun 30, 2020
Priority date	Aug 30, 2019
Publication date	Aug 23, 2022
Grant date	Aug 23, 2022

Abstract

A system and method for controlling a vehicle platform, the system comprising on onboard controller and an off-board controller that work together to provide autonomous navigation in fields or similar areas where the vehicle is deployed, perception for obstacle detection and avoidance, and a user interface for user/vehicle interaction and control.

First claim

What is claimed is:

1. A system for controlling a vehicle operating autonomously in an agricultural field and having at least one sensor capable of providing data related to an environment of the vehicle, the system comprising:
an onboard controller connected to a data port on the vehicle for receiving the data and developing a navigation plan, the onboard controller comprising:
an interface control module that provides instructions to low-level controllers to execute the navigation plan,
a pose estimation module that estimates a pose of the vehicle with respect to a global frame,
a perception module that identifies obstacles within a vicinity of the vehicle,
a path navigation module that tracks the vehicle and sends navigation updates to the interface control module, and
an obstacle avoidance module that plans a path to avoid the obstacles identified by the perception module;

an off-board controller that sends mission data and a set of way-points to the onboard controller,
wherein the onboard controller develops the navigation plan based on at least one of the mission data and the set of way-points, and
wherein the set of way-points define a path to cover an area of the agricultural field identified in the mission data.

2. The system of claim 1 , wherein the off-board controller comprises:
a mission configuration module that receives mission details from a user to generate a mission output;
a static machine module that receives the mission output and generates the set of way-points used by the onboard controller to develop the navigation plan.

3. The system of claim 2 , wherein the off-board controller further comprises:
a machine state module that receives state data from the vehicle and displays the state data on a user interface.

4. The system of claim 2 , wherein the mission details are selected from a group consisting of application area, application rate, navigation speed, vehicle width, vehicle turning threshold, and refueling threshold.

5. The system of claim 2 , wherein the way-points comprise tender and normal way-points.

6. The system of claim 1 , wherein the off-board controller further comprises:
an override controls module that sends override data to the onboard controller, wherein the override data interrupts autonomous operation of the vehicle.

7. The system of claim 6 , wherein the override data comprises a message related to the mission data.

8. The system of claim 6 , wherein the override data comprise a message when received by the onboard controller causes the vehicle to stop.

9. The system of claim 1 , wherein the onboard controller further comprises:
a remote operation module that receives data from the at least one sensor and transmits the data to the off-board controller for display on a user interface.

10. The system of claim 1 , wherein the low-level controllers are selected from a group consisting of a steering controller, a braking controller, and a propulsion controller.

11. The system of claim 1 , wherein the pose estimation module estimates the pose of the vehicle by using an extended Kalman filter that assumes a uniform velocity model.

12. The system of claim 11 , wherein the pose is updated using data from the at least one sensor.

13. The system of claim 1 , wherein the perception module creates a map in a global coordinate frame using data from the at least one sensor.

14. The system of claim 1 , wherein the perception module identifies objects in the environment without reliance on image features.

15. The system of claim 1 , wherein the off-board controller is connected to the data port via a wireless link.

16. The system of claim 1 , wherein the at least one sensor is selected from a group consisting of: an imaging system, a stereo camera, a radar system, a lidar system, a location-determining receiver, a satellite navigation receiver, a dead-reckoning sensor, an odometer, a gyroscope, an accelerometer, an inertial measurement unit, and a tilt, roll, and yaw sensor.

17. The system of claim 1 , wherein the data comprises at least one of position data, motion data, and attitude data.

18. A method of controlling an autonomous vehicle operating in an agricultural field and having an onboard controller comprising:
generating mission data and a set of way-points using an off-board controller,
wherein the mission data comprises an initial map of a region to be traversed by the autonomous vehicle, and
wherein the set of way-points define a path to cover the region;

receiving the mission data and set of way-points at an onboard controller;
developing a path plan using at least one of the mission data and set of way-points;
determining a pose of the vehicle;
navigating the path plan by tracking the set of way-points; and
detecting objects within the path plan using a sensor, wherein the sensor provides information about an environment surrounding the autonomous vehicle.

19. The method of claim 18 , where detecting objects comprises:
computing depth information from a stereo camera and a lidar point cloud having a plurality of points, wherein the points are projected into a local reference frame;
accumulating the plurality of points over a period of time in a global coordinate frame identified in the pose;
clustering voxels from the global coordinate frame voxel clusters; and
determining an objectness-score based on the voxel clusters.

20. The method of claim 19 , further comprising:
identifying an object using the objectness-score.

Assignees

• Deere & Co
• Univ Carnegie Mellon

Inventors

• Connell Richard
• Miller Michael M
• LAWSON Joshua
• Saxena Suryansh
• Levine Matthew
• Kini Prathamesh
• Bouterige Raphael
• Glisson Matthew
• Russell Raymond
• Ketterer James
• Herman Herman

Classifications

• A01B69/001

  Steering by means of optical assistance, e.g. television cameras (steering devices for road marking vehicles E01C23/163) · CPC title

• H04W4/029 Primary

  Location-based management or tracking services · CPC title

• A01B69/008

  automatic · CPC title

• A01M7/0085

  Tanks · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title