Control system and method for brake bleeding

• US 9,902,071 B2
• Filed: 03/02/2016
• Issued: 02/27/2018
• Est. Priority Date: 12/18/2015
• Status: Active Grant

• Current Assignee: GE Global Sourcing LLC (Westinghouse Air Brake Technologies Corporation)
• Original Assignee: General Electric Company
• Inventors: Tan, Huan, Lizzi, John Michael, Forman, Douglas, Theurer, Charles Burton, Al Assad, Omar, Patrick, Romano, Kannan, Balajee, Gefen, Yonatan
• Primary Examiner(s): Oh, Harry Y
• Application Number:
  US15/058,423
• Publication Number:
  US 20170173795A1
• Time in Patent Office: 727 Days
• Field of Search: 700245
• CPC Class Codes: B25J 11/00 Manipulators not otherwise provided for
• CPC Class Codes: B25J 13/003 by means of an audio-responsive input audible safety signals B25J19/061
• CPC Class Codes: B25J 13/085 Force or torque sensors B25J13/082, B25J13/084 take precedence
• CPC Class Codes: B25J 19/021 Optical sensing devices
• CPC Class Codes: B25J 19/023 including video camera means
• CPC Class Codes: B25J 9/1612 characterised by the hand, wrist, grip control
• CPC Class Codes: B25J 9/162 Mobile manipulator, movable base with manipulator arm mounted on it
• CPC Class Codes: B25J 9/1661 characterised by task planning, object-oriented languages
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: B25J 9/1679 characterised by the tasks executed
• CPC Class Codes: B25J 9/1694 characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: B60T 15/048 Controlling pressure brakes of railway vehicles
• CPC Class Codes: B60T 15/54 for controlling exhaust from triple valve or from brake cylinder
• CPC Class Codes: B60T 7/16 operated by remote control, i.e. initiating means not mounted on vehicle
• CPC Class Codes: G05B 2219/40039 Robot mounted or sliding inside vehicle, on assembly line or for test, service
• CPC Class Codes: G05B 2219/40586 6-DOF force sensor
• CPC Class Codes: G05B 2219/40613 Camera, laser scanner on end effector, hand eye manipulator, local
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: H04N 23/54 : Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils
• CPC Class Codes: H04N 7/181 : for receiving images from a plurality of remote sources
• CPC Class Codes: Y10S 901/01 : Mobile robot

Abstract

A system is provided that includes a machine assembly, a first imaging sensor, an encoder, and one or more processors. The machine assembly is movable to actuate a brake lever of a vehicle in order to open a valve of an air brake system. The first imaging sensor is positioned to acquire two-dimensional perception information of a working environment that includes the brake lever during movement of the machine assembly towards the brake lever. The encoder detects a displacement of the machine assembly relative to a reference position of the machine assembly. The one or more processors estimate a target position of the brake lever relative to the machine assembly during movement of the machine assembly based on the two-dimensional perception information and the displacement. The one or more processors drive the movement of the machine assembly towards the target position of the brake lever.

Claims

1. A system comprising:

a machine assembly that is movable to actuate a brake lever of a vehicle in order to open a valve of an air brake system of the vehicle;

a first imaging sensor positioned to acquire two-dimensional perception information of a working environment that includes the brake lever, the first imaging sensor configured to acquire the two-dimensional perception information during movement of the machine assembly towards the brake lever;

an encoder detecting a displacement of the machine assembly relative to a reference position of a robotic arm of the machine assembly, the displacement including at least one of position information or motion information of the machine assembly during movement of the machine assembly towards the brake lever; and

one or more processors configured to estimate a target position of the brake lever relative to the machine assembly as the machine assembly moves toward the brake lever based on the two-dimensional perception information and the displacement of the machine assembly, the one or more processors further configured to drive the movement of the machine assembly towards the target position of the brake lever,

wherein the machine assembly includes a moveable arm and the first imaging sensor is mounted on the movable arm, the system further comprising a second imaging sensor that is configured to acquire three-dimensional perception information of the working environment, the three-dimensional perception information acquired by the second imaging sensor being more precise than the two-dimensional perception information acquired by the first imaging sensor, the three-dimensional perception information being acquired at an acquisition rate that is slower than an acquisition rate of the two-dimensional perception information.

2. The system of claim 1, wherein the machine assembly includes a moveable arm that has an end-effector disposed at a distal end of the movable arm, the end-effector grasping the brake lever to actuate the brake lever, the first imaging sensor being mounted on the movable arm at least one of on or proximate to the end-effector.

3. The system of claim 1, wherein the machine assembly includes a moveable arm and the first imaging sensor is mounted on the movable arm, the one or more processors are configured to estimate the target position of the brake lever relative to the machine assembly as the movable arm of the machine assembly moves by using optical flow-based analysis on a sequence of two-dimensional images of the brake lever acquired by the first imaging sensor from different positions of the first imaging sensor relative to the brake lever.

4. The system of claim 1, wherein the one or more processors are configured to estimate the target position of the brake lever during movement of the movable arm based on the three-dimensional perception information in response to receipt of updated three-dimensional perception information, and the one or more processors are configured to estimate the target position of the brake lever during movement of the movable arm based on the two-dimensional perception information and the displacement of the movable arm in response to a lack of receipt of updated three-dimensional perception information.

5. The system of claim 1, wherein the first and second imaging sensors are both mounted on the movable arm.

6. The system of claim 1, wherein the first imaging sensor is a mono camera and the second imaging sensor is a laser scanner.

7. The system of claim 1, wherein the one or more processors are further configured to generate a motion trajectory for the machine assembly that provides a path from the machine assembly to the position of the brake lever, the motion trajectory configured to avoid obstacles located between the machine assembly and the brake lever.

8. The system of claim 7, wherein the one or more processors generate the motion trajectory as a series of via-points between the machine assembly and the brake lever, the motion trajectory including dynamics values for position, velocity, and acceleration of the machine assembly associated with each via-point, the one or more processors configured to drive the machine assembly through the via-points with the dynamics values at each corresponding via-point.

9. The system of claim 1, further comprising a force sensor operably coupled to the machine assembly, the force sensor configured to detect one or more forces generated by the machine assembly as the machine assembly actuates the brake lever.

10. The system of claim 1, wherein the machine assembly includes a movable arm having multiple joints, the one or more processors being configured to generate designated torques for corresponding joints of the arm, the one or more processors driving the arm of the machine assembly according to the designated torques.

11. A method comprising:

acquiring perception information of a brake lever of a vehicle to detect a target position of the brake lever relative to a robotic arm of a machine assembly, the brake lever being actuatable to open a valve of an air brake system of the vehicle, the perception information being acquired by a first imaging sensor mounted on the robotic arm;

driving the robotic arm towards the target position of the brake lever to actuate the brake lever for opening the valve of the air brake system

detecting a displacement of the robotic arm as the robotic arm moves towards the target position, the displacement information including at least one of position information or motion information of the robotic arm; and

estimating, using one or more processors, an updated target position of the brake lever based at least in part on the perception information acquired during the movement of the robotic arm and the displacement information of the robotic arm,

wherein the perception information is two-dimensional perception information acquired by the first imaging sensor and the method further includes acquiring three-dimensional perception information of the brake lever from a second imaging sensor, the three-dimensional perception information being more precise than the two-dimensional perception information, the three-dimensional perception information being acquired at a slower acquisition rate than the two-dimensional perception information.

12. The method of claim 11, wherein the first imaging sensor is a mono camera and the perception information is two-dimensional images of the brake lever, the updated target position being estimated by analyzing a sequence of the two-dimensional images of the brake lever acquired by the mono camera at different positions of the mono camera relative to the brake lever as the robotic arm moves towards the target position.

13. The method of claim 11, wherein a first updated target position is estimated based on the three-dimensional perception information acquired by the second imaging sensor responsive to receipt of updated three-dimensional perception information, and a subsequent second updated target position is estimated based on both the two-dimensional perception information acquired by the first imaging sensor and the displacement of the movable arm responsive to a lack of receipt of updated three-dimensional perception information.

14. The method of claim 11, further comprising mounting the first and second imaging sensors on the robotic arm of the machine assembly.

15. The method of claim 11, wherein the first imaging sensor is a mono camera and the second imaging sensor is a laser scanner.

16. The method of claim 11, further comprising revising, using the one or more processors, a motion trajectory for the robotic arm based on the updated target position of the brake lever that is estimated during movement of the robotic arm, the motion trajectory including a series of via-points that form a path for the robotic arm to move along towards the brake lever while avoiding identified obstacles.

17. The method of claim 16, further comprising generating, using the one or more processors, designated torques for the robotic arm at corresponding via-points based on the motion trajectory, the designated torques being used to drive the robotic arm towards the target position of the brake lever to actuate the brake lever.

18. The method of claim 17, further comprising receiving force generation information from a force sensor as the robotic arm moves towards the brake lever, and revising the designated torques based on the force generation information that is received.