Systems and methods for autonomously backing a vehicle to a dock

1 . A method of autonomously backing a vehicle to a target object, the method comprising:

determining, by an autonomous backing module of the vehicle, a target object;

determining, by the autonomous backing module, a distance to the target object, an angle of an axis of the target object, and an angle of an axis of the vehicle, wherein determining the angle of the axis of the target object and the distance to the target object includes:

detecting, within an image, by the autonomous backing module, a left edge of the target object and a right edge of the target object in an edge map generated from the image;

determining, by the autonomous backing module, a first distance from the vehicle to the left edge and a second distance from the vehicle to the right edge by cross-referencing locations in the edge map against information in a depth map, wherein cross-referencing locations in the edge map against information from the depth map includes identifying depth discontinuities in the depth map and verifying that locations of the depth discontinuities in the depth map correspond to locations of the left edge and the right edge detected on the edge map to confirm presence of one or more of the left edge or the right edge as detected from the edge map; and

determining, by the autonomous backing module, the angle of the axis of the target object and the angle of the axis of the vehicle based on the first distance and the second distance; and

determining, by the autonomous backing module, a path to the target object; and

transmitting, by the autonomous backing module, one or more commands to components of the vehicle to autonomously control the vehicle to back along the determined path to the target object.

2 . The method of claim 1 , wherein the target object is a loading dock, a loading bay, a dock leveler, a garage door, a wall area between two bumpers, a wall area between two painted lines, another vehicle, or an end of an alley.

3 . The method of claim 1 , wherein determining the target object includes:

presenting, by an operator interface device of the vehicle, an image captured by a first environment sensor mounted to a rear portion of the vehicle; and

receiving, by the operator interface device, an input from an operator indicating a location within the image that corresponds to a surface of the target object.

4 . The method of claim 1 , wherein detecting the left edge of the target object comprises finding an edge to the left of the location indicated by the operator, and wherein detecting the right edge of the target object comprises finding an edge to the right of the location indicated by the operator.

5 . The method of claim 1 , wherein determining the path to the target object includes:

determining a multi-order polynomial function,

wherein the function is defined in a Cartesian space having an origin at the center of a surface of the target object, and an X-axis parallel to an axis of the target object; and

wherein the function includes terms that represent:

an X-Y position of a rear axle of the vehicle, and

an X-Y position of a front axle of the vehicle.

6 . The method of claim 1 , wherein transmitting, by the autonomous backing module, one or more commands to components of the vehicle to autonomously control the vehicle to back along the determined path to the target object includes:

transmitting commands to one or more of a braking control module, a steering control module, and a torque request module.

7 . A vehicle configured to autonomously back to a target object, the vehicle comprising:

a braking control module for electronically controlling a brake system;

a steering control module for electronically controlling a steering system;

a torque request module for electronically causing the vehicle to produce a requested amount of torque; and

an electronic control module (ECM) configured to:

determine a target object;

determine a distance to the target object, an angle of an axis of the target object, and an angle of an axis of the vehicle, wherein the ECM is configured to:

detect, within an image, a left edge of the target object and a right edge of the target object in an edge map generated from the image;

determine a first distance from the vehicle to the left edge and a second distance from the vehicle to the right edge by cross-referencing locations in the edge map against information in a depth map, wherein cross-referencing locations in the edge map against information from the depth map includes identifying depth discontinuities in the depth map and verifying that locations of the depth discontinuities in the depth map correspond to locations of the left edge and the right edge detected on the edge map to confirm presence of one or more of the left edge or the right edge as detected from the edge map; and

determine the angle of the axis of the target object and the angle of the axis of the vehicle based on the first distance and the second distance; and

determine a path to the target object; and

transmit one or more commands to the braking control module, the steering control module, and the torque request module to autonomously control the vehicle to back along the determined path to the target object.

8 . The vehicle of claim 7 , wherein the target object is a loading dock, a loading bay, a dock leveler, a garage door, a wall area between two bumpers, a wall area between two painted lines, another vehicle, or an end of an alley.

9 . The vehicle of claim 7 , further comprising an operator interface device and a first environment sensor, wherein the first environment sensor is mounted to a rear portion of the vehicle, and wherein determining a target object includes:

presenting, by the operator interface device, an image captured by the first environment sensor; and

receiving, by the operator interface device, an input from an operator indicating a location within the image that corresponds to a surface of the target object.

10 . The vehicle of claim 7 , wherein detecting the left edge of the target object comprises finding an edge to the left of the location indicated by the operator, and wherein detecting the right edge of the target object comprises finding an edge to the right of the location indicated by the operator.

11 . The vehicle of claim 7 , wherein determining the path to the target object includes:

determining a multi-order polynomial function;

wherein the function is defined in a Cartesian space having an origin at the center of a surface of the target object, and an X-axis parallel to an axis of the target object; and

wherein the function includes terms that represent:

an X-Y position of a rear axle of the vehicle; and

an X-Y position of a front axle of the vehicle.

12 . A non-transitory computer-readable medium having computer-executable instructions stored thereon that, in response to execution by an electronic control unit (ECU) of a vehicle, cause the vehicle to perform actions for autonomously backing to a target object, the actions comprising:

determining, by the ECU, the target object;

determining, by the ECU, a distance to the target object, an angle of an axis of the target object, and an angle of an axis of the vehicle, wherein determining the angle and the distance to the target object includes:

detecting within an image, by the ECU, a left edge of the target object and a right edge of the target object in an edge map generated from the image;

determining, by the ECU, a first distance from the vehicle to the left edge and a second distance from the vehicle to the right edge by cross-referencing locations in the edge map against information in the depth map, wherein cross-referencing locations in the edge map against information from the depth map includes identifying depth discontinuities in the depth map and verifying that locations of the depth discontinuities in the depth map correspond to locations of the left edge and the right edge detected on the edge map to confirm presence of one or more of the left edge or the right edge as detected from the edge map; and

determining, by the ECU, the angle of the axis of the target object and the angle of the axis of the vehicle based on the first distance and the second distance;

determining, by the ECU, a path to the target object; and

transmitting, by the ECU, one or more commands to components of the vehicle to autonomously control the vehicle to back along the determined path to the target object.

13 . The computer-readable medium of claim 12 , wherein the target object is a loading dock, a loading bay, a dock leveler, a garage door, a wall area between two bumpers, a wall area between two painted lines, another vehicle, or an end of an alley.

14 . The computer-readable medium of claim 12 , wherein determining the target object includes:

presenting, by an operator interface device of the vehicle, an image captured by a first environment sensor mounted to a rear portion of the vehicle; and

receiving, by the operator interface device, an input from an operator indicating a location within the image that corresponds to a surface of the target object.

15 . The computer-readable medium of claim 12 , wherein detecting the left edge of the target object comprises finding an edge to the left of the location indicated by the operator, and wherein detecting the right edge of the target object comprises finding an edge to the right of the location indicated by the operator.

16 . The computer-readable medium of claim 12 , wherein determining the path to the target object includes:

determining a multi-order polynomial function;

wherein the function is defined in a Cartesian space having an origin at the center of a surface of the target object, and an X-axis parallel to an axis of the target object; and

wherein the function includes terms that represent:

an X-Y position of a rear axle of the vehicle; and

an X-Y position of a front axle of the vehicle.

17 . The computer-readable medium of claim 12 , wherein transmitting one or more commands to components of the vehicle to autonomously control the vehicle to back along the determined path to the target object includes:

transmitting commands to one or more of a braking control module, a steering control module, and a torque request module.