Systems and methods for vehicle motion planning
This document discloses system, method, and computer program product embodiments for operating a robot. For example, the method includes: detecting an object in proximity to the robot; generating a path of travel for the object that is defined by a plurality of first data points representing different object locations in an area; generating cost curves respectively associated with the plurality of first data points; generating a polyline comprising a plurality of second data points associated with displacements of the cost curves from a particular location in the area; defining a predicted path of travel for the object based on the polyline; and using the predicted path of travel for the object to facilitate at least one autonomous operation of the robot.
1. A method for operating a robot, comprising:
detecting, by a computing device, an object in proximity to the robot;
generating, by the computing device, a path of travel for the object that is defined by a plurality of first data points representing different object locations in an area;
generating, by the computing device, cost curves respectively associated with the plurality of first data points;
generating, by the computing device, a polyline comprising a plurality of second data points associated with displacements of the cost curves from a particular location along a given cross line in the area;
defining, by the computing device, a predicted path of travel for the object based on the polyline; and
using, by the computing device, the predicted path of travel for the object to facilitate at least one autonomous operation of the robot.
2. The method according to claim 1 , further comprising selecting a total number of data points that are to define the path of travel based on a geometry of the area in which the object resides.
3. The method according to claim 2 , wherein the total number of data points has a first value when the area comprises a straight lane and a second different value when the area comprises a curved lane.
4. The method according to claim 1 , wherein each cost curve represents a displacement cost to be at a particular location along the given cross line that (i) passes through a respective data point of said plurality of first data points and (ii) extends perpendicular to and between boundary lines of the area.
5. The method according to claim 1 , wherein each of the plurality of first data points is longitudinally offset from a current location of the object in the area.
6. The method according to claim 1 , wherein the cost curves are generated using a cost function representing a distance from the object to a left boundary of the area, a cost function representing a distance from the object to a right boundary of the area, a cost function representing how close the object should follow a center line of the area, a cost function representing location consistencies to the left and right boundaries of the area, or a cost function representing locations that are close to static obstacles.
7. The method according to claim 1 , wherein the path of travel for the object is generated when the object is considered by the computing device as having a driving intention.
8. The method according to claim 1 , wherein the predicted path of travel for the object follows the polyline.
9. The method according to claim 1 , further comprising generating a forecasted path of travel for the object using the predicted path of travel.
10. The method according to claim 9 , wherein the forecasted path of travel for the object is used in addition to or as an alternative to the predicted path of travel to facilitate at 1 east one autonomous operation of the robot.
11. A system, comprising:
a processor;
a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for operating a robot, wherein the programming instructions comprise instructions to:
detect an object in proximity to the robot;
generate a path of travel for the object that is defined by a plurality of first data points representing different object locations in an area;
generate cost curves respectively associated with the plurality of first data points;
generate a polyline comprising a plurality of second data points associated with displacements of the cost curves from a particular location along a given cross line in the area;
define a predicted path of travel for the object based on the polyline; and
use the predicted path of travel for the object to facilitate at least one autonomous operation of the robot.
12. The system according to claim 11 , wherein the programming instructions comprise instructions to select a total number of data points that are to define the path of travel based on a geometry of the area in which the object resides.
13. The system according to claim 12 , wherein the total number of data points has a first value when the area comprises a straight lane and a second different value when the area comprises a curved lane.
14. The system according to claim 11 , wherein each cost curve represents a displacement cost to be at a particular location along the given cross line that (i) passes through a respective data point of said plurality of first data points and (ii) extends perpendicular to and between boundary lines of the area.
15. The system according to claim 11 , wherein each of the plurality of first data points is longitudinally offset from a current location of the object in the area.
16. The system according to claim 11 , wherein the cost curves are generated using a cost function representing a distance from the object to a left boundary of the area, a cost function representing a distance from the object to a right boundary of the area, a cost function representing how close the object should follow a center line of the area, a cost function representing location consistencies to the left and right boundaries of the area, or a cost function representing locations that are close to static obstacles.
17. The system according to claim 11 , wherein the path of travel for the object is generated when the object is considered as having a driving intention.
18. The system according to claim 11 , wherein the predicted path of travel for the object follows the polyline.
19. The system according to claim 11 , wherein the programming instructions comprise instructions to generate a forecasted path of travel for the object using the predicted path of travel and the forecasted path of travel for the object is used in addition to or as an alternative to the predicted path of travel to facilitate at least one autonomous operation of the robot.
20. A non-transitory computer-readable medium that stores instructions that, when executed by at least one computing device, will cause the at least one computing device to perform operations comprising:
detecting an object in proximity to a robot;
generating a path of travel for the object that is defined by a plurality of first data points representing different object locations in an area;
generating cost curves respectively associated with the plurality of first data points;
generating a polyline comprising a plurality of second data points associated with displacements of the cost curves from a particular location along a given cross line in the area, the given cross line (i) passes through a respective data point of said plurality of first data points and (ii) extends perpendicular to and between boundary lines of the area;
defining a predicted path of travel for the object based on the polyline; and
using the predicted path of travel for the object to facilitate at least one autonomous operation of the robot.