System and method for tracking objects
View Patent ↗Embodiments of a system and method for tracking objects are described herein. Aspects of this disclosure efficiently update object “belief” data by creating a bitmap representation of object locations and velocities. The bitmap provides a three-dimensional representation of the object as viewed by one or more sensors. The bitmap representations are blended with sensor data over time to determine a current object belief state which can accurately account for asynchronous sensor data. Peaks in the belief data, which may be represented by pixels with an intensity value above a threshold value, are identified as likely objects. Additional sensor data is used to detect longitudinal velocities located at one or more of the peaks.
1. A computer-implemented method for tracking objects, the method comprising:
obtaining a set of input from one or more sensors, the sensors being configured to perceive an environment;
determining, using one or more processors, a three-dimensional bitmap associated with an environmental state based on the set of input, the three-dimensional bitmap comprising a plurality of pixels; and
identifying, using the one or more processors, a position for an object using the three-dimensional bitmap, wherein an intensity of each pixel at a particular coordinate of the bitmap represents a likelihood that the object is at a location within the environment corresponding to the particular coordinate of the three-dimensional bitmap; and
controlling a vehicle using an automated driving system based on the position in order to avoid the object.
2. The method of claim 1 , wherein the three dimensions of the three-dimensional bitmap correspond to a first environmental position along an x axis, a second environmental position along a y axis, and a lateral velocity.
3. The method of claim 2 , further comprising modifying the set of input obtained from the one or more sensors from a four-dimensional representation to a three-dimensional representation by eliminating a longitudinal velocity from the obtained input.
4. The method of claim 3 , further comprising:
identifying a peak of intensity within the three-dimensional bitmap; and
determining a longitudinal velocity of a given object located at the intensity peak.
5. The method of claim 2 , wherein the longitudinal velocity is identified using a radar sensor.
6. The method of claim 1 , further comprising providing the identified position of the object to an autonomous vehicle.
7. The method of claim 1 , wherein the one or more sensors comprise at least one of a camera, a laser scanner, and a radar detector.
8. The method of claim 1 , further comprising:
obtaining a second set of input from the one or more sensors; and
generating a new environmental state by painting the obtained sets of input into a second three-dimensional bitmap, the second three-dimensional bitmap representing an updated environmental state incorporating the second set of input.
9. A tangible, non-transitory, computer-readable storage medium comprising instructions that, when executed by one or more processors, perform a method for tracking objects, the method comprising:
obtaining a set of input from one or more sensors, the sensors being configured to perceive an environment;
determining a three-dimensional bitmap associated with an environmental state based on the set of input, the three-dimensional bitmap comprising a plurality of pixels;
identifying a position for an object using the three-dimensional bitmap, wherein an intensity of each pixel at a particular coordinate of the bitmap represents a likelihood that the object is at a location within the environment corresponding to the particular coordinate of the three-dimensional bitmap; and
controlling a vehicle using an automated driving system based on the position in order to avoid the object.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the three dimensions of the three-dimensional bitmap correspond to a first environmental position along an x axis, a second environmental position along a y axis, and a lateral velocity.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the method further comprising modifying the set of input obtained from the one or more sensors from a four-dimensional representation to a three-dimensional representation by eliminating a longitudinal velocity from the obtained input.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the method further comprising:
identifying a peak of intensity within the three-dimensional bitmap; and
determining a longitudinal velocity of a given object located at the intensity peak.
13. A processing system for tracking objects comprising:
one or more sensors;
a memory for storing a three-dimensional bitmap; and
one or more processors coupled to the memory, the one or more processors being configured to:
obtain a set of input from the one or more sensors, the sensors being configured to perceive an environment;
determine a three-dimensional bitmap associated with an environmental state based on the set of input, the three-dimensional bitmap comprising a plurality of pixels; and
identify a position for an object using the three-dimensional bitmap, wherein an intensity of each pixel at a particular coordinate of the bitmap represents a likelihood that the object is at a location within the environment corresponding to the particular coordinate of the three-dimensional bitmap; and
controlling a vehicle using an automated driving system based on the position in order to avoid the object.
14. The processing system of claim 13 , wherein the three dimensions of the three-dimensional bitmap correspond to a first environmental position along an x axis, a second environmental position along a y axis, and a lateral velocity.
15. The processing system of claim 14 , wherein the one or more processors are further configure to modify the set of input obtained from the one or more sensors from a four-dimensional representation to a three-dimensional representation by eliminating a longitudinal velocity from the obtained input.
16. The processing system of claim 15 , wherein the one or more processors are further configure to:
identify a peak of intensity within the three-dimensional bitmap; and
determine a longitudinal velocity of a given object located at the intensity peak.
17. The processing system of claim 14 , wherein the longitudinal velocity is identified using a radar sensor.
18. The processing system of claim 13 , wherein the processor is further configure to provide the identified position of the object to an autonomous vehicle.
19. The processing system of claim 13 , wherein the one or more sensors comprise at least one of a camera, a laser scanner, and a radar detector.
20. The processing system of claim 13 , wherein the one or more processors are further configure to:
obtain a second set of input from the one or more sensors; and
generate a new environmental state by painting the obtained sets of input into a second three-dimensional bitmap, the second three-dimensional bitmap representing an updated environmental state incorporating the second set of input.