Object tracking based on temporal data attribute inferences
Techniques for determining attributes associated with objects represented in temporal sensor data. In some examples, the techniques may include receiving sensor data including a representation of an object in an environment. The sensor data may be generated by a temporal sensor of a vehicle and, in some instances, a trajectory of the object or the vehicle may contribute to a distortion in the representation of the object. For instance, a shape of the representation of the object may be distorted relative to an actual shape of the object. The techniques may also include determining an attribute (e.g., velocity, bounding box, etc.) associated with the object based at least in part on a difference between the representation of the object and another representation of the object (e.g., in other sensor data) or the actual shape of the object.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving, from a first sensor of a vehicle, first sensor data representing an object in an environment in which the vehicle is operating, wherein a movement of at least one of the object or the vehicle contributes to a distortion in a representation of the object;
determining, based at least in part on the first sensor data, a difference between the distortion in the representation of the object and an actual shape of the object from a perspective of the vehicle;
determining, based at least in part on the difference, a lateral instantaneous velocity component associated with the object, the lateral instantaneous velocity component perpendicular to a line of sight associated with the first sensor;
receiving, from a second sensor of the vehicle, second sensor data indicative of a longitudinal instantaneous velocity component, the longitudinal instantaneous velocity component parallel to the line of sight;
determining a predicted trajectory of the object based at least in part on the lateral instantaneous velocity component and the longitudinal instantaneous velocity component; and
controlling operation of the vehicle based at least in part on the predicted trajectory of the object.
2. The system of claim 1 , wherein the first sensor data is at least one of lidar data generated by a rotating lidar sensor or image data generated by a rolling shutter image sensor.
3. The system of claim 1 , wherein the lateral instantaneous velocity component is determined further based at least in part on:
a length of a period of time associated with the first sensor scanning the object; and
a distance between the vehicle and the object.
4. The system of claim 1 , the operations further comprising determining, based at least in part on the lateral instantaneous velocity component, that the object corresponds with a tracked object, wherein the predicted trajectory of the object is determined based at least in part on associating the lateral instantaneous velocity with the tracked object.
5. A method comprising:
receiving sensor data generated by a temporal sensor of a vehicle operating in an environment;
determining a lateral instantaneous velocity associated with an object in the environment, at least a portion of the object being represented in the sensor data,
wherein the lateral instantaneous velocity is a component of a velocity vector associated with the object, the component being perpendicular to another component of the velocity vector that is parallel to a line of sight associated with the temporal sensor;
determining, based at least in part on the lateral instantaneous velocity, a predicted trajectory of the object; and
controlling operation of the vehicle based at least in part on the predicted trajectory.
6. The method of claim 5 , wherein a velocity magnitude of the other component of the velocity vector that is parallel to the line of sight is determined based at least in part on radar data received from a radar sensor of the vehicle.
7. The method of claim 5 , further comprising determining, based at least in part on the lateral instantaneous velocity, that the object corresponds with a tracked object.
8. The method of claim 5 , wherein the lateral instantaneous velocity is determined based at least in part on a distortion associated with the at least the portion of the object represented in the sensor data, the distortion contributable to a movement of at least one of the object or the vehicle during a scan of the temporal sensor.
9. The method of claim 8 , wherein the distortion is at least one of a distortion in shape of the at least the portion of the object relative to an actual shape of the at least the portion of the object from a perspective of the vehicle.
10. The method of claim 8 , wherein a magnitude of the distortion is proportional to a magnitude of the lateral instantaneous velocity associated with the object.
11. The method of claim 5 , wherein determining the lateral instantaneous velocity associated with the object is further based at least in part on a length of a period of time associated with the temporal sensor scanning the at least the portion of the object.
12. One or more non-transitory computer-readable media storing instructions that, when executed, cause one or more computing devices to perform operations comprising:
receiving sensor data generated by a temporal sensor of a vehicle operating in an environment;
determining a lateral instantaneous velocity associated with an object in the environment, at least a portion of the object being represented in the sensor data,
wherein the lateral instantaneous velocity is determined based at least in part on a distortion associated with the at least the portion of the object represented in the sensor data, the distortion contributable to a movement of at least one of the object or the vehicle during a scan of the temporal sensor;
determining, based at least in part on the lateral instantaneous velocity, a predicted trajectory of the object; and
controlling operation of the vehicle based at least in part on the predicted trajectory.
13. The one or more non-transitory computer-readable media of claim 12 , wherein the lateral instantaneous velocity is perpendicular to a line of sight associated with the temporal sensor.
14. The one or more non-transitory computer-readable media of claim 12 , wherein the lateral instantaneous velocity is a component of a velocity vector associated with the object, the component perpendicular to another component of the velocity vector that is parallel to a line of sight associated with the temporal sensor.
15. The one or more non-transitory computer-readable media of claim 14 , wherein a velocity magnitude of the other component of the velocity vector that is parallel to the line of sight is determined based at least in part on other sensor data received from a radar sensor of the vehicle.
16. The one or more non-transitory computer-readable media of claim 12 , the operations further comprising determining, based at least in part on the lateral instantaneous velocity, that the object corresponds with a tracked object.
17. The one or more non-transitory computer-readable media of claim 16 , wherein the predicted trajectory of the object is determined based at least in part on associating the lateral instantaneous velocity with the tracked object.
18. The one or more non-transitory computer-readable media of claim 12 , wherein determining the lateral instantaneous velocity associated with the object is further based at least in part on a length of a period of time associated with the temporal sensor scanning the at least the portion of the object.
19. The one or more non-transitory computer-readable media of claim 12 , wherein the distortion is at least one of a distortion in shape of the at least the portion of the object relative to an actual shape of the at least the portion of the object from a perspective of the vehicle.
20. The one or more non-transitory computer-readable media of claim 12 , wherein a magnitude of the distortion is proportional to a magnitude of the lateral instantaneous velocity associated with the object.