Moving track prediction method and apparatus
A moving track prediction method includes obtaining an initial state, of a moving target that includes an initial location and an initial motion state, generating one or more destination states of the moving target based on the initial state of the moving target and preset path information, and predicting a moving track of the moving target based on the initial state of the moving target and the one or more destination states to obtain one or more predicted moving tracks.
1. A method comprising:
obtaining, by one or more target detection sensors, an initial state of a moveable target, wherein the initial state comprises an initial location and an initial motion state;
obtaining, by a destination state generator using a model training algorithm comprising a softmax function, a parameter;
generating one or more destination states of the target based on the parameter, the initial state and preset path information, wherein each of the one or more destination states comprises a destination location;
predicting, based on the initial state and the one or more destination states, a moving track of the target to obtain one or more predicted moving tracks; and
controlling, with reference to the one or more predicted moving tracks, the target.
2. The method of claim 1 , further comprising:
determining, based on the initial location and the preset path information, one or more preset paths associated with the target; and
further generating, based on a motion model, the one or more destination states corresponding to the one or more preset paths.
3. The method of claim 2 , further comprising:
establishing one or more Frenet coordinate systems based on the one or more preset paths; and
further generating the one or more destination states respectively in the one or more Frenet coordinate systems.
4. The method of claim 1 , further comprising:
generating, based on the initial state and preset path information, a first probability of each of a plurality of destination states; and
obtaining, based on the first probability of each of the destination states, a second probability of each of the one or more predicted moving tracks.
5. The method of claim 1 , wherein each of the one or more destination states further comprises a destination motion state, and wherein the destination motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
6. The method of claim 1 , wherein the initial motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
7. An apparatus comprising:
a memory configured to store instructions; and
a processor coupled to the memory, wherein the instructions cause the processor to be configured to:
obtain, from one or more target detection sensors, an initial state of a moveable target, wherein the initial state comprises an initial location and an initial motion state;
obtain, by a destination state generator using a model training algorithm comprising a boosting function, a parameter;
generate one or more destination states of the target based on the parameter, the initial state and preset path information, wherein each of the one or more destination states comprises a destination location;
predict, based on the initial state and the one or more destination states, a moving track of the target to obtain one or more predicted moving tracks; and
control, with reference to the one or more predicted moving tracks, the target.
8. The apparatus of claim 7 , wherein the instructions further cause the processor to be configured to:
determine, based on the initial location and the preset path information, one or more preset paths associated with the target; and
further generate, based on a motion model, the one or more destination states corresponding to the one or more preset paths.
9. The apparatus of claim 8 , wherein the instructions further cause the processor to be configured to:
establish one or more Frenet coordinate systems based on the one or more preset paths; and
further generate the one or more destination states respectively in the one or more Frenet coordinate systems.
10. The apparatus of claim 7 , wherein the instructions further cause the processor to be configured to:
generate, based on the initial state and the preset path information, a first probability of each of a plurality of destination states; and
obtain, based on the first probability of each destination state, a second probability of each of the one or more predicted moving tracks.
11. The apparatus of claim 7 , wherein each of the one or more destination states further comprises a destination motion state, and wherein the destination motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
12. The apparatus of claim 7 , wherein the initial motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
13. A computer program product comprising computer-executable instructions that are stored on a non-transitory computer readable medium and that, when executed by a processor, cause an apparatus to:
obtain, with one or more target detection sensors, an initial state of a moveable target, wherein the initial state comprises an initial location and an initial motion state;
obtain, by a destination state generator using a model training algorithm comprising a decision tree, a parameter;
generate one or more destination states of the target based on the parameter, the initial state and preset path information, wherein each of the one or more destination states comprises a destination location;
predict, based on the initial state and the one or more destination states, a moving track of the target to obtain one or more predicted moving tracks; and
control, with reference to the one or more predicted moving tracks, the target.
14. The computer program product of claim 13 , wherein the computer-executable instructions further cause the apparatus to:
determine, based on the initial location and the preset path information, one or more preset paths associated with the target; and
further generate, based on a motion model, the one or more destination states corresponding to the one or more preset paths.
15. The computer program product of claim 14 , wherein the computer-executable instructions further cause the apparatus to:
establish one or more Frenet coordinate systems based on the one or more preset paths; and
further generate the one or more destination states respectively in the one or more Frenet coordinate systems.
16. The computer program product of claim 13 , wherein each of the one or more destination states further comprises a destination motion state, and wherein the destination motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
17. The computer program product of claim 13 , wherein the initial motion state comprises at least one of a velocity, an acceleration, an angular velocity, or an angular acceleration.
18. The computer program product of claim 13 , wherein the computer-executable instructions further cause the apparatus to:
generate, based on the initial state and the preset path information, a first probability of each of a plurality of destination states; and
obtain, based on the first probability of each destination state, a second probability of each of the one or more predicted moving tracks.
19. The method of claim 1 , wherein the one or more target detection sensors comprise a laser radar.
20. The apparatus of claim 7 , wherein the one or more target detection sensors comprises a millimeter-wave radar.