Track prediction and identification via particle motion with intent

• US 20090306894A1
• Filed: 06/04/2008
• Published: 12/10/2009
• Est. Priority Date: 06/04/2008
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Gokcen, Serdar N., Noble, William B., Payton, David W., Howard, Michael D.
• Granted Patent: US 9,002,642 B2
• Time in Patent Office: Days
• US Class Current: 701/300
• CPC Class Codes: G01S 13/723 by using numerical data
• CPC Class Codes: G01S 13/878 Combination of several spaced transmitters or receivers of known location for determining the position of a transponder or a reflector G01S13/874 takes precedence
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target
• CPC Class Codes: G06Q 10/08355 Routing methods

Abstract

Provided is a system and method for tracking and identifying a target in an area of interest based on a comparison of predicted target behavior or movement and sensed target behavior or movement. Incorporating aspects of both particle diffusion and mobility constraint models with target intent derivations, the system may continuously track a target while simultaneously refining target identification information. Alternatively, the system and method are applied to reacquire a target track based on prioritized intents and predicted target location.

Claims

1. A method of tracking a target, comprising:

sensing a target in an area of interest;

creating a set of particles to represent the sensed target;

attributing to each particle a functional intent, wherein the probability density of the particles in the set of particles correlates to the probability the target is a target-of-interest;

grouping the set of particles based on functional intent;

defining at least one vehicle type having predetermined vehicle characteristics;

identifying objects within the area of interest with which the target may interact;

allocating to each object an attraction-repulsion factor for each functional intent;

correlating functional intents, vehicle types, vehicle characteristics, and objects having attraction-repulsion factors with defined mobility constraints for the area of interest, to define at least one rule of behavior for each particle;

applying the at least one rule of behavior to predict a movement and geographic location for each particle representing the object; and

moving each particle representing a predicted location of the object in accordance with the observed movements of the object, inferred intent and all other attributes ascribed to that particle and geographic location for the particle.

2. The method of claim 1, further comprising categorizing particles of like functional intent as a target-of-interest.

3. The method of claim 2, further comprising:

pruning particles not categorized as a target-of-interest;

creating additional particles such that the number of particles pruned and the number of particles additionally created are equal; and

distributing created particles to modify functional intent probabilities.

4. The method of claim 1, further comprising comparing the predicted movement and geographic location for each particle of like functional intent to a known movement and geographic location for the target to identify the functional intent of the target.

5. The method of claim 1, wherein the target is land based.

6. The method of claim 1, wherein sensor coverage of the target is discontinuous, and further wherein a reacquisition of the tracked target is desired.

7. The method of claim 6, further comprising:

establishing a priority for each functional intent; and

initiating a reacquisition of the target based on functional intent priorities.

8. The method of claim 1, further comprising:

selecting a goal for each particle representing a functional intent; and

applying mobility constraints and attraction-repulsion factors to define at least one route for reaching the goal.

9. The method of claim 8, further comprising optimizing the route.

10. The method of claim 8, further comprising incorporating a probability that a particle will divert from a chosen goal to a different goal.

11. The method of claim 1, further comprising apportioning to each particle a selected behavior.

12. The method of claim 11, wherein the selected behavior is chosen from a group consisting of:

speed, route diversion, hazard avoidance,

13. A system for tracking and identifying a target, comprising:

at least one sensor for sensing the target in an area of interest;

a first database defining a population of vehicle types and corresponding vehicle characteristics;

a second database identifying functional intents;

a third database populated with objects in the area of interest having a predetermined attraction-repulsion factor, wherein the attraction-repulsion factor is related to a relationship between a given functional intent and a given object; and

a processor for correlating sensed data and the first, second, and third databases information with pre-determined mobility constraints to describe the target in terms of particles having predicted rules of behavior, and to track and identify the target based on a comparison of predicted particle behavior and sensed target behavior.

14. The system of claim 13 wherein the sensor coverage of the object is discontinuous, and further wherein reacquisition of the track is initiated using predetermined priorities for each functional intent.

15. The system of claim 13, further comprising a pruning function for eliminating particles.

16. The system of claim 13, further comprising one or more finite state machines.

17. The system of claim 16, wherein the finite state machine models target behaviors selected from a group consisting of:

goal achievement, goal modification, target speed, route diversion, and hazard avoidance.

18. The system of claim 13, wherein the target is selected from a group consisting of:

at least one land based target, at least one sea based target, at least one air based target, and at least one space based target, or any combination thereof.

19. A system for tracking and identifying a target, comprising:

a means for sensing the target in an area of interest; and

a means for correlating and processing sensed data and information contained in pre-defined databases to track and identify the target based on a comparison of predicted target behavior and sensed target behavior

wherein the target'"'"'s movement is represented in terms of particle densities, and further wherein rules of behavior are assigned to each particle defining a target, the rules of behavior derived from a correlation of data and information in the databases, to include vehicle types and characteristics, target intent, objects to interact with the target, and selected target behavior.

20. The system of claim 19, wherein the sensor coverage is discontinuous.