# US 2018/0322642 A1 · Prediction of multi-agent adversarial movements through signature-formations using radon-cumulative distribution transform and canonical correlation analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0322642 A1
- Document ID: US20180322642A1
- Status: Published application
- Kind: A1
- Application number: 15/971,982
- Filed: 2018-05-04
- Published: 2018-11-08
- Earliest claimed: 2017-05-05
- Assignees: HRL Laboratories, LLC
- Applicants: HRL Laboratories, LLC
- Inventors: Soheil Kolouri; Amir M. Rahimi; Rajan Bhattacharyya
- Web page: https://patentgrep.com/patent/US20180322642A1

## CPC

- G06V 20/13: Satellite images
- G06F 18/21347: {using domain transformations}
- G06F 18/2135: based on approximation criteria, e.g. principal component analysis
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 20/00: Machine learning
- G06T 7/262: using transform domain methods, e.g. Fourier domain methods
- G06T 7/277: involving stochastic approaches, e.g. using Kalman filters
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 20/17: taken from planes or by drones
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- A63B 69/0071: {for basketball}
- A63B 2024/0056: {for statistical or strategic analysis}
- G06T 2207/20081: Training; Learning
- G06T 2207/30196: Human being; Person
- G06T 2207/30221: Sports video; Sports image
- G06T 2207/30241: Trajectory
- G08G 5/55: for a single aircraft
- G08G 5/57: for unmanned aircraft
- G08G 9/00: Traffic control systems for craft where the kind of craft is irrelevant or unspecified
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A63B: APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT (apparatus for passive exercising, massage A61H)
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})

## Abstract

Described is a system for predicting multi-agent movements. A Radon Cumulative Distribution Transform (Radon-CDT) is applied to pairs of signature-formations representing agent movements. Canonical correlation analysis (CCA) components are identified for the pairs of signature-formations. Then, a relationship between the pairs of signature formations is learned using the CCA components. A counter signature-formation for a new dataset is predicted using the learned relationship and a new signature-formation. Control parameters of a device can be adjusted based on the predicted counter signature-formation.

## Claims

### Claim 1

A system for predicting multi-agent movements, the system comprising:
one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from a dataset, wherein signature-formations represent agent movements; and
identifying canonical correlation analysis (CCA) components for the pairs of signature-formations.

### Claim 2

A system for predicting multi-agent movements, the system comprising:
one or more processor and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of:
learning a relationship between pairs of signature formations obtained from a dataset using canonical correlation analysis (CCA) components, wherein signature-formations represent agent movements;
predicting a counter signature-formation for a new dataset using the learned relationship and a new signature-formation; and
adjusting control parameters of a device based on the predicted counter signature-formation.

### Claim 3 (depends on 2)

The system as set forth in claim 2, wherein the one or more processors further perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from the new dataset, wherein the pairs of signature-formation represent a first set of agents' movements;
predicting a corresponding counter signature-formation for the pairs of signature-formations obtained from the new dataset in a Radon-CDT space using CCA, resulting in the predicted counter signature-formation, wherein the predicted counter signature-formation represents a second set of agents' movements; and
inverting the predicted signature-formation from the Radon-CDT space to an image space.

### Claim 4 (depends on 2)

The system as set forth in claim 2, wherein the predicted counter signature-formation is used to predict how to counter at least one adversary's spatial formation.

### Claim 5 (depends on 3)

The system as set forth in claim 3, wherein the one or more processors further perform an operation of applying an inverse Radon Cumulative Distribution Transform (iRadon-CDT) to visualize counter signature-formations in the image space.

### Claim 6 (depends on 2)

The system as set forth in claim 2, wherein a displayed counter signature-formation provides real-time tactical feedback to a user.

### Claim 7

A computer implemented method for predicting multi-agent movements, the method comprising an act of:
causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from a dataset, wherein signature-formations represent agent movements; and
identifying canonical correlation analysis (CCA) components for the pairs of signature-formations.

### Claim 8

A computer implemented method for predicting multi-agent movements, the method comprising an act of:
causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
learning a relationship between pairs of signature formations obtained from a dataset using canonical correlation analysis (CCA) components, wherein signature-formations represent agent movements;
predicting a counter signature-formation for a new dataset using the learned relationship and a new signature-formation; and
adjusting control parameters of a device based on the predicted counter signature-formation.

### Claim 9 (depends on 8)

The method as set forth in claim 8, wherein the one or more processors further perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from the new dataset, wherein the pairs of signature-formation represent a first set of agents' movements;
predicting a corresponding counter signature-formation for the pairs of signature-formations obtained from the new dataset in a Radon-CDT space using CCA, resulting in the predicted counter signature-formation, wherein the predicted counter signature-formation represents a second set of agents' movements; and
inverting the predicted signature-formation from the Radon-CDT space to an image space.

### Claim 10 (depends on 8)

The method as set forth in claim 8, wherein the predicted counter signature-formation is used to predict how to counter at least one adversary's spatial formation.

### Claim 11 (depends on 9)

The method as set forth in claim 9, wherein the one or more processors further perform an operation of applying an inverse Radon Cumulative Distribution Transform (iRadon-CDT) to visualize counter signature-formations in the image space.

### Claim 12 (depends on 8)

The method as set forth in claim 8, wherein a displayed counter signature-formation provides real-time tactical feedback to a user.

### Claim 13

A computer program product for predicting multi-agent movements, the computer program product comprising:
computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having one or more processors for causing the processor to perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from a dataset, wherein signature-formations represent agent movements; and
identifying canonical correlation analysis (CCA) components for the pairs of signature-formations.

### Claim 14

A computer program product for predicting multi-agent movements, the computer program product comprising:
computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having one or more processors for causing the processor to perform operations of:
learning a relationship between pairs of signature formations obtained from a dataset using canonical correlation analysis (CCA) components, wherein signature-formations represent agent movements;
predicting a counter signature-formation for a new dataset using the learned relationship and a new signature-formation; and
adjusting control parameters of a device based on the predicted counter signature-formation.

### Claim 15 (depends on 14)

The computer program product as set forth in claim 14, further comprising instructions for causing the one or more processors to further perform operations of:
applying a Radon Cumulative Distribution Transform (Radon-CDT) to pairs of signature-formations obtained from the new dataset, wherein the pairs of signature-formation represent a first set of agents' movements;
predicting a corresponding counter signature-formation for the pairs of signature-formations obtained from the new dataset in a Radon-CDT space using CCA, resulting in the predicted counter signature-formation, wherein the predicted counter signature-formation represents a second set of agents' movements; and
inverting the predicted signature-formation from the Radon-CDT space to an image space.

### Claim 16 (depends on 14)

The computer program product as set forth in claim 14, wherein the predicted counter signature-formation is used to predict how to counter at least one adversary's spatial formation.

### Claim 17 (depends on 15)

The computer program product as set forth in claim 15, further comprising instructions for causing the one or more processors to further perform an operation of applying an inverse Radon Cumulative Distribution Transform (iRadon-CDT) to visualize counter signature-formations in the image space.

### Claim 18 (depends on 14)

The computer program product as set forth in claim 14, wherein a displayed counter signature-formation provides real-time tactical feedback to a user.

### Claim 19 (depends on 2)

The system as set forth in claim 2, wherein the device is an unmanned aerial vehicle (UAV).

### Claim 20 (depends on 2)

The system as set forth in claim 2, wherein the device is an autonomous vehicle.

### Claim 21 (depends on 2)

The system as set forth in claim 2, wherein the device is a camera.
