# US 2021/0279570 A1 · Method for proving or identifying counter-examples in neural network systems that process point cloud data

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

- Number: US 2021/0279570 A1
- Document ID: US20210279570A1
- Status: Published application
- Kind: A1
- Application number: 17/078,079
- Filed: 2020-10-22
- Published: 2021-09-09
- Earliest claimed: 2020-03-03
- Applicants: HRL Laboratories, LLC
- Inventors: Michael A. Warren; Christopher Serrano; Aleksey Nogin
- Web page: https://patentgrep.com/patent/US20210279570A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/105: {Shells for specifying net layout}
- G05D 1/0221: {involving a learning process}
- G05D 1/0276: {using signals provided by a source external to the vehicle (involving a plurality of vehicles G05D1/0287; automatically controlling vehicle speed responsive to externally generated signals B60K31/0058)}
- G05D 1/22: Command input arrangements
- G05D 1/247: using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/045: Combinations of networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 5/013: {Automatic theorem proving}
- B60W 60/001: {Planning or execution of driving tasks}
- B60W 2556/45: External transmission of data to or from the vehicle
- G01S 7/4808: {Evaluating distance, position or velocity data}
- G01S 17/89: for mapping or imaging
- G01S 17/931: of land vehicles
- G06F 7/544: for evaluating functions by calculation {(G06F7/4824 takes precedence)}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Described is a system for proving correctness properties of a neural network for providing estimates for point cloud data. The system receives as input a description of a neural network for generating estimates from a set of point cloud data. The description of the neural network is parsed to obtain a symbolic representation. Based on a combination of the symbolic representation and a set of analysis parameters, the system generates an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data. The analysis output is a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, or a report that progress could not be made by the analysis.

## Claims

### Claim 1

A system for proving correctness properties of a neural network for providing estimates for point cloud data, 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:
receiving, as input, a description of a neural network for generating estimates from a set of point cloud data, wherein the description of the neural network is in one of a source code format or a serialized format;
parsing the description of the neural network to obtain a symbolic representation;
based on a combination of the symbolic representation and a set of analysis parameters, generating an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data,
wherein the analysis output is one of a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, and a report that progress could not be made by the analysis.

### Claim 2 (depends on 1)

The system as set forth in claim 1, wherein the analysis output acts as a stopping condition for preventing deployment of the neural network.

### Claim 3 (depends on 1)

The system as set forth in claim 1, wherein the estimates comprise an estimate of a slope of a patch of the set of point cloud data.

### Claim 4 (depends on 1)

The system as set forth in claim 1, wherein the estimates comprise an estimate of a surface normal of a patch of the set of point cloud data.

### Claim 5 (depends on 1)

The system as set forth in claim 1, wherein the estimates comprise an estimate regarding whether a patch of the set of point cloud data is ground or non-ground.

### Claim 6 (depends on 1)

The system as set forth in claim 1, wherein the set of analysis parameters describe geometric properties of the set of point cloud data.

### Claim 7

A computer implemented method for proving correctness properties of a neural network for providing estimates for point cloud data, the method comprising an act of:
causing one or more processors to execute instructions encoded on one or more associated memories, each associated memory being a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
receiving, as input, a description of a neural network for generating estimates from a set of point cloud data, wherein the description of the neural network is in one of a source code format or a serialized format;
parsing the description of the neural network to obtain a symbolic representation;
based on a combination of the symbolic representation and a set of analysis parameters, generating an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data,
wherein the analysis output is one of a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, and a report that progress could not be made by the analysis.

### Claim 8 (depends on 7)

The method as set forth in claim 7, wherein the analysis output acts as a stopping condition for preventing deployment of the neural network.

### Claim 9 (depends on 7)

The method as set forth in claim 7, wherein the estimates comprise an estimate of a slope of a patch of the set of point cloud data.

### Claim 10 (depends on 7)

The method as set forth in claim 7, wherein the estimates comprise an estimate of a surface normal of a patch of the set of point cloud data.

### Claim 11 (depends on 7)

The method as set forth in claim 7, wherein the estimates comprise an estimate regarding whether a patch of the set of point cloud data is ground or non-ground.

### Claim 12 (depends on 7)

The method as set forth in claim 7, wherein the set of analysis parameters describe geometric properties of the set of point cloud data.

### Claim 13

A computer readable program for proving correctness properties of a neural network for providing estimates for point cloud data, the computer readable program 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:
receiving, as input, a description of a neural network for generating estimates from a set of point cloud data, wherein the description of the neural network is in one of a source code format or a serialized format;
parsing the description of the neural network to obtain a symbolic representation;
based on a combination of the symbolic representation and a set of analysis parameters, generating an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data,
wherein the analysis output is one of a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, and a report that progress could not be made by the analysis.

### Claim 14 (depends on 13)

The computer readable program as set forth in claim 13, wherein the analysis output acts as a stopping condition for preventing deployment of the neural network.

### Claim 15 (depends on 13)

The computer readable program as set forth in claim 13, wherein the estimates comprise an estimate of a slope of a patch of the set of point cloud data.

### Claim 16 (depends on 13)

The computer readable program as set forth in claim 13, wherein the estimates comprise an estimate of a surface normal of a patch of the set of point cloud data.

### Claim 17 (depends on 13)

The computer readable program as set forth in claim 13, wherein the estimates comprise an estimate regarding whether a patch of the set of point cloud data is ground or non-ground.

### Claim 18 (depends on 13)

The computer readable program as set forth in claim 13, wherein the set of analysis parameters describe geometric properties of the set of point cloud data.
