# US 2026/0249856 A1 · Driver Intoxication Measurement From Passive Face and Voice Analysis

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

- Number: US 2026/0249856 A1
- Document ID: US20260249856A1
- Status: Published application
- Kind: A1
- Application number: 19/544,438
- Filed: 2026-02-19
- Published: 2026-08-27
- Earliest claimed: 2025-02-23
- Assignees: Blueskeye AI Ltd
- Applicants: Blueskeye AI Ltd
- Inventors: Michel François Valstar; Mani Kumar Tellamekala; Anthony Brown; Adrian Cornelius Marinescu; Thomas Smith; Shashank Jaiswal
- Web page: https://patentgrep.com/patent/US20260249856A1

## CPC

- A61B 5/00: Measuring for diagnostic purposes (radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00); Identification of persons
- B60W 40/08: related to drivers or passengers
- A61B 5/18: for vehicle drivers {or machine operators}
- B60K 28/06: responsive to incapacity of driver
- B60W 2040/0836: {due to alcohol}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- 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
- B60K: ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES

## Abstract

Described is reducing the number of instances when a potential driver needs to use a breathalyzers via analysis of the driver's passive expressive gait, face and voice analysis. Fitness to drive is tested both before setting off and continue measuring during a drive. Reliable indicators for intoxication can be collected passively from visual behavior as a driver approaches (using the cars external cameras) and/or enters the car (using DMS cameras); and from face and voice behavior if the driver interacts with a voice assistant and as part of that utters a short, known sentence.

## Claims

### Claim 1

A method comprising:
performing an intoxication test on a driver by a detection system in a car, comprising:
the driver commanding the detection system to start the car;
the detection system analyzing eye movements of the driver in the car to produce internal driver eye data;
the detection system performing the intoxication test of the driver based on the internal driver eye data;
wherein the analyzing eye movements comprises analyzing smooth pursuit gaze angle pitch of the eye movements.

### Claim 2 (depends on 1)

The method of claim 1, wherein the analyzing smooth pursuit gaze angle pitch of the eye movements comprises using an intended path via Savitzky-Golay filtering techniques.

### Claim 3 (depends on 2)

The method of claim 2, wherein the analyzing smooth pursuit gaze angle pitch of the eye movements further comprises using root mean squared error.

### Claim 4 (depends on 3)

The method of claim 3, wherein the detection system further comprises:
analyzing the eye movements of the driver outside the car to produce external driver eye data; and
performing the intoxication test of the driver based on the internal driver eye data and the external driver eye data.

### Claim 5 (depends on 4)

The method of claim 4, wherein if the detection system determines the driver is intoxicated, the detection system stops the driver from controlling the car.

### Claim 6

A method comprising:
performing an intoxication test on a driver by a detection system in a car, comprising:
the driver commanding the detection system to start the car;
the detection system analyzing eye movements of the driver in the car to produce internal driver eye data;
the detection system performing the intoxication test of the driver based on the internal driver eye data;
wherein the analyzing eye movements comprises analyzing saccadic peak velocity of the eye movements.

### Claim 7 (depends on 6)

The method of claim 6, wherein the analyzing saccadic peak velocity of the eye movements comprises calculating a standard deviation of horizontal raw yaw angle while changing gaze fixation from one location to another.

### Claim 8 (depends on 7)

The method of claim 7, wherein the detection system further comprises:
analyzing the eye movements of the driver outside the car to produce external driver eye data; and
performing the intoxication test of the driver based on the internal driver eye data and the external eye data.

### Claim 9 (depends on 8)

The method of claim 8, wherein if the detection system determines the driver is intoxicated, the detection system stops the driver from controlling the car.

### Claim 10

A method comprising:
performing an intoxication test on a driver by a detection system in a car, comprising:
the driver commanding the detection system to start the car;
the detection system analyzing eye movements of the driver in the car to produce internal driver eye data;
the detection system performing the intoxication test of the driver based on the internal driver eye data;
wherein the analyzing eye movements comprises analyzing horizontal fixation stability of the eye movements.

### Claim 11 (depends on 10)

The method of claim 10, wherein the analyzing horizontal fixation stability of the eye movements comprises calculating a standard deviation of horizontal raw yaw angle while viewing a static target.

### Claim 12 (depends on 11)

The method of claim 11, wherein the detection system further comprises:
analyzing the eye movements of the driver outside the car to produce external driver eye data; and
performing the intoxication test of the driver based on the internal driver eye data and the external eye data.

### Claim 13 (depends on 12)

The method of claim 12, wherein if the detection system determines the driver is intoxicated, the detection system stops the driver from controlling the car.

### Claim 14

A method comprising:
performing an intoxication test on a driver by a detection system in a car, comprising:
the driver commanding the detection system to start the car;
the detection system requesting the driver to recite a phrase;
the driver repeating the phrase thereby generating internal driver audio;
the detection system analyzing the internal driver audio to produce internal driver audio data;
the detection system performing the intoxication test of the driver based on the internal driver audio data;
wherein the analyzing the internal driver audio comprises using a linear mixed-effects models to isolate specific chemical effect of alcohol on the driver.

### Claim 15 (depends on 14)

The method as in claim 14, wherein the analyzing the internal driver audio further comprises using a plurality of coefficients of Mel-frequency cepstrum of the internal driver audio.

### Claim 16 (depends on 14)

The method as in claim 14, wherein the analyzing the internal driver audio further comprises using a frequency below which a specified percentage of total spectral energy of the internal driver audio resides.

### Claim 17 (depends on 14)

The method as in claim 14, wherein the analyzing the internal driver audio further comprises using an amplitude-weighted mean of frequencies present in the internal driver audio.

### Claim 18 (depends on 14)

The method as in claim 14, further comprising:
the detection system analyzing eye movements of the driver to produce internal driver eye data;
the detection system performing the intoxication test of the driver based on the internal driver eye data;
wherein the analyzing eye movements comprises analyzing at least one of: (a) smooth pursuit gaze angle pitch; (b) saccadic peak velocity; and (c) horizontal fixation stability.
