In-Cabin Sleep Mode Control Using Video-Based Passenger Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems fail to automatically determine the sleeping or drowsy state of a passenger in a vehicle and adjust the in-cabin environment accordingly, requiring manual intervention for comfortable sleep or rest.

Innovation Solution

A system utilizing a video sensor with convolutional neural networks to monitor passenger states, combined with biometric and illuminance sensors, automatically controls the seat, air conditioning, lighting, sound, and window tinting/sunroof to a sleep mode based on passenger drowsiness or sleepiness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual adjustment of in-cabin environment is required for passenger comfort, then passenger control capability is improved, but ease of operation deteriorates

Engineering Contradiction:
Improveease of operationVSAvoidextent of automation
Core Design Contradiction:
Ease of operationVSExtent of automation

Solution Approach 1:

The system automatically detects passenger state through video sensors and autonomously adjusts in-cabin environment parameters (lighting, temperature, seat position) without requiring manual passenger input. The passenger simply needs to indicate sleep mode activation, and the system handles all subsequent adjustments automatically.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system continuously monitors passenger state through video sensors and uses this feedback to automatically adjust environmental parameters. The closed-loop control ensures the in-cabin environment adapts dynamically to passenger needs without manual intervention.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If wearable devices are used to determine passenger state, then measurement precision is improved, but device complexity worsens

Engineering Contradiction:
Improvemeasurement precisionVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the state detection function from external wearable devices and integrates it into the vehicle's built-in video sensor system. This eliminates the need for passengers to wear separate devices while maintaining state detection capability through computer vision algorithms.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The video sensor system serves multiple functions: it monitors passenger state for sleep detection, tracks passenger position for safety, and provides visual data for environmental control. This multi-functionality replaces the need for specialized wearable devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If automated sleep mode control is implemented, then ease of operation is improved, but measurement precision worsens

Engineering Contradiction:
Improveease of operationVSAvoidmeasurement precision
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary state assessment through video analysis before activating sleep mode controls. It detects facial expressions, head position, and body posture in advance to accurately determine sleep state, ensuring precise measurement before automated adjustment begins.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4177852B1Method for automatically controlling in-cabin environment for passenger and system therefor
Publication Date: 2026.03.25 HYUNDAI MOBIS CO LTD
  • EP4177852B1 patent drawingFigure 1
  • EP4177852B1 patent drawingFigure 2
  • EP4177852B1 patent drawingFigure 3

AI summary

A method for automatically controlling an in-cabin environment for a passenger in an autonomous vehicle includes monitoring a state of the passenger via a video sensor; determining whether the state of the passenger corresponds to one of preset states of a predetermined number; and adjusting, when the state corresponds to the one of the preset states, any one or any combination of any two or more of a seat, an air conditioning system, a lighting system, a sound system, a variable window tinting, and a variable sunroof of the autonomous vehicle based on the state. The determining of the state of the passenger includes detecting a plurality of determination target objects from a video of the video sensor, cropping an image of each of the plurality of determination target objects, and determining whether the state of the passenger corresponds to the one of the preset states.