Adaptive Occupant Protection via Seating Position Modeling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Occupant protection systems in vehicles are inefficient due to the changing posture of occupants during travel, which can lead to injuries rather than protection in the event of a crash, as existing systems do not adequately adapt to varying seating positions and postures.

Innovation Solution

A method and safety system that utilize sensor data from multiple sensors, such as LIDAR and RGB cameras, to construct a software-based model of the occupant's seating position, allowing for adaptive adjustment of protection features like airbag deployment and seat positioning to enhance safety based on the occupant's posture and the vehicle's safety state.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If airbags are deployed based on traditional sensor systems, then collision protection is provided, but occupants in unsuitable seating positions may suffer injuries rather than protection

Engineering Contradiction:
Improveoccupant protection effectivenessVSAvoidinjuries to occupants in unsuitable positions
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system dynamically adjusts airbag deployment decisions based on real-time detection of occupant seating position and posture using multiple sensors (LIDAR, RGB cameras). The protection system transitions from a static, one-size-fits-all approach to a dynamic, adaptive approach that responds to changing occupant configurations, thereby preventing injuries to occupants in unsuitable positions while maintaining protection for those in correct positions.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system employs feedback loops where sensor data continuously monitors occupant position and posture, feeds this information to the control unit, which then adjusts airbag deployment status accordingly. This closed-loop feedback mechanism enables the system to learn from and respond to occupant behavior patterns, improving protection effectiveness while avoiding harmful deployments.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If multiple sensors are used to detect occupant position, then seating position accuracy is improved, but system complexity increases

Engineering Contradiction:
Improveseating position detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system merges data from multiple different sensor types (LIDAR for 3D spatial mapping, RGB cameras for visual recognition) into a unified occupant model. By combining these complementary sensing modalities, the system achieves high measurement precision for occupant position and posture detection while managing complexity through integrated data processing and fusion algorithms.

Inventive Principle:
Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively adapts occupant protection features to improve safety by accurately determining seating positions and postures, preventing injuries by deactivating airbags in unsuitable positions and alerting occupants to hazardous seating or objects, thereby enhancing overall vehicle safety.

Implementation Method 1

sensor data from multiple sensors, such as LIDAR and RGB cameras

Methodology Applied
Scientific EffectLIDAR: LIDAR

Implementation Method 2

sensor data from multiple sensors, such as LIDAR and RGB cameras

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3581440A1Method and system for controlling a state of an occupant protection feature for a vehicle
Publication Date: 2019.12.18 POLESTAR PERFORMANCE
  • EP3581440A1 patent drawingFigure 1a~1c
  • EP3581440A1 patent drawingFigure 1d~1g
  • EP3581440A1 patent drawingFigure 2~3a

AI summary

The present invention relates to a method for adapting an occupant protection feature (302, 304, 306) of a vehicle. Receiving (S102) sensor data from at least two sensors (402, 204, 206), the sensor data is indicative of a detected occupant (102,108,110) in the vehicle. Constructing (S104) a model of a seating position of the detected occupant in the vehicle based on the sensor data. Adapting (S106) the occupant protection feature based on the modelled occupant's seating position.