Seat Occupant Classification Using Posture-Aware Force Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional occupant classification systems in automotive vehicles misclassify the weight of seat occupants due to variations in posture, which affects the accuracy of weight measurements, as they do not distinguish between different sitting postures.
Innovation Solution
An occupant classification system that includes a plurality of sensors, a posture classifier, and a weight classification system, using a probabilistic method to identify the posture and weight class of an occupant based on the distribution of forces applied to the sensors, and employing a deterministic method to derive weight classes, with the option to use a second probabilistic method when initial classification is uncertain.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional pressure sensing devices measure force on the seat cushion to determine occupant weight, then the system can provide weight information for safety system optimization, but the measurement accuracy deteriorates due to variations in occupant posture affecting weight distribution
Solution Approach 1:
The seat cushion is divided into multiple sensing zones with individual pressure sensors distributed across the surface. This segmentation allows the system to detect not only total weight but also the spatial distribution of force, enabling posture identification and compensation algorithms to improve weight measurement accuracy despite posture variations
Solution Approach 2:
The system uses the pattern of force distribution across multiple sensors as feedback to identify occupant posture. This posture information is then fed back to adjust or compensate the weight calculation, creating a closed-loop system that corrects for posture-induced measurement errors and improves overall reliability
2Device complexity
If the system uses a single force measurement point to determine weight, then the device complexity is reduced, but the ability to distinguish different sitting postures is lost, leading to misclassification
Solution Approach 1:
Instead of a single measurement point, the system segments the seat cushion into multiple sensing zones with distributed sensors. This segmentation provides the spatial resolution needed to distinguish different postures while keeping each individual sensor simple, balancing complexity and precision
Solution Approach 2:
The system transitions from one-dimensional single-point weight measurement to two-dimensional force distribution mapping across the seat cushion surface. This dimensional expansion enables posture identification by detecting patterns in the spatial distribution of force, adding discriminatory power without requiring complex individual sensors
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
Significantly improves the accuracy of weight classification by accounting for posture variations, allowing for precise identification of weight classes and optimizing vehicle safety systems like airbag deployment.
Implementation Method 1
Each of the plurality of sensors measures a force applied to the seat cushion by an occupant of the seat assembly
Data Source
AI summary
An occupant classification system for a seat assembly (20) includes a plurality of sensors (32), a posture classifier and a weight classification system. The seat assembly includes a seat cushion (22) and a seat back (24). Each of the plurality of sensors (32) measures a force applied to the seat cushion (22) by an occupant of the seat assembly. The posture classifier identifies a posture of the occupant based on the distribution of forces applied to each of the plurality of sensors (32). The weight classification system identifies a weight class of the occupant based on the posture and the magnitude of forces applied to each of the plurality of sensors (32).