Vehicle 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 and often mistake child seats for adults or fail to distinguish between different sitting postures.
Innovation Solution
An occupant classification system that includes an array of sensing cells in both the seat cushion and seat back, using a probabilistic model, specifically a neural network, to classify postures and weight classes by analyzing the distribution of forces, distinguishing between various sitting postures and weight classes, and providing accurate weight class assignment to optimize airbag deployment systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a pressure sensing device measures force on the seat cushion to determine occupant weight, then the system can provide weight information for airbag deployment, but the measurement accuracy deteriorates because the occupant's posture affects weight distribution between the seat cushion and seat back
Solution Approach 1:
The patent divides the sensing system into multiple independent sensing cells arranged in an array across the seat cushion and seat back. Each cell independently measures local force, and the system segments the total weight measurement into contributions from different seating zones. This segmentation allows the system to detect not only total weight but also weight distribution patterns that indicate occupant posture, thereby resolving the contradiction between measurement accuracy and posture adaptability.
Solution Approach 2:
The patent transitions from a single-point or simple array weight measurement to a two-dimensional array of sensing cells that captures spatial distribution of force across the seat surface. By adding the spatial dimension to weight measurement, the system can distinguish between different posture configurations (e.g., sitting upright vs. reclined) that produce different weight distribution patterns, thus maintaining measurement accuracy across varying postures.
2Measurement precision
If the system uses a single weight measurement point to classify occupant weight, then the device complexity is low, but the classification accuracy deteriorates because it cannot distinguish between different sitting postures
Solution Approach 1:
The patent segments the sensing system into multiple sensing cells that independently measure force at different locations on the seat cushion and seat back. This segmentation enables the system to capture weight distribution patterns across the seating surface, providing rich data for accurate weight class classification while accounting for posture variations. The segmented approach transforms a simple weight measurement into a distributed sensing network that extracts both weight and posture information.
Solution Approach 2:
The array of sensing cells serves multiple functions simultaneously: it measures total occupant weight, detects weight distribution patterns, identifies occupant posture, and provides data for weight class classification. This multi-functionality allows a single sensing system to address multiple measurement needs without requiring separate dedicated sensors for each function, thereby managing complexity while enhancing accuracy.
3Measurement precision
If the system only measures force on the seat cushion without considering the seat back, then the sensing system is simple, but the weight measurement accuracy deteriorates because it does not account for weight distribution between cushion and back
Solution Approach 1:
The patent segments the sensing system into two distinct arrays: one array of sensing cells in the seat cushion and another array in the seat back. Each array independently measures force in its respective zone. This segmentation allows the system to capture the complete weight distribution picture by combining data from both seating zones, accurately determining how much weight is borne by the cushion versus the back, thereby improving measurement accuracy while maintaining modular system architecture.
Solution Approach 2:
The patent extends the sensing coverage from a single seating zone (cushion only) to multiple zones by adding sensing cells in the seat back. This dimensional expansion from one seating region to multiple regions enables the system to detect weight transfer between cushion and back that occurs during posture changes, providing more accurate weight measurement that accounts for the dynamic weight distribution across the entire seating structure.
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 significantly improves the accuracy of weight class assignment by accounting for posture variations, reducing misclassification and enhancing the precision of airbag deployment systems by providing detailed posture and weight class information to the occupant restraint controller.
Implementation Method 1
a pressure sensing device, such as a plurality of sensing cells or a bladder system, located in the seat cushion, which determines the weight of an occupant by measuring the amount of force applied to the seat cushion
Data Source
Figure 1A~1B
Figure 2A~2B
Figure 3
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).