Vehicle Driving Mode Recognition Using Driver-Specific Fuzzy Logic

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle driving mode recognition methods do not account for individual driver behavior and instantaneous mood, relying on typical behavior of a reference driver and requiring manual driver input.

Innovation Solution

A method using fuzzy logic that determines the real membership function of driving parameters based on statistical distributions specific to each driver, incorporating instantaneous behavior and adjusting Gaussian curves in real-time to recognize the most appropriate driving mode automatically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If a reference driver model is used for driving mode recognition, then the recognition method is simple to implement, but it cannot account for individual driver behavior and instantaneous mood

Engineering Contradiction:
ImproveEase of implementationVSAvoidAdaptability to individual driver
Core Design Contradiction:
Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary learning of driver behavior patterns during a training phase before actual driving mode recognition begins. Statistical parameters such as mean and standard deviation of driving inputs are pre-calculated and stored, enabling the system to quickly adapt to individual drivers without complex real-time computation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously compares actual driver inputs against the learned statistical model and uses this feedback to dynamically adjust driving mode recognition. The deviation between actual inputs and expected inputs based on the statistical model provides feedback that enables the system to detect changes in driver mood or intent

Inventive Principle:
Principle #23Feedback

2Ease of operation

If manual driver input is required for driving mode selection, then the system is simple to control, but it is not automated and requires continuous driver action

Engineering Contradiction:
ImproveEase of controlVSAvoidAutomation level
Core Design Contradiction:
Ease of operationVSExtent of automation

Solution Approach 1:

The system performs driving mode recognition automatically by analyzing driver behavior patterns without requiring explicit driver input or selection. The driver simply operates the vehicle as normal, and the system self-determines the appropriate driving mode based on statistical analysis of driving inputs, making the automation transparent and effortless

Inventive Principle:
Principle #25Self-service

3Reliability

If typical behavior of a reference driver is used, then the recognition method works for general cases, but it fails to capture individual driver variations and instantaneous mood changes

Engineering Contradiction:
ImproveReliability for general casesVSAvoidPrecision for individual driver
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The system transitions from a universal reference driver model to driver-specific statistical models. Each driver has their own learned parameters (mean and standard deviation) that capture their individual driving characteristics. This local customization allows the system to maintain reliability across different drivers while achieving precision for each individual driver's behavior patterns

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4132828B1Method for recognising a driving mode of a vehicle and associated recognition device
Publication Date: 2024.12.18 AMPERE SAS
  • EP4132828B1 patent drawingFigure 1~2
  • EP4132828B1 patent drawingFigure 3~4
  • EP4132828B1 patent drawingFigure 5~7

AI summary

The invention relates to a method for recognising a driving mode (Mn(t)) from among a plurality of predetermined driving modes (Mn): a) establishing a fuzzy logic rule (Rx) associating, at the input, the at least one premise concerning the membership of a driving parameter (Li) of the vehicle to a fuzzy set (Az), and, at the output, one of the predetermined driving modes; b) weighting the predetermined driving mode resulting from each fuzzy logic rule; and c) recognising the driving mode of the vehicle from the weighted driving mode (Mn(P)) resulting from each fuzzy logic rule. According to the invention, in step b), the weighting of each driving mode is deduced from a function of real membership (F) of the parameter to the corresponding fuzzy set, the real membership function being deduced from a reference membership function of said parameter to said fuzzy set and from a statistical distribution (G(Li)) of the values that said parameter is likely to take.