Driver Identification via Behavioral Clustering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vehicle driver identification systems are inaccurate due to shared key fobs and require additional hardware, necessitating a fast and reliable software-based solution that can differentiate drivers based on their behaviors.

Innovation Solution

A system and method that analyze a sequence of vehicle start-up behaviors and longitudinal driving patterns using statistical clustering techniques, employing existing vehicle sensors to identify drivers without additional hardware, by detecting and evaluating events like door opening, seat belt fastening, ignition switch usage, and driving habits.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If device-detection systems (key fob, mobile device) are used for driver identification, then driver identification can be implemented, but the system requires additional hardware and suffers from inaccuracy due to shared devices

Engineering Contradiction:

Improvedriver identification accuracyVSAvoidhardware requirements

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces hardware-based detection systems (key fob receivers, mobile device detectors) with a software-based behavioral analysis system. The system uses existing vehicle sensors to collect data about driver behaviors such as door opening/closing sequences, seat adjustment patterns, steering wheel movements, and pedal usage, then analyzes these behavioral patterns to identify the driver. This substitution eliminates the need for additional identification hardware while improving accuracy since behavioral patterns are unique to each driver unlike shared key fobs

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system leverages data already being collected by the vehicle's existing sensors for other purposes (monitoring driver behavior for safety, comfort, and performance optimization) and repurposes this data for driver identification. The vehicle's normal operational sensors serve dual functions: their original safety/comfort functions plus driver identification, eliminating the need for separate identification hardware

Inventive Principle:

Principle #25Self-service

2Ease of manufacture

If key fob-based identification is used, then driver identification is simple to implement, but accuracy deteriorates because family members share keys

Engineering Contradiction:

Improvesystem implementation simplicityVSAvoiddriver identification accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system changes the identification parameter from static device ownership (key fob possession) to dynamic behavioral patterns (sequences of actions, timing, intensity). By monitoring multiple behavioral parameters simultaneously (door opening speed, seat adjustment sequence, steering input patterns), the system achieves high identification accuracy while maintaining implementation simplicity, as the analysis uses software processing of existing sensor data rather than complex hardware

Inventive Principle:

Principle #35Parameter changes

3Reliability

If comprehensive driver behavior analysis is performed for accurate identification, then identification reliability improves, but processing time and computational complexity increase

Engineering Contradiction:

Improvedriver identification accuracyVSAvoididentification processing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system begins collecting and analyzing behavioral data from the moment the driver approaches or enters the vehicle, using door opening/closing sequences and initial seat adjustments as early identification indicators. This preliminary analysis provides rapid initial identification, and the system continues gathering data to refine and verify the identification over subsequent minutes of driving, thus achieving high accuracy without requiring lengthy processing periods

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The behavioral analysis is divided into multiple segments or phases: initial rapid identification based on entry behavior (door sequences, immediate seat adjustments), intermediate verification using driving patterns (steering, acceleration, braking), and ongoing refinement. This segmentation allows the system to provide identification results at different time scales, delivering fast initial identification while achieving high confidence through progressive verification

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10332020B2Method and apparatus of differentiating drivers based on driving behaviors

Publication Date: 2019.06.25 GM GLOBAL TECHNOLOGY OPERATIONS LLC

AI summary

A system and method for identifying a vehicle driver based on driver behaviors. The system and method include analyzing a sequence of vehicle start-up behaviors for rapid identification of the driver. The start-up analysis includes detecting and evaluating the sequence and timing of events including door opening, door closing, seat belt fastening, ignition switch usage and shift/drive, among others. The technique further includes analyzing a set of longitudinal (or long-term) behaviors for more robust verification of driver identification. The longitudinal behaviors include acceleration and braking patterns, speed pattern (compared to road type and speed limit), stop sign behavior, cruise control usage and many others. Statistical clustering techniques are employed for both the start-up and longitudinal behavior analyses to identify the driver.