Driving Pattern Recognition for Automated Vehicle Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Automated driving systems in modern vehicles do not consider a driver's history or patterns, limiting their ability to provide personalized and efficient navigation and assistance.

Innovation Solution

A system and method that recognizes and predicts driving patterns by collecting and processing vehicle data, including driver input and sensor information, to anticipate user actions and preferences, enabling automated driving and assistance features such as preferred route navigation and notifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If automated driving systems rely only on driver's environment without taking into account driving history, then the system complexity is reduced, but the adaptability and personalization capability deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidpersonalization capability
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary actions by collecting and storing driver input data and sensor information in advance, building a comprehensive driving history database that enables future pattern recognition and personalized automation without increasing real-time system complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces driving pattern recognition as an intermediary layer between raw sensor data and automated driving decisions, allowing the system to process historical data separately and apply learned patterns to current situations, thereby separating data collection complexity from decision-making complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If driving patterns are recognized and stored in association with sensor information and timestamps, then the adaptability and personalization improve, but the data storage requirements and processing complexity increase

Engineering Contradiction:
Improvepattern recognition capabilityVSAvoiddata processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments driving data into distinct components (driver input, sensor information, timestamps) and processes them separately through different modules, allowing complex pattern recognition to be achieved through coordinated simple operations rather than monolithic complex processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements feedback mechanisms where recognized driving patterns are continuously refined and updated based on new data, allowing the system to improve personalization capability while maintaining processing efficiency through iterative learning rather than exhaustive analysis

Inventive Principle:
Principle #23Feedback

3Ease of operation

If driving patterns are used to automatically control vehicle actions, then the ease of operation improves, but the extent of automation increases which may reduce driver control

Engineering Contradiction:
Improveease of operationVSAvoidautomation level
Core Design Contradiction:
Ease of operationVSExtent of automation

Solution Approach 1:

The system applies partial automation by using driving patterns to assist specific aspects of vehicle operation rather than complete automation, allowing the system to improve ease of operation for routine tasks while maintaining driver control and decision-making authority for overall vehicle operation

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10315665B2System and method for driver pattern recognition, identification, and prediction
Publication Date: 2019.06.11 FARADAY&FUTURE INC
  • US10315665B2 patent drawing
  • US10315665B2 patent drawing
  • US10315665B2 patent drawing

AI summary

Examples of the present invention are directed to a method and system of recognizing a driving pattern of a vehicle. Driver input controlling the vehicle can be received and stored in association with various sensor information (e.g., GPS location, camera data, radar data, etc.) and a timestamp. Then, driving patterns can be recognized from the stored information. For example, preferred routes, destinations, driving speeds, driving styles, etc. can be recognized. The driving patterns can be used by automated driving or driving assistance systems to automatically drive on preferred routes or to preferred destinations.