Driver Learning Interface for Automatic Vehicle Setting Adaptation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Luxury vehicles do not provide a personalized driving experience tailored to each driver's unique preferences and driving style, despite features like adjustable driving modes and seat settings, as they lack the ability to automatically adapt settings based on individual driver habits.

Innovation Solution

A system utilizing an on-board controller with a CPU and memory to identify specific drivers and automatically adjust vehicle settings such as audio, HVAC, mode selector, and suspension systems by learning and memorizing their preferences over time, with options for driver confirmation and override features.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If automatic seat positioning and driver-selectable driving modes are provided, then user customization capability is improved, but the system still lacks the ability to automatically adapt to individual driver habits and preferences

Engineering Contradiction:
Improveuser customization capabilityVSAvoidautomatic adaptation to driver habits
Core Design Contradiction:
Adaptability or versatilityVSExtent of automation

Solution Approach 1:

The system automatically monitors driver adjustments to vehicle functions and learns preferences without requiring manual input or programming. The controller autonomously observes when the driver adjusts functions like climate control, audio, or seat positioning, and automatically applies these learned preferences in future driving sessions, making the system self-improving and adaptive

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system continuously monitors and detects driver actions and adjustments to vehicle functions, using this feedback information to learn and update driver preferences. The controller tracks patterns in driver behavior over multiple driving sessions and uses this feedback to automatically adjust settings, creating a closed-loop learning system that improves customization over time

Inventive Principle:
Principle #23Feedback

2Measurement precision

If multiple vehicle systems are monitored and adjusted based on driver behavior, then personalization accuracy is improved, but system complexity increases

Engineering Contradiction:
Improvepersonalization accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

A single on-board system controller performs multiple functions: it monitors various vehicle systems (climate control, audio, suspension, steering), detects driver adjustments, learns preferences, and automatically applies learned settings. This multi-functional approach consolidates what could be multiple separate systems into one integrated controller, managing complexity while maintaining comprehensive personalization capability

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent combines driver identification, function monitoring, preference learning, and automatic adjustment capabilities into a unified system. The controller integrates data from multiple vehicle systems and combines this with driver behavior patterns to create a cohesive personalization system, rather than operating as separate independent systems

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS9487218B2Event sensitive learning interface
Publication Date: 2016.11.08 ATIEVA INC(US)
  • US9487218B2 patent drawing
  • US9487218B2 patent drawing
  • US9487218B2 patent drawing

AI summary

A vehicle control system is provided that is able to identify a particular driver from other potential drivers, monitor various vehicle functions, and determine if the identified driver repeatedly performs the same behavior upon activation of the car. When the control system determines that the identified driver repeats the same behavior each time the car is activated, the controller learns that behavior and associates it with the identified driver so that the learned behavior can be automatically performed, without driver interaction, when the driver is identified and the car is activated.