Self-Driving Model Personalization Using User Psychological Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing self-driving models lack personalization and often cause discomfort due to not considering individual user preferences and driving styles, leading to decreased trust and potential abandonment by users.

Innovation Solution

A method for modifying self-driving models using real-time physiological data from users to adjust driving actions, incorporating machine learning to re-train the model and align it with individual user preferences and styles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If self-driving models are modified based on feedback from users, then the overall performance of self-driving models improves, but the time required to collect feedback and modify the model increases

Engineering Contradiction:

Improveperformance of self-driving modelVSAvoidtime to collect feedback and modify model

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting sensor data continuously and pre-processing it to detect psychological states in real-time. This allows the model to be modified immediately when discomfort is detected, rather than waiting for post-drive feedback collection and analysis, thereby reducing the time delay between identifying performance issues and implementing corrections

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements continuous feedback loops where sensor data from physiological sensors provides real-time information about user psychological states. This feedback is processed immediately to detect discomfort and trigger model modifications, creating a closed-loop system that continuously improves performance without requiring lengthy external feedback collection processes

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If self-driving models are modified based on average driving styles and preferences, then the model reflects general user preferences, but the modifications may decrease perceived performance for individual users with different driving styles

Engineering Contradiction:

Improvegeneral applicability of modelVSAvoidperceived performance for individual users

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system applies local quality by detecting individual user psychological states and comfort levels in real-time, then customizing driving decisions to match that specific user's preferences and tolerance. Instead of applying uniform average preferences to all users, the model adapts its behavior locally to each user's detected state, ensuring optimal performance for each individual while maintaining overall system versatility

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system implements dynamics by making the self-driving model adaptable and changeable in real-time based on detected user psychological states. The model transitions from static average preferences to dynamic, user-specific adjustments, allowing it to evolve its behavior during operation to match individual user needs while maintaining general applicability across different users

Inventive Principle:

Principle #15Dynamics

3Productivity

If self-driving models do not take into account how different driving actions affect users, then the model can make driving decisions efficiently, but users may feel uncomfortable or not in control

Engineering Contradiction:

Improveefficiency of driving decisionsVSAvoiduser comfort and sense of control

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system implements feedback by continuously monitoring user physiological responses through sensors and using this information to adjust driving decisions. This closed-loop feedback ensures that efficiency gains from automated decision-making do not compromise user comfort, as the model receives real-time information about user reactions and adapts accordingly

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system introduces an intermediary layer between automated driving decisions and user experience by inserting psychological state detection and analysis. This intermediary processes sensor data to understand user comfort levels and mediates between efficient automated decisions and user preferences, ensuring that productivity gains do not come at the expense of user comfort

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentEP3892511B1Method and system for modifying a self-driving model

Publication Date: 2025.08.13 HARMAN INT IND INC

Figure 1
Figure 2
Figure 3

AI summary

While a self-driving model operates a vehicle, a user monitoring subsystem acquires sensor data associated with a user of the vehicle and a vehicle observation subsystem acquires sensor data associated with the vehicle. The user monitoring subsystem computes values for a psychological metric based on the sensor data associated with the user. Based on the values for the psychological metric, a feedback application determines a description of the user over a first time period. The feedback application generates a dataset based on the description and the sensor data associated with the vehicle. Subsequently, a training application performs machine learning operation(s) on the self-driving model based on the dataset to generate a modified self-driving model. Advantageously, the dataset enables the training application to automatically modify the self-driving model to account for the impact different driving actions have on the user.