Parking Preference Learning via Trajectory Analysis

Solution Overview

Problem

Drivers face challenges in finding preferred parking spaces efficiently, as existing systems require manual input of preferences or rely on autonomous vehicles to park in the first available space, which may not meet passenger preferences.

Innovation Solution

A system that automatically learns driver parking selection preferences by analyzing trajectory and attribute data from past parking events, eliminating irrelevant data, and training a decision model to recommend preferred parking candidates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the driver manually searches for preferred parking spaces, then the driver can find suitable parking according to preferences, but the time and effort required increases significantly

Engineering Contradiction:

Improveparking preference satisfactionVSAvoidtime spent searching for parking

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system automatically learns driver parking preferences by analyzing historical trajectory data and parking selection patterns without requiring manual input. The machine learning model self-trains on observed driver behavior to autonomously generate personalized parking recommendations, eliminating the need for drivers to manually search or explicitly define preferences.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary learning and analysis of driver preferences in advance by processing historical parking data. The machine learning model is trained beforehand on accumulated trajectory and selection data, so that when parking recommendations are needed, the system already has a prepared understanding of driver preferences ready to generate instant recommendations.

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If autonomous vehicles park in the first available space or predetermined zone, then parking is handled automatically, but the passenger preferences are not satisfied

Engineering Contradiction:

Improveautomated parking handlingVSAvoidpassenger preference satisfaction

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system automatically learns driver parking preferences by analyzing historical trajectory data and parking selection patterns without requiring manual input. The machine learning model self-trains on observed driver behavior to autonomously generate personalized parking recommendations, eliminating the need for drivers to manually search or explicitly define preferences.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system continuously learns from historical parking event data, using feedback from actual driver selections and trajectory patterns to refine and update the machine learning model. This feedback loop enables the system to improve its understanding of passenger preferences over time, making automated recommendations increasingly accurate.

Inventive Principle:

Principle #23Feedback

3Ease of operation

If the driver defines predetermined zones according to preferences, then parking can be automated, but the driver may make mistakes or spend time defining preferences

Engineering Contradiction:

Improveautomated parking handlingVSAvoidpreference definition process

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system automatically learns driver parking preferences by analyzing historical trajectory data and parking selection patterns without requiring manual input. The machine learning model self-trains on observed driver behavior to autonomously generate personalized parking recommendations, eliminating the need for drivers to manually search or explicitly define preferences.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the manual mechanical process of defining preference zones with an automated data analysis process. Instead of drivers manually drawing or specifying preference zones, the system uses machine learning algorithms to automatically analyze trajectory data and infer preferences, substituting computational analysis for manual configuration.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11631327B2Systems and methods for learning driver parking preferences and generating parking recommendations

Publication Date: 2023.04.18 TOYOTA JIDOSHA KK

AI summary

A method for automatically learning parking preferences for a driver and generating parking recommendations includes generating training data based at least in part on: 1) trajectory data indicating a trajectory of a vehicle during a plurality of parking events, each in which a driver of the vehicle selected a parking candidate from among a plurality of parking candidates, and 2) attribute data indicating attributes of each of the plurality of parking candidates, removing, from the training data, data associated with at least one available parking candidate based on one or more conditions that indicate the driver did not consider the at least one available parking candidate, and training a decision model, based on remaining training data, to estimate a preferred parking candidate for the driver from among a set of available parking candidates.