Crowd-sourced Parking Advisory System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The search for parking spots in urban areas significantly contributes to traffic congestion, and existing solutions like sensor-based systems are costly and not deployable in commercial vehicle settings.
Innovation Solution
A crowd-sourced system utilizing geolocation data and inertial sensors on mobile devices or vehicles to compute the probability of finding parking spots, providing real-time advisory services to drivers through graphical and audio interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor-based systems are deployed to detect parking spot availability, then parking information accuracy is improved, but installation and maintenance costs increase significantly
Solution Approach 1:
The patent creates a virtual copy of the physical parking environment by collecting geolocation data from mobile devices and processing it into a digital representation of parking availability. Instead of deploying physical sensors throughout the city, the system uses software-based processing of existing mobile device data to create accurate parking information, eliminating the need for expensive physical infrastructure while maintaining measurement precision.
Solution Approach 2:
The system leverages existing mobile devices that users already carry, which contain their own sensors and processing capabilities. These devices independently collect geolocation data and contribute it to the crowd-sourced network, eliminating the need for external sensor deployment and maintenance infrastructure. The mobile devices serve themselves by utilizing their built-in capabilities to participate in the parking detection system.
2Reliability
If ultrasonic sensors are mounted on vehicles to detect free spots, then real-time parking detection is improved, but device complexity and deployment feasibility worsen
Solution Approach 1:
The patent makes existing mobile devices perform multiple functions: they serve as geolocation sensors, parking detectors, and navigation aids all in one. By utilizing the existing GPS, accelerometer, and processor in standard mobile devices, the system achieves real-time parking detection without adding specialized ultrasonic sensors or complex hardware modifications to vehicles.
Solution Approach 2:
The patent replaces the mechanical sensor mounting system with a software-based solution. Instead of physically attaching ultrasonic sensors to vehicles, the system uses software algorithms that process geolocation data from mobile devices to detect parking availability, eliminating the need for mechanical installation and complex sensor hardware.
3Ease of operation
If drivers search for parking spots manually by circling city blocks, then parking spot detection capability is improved, but traffic congestion worsens
Solution Approach 1:
The system performs preliminary detection and analysis of parking availability before drivers arrive at their destination. By processing crowd-sourced geolocation data in advance and providing parking probability information ahead of time, the system enables drivers to make informed decisions about where to park, avoiding unnecessary circling and reducing traffic congestion caused by manual parking searches.
Solution Approach 2:
The system implements a feedback loop where crowd-sourced geolocation data from multiple drivers is continuously collected, processed, and used to generate real-time parking availability information. This feedback is provided back to drivers through the mobile application, enabling them to adjust their parking search behavior based on current conditions, thereby reducing traffic congestion while maintaining effective parking detection capability.
Data Source
AI summary
Architecture that employs crowd-sourced parking-related information to compute the probability of finding parking spots at specific road segments, parking lots, and/or in larger geographic areas. The crowd-sourced parking-related information can be obtained from geolocation (geographical location) traces. This approach utilizes a method of mining location traces to compute the probability of finding parking spots at specific road segments, parking lots, and/or in larger geographic areas. The location traces can be mined to classify parking areas as public, private, and semi-private (e.g., only for company employees in certain area that also include public parking areas). The location traces can be mined to infer the times and dates (e.g., hours of the day and the days of the week) during which a vehicle is allowed to park at a given location.