Vehicle Parking Tracking Using Steering Angle and Event Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems face challenges in processing and analyzing high-volume vehicle location event data in real-time, particularly in accurately tracking vehicle journeys and determining parking locations within multi-level parking lots, due to latency and GPS data accuracy issues.
Innovation Solution
A system and method utilizing a processor to determine parking lot geometry, receive vehicle event data including speed and steering angle, and track vehicle movement to determine parking location, using predetermined relationships between steering angles, heading changes, and gear shifts to accurately identify floor transitions and vehicle location, even with poor GPS accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional systems process high-volume vehicle location event data, then data processing capacity is improved, but latency increases and real-time analysis capability deteriorates
Solution Approach 1:
The system segments vehicle location event data into discrete events (e.g., trip start, trip end, parking events) and processes them through specialized algorithms that identify patterns and transitions. This segmentation allows the system to handle high-volume data (600,000 records per second) while maintaining low latency by processing only relevant event transitions rather than every individual data point.
Solution Approach 2:
The system pre-processes vehicle event data to identify and flag significant events (trip starts, trips ends, parking maneuvers) before detailed analysis. By performing preliminary filtering and event detection, the system prepares data for rapid real-time analysis, reducing latency when actual parking location determination is needed.
2Device complexity
If GPS data is used to determine vehicle location in multi-level parking lots, then location tracking is simplified, but measurement precision deteriorates due to poor GPS accuracy
Solution Approach 1:
The system introduces intermediate variables (steering angle, gear shift data, vehicle speed) as mediators between GPS location data and final parking location determination. These intermediate variables provide additional context about vehicle maneuvering behavior, allowing the system to accurately infer parking locations and floor transitions even when GPS accuracy is poor in multi-level parking structures.
Solution Approach 2:
The system changes from relying solely on spatial parameters (GPS coordinates) to incorporating temporal and behavioral parameters (steering angle over time, gear shift sequences, speed patterns). This multi-parameter approach enables accurate location determination by analyzing the pattern and duration of steering inputs and vehicle state transitions, compensating for GPS signal degradation in parking lots.
3Loss of time
If vehicle event data is processed in real-time to identify parking events, then response time is improved, but computational complexity increases
Solution Approach 1:
The system applies different processing complexity to different data contexts: simple threshold-based detection for basic trip events, and more complex pattern recognition algorithms specifically for parking event identification. By localizing computational intensity to where it is most needed (parking maneuver detection using steering angle and gear data), the system achieves real-time response without uniformly high computational complexity across all processing.
Data Source
AI summary
A system and method is provided for determining where a vehicle has parked in a parking lot. The method includes determining a geometry for a parking lot; receiving vehicle event data including periodic vehicle event data for vehicle speed and steering angle; tracking a movement of a vehicle using the vehicle event data; and determining where a vehicle has parked using a steering angle to determine a number of turns in the parking lot geometry.