Mobile Device Sensor Fusion for Automatic Parking Location Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile devices require user input to perform functions, lacking the ability to automatically determine when a user has exited a vehicle, which limits their functionality in transitioning between driving and walking modes or performing tasks like marking a parking location.
Innovation Solution
The use of sensors in mobile devices to detect disturbances, such as loss of communication with a car computer or changes in motion, to determine an exit confidence score, allowing the device to automatically identify when a user has exited a vehicle and trigger corresponding functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If sensors are used to detect disturbances and automatically determine user exit from vehicle, then automation extent is improved, but device complexity increases
Solution Approach 1:
The patent applies multi-functionality by using existing mobile device sensors (accelerometer, gyroscope, microphone, GPS) for multiple purposes: navigation, communication, and now exit detection. The sensor fusion algorithm combines data from these existing sensors to detect vehicle exit events, avoiding additional hardware while achieving automated functionality.
Solution Approach 2:
The system performs self-service by automatically detecting when the user exits the vehicle using onboard sensors and algorithms, then autonomously marking the parking location and switching modes without requiring user input. The disturbance detection algorithm continuously monitors sensor data and automatically triggers appropriate actions based on detected patterns.
2Measurement precision
If multiple sensors are integrated to improve detection accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent merges data from multiple existing sensors (accelerometer, gyroscope, microphone, GPS) into a unified disturbance detection algorithm. By fusing these sensor inputs, the system achieves high measurement precision for exit detection while utilizing already-present hardware components rather than adding new sensors.
Solution Approach 2:
The system changes parameters by analyzing variations in sensor data patterns over time - detecting disturbances through changes in acceleration, orientation, sound levels, and GPS signal characteristics. The algorithm identifies exit events by recognizing specific parameter change patterns, achieving accurate detection through temporal and spatial parameter analysis.
3Ease of operation
If automatic functions are implemented without user input, then ease of operation is improved, but reliability may worsen due to false detections
Solution Approach 1:
The system implements feedback through continuous monitoring of sensor data and iterative refinement of the disturbance detection algorithm. The confidence score mechanism provides feedback by accumulating evidence from multiple sensor inputs over time, only triggering exit detection when the confidence threshold is met, thereby reducing false positives while maintaining ease of operation.
Solution Approach 2:
The system performs preliminary action by continuously analyzing sensor data and building a confidence score before triggering the exit detection function. This preliminary analysis phase filters out spurious signals by requiring sustained patterns across multiple sensors, ensuring reliable detection while maintaining automatic operation.
Data Source
AI summary
Methods and devices for detecting a change in a motion state of a user of a mobile device are provided. The method includes determining, based on one or more sensors of the mobile device, that the motion state of the user is a driving state, the driving state indicating that the user is inside a vehicle that is moving, monitoring, with the mobile device, the one or more sensors, determining that a new motion state is a non-driving state. The method further includes identifying a location where the user exited the vehicle using one or more of the measurements from the one or more sensors before the determining that the new motion state is the non-driving state, and identifying the location where the user exited the vehicle as corresponding to a parked location of the vehicle.