Dynamic Sensor Fusion for Vehicle Braking Detection Under Power Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for detecting vehicle braking events using sensor data from mobile devices are not power-efficient and often fail to notify nearby vehicles effectively.
Innovation Solution
Collecting raw sensor data from mobile devices within a vehicle using a dynamically determined polling frequency based on vehicle speed, battery status, traffic information, and weather conditions, and processing this data to detect braking events using classification machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is collected continuously at high polling frequency, then braking event detection accuracy is improved, but power consumption increases
Solution Approach 1:
The polling frequency is made dynamic rather than static, adjusting based on vehicle speed, battery status, traffic conditions, and weather. This resolves the contradiction by allowing high polling frequency (improving detection accuracy) only when necessary, while reducing frequency when conditions permit, thus balancing accuracy with power consumption.
Solution Approach 2:
The system changes the parameter of polling frequency based on multiple contextual factors. By monitoring vehicle speed, battery status, traffic information, and weather conditions, the system adapts the data collection rate to match actual needs, achieving accurate braking detection when required while conserving power during normal conditions.
2Reliability
If polling frequency is increased to improve detection accuracy, then braking event detection reliability is improved, but battery status deteriorates
Solution Approach 1:
The polling frequency dynamically adjusts based on battery status among other factors. When battery levels are low, the system reduces polling frequency to conserve power while maintaining adequate detection reliability. When battery status is good and detection reliability is needed, the system increases frequency appropriately.
Solution Approach 2:
The system modifies the polling frequency parameter in response to battery status changes. This allows the system to maintain reliable braking detection when energy is available while extending battery life and maintaining operational reliability when energy is constrained.
3Measurement precision
If data collection is performed frequently to improve detection accuracy, then braking event detection precision is improved, but data transmission volume increases
Solution Approach 1:
The polling frequency is dynamically adjusted based on traffic information and other contextual factors. This allows the system to collect data at high frequency when detection precision is critical (such as in heavy traffic or adverse weather) while reducing frequency when conditions are favorable, thereby optimizing detection precision while managing data transmission volume.
Solution Approach 2:
The system changes the data collection frequency parameter based on multiple including traffic conditions. This adaptive approach ensures high detection precision when needed while reducing unnecessary data transmission during periods when lower frequency collection suffices, balancing precision requirements with data management efficiency.
Data Source
AI summary
One or more braking event detection computing devices and methods are disclosed herein based on fused sensor data collected during a window of time from various sensors of a mobile device found within an interior of a vehicle. The various sensors of the mobile device may include a GPS receiver, an accelerometer, a gyroscope, a microphone, a camera, and a magnetometer. Data from vehicle sensors and other external systems may also be used. The braking event detection computing devices may adjust the polling frequency of the GPS receiver of the mobile device to capture non-consecutive data points based on the speed of the vehicle, the battery status of the mobile device, traffic-related information, and weather-related information. The braking event detection computing devices may use classification machine learning algorithms on the fused sensor data to determine whether or not to classify a window of time as a braking event.