Vehicle Speed Estimation Using IMU Signals Instead of GPS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting vehicle crashes in mobile devices rely heavily on GPS receivers, which consume significant power and shorten the device's operating time, making them undesirable for continuous use.
Innovation Solution
The method involves using sensor measurements from an inertial measurement unit (IMU) to predict vehicle speed and detect crash events, eliminating the need for GPS data by employing bandpass filtering, feature extraction, and a trained neural network to generate speed and crash predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS receivers are used for vehicle crash detection, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent segments the crash detection function into two parts: GPS provides location and speed data, while IMU provides acceleration and impact data. By dividing the detection task across multiple sensors with different power consumption characteristics, the system achieves accurate crash detection while reducing overall power usage compared to relying solely on GPS
Solution Approach 2:
The IMU acts as an intermediary sensor that complements GPS data. The system uses IMU acceleration measurements to detect crash events, reducing dependence on continuous GPS operation. This intermediary approach allows the system to maintain detection precision while managing power consumption through selective sensor activation
2Reliability
If GPS receivers operate continuously for crash detection, then reliability is improved, but duration of action decreases
Solution Approach 1:
Instead of continuous GPS operation, the system employs periodic IMU sampling at optimized intervals. The IMU continuously monitors acceleration at lower power consumption, while GPS operates periodically to provide position updates. This periodic action pattern extends operating time while maintaining sufficient detection reliability through the complementary IMU measurements
3Measurement precision
If IMU sensor measurements are processed with bandpass filtering and neural networks, then measurement precision is maintained, but device complexity increases
Solution Approach 1:
The patent applies bandpass filtering to transform IMU acceleration measurements into velocity and position estimates by changing the frequency domain parameters. The neural network further processes these transformed parameters to estimate vehicle speed. These parameter changes enable precise speed estimation from raw IMU data while managing computational complexity through optimized processing pipelines
Data Source
AI summary
A method includes receiving, from a mobile device disposed within a vehicle, a set of sensor measurements collected from an accelerometer of the mobile device during a first time period and converting the set of sensor measurements into a frequency domain. The method also includes filtering the set of sensor measurements to eliminate high frequency sensor measurements and defining a set of contiguous windows based on a remaining sensor measurements in the set of sensor measurements. Each contiguous window of the set of contiguous windows represents a contiguous portion of the remaining sensor measurements. The method further includes generating, for each contiguous window of the set of contiguous windows, a set of features by resampling the remaining sensor measurements of the contiguous window at one or more predefined frequencies and generating an estimated speed of the vehicle during the first time period using the set of features.