Free-positioned Smartphone Sensing for Vehicle Dynamics Estimation – Validation and Application

Paper #:
  • 2017-01-0072

  • 2017-03-28
The proliferation of smartphone application has made a great impact in the automotive industry. Smartphones contain a variety of useful sensors including cameras, microphones, as well as their Inertial Measurement Units (IMU) such as accelerometer, gyroscope, and GPS. These multi-channel signals would also be synchronized to provide a comprehensive description of driving scenarios. Therefore, the smartphone could potentially be leveraged for in-vehicle data collection, monitoring, and added safety options/feedback strategies. In our previous study, a smartphone/tablet solution with our Android App - MobileUTDrive - was developed. This platform provides a cost effective approach, which allows for a wider range of naturalistic driving study opportunities for drivers operating their own vehicles. The most meaningful reason for introducing the smartphone platform is its potential ability to be integrated with intelligent telematics services. Smartphone-based on-board sensing in the vehicle is able to capture various sources of information, including traffic (other vehicle and pedestrian movements), vehicle (diagnostics), environment (road and weather), and driver behavior information. It would be beneficial to connect this platform with ITS or V2V/V2I, share the information, and realize the concept of Internet-of-Vehicles. However, challenges of smartphone platform use in the vehicle comes from the deployment difficulty, measurement accuracy, as well as system reliability. The smartphone IMU data can be an effective estimate of vehicle dynamics, which potentially can replace direct CAN-Bus data capture. However, the orientation and relative movement of the smartphone inside the vehicle yields the main challenge for platform deployment. There are three typical positioning scenarios. First, the smartphone device could be mounted at a fixed position; a low-level calibration is needed to compensate for the mounting variance. In the second case, the device is stationary and sitting in the vehicle, but its orientation is unknown. The phone-referenced sensors reading should therefore be converted to the car-referenced dynamic outputs. In case #3, hand-held or any freestyle situation, the relative movement of the device inside the vehicle should be decoupled if it exists. This study proposes a coordinate transformation technique and a movement decouple strategy that can be applied for these scenarios. The coordinate transformation is derived as a combination of 3 rotational matrices, followed with an axis alignment step referenced with gravity and GPS speed. To decouple the relative movement between the vehicle and its inside smartphone, this study will propose a Kalman Filter based stochastic model that minimizes the mean square error between the moving and stationary device measurements. An experiment is designed to quantify the effectiveness of the proposed approach. 6 smartphones simultaneously running the same Android App are placed in a test vehicle. The positioning methods of these devices are listed in Table I. The cross-correlation between two fixed devices (#1 and #2) provides the baseline. The signals collected by other devices, before and after processed, will be compared with Device #1. The expected results will show that cross-correlations between Device #X and #1 after converting will increase, and will get closer to that of #2. Table I - Devices Placement in a Test Vehicle Device Status Orientation Placement #1 Fixed Aligned Mounted with a bracket on the windshield #2 Fixed Aligned Mounted with a bracket on the windshield #3 Stationary Not-Aligned Stayed horizontally on the seat #4 Stationary Not-Aligned Stayed vertically in the door closet #5 Moving Changing Placed in pocket #6 Moving Changing Played in hand As an application of the smartphone platform, this paper will present a case study for the driving scenarios detection. As summarized in Table II, the converted smartphone data have the capability of estimating vehicle dynamics in the lateral, longitudinal, and vertical directions. The major peak/valley distinctions can reflect the turn, stop-and-go, and up/down-hill scenarios; whereas the minor fluctuations will be the reflections of lane-change, gas/brake-hit, and bump-pass. It is worthwhile to note that scenarios caused by road conditions (e.g., bump-pass) cannot be detected from the controlling signals within the CAN-Bus data flow, which makes it an advantage for deploying the smartphone platform. Experiments will be designed to collect naturalistic driving data of these scenarios. Detection false-positives & negatives will be examined to assess the efficiency. Table II - Driving Scenarios Lateral Longitudinal Vertical Major Turn Stop-and-go Up-hill, Down-hill Minor Lane-change Gas-hit, Brake-hit Bump-pass
SAE MOBILUS Subscriber? You may already have access.
Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 36% off list price.
HTML for Linking to Page
Page URL

Related Items

Technical Paper / Journal Article
Training / Education
Training / Education
Technical Paper / Journal Article