Driving Behavior Analysis through CAN Bus Data in an Uncontrolled Environment

Abstract

Cars can nowadays record several thousands of signals through the CAN bus technology and potentially provide real-time information on the car, the driver and the surrounding environment. This paper proposes a new method for the analysis and classification of driver behavior using a selected subset of CAN bus signals, specifically gas pedal position, brake pedal pressure, steering wheel angle, steering wheel momentum, velocity, RPM, frontal and lateral acceleration. Data has been collected in a completely uncontrolled experiment, where 64 people drove 10 cars for or a total of over 2000 driving trips without any type of pre-determined driving instruction on a wide variety of road scenarios. We propose an unsupervised learning technique that clusters drivers in different groups, and offers a validation method to test the robustness of clustering in a wide range of experimental settings. The minimal amount of data needed to preserve robust driver clustering is also computed. The presented study provides a new methodology for near-real-time classification of driver behavior in uncontrolled environments.

Extracting Vehicle Sensor Signals from CAN Logs for Driver Re-identification

“…For the field test, by only applying cepstral analysis on pedal signals the identification rate was down to 76.8% (276 drivers). Fugiglando et al Fugiglando et al (2018) developed a new methodology for near-real-time classification of driver behavior in uncontrolled environments, where 64 people drove 10 cars for a total of over 2000 driving trips without any type of predetermined driving instruction. Despite their advance use of unsupervised machine learning techniques they conclude that clustering drivers based on their behavior remains a challenging problem.…”

“…For driver re-identification, similarly to previous works (Fugiglando et al, 2018;Miyajima et al, 2007), we use a separate classifier that is trained on the already extracted signals of the car. This classifier learns the distinguishing features of different drivers (and not that of signals like the first classifier) using the signals produced during their drives.…”

Accelerating Automotive Analytics: The M2DC Appliance Approach

“…In particular, data-driven machine learning algorithms became one of the promising solutions due to the increasing volume of data gathered by sensors. Nevertheless, there are two relevant limitations in most of the previous works: they rely on input data mainly retrieved with invasive methodologies [9,11,18] and they leverage supervised techniques [9,18,24] (e.g., SVM, Random Forest Classifier, Neural Network). The former requires the reading from the vehicle Electronic Computed Board or the CAN bus, leading to compatibility issues between different car manufactures and safety-related concerns.…”

CoDR: Correlation-Based Data Reduction Scheme for Efficient Gathering of Heterogeneous Driving Data

“…Deep learning for autonomous driving needs to handle several challenges, and among them, a mountainous challenge is data acquisition, labeling and management [7]. For this purpose, many researches gather various driving data from cameras, OBD (nn-board diagnostics)-II, smartphones and external sensors [8][9][10][11]. Additionally, leading companies such as Tesla, Google and Baidu announced that they collect a large amount of driving data and are willing to release some datasets for autonomous driving studies [12,13].…”