Real-Time Performance Analysis of Multiple Parameters of Automotive Sensor’s CAN Data to Predict Vehicle Driving Efficiency

Abstract

Traffic accidents usually lead to severe human casualties and huge economic losses in real-world scenarios. Timely accurate prediction of traffic accidents has great potential to protect public safety and reduce economic losses. However, it is challenging to predict traffic accidents due to the complex causality of traffic accidents with multiple interconnected sensor factors. Driving is a complex activity whose safety is influenced by a wide range of factors such as driver behavior, vehicle design and the road environment. Although many encouraging achievements have been made to improve road safety, annually 1.35 million people die and as many as 50 million are injured and experience long-term disability from road traffic crashes ("World Health Organisation report, 2018,"). The next frontier of crash prevention is in the technology space with an increasing presence of active safety technologies such as Advanced Driver Assistance Systems (ADAS). A clear understanding of different parameters impacting driver interaction with road environment to make decisions to control their vehicle can provide a new design approach for a more effective driver assistance system. To explore the most influential contributing factors, in the proposed work driving style can be analyzed with some safety features and driver-assist features to include, Antilock Braking System (ABS), Traction Control System (TCS), Electronic Stability Control (ESC), Hill Start Assist (HSA) and clutch actuation technique. In the present work, experimental analysis is conducted to evaluate the driver efficiency by using multiple vehicle safety features by acquiring corresponding multiple CAN data wirelessly using Raspberry pi with the ThingSpeak platform. The developed Wireless HMI interface will report vehicle driving patterns and fuel efficiency by giving warning notifications with safety standards to improve the driver driving style following the road environment.