Abstract

Electric-vehicle technology is an emerging area offering several benefits such as economy due to low running costs. Electric vehicles can also help to significantly reduce CO2 emission, which is a vital factor for environmental pollution. Modern vehicles are equipped with driver-assistance systems that facilitate drivers by offloading some of the tasks a driver does while driving. Human beings are prone to errors. Therefore, accidents and fatalities can happen if the driver fails to perform a particular task within the deadline. In electric vehicles, the focus has always been to optimize the power and battery life, and thus, any additional hardware can affect their battery life significantly. In this paper, the design of driver-assistance systems has been introduced to automate and assist in some of the vital tasks, such as a braking system, in an optimized manner. We revamp the idea of the traditional driver-assistance system and propose a generic lightweight system based on the leading factors and their impact on accidents. We model tasks for these factors and simulate a low-cost driver-assistance system in a real-time context, where these scenarios are investigated and tasks schedulability is formally proved before deploying them in electric vehicles. The proposed driver-assistance system offers many advantages. It decreases the risk of accidents and monitors the safety of driving. If, at some point, the risk index is above a certain threshold, an automated control algorithm is triggered to reduce it by activating different actuators. At the same time, it is lightweight and does not require any dedicated hardware, which in turn has a significant advantage in terms of battery life. Results show that the proposed system not only is accurate but also has a very negligible effect on energy consumption and battery life.

Highlights

  • Internet of Things (IoT) is a well-known paradigm of ICT (Information and CommunicationTechnologies) and is attributed to the advanced connectivity of several elements, such as systems, devices, and services [1,2]

  • IoT focused on object connectivity, while the modern IoT focuses on real-time object interaction, creating a new generic term for the Internet of Things in real-time (RT-IoT) [3,4]

  • If we look at the first control task with ID task1.1, the control output scheduling algorithm executes it with 0 response time and EDF and Rate Monotonic (RM) drops it, which is indicated by −1, while Fair Emergency First (FEF) executes it after a delay of 7 ms

Read more

Summary

Introduction

Internet of Things (IoT) is a well-known paradigm of ICT There are a variety of driver-assistance systems such as adaptive headlights [10], anti-lock braking system [11], drowsiness monitoring [12], and Light Detection and Ranging (LIDAR), to name a few These systems are costly, and for each system, a certain electronic control unit (ECU) must be installed on the vehicle, which puts an extra load on the battery of the vehicle. Battery optimization has been a critical issue; a system should be designed in such a way that it should not affect the performance of the battery with this additional processing Implementing it within the road network has the potential to significantly reduce the number of crashes caused by drivers through the gradual removal of human interventions [14].

Related Work
Limitations
System Model for Task Modelling in Proposed Driver-Assistance System
Accident Risk Index Formulation
Control Scheduling
Task Analysis and Modeling Based on Safe Driving Scenarios
Rainfall
Noise Intensity
Surface Friction
Wind Speed
Blurriness Detection
Camera Images for Detecting Head Pose and Drowsiness
Brake Status
Tire Status
Car Distance
Tasks Dataset Generation
Driver-Assistance System Prototype Implementation
Control Scheduling Algorithm and Deployment of Complex Tasksets
Embedded System for Driver-Assistance System Prototype
Performance Testing
Task Missing Rate
EV Battery Impact on the Proposed Driver-Assistance System
Discussion
Conclusions
Findings
Implication for the Industry
Implication for Academia
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call