Hybrid Inference Based Scheduling Mechanism for Efficient Real Time Task and Resource Management in Smart Cars for Safe Driving

Abstract

In recent years, the focus of the smart transportation industry has been shifting towards the research and development of smart cars with autonomous control. Smart cars are considered to be a smart investment, as they promote safe driving while focusing on an alternate transportation fuel resource, making them eco-friendly too. Safe driving is one of the crucial concerns in autonomous smart cars. The major issue for the better provision of safe driving is real time tasks management and an efficient inference system for autonomous control. Real time task management is of huge significance in smart cars control systems. An optimal control system consists of a knowledge base and a control unit; where the knowledge base contains the data and thresholds for rules and the control unit contains the functionality for smart vehicle autonomous control. In this work, we propose a hybrid of an inference engine and a real time task scheduler for an efficient task management and resource consumption. Our proposed hybrid inference engine and task scheduler mechanism provides an efficient way of controlling smart cars in different scenarios such as heavy rainfall, obstacle detection, driver’s focus diversion etc., while ensuring the practices of safe driving. For the performance analysis of our proposed hybrid inference based scheduling mechanism, we have simulated a non-hybrid version with the same system constraints and a basic implementation of inference engine. For performance evaluation, CPU time utilization, tasks’ missing rate, average response time are used as performance metrics.

Design of Lightweight Driver-Assistance System for Safe Driving in Electric Vehicles

“…However, they use a system-on-chip approach and use a dedicated Electronic Control Unit (ECU), making it hard to modify and inflexible. Consequently, there is a need to have a consolidated application to perform similar actions as ADAS in a low-cost and flexible way [23,24]. The main difference is that, if modern technologies such as edge computing and RT-IoT are considered in the design of EVs, they can help in offloading the system-on-chip ECUs.…”

“…The main difference is that, if modern technologies such as edge computing and RT-IoT are considered in the design of EVs, they can help in offloading the system-on-chip ECUs. It has been suggested in these studies that it is quite possible to model an autonomous EV as an RT-IoT system [13,24]. It is envisioned that modern EVs are real-time IoT systems with the constraint of energy and battery.…”

“…These patterns trigger specific tasks that can be performed by actuators. The use of rule engines such as Drools to intelligently predict some actions based on the sensing data is being witnessed in modern research studies on autonomous EVs [24]. The tasks, if ensured to guarantee their deadline, can assist drivers without the need to deploy expensive ADAS hardware.…”

Effective Selection of Entities From Heterogeneous and Large Resources Using a Cooperative Neuro-Fuzzy System

“…The inference mechanism chosen here follows the standard backward chaining approach. The inference can also be developed using forward chaining or hybrid chaining techniques on need (Malik, Ahmad, Kim, Park, & Kim, 2019).…”

Reinforcement Learning Based Passengers Assistance System for Crowded Public Transportation in Fog Enabled Smart City

“…Moreover, in autonomous smart cars the emergency situation needs a priority based decision making. Similar issue is addressed in [16] with flexible parameter setting system, considering constrains from different IoT systems on a vehicle and built an inference based earliest deadline scheduling mechanism i.e., Fair Emergency First (FEF) algorithm. On the other hand, the authors in [17] have collected CCTV image data from the Singapore Public Transportation Company and have analyzed the data using a CNN based model to classify the crowd density in individual train cabins and to identify the vacant cabins and avoid overcrowding in a single cabin near to the escalators in the boarding trains.…”