Intelligent Car Research Articles

A Novel Light-Weight Machine Learning Classifier for Intrusion Detection in Controller Area Network in Smart Cars

The automotive industry has evolved enormously in recent years, marked by the proliferation of smart vehicles furnished with avant-garde technologies. These intelligent automobiles leverage cutting-edge innovations to deliver enhanced connectivity, automation, and convenience to drivers and passengers. Despite the myriad benefits of smart vehicles, their integration of digital systems has raised concerns regarding cybersecurity vulnerabilities. The primary components of smart cars within smart vehicles encompass in-vehicle communication and intricate computation, in addition to conventional control circuitry. In-vehicle communication is facilitated through a controller area network (CAN), whereby electronic control units communicate via message transmission across the CAN-bus, omitting explicit destination specifications. This broadcasting and non-delineating nature of CAN makes it susceptible to cyber attacks and intrusions, posing high-security risks to the passengers, ultimately prompting the requirement of an intrusion detection system (IDS) accepted for a wide range of cyber-attacks in CAN. To this end, this paper proposed a novel machine learning (ML)-based scheme employing a Pythagorean distance-based algorithm for IDS. This paper employs six real-time collected CAN datasets while studying several cyber attacks to simulate the IDS. The resilience of the proposed scheme is evaluated while comparing the results with the existing ML-based IDS schemes. The simulation results showed that the proposed scheme outperformed the existing studies and achieved 99.92% accuracy and 0.999 F1-score. The precision of the proposed scheme is 99.9%, while the area under the curve (AUC) is 0.9997. Additionally, the computational complexity of the proposed scheme is very low compared to the existing schemes, making it more suitable for the fast decision-making required for smart vehicles.

Construction of virtual test scenarios for intelligent car-pedestrian interaction

Aiming at the needs of intelligent car and pedestrian interaction testing under urban conditions, this paper proposes a scenario generation method that comprehensively considers the frequency of scenarios in the real world and the degree of challenge to human-vehicle interaction performance. First, according to the key features of intelligent car and pedestrian interaction, the original scene data of pedestrians crossing the road is extracted from the natural driving dataset; then, according to the needs of accelerated testing, a key scenario extraction method based on importance sampling theory is designed to extract and construct important scenarios for intelligent car-pedestrian interaction testing from the original scenes; finally, by comparing the data distribution of important scenarios with original scenarios, it is shown that this method can effectively screen out scenarios that may challenge safety performance during driving, thereby realizing accelerated testing, while taking into account the statistical characteristics of the test scenarios.

Full‐vdW Heterosynaptic Memtransistor with the Ferroelectric Inserted Functional Layer and its Neuromorphic Applications

AbstractThe emergence of 2D van der Waals (vdW) materials, owing to highly tunable electrical conductivity, remarkably free stackability, and excellent compatibility for heterojunction integration, has provided abundant research diversity of artificial synapses. Here, an innovative 2D vdW heterosynaptic memtransistor (vdW‐HT) synapse is proposed with a ferroelectric CuInP2S6 inserted layer. Neuromorphic synaptic weight change of the vdW‐HT synapse in this work are modulated by the synergistic effects of interlayer coupling and ferroelectric polarization reversal. It is the first time to evaluate the required initial energy consumption of ferroelectric vdW‐HT synapses with matrixed biomimetic characteristics of “Learning–Forgetting–Re‐learning–Memorizing.” The required initial energy consumption is only ≈3.06 pJ, which provided supporting evidence to indicate the promising potential of vdW‐HT synapses in exploring neuromorphic applications. A vdW‐HT computing system with artificial recognition capability for intelligent automobiles is established and demonstrated outstanding recognition abilities for multiple targets in various environments. The highest recognition accuracy for pedestrians is 98%. In addition, the excellent recognition property is integrated with a robotic arm, successfully achieving high‐precision grasping behavior and designated position transmission for identified targets. These results provide promising strategies for the integrated development of emerging neuromorphic electronics and industrial applications.

High accuracy line following intelligent car based on infrared sensor

This research aims to describe the design and construction of a line-following intelligent automobile using the TM4C123GH6PZ microcontroller as the central processing unit. The vehicle uses two MG310P20_7 motors, one motor driver circuit and a 12-gray sensor for propulsion, motor control and line detection. The sensors made the high-accuracy angler movement in tests, the vehicle is 91.85% stabile to follow the line, taking an average of 3.44 seconds to complete a 3-meter road. Therefore, this concept demonstrates how infrared sensors and sophisticated control algorithms can be used to be more stable in creating driverless vehicles.

Application of Adaptive Fuzzy Algorithm in Single-Chip Microcomputer Control System

Objective: In practical application, an SCM control system needs to respond to user instructions quickly and accurately, and at the same time needs to have robustness and adaptability to adapt to complex and changeable environments and working states. Therefore, how to improve the control accuracy and stability of SCM control systems, and how to adapt to the change of different working environments and working states, has become one of the important issues in the design and research of SCM control systems. Methods: Adaptive fuzzy algorithm, as a new control algorithm, has the advantages of simple structure, easy implementation and high precision, and has been widely used in many fields. On the basis of three kinds of fuzzy logic system framework, this paper analyzes the self-adaptive fuzzy algorithm single-chip microcomputer control system and carries on the corresponding performance test of the system by constructing an intelligent car. The testability test of single-chip microcomputer detection, hardware detection, algorithm recognition rate and system control rate is tested, respectively, to ensure the normal operation of the system. Conclusion: The microcontroller control system of fuzzy algorithm system is compared with that of traditional algorithm system in many aspects. The average error rate of the traditional algorithm system is 2%, while the average error rate of the fuzzy algorithm system is 0.8%. In other aspects, the fuzzy algorithm system is superior to the traditional system. For example, the fuzzy algorithm system has a 100% instruction recognition rate and a data processing speed of up to 1 second. According to the characteristics and requirements of the single-chip microcomputer control system, applying the adaptive fuzzy algorithm to the design of a single-chip microcomputer control system can effectively improve the control precision and stability of thesystem.

Multi-agent Iot-based System for Intelligent Vehicle Traffic Management Using Wireless Sensor Networks

Aims: Integrated computing technologies such as the Internet of Things (IoT), Multi- Agent Systems (MAS), and automatic networking to deliver Internet of Vehicles (IoV) applications. Methodology: The main objective of this paper is to combine MAS with IoT or IoV a new paradigm within its Cypher Physical System (CPS) for intelligent car applications. We proposed the MAS algorithm and applied it to control traffic lights at multiple intersections. When using MAS together with scattered computing architectures, IoV can achieve higher efficiency. The proposed combination is based on the independent knowledge, adaptability, assertiveness, and responsiveness that can be used in wireless sensor paradigms to bring new remedies. Smart products will explore further advancements and diverse mobility capabilities. Results: IoT provides an appropriate atmosphere for connecting with MAS concepts and programs in addition to providing reliable, adaptable, efficient, and intelligent solutions in the automotive network. In addition, the combination of MAS with IoT and cognitive conditions could result in scalable, automated, and smart wireless sensor solutions. Conclusion: We conduct experiments on three different datasets, and the results demonstrate that MAS outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time.

Analyzing traffic conflict scenarios and safety assessment in the context of intelligent vehicles: A research review

The several internal disputes and various types of traffic accidents at an urban crossroads make for a complex traffic scenario. Because accident data and crash-based methodologies are limited, researchers are now examining other safety measures, including traffic conflicts that do not depend on crashes. To better assess road safety in the decades to come new real-time data is essential. The automobile industry is heading toward intelligent cars with the goal of enhancing road safety. Although there is a common failure mechanism between accidents and traffic conflicts during driving, which makes it possible to apply crash frequency and severity estimates to traffic conflict frequency and severity models, predicting traffic conflicts presents distinct difficulties. This study discusses conceptual and methodological concerns while reviewing research papers on traffic disputes as safety measures. It offers a thorough synopsis of previous research from the viewpoint of intelligent vehicles. It explains that there are three primary categories into which the perception technology of intelligent cars may be separated: perception technology, communication technology, and the combination of perception and communication technologies. The paper emphasizes the need of harmonizing international safety standards as well as the role that governments and regulatory agencies play in guaranteeing the security of intelligent vehicles. It highlights the need for additional research on transport conflict modeling techniques and offers practical recommendations for future study.

Vehicular ad-hoc security improvements using decentralised consensus blockchain

For safer roads, a more efficient driving experience, and protection against attackers, the intelligent cars communicate with one another or with the roadside unit (RSU). The fundamental security requirements of Vehicular Ad-hoc Networks (VANETs) must be nonrepudiable, genuine, and incorporate these three. Additionally, protecting against attackers should be done in particular specific situations. However, the VANET's main disadvantages are its centralized design and the absence of procedures for ensuring confidentiality and privacy. In this paper, proposed decentralised consensus blockchain architecture for VANET that uses blockchain technology to address these problems. The VANET no longer needs a central authority or third-party administration thanks to the introduction of the blockchain. In order to ensure data integrity and accelerate up system processing, the hash value of the pseudonyms will be recorded on the blockchain. By eliminating trust difficulties between the entities, this effectively addresses challenges that arise in centralised designs. The suggested method for VANETs security. Experimental investigation demonstrates that the provided architecture outperforms the available options in terms of security enhancement.

A Mixed-Criticality Traffic Scheduler with Mitigating Congestion for CAN-to-TSN Gateway

The network architecture that Time-Sensitive Networking (TSN) is used as the backbone network and the Controller Area Network (CAN) serves as the intra-domain network is considered as the CAN-TSN interconnection network architecture, which has gained considerable attention within industrial embedded networks, such as spacecraft, intelligent automobiles, and factory automation. The architecture employs the CAN-TSN gateway as a central hub for transmitting and managing a significant volume of communications between the CAN domains and TSN. However, the CAN-TSN gateway faces a high congestion challenge due to the rapid growth in data volume, making it difficult to effectively support different time planning mechanisms provided by TSN. In this paper, we propose a two-stage mixed-criticality traffic scheduler. The scheduler in the first stage adopts a Message Optimization Algorithm (MOA) to aggregate multiple CAN messages into a single TSN message (including the aggregation of critical and non-critical CAN messages), which reduces the number of CAN messages requiring transmission. In the second stage, the scheduler proposes a Message Scheduling Optimization Algorithm (MSOA) to schedule critical TSN messages. This algorithm reassembles all the critical CAN messages (within the un-schedulable TSN messages) to generate new TSN messages for rescheduling. Experimental results show that our proposed scheduler effectively improves the acceptance ratio of critical and non-critical CAN messages and outperforms the state-of-the-art message scheduling method in terms of acceptance ratio while improving the bandwidth utilization and the number of schedule table entries. We further construct a hardware platform to evaluate the performance of MSOA. The consistency between practical results and theoretical results shows the effectiveness of MSOA.

Smart solutions in car dashboard interfaces as a response to needs of drivers and their assessment

Current trends in the production of passenger cars focus on the development of the so-called intelligent cars, richly equipped with multimedia systems with uninterrupted access to the Internet, connected to digital road infrastructure leading to autonomous driving in the future. Such changes lead to the development of new solutions and testing them, first in laboratory conditions, and then in practical use with the participation of consumers, and especially drivers. Vehicle designers are guided by the idea of simplifying vehicle interfaces’ operation and making them more comfortable and easier to use, while maintaining safety standards for traveling people and other road users. However, the question arises whether they actually achieve the expected results. The authors of the work focused on selected solutions and on assessing the validity of using such solutions in terms of convenience and safety. Various factors influencing drivers' driving behavior were discussed, mainly related to media handling. The research was based on a survey questionnaire containing a number of questions addressed to people using particular systems. Vehicle users expressed their opinions on three solutions available on the market used in car cockpits (ASD – analogue switch dashboards, GSD – gesture/speech controlled dashboards, and TSD – touch screen dashboards). The analysis of the collected data made it possible to clarify the extent to which the use of the car cockpit is adapted to the actual needs of the users. In order to qualitatively evaluate the research results, correspondence and decision tree analyzes were used. The obtained results indicate significant differences in the assessment of communication interface solutions in groups of respondents due to different grouping variables.

ChatGPT-powered Inquiry-based Learning Model of Training for Intelligent Car Racing Competition

ChatGPT-powered Inquiry-based Learning Model of Training for Intelligent Car Racing Competition

An Infrared Obstacle Avoidance Car Based on STM32

With the rapid development and wide application of artificial intelligence technology, the function of intelligent obstacle avoidance vehicle is becoming increasingly prominent. This article presents a design and realization method of infrared obstacle avoidance intelligent car based on STM32 MCU. The design is driven by two DC motors as main power sources. The motor drive circuit adopts L298N driver chip to control the DC motor to achieve the purpose of controlling the trolley. The infrared obstacle-avoidance sensor is used to judge obstacles and road conditions, and the distance between the car and obstacles is monitored in real time. The error caused by external physical condition can be eliminated by the calibration and optimization of the infrared obstacle avoidance module and the program of the single-chip microcomputer, so as to achieve the goal of accurate location of obstacles.

Cognitive task analysis-driven intelligent steering wheel interaction design

With the increasing levels of intelligence and automation, the relationship between humans and vehicles has evolved from a utilitarian perspective to a partnership. Among the crucial factors for enhancing user experiences are the analysis of driving tasks, the construction of user needs models, and the design of intelligent interfaces. Based on this background, this paper proposes a cognitive task analysis model using intelligent steering wheel information interaction design as the vehicle. The model aims to extract key design elements to assist designers in making design decisions, thereby improving the human-machine cooperation performance of intelligent automobiles and enhancing user perceptual experiences. Firstly, within the context of human-machine cooperation systems, a cognitive task analysis method integrating the SRK model is proposed. By analyzing the behavioral decision characteristics between the vehicle and the user, a framework for the human-machine interface (HMI) logic of the steering wheel and a dynamic layout prototype are established. Secondly, the design of the steering wheel’s HMI interaction is based on an analysis of users’ affective needs and rational physiological characteristics. This paper integrates the analysis of users’ affective needs to identify design elements that align with a high level of user satisfaction. Lastly, the design methodology model is applied to a navigation scenario, resulting in the creation of a steering wheel HMI prototype within a human-machine cooperation system. The prototype is then subjected to a combined subjective and objective experimental analysis, thereby validating the superiority of the steering wheel HMI’s detection indicators over those of the central control HMI and establishing the design pattern for the steering wheel HMI.

Control of an intelligent car based on OpenMV perception

This project presents an intelligent car system based on machine vision, which enables the car to perform a series of tasks through visual perception. The project utilizes an OpenMV camera and an Arduino microcontroller board, where the OpenMV camera captures and preprocesses images, and the processed data is then transmitted to the Arduino for further processing and recognition. In addition, the project incorporates the GoogleNet network for training and classifying the preprocessed images. The network is used to recognize common objects, and the model is optimized and tested accordingly. The results demonstrate a high accuracy in image recognition, making it applicable to visual perception in vehicles.

Intelligent Car Cockpit Comfort Evaluation Model Based on SVM

Intelligent Car Cockpit Comfort Evaluation Model Based on SVM

Solving reliability issues during the transition to highly intelligent road transport

Since the operation stage is the longest of all life cycle stages, it is in the corporate service system that strategies are implemented to find possible causes of failures of automotive equipment. To collect information about failures, a defect codifier was used, which simplifies the analysis of the causes of failures and planning a car maintenance strategy. During the FMEA analysis of the activity of the car center in question, a service process flow map, a PFMEA matrix, and a plan for the implementation of key corrective measures were developed. Keywords highly intelligent cars, reliability, claims analysis, FMEA analysis

High-Performance Hydrogel Sensors Enabled Multimodal and Accurate Human-Machine Interaction System for Active Rehabilitation.

Human-machine interaction (HMI) technology shows an important application prospect in rehabilitation medicine, but it is greatly limited by the unsatisfactory recognition accuracy and wearing comfort. Here, this work develops a fully flexible, conformable, and functionalized multimodal HMI interface consisting of hydrogel-based sensors and a self-designed flexible printed circuit board. Thanks to the component regulation and structural design of the hydrogel, both electromyogram (EMG) and forcemyography (FMG) signals can be collected accurately and stably, so that they are later decoded with the assistance of artificial intelligence (AI). Compared with traditional multichannel EMG signals, the multimodal human-machine interaction method based on the combination of EMG and FMG signals significantly improves the efficiency of human-machine interaction by increasing the information entropy of the interaction signals. The decoding accuracy of the interaction signals from only two channels for different gestures reaches 91.28%. The resulting AI-powered active rehabilitation system can control a pneumatic robotic glove to assist stroke patients in completing movements according to the recognized human motion intention. Moreover, this HMI interface is further generalized and applied to other remote sensing platforms, such as manipulators, intelligent cars, and drones, paving the way for the design of future intelligent robot systems.

The pricing strategies behind New Energy Vehicles price war: Taking Tesla and XPeng as examples

With the acceleration of the new energy vehicle industry, many automobile companies have entered the market and formed a competitive situation. Tesla, as the leader of the initial producer of energy storage equipment and new energy vehicles, further lowered the price at the beginning of the year and had a great impact on the price war of new energy vehicles. XPeng, an AI+Internet-based intelligent car manufacturer, followed Tesla’s pace in the price war. However, it can be found that XPeng’s revenue level is not up to expectations after the price reduction, while Tesla’s sales are increasing annually and its market share occupies the forefront. Therefore, the success of Tesla and the pricing strategy factors behind it can help XPeng, an emerging domestic automobile brand, find the current bottleneck and provide an important reference value for future development. This paper analyzes the development status of Tesla and XPeng and three factors affecting prices through case comparison. The study found that Tesla and XPeng differ in managerial decisions and production factors. XPeng has higher supply chain costs, no emerging battery technology, limited brand positioning, and insufficient demand. Hence, changes need to be made to enhance XPeng’s competitiveness.

Analysis of Energy Consumption Optimization for Shared Cache Conflicts

Multi-core shared cache conflict constraint technology for low energy consumption and low latency can be widely applied in various industries such as intelligent automobiles, aviation, aerospace, medical, industrial control, etc., and has important application backgrounds. This paper analyzes the energy consumption optimization method for multi-core shared cache conflict constraints, providing important reference for energy consumption optimization research under shared resource conflicts and promoting the development of multi-core industries.

Review on Advanced Obstacle Avoidance Techniques for Arduino-based Intelligent Vehicles

Abstract: Robotics is a rapidly expanding and fascinating field in the modern world. Because of its high level of intelligence, a smart car can utilize all of the available space. This thesis presents the design and execution of a self-driving, obstacle-avoiding Smart Car that uses an ultrasonic wave sensor. The goal of the project is to create a Smart Car that can move around obstacles by employing ultrasonic sensors. To carry out the needed procedure, an ATmega328 microcontroller is employed. A machine that can work automatically or with instruction is referred to as a smart car. The proposal suggests a smart car that can selfsteer when an impediment is in its way since it has intelligence built into it. A microcontroller from the AT mega 328 series was used to construct this Smart Car vehicle. Any obstruction in front of it is detected by an ultrasonic sensor, which then sends an instruction to the microcontroller. The microcontroller instructs the Intelligent Car to travel in a different direction based on the signal that it receives by activating the motors that are connected to it by a motor driver. The roadblock avoidance distance may be calculated by emitting pulses. We can simultaneously manage the steering to carry out the function of obstacle avoidance. The Smart Car has rear wheel drive and front axle steering. Two electric motors using gear reduction systems power two driving tires. Using an Arduino MCU microchip as the brains of the Smart Car's control system. We construct our Smart Car platform while achieving positive experimental results through the design for both the software and the hardware systems.