Search Results

Environmental perception is a crucial subsystem in autonomous vehicles. In order to build safe and efficient traffic transportation, several researches have been proposed to build accurate, robust and real-time perception systems. Camera and LiDAR are widely equipped on autonomous self-driving cars and developed with many algorithms in recent years. The fusion system of camera and LiDAR provides state-of the-art methods for environmental perception due to the defects of single vehicular sensor. Extrinsic parameter calibration is able to align the coordinate systems of sensors and has been drawing enormous attention. However, differ from spatial alignment of two sensors’ data, joint calibration of multi-sensors (more than two sensors) should balance the degree of alignment between each two sensors.

With the increasing worldwide concern on environmental pollution, battery electrical vehicles (BEV) have attracted a lot attention. However, it still couldn’t satisfy the market requirements because of the low battery power density, high cost and long charging time. The range-extended electrical vehicle (REEV) got more attention because it could avoid the mileage anxiety of the BEVs with lower cost and potentially higher efficiency. When internal combustion engine (ICE) works as the power source of range extender (RE) for REEV, its NVH, emissions in starting process need to be optimized. In this paper, a 2-cylinder PFI gasoline engine and a permanent magnet synchronous motor (PMSM) are coaxially connected. Meanwhile, batteries and load systems were equipped. The RE co-control system was developed based on Compact RIO (Compact Reconfigurable IO), Labview and motor control unit (MCU).

The radar-based advanced driver assistance systems (ADAS) like autonomous emergency braking (AEB) and forward collision warning (FCW) can reduce accidents, so as to make vehicles, drivers and pedestrians safer. For active safety, automotive millimeter-wave radar is an indispensable role in the automotive environmental sensing system since it can work effectively regardless of the bad weather while the camera fails. One crucial task of the automotive radar is to detect and distinguish some objects close to each other precisely with the increasingly complex of the road condition. Nowadays almost all the automotive radar products work in bidimensional area where just the range and azimuth can be measured. However, sometimes in their field of view it is not easy for them to differentiate some objects, like the car, the manhole covers and the guide board, when they align with each other in vertical direction.

As the connectivity of vehicles increases rapidly, more vehicles have the capability to communicate with each other. Because Vehicular Ad-hoc NETworks (VANETs) have the characteristics of solid mobility and decentralization, traditional security strategies such as authentication, firewall, and access control are difficult to play an influential role. As a soft security method, trust management can ensure the security attributes of VANETs. However, the rapid growth of newly encountered nodes of the trust management system also increases the requirements for trust establishing mechanisms. Without a proper trust establishment mechanism, the trust value of the newly encountered nodes will deviate significantly from its actual performance, and the trust management system will suffer from newcomer attacks.

Automotive embedded DCS is widely used to solve automotive control problems. This paper presents a model-driven development technology for such systems. Models of automotive embedded DCS are built up strictly complying with the four-layer-model architecture, which is presented by Model-Driven Architecture (MDA). Three kinds of models are used to describe the protocol data structure, the algorithm process and visualization aspects of automotive embedded DCS. Corresponding XML databases are created based upon these models. As a single data source, these databases play key roles in further development phases, including generating the protocol specification, MC&D systems and embedded programming, etc. Some demonstrative applications are presented in this paper.

For high levels autonomous driving functions, the Decision Layer often takes on more responsibility due to the requirement of facing more diverse and even rare conditions. It is very difficult to accurately find a safe and efficient lane change timing when autonomous vehicles encounter complex traffic flow and need to change lanes. The traditional method based on rules and experiences has the limitation that it is difficult to be taken into account all possible conditions. Therefore, this paper designs a lane-changing decision algorithm based on data-driven and machine learning, and uses the DQN (Deep Q Network) algorithm in Reinforcement Learning to determine the appropriate lane-changing timing and target lane. Firstly, the scene characteristics of the highway are analyzed, the input and output of the decision-making model are designated and the data from the Perception Layer are processed.

Intrusion Detection Systems (IDS), technically speaking, is to monitor the network, system, and operation status according to certain security policies, and try to find various attack attempts, attacks or attack results to ensure the confidentiality, integrity and availability of network system resources. Automotive intrusion detection systems can identify and alert by analyzing in-vehicle traffic and log when software applications or devices with malicious activity exist, or the in-vehicle network is tampered and injected. But unfortunately, automotive cybersecurity researchers hardly produce a comprehensive detection method due to the confidential nature of Controller Area Network (CAN) DBC format files, which is a standard long maintained by car manufacturers. In this paper, an enhanced intrusion detection method is proposed based on the double-decision-tree to classify different attack models for in-vehicle CAN network without the need to obtain complete DBC files.

Electromagnetic compatibility of electric vehicles is withstanding great challenges because of multiple ECU and actuators distributed in vehicle. At present, researches on electromagnetic characteristics of vehicle mainly focus on rectification based on the EMC experiment, which take much time and energy. Thus, this paper adopts the way of computer simulation studying the electromagnetism model and electromagnetic characteristics of electric vehicle with following procedure. Firstly, the equivalent model of wiring harness was deduced and built. Harnesses were divided into different groups according to terminal reflection property. The equivalent unit parameter matrix was calculated to build the equivalent wiring harness. The crosstalk and radiation cases were set to check the equivalent harness method.

Lane Keeping Assistance (LKA) system is a very important part in Advanced Driver Assistance Systems (ADAS). It prevents a vehicle from departing out of the lane by exerting intervention. But an inappropriate performance during LKA intervention makes driver feel uncomfortable. The intervention of LKA can be divided into 3 parts: intervention timing, intervention process and intervention ending. Many researches have studied about the intervention timing and ending, but factors during intervention process also affect driver feelings a lot, such as yaw rate and steering wheel velocity. To increase driver’s acceptance of LKA, objective and subjective tests were designed and conducted to explore important indices which are highly correlated with the driver feelings. Different kinds of LKA controller control intervention process in different ways. Therefore, it’s very important to describe the intervention process uniformly and objectively.

Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network.

Activation loss, mass transfer loss and ohmic loss are the three main voltage losses of the polymer electrolyte membrane fuel cell. While the former two types are relevant to concentration of oxygen in catalyst layer and the later one is associated with the water content in membrane. Distributions of water content and oxygen in a single cell are inconsistent which cause that current densities in each segment of the single cell are different. For the dry inlet gas, the water in the segments near the gas inlet channel will be carried to the segments near the gas outlet channel, which causes high ohmic loss of the segments near the gas inlet channel. In this work, a transfer non-isothermal quasi-three-dimensional model is developed to investigate inconsistency of current densities.

Automotive security has become one of important topics in recent years under new automotive Electronic and Electrical Architecture (EEA). With the development of Intelligent Connected Vehicle (ICV), it has become possible to hack an automotive through in-vehicle networks. The introduction of Information Communications Technology (ICT) brings more risk threats to automotive. Researchers have shown that an attacker can easily tamper with many automotive functions via On-Board Diagnostic II (OBD-II) or In-Vehicle Infotainment (IVI). In order to protect automotive against malicious attacks, automotive security risks were analyzed and then security mechanisms based on network firewall were designed in this paper. Automotive network firewall is a security system that monitors and controls incoming and outgoing network traffics of automotive based on predetermined security rules. The main functions of network firewall include packet filter, anti-DoS and access control.

With the explosion of in-vehicle data, Time Sensitive Network (TSN) is increasingly becoming the backbone of the in-vehicle network to ensure deterministic real-time communication and Quality of Service (QoS). However, legacy buses such as CAN FD and LIN will not disappear for a long time in the future. Many protocols are deployed in the gateway and it is an important component in the security and functional safety of the communication process. In this paper, the recommended Electrical/Electronic Architecture is first given and the use cases for the TSN/CAN FD gateway are illustrated. Then, a TSN/CAN FD routing mechanism is designed and security mechanisms are deployed. The routing mechanism includes the protocol conversion module, queue cache module, and forwarding scheduling module. The protocol conversion module unpacks or packs the TSN or CAN FD frames according to the routing table.

Permanent magnet synchronous motors (PMSM) are widely used in the electric vehicles for their high power density and high energy efficiency. And the motor control system for electric vehicles is one of the most critical safety related systems in electric vehicles, because potential failures of this system can lead to serious harm to humans’ body, so normally a high automotive safety integrity level (ASIL) will be assigned to this system. In this paper, an ASIL-C motor control system based on a multicore microcontroller is presented. At the same time, due to the increasing number of connectivity on the vehicle, secure onboard communication conformed to the AUTOSAR standard is also implemented in the system to prevent external attacks.

In the automotive network architecture, the basic functions of gateway include routing, diagnostic, network management and so on. With the rapid development of connected vehicles, the cybersecurity has become an important topic in the automotive network. A spoof ECU can be used to hack the automotive network. In order to prevent the in-vehicle networks from attacking, the automotive gateway is an important part of the security architecture. A secure gateway should be able to authenticate the connected ECU and control the access to the critical network domain. The data and signals transferred between gateway and ECUs should be protected to against wiretap attacking. The purpose of this paper is to design a secure gateway for in-vehicle networks. In this paper, the designing process of the automotive secure gateway is presented. Based on the threat analysis, security requirements for automotive gateway are defined.

As a key component of in-vehicle intelligent voice technology, speech enhancement can extract clean speech signals contaminated by environmental noise to improve the perceptual quality and intelligibility of speech. It has extensive applications in the field of intelligent car cabins. Although some end-to-end speech enhancement methods based on time domain have been proposed, there is often limited consideration given to designing model architectures based on the characteristics of the speech signal. In this paper, we propose a new U-Net based speech enhancement framework that utilizes the temporal correlation of speech signals to reconstruct higher-quality and more intelligible clean speech.

The functions of modern intelligent connected vehicles are becoming increasingly complex and diverse, and software plays an important role in these advanced features. In order to decouple the software and the hardware and improve the portability and reusability of code, Service-Oriented Architecture (SOA) has been introduced into the automotive industry. Data Distribution Service (DDS) is a widely used communication middleware which provides APIs for service-oriented Remote Procedure Call (RPC) and Service-Oriented Communications (SOC). By using DDS, application developers can flexibly define the data format according to their needs and transfer them more conveniently by publishing and subscribing to the corresponding topic. However, current open source DDS protocols all use unicast communication during the transmission of user data. When there are multiple data readers subscribing to the same topic, the data writer needs to send a unicast message to each data reader individually.

The on-ramp merging driving scenario is challenging for achieving the highest-level autonomous driving. Current research using reinforcement learning methods to address the on-ramp merging problem of automated vehicles (AVs) is mainly designed for a single AV, treating other vehicles as part of the environment. This paper proposes a control framework for cooperative on-ramp merging of multiple AVs based on multi-agent deep reinforcement learning (MADRL). This framework facilitates AVs on the ramp and adjacent mainline to learn a coordinate control policy for their longitudinal and lateral motions based on the environment observations. Unlike the hierarchical architecture, this paper integrates decision and control into a unified optimal control problem to solve an on-ramp merging strategy through MADRL.