Review of Electrical and Electronic Architectures for Autonomous Vehicles:Topologies,Networking and Simulators

With the rapid development of autonomous vehicles,more and more functions and computing requirements have led to the continuous centralization in the topology of electrical and electronic(E/E)architectures.While certain Tier1 suppliers,such as BOSCH,have previously proposed a serial roadmap for E/E architecture development,implemented since 2015 with significant contributions to the automotive industry,lingering misconceptions and queries persist in actual engineering processes.Notably,there are concerns regarding the perspective of zone-oriented E/E architectures,characterized by zonal concentration,as successors to domain-oriented E/E architectures,known for functional concentration.Addressing these misconceptions and queries,this study introduces a novel parallel roadmap for E/E architecture development,concurrently evaluating domain-oriented and zone-oriented schemes.Furthermore,the study explores hybrid E/E architectures,amalgamating features from both paradigms.To align with the evolution of E/E architectures,networking technologies must adapt correspondingly.The networking mechanisms pivotal in E/E architecture design are comprehensively discussed.Additionally,the study delves into modeling and verification tools pertinent to E/E architecture topologies.In conclusion,the paper outlines existing challenges and unresolved queries in this domain.

Driver Steering Behaviour Modelling Based on Neuromuscular Dynamics and Multi‑Task Time‑Series Transformer

Driver steering intention prediction provides an augmented solution to the design of an onboard collaboration mechanism between human driver and intelligent vehicle.In this study,a multi-task sequential learning framework is developed to pre-dict future steering torques and steering postures based on upper limb neuromuscular electromyography signals.The joint representation learning for driving postures and steering intention provides an in-depth understanding and accurate modelling of driving steering behaviours.Regarding different testing scenarios,two driving modes,namely,both-hand and single-right-hand modes,are studied.For each driving mode,three different driving postures are further evaluated.Next,a multi-task time-series transformer network(MTS-Trans)is developed to predict the future steering torques and driving postures based on the multi-variate sequential input and the self-attention mechanism.To evaluate the multi-task learning performance and information-sharing characteristics within the network,four distinct two-branch network architectures are evaluated.Empirical validation is conducted through a driving simulator-based experiment,encompassing 21 participants.The pro-posed model achieves accurate prediction results on future steering torque prediction as well as driving posture recognition for both two-hand and single-hand driving modes.These findings hold significant promise for the advancement of driver steering assistance systems,fostering mutual comprehension and synergy between human drivers and intelligent vehicles.

Review and Perspectives on Human Emotion for Connected Automated Vehicles

The progression toward automated driving and the latest advancement in vehicular networking have led to novel and natural human-vehicle-road systems,in which affective human-vehicle interaction is a crucial factor affecting the acceptance,safety,comfort,and traffic efficiency of connected and automated vehicles(CAVs).This development has inspired increasing inter-est in how to develop affective interaction framework for intelligent cockpit in CAVs.To enable affective human-vehicle interactions in CAVs,knowledge from multiple research areas is needed,including automotive engineering,transportation engineering,human-machine interaction,computer science,communication,as well as industrial engineering.However,there is currently no systematic survey considering the close relationship between human-vehicle-road and human emotion in the human-vehicle-road coupling process in the CAV context.To facilitate progress in this area,this paper provides a comprehensive literature survey on emotion-related studies from multi-aspects for better design of affective interaction in intelligent cockpit for CAVs.This paper discusses the multimodal expression of human emotions,investigates the human emotion experiment in driving,and particularly emphasizes previous knowledge on human emotion detection,regulation,as well as their applications in CAVs.The promising research perspectives are outlined for researchers and engineers from different research areas to develop CAVs with better acceptance,safety,comfort,and enjoyment for users.

Mode Switching and Consistency Control for Electric-Hydraulic Hybrid Steering System

Electric-hydraulic hybrid power steering(E-HHPS)system,a novel device with multiple modes for commercial electric vehicles,is designed to realize both superior steering feel and high energy efficiency.However,inconsistent steering perfor-mance occurs in the mode-switching process due to different dynamic characteristics of electric and hydraulic components,which even threatens driving safety.In this paper,mode-switching strategy and dynamic compensation control method are proposed for the E-HHPS system to eliminate the inconsistency of steering feel,which comprehensively considers ideal assistance characteristics and energy consumption of the system.Then,the influence of disturbances on system stability is analyzed,and H_(∞)robust controller is employed to guarantee system robustness and stability.The experimental results dem-onstrate that the proposed strategy can provide a steering system with natural steering feel without apparent inconsistency and effectively minimize energy consumption.

Frequency and Reliability Analysis of Load-Bearing Composite Beams

The increasing utilization of fiber-reinforced thermoplastics(FRTPs)as a substitute for metal in load-bearing structures poses challenges related to NVH issues arising from frequency variations and reliability concerns stemming from fiber dispersion within the resin matrix.In this study,the steel automobile seat beam serves as a benchmark for comparison.FRTP beams are designed and fabricated using two distinct processes:compression molding and injection over-molding.Subsequently,their modal frequency and reliability are meticulously analyzed.Experimental investigations are conducted to explore the influence of various factors,including the combination of laminates and ribs,as well as the stacking sequence of laminates,on the modal frequency.The findings reveal that the modal frequency and vibration mode are subject to alterations based on the fiber type,beam material,and laminate stacking sequence.Notably,in comparison to the steel benchmark,the first-order frequency of the FRTP beam in this study experiences a 6.59%increase while simultaneously achieving a weight reduction of 32.42%.To assess reliability,a comprehensive analysis is performed,considering a six-fold standard deviation.This analysis yields the permissible range of fluctuation for material elastic constants,bending performance,and frequency response.Encouragingly,the FRTP beams meet the required reliability criteria.These results provide valuable insights for comprehending the stiffness-dependent response and effectively controlling structural performance when implementing FRTP for weight reduction purposes.

LLTH‑YOLOv5:A Real‑Time Traffic Sign Detection Algorithm for Low‑Light Scenes

Traffic sign detection is a crucial task for autonomous driving systems.However,the performance of deep learning-based algorithms for traffic sign detection is highly affected by the illumination conditions of scenarios.While existing algo-rithms demonstrate high accuracy in well-lit environments,they suffer from low accuracy in low-light scenarios.This paper proposes an end-to-end framework,LLTH-YOLOv5,specifically tailored for traffic sign detection in low-light scenarios,which enhances the input images to improve the detection performance.The proposed framework comproses two stages:the low-light enhancement stage and the object detection stage.In the low-light enhancement stage,a lightweight low-light enhancement network is designed,which uses multiple non-reference loss functions for parameter learning,and enhances the image by pixel-level adjustment of the input image with high-order curves.In the object detection stage,BIFPN is introduced to replace the PANet of YOLOv5,while designing a transformer-based detection head to improve the accuracy of small target detection.Moreover,GhostDarkNet53 is utilized based on Ghost module to replace the backbone network of YOLOv5,thereby improving the real-time performance of the model.The experimental results show that the proposed method significantly improves the accuracy of traffic sign detection in low-light scenarios,while satisfying the real-time requirements of autonomous driving.

In-Vehicle Network Injection Attacks Detection Based on Feature Selection and Classification

Detecting abnormal data generated from cyberattacks has emerged as a crucial approach for identifying security threats within in-vehicle networks.The transmission of information through in-vehicle networks needs to follow specific data for-mats and communication protocols regulations.Typically,statistical algorithms are employed to learn these variation rules and facilitate the identification of abnormal data.However,the effectiveness of anomaly detection outcomes often falls short when confronted with highly deceptive in-vehicle network attacks.In this study,seven representative classification algorithms are selected to detect common in-vehicle network attacks,and a comparative analysis is employed to identify the most suitable and favorable detection method.In consideration of the communication protocol characteristics of in-vehicle networks,an optimal convolutional neural network(CNN)detection algorithm is proposed that uses data field characteristics and classifier selection,and its comprehensive performance is tested.In addition,the concept of Hamming distance between two adjacent packets within the in-vehicle network is introduced,enabling the proposal of an enhanced CNN algorithm that achieves robust detection of challenging-to-identify abnormal data.This paper also presents the proposed CNN classifica-tion algorithm that effectively addresses the issue of high false negative rate(FNR)in abnormal data detection based on the timestamp feature of data packets.The experimental results validate the efficacy of the proposed abnormal data detection algorithm,highlighting its strong detection performance and its potential to provide an effective solution for safeguarding the security of in-vehicle network information.

Analysis and Optimization of Transient Mode Switching Behavior for Power Split Hybrid Electric Vehicle with Clutch Collaboration

The power split hybrid electric vehicle(HEV)adopts a power coupling configuration featuring dual planetary gearsets and multiple clutches,enabling diverse operational modes through clutch engagement and disengagement.The multi-clutch configuration usually involves the collaboration of two clutches during the transient mode switching process,thereby substantially elevating control complexity.This study focuses on power split HEVs that integrate multi-clutch mechanisms and investigates how different clutch collaboration manners impact the characteristics of transient mode switching.The powertrain model for the power-split HEV is established utilizing matrix-based methodologies.Through the formulation of clutch torque curves and clutch collaboration models,this research systematically explores the effects of clutch engagement timing and the duration of clutch slipping state on transient mode switching behaviors.Building upon this analysis,an optimization problem for control parameters pertaining to the two collaborative clutches is formulated.The simulated annealing algorithm is employed to optimize these control parameters.Simulation results demonstrate that the clutch collaboration manners have a great influence on the transient mode switching performance.Compared with the pre-calibrated benchmark and the optimal solution derived by the genetic algorithm,the maximal longitudinal jerk and clutch slipping work during the transient mode switching process is reduced obviously with the optimal control parameters derived by the simulated annealing algorithm.The study provides valuable insights for the dynamic coordinated control of the power-split HEVs featuring complex clutch collaboration mechanisms.

Human-Machine Shared Lateral Control Strategy for Intelligent Vehicles Based on Human Driver Risk Perception Reliability

Intelligent vehicle(Ⅳ)technology has developed rapidly in recent years.However,achieving fully unmanned driving still presents numerous challenges,which means that human drivers will continue to play a vital role in vehicle operation for the foreseeable future.Human-machine shared driving,involving cooperation between a human driver and an automated driving system(AVS),has been widely regarded as a necessary stage for the development of IVs.Focusing onⅣdriving safety,this study proposed a human-machine shared lateral control strategy(HSLCS)based on the reliability of driver risk perception.The HSLCS starts by identifying the effective areas of driver risk perception based on eye movements.It establishes an anisotropic driving risk field,which serves as the foundation for the AVS to assess risk levels.Building upon the cumulative and diminishing effects of risk perception,the proposed approach leverages the driver's risk perception effective area and converts the risk field into a representation aligned with the driver's perspective.Subsequently,it quantifies the reliability of the driver's risk perception by using area-matching rules.Finally,based on the driver’s risk perception reliability and dif-ferences in lateral driving operation between the human driver and the AVS,the dynamic distribution of driving authority is achieved through a fuzzy rule-based system,and the human-machine shared lateral control is completed by using model predictive control.The HSLCS was tested across various scenarios on a driver-in-the-loop test platform.The results show that the HSLCS can realize the synergy and complementarity of human and machine intelligence,effectively ensuring the safety ofⅣoperation.

Curve Trajectory Model for Human Preferred Path Planning of Automated Vehicles

Automated driving systems are often used for lane keeping tasks.By these systems,a local path is planned ahead of the vehicle.However,these paths are often found unnatural by human drivers.In response to this,this paper proposes a linear driver model,which can calculate node points reflective of human driver preferences and based on these node points a human driver preferred motion path can be designed for autonomous driving.The model input is the road curvature,effectively harnessed through a self-developed Euler-curve-based curve fitting algorithm.A comprehensive case study is undertaken to empirically validate the efficacy of the proposed model,demonstrating its capacity to emulate the average behavioral pat-terns observed in human curve path selection.Statistical analyses further underscore the model's robustness,affirming the authenticity of the established relationships.This paradigm shift in trajectory planning holds promising implications for the seamless integration of autonomous driving systems with human driving preferences.

A Hierarchical LSTM-Based Vehicle Trajectory Prediction Method Considering Interaction Information

Trajectory prediction is an essential component in autonomous driving systems,as it can forecast the future movements of surrounding vehicles,thereby enhancing the decision-making and planning capabilities of autonomous driving systems.Traditional models relying on constant acceleration and constant velocity often experience a reduction in prediction accu-racy as the forecasted timeframe extends.This limitation makes it challenging to meet the demands for medium to long-term trajectory prediction.Conversely,data-driven models,particularly those based on Long Short-Term Memory(LSTM)neural networks,have demonstrated superior performance in medium to long-term trajectory prediction.Therefore,this study introduces a hierarchical LSTM-based method for vehicle trajectory prediction.Considering the difficulty of using a single LSTM model to predict trajectories for all driving intentions,the trajectory prediction task is decomposed into three sequential steps:driving intention prediction,lane change time prediction,and trajectory prediction.Furthermore,given that the driving intent and trajectory of a vehicle are always subject to the influence of the surrounding traffic flow,the predictive model proposed in this paper incorporates the interactional information of neighboring vehicle movements into the model input.The proposed method is trained and validated on the real vehicle trajectory dataset Next Generation Simulation.The results show that the proposed hierarchical LSTM method has a lower prediction error compared to the integral LSTM model.

Preface for Feature Topic on Human Driver Behaviours for Intelligent Vehicles

1 Introduction With the advancement of sensing,machine learning,and computing systems,automated driving applications have been growing rapidly worldwide.Together with the devel-opment of communication technologies such as dedicated short-range communication,extensively emerging intelli-gent vehicles have been developed to connect with vehicles,pedestrians,infrastructures,and clouds in the transportation network.Thus,intelligent vehicles have become intelligent mobile terminal that carries rich functions and services.

Mechanically Joined Extrusion Profiles for Battery Trays

In the context of electromobility,ensuring the leak tightness of assemblies is of paramount importance,particularly in bat-tery housings.Current battery housings,often featuring base assemblies crafted from extruded aluminum profiles,address the challenge of leak tightness at joints through methods like friction stir welding,a process known for its time and cost intensiveness.The aim of this study is to develop and implement a new type of extruded profile concept to produce tight base assemblies for battery housings by a longitudinal mechanical single stroke joining process.The geometry,the process and the properties of the aluminum profiles are investigated to get a joint that meets the tightness requirements and achieve high load-bearing capacities in agreement with the high homologation requirements set to vehicles with high-voltage systems.The joint is formed by means of a single stage press stroke,which eliminates the need for complex tool designs that are neces-sary for continuous joining(roll joining).Flat steel contact surfaces are used as joining tools.To evaluate the joint quality,force curves from the joining process are analyzed and the resulting joint geometries are assessed using micrographs.The resulting leak tightness of the linear joints is measured by a helium sniffer leak detector and the load-bearing capacities are investigated by shear lap and bending tests and fatigue strength test.The study also explores whether a difference in strength between the two joining partners has a positive effect on the joint properties.

Hierarchical Parking Path Planning Based on Optimal Parking Positions

Automated valet parking(AVP)has attracted the attention of industry and academia in recent years.However,there are still many challenges to be solved,including shortest path search,optimal time efficiency,and applicability of algorithm in complex scenarios.In this paper,a hierarchical AVP path planner is proposed,which divides a complete AVP path planning into the guided layer and the planning layer from the perspective of global decision-making.The guided layer is mainly used to divide a complex AVP path planning into several simple path plannings,which makes the hybrid A*algorithm more applicable in a complex parking environment.The planning layer mainly adopts different optimization methods for driving and parking path planning.The proposed method is verified by a large number of simulations which include the verification of the optimal parking position,the performance of the planner for perpendicular parking,and the scalability of the planner for parallel parking and inclined parking.The simulation results reveal that the efficiency of the algorithm is increased by more than 20 times,and the average path length is also shortened by more than 20%.Furthermore,the planner overcomes the problem that the hybrid A*algorithm is not applicable in complex parking scenarios.

On‑Ramp Merging for Highway Autonomous Driving:An Application of a New Safety Indicator in Deep Reinforcement Learning

This paper proposes an improved decision-making method based on deep reinforcement learning to address on-ramp merging challenges in highway autonomous driving.A novel safety indicator,time difference to merging(TDTM),is introduced,which is used in conjunction with the classic time to collision(TTC)indicator to evaluate driving safety and assist the merging vehicle in finding a suitable gap in traffic,thereby enhancing driving safety.The training of an autonomous driving agent is performed using the Deep Deterministic Policy Gradient(DDPG)algorithm.An action-masking mechanism is deployed to prevent unsafe actions during the policy exploration phase.The proposed DDPG+TDTM+TTC solution is tested in on-ramp merging scenarios with different driving speeds in SUMO and achieves a success rate of 99.96%without significantly impacting traffic efficiency on the main road.The results demonstrate that DDPG+TDTM+TTC achieved a higher on-ramp merging success rate of 99.96%compared to DDPG+TTC and DDPG.

A Trajectory Planning Method of Automatic Lane Change Based on Dynamic Safety Domain

Traditional research on automatic lane change has primarily focused on high-speed scenarios and has not considered the dynamic state changes of surrounding vehicles.This paper addresses this problem by proposing a trajectory planning method to enable automatic lane change at medium and low speeds.The method is based on a dynamic safety domain model,which takes into account the actual state change of surrounding vehicles,as well as the upper boundary of the safety domain for collision avoidance and the lower boundary of comfort for vehicle stability.The proposed method involves the quantification of the safety and comfort boundaries through parametric modeling of the vehicle.A quintic polynomial trajectory planning method is proposed and evaluated through simulation and testing,resulting in improved safety and comfort for automatic lane change.

Real‑Time Optimal Trajectory Planning for Autonomous Driving with Collision Avoidance Using Convex Optimization

An online trajectory planning method for collision avoidance is proposed to improve vehicle driving safety and comfort simultaneously.The collision-free trajectory for autonomous driving is formulated as a nonlinear optimization problem.A novel approximate convex optimization approach is developed for the online optimal trajectory in both longitudinal and lateral directions.First,a dual variable is used to model the non-convex collision-free constraint for driving safety and is calculated by solving a dual problem of the relative distance between vehicles.Second,the trajectory is further optimized in a model predictive control framework considering the safety.It realizes continuous-time and dynamic feasible motion with collision avoidance.The geometry of object vehicles is described by polygons instead of circles or ellipses in traditional methods.In order to avoid aggressive maneuver in the longitudinal and lateral directions for driving comfort,rates of the acceleration and the steering angle are restricted.The final formulated optimization problem is convex,which can be solved by using quadratic programming solvers and is computationally efficient for online application.Simulation results show that this approach can obtain similar driving performance compared to a state-of-the-art nonlinear optimization method.Furthermore,various driving scenarios are tested to evaluate the robustness and the ability for handling complex driving tasks.

Global Optimization‑Based Energy Management Strategy for Series–Parallel Hybrid Electric Vehicles Using Multi‑objective Optimization Algorithm

The study of series–parallel plug-in hybrid electric vehicles(PHEVs)has become a research hotspot in new energy vehicles.The global optimal Pareto solutions of energy management strategy(EMS)play a crucial role in the development of PHEVs.This paper presents a multi-objective global optimization algorithm for the EMS of PHEVs.The algorithm combines the Radau Pseudospectral Knotting Method(RPKM)and the Nondominated Sorting Genetic Algorithm(NSGA)-II to optimize both energy conservation and battery lifespan under the suburban driving conditions of the New European Driving Cycle.The driving conditions are divided into stages at evident mode switching points and the optimal objectives are computed using RPKM.The RPKM results serve as the fitness values in iteration through the NSGA-II method.The results of the algorithm applied to a PHEV simulation show a 26.74%–53.87%improvement in both objectives after 20 iterations compared to the solutions obtained using only RPKM.The proposed algorithm is evaluated against the weighting dynamic programming and is found to be close to the global optimality,with the added benefits of faster and more uniform solutions.

Thermal Runaway Characteristics and Modeling of LiFePO4 Power Battery for Electric Vehicles

LiFePO_(4)(LFP)lithium-ion batteries have gained widespread use in electric vehicles due to their safety and longevity,but thermal runaway(TR)incidents still have been reported.This paper explores the TR characteristics and modeling of LFP batteries at different states of charge(SOC).Adiabatic tests reveal that TR severity increases with SOC,and five stages are identified based on battery temperature evolution.Reaction kinetics parameters of exothermic reactions in each TR stage are extracted,and TR models for LFP batteries are established.The models accurately simulate TR behaviors at different SOCs,and the simulated TR characteristic temperatures also agree well with the experimental results,with errors of TR characteristic temperatures less than 3%.The prediction errors of TR characteristic temperatures under oven test conditions are also less than 1%.The results provide a comprehensive understanding of TR in LFP batteries,which is useful for battery safety design and optimization.

Review of Abnormality Detection and Fault Diagnosis Methods for Lithium‑Ion Batteries

Electric vehicles are developing prosperously in recent years.Lithium-ion batteries have become the dominant energy storage device in electric vehicle application because of its advantages such as high power density and long cycle life.To ensure safe and efficient battery operations and to enable timely battery system maintenance,accurate and reliable detection and diagnosis of battery faults are necessitated.In this paper,the state-of-the-art battery fault diagnosis methods are comprehensively reviewed.First,the degradation and fault mechanisms are analyzed and common abnormal behaviors are summarized.Then,the fault diagnosis methods are categorized into the statistical analysis-,model-,signal processing-,and data-driven methods.Their distinctive characteristics and applications are summarized and compared.Finally,the challenges facing the existing fault diagnosis methods are discussed and the future research directions are pointed out.