Ensuring that autonomous vehicles maintain high precision and rapid response capabilities in complex and dynamic driving environments is a critical challenge in the field of autonomous driving.This study aims to enhan...Ensuring that autonomous vehicles maintain high precision and rapid response capabilities in complex and dynamic driving environments is a critical challenge in the field of autonomous driving.This study aims to enhance the learning efficiency ofmulti-sensor feature fusion in autonomous driving tasks,thereby improving the safety and responsiveness of the system.To achieve this goal,we propose an innovative multi-sensor feature fusion model that integrates three distinct modalities:visual,radar,and lidar data.The model optimizes the feature fusion process through the introduction of two novel mechanisms:Sparse Channel Pooling(SCP)and Residual Triplet-Attention(RTA).Firstly,the SCP mechanism enables the model to adaptively filter out salient feature channels while eliminating the interference of redundant features.This enhances the model’s emphasis on critical features essential for decisionmaking and strengthens its robustness to environmental variability.Secondly,the RTA mechanism addresses the issue of feature misalignment across different modalities by effectively aligning key cross-modal features.This alignment reduces the computational overhead associated with redundant features and enhances the overall efficiency of the system.Furthermore,this study incorporates a reinforcement learning module designed to optimize strategies within a continuous action space.By integrating thismodulewith the feature fusion learning process,the entire system is capable of learning efficient driving strategies in an end-to-end manner within the CARLA autonomous driving simulator.Experimental results demonstrate that the proposedmodel significantly enhances the perception and decision-making accuracy of the autonomous driving system in complex traffic scenarios while maintaining real-time responsiveness.This work provides a novel perspective and technical pathway for the application of multi-sensor data fusion in autonomous driving.展开更多
This article takes the current autonomous driving technology as the research background and studies the collaborative protection mechanism between its system-on-chip(SoC)functional safety and information security.It i...This article takes the current autonomous driving technology as the research background and studies the collaborative protection mechanism between its system-on-chip(SoC)functional safety and information security.It includes an introduction to the functions and information security of autonomous driving SoCs,as well as the main design strategies for the collaborative prevention and control mechanism of SoC functional safety and information security in autonomous driving.The research shows that in the field of autonomous driving,there is a close connection between the functional safety of SoCs and their information security.In the design of the safety collaborative protection mechanism,the overall collaborative protection architecture,SoC functional safety protection mechanism,information security protection mechanism,the workflow of the collaborative protection mechanism,and its strategies are all key design elements.It is hoped that this analysis can provide some references for the collaborative protection of SoC functional safety and information security in the field of autonomous driving,so as to improve the safety of autonomous driving technology and meet its practical application requirements.展开更多
Trajectory prediction is a critical task in autonomous driving systems.It enables vehicles to anticipate the future movements of surrounding traffic participants,which facilitates safe and human-like decision-making i...Trajectory prediction is a critical task in autonomous driving systems.It enables vehicles to anticipate the future movements of surrounding traffic participants,which facilitates safe and human-like decision-making in the planning and control layers.However,most existing approaches rely on end-to-end deep learning architectures that overlook the influence of driving style on trajectory prediction.These methods often lack explicit modeling of semantic driving behavior and effective interaction mechanisms,leading to potentially unrealistic predictions.To address these limitations,we propose the Driving Style Guided Trajectory Prediction framework(DSG-TP),which incorporates a probabilistic representation of driving style into trajectory prediction.Our approach enhances the model’s ability to interact with vehicle behavior characteristics in complex traffic scenarios,significantly improving prediction reliability in critical decision-making situations by incorporating the driving style recognition module.Experimental evaluations on the Argoverse 1 dataset demonstrate that our method outperforms existing approaches in both prediction accuracy and computational efficiency.Through extensive ablation studies,we further validate the contribution of each module to overall performance.Notably,in decision-sensitive scenarios,DSG-TP more accurately captures vehicle behavior patterns and generates trajectory predictions that align with different driving styles,providing crucial support for safe decision-making in autonomous driving systems.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
This paper introduces autonomous driving image perception technology,including deep learning models(such as CNN and RNN)and their applications,analyzing the limitations of traditional algorithms.It elaborates on the s...This paper introduces autonomous driving image perception technology,including deep learning models(such as CNN and RNN)and their applications,analyzing the limitations of traditional algorithms.It elaborates on the shortcomings of Faster R-CNN and YOLO series models,proposes various improvement techniques such as data fusion,attention mechanisms,and model compression,and introduces relevant datasets,evaluation metrics,and testing frameworks to demonstrate the advantages of the improved models.展开更多
Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning frame...Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.展开更多
Autonomous driving has witnessed rapid advancement;however,ensuring safe and efficient driving in intricate scenarios remains a critical challenge.In particular,traffic roundabouts bring a set of challenges to autonom...Autonomous driving has witnessed rapid advancement;however,ensuring safe and efficient driving in intricate scenarios remains a critical challenge.In particular,traffic roundabouts bring a set of challenges to autonomous driving due to the unpredictable entry and exit of vehicles,susceptibility to traffic flow bottlenecks,and imperfect data in perceiving environmental information,rendering them a vital issue in the practical application of autonomous driving.To address the traffic challenges,this work focused on complex roundabouts with multi-lane and proposed a Perception EnhancedDeepDeterministic Policy Gradient(PE-DDPG)for AutonomousDriving in the Roundabouts.Specifically,themodel incorporates an enhanced variational autoencoder featuring an integrated spatial attention mechanism alongside the Deep Deterministic Policy Gradient framework,enhancing the vehicle’s capability to comprehend complex roundabout environments and make decisions.Furthermore,the PE-DDPG model combines a dynamic path optimization strategy for roundabout scenarios,effectively mitigating traffic bottlenecks and augmenting throughput efficiency.Extensive experiments were conducted with the collaborative simulation platform of CARLA and SUMO,and the experimental results show that the proposed PE-DDPG outperforms the baseline methods in terms of the convergence capacity of the training process,the smoothness of driving and the traffic efficiency with diverse traffic flow patterns and penetration rates of autonomous vehicles(AVs).Generally,the proposed PE-DDPGmodel could be employed for autonomous driving in complex scenarios with imperfect data.展开更多
While traditional Convolutional Neural Network(CNN)-based semantic segmentation methods have proven effective,they often encounter significant computational challenges due to the requirement for dense pixel-level pred...While traditional Convolutional Neural Network(CNN)-based semantic segmentation methods have proven effective,they often encounter significant computational challenges due to the requirement for dense pixel-level predictions,which complicates real-time implementation.To address this,we introduce an advanced real-time semantic segmentation strategy specifically designed for autonomous driving,utilizing the capabilities of Visual Transformers.By leveraging the self-attention mechanism inherent in Visual Transformers,our method enhances global contextual awareness,refining the representation of each pixel in relation to the overall scene.This enhancement is critical for quickly and accurately interpreting the complex elements within driving sce-narios—a fundamental need for autonomous vehicles.Our experiments conducted on the DriveSeg autonomous driving dataset indicate that our model surpasses traditional segmentation methods,achieving a significant 4.5%improvement in Mean Intersection over Union(mIoU)while maintaining real-time responsiveness.This paper not only underscores the potential for optimized semantic segmentation but also establishes a promising direction for real-time processing in autonomous navigation systems.Future work will focus on integrating this technique with other perception modules in autonomous driving to further improve the robustness and efficiency of self-driving perception frameworks,thereby opening new pathways for research and practical applications in scenarios requiring rapid and precise decision-making capabilities.Further experimentation and adaptation of this model could lead to broader implications for the fields of machine learning and computer vision,particularly in enhancing the interaction between automated systems and their dynamic environments.展开更多
In this study,a machine vision-based pattern matching technique was applied to estimate the location of an autonomous driving robot and perform 3D tunnel mapping in an underground mine environment.The autonomous drivi...In this study,a machine vision-based pattern matching technique was applied to estimate the location of an autonomous driving robot and perform 3D tunnel mapping in an underground mine environment.The autonomous driving robot continuously detects the wall of the tunnel in the horizontal direction using the light detection and ranging(Li DAR)sensor and performs pattern matching by recognizing the shape of the tunnel wall.The proposed method was designed to measure the heading of the robot by fusion with the inertial measurement units sensor according to the pattern matching accuracy;it is combined with the encoder sensor to estimate the location of the robot.In addition,when the robot is driving,the vertical direction of the underground mine is scanned through the vertical Li DAR sensor and stacked to create a 3D map of the underground mine.The performance of the proposed method was superior to that of previous studies;the mean absolute error achieved was 0.08 m for the X-Y axes.A root mean square error of 0.05 m^(2)was achieved by comparing the tunnel section maps that were created by the autonomous driving robot to those of manual surveying.展开更多
In mixed and dynamic traffic environments,accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles to accomplish reasonable behavioral decisio...In mixed and dynamic traffic environments,accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles to accomplish reasonable behavioral decisions and guarantee driving safety.In this paper,we propose an integrated probabilistic architecture for long-term vehicle trajectory prediction,which consists of a driving inference model(DIM)and a trajectory prediction model(TPM).The DIM is designed and employed to accurately infer the potential driving intention based on a dynamic Bayesian network.The proposed DIM incorporates the basic traffic rules and multivariate vehicle motion information.To further improve the prediction accuracy and realize uncertainty estimation,we develop a Gaussian process-based TPM,considering both the short-term prediction results of the vehicle model and the driving motion characteristics.Afterward,the effectiveness of our novel approach is demonstrated by conducting experiments on a public naturalistic driving dataset under lane-changing scenarios.The superior performance on the task of long-term trajectory prediction is presented and verified by comparing with other advanced methods.展开更多
The study of vehicular networks has attracted considerable interest in academia and the industry.In the broad area,connected vehicles and autonomous driving are technologies based on wireless data communication betwee...The study of vehicular networks has attracted considerable interest in academia and the industry.In the broad area,connected vehicles and autonomous driving are technologies based on wireless data communication between vehicles or between vehicles and infrastructures.A Vehicle-to-Infrastructure(V2I)system consists of communications and computing over vehicles and related infrastructures.In such a system,wireless sensors are installed in some selected points along roads or driving areas.In autonomous driving,it is crucial for a vehicle to figure out the ideal routes by the communications between its equipped sensors and infrastructures then the vehicle is automatically moving along the routes.In this paper,we propose a Bezier curve based recursive algorithm,which effectively creates routes for vehicles through the communication between the On-Board Unit(OBU)and the Road-Side Units(RSUs).In addition,this approach generates a very low overhead.We conduct simulations to test the proposed algorithm in various situations.The experiment results demonstrate that our algorithm creates almost ideal routes.展开更多
In order to deeply analyze the differences in the acceptance of autonomous driving technology among different gender groups,a multiple indicators and multiple causes model was constructed by integrating a technology a...In order to deeply analyze the differences in the acceptance of autonomous driving technology among different gender groups,a multiple indicators and multiple causes model was constructed by integrating a technology acceptance model and theory of planned behavior to comprehensively reveal the gender differences in the influence mechanisms of subjective and objective factors.The analysis is based on data collected from Chinese urban residents.Among objective factors,age has a significant negative impact on women's perceived behavior control and a significant positive impact on perceived ease of use.Education has a significant positive impact on men's perceived behavior control,and has a strong positive impact on women's perceived usefulness(PU).For men,income and education are found to have strong positive impacts on perceived behavior control.Among subjective factors,perceived ease of use(PEU)has the greatest influence on women's behavior intention,and it is the only influential factor for women's intention to use autonomous driving technology,with an influence coefficient of 0.72.The influencing path of men's intention to use autonomous driving technology is more complex.It is not only directly affected by the significant and positive joint effects of attitude and PU,but also indirectly affected by perceived behavior controls,subjective norms,and PEU.展开更多
This paper is to explore the problems of intelligent connected vehicles(ICVs)autonomous driving decision-making under a 5G-V2X structured road environment.Through literature review and interviews with autonomous drivi...This paper is to explore the problems of intelligent connected vehicles(ICVs)autonomous driving decision-making under a 5G-V2X structured road environment.Through literature review and interviews with autonomous driving practitioners,this paper firstly puts forward a logical framework for designing a cerebrum-like autonomous driving system.Secondly,situated on this framework,it builds a hierarchical finite state machine(HFSM)model as well as a TOPSIS-GRA algorithm for making ICV autonomous driving decisions by employing a data fusion approach between the entropy weight method(EWM)and analytic hierarchy process method(AHP)and by employing a model fusion approach between the technique for order preference by similarity to an ideal solution(TOPSIS)and grey relational analysis(GRA).The HFSM model is composed of two layers:the global FSM model and the local FSM model.The decision of the former acts as partial input information of the latter and the result of the latter is sent forward to the local pathplanning module,meanwhile pulsating feedback to the former as real-time refresh data.To identify different traffic scenarios in a cerebrum-like way,the global FSM model is designed as 7 driving behavior states and 17 driving characteristic events,and the local FSM model is designed as 16 states and 8 characteristic events.In respect to designing a cerebrum-like algorithm for state transition,this paper firstly fuses AHP weight and EWM weight at their output layer to generate a synthetic weight coefficient for each characteristic event;then,it further fuses TOPSIS method and GRA method at the model building layer to obtain the implementable order of state transition.To verify the feasibility,reliability,and safety of theHFSMmodel aswell as its TOPSISGRA state transition algorithm,this paper elaborates on a series of simulative experiments conducted on the PreScan8.50 platform.The results display that the accuracy of obstacle detection gets 98%,lane line prediction is beyond 70 m,the speed of collision avoidance is higher than 45 km/h,the distance of collision avoidance is less than 5 m,path planning time for obstacle avoidance is averagely less than 50 ms,and brake deceleration is controlled under 6 m/s2.These technical indexes support that the driving states set and characteristic events set for the HFSM model as well as its TOPSIS-GRA algorithm may bring about cerebrum-like decision-making effectiveness for ICV autonomous driving under 5G-V2X intelligent road infrastructure.展开更多
1 Introduction Autonomous driving technology has made significant advancements in recent years.The evolution of autonomous driving systems from traditional modular designs to end-to-end learning paradigms has led to c...1 Introduction Autonomous driving technology has made significant advancements in recent years.The evolution of autonomous driving systems from traditional modular designs to end-to-end learning paradigms has led to comprehensive improvements in driving capabilities.In modular designs,driving tasks are segmented into independent modules,such as perception,decision-making,planning,and control.展开更多
Platoon-based autonomous driving is indispensable for traffic automation,but it confronts substantial constraints in rugged terrains with unreliable links and scarce communication resources.This paper proposes a novel...Platoon-based autonomous driving is indispensable for traffic automation,but it confronts substantial constraints in rugged terrains with unreliable links and scarce communication resources.This paper proposes a novel hierarchical Digital Twin(DT)and consensus empowered cooperative control framework for safe driving in harsh areas.Specifically,leveraging intra-platoon information exchange,one platoon-level DT is constructed on the leader and multiple vehicle-level DTs are distributed among platoon members.The leader first makes critical platoon-driving decisions based on the platoon-level DT.Then,considering the impact of unreliable links on the platoon-level DT accuracy and the consequent risk of unsafe decision-making,a distributed consensus scheme is proposed to negotiate critical decisions efficiently.Upon successful negotiation,vehicles proceed to execute critical decisions,relying on their vehicle-level DTs.Otherwise,a Space-Air-Ground-Integrated-Network(SAGIN)enabled information exchange is utilized to update the platoon-level DT for subsequent safe decision-making in scenarios with unreliable links,no roadside units,and obstructed platoons.Furthermore,based on this framework,an adaptive platooning scheme is designed to minimize total delay and ensure driving safety.Simulation results indicate that our proposed scheme improves driving safety by 21.1%and reduces total delay by 24.2%in harsh areas compared with existing approaches.展开更多
Learning-based algorithm attracts great attention in the autonomous driving control field,especially for decisionmaking,to meet the challenge in long-tail extreme scenarios,where traditional methods demonstrate poor a...Learning-based algorithm attracts great attention in the autonomous driving control field,especially for decisionmaking,to meet the challenge in long-tail extreme scenarios,where traditional methods demonstrate poor adaptability even with a significant effort.To improve the autonomous driving performance in extreme scenarios,specifically consecutive sharp turns,three deep reinforcement learning algorithms,i.e.Deep Deterministic Policy Gradient(DDPG),Twin Delayed Deep Deterministic policy gradient(TD3),and Soft Actor-Critic(SAC),based decision-making policies are proposed in this study.The role of the observation variable in agent training is discussed by comparing the driving stability,average speed,and consumed computational effort of the proposed algorithms in curves with various curvatures.In addition,a novel reward-setting method that combines the states of the environment and the vehicle is proposed to solve the sparse reward problem in the reward-guided algorithm.Simulation results from the road with consecutive sharp turns show that the DDPG,SAC,and TD3 algorithms-based vehicles take 367.2,359.6,and 302.1 s to finish the task,respectively,which match the training results,and verifies the observation variable role in agent quality improvement.展开更多
Autonomous driving systems(ADSs)have attracted wide attention in the machine learning communities.With the help of deep neural networks(DNNs),ADSs have shown both satisfactory performance under significant uncertainti...Autonomous driving systems(ADSs)have attracted wide attention in the machine learning communities.With the help of deep neural networks(DNNs),ADSs have shown both satisfactory performance under significant uncertainties in the environment and the ability to compensate for system failures without external intervention.However,the vulnerability of ADSs has raised concerns since DNNs have been proven vulnerable to adversarial attacks.In this paper,we present a comprehensive survey of current physical adversarial vulnerabilities in ADSs.We first divide the physical adversarial attack methods and defense methods by their restrictions of deployment into three scenarios:the real-world,simulator-based,and digital-world scenarios.Then,we consider the adversarial vulnerabilities that focus on various sensors in ADSs and separate them as camera-based,light detection and ranging(LiDAR)based,and multifusion-based attacks.Subsequently,we divide the attack tasks by traffic elements.For the physical defenses,we establish the taxonomy with reference to input image preprocessing,adversarial example detection,and model enhancement for the DNN models to achieve full coverage of the adversarial defenses.Based on the above survey,we finally discuss the challenges in this research field and provide further outlook on future directions.展开更多
End-to-end autonomous driving,with its holistic optimization capabilities,has gained increasing traction in academia and industry.Vectorized representations,which preserve instance-level topological information while ...End-to-end autonomous driving,with its holistic optimization capabilities,has gained increasing traction in academia and industry.Vectorized representations,which preserve instance-level topological information while reducing computational overhead,have emerged as promising paradigms.However,existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points,resulting in geometrically inconsistent outputs(e.g.,fragmented HD map elements or oscillatory trajectories).To address these limitations,we propose intra-instance vectorized driving transformer(InVDriver),a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers,thereby enhancing planning accuracy and trajectory smoothness.Across all core modules,i.e.,perception,prediction,and planning,InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions,enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise.The experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance,surpassing prior methods in both accuracy and safety,while maintaining high computational efficiency.展开更多
Lane detection is one of the critical tasks for autonomous driving.Earlier works revolved around semantic segmentation and object detection with a special program for lanes.However,most methods still suffer from unsta...Lane detection is one of the critical tasks for autonomous driving.Earlier works revolved around semantic segmentation and object detection with a special program for lanes.However,most methods still suffer from unstable post-processing algorithms which leads to a gap between camera input and downstream applications.In this paper,we propose a novel detection presentation form for lanes and design a simple network without any complicated post-process.Specifically,we use sampled gird points to express lane lines and construct a network for the special lane format,which is called SGPLane.Therefore,the network learns a regression branch and a confidence branch to realize end-to-end lane detection by setting the threshold confidence value.Our model is validated on the typical dataset and real-world driving scenes.Experiments on lane detection benchmarks show that our method outperforms previous methods with accuracy score of 96.845%on Tusimple dataset with high FPS and 76.85%on our real-world dataset.展开更多
This study investigates the use of autonomous vehicles in bus rapid transit lanes during the initial phases of autonomous driving development.The aim is to accelerate the advancement of autonomous driving technologies...This study investigates the use of autonomous vehicles in bus rapid transit lanes during the initial phases of autonomous driving development.The aim is to accelerate the advancement of autonomous driving technologies and enhance the efficiency of bus lane usage.We first develop a dynamic joint optimization model that adjusts autonomous vehicle speeds and bus timetables to minimize vehicle travel times while reducing bus passenger waiting times.We account for random variables such as stochastic passenger arrivals at bus stations and variable demand for autonomous vehicle travel by constructing a stochastic dynamic model.To address the computational challenges of large-scale scenarios,we implement a simulation-based heuristic algorithm framework.This framework is designed to efficiently produce high-quality solutions within feasible time limits.Our numerical studies on an actual bus line show that our approach significantly improves system throughput compared to existing benchmarks.Moreover,by strategically managing the entry of autonomous vehicles into the lane and modifying bus timetables,we further enhance the operational efficiency of the system.展开更多
文摘Ensuring that autonomous vehicles maintain high precision and rapid response capabilities in complex and dynamic driving environments is a critical challenge in the field of autonomous driving.This study aims to enhance the learning efficiency ofmulti-sensor feature fusion in autonomous driving tasks,thereby improving the safety and responsiveness of the system.To achieve this goal,we propose an innovative multi-sensor feature fusion model that integrates three distinct modalities:visual,radar,and lidar data.The model optimizes the feature fusion process through the introduction of two novel mechanisms:Sparse Channel Pooling(SCP)and Residual Triplet-Attention(RTA).Firstly,the SCP mechanism enables the model to adaptively filter out salient feature channels while eliminating the interference of redundant features.This enhances the model’s emphasis on critical features essential for decisionmaking and strengthens its robustness to environmental variability.Secondly,the RTA mechanism addresses the issue of feature misalignment across different modalities by effectively aligning key cross-modal features.This alignment reduces the computational overhead associated with redundant features and enhances the overall efficiency of the system.Furthermore,this study incorporates a reinforcement learning module designed to optimize strategies within a continuous action space.By integrating thismodulewith the feature fusion learning process,the entire system is capable of learning efficient driving strategies in an end-to-end manner within the CARLA autonomous driving simulator.Experimental results demonstrate that the proposedmodel significantly enhances the perception and decision-making accuracy of the autonomous driving system in complex traffic scenarios while maintaining real-time responsiveness.This work provides a novel perspective and technical pathway for the application of multi-sensor data fusion in autonomous driving.
文摘This article takes the current autonomous driving technology as the research background and studies the collaborative protection mechanism between its system-on-chip(SoC)functional safety and information security.It includes an introduction to the functions and information security of autonomous driving SoCs,as well as the main design strategies for the collaborative prevention and control mechanism of SoC functional safety and information security in autonomous driving.The research shows that in the field of autonomous driving,there is a close connection between the functional safety of SoCs and their information security.In the design of the safety collaborative protection mechanism,the overall collaborative protection architecture,SoC functional safety protection mechanism,information security protection mechanism,the workflow of the collaborative protection mechanism,and its strategies are all key design elements.It is hoped that this analysis can provide some references for the collaborative protection of SoC functional safety and information security in the field of autonomous driving,so as to improve the safety of autonomous driving technology and meet its practical application requirements.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant No.52267003.
文摘Trajectory prediction is a critical task in autonomous driving systems.It enables vehicles to anticipate the future movements of surrounding traffic participants,which facilitates safe and human-like decision-making in the planning and control layers.However,most existing approaches rely on end-to-end deep learning architectures that overlook the influence of driving style on trajectory prediction.These methods often lack explicit modeling of semantic driving behavior and effective interaction mechanisms,leading to potentially unrealistic predictions.To address these limitations,we propose the Driving Style Guided Trajectory Prediction framework(DSG-TP),which incorporates a probabilistic representation of driving style into trajectory prediction.Our approach enhances the model’s ability to interact with vehicle behavior characteristics in complex traffic scenarios,significantly improving prediction reliability in critical decision-making situations by incorporating the driving style recognition module.Experimental evaluations on the Argoverse 1 dataset demonstrate that our method outperforms existing approaches in both prediction accuracy and computational efficiency.Through extensive ablation studies,we further validate the contribution of each module to overall performance.Notably,in decision-sensitive scenarios,DSG-TP more accurately captures vehicle behavior patterns and generates trajectory predictions that align with different driving styles,providing crucial support for safe decision-making in autonomous driving systems.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
文摘This paper introduces autonomous driving image perception technology,including deep learning models(such as CNN and RNN)and their applications,analyzing the limitations of traditional algorithms.It elaborates on the shortcomings of Faster R-CNN and YOLO series models,proposes various improvement techniques such as data fusion,attention mechanisms,and model compression,and introduces relevant datasets,evaluation metrics,and testing frameworks to demonstrate the advantages of the improved models.
基金the financial support of the National Key Research and Development Program of China(2020AAA0108100)the Shanghai Municipal Science and Technology Major Project(2021SHZDZX0100)the Shanghai Gaofeng and Gaoyuan Project for University Academic Program Development for funding。
文摘Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.
基金supported in part by the projects of the National Natural Science Foundation of China(62376059,41971340)Fujian Provincial Department of Science and Technology(2023XQ008,2023I0024,2021Y4019),Fujian Provincial Department of Finance(GY-Z230007,GYZ23012)Fujian Key Laboratory of Automotive Electronics and Electric Drive(KF-19-22001).
文摘Autonomous driving has witnessed rapid advancement;however,ensuring safe and efficient driving in intricate scenarios remains a critical challenge.In particular,traffic roundabouts bring a set of challenges to autonomous driving due to the unpredictable entry and exit of vehicles,susceptibility to traffic flow bottlenecks,and imperfect data in perceiving environmental information,rendering them a vital issue in the practical application of autonomous driving.To address the traffic challenges,this work focused on complex roundabouts with multi-lane and proposed a Perception EnhancedDeepDeterministic Policy Gradient(PE-DDPG)for AutonomousDriving in the Roundabouts.Specifically,themodel incorporates an enhanced variational autoencoder featuring an integrated spatial attention mechanism alongside the Deep Deterministic Policy Gradient framework,enhancing the vehicle’s capability to comprehend complex roundabout environments and make decisions.Furthermore,the PE-DDPG model combines a dynamic path optimization strategy for roundabout scenarios,effectively mitigating traffic bottlenecks and augmenting throughput efficiency.Extensive experiments were conducted with the collaborative simulation platform of CARLA and SUMO,and the experimental results show that the proposed PE-DDPG outperforms the baseline methods in terms of the convergence capacity of the training process,the smoothness of driving and the traffic efficiency with diverse traffic flow patterns and penetration rates of autonomous vehicles(AVs).Generally,the proposed PE-DDPGmodel could be employed for autonomous driving in complex scenarios with imperfect data.
文摘While traditional Convolutional Neural Network(CNN)-based semantic segmentation methods have proven effective,they often encounter significant computational challenges due to the requirement for dense pixel-level predictions,which complicates real-time implementation.To address this,we introduce an advanced real-time semantic segmentation strategy specifically designed for autonomous driving,utilizing the capabilities of Visual Transformers.By leveraging the self-attention mechanism inherent in Visual Transformers,our method enhances global contextual awareness,refining the representation of each pixel in relation to the overall scene.This enhancement is critical for quickly and accurately interpreting the complex elements within driving sce-narios—a fundamental need for autonomous vehicles.Our experiments conducted on the DriveSeg autonomous driving dataset indicate that our model surpasses traditional segmentation methods,achieving a significant 4.5%improvement in Mean Intersection over Union(mIoU)while maintaining real-time responsiveness.This paper not only underscores the potential for optimized semantic segmentation but also establishes a promising direction for real-time processing in autonomous navigation systems.Future work will focus on integrating this technique with other perception modules in autonomous driving to further improve the robustness and efficiency of self-driving perception frameworks,thereby opening new pathways for research and practical applications in scenarios requiring rapid and precise decision-making capabilities.Further experimentation and adaptation of this model could lead to broader implications for the fields of machine learning and computer vision,particularly in enhancing the interaction between automated systems and their dynamic environments.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2021R1A2C1011216)。
文摘In this study,a machine vision-based pattern matching technique was applied to estimate the location of an autonomous driving robot and perform 3D tunnel mapping in an underground mine environment.The autonomous driving robot continuously detects the wall of the tunnel in the horizontal direction using the light detection and ranging(Li DAR)sensor and performs pattern matching by recognizing the shape of the tunnel wall.The proposed method was designed to measure the heading of the robot by fusion with the inertial measurement units sensor according to the pattern matching accuracy;it is combined with the encoder sensor to estimate the location of the robot.In addition,when the robot is driving,the vertical direction of the underground mine is scanned through the vertical Li DAR sensor and stacked to create a 3D map of the underground mine.The performance of the proposed method was superior to that of previous studies;the mean absolute error achieved was 0.08 m for the X-Y axes.A root mean square error of 0.05 m^(2)was achieved by comparing the tunnel section maps that were created by the autonomous driving robot to those of manual surveying.
基金This work was supported by the National Natural Science Foundation of China(51975310 and 52002209).
文摘In mixed and dynamic traffic environments,accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles to accomplish reasonable behavioral decisions and guarantee driving safety.In this paper,we propose an integrated probabilistic architecture for long-term vehicle trajectory prediction,which consists of a driving inference model(DIM)and a trajectory prediction model(TPM).The DIM is designed and employed to accurately infer the potential driving intention based on a dynamic Bayesian network.The proposed DIM incorporates the basic traffic rules and multivariate vehicle motion information.To further improve the prediction accuracy and realize uncertainty estimation,we develop a Gaussian process-based TPM,considering both the short-term prediction results of the vehicle model and the driving motion characteristics.Afterward,the effectiveness of our novel approach is demonstrated by conducting experiments on a public naturalistic driving dataset under lane-changing scenarios.The superior performance on the task of long-term trajectory prediction is presented and verified by comparing with other advanced methods.
基金the Presidential Incentive Awards(No.1103 and No.1105)MCCB summer research award in the University of North Georgia.
文摘The study of vehicular networks has attracted considerable interest in academia and the industry.In the broad area,connected vehicles and autonomous driving are technologies based on wireless data communication between vehicles or between vehicles and infrastructures.A Vehicle-to-Infrastructure(V2I)system consists of communications and computing over vehicles and related infrastructures.In such a system,wireless sensors are installed in some selected points along roads or driving areas.In autonomous driving,it is crucial for a vehicle to figure out the ideal routes by the communications between its equipped sensors and infrastructures then the vehicle is automatically moving along the routes.In this paper,we propose a Bezier curve based recursive algorithm,which effectively creates routes for vehicles through the communication between the On-Board Unit(OBU)and the Road-Side Units(RSUs).In addition,this approach generates a very low overhead.We conduct simulations to test the proposed algorithm in various situations.The experiment results demonstrate that our algorithm creates almost ideal routes.
基金The National Key Research and Development Program of China(No.2018YFB1601304)the National Natural Science Foundation of China(No.71871107)Philosophy and Social Science Foundation Project of Universities in Jiangsu Province(No.2020SJA2059).
文摘In order to deeply analyze the differences in the acceptance of autonomous driving technology among different gender groups,a multiple indicators and multiple causes model was constructed by integrating a technology acceptance model and theory of planned behavior to comprehensively reveal the gender differences in the influence mechanisms of subjective and objective factors.The analysis is based on data collected from Chinese urban residents.Among objective factors,age has a significant negative impact on women's perceived behavior control and a significant positive impact on perceived ease of use.Education has a significant positive impact on men's perceived behavior control,and has a strong positive impact on women's perceived usefulness(PU).For men,income and education are found to have strong positive impacts on perceived behavior control.Among subjective factors,perceived ease of use(PEU)has the greatest influence on women's behavior intention,and it is the only influential factor for women's intention to use autonomous driving technology,with an influence coefficient of 0.72.The influencing path of men's intention to use autonomous driving technology is more complex.It is not only directly affected by the significant and positive joint effects of attitude and PU,but also indirectly affected by perceived behavior controls,subjective norms,and PEU.
基金funded by Chongqing Science and Technology Bureau (No.cstc2021jsyj-yzysbAX0008)Chongqing University of Arts and Sciences (No.P2021JG13)2021 Humanities and Social Sciences Program of Chongqing Education Commission (No.21SKGH227).
文摘This paper is to explore the problems of intelligent connected vehicles(ICVs)autonomous driving decision-making under a 5G-V2X structured road environment.Through literature review and interviews with autonomous driving practitioners,this paper firstly puts forward a logical framework for designing a cerebrum-like autonomous driving system.Secondly,situated on this framework,it builds a hierarchical finite state machine(HFSM)model as well as a TOPSIS-GRA algorithm for making ICV autonomous driving decisions by employing a data fusion approach between the entropy weight method(EWM)and analytic hierarchy process method(AHP)and by employing a model fusion approach between the technique for order preference by similarity to an ideal solution(TOPSIS)and grey relational analysis(GRA).The HFSM model is composed of two layers:the global FSM model and the local FSM model.The decision of the former acts as partial input information of the latter and the result of the latter is sent forward to the local pathplanning module,meanwhile pulsating feedback to the former as real-time refresh data.To identify different traffic scenarios in a cerebrum-like way,the global FSM model is designed as 7 driving behavior states and 17 driving characteristic events,and the local FSM model is designed as 16 states and 8 characteristic events.In respect to designing a cerebrum-like algorithm for state transition,this paper firstly fuses AHP weight and EWM weight at their output layer to generate a synthetic weight coefficient for each characteristic event;then,it further fuses TOPSIS method and GRA method at the model building layer to obtain the implementable order of state transition.To verify the feasibility,reliability,and safety of theHFSMmodel aswell as its TOPSISGRA state transition algorithm,this paper elaborates on a series of simulative experiments conducted on the PreScan8.50 platform.The results display that the accuracy of obstacle detection gets 98%,lane line prediction is beyond 70 m,the speed of collision avoidance is higher than 45 km/h,the distance of collision avoidance is less than 5 m,path planning time for obstacle avoidance is averagely less than 50 ms,and brake deceleration is controlled under 6 m/s2.These technical indexes support that the driving states set and characteristic events set for the HFSM model as well as its TOPSIS-GRA algorithm may bring about cerebrum-like decision-making effectiveness for ICV autonomous driving under 5G-V2X intelligent road infrastructure.
基金support of the Royal Society(Grant No.RG\R1\251434).
文摘1 Introduction Autonomous driving technology has made significant advancements in recent years.The evolution of autonomous driving systems from traditional modular designs to end-to-end learning paradigms has led to comprehensive improvements in driving capabilities.In modular designs,driving tasks are segmented into independent modules,such as perception,decision-making,planning,and control.
基金partly supported by the National Natural Science Foundation of China(Nos.62171104 and 62201122)Chengdu Bureau of Science and Technology with No.2023-YF06-00030-HZ.
文摘Platoon-based autonomous driving is indispensable for traffic automation,but it confronts substantial constraints in rugged terrains with unreliable links and scarce communication resources.This paper proposes a novel hierarchical Digital Twin(DT)and consensus empowered cooperative control framework for safe driving in harsh areas.Specifically,leveraging intra-platoon information exchange,one platoon-level DT is constructed on the leader and multiple vehicle-level DTs are distributed among platoon members.The leader first makes critical platoon-driving decisions based on the platoon-level DT.Then,considering the impact of unreliable links on the platoon-level DT accuracy and the consequent risk of unsafe decision-making,a distributed consensus scheme is proposed to negotiate critical decisions efficiently.Upon successful negotiation,vehicles proceed to execute critical decisions,relying on their vehicle-level DTs.Otherwise,a Space-Air-Ground-Integrated-Network(SAGIN)enabled information exchange is utilized to update the platoon-level DT for subsequent safe decision-making in scenarios with unreliable links,no roadside units,and obstructed platoons.Furthermore,based on this framework,an adaptive platooning scheme is designed to minimize total delay and ensure driving safety.Simulation results indicate that our proposed scheme improves driving safety by 21.1%and reduces total delay by 24.2%in harsh areas compared with existing approaches.
文摘Learning-based algorithm attracts great attention in the autonomous driving control field,especially for decisionmaking,to meet the challenge in long-tail extreme scenarios,where traditional methods demonstrate poor adaptability even with a significant effort.To improve the autonomous driving performance in extreme scenarios,specifically consecutive sharp turns,three deep reinforcement learning algorithms,i.e.Deep Deterministic Policy Gradient(DDPG),Twin Delayed Deep Deterministic policy gradient(TD3),and Soft Actor-Critic(SAC),based decision-making policies are proposed in this study.The role of the observation variable in agent training is discussed by comparing the driving stability,average speed,and consumed computational effort of the proposed algorithms in curves with various curvatures.In addition,a novel reward-setting method that combines the states of the environment and the vehicle is proposed to solve the sparse reward problem in the reward-guided algorithm.Simulation results from the road with consecutive sharp turns show that the DDPG,SAC,and TD3 algorithms-based vehicles take 367.2,359.6,and 302.1 s to finish the task,respectively,which match the training results,and verifies the observation variable role in agent quality improvement.
基金supported by the National Natural Science Foundation of China(Nos.62376186 and 61932009)。
文摘Autonomous driving systems(ADSs)have attracted wide attention in the machine learning communities.With the help of deep neural networks(DNNs),ADSs have shown both satisfactory performance under significant uncertainties in the environment and the ability to compensate for system failures without external intervention.However,the vulnerability of ADSs has raised concerns since DNNs have been proven vulnerable to adversarial attacks.In this paper,we present a comprehensive survey of current physical adversarial vulnerabilities in ADSs.We first divide the physical adversarial attack methods and defense methods by their restrictions of deployment into three scenarios:the real-world,simulator-based,and digital-world scenarios.Then,we consider the adversarial vulnerabilities that focus on various sensors in ADSs and separate them as camera-based,light detection and ranging(LiDAR)based,and multifusion-based attacks.Subsequently,we divide the attack tasks by traffic elements.For the physical defenses,we establish the taxonomy with reference to input image preprocessing,adversarial example detection,and model enhancement for the DNN models to achieve full coverage of the adversarial defenses.Based on the above survey,we finally discuss the challenges in this research field and provide further outlook on future directions.
基金supported by the National Natural Science Foundation of China,the Science Fund for Creative Research Groups(No.52221005)the National Natural Science Foundation of China,the Key Project(No.52131201).
文摘End-to-end autonomous driving,with its holistic optimization capabilities,has gained increasing traction in academia and industry.Vectorized representations,which preserve instance-level topological information while reducing computational overhead,have emerged as promising paradigms.However,existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points,resulting in geometrically inconsistent outputs(e.g.,fragmented HD map elements or oscillatory trajectories).To address these limitations,we propose intra-instance vectorized driving transformer(InVDriver),a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers,thereby enhancing planning accuracy and trajectory smoothness.Across all core modules,i.e.,perception,prediction,and planning,InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions,enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise.The experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance,surpassing prior methods in both accuracy and safety,while maintaining high computational efficiency.
基金supported in part by the National Natural Science Foundation of China(52102464,U22A20104)was funded in part by Tsinghua University-DiDi Joint Research Center for Future Mobility(20230908006).
文摘Lane detection is one of the critical tasks for autonomous driving.Earlier works revolved around semantic segmentation and object detection with a special program for lanes.However,most methods still suffer from unstable post-processing algorithms which leads to a gap between camera input and downstream applications.In this paper,we propose a novel detection presentation form for lanes and design a simple network without any complicated post-process.Specifically,we use sampled gird points to express lane lines and construct a network for the special lane format,which is called SGPLane.Therefore,the network learns a regression branch and a confidence branch to realize end-to-end lane detection by setting the threshold confidence value.Our model is validated on the typical dataset and real-world driving scenes.Experiments on lane detection benchmarks show that our method outperforms previous methods with accuracy score of 96.845%on Tusimple dataset with high FPS and 76.85%on our real-world dataset.
文摘This study investigates the use of autonomous vehicles in bus rapid transit lanes during the initial phases of autonomous driving development.The aim is to accelerate the advancement of autonomous driving technologies and enhance the efficiency of bus lane usage.We first develop a dynamic joint optimization model that adjusts autonomous vehicle speeds and bus timetables to minimize vehicle travel times while reducing bus passenger waiting times.We account for random variables such as stochastic passenger arrivals at bus stations and variable demand for autonomous vehicle travel by constructing a stochastic dynamic model.To address the computational challenges of large-scale scenarios,we implement a simulation-based heuristic algorithm framework.This framework is designed to efficiently produce high-quality solutions within feasible time limits.Our numerical studies on an actual bus line show that our approach significantly improves system throughput compared to existing benchmarks.Moreover,by strategically managing the entry of autonomous vehicles into the lane and modifying bus timetables,we further enhance the operational efficiency of the system.
