Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

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.

Perception Enhanced Deep Deterministic Policy Gradient for Autonomous Driving in Complex Scenarios

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.

Enhancing Safety in Autonomous Vehicle Navigation:An Optimized Path Planning Approach Leveraging Model Predictive Control

This paper explores the application of Model Predictive Control(MPC)to enhance safety and efficiency in autonomous vehicle(AV)navigation through optimized path planning.The evolution of AV technology has progressed rapidly,moving from basic driver-assistance systems(Level 1)to fully autonomous capabilities(Level 5).Central to this advancement are two key functionalities:Lane-Change Maneuvers(LCM)and Adaptive Cruise Control(ACC).In this study,a detailed simulation environment is created to replicate the road network between Nantun andWuri on National Freeway No.1 in Taiwan.The MPC controller is deployed to optimize vehicle trajectories,ensuring safe and efficient navigation.Simulated onboard sensors,including vehicle cameras and millimeterwave radar,are used to detect and respond to dynamic changes in the surrounding environment,enabling real-time decision-making for LCM and ACC.The simulation resultshighlight the superiority of the MPC-based approach in maintaining safe distances,executing controlled lane changes,and optimizing fuel efficiency.Specifically,the MPC controller effectively manages collision avoidance,reduces travel time,and contributes to smoother traffic flow compared to traditional path planning methods.These findings underscore the potential of MPC to enhance the reliability and safety of autonomous driving in complex traffic scenarios.Future research will focus on validating these results through real-world testing,addressing computational challenges for real-time implementation,and exploring the adaptability of MPC under various environmental conditions.This study provides a significant step towards achieving safer and more efficient autonomous vehicle navigation,paving the way for broader adoption of MPC in AV systems.

Efficient Vision Transformers for Autonomous Off-Road Perception Systems

The development of autonomous vehicles has become one of the greatest research endeavors in recent years. These vehicles rely on many complex systems working in tandem to make decisions. For practical use and safety reasons, these systems must not only be accurate, but also quickly detect changes in the surrounding environment. In autonomous vehicle research, the environment perception system is one of the key components of development. Environment perception systems allow the vehicle to understand its surroundings. This is done by using cameras, light detection and ranging (LiDAR), with other sensor systems and modalities. Deep learning computer vision algorithms have been shown to be the strongest tool for translating camera data into accurate and safe traversability decisions regarding the environment surrounding a vehicle. In order for a vehicle to safely traverse an area in real time, these computer vision algorithms must be accurate and have low latency. While much research has studied autonomous driving for traversing well-structured urban environments, limited research exists evaluating perception system improvements in off-road settings. This research aims to investigate the adaptability of several existing deep-learning architectures for semantic segmentation in off-road environments. Previous studies of two Convolutional Neural Network (CNN) architectures are included for comparison with new evaluation of Vision Transformer (ViT) architectures for semantic segmentation. Our results demonstrate viability of ViT architectures for off-road perception systems, having a strong segmentation accuracy, lower inference speed and memory footprint compared to previous results with CNN architectures.

Modeling and TOPSIS-GRA Algorithm for Autonomous Driving Decision-Making Under 5G-V2X Infrastructure

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.

Parallel Planning:A New Motion Planning Framework for Autonomous Driving

Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human drivers.Moreover, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.

A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving

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.

Human-Like Decision-Making of Autonomous Vehicles in Dynamic Traffic Scenarios

With the maturation of autonomous driving technology, the use of autonomous vehicles in a socially acceptable manner has become a growing demand of the public. Human-like autonomous driving is expected due to the impact of the differences between autonomous vehicles and human drivers on safety.Although human-like decision-making has become a research hotspot, a unified theory has not yet been formed, and there are significant differences in the implementation and performance of existing methods. This paper provides a comprehensive overview of human-like decision-making for autonomous vehicles. The following issues are discussed: 1) The intelligence level of most autonomous driving decision-making algorithms;2) The driving datasets and simulation platforms for testing and verifying human-like decision-making;3) The evaluation metrics of human-likeness;personalized driving;the application of decisionmaking in real traffic scenarios;and 4) The potential research direction of human-like driving. These research results are significant for creating interpretable human-like driving models and applying them in dynamic traffic scenarios. In the future, the combination of intuitive logical reasoning and hierarchical structure will be an important topic for further research. It is expected to meet the needs of human-like driving.

Location estimation of autonomous driving robot and 3D tunnel mapping in underground mines using pattern matched LiDAR sequential images

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.

Modeling and gender difference analysis of acceptance of autonomous driving technology

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.

Generating routes for autonomous driving in vehicle-to-infrastructure communications

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.

GDMNet: A Unified Multi-Task Network for Panoptic Driving Perception

To enhance the efficiency and accuracy of environmental perception for autonomous vehicles,we propose GDMNet,a unified multi-task perception network for autonomous driving,capable of performing drivable area segmentation,lane detection,and traffic object detection.Firstly,in the encoding stage,features are extracted,and Generalized Efficient Layer Aggregation Network(GELAN)is utilized to enhance feature extraction and gradient flow.Secondly,in the decoding stage,specialized detection heads are designed;the drivable area segmentation head employs DySample to expand feature maps,the lane detection head merges early-stage features and processes the output through the Focal Modulation Network(FMN).Lastly,the Minimum Point Distance IoU(MPDIoU)loss function is employed to compute the matching degree between traffic object detection boxes and predicted boxes,facilitating model training adjustments.Experimental results on the BDD100K dataset demonstrate that the proposed network achieves a drivable area segmentation mean intersection over union(mIoU)of 92.2%,lane detection accuracy and intersection over union(IoU)of 75.3%and 26.4%,respectively,and traffic object detection recall and mAP of 89.7%and 78.2%,respectively.The detection performance surpasses that of other single-task or multi-task algorithm models.

Cooperative Intelligence for Autonomous Driving

Autonomous driving is an emerging technology attracting interests from various sectors in recent years.Most of existing work treats autonomous vehicles as isolated individuals and has focused on developing separate intelligent modules.In this paper,we attempt to exploit the connectivity among vehicles and propose a systematic framework to develop autonomous driving techniques.We first introduce a general hierarchical information fusion framework for cooperative sensing to obtain global situational awareness for vehicles.Following this,a cooperative intelligence framework is proposed for autonomous driving systems.This general framework can guide the development of data collection,sharing and processing strategies to realize different intelligent functions in autonomous driving.

Adversarial robustness analysis of LiDAR-included models in autonomous driving

In autonomous driving systems,perception is pivotal,relying chiefly on sensors like LiDAR and cameras for environmental awareness.LiDAR,celebrated for its detailed depth perception,is being increasingly integrated into autonomous vehicles.In this article,we analyze the robustness of four LiDAR-included models against adversarial points under physical constraints.We first introduce an attack technique that,by simply adding a limited number of physically constrained adversarial points above a vehicle,can make the vehicle undetectable by the LiDAR-included models.Experiments reveal that adversarial points adversely affect the detection capabilities of both LiDAR-only and LiDAR–camera fusion models,with a tendency for more adversarial points to escalate attack success rates.Notably,voxel-based models are more susceptible to deception by these adversarial points.We also investigated the impact of the distance and angle of the added adversarial points on the attack success rate.Typically,the farther the victim object to be hidden and the closer to the front of the LiDAR,the higher the attack success rate.Additionally,we have experimentally proven that our generated adversarial points possess good cross-model adversarial transferability and validated the effectiveness of our proposed optimization method through ablation studies.Furthermore,we propose a new plug-and-play,modelagnostic defense method based on the concept of point smoothness.The ROC curve of this defense method shows an AUC value of approximately 0.909,demonstrating its effectiveness.

A self-driving solution for resource-constrained autonomous vehicles in parked areas

Autonomous vehicles in industrial parks can provide intelligent,efficient,and environmentally friendly transportation services,making them crucial tools for solving internal transportation issues.Considering the characteristics of industrial park scenarios and limited resources,designing and implementing autonomous driving solutions for autonomous vehicles in these areas has become a research hotspot.This paper proposes an efficient autonomous driving solution based on path planning,target recognition,and driving decision-making as its core components.Detailed designs for path planning,lane positioning,driving decision-making,and anti-collision algorithms are presented.Performance analysis and experimental validation of the proposed solution demonstrate its effectiveness in meeting the autonomous driving needs within resource-constrained environments in industrial parks.This solution provides important references for enhancing the performance of autonomous vehicles in these areas.

Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles on highway roads

A new vision-based long-distance lane perception and front vehicle location method was developed for decision making of full autonomous vehicles on highway roads,Firstly,a real-time long-distance lane detection approach was presented based on a linear-cubic road model for two-lane highways.By using a novel robust lane marking feature which combines the constraints of intensity,edge and width,the lane markings in far regions were extracted accurately and efficiently.Next,the detected lane lines were selected and tracked by estimating the lateral offset and heading angle of ego vehicle with a Kalman filter,Finally,front vehicles were located on correct lanes using the tracked lane lines,Experiment results show that the proposed lane perception approach can achieve an average correct detection rate of 94.37% with an average false positive detection rate of 0.35%,The proposed approaches for long-distance lane perception and front vehicle location were validated in a 286 km full autonomous drive experiment under real traffic conditions.This successful experiment shows that the approaches are effective and robust enough for full autonomous vehicles on highway roads.

Towards the Unified Principles for Level 5 Autonomous Vehicles

The rapid advance of autonomous vehicles(AVs)has motivated new perspectives and potential challenges for existing modes of transportation.Currently,driving assistance systems of Level 3 and below have been widely produced,and several applications of Level 4 systems to specific situations have also been gradually developed.By improving the automation level and vehicle intelligence,these systems can be further advanced towards fully autonomous driving.However,general development concepts for Level 5 AVs remain unclear,and the existing methods employed in the development processes of Levels 0-4 have been mainly based on task-driven function development related to specific scenarios.Therefore,it is difficult to identify the problems encountered by high-level AVs.The essential logical and physical mechanisms of vehicles have hindered further progression towards Level 5 systems.By exploring the physical mechanisms behind high-level autonomous driving systems and analyzing the essence of driving,we put forward a coordinated and balanced framework based on the brain-cerebellum-organ concept through reasoning and deduction.Based on a mixed mode relying on the crow inference and parrot imitation approach,we explore the research paradigm of autonomous learning and prior knowledge to realize the characteristics of self-learning,self-adaptation,and self-transcendence for AVs.From a systematic,unified,and balanced point of view and based on least action principles and unified safety field concepts,we aim to provide a novel research concept and develop an effective approach for the research and development of high-level AVs,specifically at Level 5.

Probabilistic Lane-Change Decision-Making and Planning for Autonomous Heavy Vehicles

To improve the safety and driving stability of the autonomous heavy truck, it is necessary to consider the differences of driving behavior and drivable trajectories between the heavy trucks and passenger cars. This study proposes a probabilistic decision-making and trajectory planning framework for the autonomous heavy trucks. Firstly, the driving decision process is divided into intention generation and feasibility evaluations, which are realized using the utility theory and risk assessment, respectively. Subsequently the driving decision is made and sent to the trajectory planning module. In order to reflect the greater risks of the truck to other surrounding vehicles, the aggressiveness index(AI) is proposed and quantified to infer the asymmetrical risk level of lane-change maneuver. In the planning stage, the lateral and roll dynamics stability domains are developed as the constraints to exclude the candidate trajectories that would cause vehicle instability. Finally, the simulation results are compared between the proposed model and the artificial potential filed model in the scenarios extracted from the naturalistic driving data. It is shown that the proposed framework can provide the human-like lane-change decisions and truck-friendly trajectories, and performs well in dynamic driving environments.

Intelligent Autonomous-Robot Control for Medical Applications

The COVID-19 pandemic has shown that there is a lack of healthcare facilities to cope with a pandemic.This has also underscored the immediate need to rapidly develop hospitals capable of dealing with infectious patients and to rapidly change in supply lines to manufacture the prescription goods(including medicines)that is needed to prevent infection and treatment for infected patients.The COVID-19 has shown the utility of intelligent autonomous robots that assist human efforts to combat a pandemic.The artificial intelligence based on neural networks and deep learning can help to fight COVID-19 in many ways,particularly in the control of autonomous medic robots.Health officials aim to curb the spread of COVID-19 among medical,nursing staff and patients by using intelligent robots.We propose an advanced controller for a service robot to be used in hospitals.This type of robot is deployed to deliver food and dispense medications to individual patients.An autonomous line-follower robot that can sense and follow a line drawn on the floor and drive through the rooms of patients with control of its direction.These criteria were met by using two controllers simultaneously:a deep neural network controller to predict the trajectory of movement and a proportional-integral-derivative(PID)controller for automatic steering and speed control.

Artificial Intelligence Applications in the Development of Autonomous Vehicles:A Survey

The advancement of artificial intelligence(AI)has truly stimulated the development and deployment of autonomous vehicles(AVs)in the transportation industry.Fueled by big data from various sensing devices and advanced computing resources,AI has become an essential component of AVs for perceiving the surrounding environment and making appropriate decision in motion.To achieve goal of full automation(i.e.,self-driving),it is important to know how AI works in AV systems.Existing research have made great efforts in investigating different aspects of applying AI in AV development.However,few studies have offered the research community a thorough examination of current practices in implementing AI in AVs.Thus,this paper aims to shorten the gap by providing a comprehensive survey of key studies in this research avenue.Specifically,it intends to analyze their use of AIs in supporting the primary applications in AVs:1)perception;2)localization and mapping;and 3)decision making.It investigates the current practices to understand how AI can be used and what are the challenges and issues associated with their implementation.Based on the exploration of current practices and technology advances,this paper further provides insights into potential opportunities regarding the use of AI in conjunction with other emerging technologies:1)high definition maps,big data,and high performance computing;2)augmented reality(AR)/virtual reality(VR)enhanced simulation platform;and 3)5G communication for connected AVs.This paper is expected to offer a quick reference for researchers interested in understanding the use of AI in AV research.