Search

Advances in Artificial Intelligence (AI) are poised to transform society, national defense, and the economy by increasing efficiency, precision, and safety. Yet, widespread adoption within society depends on public trust and willingness to use AI-enabled technologies. In this study, we propose the possibility of an AI "trust paradox," in which individuals' willingness to use AI-enabled technologies exceeds their level of trust in these capabilities. We conduct a two-part study to explore the trust paradox. First, we conduct a conjoint analysis, varying different attributes of AI-enabled technologies in different domains-including armed drones, general surgery, police surveillance, self-driving cars, and social media content moderation-to evaluate whether and under what conditions a trust paradox may exist. Second, we use causal mediation analysis in the context of a second survey experiment to help explain why individuals use AI-enabled technologies that they do not trust. We find strong support for the trust paradox, particularly in the area of AI-enabled police surveillance, where the levels of support for its use are both higher than other domains but also significantly exceed trust. We unpack these findings to show that several underlying beliefs help account for public attitudes of support, including the fear of missing out, optimism that future versions of the technology will be more trustworthy, a belief that the benefits of AI-enabled technologies outweigh the risks, and calculation that AI-enabled technologies yield efficiency gains. Our findings have important implications for the integration of AI-enabled technologies in multiple settings., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Kreps et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Advanced Driver Assistance Systems (ADAS) are only applied to relatively simple scenarios, such as highways. If there is an emergency while driving, the driver should take control of the car to deal properly with the situation at any time. Obviously, this incurs the uncertainty of safety. Recently, in the literature, several studies have been proposed for the above-mentioned issue via Artificial Intelligence (AI). The achievement is exactly the aim that we look forward to, i.e., the autonomous vehicle. In this paper, we realize the autonomous driving control via Deep Reinforcement Learning (DRL) based on the CARLA (Car Learning to Act) simulator. Specifically, we use the ordinary Red-Green-Blue (RGB) camera and semantic segmentation camera to observe the view in front of the vehicle while driving. Then, the captured information is utilized as the input for different DRL models so as to evaluate the performance, where the DRL models include DDPG (Deep Deterministic Policy Gradient) and RDPG (Recurrent Deterministic Policy Gradient). Moreover, we also design an appropriate reward mechanism for these DRL models to realize efficient autonomous driving control. According to the results, only the RDPG strategies can finish the driving mission with the scenario that does not appear/include in the training scenario, and with the help of the semantic segmentation camera, the RDPG control strategy can further improve its efficiency.

The advancement in sensor technologies, mobile network technologies, and artificial intelligence has pushed the boundaries of different verticals, e.g., eHealth and autonomous driving. Statistics show that more than one million people are killed in traffic accidents yearly, where the vast majority of the accidents are caused by human negligence. Higher-level autonomous driving has great potential to enhance road safety and traffic efficiency. One of the most crucial links to building an autonomous system is the task of decision-making. The ability of a vehicle to make robust decisions on its own by anticipating and evaluating future outcomes is what makes it intelligent. Planning and decision-making technology in autonomous driving becomes even more challenging, due to the diversity of the dynamic environments the vehicle operates in, the uncertainty in the sensor information, and the complex interaction with other road participants. A significant amount of research has been carried out toward deploying autonomous vehicles to solve plenty of issues, however, how to deal with the high-level decision-making in a complex, uncertain, and urban environment is a comparatively less explored area. This paper provides an analysis of decision-making solutions approaches for autonomous driving. Various categories of approaches are analyzed with a comparison to classical decision-making approaches. Following, a crucial range of research gaps and open challenges have been highlighted that need to be addressed before higher-level autonomous vehicles hit the roads. We believe this survey will contribute to the research of decision-making methods for autonomous vehicles in the future by equipping the researchers with an overview of decision-making technology, its potential solution approaches, and challenges.

The intelligent transportation system, especially autonomous vehicles, has seen a lot of interest among researchers owing to the tremendous work in modern artificial intelligence (AI) techniques, especially deep neural learning. As a result of increased road accidents over the last few decades, significant industries are moving to design and develop autonomous vehicles. Understanding the surrounding environment is essential for understanding the behavior of nearby vehicles to enable the safe navigation of autonomous vehicles in crowded traffic environments. Several datasets are available for autonomous vehicles focusing only on structured driving environments. To develop an intelligent vehicle that drives in real-world traffic environments, which are unstructured by nature, there should be an availability of a dataset for an autonomous vehicle that focuses on unstructured traffic environments. Indian Driving Lite dataset (IDD-Lite), focused on an unstructured driving environment, was released as an online competition in NCPPRIPG 2019. This study proposed an explainable inception-based U-Net model with Grad-CAM visualization for semantic segmentation that combines an inception-based module as an encoder for automatic extraction of features and passes to a decoder for the reconstruction of the segmentation feature map. The black-box nature of deep neural networks failed to build trust within consumers. Grad-CAM is used to interpret the deep-learning-based inception U-Net model to increase consumer trust. The proposed inception U-net with Grad-CAM model achieves 0.622 intersection over union (IoU) on the Indian Driving Dataset (IDD-Lite), outperforming the state-of-the-art (SOTA) deep neural-network-based segmentation models.

eXplainable Artificial Intelligence (XAI) is a new trend of machine learning. Machine learning models are used to predict or decide something, and they derive output based on a large volume of data set. Here, the problem is that it is hard to know why such prediction was derived, especially when using deep learning models. It makes the models unreliable in the case of reliability-critical applications. So, it is required to explain how they derived such output. It is a reliability-critical application for self-driving cars because the mistakes made by the computers inside them can lead to critical accidents. So, it is necessary to adopt XAI models in this field. In this paper, we propose an XAI method based on computing and explaining the difference of the output values of the neurons in the last hidden layer of convolutional neural networks. First, we input the original image and some modified images of it. Then we derive output values for each image and compare these values. Then, we introduce the Sensitivity Analysis technique to explain which parts of the original image are needed to distinguish the category. In detail, we divide the image into several parts and fill these parts with shades. First, we compute the influence value on the vector indicating the last hidden layer of the model for each of these parts. Then we draw shades whose darkness is in proportion to the influence values. The experimental results show that our approach for XAI in self-driving cars finds the parts needed to distinguish the category of these images accurately., Competing Interests: The authors have declared that no competing interests exist.

In this paper, we have demonstrated a robust in-cabin monitoring system (IMS) for safety, security, surveillance, and monitoring, including privacy concerns for personal and shared autonomous vehicles (AVs). It consists of a set of monitoring cameras and an onboard device (OBD) equipped with artificial intelligence (AI). Hereafter, this combination of a camera and an OBD is referred to as the AI camera. We have investigated the issues for mobility services in higher levels of autonomous driving, what needs to be monitored, how to monitor, etc. Our proposed IMS is an on-device AI system that indigenously has improved the privacy of the users. Furthermore, we have enlisted the essential actions to be considered in an IMS and developed an appropriate database (DB). Our DB consists of multifaced scenarios important for monitoring the in-cabin of the higher-level AVs. Moreover, we have compared popular AI models applied for object and occupant recognition. In addition, our DB is available on request to support the research on the development of seamless monitoring of the in-cabin higher levels of autonomous driving for the assurance of safety and security.

This paper examines recent street tests of autonomous vehicles (AVs) in the UK and makes the case for an experimental approach in the sociology of intelligent technology. In recent years intelligent vehicle testing has moved from the laboratory to the street, raising the question of whether technology trials equally constitute tests of society. To adequately address this question, I argue, we need to move beyond analytic frameworks developed in 1990s Science and Technology Studies, which stipulated "a social deficit" of both intelligent technology and technology testing. This diagnosis no longer provides an effective starting point for sociological analysis, as real-world tests of intelligent technology explicitly seek to bring social phenomena within the remit of technology testing. I propose that we examine instead whether and how the introduction of intelligent vehicles into the street involves the qualification and re-qualification of relations and dynamics between social actors. I develop this proposal through a discussion of a field study of AV street trials in three cities in the UK-London, Milton Keynes, and Coventry. These urban trials were accompanied by the claim that automotive testing on the open road will enable cars to operate in tune with the social environment, and I show how iterations of street testing undo this proposition and compel its reformulation. Current test designs are limited by their narrow conception of sociality in terms of interaction between cars and other road users. They exclude from consideration the relational capacities of vehicles and human road users alike-their ability to co-exist on the open road. I conclude by making the case for methodological innovation in social studies of intelligent technology: by combining social research and design methods, we can re-purpose real-world test environments in order to elucidate social issues and dynamics raised by intelligent vehicles in society by experimental means, and, possibly, test society., (© 2020 London School of Economics and Political Science.)

Applications in artificial intelligence such as self-driving cars may profoundly transform our society, yet emerging technologies are frequently faced with suspicion or even hostility. Meanwhile, public opinions about scientific issues are increasingly polarized along the ideological line. By analyzing a nationally representative panel in the United States, we reveal an emerging ideological divide in public reactions to self-driving cars. Compared with liberals and Democrats, conservatives and Republicans express more concern about autonomous vehicles and more support for restrictively regulating autonomous vehicles. This ideological gap is largely driven by social conservatism. Moreover, both familiarity with driverless vehicles and scientific literacy reduce respondents' concerns over driverless vehicles and support for regulation policies. Still, the effects of familiarity and scientific literacy are weaker among social conservatives, indicating that people may assimilate new information in a biased manner that promotes their worldviews.

The advent of autonomous vehicles (AVs) has gained increasing attention in China. Although auto manufacturers and innovators have attempted to confirm that AVs are safe and have introduced them on public roads, it is vital to understand end-users' acceptance of AVs. A total of 1453 participants voluntarily and validly completed a series of questionnaires. The questionnaires included the Autonomous Vehicle Acceptability Scale (AVAS), the Traffic Climate Scale (TCS), and sociodemographic variables. The satisfactory internal consistency reliability and construct validity revealed that the newly developed Chinese version of the AVAS is a suitable tool to measure public acceptance of AVs. Moreover, exploratory factor analysis and confirmatory factor analysis conformed to the four factors of AVAS, including benefits in usefulness (BIU), benefits in situations (BIS), concern scenarios (CS) and system concern (SC). Scores higher on benefits and lower on concerns represent more acceptance of AVs. In addition, we found that the public's perceived local traffic safety climate affected the attitude toward AVs. More specifically, external affective demands (EAD) were found to be a significant predictor of SC, internal requirements (IR) were shown to have an effect on BIS and CS, and functionality was found to be a significant predictor of BIU and SC. Furthermore, the differences between drivers and non-drivers revealed that drivers were concerned significantly less about AVs and regarded AVs as more useful than non-drivers did. To gain more customers for the purchase of AVs, it is necessary for automotive vehicle manufacturers and retailers to introduce and advertise the functions and usability of autonomous driving systems to the public. Gaining acceptance from end users and understanding the factors that affect acceptability will be critical to the widespread deployment of AVs., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

This article investigates both the claims made for, and the dangers or opportunities posed by, the development of (allegedly), aspiring or "would-be" autonomous vehicles and other artificially superintelligent machines. It also examines the dilemmas posed by the fact that these individuals might develop ideas above their station. These ideas may also limit or challenge the legitimacy of the proposed management and safety strategies that might be devised to limit the ways in which they might function or malfunction.

With the rapid advancement of information technology and intelligent systems, autonomous driving has garnered significant attention and research in recent years. Key technologies, such as Simultaneous Localization and Mapping (SLAM), Perception and Localization, and Scene Segmentation, have proven to be essential in this field. These technologies not only evolve independently, each with its own research focus and application paths, but also complement and rely on one another in various complex autonomous driving scenarios. This paper provides a comprehensive review of the development and current state of these technologies, along with a forecast of their future trends. [ABSTRACT FROM AUTHOR]

Target detection in autonomous driving tasks presents a complex and critical challenge due to the diversity of targets and the intricacy of the environment. To address this issue, this paper proposes an enhanced YOLOv8 model. Firstly, the original large target detection head is removed and replaced with a detection head tailored for small targets and high‐level semantic details. Secondly, an adaptive feature fusion method is proposed, where input feature maps are processed using dilated convolutions with different dilation rates, followed by adaptive feature fusion to generate adaptive weights. Finally, an improved attention mechanism is incorporated to enhance the model's focus on target regions. Additionally, the impact of Group Shuffle Convolution (GSConv) on the model's detection speed is investigated. Validated on two public datasets, the model achieves a mean Average Precision (mAP) of 53.7% and 53.5%. Although introducing GSConv results in a slight decrease in mAP, it significantly improves frames per second. These findings underscore the effectiveness of the proposed model in autonomous driving tasks. [ABSTRACT FROM AUTHOR]

Pedestrian action prediction is crucial for many applications such as autonomous driving. However, state-of-the-art methods lack the explainability needed for trustworthy predictions. In this paper, a novel framework called MulCPred is proposed that explains its predictions based on multi-modal concepts represented by training samples. Previous concept-based methods have limitations, including the following: (1) they cannot be directly applied to multi-modal cases; (2) they lack the locality needed to attend to details in the inputs; (3) they are susceptible to mode collapse. These limitations are tackled accordingly through the following approaches: (1) a linear aggregator to integrate the activation results of the concepts into predictions, which associates concepts of different modalities and provides ante hoc explanations of the relevance between the concepts and the predictions; (2) a channel-wise recalibration module that attends to local spatiotemporal regions, which enables the concepts with locality; (3) a feature regularization loss that encourages the concepts to learn diverse patterns. MulCPred is evaluated on multiple datasets and tasks. Both qualitative and quantitative results demonstrate that MulCPred is promising in improving the explainability of pedestrian action prediction without obvious performance degradation. Moreover, by removing unrecognizable concepts, MulCPred shows improved cross-dataset prediction performance, suggesting its potential for further generalization. [ABSTRACT FROM AUTHOR]

The integration of IoT systems into automotive vehicles has raised concerns associated with intrusion detection within these systems. Vehicles equipped with a controller area network (CAN) control several systems within a vehicle where disruptions in function can lead to significant malfunctions, injuries, and even loss of life. Detecting disruption is a primary concern as vehicles move to higher degrees of autonomy and the possibility of self-driving is explored. Tackling cyber-security challenges within CAN is essential to improve vehicle and road safety. Standard differences between different manufacturers make the implementation of a discreet system difficult; therefore, data-driven techniques are needed to tackle the ever-evolving landscape of cyber security within the automotive field. This paper examines the possibility of using machine learning classifiers to identify cyber assaults in CAN systems. To achieve applicability, we cover two classifiers: extreme gradient boost and K-nearest neighbor algorithms. However, as their performance hinges on proper parameter selection, a modified metaheuristic optimizer is introduced as well to tackle parameter optimization. The proposed approach is tested on a publicly available dataset with the best-performing models exceeding 89% accuracy. Optimizer outcomes have undergone rigorous statistical analysis, and the best-performing models were subjected to analysis using explainable artificial intelligence techniques to determine feature impacts on the best-performing model. [ABSTRACT FROM AUTHOR]

Qualities of organizations constitute dimensions of trustworthiness. Guided by the integrative model of organizational trust, we developed dimensions of trustworthiness of policymakers, technology developers, and media organizations that are involved in introducing artificial intelligence for autonomous vehicles. We collected data through six focus group discussions with the public in Singapore. In addition to the core dimensions of trustworthiness, the public would consider acclaim, collaboration, public communication, and affiliation. Further, we identified all the dimensions of trustworthiness as either ability-, recognition-, relation-, or principle-based. These findings carry important implications for the development of the model and stakeholders' communication about science and technology. [ABSTRACT FROM AUTHOR]

Fueled by substantial advancements in deep learning, the domain of autonomous driving is swiftly advancing towards more robust and effective intelligent systems. One of the critical challenges in this field is achieving accurate 3D object detection, which is often hindered by data sparsity and occlusion. To address these issues, we propose a method centered around a multi-modal fusion strategy that leverages vehicle-road cooperation to enhance perception capabilities. Our approach integrates label information from roadside perception point clouds to harmonize and enrich the representation of image and LiDAR data. This comprehensive integration significantly improves detection accuracy by providing a fuller understanding of the surrounding environment. Rigorous evaluations of our proposed method on two benchmark datasets, KITTI and Waymo Open, demonstrate its superior performance, with our model achieving 87.52% 3D Average Precision (3D AP) and 93.71% Bird's Eye View Average Precision (BEV AP) on the KITTI v a l set. These results highlight the effectiveness of our method in detecting sparse and distant objects, contributing to the development of safer and more efficient autonomous driving solutions. [ABSTRACT FROM AUTHOR]

Distracted driving is a significant threat to road safety, causing numerous accidents every year. Driver distraction detection systems offer a promising solution by alerting the driver to refocus on the primary driving task. Even with increasing vehicle automation, human drivers must remain alert, especially in partially automated vehicles where they may need to take control in critical situations. In this work, an AI-based distraction detection model is developed that focuses on improving classification performance using a long short-term memory (LSTM) network. Unlike traditional approaches that evaluate individual frames independently, the LSTM network captures temporal dependencies across multiple time steps. In addition, this study investigated the integration of vehicle sensor data and an inertial measurement unit (IMU) to further improve detection accuracy. The results show that the recurrent LSTM network significantly improved the average F1 score from 71.3% to 87.0% compared to a traditional vision-based approach using a single image convolutional neural network (CNN). Incorporating sensor data further increased the score to 90.1%. These results highlight the benefits of integrating temporal dependencies and multimodal inputs and demonstrate the potential for more effective driver distraction detection systems that can improve road safety. [ABSTRACT FROM AUTHOR]

Autonomous vehicles (AV) can not only improve traffic safety and congestion, but also have strategic significance for the development of the transportation industry. With the continuous updating of core technologies such as artificial intelligence, sensor detection, synchronous positioning, and high‐precision mapping, the development of AV has been promoted. When 5G network is combined with Internet of Vehicles, the problems of AV can be solved by taking advantage of 5G ultra‐large bandwidth, low latency and high reliability. However, when the user controls the vehicle remotely, a real‐time and reliable authentication process is needed, while minimizing the overhead of security protocols. Therefore, this article proposes a practical and secure multifactor user authentication protocol for AV in 5G network. By introducing non‐interactive zero‐knowledge proof technology and physical uncloning function, the protocol completes mutual authentication and key agreement without revealing any sensitive information. The article proves the security of the protocol through BAN logic and the simulation of Scyther. And it can resist malicious attacks and provide more security features. The informal security analysis shows that the protocol can meet the proposed security requirements. Finally, we evaluate the efficiency of the protocol, and the results show that the protocol can provide better performance. [ABSTRACT FROM AUTHOR]

Internet of autonomous unmanned vehicles (IAUV) is a global network of sensors, robots, and autonomous vehicles. Person re‐identification (Re‐ID) is an important intelligent transportation application in IAUV, which needs to be solved using artificial intelligence algorithms. In this study, a domain adaptation metric learning method embedded with structural information (called DAML‐ESI) is designed for person Re‐ID in IAUV. Due to the lack of labeling information in the target domain, DAML‐ESI realizes person Re‐ID with the help of the discriminative and structural information of pedestrian images of related domains. DAML‐ESI projects pedestrian images selected from different domains into a common metric space and establishes a discriminative metric learning model, which requires that the positive sample pair be mapped to a point, and the distance distribution of the negative sample pair be mapped to a fixed value. The projection matrix learned by DAML‐ESI is used to eliminate the distribution differences between different domains, and the distance metric is used to ensure that the learned metric learning model has strong discriminative ability in the metric space. To verify the effectiveness of DAML‐ESI, experimental comparisons are conducted on three person Re‐ID datasets, and DAML‐ESI achieves satisfactory recognition performance. [ABSTRACT FROM AUTHOR]

Autonomous vehicles (AVs) represent a transformative advancement in transportation technology, promising to enhance travel efficiency, reduce traffic accidents, and revolutionize our road systems. Central to the operation of AVs is the integration of artificial intelligence (AI), which enables these vehicles to navigate complex environments with minimal human intervention. This review critically examines the potential dangers associated with the increasing reliance on AI in AV navigation. It explores the current state of AI technologies, highlighting key techniques such as machine learning and neural networks, and identifies significant challenges including technical limitations, safety risks, and ethical and legal concerns. Real-world incidents, such as Uber's fatal accident and Tesla's crash, underscore the potential risks and the need for robust safety measures. Future threats, such as sophisticated cyber-attacks, are also considered. The review emphasizes the importance of improving AI systems, implementing comprehensive regulatory frameworks, and enhancing public awareness to mitigate these risks. By addressing these challenges, we can pave the way for the safe and reliable deployment of autonomous vehicles, ensuring their benefits can be fully realized. [ABSTRACT FROM AUTHOR]

The integration of advanced image analysis using artificial intelligence (AI) is pivotal for the evolution of autonomous vehicles (AVs). This article provides a thorough review of the most significant datasets and latest state-of-the-art AI solutions employed in image analysis for AVs. Datasets such as Cityscapes, NuScenes, CARLA, and Talk2Car form the benchmarks for training and evaluating different AI models, with unique characteristics catering to various aspects of autonomous driving. Key AI methodologies, including Convolutional Neural Networks (CNNs), Transformer models, Generative Adversarial Networks (GANs), and Vision Language Models (VLMs), are discussed. The article also presents a comparative analysis of various AI techniques in real-world scenarios, focusing on semantic image segmentation, 3D object detection, vehicle control in virtual environments, and vehicle interaction using natural language. Simultaneously, the roles of multisensor datasets and simulation platforms like AirSim, TORCS, and SUMMIT in enriching the training data and testing environments for AVs are highlighted. By synthesizing information on datasets, AI solutions, and comparative performance evaluations, this article serves as a crucial resource for researchers, developers, and industry stakeholders, offering a clear view of the current landscape and future directions in autonomous vehicle image analysis technologies. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) systems of autonomous systems such as drones, robots and self-driving cars may consume up to 50% of the total power available onboard, thereby limiting the vehicle's range of functions and considerably reducing the distance the vehicle can travel on a single charge. Next-generation onboard AI systems need an even higher power since they collect and process even larger amounts of data in real time. This problem cannot be solved using traditional computing devices since they become more and more power-consuming. In this review article, we discuss the perspectives on the development of onboard neuromorphic computers that mimic the operation of a biological brain using the nonlinear–dynamical properties of natural physical environments surrounding autonomous vehicles. Previous research also demonstrated that quantum neuromorphic processors (QNPs) can conduct computations with the efficiency of a standard computer while consuming less than 1% of the onboard battery power. Since QNPs are a semi-classical technology, their technical simplicity and low cost compared to quantum computers make them ideally suited for applications in autonomous AI systems. Providing a perspective on the future progress in unconventional physical reservoir computing and surveying the outcomes of more than 200 interdisciplinary research works, this article will be of interest to a broad readership, including both students and experts in the fields of physics, engineering, quantum technologies and computing. [ABSTRACT FROM AUTHOR]

This paper evaluates the effectiveness of different decoder architectures in enhancing the reconstruction quality of Capsule Neural Networks (CapsNets), which impacts model interpretability. We compared linear, convolutional, and residual decoders to assess their performance in improving CapsNet reconstructions. Our experiments revealed that the Conditional Variational Autoencoder Capsule Network (CVAECapOSR) achieved the best reconstruction quality on the CIFAR-10 dataset, while the residual decoder outperformed others on the Brain Tumor MRI dataset. These findings highlight how improved decoder architectures can generate reconstructions of better quality, which can enhance changes by deforming output capsules, thereby making the feature extraction and classification processes within CapsNets more transparent and interpretable. Additionally, we evaluated the computational efficiency and scalability of each decoder, providing insights into their practical deployment in real-world applications such as medical diagnostics and autonomous driving. [ABSTRACT FROM AUTHOR]

The advancement of artificial intelligence (AI) has become a crucial element in autonomous cars. A well-designed AI architecture will be necessary to attain the full potential of autonomous vehicles and will significantly accelerate the development and deployment of autonomous cars in the transportation sector. Promising autonomous cars for innovating modern transportation systems are anticipated to address many long-standing transporting challenges related to congestion, safety, parking, and energy conservation. Choosing the optimal AI architecture for autonomous vehicles is a multi-attribute decision-making (MADM) dilemma, as it requires making a complicated decision while considering a number of attributes, and these attributes can have two-dimensional uncertainty as well as indiscernibility. Thus, in this framework, we developed a novel mathematical framework "complex intuitionistic fuzzy rough set" for tackling both two-dimensional uncertainties and indiscernibility. We also developed the elementary operations of the deduced complex intuitionistic fuzzy rough set. Moreover, we developed complex intuitionistic fuzzy rough (weighted averaging, ordered weighted averaging, weighted geometric, and ordered weighted geometric) aggregation operators. Afterward, we developed a method of MADM by employing the devised operators and investigated the case study "Selection of optimal AI architecture for autonomous vehicles" to reveal the practicability of the devised method of MADM. Finally, to reveal the dominance and supremacy of our proposed work, a benchmark dilemma was used for comparison with various prevailing techniques. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) systems of autonomous systems such as drones, robots and self-driving cars may consume up to 50% of the total power available onboard, thereby limiting the vehicle’s range of functions and considerably reducing the distance the vehicle can travel on a single charge. Next-generation onboard AI systems need an even higher power since they collect and process even larger amounts of data in real time. This problem cannot be solved using traditional computing devices since they become more and more power-consuming. In this review article, we discuss the perspectives on the development of onboard neuromorphic computers that mimic the operation of a biological brain using the nonlinear–dynamical properties of natural physical environments surrounding autonomous vehicles. Previous research also demonstrated that quantum neuromorphic processors (QNPs) can conduct computations with the efficiency of a standard computer while consuming less than 1% of the onboard battery power. Since QNPs are a semi-classical technology, their technical simplicity and low cost compared to quantum computers make them ideally suited for applications in autonomous AI systems. Providing a perspective on the future progress in unconventional physical reservoir computing and surveying the outcomes of more than 200 interdisciplinary research works, this article will be of interest to a broad readership, including both students and experts in the fields of physics, engineering, quantum technologies and computing.

In-cabin occupancy detection has become increasingly important due to incidents involving children left in vehicles under extreme temperature conditions. Frequency modulated continuous wave (FMCW) radars are widely used for non-contact monitoring and sensing applications, particularly for occupancy detection. However, the confined and metallic environment inside vehicle cabins presents significant challenges due to multipath reflections. This paper introduces a novel approach that detects the occupied space in each seat to determine occupancy, using the variance of detected points as an indicator of volume occupancy. In an experimental study involving 70 different scenarios with single and multiple subjects, we classify occupants in each seat into one of three categories: adult, baby, or empty. The proposed method achieves an overall accuracy of 96.7% using an Adaboost classifier and a miss-detection rate of 1.8% for detecting babies. This approach demonstrates superior robustness to multipath interference compared to traditional energy-based methods, offering a significant advancement in in-cabin occupancy detection technology. [ABSTRACT FROM AUTHOR]

Deep learning approaches have been gaining importance in several applications. However, the widespread use of these methods in safety-critical domains, such as Autonomous Driving, is still dependent on their reliability and trustworthiness. The goal of this paper is to provide a review of deep learning-based uncertainty methods and their applications to support perception tasks for Autonomous Driving. We detail significant Uncertainty Quantification and calibration methods, and their contributions and limitations, as well as important metrics and concepts. We present an overview of the state of the art of out-of-distribution detection and active learning, where uncertainty estimates are commonly applied. We show how these methods have been applied in the automotive context, providing a comprehensive analysis of reliable AI for Autonomous Driving. Finally, challenges and opportunities for future work are discussed for each topic. [ABSTRACT FROM AUTHOR]

The development of artificial intelligence and information communication technology has significantly propelled advancements in autonomous driving. The advent of autonomous driving has a profound impact on societal development and transportation methods. However, as intelligent systems, autonomous driving systems (ADSs) often make wrong judgements in specific scenarios, resulting in accidents. There is an urgent need for comprehensive testing and validation of ADSs. Metamorphic testing (MT) techniques have demonstrated effectiveness in testing ADSs. Nevertheless, existing testing methods primarily encompass relatively simple metamorphic relations (MRs) that only verify ADSs from a single perspective. To ensure the safety of ADSs, it is essential to consider the various elements of driving scenarios during the testing process. Therefore, this paper proposes MetaSem, a novel metamorphic testing method based on semantic information of autonomous driving scenes. Based on semantic information of the autonomous driving scenes and traffic regulations, we design 11 MRs targeting different scenario elements. Three transformation modules are developed to execute addition, deletion and replacement operations on various scene elements within the images. Finally, corresponding evaluation metrics are defined based on MRs. MetaSem automatically discovers inconsistent behaviours according to the evaluation metrics. Our empirical study on three advanced and popular autonomous driving models demonstrates that MetaSem not only efficiently generates visually natural and realistic scene images but also detects 11,787 inconsistent behaviours on three driving models. [ABSTRACT FROM AUTHOR]

Data security in autonomous vehicles is of primary importance due to the possibility of cyberattacks on these interconnected and complex systems. As these vehicles are equipped with a number of sensors, software, and communication infrastructure, they are more vulnerable to different types of security issues. In this article. blockchain-supported QoS-based secure data communication (QoS-SDC) is proposed for high-speed, software-defined autonomous vehicles. This proposed mechanism will provide a promising solution for delivering protected data among autonomous vehicles. This model is evaluated by using the NS3 simulator, and the simulation results exhibit satisfactory secure data transactions. [ABSTRACT FROM AUTHOR]

User acceptance is essential for successfully introducing automated vehicles (AVs). Understanding the technology is necessary to overcome skepticism and achieve acceptance. This could be achieved by visualizing (uncertainties of) AV's internal processes, including situation perception, prediction, and trajectory planning. At the same time, relevant scenarios for communicating the functionalities are unclear. Therefore, we developed EduLicit to concurrently elicit relevant scenarios and evaluate the effects of visualizing AV's internal processes. A website capable of showing annotated videos enabled this methodology. With it, we replicated the results of a previous online study (N=76) using pre-recorded real-world videos. Additionally, in a second online study (N=22), participants uploaded scenarios they deemed challenging for AVs using our website. Most scenarios included large intersections and/or multiple vulnerable road users. Our work helps assess scenarios perceived as challenging for AVs by the public and, simultaneously, can help educate the public about visualizations of the functionalities of current AVs. • EduLicit –a method to elicit user-chosen driving scenarios and educate on automated vehicle functionalities and challenges. • Applying neural networks to scenario videos to visualize vehicles' detection, prediction, and trajectory planning functionalities. • Website implementation of EduLicit , where users upload in-the-wild driving videos for automated visualization and education. • User-chosen driving scenarios primarily include large intersections and/or multiple vulnerable road users. • Users perceive vulnerable road users as more unreliable, unpredictable, and harder to detect by sensors than vehicles. [ABSTRACT FROM AUTHOR]

Recent advances in artificial intelligence technology and perception components have promoted the rapid development of autonomous vehicles. However, as safety‐critical software, autonomous driving systems often make wrong judgments, seriously threatening human and property safety. LiDAR is one of the most critical sensors in autonomous vehicles, capable of accurately perceiving the three‐dimensional information of the environment. Nevertheless, the high cost of manually collecting and labeling point cloud data leads to a dearth of testing methods for LiDAR‐based perception modules. To bridge the critical gap, we introduce MetaLiDAR, a novel automated metamorphic testing methodology for LiDAR‐based autonomous driving systems. First, we propose three object‐level metamorphic relations for the domain characteristics of autonomous driving systems. Next, we design three transformation modules so that MetaLiDAR can generate natural‐looking follow‐up point clouds. Finally, we define corresponding evaluation metrics based on metamorphic relations. MetaLiDAR automatically determines whether source and follow‐up test cases meet the metamorphic relations based on the evaluation metrics. Our empirical research on five state‐of‐the‐art LiDAR‐based object detection models shows that MetaLiDAR can not only generate natural‐looking test point clouds to detect 181,547 inconsistent behaviors of different models but also significantly enhance the robustness of models by retraining with synthetic point clouds. [ABSTRACT FROM AUTHOR]

Despite the benefits such as road mobility and capacity enlargement, mortality lowering, and emissions drop, AI Autonomous Vehicles (AI-AVs) have introduced emerging threats that paired with cybersecurity threats, are changing the cybersecurity threat landscape. AI-AVs can be used as a moving intelligence collection for espionage and surveillance. They can be weaponized and operated for physical (logistical and transport) or furtive cyberattacks. AI-AVs have also introduced concerns about data privacy, governance, and ethical considerations. Therefore, it is crucial for both a domestic and foreign AI-AVs cross-disciplinary mitigation framework to address the threats introduced by AI-AVs. This study emphasizes solutions to AI-AV threats and addresses them through the cross-disciplinary framework mitigation approach that prepares society, nations, and individuals for ongoing transportation advancements, the rise of AI applications, and their threats despite the revolutionary benefits. The researchers proposed a cross-disciplinary approach that converges the strategic and resilient approach, including the transport department road safety administration, and all the entities involved in the coalition such as AI-AV manufacturers, transport stakeholders, lawmakers, advocates for safety, academia, local, and foreign entities. [ABSTRACT FROM AUTHOR]

With the rapid development of technology, unmanned vehicles have become a hot research topic in the field of intelligent transportation. Unmanned vehicles have many advantages, such as improving traffic efficiency, reducing traffic accidents, and reducing energy consumption. However, the controllability and safety of unmanned vehicles have always been a key issue in research. The Internet of Things can achieve information exchange and data sharing between vehicles, transportation facilities, traffic management centers, etc., providing real-time traffic and road condition information, and providing accurate data support for intelligent decision-making and path planning of unmanned vehicles. Therefore, the artificial intelligence unmanned vehicle control device based on IoT intelligent transportation has become an important research direction. This paper used deep reinforcement learning as the decision-making control algorithm, and designed a set of unmanned vehicle control system based on the DDPG (Deep Deterministic Policy Grad) algorithm, supplemented by meta DDPG algorithm, which is the knowledge of meta learning. Through the test of the simulation platform, it was concluded that the control system has good generalization. This study combined the Internet of Things and artificial intelligence algorithms, which has certain guiding significance for the development and application of unmanned vehicles in the future. [ABSTRACT FROM AUTHOR]

The application of chemicals through spraying is an essential component of agricultural management systems. However, the use of these chemical products results in the accumulation of residues in the soil, leading to a decline in soil fertility and plant diversity. Additionally, farmers who manually spray pesticides onto their crop fields are at risk of developing health issues such as tumors, hypersensitivity, allergies, and skin diseases. As the global population continues to grow and climate change impacts farmland ecosystems, the occurrence of pest epidemics in crops is becoming more frequent. Consequently, there is a greater demand for enhanced tools and methods to improve crop production. Unmanned ground vehicles (UGVs) have the potential to revolutionize agricultural spraying by offering efficient and effective applications of crop protection agrochemicals. This article provides an overview and consolidation of the present research and advancements in UGV application technologies and different sensors that are specifically designed for spray applications of agrichemicals. It examines the features of both hardware and software architecture for implementing control strategies, obstacle detection, and avoidance systems with real-time integrated systems, and the ability to perform variable-rate agrochemical applications. [ABSTRACT FROM AUTHOR]

Image segmentation and object detection using CNN (Convolutional Neural Network) and OpenCV (Open-Source Computer Vision) is a popular research area in the field of computer vision and autonomous driving. This method employs deep learning techniques and image processing algorithms to detect and track objects in real-time from a video stream captured by a camera mounted on a vehicle. The main aim of this project is to develop an accurate and robust object detection system that can detect various types of objects such as vehicles, pedestrians, and bicycles on the road. The proposed system uses a pre-trained CNN model to detect objects and OpenCV for further image processing and filtering. The system is evaluated on a publicly available dataset and achieves high accuracy and detection rates for various objects. The results of this study show the potential of using deep learning and image processing algorithms for real-time object detection in autonomous vehicles and traffic control systems. This study examines the use of Convolutional Neural Network techniques that have been used for image segmentation and object detection in road traffic. The study explored the use of Gaussian filters in image pre-processing. The study also trained the model to detect road traffic objects and return output/ feedback. The experimental result of the model was an accuracy of 96% across 26 classes and a recall of 92%. The study, therefore, recommends the use of object detection models in road traffic systems and autonomous vehicles. [ABSTRACT FROM AUTHOR]

Objective - Artificial Intelligence (AI) has become a pivotal technology in transforming logistics performance. This paper aims to comprehensively understand how AI-enabled solutions improve efficiency, accuracy, and responsiveness in logistics operations. The study focuses on synthesizing current research to explore AI applications across various logistics domains, such as predictive analytics, autonomous vehicles, and smart warehousing. Methodology/Technique -- A systematic review approach was used to gather and analyze existing literature on AI applications in logistics. The review covered studies published in recent years, highlighting the advancements and impact of AI on logistics processes. The methodology included selecting relevant sources, categorizing AI applications, and assessing their effects on different logistics functions. Finding -- The findings reveal that AI adoption substantially improves logistics operations, including enhanced operational performance, cost reduction, and increased customer satisfaction. Specific AI applications, such as predictive analytics for demand forecasting, autonomous vehicles for transportation, and smart warehousing for inventory management, were identified as key contributors to these improvements. However, challenges such as data privacy concerns and integration complexities were also noted. Novelty -- This study's novelty lies in its comprehensive analysis of AI applications across various logistics domains, offering a holistic view of AI's role in optimizing logistics performance. This paper highlights the benefits of AI adoption and addresses the associated challenges, providing insights into future research directions and practical implications for leveraging AI in logistics. [ABSTRACT FROM AUTHOR]

The rapid development and deployment of autonomous vehicles (AVs) present unprecedented opportunities and challenges in the transportation sector. While AVs promise enhanced safety, efficiency, and convenience, they also introduce significant cybersecurity vulnerabilities due to their reliance on advanced electronics, connectivity, and artificial intelligence (AI). This review examines the current state of cybersecurity in autonomous vehicles, identifying major threats such as remote hacking, sensor manipulation, data breaches, and denial of service (DoS) attacks. It also explores existing countermeasures including intrusion detection systems (IDSs), encryption, over-the-air (OTA) updates, and authentication protocols. Despite these efforts, numerous challenges remain, including the complexity of AV systems, lack of standardization, latency issues, and resource constraints. This review concludes by highlighting future directions in cybersecurity research and development, emphasizing the potential of AI and machine learning, blockchain technology, industry collaboration, and legislative measures to enhance the security of autonomous vehicles. [ABSTRACT FROM AUTHOR]

Due to the considerable number of deaths and vehicle accidents caused by a driver's inattention, as reported by WHO, automobile manufacturers are aiming to combine advanced driver assistance systems (ADAS) with artificial intelligence algorithms, particularly deep learning and computer vision techniques. One feature that assists drivers is traffic sign recognition, which is a technique that allows vehicles to detect and recognize road signs placed on the road. This can be achieved by the aid of computer vision and Convolutional Neural Networks (CNN). The main aim of this research is to propose and improve a CNN based-model that can be efficiently and accurately applied for embedded applications, this might be accomplished with the help of several preprocessing algorithms. An improved network model called LeNet-5 has been developed for the classification of traffic signs. Furthermore, the proposed model network is trained using both German Traffic Sign Recognition Benchmark (GTSRB) and extended GTSRB (EGTSRB) datasets. According to the test results, the improved LeNet-5 architecture obtained an accuracy of 99.12% on GTSRB and 99.78% on EGTSRB datasets respectively, which has a positive performance compared to other state-of-the-art papers in terms of accuracy. [ABSTRACT FROM AUTHOR]

The artificial intelligence required to create self-directed automobiles relies heavily on the capability of precisely perceiving the environment around oneself. Most self-driving automobiles include several detectors, which work together to form a multi-source perception of the surroundings. Extended use of a system that drives autonomously will introduce a variety of worldwide and local failure indications due to the extreme sensitivity of the instruments involved to ambient or environmental situations. These failure indications pose significant risks to the technique's security. The paper presents a real-time information synthesis system incorporating techniques for identifying flaws and accepting faults. The compact connection can be recognized if the qualities mentioned above are provided, and the input information properties may be retrieved in real-time. One way to use the newly introduced method for assessing device reliability is to compute the detectors' worldwide and local degrees of trustworthiness. In order to ensure the precision and dependability of information combination, problem data is filtered out, and monitor duplication is used to assess both the worldwide and local assurance levels of data from sensors at the moment. The chronological and geographic association of data from sensors allows for this. Experimental findings show that the network's algorithms can outperform current techniques in terms of both rapidity and precision and can pinpoint the object's location even when specific sensors are blurry or broken. This research established that the proposed hybrid structure benefits autonomous vehicles' real-time reliability and speed. [ABSTRACT FROM AUTHOR]

In the realm of autonomous driving tort, a significant disparity exists in the parties' access to autonomous driving data and essential technical information, resulting in challenges in unilateral proof. The traditional burden of proof framework in driving litigation is inadequate for direct application in the autonomous driving sphere. As we approach the era of widespread autonomous driving operations, there is an urgent need to clarify and redefine the allocation of the burden of proof in specific litigations. Utilizing comparative legal analysis and case studies, this paper delves into the disparities in the legislative provisions concerning the burden of proof for autonomous driving in Germany and China. China can learn from Germany's legislative precedence in shifting the burden of proof for "product defect" and "fault" onto the manufacturer, thereby requiring the infringed party to merely furnish preliminary evidence indicating a "causal relationship between the defect and the damage". This approach mitigates the evidentiary burden on the aggrieved party, clarifies the litigation procedures, incentivizes manufacturers to enhance the technology, reinforces risk management, and ultimately facilitates the progression of autonomous driving technology. [ABSTRACT FROM AUTHOR]

Introduction: With the development of artificial intelligence and autonomous driving technology, the application of motion recognition in automotive autonomous driving is becoming more and more important. The traditional feature extraction method uses adaptive search hybrid learning and needs to design the feature extraction process manually, which is difficult to meet the recognition requirements in complex environments. Methods: In this paper, a fusion algorithm is proposed to classify the driving characteristics through time-frequency analysis, and perform backpropagation operation in artificial neural network to improve the convergence speed of the algorithm. The performance analysis experiments of the study were carried out on Autov data sets, and the results were compared with those of the other three algorithms. Results: When the vehicle action coefficient is 227, the judgment accuracy of the four algorithms is 0.98, 0.94, 0.93 and 0.95, respectively, indicating that the fusion algorithm is stable. When the road sample is 547, the vehicle driving ability of the fusion algorithm is 4.7, which is the best performance among the four algorithms, indicating that the fusion algorithm has strong adaptability. Discussion: The results show that the fusion algorithm has practical significance in improving the autonomous operation ability of autonomous vehicles, reducing the frequency of vehicle accidents during driving, and contributing to the development of production, life and society. [ABSTRACT FROM AUTHOR]

The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain. [ABSTRACT FROM AUTHOR]

With the development of autonomous driving technology utilizing machine learning, AI, and sensors, research on autonomous driving control has become more active, and a large number of innovative studies are underway. In the near future, all autonomous vehicle fleets will be able to communicate with each other for sharing information and overall optimal traffic control will be achieved. One of the vehicle control systems that are based on the premise of such a fully automated society is the "signal-less intersection." There is an intersection traffic control method that achieves safe and rational route selection by using virtual walls (VWs), which are virtual obstacles, but there are issues in terms of total route length and reduction of computation time. To address the issues, we propose a method that (1) prunes unneeded paths and (2) arranges VWs in a stepwise manner. The effectiveness of the proposed method was evaluated by simulation, and the results showed that the total route length and execution time were reduced. [ABSTRACT FROM AUTHOR]

Predicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning. This task is very complex, as the behaviour of road agents depends on many factors and the number of possible future trajectories can be considerable (multi‐modal). Most prior approaches proposed to address multi‐modal motion prediction are based on complex machine learning systems that have limited interpretability. Moreover, the metrics used in current benchmarks do not evaluate all aspects of the problem, such as the diversity and admissibility of the output. The authors aim to advance towards the design of trustworthy motion prediction systems, based on some of the requirements for the design of Trustworthy Artificial Intelligence. The focus is on evaluation criteria, robustness, and interpretability of outputs. First, the evaluation metrics are comprehensively analysed, the main gaps of current benchmarks are identified, and a new holistic evaluation framework is proposed. Then, a method for the assessment of spatial and temporal robustness is introduced by simulating noise in the perception system. To enhance the interpretability of the outputs and generate more balanced results in the proposed evaluation framework, an intent prediction layer that can be attached to multi‐modal motion prediction models is proposed. The effectiveness of this approach is assessed through a survey that explores different elements in the visualisation of the multi‐modal trajectories and intentions. The proposed approach and findings make a significant contribution to the development of trustworthy motion prediction systems for autonomous vehicles, advancing the field towards greater safety and reliability. [ABSTRACT FROM AUTHOR]

The development of autonomous vehicles (AV) entails complex design, production, testing, and deployment procedures that require excellent information and knowledge management in the event of security breaches. As researchers and managers, we must have a good understanding of the development of AV technology. Communication and information exchange, as well as knowledge management (KM) strategies and approaches, are undoubtedly important components. The most difficult challenge is to save the lives of drivers and passengers who use and travel in an AV that is partially or entirely managed by a machine learning model (ML) and artificial intelligence (AI). In this paper, we attempt to investigate the manufacturing process of AVs and intelligent vehicles (IVs), emphasizing the importance of information management (IM) within the factory and processes that are not explicitly articulated in the majority of scenarios. Furthermore, we discuss our method for using the knowledge management life cycle for information exchange in an organization, which could allow for faster and more efficient resolution of security issues within vehicle operating systems. This study seeks to provide an essential theoretical foundation to characterize the future scope of integrated manufacturing, which integrates software and the industry that employs it within the vehicle. [ABSTRACT FROM AUTHOR]

Adaptive cruise control (ACC) is the core building block of future full autonomous driving. Numerous recent research demonstrated that Autonomous Vehicles (AVs) adopting shorter headways generally increase road capacity and may relieve congestion at bottlenecks for moderate demand scenarios. However, with high demand scenarios, bottlenecks can still be activated causing capacity breakdown. Therefore, extra control measures as dynamic traffic control near bottlenecks is necessary. The challenge is harder on urban freeways with consecutive bottlenecks which affect each other. This paper aims to improve the performance of ACC systems in a high demand scenario. A multi‐bottleneck dynamic headway control strategy based on deep reinforcement learning (DRL) that adapts headways to optimize traffic flow and minimize delay is proposed. The controller dynamically assigns an optimal headway for each controlled section, based on state measurement representing the current traffic conditions. The case study is a freeway stretch with three consecutive bottlenecks which is then extended to include eight bottlenecks. Three different RL agent configurations are presented and compared. It is quantitatively demonstrated that the proposed control strategy improves traffic and enhances the system delay by up to 22.30%, and 18.87% compared to shortest headway setting for the three‐bottleneck and the eight‐bottleneck networks, respectively. [ABSTRACT FROM AUTHOR]

With the advancement of artificial intelligence, autonomous machines are featured with the ability to diagnose and assess the structural health of different systems. This paper presents a scalable mobile platform employed to autonomously and intelligently detect online small cracks on roads using a live camera feed and Artificial Intelligence (AI) methods. The robotic artifact is equipped with a vision-based localization system to enable autonomous navigation areas where GPS (Global Positioning System) may be poor or intermittent. The proposed approach runs at the edge a model of Convolutional Neuronal Networks (CNN) based on the Resnet 18 architecture to classify the image feed between cracks and those without cracks after training them with a combination of two public data sets and a data set generated in-house. The mobile robotic platform is scalable, depending on the particular context and requirements of the application. As opposed to off-line assessment tools, experimental results show the real-time capabilities of the system to autonomously navigate and detect cracks on a pavement structure with an accuracy of 95%. [ABSTRACT FROM AUTHOR]

Autonomous Underwater Vehicles (AUVs), as a member of the unmanned intelligent ocean vehicle group, can replace human beings to complete dangerous tasks in the ocean. It is of great significance to apply reinforcement learning (RL) to AUVs to realize intelligent control. This paper proposes an AUV obstacle avoidance framework based on event-triggered reinforcement learning. Firstly, an environment perception model is designed to judge the relative position relationship between the AUV and all unknown obstacles and known targets. Secondly, considering that the detection range of AUVs is limited, and the proposed method needs to deal with unknown static obstacles and unknown dynamic obstacles at the same time, two different event-triggered mechanisms are designed. Soft actor–critic (SAC) with a non-policy sampling method is used. Then, improved reinforcement learning and the event-triggered mechanism are combined in this paper. Finally, a simulation experiment of the obstacle avoidance task is carried out on the Gazebo simulation platform. Results show that the proposed method can obtain higher rewards and complete tasks successfully. At the same time, the trajectory and the distance between each obstacle confirm that the AUV can reach the target well while maintaining a safe distance from static and dynamic obstacles. [ABSTRACT FROM AUTHOR]