IEEE Transactions on Intelligent Vehicles最新文献

{"title":"A Learning-Based Anti-Swing Trajectory Refinement Approach for UAVs With Cable-Suspended Payload Without Offline Training","authors":"Yiming Wu;Pengyu Zhao;Dingkun Liang;Jiuxiang Dong","doi":"10.1109/TIV.2024.3391788","DOIUrl":"https://doi.org/10.1109/TIV.2024.3391788","url":null,"abstract":"In this article, a learning-based anti-swing trajectory refinement approach for unmanned aerial vehicles (UAVs) with cable-suspended payload is proposed to achieve the quadrotor's actual position and the payload's swing suppression. Specifically, the proposed trajectory is composed of two parts, one is for guaranteeing the position of the quadrotor, and the other is for suppressing the payload's swing online. The first part of the generated trajectory is related to an arbitrary given trajectory, and the second part is a neural network based term with designed online updating weights. The convergence of the quadrotor position error and payload swing angles are proved by Lyapunov-based analysis. Simulation results are presented to validate the effectiveness of the proposed method.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6950-6959"},"PeriodicalIF":14.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144500952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attention-Based Value Classification Reinforcement Learning for Collision-Free Robot Navigation","authors":"Chao Sun;Xing Wu;Yuanda Wang;Changyin Sun","doi":"10.1109/TIV.2024.3391007","DOIUrl":"https://doi.org/10.1109/TIV.2024.3391007","url":null,"abstract":"Collision avoidance is a crucial technique to achieve safe and efficient robotic vehicle navigation in unknown environments. However, moving obstacles with unpredictability in dynamic scenarios, usually increase the difficulty and complexity in collision avoidance of robotic vehicles. To enhance the stability of collision avoidance and boost its adaptability to uncertain dynamic scenes, a new attention-based value classification actor-critic (AVCAC) architecture is proposed. It is an end-to-end robot navigation model that utilizes imperfect local observation to directly plan accurate collision-free motion commands. First, we design a value-classified rollout replaybuffer to categorize the experiences into different pools. It can prevent any overfitting or bias that may result from repeatedly sampling experiences of a certain type during policy learning. Then, we improve the conventional actor-critic network with a multi-head local attention module to extract the local observations at entity-level. This way, the collision avoidance system can focus on key environmental features to operate more efficiently and respond more swiftly to dynamic changes in the environment. Moreover, a lookahead multi-step prediction (LMP) reward setting is devised in the AVCAC-based reinforcement learning (RL) framework to facilitate more informed and forward-looking decision-making. Finally, the policy entropy (PE) and policy delay (PD) are extended to AVCAC model to enhance policy exploration and make policy more robust. Extensive experimental results reveal that our method can generate time-efficient and collision-free guide paths to dodge collisions under complex dynamic environments.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6898-6911"},"PeriodicalIF":14.0,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing","authors":"Jiahang Li;Yikang Zhang;Peng Yun;Guangliang Zhou;Qijun Chen;Rui Fan","doi":"10.1109/TIV.2024.3388726","DOIUrl":"https://doi.org/10.1109/TIV.2024.3388726","url":null,"abstract":"The recent advancements in deep convolutional neural networks have shown significant promise in the domain of road scene parsing. Nevertheless, the existing works focus primarily on freespace detection, with little attention given to hazardous road defects that could compromise both driving safety and comfort. In this article, we introduce RoadFormer, a novel Transformer-based data-fusion network developed for road scene parsing. RoadFormer utilizes a duplex encoder architecture to extract heterogeneous features from both RGB images and surface normal information. The encoded features are subsequently fed into a novel heterogeneous feature synergy block for effective feature fusion and recalibration. The pixel decoder then learns multi-scale long-range dependencies from the fused and recalibrated heterogeneous features, which are subsequently processed by a Transformer decoder to produce the final semantic prediction. Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10,407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes. Extensive experimental evaluations conducted on our SYN-UDTIRI dataset, as well as on three public datasets, including KITTI road, CityScapes, and ORFD, demonstrate that RoadFormer outperforms all other state-of-the-art networks for road scene parsing. Specifically, RoadFormer ranks first on the KITTI road benchmark.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 7","pages":"5163-5172"},"PeriodicalIF":14.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CASKA-CRT: Chinese Remainder Theorem Empowered Certificateless Aggregate Signcryption Scheme With Key Agreement in IoVs","authors":"Yingzhe Hou;Yue Cao;Hu Xiong;Zhili Sun;Shahid Mumtaz;Daxin Tian","doi":"10.1109/TIV.2024.3388724","DOIUrl":"https://doi.org/10.1109/TIV.2024.3388724","url":null,"abstract":"To enhance the privacy of messages in Internet of Vehicles (IoVs), it is critical to preserve the communication security between Road Side Unit (RSU) and numerous vehicles. The primitive of signcryption is introduced to guarantee the confidentiality, integrity and unforgeability of transmitted messages. Nevertheless, the existing signcryption schemes fail to achieve a balance between security and efficiency. In this paper, we construct a Chinese remainder theorem (CRT) empowered certificateless aggregate signcryption scheme with key agreement (CASKA-CRT). As the vehicle joins and leaves dynamically, the proposed scheme can ensure the dynamic security via one modulo division operation. Besides, the certificateless aggregate signcryption and key agreement mechanisms are embedded. The former idea can both address the certificate management and key escrow problems, while the latter technology can create authentication as a premise of secure communication. Based on this construction, the hash-to-group operation and bilinear pairing are avoided, to realize a faster verification with the increased number of messages. Moreover, the security of proposed scheme is proved under the random oracle model. Finally, the performance analysis demonstrates the advantage of CASKA-CRT in terms of security and reliability over related works.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6814-6829"},"PeriodicalIF":14.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Relevance Inference Based on Direct Contribution: Counterfactual Explanation to Deep Networks for Intelligent Decision-Making","authors":"Xinyu Li;Xiaoguang Gao;Chenfeng Wang;Qianglong Wang;Bo Li;Kaifang Wan","doi":"10.1109/TIV.2024.3390426","DOIUrl":"https://doi.org/10.1109/TIV.2024.3390426","url":null,"abstract":"With the widespread application of Deep Learning (DL), the black-box characteristics of DL raise questions, especially in high-stake decision-making fields like autonomous driving. Consequently, there is a growing demand for research on the interpretability of DL, leading to the emergence of eXplainable Artificial Intelligence as a current research hotspot. Current research on DL interpretability primarily focuses on transparency and post-hoc interpretability. Enhancing interpretability in transparency often requires targeted modifications to the model structure, potentially compromising the model's accuracy. Conversely, improving the interpretability of DL models based on post-hoc interpretability usually does not necessitate adjustments to the model itself. To provide a fast and accurate counterfactual explanation of DL without compromising its performance, this paper proposes a post-hoc interpretation method called relevance inference based on direct contribution to employ counterfactual reasoning in DL. In this method, direct contribution is first designed by improving Layer-wise Relevance Propagation to measure the relevance between the outputs and the inputs. Subsequently, we produce counterfactual examples based on direct contribution. Ultimately, counterfactual results for the DL model are obtained with these counterfactual examples. These counterfactual results effectively describe the behavioral boundaries of the model, facilitating a better understanding of its behavior. Additionally, direct contribution offers an easily implementable interpretable analysis method for studying model behavior. Experiments conducted on various datasets demonstrate that relevance inference can be more efficiently and accurately generate counterfactual examples compared to the state-of-the-art methods, aiding in the analysis of behavioral boundaries in intelligent decision-making models for vehicles.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6881-6897"},"PeriodicalIF":14.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Online Spatial-Temporal Graph Trajectory Planner for Autonomous Vehicles","authors":"Jilan Samiuddin;Benoit Boulet;Di Wu","doi":"10.1109/TIV.2024.3389640","DOIUrl":"10.1109/TIV.2024.3389640","url":null,"abstract":"The autonomous driving industry is expected to grow by over 20 times in the coming decade and, thus, motivate researchers to delve into it. The primary focus of their research is to ensure safety, comfort, and efficiency. An autonomous vehicle has several modules responsible for one or more of the aforementioned items. Among these modules, the trajectory planner plays a pivotal role in the safety of the vehicle and the comfort of its passengers. The module is also responsible for respecting kinematic constraints and any applicable road constraints. In this paper, a novel online spatial-temporal graph trajectory planner is introduced to generate safe and comfortable trajectories. First, a spatial-temporal graph is constructed using the autonomous vehicle, its surrounding vehicles, and virtual nodes along the road with respect to the vehicle itself. Next, the graph is forwarded into a sequential network to obtain the desired states. To support the planner, a simple behavioral layer is also presented that determines kinematic constraints for the planner. Furthermore, a novel potential function is also proposed to train the network. Finally, the proposed planner is tested on three different complex driving tasks, and the performance is compared with two frequently used methods. The results show that the proposed planner generates safe and feasible trajectories while achieving similar or longer distances in the forward direction and comparable comfort ride.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6843-6852"},"PeriodicalIF":14.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140687705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enabling Seamless Data Security, Consensus, and Trading in Vehicular Networks","authors":"Emanuel Vieira;João Almeida;Joaquim Ferreira;Paulo C. Bartolomeu","doi":"10.1109/TIV.2024.3388247","DOIUrl":"https://doi.org/10.1109/TIV.2024.3388247","url":null,"abstract":"Cooperative driving is an emerging paradigm aimed at enhancing the safety and efficiency of autonomous vehicles. To ensure successful cooperation, road users must reach a consensus for making collective decisions, while recording vehicular data to analyze and address failures related to such agreements. This data has the potential to provide valuable insights into various vehicular events, while also potentially improving accountability measures. Furthermore, vehicles may benefit from the ability to negotiate and trade services among themselves, adding value to the cooperative driving framework. However, the majority of proposed systems aiming to ensure data security, consensus, or service trading, lack efficient and thoroughly validated mechanisms that consider the distinctive characteristics of vehicular networks. These limitations are amplified by a dependency on the centralized support provided by the infrastructure. Furthermore, corresponding mechanisms must diligently address security concerns, especially regarding potential malicious or misbehaving nodes, while also considering the inherent constraints of the wireless medium. We introduce the <italic>Verifiable Event Extension</i> (VEE), an applicational extension designed for Intelligent Transportation System (ITS) messages. The VEE operates seamlessly with any existing standardized vehicular communications protocol, addressing crucial aspects of data security, consensus, and trading with minimal overhead. To achieve this, VEE comprises data associated with blockchain techniques, Byzantine fault tolerance (BFT) consensus protocols, and cryptocurrency-based mechanics. Using this mechanism, we piggyback new protocols on the existing ITS traffic, minimally impacting the vehicular network. To assess our proposal's feasibility and lightweight nature, we employed a hardware-in-the-loop setup for analysis. Experimental results demonstrate the viability and efficiency of the VEE extension in overcoming the challenges posed by the distributed and opportunistic nature of wireless vehicular communications.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 10","pages":"6716-6737"},"PeriodicalIF":14.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Safety in Nonlinear Systems: Design and Stability Analysis of Adaptive Cruise Control","authors":"Fan Yang;Haoqi Li;Maolong Lv;Jiangping Hu;Qingrui Zhou;Bijoy K. Ghosh","doi":"10.1109/TIV.2024.3388425","DOIUrl":"https://doi.org/10.1109/TIV.2024.3388425","url":null,"abstract":"The safety of autonomous driving systems, particularly self-driving vehicles, remains of paramount concern. These systems exhibit affine nonlinear dynamics and face the challenge of executing predefined control tasks while adhering to state and input constraints to mitigate risks. However, achieving safety control within the framework of control input constraints, such as collision avoidance and maintaining system states within secure boundaries, presents challenges due to limited options. In this article, we introduce a novel approach to address safety concerns by transforming safety conditions into control constraints with a relative degree of 1. This transformation is facilitated through the design of control barrier functions, enabling the creation of a safety control system for affine nonlinear networks. Subsequently, we formulate a robust control strategy that incorporates safety protocols and conduct a comprehensive analysis of its stability and reliability. To illustrate the effectiveness of our approach, we apply it to a specific problem involving adaptive cruise control. Through simulations, we validate the efficiency of our model in ensuring safety without compromising control performance. Our approach signifies significant progress in the field, providing a practical solution to enhance safety for autonomous driving systems operating within the context of affine nonlinear dynamics.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6803-6813"},"PeriodicalIF":14.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatiotemporal Receding Horizon Control With Proactive Interaction Towards Autonomous Driving in Dense Traffic","authors":"Lei Zheng;Rui Yang;Zengqi Peng;Michael Yu Wang;Jun Ma","doi":"10.1109/TIV.2024.3389827","DOIUrl":"https://doi.org/10.1109/TIV.2024.3389827","url":null,"abstract":"In dense traffic scenarios, ensuring safety while keeping high task performance for autonomous driving is a critical challenge. To address this problem, this paper proposes a computationally-efficient spatiotemporal receding horizon control (ST-RHC) scheme to generate a safe, dynamically feasible, energy-efficient trajectory in control space, where different driving tasks in dense traffic can be achieved with high accuracy and safety in real time. In particular, an embodied spatiotemporal safety barrier module considering proactive interactions is devised to mitigate the effects of inaccuracies resulting from the trajectory prediction of other vehicles. Subsequently, the motion planning and control problem is formulated as a constrained nonlinear optimization problem, which favorably facilitates the effective use of off-the-shelf optimization solvers in conjunction with multiple shooting. The effectiveness of the proposed ST-RHC scheme is demonstrated through comprehensive comparisons with state-of-the-art algorithms on synthetic and real-world traffic datasets under dense traffic, and the attendant outcome of superior performance in terms of accuracy, efficiency and safety is achieved.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6853-6868"},"PeriodicalIF":14.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model-Free Safety Critical Model Predictive Control for Mobile Robot in Dynamic Environments","authors":"Minh-Nhat Nguyen;Mien Van;Stephen McIlvanna;Yuzhu Sun;Jack Close;Kabirat Olayemi;Yan Jin","doi":"10.1109/TIV.2024.3389111","DOIUrl":"https://doi.org/10.1109/TIV.2024.3389111","url":null,"abstract":"Within the context of Nonlinear Model Predictive Control (NMPC) design for autonomous mobile robots, which face challenges such as parametric uncertainty and measurement inaccuracies, focusing on dynamic modelling and parameter identification becomes crucial. This paper presents a novel safety-critical control framework for a mobile robot system that utilises NMPC with a prediction model derived entirely from noisy measurement data. The Sparse Identification of Nonlinear Dynamics (SINDY) is employed to predict the system's state under actuation effects. Meanwhile, the Control Barrier Function (CBF) is integrated into the NMPC as a safety-critical constraint, ensuring obstacle avoidance even when the robot's planned path is significantly distant from these obstacles. The closed-loop system demonstrates Input-to-State Stability (ISS) with respect to the prediction error of the learned model. The proposed framework undergoes exhaustive analysis in three stages, training, prediction, and control, across varying noise levels in the state data. Additionally, validation in Matlab and Gazebo illustrates that the NMPC-SINDY-CBF approach enables smooth, accurate, collision-free movement, even with measurement noise and short prediction times. Our findings, supported by tests conducted with the Husky A200 robot, confirm the approach's applicability in real-time scenarios.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"6830-6842"},"PeriodicalIF":14.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}