相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Dafeng Wang et al.
Summary: In this paper, a novel Sequence Entropy Energy-based Model (SEEM) is proposed to address the limitations of current trajectory prediction models. SEEM achieves diversity in candidate trajectory generation by optimizing sequence entropy, and improves accuracy and stability through probability distribution clipping mechanism and energy network. Experimental results demonstrate that SEEM outperforms the state-of-the-art approaches in terms of diversity, accuracy, and stability of pedestrian trajectory prediction.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Civil
Yuhuan Lu et al.
Summary: Accurate trajectory prediction of surrounding vehicles is crucial for the sustainability and safety of connected and autonomous vehicles. This study proposes a novel Heterogeneous Context-Aware Graph Convolutional Networks that extracts hidden contexts from individual historical trajectories, driving scenes, and inter-vehicle interactions. The model achieves high prediction accuracy and stability on real-world datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Xiaoyu Mo et al.
Summary: The article introduces a method for simultaneous trajectory prediction for multiple heterogeneous traffic participants, which addresses the challenges of varying number of agents and multiple factors affecting their future motions. The proposed three-channel framework and HEAT network can achieve simultaneous trajectory predictions for multiple agents under complex traffic situations, with state-of-the-art performance in terms of prediction accuracy.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Yu Wang et al.
Summary: This paper proposes a novel multi-vehicle collaborative learning model for vehicle trajectory prediction, which incorporates spatial and temporal information among vehicles, as well as a generative adversarial network to handle multi-modal characteristics. Experimental results show that this approach outperforms existing techniques. Additionally, qualitative analyses are presented for multi-modal vehicle trajectory generation and the impacts of surrounding vehicles on trajectory prediction.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Lei Lin et al.
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2022)
Article
Engineering, Civil
Jiachen Li et al.
Summary: STG-DAT is a generic generative neural system for multi-agent trajectory prediction, combining relational reasoning and scene context information, enhancing feasibility constraints and achieving improved model performance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jiyao An et al.
Summary: This paper investigates vehicle trajectory prediction problems in real traffic scenarios by fully harnessing the spatio-temporal dependencies between multiple vehicles. A new dynamic graph and interaction-aware neural network model called DGInet is proposed to better describe the relationship between driving vehicles and capture the basic spatial interaction features of the driving scene.
Article
Computer Science, Information Systems
Luyao Ye et al.
Summary: Modeling interactions among vehicles is critical for improving efficiency and safety in autonomous driving. Most existing works consider interaction information implicitly and do not explore shared interaction representations. This article proposes a general graph self-attention network to learn interaction representations and utilizes pretraining and fine-tuning steps.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Kunpeng Zhang et al.
IEEE Transactions on Intelligent Vehicles
(2022)
Article
Engineering, Civil
Vinit Katariya et al.
Summary: Vehicle trajectory prediction is crucial for intelligent transportation systems, and DeepTrack, a novel deep learning algorithm, offers high accuracy, smaller model sizes, and simpler computations for real-time applications.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Xiaobo Chen et al.
Summary: This paper proposes a novel spatial-temporal dynamic attention network for vehicle trajectory prediction, which comprehensively captures temporal and social patterns. Different sequential models are used to capture temporal correlation and social interaction, along with a driving intention-specific feature fusion mechanism for multi-modal trajectory prediction.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Zihao Sheng et al.
Summary: This paper proposes a graph-based spatial-temporal convolutional network (GSTCN) to predict future trajectory distributions of neighbor vehicles. The network combines graph convolutional network (GCN) and convolutional neural network (CNN) to capture spatial interactions and temporal features between vehicles, resulting in accurate trajectory predictions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Zhi Zhong et al.
Summary: To achieve safe and efficient navigation for autonomous vehicles in driving environments, this paper proposes a new learning algorithm called Spatial-Temporal Generative Model (STGM) that leverages a stochastic generative model to address the modal distribution problem. Empirical evaluation on two public datasets demonstrates that STGM outperforms baseline models such as Covernet and MTP.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiangbei Yue et al.
Summary: In this paper, a new method combining model-based and model-free techniques for trajectory prediction is proposed. By using an explicit physics model and a deep neural network, the method achieves excellent performance in modeling pedestrian behaviors and data fitting. The method also demonstrates better generalizability in different scenarios and provides explanations for pedestrian behaviors.
COMPUTER VISION, ECCV 2022, PT XXXIV
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yi Xu et al.
Summary: This study proposes a novel Transferable Graph Neural Network (T-GNN) framework for pedestrian trajectory prediction and domain alignment. By exploring structural motion knowledge and individual-level feature representations, it addresses the disparities across different trajectory domains.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Yanjun Huang et al.
Summary: This paper provides a comprehensive and comparative review of trajectory-prediction methods proposed over the last two decades for autonomous driving. It introduces and analyzes popular methods based on physics, classic machine learning, deep learning, and reinforcement learning, and evaluates their performance.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2022)
Article
Engineering, Electrical & Electronic
Hongyan Guo et al.
Summary: This article proposes a trajectory prediction method based on a dual-attention mechanism and long short-term memory encoding, which enhances driving safety and driving assistance for intelligent vehicles. Tests show that this method achieves higher prediction accuracy than existing models and can analyze the impact of neighboring vehicles on the target vehicle's trajectory.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Ya Wu et al.
Summary: In this paper, a Hierarchical Spatio-Temporal Attention architecture (HSTA) is proposed to capture spatial interactions using graph attention mechanism (GAT), encode temporal correlations with multi-head attention mechanism (MHA), and integrate spatial and temporal interactions with a state gated fusion (SGF) layer. The experimental results demonstrate that the proposed method outperforms baselines on pedestrian and vehicle datasets, achieving state-of-the-art achievements.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Yingfeng Cai et al.
Summary: This study introduces a novel Environment-Attention Network model (EA-Net) to address the challenge of modeling interaction relationships in vehicle trajectory prediction. By constructing a parallel structure of Graph Attention network and Convolutional social pooling, comprehensive and effective feature information is extracted, leading to superior prediction accuracy compared to existing models in testing scenarios.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Liang Zhao et al.
Summary: The study introduces a vehicle trajectory prediction method based on Generative Adversarial Networks, including vehicle coordinate transformation, neural network prediction model, and vehicle turning model. Experimental results show that GAN-VEEP exhibits higher effectiveness in terms of average accuracy, mean absolute error, and root-mean-squared error compared to other models.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Robotics
Vasileios Lefkopoulos et al.
Summary: This study addresses the prediction of vehicle motion around an autonomous car, focusing on improved motion planning without inter-vehicle communication. A filtering scheme and an optimization-based projection are used for single-vehicle estimation and non-colliding predictions. The approach is extended to estimate multiple vehicles simultaneously with a dynamically adapted priority list.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Automation & Control Systems
Omveer Sharma et al.
Summary: Autonomous vehicles are gaining attention in academic and industrial research due to their advantages such as safety improvement and reduced traffic congestion. Intelligent motion and behavior planning play crucial roles in decision making process, considering factors like safety, comfort, and traffic rules. Various techniques have been developed over the past few decades, but there is still a need for rigorous evaluation and improvement of existing approaches.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Robotics
Yi Xu et al.
Summary: Accurate trajectory prediction is crucial for robot navigation, especially in crowded scenes. The proposed Global Social Spatial-Temporal Attentive Neural Network combines spatial interaction features and temporal dependency to achieve better performance on various datasets.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Xulei Liu et al.
Summary: The study proposes a trajectory prediction method based on the CFPG model, which combines maneuver recognition and deep conditional generative models to improve accuracy. Results show that compared to traditional methods, this approach can predict vehicle trajectories more accurately and reliably.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Automation & Control Systems
Runqi Chai et al.
Summary: A novel swarm intelligence-based algorithm is proposed for generating multiobjective optimal overtaking trajectories of autonomous ground vehicles. The algorithm optimizes maneuver time duration, trajectory smoothness, and vehicle visibility while considering different types of constraints.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoyu Mo et al.
Summary: Integrating trajectory prediction into decision-making and planning modules of modular autonomous driving systems is crucial for enhancing the safety and efficiency of self-driving vehicles. The proposed GNN-RNN based Encoder-Decoder network effectively predicts multi-vehicular trajectories by extracting dynamics features and encoding inter-vehicular interactions. The evaluation on the NGSIM US-101 dataset demonstrates the model's capability to predict a target vehicle's trajectory in situations with varying numbers of surrounding vehicles.
2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhezhang Ding et al.
Summary: This research proposes a unified prediction framework that models the interaction between vehicles and the relation between vehicles and the environment. A dual graph attention module is adopted for modeling, leading to effective trajectory prediction. Experimental results on the NGSIM dataset demonstrate the framework's effectiveness, with maneuver-based statistics revealing the model's prediction ability under different maneuver trajectories.
2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)
(2021)
Article
Computer Science, Artificial Intelligence
Kaouther Messaoud et al.
Summary: This paper focuses on vehicle trajectory prediction by modeling vehicle interactions, utilizing an attention mechanism to highlight neighboring vehicles' future states, and considering multiple potential futures based on different goals and driving behaviors, leading to outperforming the state-of-the-art performances on highway datasets through a combination of global and partial attention.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2021)
Article
Engineering, Electrical & Electronic
Yang Xing et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Engineering, Electrical & Electronic
Cong Fei et al.
IET INTELLIGENT TRANSPORT SYSTEMS
(2020)
Article
Robotics
Rohan Chandra et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Engineering, Civil
Ling Zhao et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Proceedings Paper
Automation & Control Systems
Jiacheng Pan et al.
2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
(2020)
Article
Engineering, Electrical & Electronic
Jun Yan et al.
IET INTELLIGENT TRANSPORT SYSTEMS
(2020)
Article
Engineering, Civil
Lian Hou et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2020)
Article
Robotics
Yuxiang Sun et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Engineering, Electrical & Electronic
Yijing Wang et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2019)
Article
Automation & Control Systems
Guotao Xie et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2018)
Article
Engineering, Civil
Matthias Schreier et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2016)
