Explore the vast range of titles available.

Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving (AD) system. However, most proposed methods aim at addressing one of the two challenges mentioned above with a single model. To tackle this dilemma, this paper proposes spatio‐temporal semantics and interaction graph aggregation for multi‐agent perception and trajectory forecasting (ST‐SIGMA), an efficient end‐to‐end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework. ST‐SIGMA adopts a trident encoder–decoder architecture to learn scene semantics and agent interaction information on bird’s‐eye view (BEV) maps simultaneously. Specifically, an iterative aggregation network is first employed as the scene semantic encoder (SSE) to learn diverse scene information. To preserve dynamic interactions of traffic agents, ST‐SIGMA further exploits a spatio‐temporal graph network as the graph interaction encoder. Meanwhile, a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed. Extensive experiments on the nuScenes data set have demonstrated that the proposed ST‐SIGMA achieves significant improvements compared to the state‐of‐the‐art (SOTA) methods in terms of scene perception and trajectory forecasting, respectively. Therefore, the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in real‐world AD scenarios.

Transformer-based models have demonstrated outstanding performance in trajectory prediction; however, their complex architecture demands substantial computing power, and their performance degrades significantly in long-term prediction. A transformer model was developed to predict vehicle trajectory in urban low-speed T-intersections. Microscopic traffic simulation data were generated to train the trajectory-prediction model; furthermore, validation data focusing on atypical scenarios were also produced. The appropriate loss function to improve prediction accuracy was explored, and the optimal input/output sequence length for efficient data management was examined. Various driving-characteristics data were employed to evaluate the model’s generalization performance. Consequently, the smooth L1 loss function showed outstanding performance. The optimal length for the input and output sequences was found to be 1 and 3 s, respectively, for trajectory prediction. Additionally, improving the model structure—rather than diversifying the training data—is necessary to enhance generalization performance in atypical driving situations. Finally, this study confirmed that the additional features such as vehicle position and speed variation extracted from the original trajectory data decreased the model accuracy by about 21%. These findings contribute to the development of applicable lightweight models in edge computing infrastructure to be installed at intersections, as well as the development of a trajectory prediction and accident analysis system for various scenarios.

The low-altitude airspace of bird flocks is gradually shared by unmanned aerial vehicles (UAVs), posing safety risks that necessitate accurate trajectory forecasting. However, existing vision-based methods often treat trajectory prediction and UAV detection as separate tasks, assume light-tailed Gaussian noise, and rely on heavy backbones. These limitations, when applied to bird trajectory forecasting, limit uncertainty calibration and embedded deployment in ground-based monocular surveillance. In this work, we propose a unified framework for low-altitude monitoring. Its core, Mini-BirdFormer, combines a lightweight Transformer encoder with a Student-t mixture density head to model heavy-tailed flight dynamics and produce calibrated uncertainty. Experiments on a real-world dataset show the model achieves strong long-horizon performance with only 1.05 million parameters, attaining a minADE of 0.785 m and reducing negative log-likelihood from 1.25 to −2.01 (lower is better) compared with a Gaussian Long Short-Term Memory (LSTM) baseline. Crucially, it enables low-latency inference on resource-constrained platforms at 616 FPS. Additionally, a system-level extension supports zero-shot UAV detection via open-vocabulary learning, attaining 92% recall without false alarms. Results demonstrate that combining heavy-tailed probabilistic modeling with a compact backbone provides a practical, deployable approach for monitoring shared airspace.

The integrated strapdown inertial navigation system (SINS)/global navigation satellite system (GNSS) has been widely adopted in railway positioning applications. However, conventional filtering-based approaches are fundamentally constrained by their dependence on instantaneous state estimates while failing to exploit valuable historical measurement information. To overcome this limitation, we develop a factor graph optimization (FGO) framework to enhance data utilization efficiency. During GNSS signal outages, existing implementations typically preserve only SINS factors while excluding GNSS observations, leading to unbounded error growth. To bridge this gap, our novel solution integrates a gated recurrent unit (GRU) with an Improved Bidirectional Long Short-Term Memory (IBiLSTM) network to generate accurate pseudo-GNSS observations through effective learning from both preceding and subsequent GNSS data sequences. Comprehensive evaluation under GNSS-denied conditions demonstrates that our approach achieves significant improvements over conventional neural network-aided methods, with horizontal root mean square error (RMSE) reductions of 49.22% (simulation) and 36.24% (onboard vehicle). Subsequent FGO processing yields additional performance gains, further reducing RMSE by 46.67% (simulation) and 35.31% (onboard vehicle). This innovative methodology effectively maintains positioning accuracy and ensures navigation continuity during GNSS outages, thereby offering a robust solution for train positioning systems in challenging environments.

Understanding spatiotemporal coordination of players in team sports is key to movement models, pattern detection, and computational tactics. Existing generative models propose to capture all stochasticity by a single latent variable and may suffer from entangled representations, or aim to uncover interaction structures of players but then do not focus on their generative ability. As a remedy, we propose a hierarchical latent variable model for predicting trajectories of multiple players. In the generative model, both, discrete role assignments and a latent interaction graph are sampled to allow for different models in subsequent node updates and message passing operations between nodes, where standard Gaussian latent variables are employed per agent and timestep. We cast our approach as a variational autoencoder that provides a disentangled latent space to capture variability in team sport movements and propose a neural architecture for its optimization. We empirically evaluate our approach on tracking data from basketball and soccer and observe that our contribution outperforms the state-of-art in all experiments.

The precise forecasting of mesoscale eddy trajectories holds significant importance for understanding their mechanisms in driving global oceanic mass and heat transport. However, mesoscale eddies are influenced by numerous stochastic and uncertain factors, leading to substantial fluctuations in their attribute variables. Additionally, the trajectories of eddies are related to historical trends and interact with surrounding eddies. These render the accurate forecasting of mesoscale eddy trajectories a formidable challenge. This study proposes a novel dynamic forecasting framework for eddies’ trajectories, termed EddyGnet, a dual graph neural network framework that synergistically models the complex multivariable association and the spatiotemporal eddy association. In this framework, the dynamic association among eddy attribute variables is first explored by a multivariable association graph (MAG) learning module. Subsequently, the spatial and temporal association among eddies are concurrently analyzed using a spatiotemporal eddy association graph (STEAG) learning module. Finally, a decayed volatility loss function is designed to properly handle the complex and variable data features and improve the forecasting performance. The experimental results on the eddy dataset verify the effectiveness of our proposed EddyGnet, demonstrating superior predictive accuracy and stability compared with existing classical methods. The findings advance the mechanistic understanding of eddy dynamics and provide a transferable paradigm for geoscientific spatiotemporal modeling.

To enhance the rationality of lane‐changing decisions and the adaptability of trajectory planning, this study incorporates short‐term driving styles to construct a multiobjective optimized lane‐changing trajectory planning model based on naturalistic driving data. First, lane‐changing behavior rules were defined to extract lane‐changing and lane‐keeping data. Essential factors influencing lane‐changing behavior were identified using the eXtreme Gradient Boosting (XGBoost) model. Based on the essential factors, drivers were classified into three categories (conservative, moderate, and aggressive) using Density‐Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, which revealed the behavioral difference during lane‐changing. Subsequently, an attention‐enhanced long short‐term memory (LSTM) network was employed to predict surrounding vehicle trajectories, generating dynamically updated environmental parameters. Further considering comfort and safety benefits during lane‐changing, a multiobjective trajectory planning model was developed. Reinforcement learning algorithms iteratively optimized the trajectories to derive the optimal trajectory. Finally, the behavioral characteristics of planned trajectories for the three categories of drivers and the deviations between planned and actual trajectories were compared. Results indicate that planned trajectories exhibit shorter lane‐changing length and higher efficiency compared with actual trajectories. Planned trajectory can smooth microlevel behavior and improve safety and comfort during lane‐changing. For different types of drivers, conservative drivers show the longest lane‐changing length but smallest headway space distances, which reflects drivers’ caution during lane‐changing. Aggressive drivers mostly focus on speed improvement. The findings can be applied to vehicle trajectory planning in connected environments, which can enhance the lane‐changing efficiency while ensuing safety.

Analysis of pedestrians’ motion is important to real-world applications in public scenes. Due to the complex temporal and spatial factors, trajectory prediction is a challenging task. With the development of attention mechanism recently, transformer network has been successfully applied in natural language processing, computer vision, and audio processing. We propose an end-to-end transformer network embedded with random deviation queries for pedestrian trajectory forecasting. The self-correcting scheme can enhance the robustness of the network. Moreover, we present a co-training strategy to improve the training effect. The whole scheme is trained collaboratively by the original loss and classification loss. Therefore, we also achieve more accurate prediction results. Experimental results on several datasets indicate the validity and robustness of the network. We achieve the best performance in individual forecasting and comparable results in social forecasting. Encouragingly, our approach achieves a new state of the art on the Hotel and Zara2 datasets compared with the social-based and individual-based approaches.

Forecasting players in sports has grown in popularity due to the potential for a tactical advantage and the applicability of such research to multi-agent interaction systems. Team sports contain a significant social component that influences interactions between teammates and opponents. However, it still needs to be fully exploited. In this work, we hypothesize that each participant has a specific function in each action and that role-based interaction is critical for predicting players’ future moves. We create RolFor , a novel end-to-end model for Role-based Forecasting. RolFor uses a new module we developed called Ordering Neural Networks (OrderNN) to permute the order of the players such that each player is assigned to a latent role. The latent role is then modeled with a RoleGCN. Thanks to its graph representation, it provides a fully learnable adjacency matrix that captures the relationships between roles and is subsequently used to forecast the players’ future trajectories. Extensive experiments on a challenging NBA basketball dataset back up the importance of roles and justify our goal of modeling them using optimizable models. When an oracle provides roles, the proposed RolFor compares favorably to the current state-of-the-art (it ranks first in terms of ADE and second in terms of FDE errors). However, training the end-to-end RolFor incurs the issues of differentiability of permutation methods, which we experimentally review. Finally, this work restates differentiable ranking as a difficult open problem and its great potential in conjunction with graph-based interaction models.

Trajectory forecasting for human mobility plays a critical role in the effective management and sustainable development of urban transportation, which aligns with the advocacy of Sustainable Development Goals (SDGs). Although several approaches have been developed in other trajectory forecasting applications, such as autonomous driving and intelligent robotics, there remain limitations in forecasting trajectories of human mobility. This is because they do not adequately consider the prior knowledge of human movement patterns and the heterogeneous effects of geographical environments. Therefore, in this study, we propose an environment-driven trajectory forecasting method that can adapt to distinct movement patterns. First, the indicator systems, which systematically summarize the heterogeneous effects of different environmental factors on human mobility, are, respectively, constructed for the convergence, divergence, and leadership patterns. Then, based on the corresponding indicator system, the potential field is generated, representing the calibrated probability of the human mobility direction under the environmental effects. A gradient descent algorithm is finally employed on the potential field to forecast the next-step mobility location. Extensive experiment results demonstrated the satisfactory performance of our proposed method under different movement patterns. Compared to other baselines, our proposed method also shows advantages in both long-term and real-time forecasting.