A Stochastic Gating Decoder for multimodal latent variable sampling, adaptively fusing kinematics and data-driven paths to capture driver intention uncertainty while maintaining kinematic consistency is introduced.
Abstract
Accurate vehicle trajectory prediction is essential for autonomous driving safety. However, existing data-driven models often ignore kinematic constraints, causing lateral jitter and trajectory distortion, while purely kinematics-based models lack flexibility in complex interactions. To address this, this paper presents a multimodal trajectory prediction method combining kinematics with dynamic interaction features. Operating in the Frenet coordinate system, the proposed model extracts historical features via a Bidirectional Gated Recurrent Unit (Bi-GRU) and utilizes an Adaptive Social Gating Network (ASGN) with multi-head attention to filter irrelevant interaction noise. This paper introduces a Stochastic Gating Decoder for multimodal latent variable sampling, adaptively fusing kinematics and data-driven paths to capture driver intention uncertainty while maintaining kinematic consistency. The model is trained using a composite loss function (Focal Loss and Best-of-K) to mitigate dataset long-tail distribution and trajectory divergence. Experiments on the HighD dataset show the proposed model achieves a minADE of 0.425 m and a minFDE of 0.955 m, outperforming baselines and reducing Lat-ADE by 53.9% compared to Social-GAN. These results confirm the model generates smoother, kinematically interpretable trajectories with higher accuracy in long-tail lane-changing scenarios.
An efficient Mamba-based feature extraction framework for jointly encoding vehicle trajectories and map information is proposed and achieves superior performance in terms of minADE, minFDE, and minMR, while maintaining high computational efficiency.
J. Li, L. Wang, J. Pei· Revista Internacional de Mét...· 0 citations
Accurate short-horizon vehicle trajectory prediction is critical for autonomous driving and vehicle-to-everything (V2X) communication. Most existing deep learning-based prediction methods rely on fixed-length historical trajectories and multi-agent context, which may be unavailable when a vehicle is newly observed. This paper studies single-frame short-horizon trajectory prediction at signalized intersections, where only one enriched observation frame is used for future motion-state forecasting. We propose a Neural Ordinary Differential Equation (Neural ODE)-based framework that formulates single-frame prediction as continuous-time motion-state forecasting. The proposed model encodes instantaneous kinematic variables, road-context information, and training-set-derived spatial priors into a latent representation, evolves the latent state in continuous time, and decodes future state variables. The predicted motion states are converted into future vehicle coordinates through kinematic integration. Experiments on the CitySIM-Intersection A dataset, evaluated by ADE and DE, show that the proposed method achieves competitive short-horizon prediction accuracy under the single-frame setting. The experiments include baseline comparisons with classical motion models and single-frame neural baselines, input ablation, coordinate and spatial-cell analyses, runtime evaluation, and supplementary studies on multi-frame sequence baselines, longer-horizon rollout, robustness, maneuver-specific performance, and statistical significance. The results clarify the applicability and limitations of single-frame short-horizon prediction on both straight and curved driving subsets.
Yijun Tang, Wenhao Huang, Yang Pu et al.· Discover Computing· 0 citations
A Decoupled Hybrid Residual Model for online adaptive prediction of vehicle dynamics is proposed, demonstrating that the proposed architecture effectively improves prediction accuracy, robustness, and implementation feasibility under varying driving conditions.
Guodong Zhu, Jialing Yao, Yiwen Bai et al.· Proceedings of the Instituti...· 0 citations
To address error accumulation from multi-variable features and complex dynamic coupling in the motion trajectory prediction of hybrid mechanisms, this paper applies a Transformer-based prediction framework. The framework integrates a spatiotemporal attention mechanism and kinematic constraints to obtain precise and physically feasible predictions of component movement. Such trajectory modeling is also meaningful for advanced electromagnetic engineering, including antenna-positioning mechanisms, microwave inspection platforms, and robotic systems used in electromagnetic measurement. The method uses a Transformer core with a hierarchical spatiotemporal attention module to model time dependency and spatial coupling among joint angles, velocities, and torques, while refining multimodal dynamic behavior. A Dynamic Graph Convolutional Network captures the influence of topological changes on motion-transfer paths and reflects configuration-dependent joint interactions. By constructing a kinematic constraint loss function based on the Lagrangian equation, the model embeds dynamic priors and improves physical consistency. Experimental results show that the method achieves an RMSE of 1.42 mm and an MAE of 1.06 mm on the standard test set, reducing these errors by 63.3% and 64.1% compared with a traditional LSTM model. In a six-degreeof-freedom mechanism, the median prediction error of critical Joint 1 is controlled at 1.42 mm, supporting accurate motion prediction for constrained serial-reachable hybrid topologies.
The proposed framework improves the safety and crossing efficiency of autonomous vehicle decision-making at unsignalized intersections and introduces a composite prioritized replay mechanism into the Twin Delayed Deep Deterministic Policy Gradient algorithm.
Shufeng Wang, Yuhang Wang, Yongxin Lei et al.· Machines· 0 citations
Comprehensive experiments on the NGSIM dataset validate the proposed model, demonstrating robust performance across structured highway driving scenarios and both the accuracy and computational efficiency of the proposed architecture.
Yang Li, Chengqian Jin, Zhikang Li· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
