Zhang Zikai
Department of Computer Science, Durham University, Stockton Rd, Durham DH1 3LE, UK.
Sensors (Basel). 2024 Nov 26;24(23):7538. doi: 10.3390/s24237538.
This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions-such as different road configurations and recording times-impact the model's prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.
本文分析了rounD数据集，以推进用于在复杂环形交叉路口环境中导航的自动驾驶车辆的运动预测算法。我们开发了一个受门控循环单元（GRU）网络和基于图的模块启发的轨迹预测框架，以有效地对车辆交互进行建模。我们的主要目标是评估所提出模型在不同训练和测试数据集上的通用性。通过广泛的实验，我们研究了不同的数据分布（如不同的道路配置和记录时间）如何影响模型的预测准确性和鲁棒性。这项研究为自动驾驶车辆轨迹预测中的领域泛化挑战提供了关键见解。
