In the rapidly evolving field of autonomous driving, accurate trajectory prediction is pivotal for vehicular safety. However, trajectory predictions often deviate from actual paths, particularly in complex and challenging environments, leading to significant errors. To address this issue, our study introduces a novel method for Dynamic Occupancy Set (DOS) prediction, enhancing trajectory prediction capabilities. This method effectively combines advanced trajectory prediction networks with a DOS prediction module, overcoming the shortcomings of existing models. It provides a comprehensive and adaptable framework for predicting the potential occupancy sets of traffic participants. The main contributions of this research include: 1) A novel DOS prediction model tailored for complex scenarios, augmenting traditional trajectory prediction; 2) The development of unique DOS representations and evaluation metrics; 3) Extensive validation through experiments, demonstrating enhanced performance and adaptability. This research contributes to the advancement of safer and more efficient intelligent vehicle and transportation systems.

翻译：在自动驾驶快速发展的领域，精确的轨迹预测对车辆安全至关重要。然而，尤其在复杂和具有挑战性的环境中，轨迹预测往往偏离实际路径，导致显著误差。为解决这一问题，本研究引入了一种动态占用集（DOS）预测的新方法，以增强轨迹预测能力。该方法有效结合了先进轨迹预测网络与DOS预测模块，克服了现有模型的不足，为预测交通参与者的潜在占用集提供了全面且适应性强的框架。本研究的主要贡献包括：1）针对复杂场景设计的新型DOS预测模型，增强了传统轨迹预测；2）独特DOS表示与评估指标的开发；3）通过大量实验验证，展示了增强的性能与适应性。本研究有助于推动更安全、更高效的智能车辆与交通系统的发展。