1. Abstract

In the rapidly evolving field of autonomous driving, reliable 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, it 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 innovative contributions of this study include the development of a novel DOS prediction model specifically tailored for navigating complex scenarios, the introduction of precise DOS mathematical representations, and the formulation of optimized loss functions that collectively advance the safety and efficiency of autonomous systems. Through rigorous validation, our method demonstrates marked improvements over traditional models, establishing a new benchmark for safety and operational efficiency in intelligent transportation systems.

2. Methodology

Trajectory-Prediction-Aware DOS Prediction Model

DOS Prediction Module

Design Objectives

3. Results

3.1. Quantitative Evaluation

3.2. Limit Analysis of Different DOS Representation

3.3. Ablation Study

3.4. Results of planning

3.5. Visualization

3. Contact

If you have any questions, please contact Wenbo Shao (swb19@mails.tsinghua.edu.cn).