对比了联合轨迹预测的多种方法，揭示其优劣与适用场景。
From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving
- 分三类方法：后处理、联合训练、生成建模
- 联合预测提升场景一致性，但效率与多模态需权衡
- 适合自动驾驶规划与决策研究者参考
在动态交通环境中，准确预测周边交通参与者运动对自动驾驶车辆的安全高效运行至关重要。传统边际预测模型独立预测每个智能体轨迹，常导致规划决策次优；而联合预测模型显式建模智能体间交互，实现更符合社会与物理规律的场景级预测。然而，现有方法在问题设定、模型结构和实现细节上差异显著，难以直接比较。本文系统评估了三类联合预测方法：对边际预测结果进行后处理、显式联合训练模型，以及将问题建模为生成任务。从预测精度、多模态性和推理效率三个维度进行全面分析，揭示各类方法的优缺点。部分预测示例见https://frommarginaltojointpred.github.io/。
原文摘要 · Abstract (English)
Accurate motion prediction of surrounding traffic participants is crucial for the safe and efficient operation of automated vehicles in dynamic environments. Marginal prediction models commonly forecast each agent's future trajectories independently, often leading to sub-optimal planning decisions for an automated vehicle. In contrast, joint prediction models explicitly account for the interactions between agents, yielding socially and physically consistent predictions on a scene level. However, existing approaches differ not only in their problem formulation but also in the model architectures and implementation details used, making it difficult to compare them. In this work, we systematically investigate different approaches to joint motion prediction, including post-processing of the marginal predictions, explicitly training the model for joint predictions, and framing the problem as a generative task. We evaluate each approach in terms of prediction accuracy, multi-modality, and inference efficiency, offering a comprehensive analysis of the strengths and limitations of each approach. Several prediction examples are available at https://frommarginaltojointpred.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。