EDA: 面向多模态运动预测的演化式差异化锚点
EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction
AI总结：
针对自动驾驶多模态运动预测中两类匹配方法的缺陷，提出EDA范式，通过锚点场景化演化重分布与差异化筛选提升回归能力和评分性能，在Waymo Open Motion Dataset上超越MTR基线并达SOTA。
摘要：
运动预测是自动驾驶中的关键任务，其主要挑战之一在于未来行为的多模态性。许多成功的研究采用了混合模型，这类模型需要确定正混合分量，相应地主要分为两大方向：基于预测的匹配和基于锚点的匹配。基于预测的匹配中存在预测聚类现象，难以为下游任务挑选具有代表性的轨迹；而基于锚点的匹配则受限于回归能力不足。本文提出了一种名为Evolving and Distinct Anchors（EDA，演化式差异化锚点）的新范式，用于为基于混合模型的多模态运动预测定义正负分量。我们让锚点能够在特定场景下演化并重新分布，以提升回归容量。此外，我们在将锚点与真值匹配前筛选出差异化锚点，实现了出色的评分性能。与基线模型MTR相比，我们的方法在所有指标上均有提升，尤其是漏检率（Miss Rate）相对降低了13.5%，在Waymo Open Motion Dataset上取得了当前最优性能。代码可在https://github.com/Longzhong-Lin/EDA获取。
英文摘要：
Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors. Many successful works have utilized mixture models which require identification of positive mixture components, and correspondingly fall into two main lines: prediction-based and anchor-based matching. The prediction clustering phenomenon in prediction-based matching makes it difficult to pick representative trajectories for downstream tasks, while the anchor-based matching suffers from a limited regression capability. In this paper, we introduce a novel paradigm, named Evolving and Distinct Anchors (EDA), to define the positive and negative components for multimodal motion prediction based on mixture models. We enable anchors to evolve and redistribute themselves under specific scenes for an enlarged regression capacity. Furthermore, we select distinct anchors before matching them with the ground truth, which results in impressive scoring performance. Our approach enhances all metrics compared to the baseline MTR, particularly with a notable relative reduction of 13.5% in Miss Rate, resulting in state-of-the-art performance on the Waymo Open Motion Dataset. Code is available at https://github.com/Longzhong-Lin/EDA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
