提出无需针对特定指标训练的轨迹预测方法，可适配多种评估标准。
Towards Metric-Agnostic Trajectory Forecasting
- 用概率化目标训练模型，不依赖具体评估指标
- 在Waymo数据集上所有指标均达当前最优
- 适合需要多指标兼容的自动驾驶系统开发
准确预测周边交通参与者轨迹是自动驾驶的核心能力，使车辆能预判行为并规划安全路径。我们发现，当前Argoverse 2和Waymo Open Motion Dataset上的先进模型会针对不同基准指标调整训练目标，而这些指标诱导出相互冲突的行为。为此，我们提出范式转变：使用与指标无关的概率化目标训练模型，将指标优化作为下游任务作用于预测分布。具体地，我们引入了轨迹分布评估（TraDiE）策略，即针对不同指标的映射策略，将预测分布转化为$K$条轨迹及对应置信度。我们通过引入DONUT-NLL，将最先进模型DONUT的训练目标改造成直接优化预测分布。借助我们的策略，DONUT-NLL在Waymo运动预测基准的所有指标上均取得当前最优表现。
原文摘要 · Abstract (English)
Accurate trajectory forecasting of surrounding traffic participants is a core capability for autonomous driving, enabling vehicles to anticipate behavior and plan safe maneuvers. We observe that current state-of-the-art forecasting models on Argoverse 2 and the Waymo Open Motion Dataset tailor their training objectives to the different benchmark metrics. Because these metrics encourage conflicting behavior, we propose a paradigm change for trajectory forecasting: training models with metric-agnostic probabilistic objectives and treating metric optimization as a downstream task applied to the predictive distribution. Concretely, we introduce Trajectory Distribution Evaluation (TraDiE) policies, metric-specific policies that map a predictive distribution to the set of $K$ trajectories and confidences required by trajectory forecasting metrics. We evaluate this framework by introducing DONUT-NLL, which adapts the training objective of the state-of-the-art trajectory forecasting model DONUT to directly optimize the predictive distribution. Using our policies, DONUT-NLL achieves state-of-the-art results on all metrics of the Waymo motion prediction benchmark.
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。