Multi-modal trajectory forecasting methods commonly evaluate using single-agent metrics (marginal metrics), such as minimum Average Displacement Error (ADE) and Final Displacement Error (FDE), which fail to capture joint performance of multiple interacting agents. Only focusing on marginal metrics can lead to unnatural predictions, such as colliding trajectories or diverging trajectories for people who are clearly walking together as a group. Consequently, methods optimized for marginal metrics lead to overly-optimistic estimations of performance, which is detrimental to progress in trajectory forecasting research. In response to the limitations of marginal metrics, we present the first comprehensive evaluation of state-of-the-art (SOTA) trajectory forecasting methods with respect to multi-agent metrics (joint metrics): JADE, JFDE, and collision rate. We demonstrate the importance of joint metrics as opposed to marginal metrics with quantitative evidence and qualitative examples drawn from the ETH / UCY and Stanford Drone datasets. We introduce a new loss function incorporating joint metrics that, when applied to a SOTA trajectory forecasting method, achieves a 7% improvement in JADE / JFDE on the ETH / UCY datasets with respect to the previous SOTA. Our results also indicate that optimizing for joint metrics naturally leads to an improvement in interaction modeling, as evidenced by a 16% decrease in mean collision rate on the ETH / UCY datasets with respect to the previous SOTA.

翻译：多模态轨迹预测方法通常采用单智能体指标（边缘指标）进行评估，例如最小平均位移误差（ADE）和最终位移误差（FDE），这些指标无法捕捉多个交互智能体的联合性能。仅关注边缘指标可能导致非自然预测，例如碰撞轨迹或明显结伴而行人群的发散轨迹。因此，针对边缘指标优化的方法会高估性能估计，这对轨迹预测研究的进展不利。针对边缘指标的局限性，我们首次全面评估了最先进的（SOTA）轨迹预测方法在多智能体指标（联合指标）下的表现，包括JADE、JFDE和碰撞率。我们通过ETH / UCY和Stanford Drone数据集上的定量证据和定性示例，论证了联合指标相较于边缘指标的重要性。我们提出了一种融合联合指标的新型损失函数，将其应用于SOTA轨迹预测方法后，在ETH / UCY数据集上相较于先前SOTA实现了7%的JADE/JFDE改进。我们的结果还表明，联合指标的优化会自然改善交互建模能力，体现在ETH / UCY数据集上平均碰撞率相较于先前SOTA下降了16%。