Towards Metric-Agnostic Trajectory Forecasting
For autonomous driving researchers, this work addresses the problem of conflicting benchmark metrics by decoupling probabilistic training from metric-specific optimization, enabling a single model to excel across all metrics.
The paper proposes a paradigm shift for trajectory forecasting: training models with metric-agnostic probabilistic objectives and treating metric optimization as a downstream task. Their method, DONUT-NLL, achieves state-of-the-art results on all metrics of the Waymo motion prediction benchmark.
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.