DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
This addresses motion forecasting for autonomous vehicles, representing a strong incremental improvement over existing goal-based methods.
The paper tackles trajectory prediction for autonomous driving by proposing DenseTNT, an anchor-free end-to-end model that outputs trajectories from dense goal candidates, achieving state-of-the-art performance with 1st place rankings on the Argoverse and Waymo Open Dataset benchmarks.
Due to the stochasticity of human behaviors, predicting the future trajectories of road agents is challenging for autonomous driving. Recently, goal-based multi-trajectory prediction methods are proved to be effective, where they first score over-sampled goal candidates and then select a final set from them. However, these methods usually involve goal predictions based on sparse pre-defined anchors and heuristic goal selection algorithms. In this work, we propose an anchor-free and end-to-end trajectory prediction model, named DenseTNT, that directly outputs a set of trajectories from dense goal candidates. In addition, we introduce an offline optimization-based technique to provide multi-future pseudo-labels for our final online model. Experiments show that DenseTNT achieves state-of-the-art performance, ranking 1st on the Argoverse motion forecasting benchmark and being the 1st place winner of the 2021 Waymo Open Dataset Motion Prediction Challenge.