Generating Synthetic Ground Truth Distributions for Multi-step Trajectory Prediction using Probabilistic Composite Bézier Curves
This addresses a data limitation for researchers and practitioners in trajectory prediction, though it is incremental as it focuses on dataset generation rather than a new prediction model.
The paper tackles the lack of ground truth probability distributions in trajectory prediction datasets by proposing a synthetic generation method using probabilistic composite Bézier curves, enabling the use of more expressive error metrics like the Wasserstein distance for model evaluation.
An appropriate data basis grants one of the most important aspects for training and evaluating probabilistic trajectory prediction models based on neural networks. In this regard, a common shortcoming of current benchmark datasets is their limitation to sets of sample trajectories and a lack of actual ground truth distributions, which prevents the use of more expressive error metrics, such as the Wasserstein distance for model evaluation. Towards this end, this paper proposes a novel approach to synthetic dataset generation based on composite probabilistic Bézier curves, which is capable of generating ground truth data in terms of probability distributions over full trajectories. This allows the calculation of arbitrary posterior distributions. The paper showcases an exemplary trajectory prediction model evaluation using generated ground truth distribution data.