Multiple Future Prediction Leveraging Synthetic Trajectories
This work addresses safety-critical trajectory prediction for autonomous vehicles, but it is incremental as it builds on existing data-driven methods with a focus on multimodality.
The paper tackles the problem of multimodal trajectory prediction for autonomous driving by generating synthetic trajectories using Markov Chains to augment training data, resulting in state-of-the-art performance improvements.
Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.