The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
This addresses the need for predicting diverse human trajectories in applications like surveillance or autonomous driving, but it is incremental as it builds on existing trajectory prediction methods.
The paper tackles the problem of predicting multiple possible future paths of people in visual scenes by introducing a new dataset for multi-future trajectory prediction and a model called Multiverse that uses multi-scale location encodings and convolutional RNNs over graphs. The model achieves the best results on their new dataset and on the real-world VIRAT/ActEV dataset.
This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse. We show that our model achieves the best results on our dataset, as well as on the real-world VIRAT/ActEV dataset (which just contains one possible future).