Back to square one: probabilistic trajectory forecasting without bells and whistles

Sep 30, 2018 NIPS 2018 Workshop Spatiotemporal Blind Submission readers: everyone
  • Keywords: probabilistic trajectory forecasting, spatio-temporal convolutional neural network
  • TL;DR: We propose a spatio-temporal convolutional neural network for probabilistic trajectory forecasting that performs well, but is much simpler and easier to train than existing aproaches.
  • Abstract: We introduce a simple spatio-temporal convolutional neural network model for trajectory forecasting from visual sources. Applied in an auto-regressive way it provides an explicit probability distribution over continuations of a given initial trajectory segment. We discuss it in relation to (more complicated) existing work and report on experiments on two standard datasets for trajectory forecasting: MNISTseq and Stanford Drones, achieving results on-par with or better than previous methods.
0 Replies