SafeCritic: Collision-Aware Trajectory Prediction

Open Access
Authors
  • T. van der Heiden
  • N.S. Nagaraja
  • C. Weiß
  • E. Gavves
Publication date 16-10-2019
Number of pages 8
Publisher ArXiv
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
Navigating complex urban environments safely is a key to realize fully autonomous systems. Predicting future locations of vulnerable road users, such as pedestrians and cyclists, thus, has received a lot of attention in the recent years. While previous works have addressed modeling interactions with the static (obstacles) and dynamic (humans) environment agents, we address an important gap in trajectory prediction. We propose SafeCritic, a model that synergizes generative adversarial networks for generating multiple "real" trajectories with reinforcement learning to generate "safe" trajectories. The Discriminator evaluates the generated candidates on whether they are consistent with the observed inputs. The Critic network is environmentally aware to prune trajectories that are in collision or are in violation with the environment. The auto-encoding loss stabilizes training and prevents mode-collapse. We demonstrate results on two large scale data sets with a considerable improvement over state-of-the-art. We also show that the Critic is able to classify the safety of trajectories.
Document type Preprint
Note Accepted for workshop Embedded AI for Real-time Machine Vision at British Machine Vision Conference (BMVC 2019), Cardiff, United Kingdom, September 9-12, 2019.
Language English
Published at https://doi.org/10.48550/arXiv.1910.06673
Other links https://ivi.fnwi.uva.nl/isis/publications/2019/HeidenBMVC2019
Downloads
1910.06673v1 (Final published version)
Permalink to this page
Back