1. [Publications](/index.php/publications) 2. Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models # Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models ![](/sites/default/files/styles/wide/public/publications/featured_5.png?itok=RhHL4xxX) Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predicting occluded agents based on the behaviour of nearby visible agents; however, as we show in experiments, these models are difficult to integrate into downstream planning. To this end, we propose Bi-level Variational Occlusion Models (BiVO), a two-step generative model that first predicts likely locations of occluded agents, and then generates likely trajectories for the occluded agents. In contrast to existing methods, BiVO outputs a trajectory distribution which can then be sampled from and integrated into standard downstream planning. We evaluate the method in closed-loop replay simulation using the real-world nuScenes dataset. Our results suggest that BiVO can successfully learn to predict occluded agent trajectories, and these predictions lead to better subsequent motion plans in critical scenarios. ## Authors Filippos Christianos (NVIDIA) [Peter Karkus](/index.php/person/peter-karkus) [Boris Ivanovic](/index.php/person/boris-ivanovic) Stefano V. Albrecht (University of Edinburgh) [Marco Pavone](/index.php/person/marco-pavone) ## Publication Date Monday, May 29, 2023 ## Published in [IEEE International Conference on Robotics and Automation (ICRA) 2023](https://www.icra2023.org/) ## Research Area [Autonomous Vehicles](/index.php/research-area/autonomous-vehicles) [Computer Vision](/index.php/research-area/computer-vision) [Resilience and Safety](/index.php/research-area/resilience) ## External Links [Paper](https://arxiv.org/abs/2210.14584) ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .