Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models

TL;DR

This paper introduces BiVO, a two-step generative model that predicts occluded traffic agents' locations and trajectories, improving autonomous vehicle planning in scenarios with hidden agents.

Contribution

The paper presents BiVO, a novel bi-level variational model that predicts occluded agents' trajectories and integrates these predictions into planning, addressing limitations of previous deep learning approaches.

Findings

BiVO accurately predicts occluded agent trajectories.

Predictions improve motion planning in critical scenarios.

Model validated on real-world nuScenes dataset.

Abstract

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.