Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
This addresses a significant open challenge for autonomous vehicle planning by improving safety in occluded scenarios, though it is an incremental advance over existing prediction methods.
The paper tackles the problem of planning for autonomous vehicles in the presence of occluded traffic agents by proposing Bi-level Variational Occlusion Models (BiVO), a two-step generative model that predicts occluded agent locations and trajectories, leading to better motion plans in critical scenarios as shown in evaluations on the nuScenes dataset.
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.