People as Sensors: Imputing Maps from Human Actions

TL;DR

This paper introduces a novel approach that models humans as sensors to improve map estimation in autonomous driving, leveraging human actions to infer occluded areas and enhance environment awareness.

Contribution

It proposes a framework that incorporates human actions into mapping, enabling the imputation of occluded map regions, which is a new perspective in autonomous vehicle perception.

Findings

Improved map accuracy using human actions as sensors

Outperforms standard mapping techniques in experiments

Enhances environment awareness in autonomous driving

Abstract

Despite growing attention in autonomy, there are still many open problems, including how autonomous vehicles will interact and communicate with other agents, such as human drivers and pedestrians. Unlike most approaches that focus on pedestrian detection and planning for collision avoidance, this paper considers modeling the interaction between human drivers and pedestrians and how it might influence map estimation, as a proxy for detection. We take a mapping inspired approach and incorporate people as sensors into mapping frameworks. By taking advantage of other agents' actions, we demonstrate how we can impute portions of the map that would otherwise be occluded. We evaluate our framework in human driving experiments and on real-world data, using occupancy grids and landmark-based mapping approaches. Our approach significantly improves overall environment awareness and out-performs standard mapping techniques.