Learning Occupancy Priors of Human Motion from Semantic Maps of Urban Environments

TL;DR

This paper introduces a novel CNN-based method to predict human occupancy priors in urban environments using semantic maps, enhancing generalization and accuracy over traditional approaches.

Contribution

It proposes a new CNN approach for occupancy prediction from semantic maps, improving generalization with limited data compared to inverse optimal control methods.

Findings

CNN method outperforms baselines in synthetic data

Method generalizes well with small training datasets

Achieves superior results in real-world environment assessments

Abstract

Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a powerful approach to discover recurrent motion patterns, generalization to new environments, where sufficient motion data are not readily available, remains a challenge. In many cases, however, semantic information about the environment is a highly informative cue for the prediction of pedestrian motion or the estimation of collision risks. In this work, we infer occupancy priors of human motion using only semantic environment information as input. To this end we apply and discuss a traditional Inverse Optimal Control approach, and propose a novel one based on Convolutional Neural Networks (CNN) to predict future occupancy maps. Our CNN method produces flexible context-aware occupancy estimations for semantically uniform map regions and generalizes well already with small amounts of training data. Evaluated on synthetic and real-world data, it shows superior results compared to several baselines, marking a qualitative step-up in semantic environment assessment.