Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps

TL;DR

This paper presents a novel deep learning framework that uses semantic-enhanced dynamic occupancy grid maps for vehicle motion prediction, demonstrating improved accuracy over traditional methods on real-world data.

Contribution

The paper introduces a new approach combining semantic labels and map information with deep learning for more accurate vehicle motion forecasting.

Findings

Outperforms conventional OGM prediction methods on NuScenes dataset

Semantic labels and map information significantly improve prediction accuracy

Model effectively predicts both static and dynamic vehicle behaviors

Abstract

Motion prediction is a challenging task for autonomous vehicles due to uncertainty in the sensor data, the non-deterministic nature of future, and complex behavior of agents. In this paper, we tackle this problem by representing the scene as dynamic occupancy grid maps (DOGMs), associating semantic labels to the occupied cells and incorporating map information. We propose a novel framework that combines deep-learning-based spatio-temporal and probabilistic approaches to predict vehicle behaviors.Contrary to the conventional OGM prediction methods, evaluation of our work is conducted against the ground truth annotations. We experiment and validate our results on real-world NuScenes dataset and show that our model shows superior ability to predict both static and dynamic vehicles compared to OGM predictions. Furthermore, we perform an ablation study and assess the role of semantic labels and map in the architecture.