ReCoG: A Deep Learning Framework with Heterogeneous Graph for Interaction-Aware Trajectory Prediction

TL;DR

ReCoG is a deep learning framework that models vehicle and infrastructure interactions using heterogeneous graphs and GNNs to improve trajectory prediction accuracy for autonomous driving.

Contribution

The paper introduces ReCoG, a novel approach combining RNN, CNN, and GNN to represent complex interactions for trajectory prediction.

Findings

ReCoG outperforms existing methods on the INTERACTION dataset.

The heterogeneous graph approach effectively captures infrastructure and vehicle interactions.

ReCoG achieves lower displacement errors compared to state-of-the-art models.

Abstract

Predicting the future trajectory of surrounding vehicles is essential for the navigation of autonomous vehicles in complex real-world driving scenarios. It is challenging as a vehicle's motion is affected by many factors, including its surrounding infrastructures and vehicles. In this work, we develop the ReCoG (Recurrent Convolutional and Graph Neural Networks), which is a general scheme that represents vehicle interactions with infrastructure information as a heterogeneous graph and applies graph neural networks (GNNs) to model the high-level interactions for trajectory prediction. Nodes in the graph contain corresponding features, where a vehicle node contains its sequential feature encoded using Recurrent Neural Network (RNN), and an infrastructure node contains spatial feature encoded using Convolutional Neural Network (CNN). Then the ReCoG predicts the future trajectory of the target vehicle by jointly considering all of the features. Experiments are conducted by using the INTERACTION dataset. Experimental results show that the proposed ReCoG outperforms other state-of-the-art methods in terms of different types of displacement error, validating the feasibility and effectiveness of the developed approach.