Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph

TL;DR

This paper introduces TrafficGraphNet, a hybrid graph neural network that models interactions between traffic actors and elements to improve trajectory prediction accuracy and interpretability in autonomous driving.

Contribution

The paper presents a novel hybrid graph structure and a semi-supervised GNN approach for better interaction modeling and trajectory prediction in traffic scenes.

Findings

Achieves state-of-the-art accuracy in trajectory prediction

Enhances interpretability through explicit interaction modeling

Maintains high performance with semi-supervised training

Abstract

Behavior prediction of traffic actors is an essential component of any real-world self-driving system. Actors' long-term behaviors tend to be governed by their interactions with other actors or traffic elements (traffic lights, stop signs) in the scene. To capture this highly complex structure of interactions, we propose to use a hybrid graph whose nodes represent both the traffic actors as well as the static and dynamic traffic elements present in the scene. The different modes of temporal interaction (e.g., stopping and going) among actors and traffic elements are explicitly modeled by graph edges. This explicit reasoning about discrete interaction types not only helps in predicting future motion, but also enhances the interpretability of the model, which is important for safety-critical applications such as autonomous driving. We predict actors' trajectories and interaction types using a graph neural network, which is trained in a semi-supervised manner. We show that our proposed model, TrafficGraphNet, achieves state-of-the-art trajectory prediction accuracy while maintaining a high level of interpretability.