Towards Human-Like Trajectory Prediction for Autonomous Driving: A Behavior-Centric Approach

TL;DR

This paper introduces HiT, a behavior-centric model for autonomous driving trajectory prediction that incorporates dynamic interaction measures to produce more human-like and accurate vehicle trajectories in complex traffic scenarios.

Contribution

The study presents a novel behavior-aware framework that dynamically models interactions among traffic participants, improving trajectory prediction accuracy over traditional static methods.

Findings

HiT outperforms existing models on multiple datasets.

The model excels in scenarios with aggressive driving behaviors.

Dynamic interaction modeling enhances prediction reliability.

Abstract

Predicting the trajectories of vehicles is crucial for the development of autonomous driving (AD) systems, particularly in complex and dynamic traffic environments. In this study, we introduce HiT (Human-like Trajectory Prediction), a novel model designed to enhance trajectory prediction by incorporating behavior-aware modules and dynamic centrality measures. Unlike traditional methods that primarily rely on static graph structures, HiT leverages a dynamic framework that accounts for both direct and indirect interactions among traffic participants. This allows the model to capture the subtle yet significant influences of surrounding vehicles, enabling more accurate and human-like predictions. To evaluate HiT's performance, we conducted extensive experiments using diverse and challenging real-world datasets, including NGSIM, HighD, RounD, ApolloScape, and MoCAD++. The results demonstrate that HiT consistently outperforms other top models across multiple metrics, particularly excelling in scenarios involving aggressive driving behaviors. This research presents a significant step forward in trajectory prediction, offering a more reliable and interpretable approach for enhancing the safety and efficiency of fully autonomous driving systems.