MFTraj: Map-Free, Behavior-Driven Trajectory Prediction for Autonomous Driving

TL;DR

MFTraj is a map-free, behavior-aware trajectory prediction model for autonomous driving that effectively captures complex interactions without relying on high-definition maps, demonstrating robustness across multiple datasets.

Contribution

The paper introduces MFTraj, a novel behavior-driven trajectory prediction model that uses dynamic graph-based interactions and attention mechanisms, eliminating the need for HD maps.

Findings

Outperforms benchmarks on multiple datasets

Maintains performance with missing data

Operates efficiently without HD maps

Abstract

This paper introduces a trajectory prediction model tailored for autonomous driving, focusing on capturing complex interactions in dynamic traffic scenarios without reliance on high-definition maps. The model, termed MFTraj, harnesses historical trajectory data combined with a novel dynamic geometric graph-based behavior-aware module. At its core, an adaptive structure-aware interactive graph convolutional network captures both positional and behavioral features of road users, preserving spatial-temporal intricacies. Enhanced by a linear attention mechanism, the model achieves computational efficiency and reduced parameter overhead. Evaluations on the Argoverse, NGSIM, HighD, and MoCAD datasets underscore MFTraj's robustness and adaptability, outperforming numerous benchmarks even in data-challenged scenarios without the need for additional information such as HD maps or vectorized maps. Importantly, it maintains competitive performance even in scenarios with substantial missing data, on par with most existing state-of-the-art models. The results and methodology suggest a significant advancement in autonomous driving trajectory prediction, paving the way for safer and more efficient autonomous systems.