Utilizing Navigation Paths to Generate Target Points for Enhanced End-to-End Autonomous Driving Planning

TL;DR

This paper presents NTT, a novel end-to-end autonomous driving planning method that generates target points from navigation paths to improve driving intent understanding and trajectory flexibility, leading to safer and more adaptable autonomous driving.

Contribution

The paper introduces NTT, a new approach that integrates navigation path-based target point generation into end-to-end planning, addressing the lack of explicit driving intent modeling in prior methods.

Findings

Achieved excellent planning performance on nuScenes dataset.

Validated effectiveness through ablation experiments.

Enhanced safety and adaptability in trajectory planning.

Abstract

In recent years, end-to-end autonomous driving frameworks have been shown to not only enhance perception performance but also improve planning capabilities. However, most previous end-to-end autonomous driving frameworks have focused primarily on enhancing environmental perception while neglecting the learning of autonomous vehicle driving intent, which refers to the vehicle's intended direction of travel. In planning, the autonomous vehicle's direction is clear and well-defined, yet this crucial aspect has often been overlooked. This paper introduces NTT (Navigation to Target for Trajectory planning), a method within an end-to-end framework for autonomous driving. NTT generates the planned trajectory in two steps. First, it generates the future target point for the autonomous vehicle on the basis of the navigation path. Then, it produces the complete planned trajectory on the basis of this target point. On the one hand, generating the target point for the autonomous vehicle from the navigation path enables the vehicle to learn a clear driving intent. On the other hand, generating the trajectory on the basis of the target point allows for a flexible planned trajectory that can adapt to complex environmental changes, thereby enhancing the safety of the planning process. Our method achieved excellent planning performance on the widely used nuScenes dataset and its effectiveness was validated through ablation experiments.