GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving

TL;DR

GraphAD introduces an Interaction Scene Graph to efficiently model critical interactions in autonomous driving, outperforming attention-based methods by capturing geometric priors and reducing computational load.

Contribution

The paper proposes the Interaction Scene Graph (ISG) for end-to-end autonomous driving, effectively modeling essential interactions and improving performance over attention-based approaches.

Findings

Outperforms strong baselines on nuScenes dataset

Enhances perception, prediction, and planning tasks

Reduces computational complexity compared to attention mechanisms

Abstract

Modeling complicated interactions among the ego-vehicle, road agents, and map elements has been a crucial part for safety-critical autonomous driving. Previous works on end-to-end autonomous driving rely on the attention mechanism for handling heterogeneous interactions, which fails to capture the geometric priors and is also computationally intensive. In this paper, we propose the Interaction Scene Graph (ISG) as a unified method to model the interactions among the ego-vehicle, road agents, and map elements. With the representation of the ISG, the driving agents aggregate essential information from the most influential elements, including the road agents with potential collisions and the map elements to follow. Since a mass of unnecessary interactions are omitted, the more efficient scene-graph-based framework is able to focus on indispensable connections and leads to better performance. We evaluate the proposed method for end-to-end autonomous driving on the nuScenes dataset. Compared with strong baselines, our method significantly outperforms in the full-stack driving tasks, including perception, prediction, and planning. Code will be released at https://github.com/zhangyp15/GraphAD.