Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions

TL;DR

This paper introduces a scene-graph based deep learning model for risk assessment in autonomous driving, improving accuracy, transferability, and explainability over existing methods, especially in complex scenarios like lane changes.

Contribution

The paper presents a novel scene-graph augmented approach with multi-relation graph convolution, LSTM, and attention layers for subjective risk modeling in autonomous driving.

Findings

Achieves higher classification accuracy than state-of-the-art on synthesized datasets.

Demonstrates effective transferability from synthesized to real-world data.

Improves model explainability with spatial and temporal attention layers.

Abstract

Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can improve ADS' safety in both normal and complex driving scenarios. However, existing deep learning-based methods often fail to model the relationships between traffic participants and can suffer when faced with complex real-world scenarios. Besides, these methods lack transferability and explainability. To address these limitations, we propose a novel data-driven approach that uses scene-graphs as intermediate representations. Our approach includes a Multi-Relation Graph Convolution Network, a Long-Short Term Memory Network, and attention layers for modeling the subjective risk of driving maneuvers. To train our model, we formulate this task as a supervised scene classification problem. We consider a typical use case to demonstrate our model's capabilities: lane changes. We show that our approach achieves a higher classification accuracy than the state-of-the-art approach on both large (96.4% vs. 91.2%) and small (91.8% vs. 71.2%) synthesized datasets, also illustrating that our approach can learn effectively even from smaller datasets. We also show that our model trained on a synthesized dataset achieves an average accuracy of 87.8% when tested on a real-world dataset compared to the 70.3% accuracy achieved by the state-of-the-art model trained on the same synthesized dataset, showing that our approach can more effectively transfer knowledge. Finally, we demonstrate that the use of spatial and temporal attention layers improves our model's performance by 2.7% and 0.7% respectively, and increases its explainability.