Abstract Scene Graphs: Formalizing and Monitoring Spatial Properties of Automated Driving Functions

2025-11-18

AI Summary

Autonomous driving functions (ADFs) must satisfy diverse, safety-critical spatial properties in complex traffic scenarios, yet formal modeling and real-time compliance verification remain challenging. To address this, we propose the Abstract Scenario Graph (ASG)—a novel formalism that structurally encodes spatial relations as a computable graph model for the first time. We rigorously define ASG syntax and semantics by extending scenario graph theory. Furthermore, we design an end-to-end runtime monitoring framework that integrates first-order logic rules with efficient graph matching algorithms to automatically map spatial properties to system behaviors and perform dynamic compliance verification. Evaluated on real-world traffic cases, ASG unifies the modeling of heterogeneous spatial constraints, enables high-precision, interpretable real-time compliance checking, and significantly enhances both safety assurance and verification traceability for ADFs.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Automated Driving Functions (ADFs) need to comply with spatial properties of varied complexity while driving on public roads. Since such situations are safety-critical in nature, it is necessary to continuously check ADFs for compliance with their spatial properties. Due to their complexity, such spatial properties need to be formalized to enable their automated checking. Scene Graphs (SGs) allow for an explicit structured representation of objects present in a traffic scene and their spatial relationships to each other. In this paper, we build upon the SG construct and propose the Abstract Scene Graph (ASG) formalism to formalize spatial properties of ADFs. We show using real-world examples how spatial properties can be formalized using ASGs. Finally, we present a framework that uses ASGs to perform Runtime Monitoring of ADFs. To this end, we also show algorithmically how a spatial property formalized as an ASG can be satisfied by ADF system behaviour.

Problem

• Formalizing spatial properties of automated driving functions for verification
• Monitoring compliance with safety-critical spatial requirements during operation
• Developing abstract scene graphs to represent traffic object relationships

Innovation

• Abstract Scene Graphs formalize spatial properties
• Runtime Monitoring framework for Automated Driving Functions
• Algorithmic satisfaction of spatial property specifications