Automated and Complete Generation of Traffic Scenarios at Road Junctions Using a Multi-level Danger Definition
🤖 AI Summary
To address incomplete coverage of hazardous scenarios in autonomous vehicle (AV) intersection safety certification, this paper proposes a systematic hazardous scenario generation framework for intersections based on abstract path overlap. Methodologically, it introduces a novel multi-level hazard modeling and abstract path combinatorial enumeration mechanism, mapping high-level driving intentions to low-level executable collision-triggering trajectories, with trajectory inversion optimization ensuring simulation feasibility. Evaluated on two real-world intersections, the framework achieves exhaustive hazardous scenario generation. As the number of external agents increases, the proportion of unsafe behaviors exhibited by the tested learning-based AV rises significantly—its variation pattern strongly correlates with the functional logic attributes of the scenarios. This work bridges maneuver-level logic with collision-triggering trajectories, establishing an interpretable and scalable paradigm for AV safety testing and certification.
Application Category
📝 Abstract
To ensure their safe use, autonomous vehicles (AVs) must meet rigorous certification criteria that involve executing maneuvers safely within (arbitrary) scenarios where other actors perform their intended maneuvers. For that purpose, existing scenario generation approaches optimize search to derive scenarios with high probability of dangerous situations. In this paper, we hypothesize that at road junctions, potential danger predominantly arises from overlapping paths of individual actors carrying out their designated high-level maneuvers. As a step towards AV certification, we propose an approach to derive a complete set of (potentially dangerous) abstract scenarios at any given road junction, i.e. all permutations of overlapping abstract paths assigned to actors (including the AV) for a given set of possible abstract paths. From these abstract scenarios, we derive exact paths that actors must follow to guide simulation-based testing towards potential collisions. We conduct extensive experiments to evaluate the behavior of a state-of-the-art learning-based AV controller on scenarios generated over two realistic road junctions with increasing number of external actors. Results show that the AV-under-test is involved in increasing percentages of unsafe behaviors in simulation, which vary according to functional- and logical-level scenario properties.
Problem
Research questions and friction points this paper is trying to address.
Autonomous Vehicles
Intersection Safety
Hazard Perception
Innovation
Methods, ideas, or system contributions that make the work stand out.
Automated Scenario Generation
Intersection Safety Testing
Autonomous Vehicles
🔎 Similar Papers
No similar papers found.
