Autonomous driving paper index
<scp>Dyn</scp> NPC: Finding More Violations Induced by ADS in Simulation Testing via Dynamic NPC Behavior Generation
One-line summary
To address these limitations, we propose a novel search-based testing framework, DynNPC , to generate more violation scenarios induced by the ADS.
Engineering notes
We compare DynNPC with four state-of-the-art scenario-based testing approaches.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。
Original abstract
Recently, a number of simulation testing approaches have been proposed to generate diverse driving scenarios for autonomous driving systems (ADSs) testing. However, many existing search-based approaches primarily determine NPC behaviors before scenario execution, which limits their ability to model interactions that depend on traffic signals and the Ego vehicle's real-time behavior. As a result, some reported violations may be dominated by unreasonable NPC behaviors, reducing the effectiveness of finding violations induced by the ADS, while the vast search space of NPC behaviors also limits efficiency. To address these limitations, we propose a novel search-based testing framework, DynNPC , to generate more violation scenarios induced by the ADS. Specifically, DynNPC enables NPC vehicles to make maneuver decisions and generate trajectories according to traffic signals and the real-time behavior of the Ego vehicle, using different driving strategies. DynNPC further integrates this dynamic behavior generation with a genetic algorithm-based scenario configuration generator to improve the search for Ego-induced violations. We compare DynNPC with four state-of-the-art scenario-based testing approaches. Our evaluation has demonstrated that DynNPC increases the proportion of violations induced by the ADS among all reported violations, on average, by 125.21%, and improves the number of discovered unique violation patterns induced by the ADS by at least 39.71%. Besides, DynNPC reduces the time to find the first violation induced by the ADS and the average time to find one violation induced by the ADS by 82.13% and 65.70%, respectively. We further conduct ablation studies along with sensitivity analyses of key parameters, and demonstrate the robustness and portability of DynNPC .
Links and sources
Need this topic turned into a technical roadmap?
Full Self Driving can prepare a custom autonomous driving literature review, code map, dataset map, and B2B technology assessment.
Request B2B research
Comments