SocialDriveGen: Generating Diverse Traffic Scenarios with Controllable Social Interactions
This work addresses the need for more realistic simulation environments in autonomous driving development, though it is incremental by building on existing generative modeling approaches.
The paper tackles the problem of generating realistic and diverse traffic scenarios for autonomous driving simulation by addressing the lack of social preference modeling in existing methods, resulting in a framework that produces scenarios with controllable driver personalities and interaction styles, enhancing policy robustness and generalization to rare situations.
The generation of realistic and diverse traffic scenarios in simulation is essential for developing and evaluating autonomous driving systems. However, most simulation frameworks rely on rule-based or simplified models for scene generation, which lack the fidelity and diversity needed to represent real-world driving. While recent advances in generative modeling produce more realistic and context-aware traffic interactions, they often overlook how social preferences influence driving behavior. SocialDriveGen addresses this gap through a hierarchical framework that integrates semantic reasoning and social preference modeling with generative trajectory synthesis. By modeling egoism and altruism as complementary social dimensions, our framework enables controllable diversity in driver personalities and interaction styles. Experiments on the Argoverse 2 dataset show that SocialDriveGen generates diverse, high-fidelity traffic scenarios spanning cooperative to adversarial behaviors, significantly enhancing policy robustness and generalization to rare or high-risk situations.