This paper presents a method for generating synthetic highway traffic scenarios. Scenarios are not only used in the training and testing phases of automated vehicles but also in the verification and validation procedures. However, obtaining a sufficient scenario database that captures the diversity of traffic is not straightforward. For increasing the size of the database while preserving the diversity, we propose a method that uses a multi-step approach with generative modeling techniques. The first stage of the method uses a Variational Autoencoder as trajectory generator. In the second stage, we make use of a Generative Adversarial Network that constructs inputs to multiple trajectory generators for obtaining complementary trajectories that form a scenario. The method is demonstrated on a lane-changing highway scenario with two vehicles. The generated scenarios are evaluated qualitatively by visual inspection using a vehicle-centered representation. Furthermore, the results are quantitatively evaluated by checking for collisions and requirements that were used to obtain the training data. Finally, the distribution of the generated data is investigated using dimensionality reduction. The results of the experiments show that our method generates multi-vehicle lane change scenarios that are similar to the ones that are found in the dataset.

It is difficult to maintain consistency between artifacts produced during the development of mechatronic systems, and to ensure the successful integration of independently developed parts. The difficulty stems from the complex, multidisciplinary nature of the problem, with multiple artifacts produced by each engineering domain, throughout the design process, and across supplier chains. In this work, we develop a methodology and a tool, CONDEnSe, that given a set of Assume/Guarantee (A/G) contracts that capture the system requirements, and a high-level decomposition of the system model, automatically generates design variants that respect the requirements and exports those variants to different engineering tools for analysis. Our methodology makes use of a contract-based design algebra to ensure that all generated artifacts for all design variants are consistent by construction, even when the process is modularized and independently developed parts are only later integrated. In contrast with previous work, our approach reduces the search space to models that comply with the captured design requirements.