We develop specialized techniques for sampling from the resulting distribution, taking advantage of the structure provided by Scenic’s domain-specific syntax. ![]() Scenic combines concise, readable syntax for spatiotemporal relationships with the ability to declaratively impose hard and soft constraints over the scenario. ![]() We design a domain-specific language, Scenic, for describing scenarios that are distributions over scenes and the behaviors of their agents over time. In this paper, we focus on systems such as autonomous cars and robots, whose environment at any point in time is a scene, a configuration of physical objects and agents. More generally, such languages can be used to write environment models, an essential prerequisite to any formal analysis. We show how a probabilistic programming language can help address these problems by specifying distributions encoding interesting types of inputs, then sampling these to generate specialized training and test data. We consider several problems arising in the design process, including training a system to be robust to rare events, testing its performance under different conditions, and debugging failures. We propose a new probabilistic programming language for the design and analysis of cyber-physical systems, especially those based on machine learning.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |