Scenic: a language for scenario specification and scene generation

By Daniel J. Fremont, Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia. ACM-SIGPLAN Symposium on Programming Language Design and Implementation, 2018

325 citations recorded by the source corpus.

We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning. Specifically, we consider the problems of training a perception system to handle rare events, testing its performance under different conditions, and debugging failures. We show how a probabilistic programming language can help address these problems by specifying distributions encoding interesting types of inputs and sampling these to generate specialized training and test sets. More generally, such languages can be used for cyber-physical systems and robotics to write environment models, an essential prerequisite to any formal analysis. In this paper, we focus on systems like autonomous cars and robots, whose environment is a scene, a configuration of physical objects and agents. We design a domain-specific language, Scenic, for describing scenarios that are distributions over scenes. As a probabilistic programming language, Scenic allows assigning distributions to features of the scene, as well as declaratively imposing hard and soft constraints over the scene. We develop specialized techniques for sampling from the resulting distribution, taking advantage of the structure provided by Scenic's domain-specific syntax. Finally, we apply Scenic in a case study on a convolutional neural network designed to detect cars in road images, improving its performance beyond that achieved by state-of-the-art synthetic data generation methods.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c9be43603c133fb61143481dc7af59653130c579

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Seon-Mee Kim
Q. Lu
Keunhae Ushiroda
Eric Boise
B. Shin
Geehoon Uhm
Dmitry Zelenkovsky
Michael Reyes

Citations in the corpus

LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving (2020, methodology): “To verify the effectiveness of our simulation, we collaborated with UC-Berkeley to test thousands of scenarios generated by Scenic [33] in the digital twin of GoMentum Station [32] and selected several representative scenarios to test in real GoMentum Station.”
End-to-End Autonomous Driving: Challenges and Frontiers (2023, unknown): “Procedural generation algorithms combine rules, heuristics, and randomization to create diverse road networks, trafﬁc patterns, lighting conditions, and object placements [94], [95].”