Scenic:

Quick Links

• Logistics
• Schedule
• Zoom Link (Breakout Room Link)
• Workshop Map

Abstract

We invite you to join us on August 21-22 for a workshop for current and potential users and developers of the Scenic probabilistic programming language for world modeling and data generation for AI-based autonomy.

The workshop will be hosted at UC Santa Cruz, and will include food and housing from dinner on August 20 through lunch on August 22; virtual attendance options are also available. The workshop will provide hands-on tutorials on programming in the Scenic language, how to interface it to your simulator of choice, how to extend Scenic with new features, and on Scenic's use cases for testing, debugging, synthetic data generation, etc. We will also have a session on industrial applications and breakout groups on topics of special interest such as Scenic's internals and application domains including autonomous driving and robotics. The schedule is summarized below:

August 21: tutorials on how to use and extend Scenic; evening reception
August 22: industry session; working groups and breakout sessions on advanced topics

Overview

Today's autonomous systems rely heavily on the use of machine learning components trained on large amounts of data. Even so, it is expensive to collect relevant data and test these systems in the real world in a manner that captures typical data distributions and also covers edge cases. Therefore, simulators are widely adopted in the robotics and computer vision community to train, test, and debug autonomous and semi-autonomous systems. However, working directly with simulators can be too low-level and problem-specific. To support the design lifecycle of autonomous/semi-autonomous systems, one needs to raise the level of abstraction above individual simulators and provide a formal framework for world modeling. Such a world model can help reason about the safety of a system and facilitate data generation and sim-to-real validation, as well as help to interpret, validate, share, or re-use training and test scenarios across the community.

The objective of this tutorial is to introduce Scenic, an open-source, domain-specific probabilistic programming language for world modeling that addresses the above needs. Scenic is designed to model and generate interactive (or reactive), multi-agent scenarios in a manner portable to any simulator. In Scenic, users can precisely model a stochastic environment in which an autonomous/semi-autonomous system operates, can perform a variety of design and analysis tasks, and can communicate them as interpretable programs. Scenic has a variety of demonstrated use cases, including synthetic data generation, data augmentation, debugging and retraining and redesign of perception components, sim-to-real validation, testing safety of autonomous system both in simulation and in the real world, training reinforcement learning agents in multiplayer settings, and more. To achieve these goals, Scenic has been designed to be (i) intuitive to learn, (ii) probabilistic to capture the uncertainty and stochasticity in the real world, (iii) simulator-agnostic, and (iv) open-source and in the public domain for external members to contribute.

Logistics

Virtual Attendance:

• On Zoom at this link. (Breakout room (here))
• Hands-on sessions will have a member of the Scenic team in the Zoom room to answer questions
• Other sessions will be recorded for those in different time zones

In-Person Attendance:

• Location: College Nine, UC Santa Cruz (detailed map here)
• Check in/out: Central Conference Office, 8 am - 8 pm (see map; contact us if arriving later)
• Parking: Lot 164 (also 114, 165, and 167)
• Main workshop room: Namaste Lounge
• Breakout room: Social Sciences 1, Room 145
• Meals: College Nine/JRL Dining Hall (see map); non-dorm participants are welcome to attend after checking in to receive meal cards.
• More: Conference Attendee Handbook; attendee FAQs; dining hall menus

Schedule

For details, please contact Daniel Fremont.
Website template by Oriane Siméoni from the Object localization for free CVPR '23 tutorial.