This workshop will be held at the CVPR 2025 on June 11th, 2025 at the Music City Center, Nashville, TN, USA. Details will follow.

Abstract

On-road testing of autonomous vehicles presents significant challenges in terms of cost and safety, underscoring the importance of simulation as a crucial tool to accelerate the development of safe autonomous driving (AD), a technology with enormous real-world impact. To extract useful information from simulation, minimizing the sim-to-real gap by developing good agent behavior models, and ensuring faithful perception simulation is essential. While recent years have witnessed a surge of publications in this rapidly evolving field, several fundamental questions remain unanswered, with the research often scattered across different robotics and machine learning venues and research fields.

This workshop aims to unite leading researchers from various specializations, including perception simulation, behavior modeling, planner development, and safety research, to foster interdisciplinary conversations and collaboration.

Call for Papers

Important Dates ๐Ÿ“…

  • Paper Submission Opens: February 18, 2025
  • Paper Submission Deadline: March 15, 2025
  • Notification to Authors: March 31, 2025
  • Camera-Ready Submission: April 7, 2025

Submission Guidelines ๐Ÿ””

We invite submissions of high-quality research to our Archival and Non-Archival tracks. All accepted papers will be eligible for poster presentation. A select number of papers will be chosen for spotlight presentations at the workshop. You need an openreview account for submission.

Topics ๐Ÿš˜

We welcome contributions in the Autonomous Driving domain in the following areas (but not limited to):

  • Improve fidelity and diversity of generative models for behavior and sensor simulation,
  • Develop new metrics for the quality and coverage of generated scenarios,
  • Combine behavior modeling, perception simulation, and safety requirements,
  • Create trust and assess the credibility of the simulation toolchain, and
  • Effectively use simulation to evaluate autonomous vehicles,
  • Effectively use simulation to train autonomous vehicles in closed loop,
  • Incorporate recent advances from other fields, such as RL or foundation models.

For inquiries, feel free to reach out to the organizing committee at: agents4ad@googlegroups.com

Agenda

This full day workshop will take place on Wednesday June 11th, 08:30 to 17:50 CDT (UTC-5).

Below times are in Nashville time. Current time in Nashville is .

Time
Event
Content
8:30
Welcome
8:45

Chelsea Finn

Stanford University

Leveraging Synthetic Data for Robot Training and Evaluation
9:15

Felix Heide

Torc Robotics & Princeton University

Learning to Plan with Self-Play: Fully Data-driven Generative Scenarios for Autonomous Driving
9:45
Poster Presentations 1
10:15
Coffee & Posters
11:00

Johan Engstrom

Waymo

Understanding and modeling of human driver behavior based on active inference
11:30

Marco Pavone

NVIDIA & Stanford University

Building Physical AI with Foundation-Model-Driven Closed-Loop Simulation
12:00
Lunch Break
14:00

Dragomir Anguelov

Waymo

tbd
14:30
Poster Presentations 2
15:15
Coffee & Posters
16:00

Eugene Vinitsky

New York University

Robust Self-Driving Emerges from Self-Play
16:30

Raquel Urtasun

Waabi

tbd
17:00
Panel Discussion (moderated by Sanja Fidler)
17:45
Closing remarks

Invited Speakers


Chelsea Finn

Stanford University

Felix Heide

Torc Robotics & Princeton University

Johan Engstrom

Waymo

Marco Pavone

NVIDIA & Stanford University

Dragomir Anguelov

Waymo

Eugene Vinitsky

New York University

Raquel Urtasun

Waabi

Organizers


Azadeh Dinparastdjadid

Waymo

Zan Gojcic

NVIDIA

Max

Maximilian Igl

NVIDIA

Max

Maximilian Naumann

Bosch Center for Artificial Intelligence and KIT

Thomas

Thomas Gilles

Waabi

Kate

Kate Tolstaya

Waymo

Sanja Fidler

NVIDIA and University of Toronto

Shimon

Shimon Whiteson

Waymo UK and University of Oxford

Contact: agents4ad@googlegroups.com

Program Committee

The DDADS workshop organizers would like to extend our sincere gratitude to the community of reviewers who generously volunteered their time and expertise to evaluate submissions for our workshop.

  • Frieda Rong
  • Ioan Andrei Bรขrsan
  • Reinis Cimurs
  • Shu-Yuan Liu
  • Thomas Roddick
  • Vishal Kirankumar Shah
  • Zhejun Zhang