This workshop will be held at the IEEE/RSJ IROS 2023, on October 5th, 2023, in Room 140E at Huntington Place, Detroit, MI, USA and streamed online (via zoom).

Abstract

Simulation is a crucial tool to accelerate the development of Autonomous Driving (AD) algorithms. Realistic traffic agent models reduce the sim-to-real gap and have the potential to massively scale evaluation of AD algorithms, paying into both development and safe deployment of AD systems.

Research in traffic agent modeling has recently made great advances, for example due to the switch to graph neural networks and training through sequential decisions. Yet, the research is scattered over different robotics and machine learning venues.

This workshop shall provide a platform to highlight recent advances and future directions towards realistic traffic agent models. Furthermore, this workshop shall provide insights from related fields such as prediction, motion planning and AV safety. Through a mix of invited talks from both academia and industry, paper presentations, and a panel discussion, attendees will be able to catch up with the latest advances, promising directions and most pressing challenges. Attendees will also be able to network in this growing field of research and related areas.

Location

On site: Room 140E at Huntington Place, Detroit, MI, USA.

Online: streamed via zoom.

Agenda

This full day workshop will take place on Thursday Oct 5th, 08:30 to 17:30 EDT (UTC-4). ICS-file.

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

Time
Event
Content
08:30
Welcome
-
08:45
Maria Soledad Elli
Data Scientist, Intel
Operational Safety Assessment of Automated Vehicles in Simulation
09:05
Alyssa Pierson
Assistant Professor, Boston University
09:25
Holger Caesar
Assistant Professor, TU Delft
09:45
Spotlight presentations of posters
-
10:00
Coffee break and poster session 1
-
11:00
Henggang Cui
Principal Engineer, Prediction Team Lead at Motional
11:20
Jonah Philion
Research Scientist, NVIDIA
PhD Student, U. of Toronto
11:40
Marco Pavone
Director AV Research, NVIDIA
Associate Professor, Stanford University
12:10
Lunch break
-
13:30
Nico Montali
Research Engineer, Waymo
John Lambert
Research Scientist, Waymo
Waymo’s Sim Agents Challenge: How to evaluate agent quality?
14:00
Eric Wolff
Research Scientist, Behavior Research Lead, Cruise
14:30
Chris Zhang
Research Scientist, Waabi
Kelvin Wong
Research Scientist, Waabi
15:00
Coffee break and poster session 2
-
16:00
Tianyu Tang
PhD Student, TU Munich
What information do humans base their (traffic) behavior decision on - insights from ergonomics
16:40
Panel Discussion
-
17:25
Closing remarks
-

Invited Speakers


Maria Soledad Elli

Data Scientist, Intel

Alyssa Pierson

Assistant Professor, Boston University

Holger Caesar

Assistant Professor, TU Delft

Henggang Cui

Principal Engineer, Prediction Team Lead at Motional

Jonah Philion

Research Scientist, NVIDIA
PhD Student, U. of Toronto

Marco Pavone

Director AV Research, NVIDIA
Associate Professor, Stanford University

Nico Montali

Research Engineer, Waymo

John Lambert

Research Scientist, Waymo

Eric Wolff

Research Scientist, Behavior Research Lead, Cruise

Chris Zhang

Research Scientist, Waabi

Kelvin Wong

Research Scientist, Waabi

Tianyu Tang

PhD Student, TU Munich

Thomas Lich

Senior Expert and Team Lead, Bosch Accident Research

Papers

Title
Authors
Links
Can you text what is happening? Integrating pretrained language encoders into trajectory prediction models for autonomous driving
Ali Keysan, Andreas Look, Eitan Kosman, Gonca Gürsun, Jörg Wagner, Yu Yao, Barbara Rakitsch
Differentiable Constrained Imitation Learning for Robot Motion Planning and Control
Christopher Diehl, Janis Adamek, Martin Krueger, Frank Hoffmann, Torsten Bertram
Simulation-based evaluation of a generic Autonomous Emergency Braking system using a cognitive pedestrian behavior model
Lucas Fonseca Alexandre de Oliveira, Lukas Brostek, Martin Meywerk

Organizers


Max

Maximilian Naumann

Bosch Center for Artifical Intelligence and KIT

Max

Maximilian Igl

Waymo Research

Simon

Simon Suo

Thomas

Thomas Gilles

Waabi and MINES Paris - PSL

Yiren

Yiren Lu

Waymo Research

Fabien

Fabien Moutarde

MINES Paris - PSL

Anca

Anca Dragan

UC Berkeley

Shimon

Shimon Whiteson

Waymo UK and University of Oxford

Contact: agents4ad@googlegroups.com

Support

This workshop is supported by the

  • IEEE RAS Technical Committee on Algorithms for Planning and Control of Robot Motion
  • IEEE RAS Technical Committee on Autonomous Ground Vehicles and Intelligent Transportation Systems
  • IEEE ITSS Technical Committee on Self-Driving Automobiles