Machine Learning for Autonomous Driving

About

Welcome to the 2023 Symposium on Machine Learning for Autonomous Driving collocated with NeurIPS!

Autonomous vehicles (AVs) offer a rich source of high-impact research problems for the machine learning (ML) community; including perception, state estimation, probabilistic modeling, time series forecasting, gesture recognition, robustness guarantees, real-time constraints, user-machine communication, multi-agent planning, and intelligent infrastructure. Further, the interaction between ML subfields towards a common goal of autonomous driving can catalyze interesting inter-field discussions that spark new avenues of research, which this symposium aims to promote. As an application of ML, autonomous driving has the potential to greatly improve society by reducing road accidents, giving independence to those unable to drive, and even inspiring younger generations with tangible examples of ML-based technology clearly visible on local streets. All are welcome to attend! This will be the 8th event in this series. Previous workshops in 2016, 2017, 2018, 2019, 2020, 2021, 2022 enjoyed wide participation from both academia and industry.

Attending:
• Attend in person: please register (free) ml4ad2023.eventbrite.com
• Attend virtually: no registration needed, simply join us on zoom
• Authors: please bring a poster up to 24wide x 36high inches

Post Event: all videos now avilable on YouTube

Speakers

Morning speakers

Wei-Lun Chao

Assistant Professor
Ohio State University
Barbara Rakitsch

Research Scientist
Bosch
Dhruv Shah

PhD candidate
UC Berkeley

Afternoon speakers

John Subosits

Research Manager
Toyota Research Institute
Aleksandr Petiushko

Head of ML Research
Nuro
Boris Ivanovic

Research Manager
NVIDIA Research

Schedule

Thursday December 14th, 2023. All times are in Central Standard Time (UTC-6). Current time is

Time	Event	Title
08:55	Welcome
09:00	Wei-Lun Chao Ohio State University	Learning to Perceive by Leveraging the Semantic Cues in Raw Data
09:45	Posters Session 1
11:00	Barbara Rakitsch Bosch	Navigating the Future: Leveraging Large Language Models for Autonomous Driving
11:45	Dhruv Shah UC Berkeley	Learning General-Purpose Robot Navigation
12:30	Lunch and Posters
13:30	John Subosits Toyota Research Institute	Learning at the Limits: ML for High Performance Driving
14:15	Aleksandr Petiushko Nuro	Scaling laws in Autonomy and Behavior
15:00	Posters Session 2
15:45	Boris Ivanovic NVIDIA Research	Architecting Next-Generation Autonomous Vehicle Stacks
16:30	CARLA Challenge German Ros	CARLA Autonomous Driving Challenge 2023
17:30	Closing Remarks and Social

Challenge

The CARLA Autonomous Driving Challenge 2023 winners will present their solutions as part of the symposium. Details here.

Papers

Extended Abstracts

Evaluation of Large Language Models for Decision Making in Autonomous Driving
Kotaro Tanahashi, Yuichi Inoue, Yu Yamaguchi, Hidetatsu Yaginuma, Daiki Shiotsuka, Hiroyuki Shimatani, Kohei Iwamasa, Yushiaki Inoue, Takafumi Yamaguchi, Koki Igari, Tsukasa Horinouchi, Kento Tokuhiro, Yugo Tokuchi, Shunsuke Aoki

Full Papers

Development and Assessment of Autonomous Vehicles in Both Fully Automated and Mixed Traffic Conditions
Ahmed Abdelrahman

Data-parallel Real-Time Perception System with Partial GPU Acceleration for Autonomous Driving
Sol Ahn*, Seungha Kim*, Ho Kang, Jong-Chan Kim

Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps
Till Beemelmanns, Wassim Zahr, Lutz Eckstein

Learn Thy Enemy: Online, Task-Aware Opponent Modeling in Autonomous Racing
Letian Chen, Shawn Manuel, James Delgado, John Subosits, Paul Tylkin

Hierarchical End-to-End Autonomous Navigation through Few-Shot Waypoint Detection
Amin Ghafourian*, Zhongying CuiZhu*, Debo Shi, Ian Chuang, Francois Charette, Rithik Sachdeva, Iman Soltani

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Cole Gulino*, Justin Fu*, Wenjie Luo*, George Tucker*, Eli Bronstein, Yiren Lu, Jean Harb, Xinlei Pan, Yan Wang, Xiangyu Chen, John D Co-Reyes, Rishabh Agarwal, Rebecca Roelofs, Yao Lu, Nico Montali, Paul Mougin, Zoey Yang, Brandyn White, Aleksandra Faust, Rowan McAllister, Dragomir Anguelov, Benjamin Sapp

Deception Game: Closing the Safety-Learning Loop for Autonomous Driving
Haimin Hu*, Zixu Zhang*, Kensuke Nakamura, Andrea Bajcsy, Jaime Fernández Fisac

Robust Driving Across Scenarios via Multi-residual Task Learning
Vindula Jayawardana, Sirui Li, Cathy Wu, Yashar Farid, Kentaro Oguchi

ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
Quanyi Li*, Zhenghao Peng*, Lan Feng*, Zhizheng Liu, Chenda Duan, Wenjie Mo, Bolei Zhou

Safety-aware Causal Representation for Trustworthy Reinforcement Learning in Autonomous Driving
Haohong Lin, Wenhao Ding, Zuxin Liu, Yaru Niu, Jiacheng Zhu, Yuming Niu, Ding Zhao

Hierarchical Learning-Based Autonomy Simulator
Haolan Liu, Jishen Zhao, Liangjun Zhang

The Waymo Open Sim Agents Challenge
Nico Montali, John Lambert, Paul Mougin, Alex Kuefler, Nicholas Rhinehart, Michelle Li, Cole Gulino, Tristan Emrich, Zoey Yang, Shimon Whiteson, Brandyn White, Dragomir Anguelov

Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving
Haoyi Niu*, Qimao Chen*, Yingyue Li, Yi Zhang, Jianming Hu

Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
Haoyi Niu*, Yizhou Xu*, Xingjian Jiang, Jianming Hu

Learning from Active Human Involvement through Proxy Value Propagation
Zhenghao Peng, Wenjie Mo, Chenda Duan, Quanyi Li, Bolei Zhou

Camera-based Context-aware Traffic Light Detection for Self-Driving Vehicles
Daiki Shiotsuka, Yuto Nakamura, Kohei Iwamasa, Yu Yamaguchi, Shunsuke Aoki

Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
Zihan Zhou, Jonathan Booher, Wei Liu, Aleksandr Petiushko, Animesh Garg

Location

Hilton Garden Inn New Orleans Convention Center, 1001 S Peters St, New Orleans, Louisiana 70130, United States
Ground Floor, Mognolia and Camellia Rooms

Organizers

Aman Sinha thisisaman@waymo.com

is a research scientist at Waymo and co-founder of Trustworthy AI, which was acquired by Waymo in 2021.

Nigamaa Nayakanti nigamaa@waymo.com

is a research scientist at Waymo working on behaviour prediction modeling for autonomous vehicles.

Lars Kunze lars@robots.ox.ac.uk

is a Departmental Lecturer in Robotics in the Oxford Robotics Institute and the Department of Engineering Science at the University of Oxford.

Maximilian Naumann Maximilian.Naumann@de.bosch.com

is a research engineer at Bosch Center for Artificial Intelligence.

Avikalp Srivastava avikalp@waymo.com

is a staff software engineer at Waymo Research.

Jiachen Li jiachen_li@stanford.edu

is a Postdoctoral Scholar at Stanford University working on scene understanding and decision making for intelligent systems.

Xinshuo Weng xweng@nvidia.com

is a research scientist at NVIDIA Autonomous Vehicle Research.

Rowan McAllister mcallister@waymo.com

is a staff research scientist at Waymo working on planning for autonomous vehicles.

Challenge Organizers

German Ros grossanchez@nvidia.com

is a director in Simulation Ecosystem Development at NVIDIA
Guillermo Lopez

is a software engineer at CVC & Embodied AI Foundation
Joel Moriana

is a software engineer at CVC & Embodied AI Foundation
Vladlen Koltun

is a Distinguished Scientist at Apple.