Workshop
Machine Learning for Autonomous Driving
Jiachen Li 路 Nigamaa Nayakanti 路 Xinshuo Weng 路 Daniel Omeiza 路 Ali Baheri 路 German Ros 路 Rowan McAllister
Theater B
Sat 3 Dec, 6:20 a.m. PST
Welcome to the NeurIPS 2022 Workshop on Machine Learning for Autonomous Driving!
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 workshop 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 7th NeurIPS workshop in this series. Previous workshops in 2016, 2017, 2018, 2019, 2020, and 2021 enjoyed wide participation from both academia and industry.
Schedule
Sat 6:20 a.m. - 6:30 a.m.
|
Welcome
(
Opening Remarks
)
>
SlidesLive Video |
馃敆 |
Sat 6:30 a.m. - 7:05 a.m.
|
Vision-centric Autonomous Driving: from Perception to Prediction
(
Talk
)
>
SlidesLive Video |
Hang Zhao 馃敆 |
Sat 7:05 a.m. - 7:40 a.m.
|
Toward Generalizable Embodied AI for Autonomous Driving
(
Talk
)
>
SlidesLive Video |
Bolei Zhou 馃敆 |
Sat 7:40 a.m. - 8:10 a.m.
|
Paper Spotlight Talks
(
Talk
)
>
SlidesLive Video |
馃敆 |
Sat 8:10 a.m. - 9:00 a.m.
|
Posters and Break
(
Poster
)
>
|
馃敆 |
Sat 9:00 a.m. - 9:35 a.m.
|
Trustworthy Machine Learning in Autonomous Driving
(
Talk
)
>
SlidesLive Video |
Bo Li 馃敆 |
Sat 9:45 a.m. - 10:10 a.m.
|
Scenario generation for long-tail discovery
(
Talk
)
>
SlidesLive Video |
Yuning Chai 馃敆 |
Sat 10:10 a.m. - 11:00 a.m.
|
Lunch and Posters
(
Poster
)
>
|
馃敆 |
Sat 11:00 a.m. - 11:35 a.m.
|
Contingency Planning with Learned Models of Behavioral and Perceptual Uncertainty
(
Talk
)
>
SlidesLive Video |
Nicholas Rhinehart 馃敆 |
Sat 11:35 a.m. - 12:10 p.m.
|
CausalAgents: A robustness benchmark for motion forecasting using causal relationships
(
Talk
)
>
SlidesLive Video |
Liting Sun 馃敆 |
Sat 12:10 p.m. - 1:00 p.m.
|
Posters and Break
(
Poster
)
>
|
馃敆 |
Sat 1:00 p.m. - 1:35 p.m.
|
Operating Autonomous Vehicles In Different Contexts - On Roads and In Shared Spaces
(
Talk
)
>
|
Stewart Worrall 馃敆 |
Sat 1:35 p.m. - 2:55 p.m.
|
CARLA Challenge
(
Talk
)
>
SlidesLive Video |
馃敆 |
Sat 2:55 p.m. - 3:00 p.m.
|
Closing Remarks
(
Closing Remarks
)
>
SlidesLive Video |
馃敆 |
-
|
Fast-BEV: Towards Real-time On-vehicle Bird鈥檚-Eye View Perception
(
Poster
)
>
SlidesLive Video |
Bin Huang 路 Yangguang Li 路 Feng Liang 路 Enze Xie 路 Luya Wang 路 Mingzhu Shen 路 Fenggang Liu 路 Tianqi Wang 路 Ping Luo 路 Jing Shao 馃敆 |
-
|
A Versatile and Efficient Reinforcement Learning Approach for Autonomous Driving
(
Poster
)
>
SlidesLive Video |
Guan Wang 路 Haoyi Niu 路 desheng zhu 路 Jianming HU 路 Xianyuan Zhan 路 Guyue Zhou 馃敆 |
-
|
VN-Transformer: Rotation-Equivariant Attention for Vector Neurons
(
Poster
)
>
SlidesLive Video |
Serge Assaad 路 Carlton Downey 路 Rami Al-Rfou 路 Nigamaa Nayakanti 路 Benjamin Sapp 馃敆 |
-
|
Improving Motion Forecasting for Autonomous Driving with the Cycle Consistency Loss
(
Poster
)
>
SlidesLive Video |
Titas Chakraborty 路 Akshay Bhagat 路 Henggang Cui 馃敆 |
-
|
Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
(
Poster
)
>
SlidesLive Video |
Hyunsu Rhee 路 Dongchan Min 路 Sunil Hwang 路 Bruno Andreis 路 Sung Ju Hwang 馃敆 |
-
|
An Intelligent Modular Real-Time Vision-Based System for Environment Perception
(
Poster
)
>
SlidesLive Video |
Amirhossein Kazerouni 路 Amirhossein Heydarian 路 Milad Soltany 路 Aida Mohammadshahi 路 Abbas Omidi 路 Saeed Ebadollahi 馃敆 |
-
|
ViT-DD: Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection
(
Poster
)
>
SlidesLive Video |
Yunsheng Ma 路 Ziran Wang 馃敆 |
-
|
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
(
Poster
)
>
SlidesLive Video |
Aleksandr Kim 路 Guillem Braso 路 Aljosa Osep 路 Laura Leal-Taix茅 馃敆 |
-
|
A Graph Representation for Autonomous Driving
(
Poster
)
>
SlidesLive Video |
Zerong Xi 路 Gita Sukthankar 馃敆 |
-
|
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation
(
Poster
)
>
SlidesLive Video |
Timo Saemann 路 Ahmed Hammam 路 Andrei Bursuc 路 Christoph Stiller 路 Horst-Michael Gross 馃敆 |
-
|
CAMEL: Learning Cost-maps Made Easy for Off-road Driving
(
Poster
)
>
SlidesLive Video |
Kasi Viswanath 路 PB Sujit 路 Srikanth Saripalli 馃敆 |
-
|
DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehicles
(
Poster
)
>
SlidesLive Video |
Peter Karkus 路 Boris Ivanovic 路 Shie Mannor 路 Marco Pavone 馃敆 |
-
|
Stress-Testing Point Cloud Registration on Automotive LiDAR
(
Poster
)
>
SlidesLive Video |
Amnon Drory 路 Raja Giryes 路 Shai Avidan 馃敆 |
-
|
Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception
(
Poster
)
>
SlidesLive Video |
Marc Uecker 路 Tobias Fleck 路 Marcel Pflugfelder 路 Marius Z枚llner 馃敆 |
-
|
Direct LiDAR-based object detector training from automated 2D detections
(
Poster
)
>
SlidesLive Video |
Robert McCraith 路 Eldar Insafutdinov 路 Lukas Neumann 路 Andrea Vedaldi 馃敆 |
-
|
Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of Experts
(
Poster
)
>
SlidesLive Video |
Stefano Pini 路 Christian Perone 路 Aayush Ahuja 路 Ana Sofia Rufino Ferreira 路 Moritz Niendorf 路 Sergey Zagoruyko 馃敆 |
-
|
Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap
(
Poster
)
>
SlidesLive Video |
Mathias Lechner 路 Ramin Hasani 路 Alexander Amini 路 Tsun-Hsuan Johnson Wang 路 Thomas Henzinger 路 Daniela Rus 馃敆 |
-
|
Verifiable Goal Recognition for Autonomous Driving with Occlusions
(
Poster
)
>
SlidesLive Video |
Cillian Brewitt 路 Massimiliano Tamborski 路 Stefano Albrecht 馃敆 |
-
|
PnP-Nav: Plug-and-Play Policies for Generalizable Visual Navigation Across Robots
(
Poster
)
>
SlidesLive Video |
Dhruv Shah 路 Ajay Sridhar 路 Arjun Bhorkar 路 Noriaki Hirose 路 Sergey Levine 馃敆 |
-
|
Finding Safe Zones of Markov Decision Processes Policies
(
Poster
)
>
SlidesLive Video |
Lee Cohen 路 Yishay Mansour 路 Michal Moshkovitz 馃敆 |
-
|
CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk Minimization
(
Poster
)
>
SlidesLive Video |
Eesha Kumar 路 Yiming Zhang 路 Stefano Pini 路 Simon Stent 路 Ana Sofia Rufino Ferreira 路 Sergey Zagoruyko 路 Christian Perone 馃敆 |
-
|
Missing Traffic Data Imputation Using Multi-Trajectory Parameter Transferred LSTM
(
Poster
)
>
SlidesLive Video |
Jungmin Kwon 路 Hyunggon Park 馃敆 |
-
|
Uncertainty-aware self-training with expectation maximization basis transformation
(
Poster
)
>
SlidesLive Video |
Zijia Wang 路 Wenbin Yang 路 Zhi-Song Liu 路 Zhen Jia 馃敆 |
-
|
Potential Energy based Mixture Model for Noisy Label Learning
(
Poster
)
>
SlidesLive Video |
Zijia Wang 路 Wenbin Yang 路 Zhi-Song Liu 路 Zhen Jia 馃敆 |
-
|
Rationale-aware Autonomous Driving Policy utilizing Safety Force Field implemented on CARLA Simulator
(
Poster
)
>
SlidesLive Video |
Ho Suk 路 Taewoo Kim 路 Hyungbin Park 路 PAMUL YADAV 路 Junyong Lee 路 Shiho Kim 馃敆 |
-
|
PlanT: Explainable Planning Transformers via Object-Level Representations
(
Poster
)
>
SlidesLive Video |
Katrin Renz 路 Kashyap Chitta 路 Otniel-Bogdan Mercea 路 A. Sophia Koepke 路 Zeynep Akata 路 Andreas Geiger 馃敆 |
-
|
Multi-Modal 3D GAN for Urban Scenes
(
Poster
)
>
SlidesLive Video |
Lo茂ck Chambon 路 Mickael Chen 路 Tuan-Hung VU 路 Alexandre Boulch 路 Andrei Bursuc 路 Matthieu Cord 路 Patrick P茅rez 馃敆 |
-
|
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
(
Poster
)
>
SlidesLive Video |
Niklas Hanselmann 路 Katrin Renz 路 Kashyap Chitta 路 Apratim Bhattacharyya 路 Andreas Geiger 馃敆 |
-
|
Enhancing System-level Safety in Autonomous Driving via Feedback Learning
(
Poster
)
>
SlidesLive Video |
Sin Yong Tan 路 Weisi Fan 路 Qisai Liu 路 Tichakorn Wongpiromsarn 路 Soumik Sarkar 馃敆 |
-
|
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
(
Poster
)
>
SlidesLive Video |
14 presentersYiren Lu 路 Yiren Lu 路 Yiren Lu 路 Justin Fu 路 George Tucker 路 Xinlei Pan 路 Eli Bronstein 路 Rebecca Roelofs 路 Benjamin Sapp 路 Brandyn White 路 Aleksandra Faust 路 Shimon Whiteson 路 Dragomir Anguelov 路 Sergey Levine |
-
|
VISTA: VIrtual STereo based Augmentation for Depth Estimation in Automated Driving
(
Poster
)
>
SlidesLive Video |
Bin Cheng 路 Kshitiz Bansal 路 Mehul Agarwal 路 Gaurav Bansal 路 Dinesh Bharadia 馃敆 |
-
|
Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification
(
Poster
)
>
SlidesLive Video |
Pasquale Antonante 路 Heath Nilsen 路 Luca Carlone 馃敆 |
-
|
Risk Perception in Driving Scenes
(
Poster
)
>
|
Nakul Agarwal 路 Yi-Ting Chen 馃敆 |
-
|
Robust Trajectory Prediction against Adversarial Attacks
(
Poster
)
>
SlidesLive Video |
Yulong Cao 路 Danfei Xu 路 Xinshuo Weng 路 Zhuoqing Morley Mao 路 Anima Anandkumar 路 Chaowei Xiao 路 Marco Pavone 馃敆 |
-
|
Calibrated Perception Uncertainty Across Objects and Regions in Bird's-Eye-View
(
Poster
)
>
SlidesLive Video |
Markus K盲ngsepp 路 Meelis Kull 馃敆 |
-
|
DriveCLIP: Zero-shot transfer for distracted driving activity understanding using CLIP
(
Poster
)
>
SlidesLive Video |
Md Zahid Hasan 路 Ameya Joshi 路 Mohammed Shaiqur Rahman 路 Venkatachalapathy Archana 路 Anuj Sharma 路 Chinmay Hegde 路 Soumik Sarkar 馃敆 |
-
|
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
(
Poster
)
>
SlidesLive Video |
Yulong Cao 路 Chaowei Xiao 路 Anima Anandkumar 路 Danfei Xu 路 Marco Pavone 馃敆 |
-
|
One-Shot Learning of Visual Path Navigation for Autonomous Vehicles
(
Poster
)
>
SlidesLive Video |
Zhongying CuiZhu 路 Francois Charette 路 Amin Ghafourian 路 Debo Shi 路 Matthew Cui 路 Anjali Krishnamachar 路 Iman Soltani 馃敆 |
-
|
TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
(
Poster
)
>
SlidesLive Video |
Suraj Kothawade 路 Saikat Ghosh 路 Sumit Shekhar 路 Yu Xiang 路 Rishabh Iyer 馃敆 |