Welcome to the NeurIPS 2019 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.
→DiDi Challenge submission due: 30th November 2019:
→Argo Challenge submission due: 1st December 2019:
→Camera-ready papers due: 1st December 2019:
1:30 PM Talk title (TBD)
Associate Professor, UToronto / Chief Scientist at Uber
Time (TBD) Talk title (TBD)
Principal Autonomous Vehicle Engineer at nuTonomy
Time (TBD) Talk title (TBD)
Assistant Professor, MIT / Microsoft
Time (TBD) Talk title (TBD)
UC Berkeley / Princeton
Camera-ready deadline: 1st December 2019 at 23:59 Anywhere on Earth
Submission website: https://cmt3.research.microsoft.com/ML4AD2019
Submission format: either extended abstracts (4 pages) or full papers (8 pages) anonymously using:
• neurips_2019_ml4ad.tex -- LaTeX template
• neurips_2019_ml4ad.sty -- style file for LaTeX 2e
• neurips_2019_ml4ad.pdf -- example PDF output
References and appendix should be appended into the same (single) PDF document, and do not count towards the page count.
We invite submissions on machine learning applied to autonomous driving, including (but not limited to):
• Supervised scene perception and classification
• Unsupervised representation learning for driving
• Behavior modeling of pedestrians and vehicles
• Gesture recognition
• Uncertainty propagation through AV software pipelines
• Metrics for autonomous driving
• Benchmarks for autonomous driving
• Real-time inference and prediction
• Causal modeling for multi-agent traffic scenarios
• Robustness to out-of-distribution road scenes
• Imitative driving policies
• Transfer learning from simulation to real-world (Sim2Real)
• Coordination with human-driven vehicles
• Coordination with vehicles (V2V) or infrastructure (V2I)
• Explainable driving decisions
• Adaptive driving styles based on user preferences
Q: Are dual submissions OK?
Q: Will there be archival proceedings?
A: No. Neither 4 or 8 page submissions will be indexed nor have archival proceedings.
Q: Should submitted papers be anonymized?
A: Yes. If accepted, we will ask for a de-anonymized version to link on the website.
Q: What is the poster specification?
A: Portrait: 36W x 48H inches (90W x 122H cm) on light weight paper, not laminated.
|9:00 AM||Talk title (TBD) Intel|
|9:30 AM||Posters + Coffee||-|
|Time (TBD)||Towards Robust Interactive Autonomy MIT|
|11:00 AM||ArgoAI Challenge||-|
|Time (TBD)||Human-inspired AI for autonomous driving iSee|
|1:30 PM||Talk title (TBD) UToronto, Uber|
|2:00 PM||DiDi Challenge||-|
|Time (TBD)||Talk title (TBD) nuTonomy|
|3:00 PM||Contributed Talks||-|
|3:30 PM||Posters + Coffee||-|
|Time (TBD)||Talk title (TBD) MIT / Microsoft|
|Time (TBD)||Talk title (TBD) UC Berkeley, Waymo|
We are hosting the first Argoverse competitions for 3d tracking and motion forecasting. The prize pool is $5,000 and winners will be invited to intern at Argo and present their methods at the workshop. More details can be found here.
Open for submissions through: 1st December 2019:
We are also hosting the D²-City Detection Domain Adaptation Challenge, a transfer learning challenge for object detection. The prize pool is $1,700 and winners will be invited to present their methods at the workshop.
Open for submissions through: 30th November 2019:
Rowan McAllister email@example.com
is a postdoctoral researcher at UC Berkeley working on probabilistic models for safe motion planning with autonomous vehicles.
Nicholas Rhinehart firstname.lastname@example.org
is a Ph.D. student at Carnegie Mellon University, focusing on understanding, forecasting, and control with computer vision and machine learning.
Fisher Yu email@example.com
is a postdoctoral researcher at UC Berkeley working in image recognition, interactive data processing systems, and high-level understanding of dynamic 3D scenes.
Li Erran Li firstname.lastname@example.org
is head of machine learning at Scale.ai and an adjunct professor at Columbia University.
Anca Dragan email@example.com
is an Assistant Professor at UC Berkeley and runs the InterACT Lab, focusing on algorithms for human-robot interaction.
We thank those who help make this workshop possible!
• Elmira Amirloo
• Hossein Azizpour
• Arjun Nitin Bhagoji
• Maciej Brzeski
• Sebastian Bujwid
• Wei-Lun Chao
• Weikai Chen
• Xinyun Chen
• Chen Chen
• Fang-Chieh Chou
• Henggang Cui
• Neema Davis
• Zihan Ding
• Nemanja Djuric
• Alexey Dosovitskiy
• Hesham M. Eraqi
• Andrien Gaidon
• Yang Gao
• Paweł Gora
• Mikael Henaff
• Ravi Kiran
• Edouard Leurent
• Zhuwen Li
• Xiaoyuan Liang
• Xiao-Yang Liu
• Sergio Macua
• Miquel Martí
• Marcin Możejko
• Lukas Neumann
• Thi Nguyen
• Gaurav Raina
• German Ros
• Ahmad El Sallab
• Axel Sauer
• Mark Schutera
• Ibrahim Sobh
• Zhaoen Su
• Anthony Tompkins
• Stephen Tu
• Andrea Vedaldi
• Dequan Wang
• Bin Wang
• Hua Wei
• Peyman Yadmellat
• Xinchen Yan
• Hengshuai Yao
• Mohamed Zahran
• Jiakai Zhang
• Yuzheng Zhuang