Machine Learning for Autonomous Driving

December 11th


Welcome to the NeurIPS 2020 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 5th NeurIPS workshop in this series. Previous workshops in 2016, 2017, 2018 and 2019 enjoyed wide participation from both academia and industry.

1. Register for NeurIPS
2. Watch talks live from our NeurIPS Portal and ask questions in the "Chat" window (begins 7:55am PST on Dec 11th)
3. Chat with authors during the GatherTown poster sessions (9:20am, 12:00pm, 2:20pm PST)



Paper Submission due: 14th October 2020
Reviewing starts: 15th October 2020
Reviewing ends: 26th October 2020
Paper Notification: 30th October 2020
Contributed talks due: 14th November 2020
Camera-ready papers due: 1st December 2020


Challenge Submission due: 25th November 2020, 22:00 PST
Challenge Notification: 26th November 2020, 22:00 PST
Technical report submission: 26th November 2020, 22:00 PST
Accepted technical report notification: 29th November 2020, 22:00 PST
Video presentation submission: 6th December 2020, 22:00 PST


Workshop event: 11th December 2020



All times are in Pacific Time (PST)

Time Event Talk
7:55 AM Welcome
8:00 AM Patrick Perez Patrick Perez Valeo Addressing some Challenges of ML4AD
8:40 AM Angela Schoellig Angela Schoellig University of Toronto Machine Learning for Safety-Critical Robotics Applications
9:20 AM Posters + Coffee Gather Town
10:00 AM Jianxiong Xiao Jianxiong Xiao AutoX Leading the Self-driving Car Innovation in Asia
10:40 AM Pin Wang Pin Wang University of California Berkeley Learning Decision-making Behaviors from Demonstrations based on Adversarial Inverse Reinforcement Learning
11:10 AM Ehud Sharlin Ehud Sharlin University of Calgary On Human-Robot Interaction and Crossing a Street in the Era of Autonomous Vehicles
12:00 PM Break + Posters Gather Town
1:00 PM Byron Boots Byron Boots University of Washington Online Learning for Adaptive Robotic Systems
1:40 PM Brandyn White Brandyn White Waymo Learning a Multi-Agent Simulator from Offline Demonstrations
2:20 PM Posters + Coffee Gather Town
3:00 PM Challenge CARLA Challenge
4:00 PM Beipeng Mu Beipeng Mu Building HDmap using Mass Production Data


The CARLA Autonomous Driving Challenge 2020 winners will present their solutions as part of the workshop. Details: here

Accepted Papers And Abstracts

Single Shot Multitask Pedestrian Detection and Behavior Prediction
Prateek Agrawal, Pratik Prabhanjan Brahma
paper | video | poster 57

Extracting Traffic Smoothing Controllers Directly From Driving Data using Offline RL
Thibaud Ardoin, Eugene Vinitsky, Alexandre Bayen
paper | video | poster 41

Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
Tiago Azevedo, René de Jong, Matthew Mattina, Partha Maji
paper | video | poster 9

MODETR: Moving Object Detection with Transformers
Eslam Bakr, Ahmad ElSallab, Hazem Rashed
paper | video | poster 30

Driving Behavior Explanation with Multi-level Fusion
Hedi Ben-Younes*, Éloi Zablocki*, Patrick Pérez, Matthieu Cord
paper | video | poster 16

Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving
Manoj Bhat, Jonathan Francis, Jean Oh
paper | video | poster 51

Haar Wavelet based Block Autoregressive Flows for Trajectories
Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario Fritz, Bernt Schiele
paper | video | poster 21

YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
Yuxuan Cai*, Geng Yuan*, Hongjia Li*, Wei Niu, Yanyu Li, Xulong Tang, Bin Ren, Yanzhi Wang
paper | video | poster 20

DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
Marvin Chancán, Michael Milford
paper | video | poster 43

SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction
Jaehoon Choi*, Dongki Jung*, Donghwan Lee, Changick Kim
paper | video | poster 31

Uncertainty-aware Vehicle Orientation Estimation for Joint Detection-Prediction Models
Henggang Cui, Fang-Chieh Chou, Jake Charland, Carlos Vallespi-Gonzalez, Nemanja Djuric
paper | video | poster 18

Multiagent Driving Policy for Congestion Reduction in a Large Scale Scenario
Jiaxun Cui, William Macke, Aastha Goyal, Harel Yedidsion, Daniel Urieli, Peter Stone
paper | video | poster 19

Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS
Flora Dellinger, Thomas Boulay, Diego Mendoza Barrenechea, Said El-Hachimi, Isabelle Leang, Fabian Bürger
paper | video | poster 38

Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
Bo Dong, Hao Liu, Yu Bai, Jinbiao Lin, Zhuoran Xu, Xinyu Xu, Qi Kong
paper | video | poster 1

3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation
Netalee Efrat, Max Bluvstein, Shaul Oron, Dan Levi, Noa Garnett, Bat El Shlomo
paper | video | poster 24

ULTRA: A Reinforcement Learning Generalization Benchmark for Autonomous Driving
Mohamed Elsayed*, Kimia Hassanzadeh*, Nhat Nguyen*, Montgomery Alban, Xiru Zhu, Daniel Graves, Jun Luo
paper | video | poster 49

Conditional Imitation Learning Driving Considering Camera and LiDAR Fusion
Hesham Eraqi, Mohamed Moustafa, Jens Honer
paper | video | poster 13

Reinforcement Learning Based Approach for Multi-Vehicle Platooning Problem with Nonlinear Dynamic Behavior
Amr Farag, Omar Abdelaziz, Ahmed Hussein, Omar Shehata
paper | video | poster 32

RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition
Xiangyu Gao, Guanbin Xing, Sumit Roy, Hui Liu
paper | video | poster 22

Disagreement-Regularized Imitation of Complex Multi-Agent Interactions
Nate Gruver, Jiaming Song, Stefano Ermon
paper | video | poster 46

Certified Interpretability Robustness for Class Activation Mapping
Alex Gu, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel
paper | video | poster 10

Physically Feasible Vehicle Trajectory Prediction
Harshayu Girase*, Jerrick Hoang*, Sai Yalamanchi, Micol Marchetti-Bowick
paper | video | poster 55

A Comprehensive Study on the Application of Structured Pruning methods in Autonomous Vehicles
Ahmed Hamed*, Ibrahim Sobh*
paper | video | poster 45

Annotating Automotive Radar efficiently: Semantic Radar Labeling Framework (SeRaLF)
Simon Isele*, Marcel Schilling*, Fabian Klein, Marius Zöllner
paper | video | poster 59

IDE-Net: Extracting Interactive Driving Patterns from Human Data
Xiaosong Jia, Liting Sun, Masayoshi Tomizuka, Wei Zhan
paper | video | poster 56

Vehicle Speed Data Imputation based on Parameter Transferred LSTM
Jungmin Kwon, Chaeyeon Cha, Hyunggon Park
paper | video | poster 58

Vehicle Trajectory Prediction by Transfer Learning of Semi-Supervised Models
Nick Lamm, Shashank Jaiprakash, Malavika Srikanth, Iddo Drori
paper | video | poster 11

Instance-wise Depth and Motion Learning from Monocular Videos
Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
paper | video | poster 62

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
Jiachen Li, Fan Yang, Masayoshi Tomizuka, Chiho Choi
paper | video | poster 8

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting
Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman, Osbert Bastani
paper | video | poster 50

A Distributed Delivery-Fleet Management Framework using Deep Reinforcement Learning and Dynamic Multi-Hop Routing
Kaushik Manchella, Marina Haliem, Vaneet Aggarwal, Bharat Bhargava
paper | video | poster 53

Calibrating Self-supervised Monocular Depth Estimation
Robert McCraith, Lukas Neumann, Andrea Vedaldi
paper | poster 15

Real-time Semantic and Class-agnostic Instance Segmentation in Autonomous Driving
Eslam Mohamed*, Mahmoud Ewaisha*, Mennatullah Siam, Hazem Rashed, Senthil Yogamani, Waleed Hamdy, Muhammad Helmi, Ahmad ElSallab
paper | video | poster 7

Investigating the Effect of Sensor Modalities in Multi-Sensor Detection-Prediction Models
Abhishek Mohta, Fang-Chieh Chou, Brian Becker, Carlos Vallespi-Gonzalez, Nemanja Djuric
paper | video | poster 37

Real2sim: Automatic Generation of Open Street Map Towns For Autonomous Driving Benchmarks
Avishek Mondal, Panagiotis Tigas, Yarin Gal
paper | video | poster 40

CARLA Real Traffic Scenarios – Novel Training Ground and Benchmark for Autonomous Driving
Błażej Osiński, Piotr Miłoś, Adam Jakubowski, Paweł Zięcina, Michał Martyniak, Christopher Galias, Antonia Breuer, Silviu Homoceanu, Henryk Michalewski
paper | video | poster 44

FisheyeYOLO: Object Detection on Fisheye Cameras for Autonomous Driving
Hazem Rashed*, Eslam Bakr*, Ganesh Sistu*, Varun Ravi Kumar, Ciarán Eising, Ahmad El-Sallab, Senthil Yogamani
paper | video | poster 6

PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D
Amir Rasouli, Tiffany Yau, Peter Lakner, Saber Malekmohammadi, Mohsen Rohani, Jun Luo
paper | video | poster 14

Risk Assessment for Machine Learning Models
Paul Schwerdtner*, Florens Greßner*, Nikhil Kapoor*, Felix Assion, René Sass, Wiebke Günther, Fabian Hüger, Peter Schlicht
paper | video | poster 33

Distributionally Robust Online Adaptation via Offline Population Synthesis
Aman Sinha*, Matthew O'Kelly*, Hongrui Zheng*
paper | video | poster 52

Temporally-Continuous Probabilistic Prediction using Polynomial Trajectory Parameterization
Zhaoen Su, Chao Wang, Henggang Cui, Nemanja Djuric, Carlos Vallespi-Gonzalez, David Bradley
paper | video | poster 42

Predicting times of waiting on red signals using BERT
Witold Szejgis, Anna Warno, Paweł Gora
paper | video | poster 61

Explainable Autonomous Driving with Grounded Relational Inference
Chen Tang, Nishan Srishankar, Sujitha Martin, Masayoshi Tomizuka
paper | video | poster 27

DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation
Linda Wang, Mahmoud Famouri, Alexander Wong
paper | video | poster 12

Bézier Curve Based End-to-End Trajectory Synthesis for Agile Autonomous Driving
Trent Weiss, Varundev Suresh Babu, Madhur Behl
paper | video | poster 39

Traffic Forecasting using Vehicle-to-Vehicle Communication and Recurrent Neural Networks
Steven Wong, Robin Walters, Lejun Jiang, Tamas Molnar, Rose Yu
paper | video | poster 60

Energy-Based Continuous Inverse Optimal Control
Yifei Xu, Jianwen Xie, Tianyang Zhao, Chris Baker, Yibiao Zhao, Ying Nian Wu
paper | video | poster 2

Modeling Affect-based Intrinsic Rewards for Exploration and Learning
Dean Zadok, Daniel McDuff, Ashish Kapoor
paper | video | poster 64


  • Rowan McAllister

    Rowan McAllister

    is a postdoctoral researcher at UC Berkeley working on probabilistic models and planning for autonomous vehicles.

  • Xinshuo Weng

    Xinshuo Weng

    is a PhD student at Carnegie Mellon University working on 3D Computer Vision and Graph Neural Networks in the context of autonomous driving.

  • Daniel Omeiza

    Daniel Omeiza

    is a PhD student at the University of Oxford working on explainability in autonomous vehicles.

  • Nicholas Rhinehart

    Nicholas Rhinehart

    is a postdoctoral researcher at UC Berkeley, focusing on understanding, forecasting, and control with computer vision and machine learning.

  • Fisher Yu

    Fisher Yu

    has a assistant professorship position in computer vision at ETH Zurich.

  • German Ros

    German Ros

    is a research scientist at Intel Intelligent Systems Lab.

  • Vladlen Koltun

    Vladlen Koltun

    is the Chief Scientist for Intelligent Systems at Intel.

Program Committee

   We thank those who help make this workshop possible!

SlidesLive Staff

A special thanks to SlidesLive technicians Tomáš Drahorád and Marcela too for their help hosting this virtual workshop!