Tuesday, November 14 Schedule

0900 - 1000
Keynote
Yan LeCun, Facebook & NYU
1000 - 1020
image2mass: Estimating the Mass of an Object from Its Image
Trevor Standley, Stanford University; Ozan Sener, Stanford University; Dawn Chen, Google; Silvio Savarese, Stanford University
1040 - 1100
Principal Variety Analysis
Reza Iraji, Colorado State University; Hamidreza Chitsaz, Colorado State University
1100 - 1130
Coffee Break
1130 - 1136
CARLA: An Open Urban Driving Simulator
Alexey Dosovitskiy, Intel Labs; German Ros, Toyota Research Institute; Felipe Codevilla, Computer Vision Center Barcelona; Antonio Lopez, Computer Vision Center Barcelona; Vladlen Koltun, Intel Labs
1136 - 1142
Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control
Paul Drews, Georgia Tech; Grady Williams, Georgia Tech; Brian Goldfain, Georgia Tech; Evangelos A. Theodorou, Georgia Tech; James M. Rehg, Georgia Tech
1142 - 1148
Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation
Wei Gao, National University of Singapore; David Hsu, National University of Singapore; Wee Sun Lee, National University of Singapore; Shengmei Shen, Panasonic R&D Center Singapore; Karthikk Subramanian, Panasonic R&D Center Singapore
1148 - 1154
Gradient-free Policy Architecture Search and Adaptation
Sayna Ebrahimi, UC Berkeley; Anna Rohrbach, Max Plank Institute for Informatics; Trevor Darrell, UC Berkeley
1154 - 1200
Long-Term On-Board Prediction of Pedestrians in Traffic Scenes
Apratim Bhattacharyya, Max Planck Institute for Informatics Saarland Informatics Campus; Mario Fritz, Max Planck Institute for Informatics Saarland Informatics Campus; Bernt Schiele, Max Planck Institute for Informatics Saarland Informatics Campus
1200 - 1206
Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks
Zackory Erickson, Georgia Institute of Technology; Sonia Chernova, Georgia Institute of Technology; Charles C. Kemp, Georgia Institute of Technology
1206 - 1212 
CORe50: a New Dataset and Benchmark for Continuous Object Recognition
Vincenzo Lomonaco, University of Bologna; Davide Maltoni, University of Bologna
1212 - 1218
How Robots Learn to Classify New Objects Trained from Small Data Sets
Tick Son Wang, German Aerospace Center (DLR); Zoltan-Csaba Marton, DLR; Manuel Brucker, DLR; Rudolph Triebel, DLR and TUM
1218 - 1224
Learning to Fly by Crashing
Dhiraj Gandhi, CMU; Lerrel Pinto, CMU; Abhinav Gupta, CMU
1224 - 1230
Towards Grasp Transfer Using Shape Deformation
Andrey Kurenkov, Stanford University; Viraj Mehta, Stanford University; Jingwei Ji, Stanford University; Animesh Garg, Stanford University; Silvio Savarese, Stanford University
1230 - 1330
Lunch
1330 - 1430
Keynote
Drew Bagnell, Carnegie Mellon University
1430 - 1450
Sim-to-Real Robot Learning from Pixels with Progressive Nets
Andrei A. Rusu, DeepMind; Matej Večerík, DeepMind; Thomas Rothörl, DeepMind; Nicolas Heess, DeepMind; Razvan Pascanu, DeepMind; Raia Hadsell, DeepMind
1450 - 1510
Learning Heuristic Search via Imitation
Mohak Bhardwaj, Carnegie Mellon University; Sanjiban Choudhury, Carnegie Mellon University; Sebastian Scherer, Carnegie Mellon University
1510 - 1530
Mutual Alignment Transfer Learning
Markus Wulfmeier, University of Oxford; Ingmar Posner, University of Oxford; Pieter Abbeel, UC Berkeley
1530 - 1600
Coffee Break
1600 - 1606
Uncertainty-driven Imagination for Continuous Deep Reinforcement Learning
Gabriel Kalweit, University of Freiburg; Joschka Boedecker, University of Freiburg
1606 - 1612
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
Serkan Cabi, DeepMind; Sergio Gomez Colmenarejo, DeepMind; Matthew W. Hoffman, DeepMind; Misha Denil, DeepMind; Ziyu Wang, DeepMind; Nando de Freitas, DeepMind
1612 - 1618
Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation
Guan-Horng Liu, Carnegie Mellon University; Avinash Siravuru, Carnegie Mellon University; Sai Prabhakar, Carnegie Mellon University; Manuela Veloso, Carnegie Mellon University; George Kantor,Carnegie Mellon University
1618 - 1624
Reverse Curriculum Generation for Reinforcement Learning
Carlos Florensa, UC Berkeley; David Held, UC Berkeley; Markus Wulfmeier, Oxford; Michael Zhang, UC Berkeley; Pieter Abbeel, OpenAI
1624 - 1630
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Ofir Nachum, Google Brain; Mohammad Norouzi, Google Brain; Kelvin Xu, Google Brain; Dale Schuurmans, Google Brain
1630 - 1636
IntentionGAN: Multi-Task Imitation Learning from Unstructured Demonstrations
Karol Hausman, USC; Yevgen Chebotar, USC; Stefan Schaal, USC; Gaurav Sukhatme, USC; Joseph Lim, USC
1636 - 1642
Manifold Regularization for Kernelized LSTD
Xinyan Yan, Google Brain Robotics; Krzysztof Choromanski, Google Brain Robotics; Byron Boots, Google Brain Robotics; Vikas Sindhwani, Google Brain Robotics
1648 - 1654
Predictive State Recurrent Neural Networks
Carlton Downey, Carnegie Mellon University; Ahmed Hefny, Carnegie Mellon University; Byron Boots, Georgia Tech; Geoffrey Gordon, Carnegie Mellon University
1654 - 1700
Predictive State Models for Prediction and Control in Partially Observable Environments
Ahmed Hefny, CMU; Zita Marinho, CMU; Carlton Downey, CMU; Wen Sun, CMU; Siddhartha Srinivasa, CMU; Geoffrey Gordon, CMU
1700 - 1800
Poster Session
1800 - 2000
Reception at the Computer History Museum