1638782178_maxresdefault.jpg
0
03:08

CoRL 2020, Spotlight Talk 182: Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Intera…

“**Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians** Bruno Ferreira de Brito (Delft University of Technology)*; Hai Zhu (Delft University of Technology); Wei Pan (TUDelft); Javier Alonso-Mora (Delft University of Technology) Publication: http://corlconf.github.io/paper_182/ **Abstract** Prediction of human motions is key for safe navigation of autonomous robots among humans. In cluttered environments, several motion hypotheses may […]
1638760496_maxresdefault.jpg
5
05:00

CoRL 2020, Spotlight Talk 107: Auxiliary Tasks Speed Up Learning PointGoal Navigation

**Auxiliary Tasks Speed Up Learning PointGoal Navigation** Joel Ye (Georgia Institute of Technology)*; Dhruv Batra (Georgia Tech & Facebook AI Research); Erik Wijmans (Georgia Tech); Abhishek Das (Facebook AI Research) Publication: http://corlconf.github.io/paper_107/ **Abstract** PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment. Wijmans et al. […]
1638738827_maxresdefault.jpg
1
05:06

CoRL 2020, Spotlight Talk 417: Few-shot Object Grounding and Mapping for Natural Language Robot I…

“**Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following** Valts Blukis (Cornell University)*; Ross Knepper (Cornell University); Yoav Artzi (Cornell University) Publication: http://corlconf.github.io/paper_417/ **Abstract** We study the problem of learning a robot policy to follow natural language instructions that can be easily extended to reason about new objects. We introduce a few-shot language-conditioned […]
1638717173_maxresdefault.jpg
1
05:05

CoRL 2020, Spotlight Talk 166: Untangling Dense Knots by Learning Task-Relevant Keypoints

“**Untangling Dense Knots by Learning Task-Relevant Keypoints** Jennifer Grannen (UC Berkeley)*; Priya Sundaresan (UC Berkeley)*; Brijen Thananjeyan (UC Berkeley); Jeffrey Ichnowski (University of California, Berkeley); Ashwin Balakrishna (UC Berkeley); Minho Hwang (UC Berkeley); Vainavi Viswanath (UC Berkeley); Michael Laskey (UC Berkeley); Joseph Gonzalez (UC Berkeley); Ken Goldberg (UC Berkeley) Publication: http://corlconf.github.io/paper_166/ **Abstract** Untangling ropes, wires, […]
1638695529_maxresdefault.jpg
2
05:13

CoRL 2020, Spotlight Talk 516: Multi-Level Structure vs. End-to-End-Learning in High-Performance …

“**Multi-Level Structure vs. End-to-End-Learning in High-Performance Tactile Robotic Manipulation** Florian Voigt (Technical University of Munich)*; Lars Johannsmeier (Technical University of Munich); Sami Haddadin (Technical University of Munich) Publication: http://corlconf.github.io/paper_516/ **Abstract** In this paper we apply a multi-level structure to robotic manipulation learning. It consists of a hybrid dynamical system we denote skill and a parameter […]
1638673885_maxresdefault.jpg
0
04:37

CoRL 2020, Spotlight Talk 345: Amodal 3D Reconstruction for Robotic Manipulation via Stability an…

**Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity** William Agnew (University of Washington)*; Christopher Xie (University of Washington); Aaron Walsman (University of Washington); Octavian Murad (University of Washington); Yubo Wang (University of Washington); Pedro Domingos (University of Washington); Siddhartha Srinivasa (University of Washington) Publication: http://corlconf.github.io/paper_345/ **Abstract** Learning-based 3D object reconstruction enables single- or […]
1638652224_maxresdefault.jpg
2
05:24

CoRL 2020, Spotlight Talk 221: Towards General and Autonomous Learning of Core Skills: A Case Stu…

“**Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion** Roland Hafner (Google DeepMind)*; Tim Hertweck (DeepMind); Philipp Kloeppner (TU Darmstadt); Michael Bloesch (Google); Michael Neunert (Google DeepMind); Markus Wulfmeier (DeepMind); Saran Tunyasuvunakool (DeepMind); Nicolas Heess (DeepMind); Martin Riedmiller (DeepMind) Publication: http://corlconf.github.io/paper_221/ **Abstract** Modern Reinforcement Learning (RL) algorithms promise to solve difficult […]
1638630503_maxresdefault.jpg
0
04:50

CoRL 2020, Spotlight Talk 245: Learning to Walk in the Real World with Minimal Human Effort

**Learning to Walk in the Real World with Minimal Human Effort** Sehoon Ha (Georgia Institute of Technology); Peng Xu (Google Inc); Zhenyu Tan (Google); Sergey Levine (UC Berkeley)*; Jie Tan (Google) Publication: http://corlconf.github.io/paper_245/ **Abstract** Reliable and stable locomotion has been one of the most fundamental challenges for legged robots. Deep reinforcement learning (deep RL) has […]
1638608696_maxresdefault.jpg
0
05:03

CoRL 2020, Spotlight Talk 203: Contrastive Variational Reinforcement Learning for Complex Observa…

**Contrastive Variational Reinforcement Learning for Complex Observations** Xiao Ma (National University of Singapore)*; SIWEI CHEN (National University of Singapore); David Hsu (NUS); Wee Sun Lee (National University of Singapore) Publication: http://corlconf.github.io/paper_203/ **Abstract** Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains […]
1638587026_maxresdefault.jpg
2
04:29

CoRL 2020, Spotlight Talk 151: Model-based Reinforcement Learning for Decentralized Multiagent Re…

“**Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous** Rose Wang (MIT)*; J. Chase Kew (Google Brain); Dennis Lee (Google Inc.); Tsang-Wei Lee (Google Brain); Tingnan Zhang (Google); Brian Ichter (Google Brain); Jie Tan (Google); Aleksandra Faust (Google Brain) Publication: http://corlconf.github.io/paper_151/ **Abstract** Collaboration requires agents to align their goals on the fly. Underlying the human ability to […]
1638565353_maxresdefault.jpg
3
05:05

CoRL 2020, Spotlight Talk 147: Interactive Imitation Learning in State-Space

“**Interactive Imitation Learning in State-Space** Snehal Jauhri (TU Delft)*; Carlos Celemin (TU Delft); Jens Kober (TU Delft) Publication: http://corlconf.github.io/paper_147/ **Abstract** Imitation Learning techniques enable programming the behaviour of agents through demonstrations rather than manual engineering. However, they are limited by the quality of available demonstration data. Interactive Imitation Learning techniques can improve the efficacy of […]
1638543632_maxresdefault.jpg
2
04:55

CoRL 2020, Spotlight Talk 101: Modeling Long-horizon Tasks as Sequential Interaction Landscapes

“**Modeling Long-horizon Tasks as Sequential Interaction Landscapes** Soeren Pirk (Google)*; Karol Hausman (Google Brain); Alexander Toshev (Google); Mohi Khansari (X, The Moonshot Factory) Publication: http://corlconf.github.io/paper_101/ **Abstract** Task planning over long-time horizons is a challenging and open problem in robotics and its complexity grows exponentially with an increasing number of subtasks. In this paper we present […]
1638521935_maxresdefault.jpg
2
05:06

CoRL 2020, Spotlight Talk 444: Visual Imitation Made Easy

“**Visual Imitation Made Easy** Sarah Young (UC Berkeley)*; Dhiraj Gandhi (Carnegie Mellon University); Shubham Tulsiani (Facebook AI Research); Abhinav Gupta (CMU/FAIR); Pieter Abbeel (UC Berkeley); Lerrel Pinto (NYU/Berkeley) Publication: http://corlconf.github.io/paper_444/ **Abstract** Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching […]
1638500231_maxresdefault.jpg
8
04:51

CoRL 2020, Spotlight Talk 195: Planning Paths Through Unknown Space by Imagining What Lies Therein

“**Planning Paths Through Unknown Space by Imagining What Lies Therein** Yutao Han (Cornell University)*; Jacopo Banfi (Cornell University); Mark Campbell (Cornell University) Publication: http://corlconf.github.io/paper_195/ **Abstract** This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an […]
1638478453_maxresdefault.jpg
2
05:03

CoRL 2020, Spotlight Talk 426: ACNMP: Skill Transfer and Task Extrapolation through Learning from…

“**ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing** Mete Akbulut (Bogazici University)*; Erhan Oztop (Ozyeğin Üniversitesi); Muhammet Yunus Seker (Bogazici University); Hh X (University); Ahmet Tekden (Boğaziçi Üniversitesi); Emre Ugur (Bogazici University) Publication: http://corlconf.github.io/paper_426/ **Abstract** To equip robots with dexterous skills, an effective approach is to first […]
1638456631_maxresdefault.jpg
2
05:03

CoRL 2020, Spotlight Talk 18: DROGON: A Trajectory Prediction Model based on Intention-Conditione…

“**DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning** Chiho Choi (Honda Research Institute US)*; Srikanth Malla (Honda Research Institute); Abhishek Patil (Hilti Inc); Joon Hee Choi (Sungkyunkwan University) Publication: http://corlconf.github.io/paper_18/ **Abstract** We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in […]
1638434885_maxresdefault.jpg
0
04:54

CoRL 2020, Spotlight Talk 482: Differentiable Logic Layer for Rule Guided Trajectory Prediction

“**Differentiable Logic Layer for Rule Guided Trajectory Prediction** Xiao Li (MIT)*; Guy Rosman (MIT); Igor Gilitschenski (Massachusetts Institute of Technology); Jonathan DeCastro (Toyota Research Institute); Cristian-Ioan Vasile (Lehigh University); Sertac Karaman (Massachusetts Institute of Technology); Daniela Rus (MIT CSAIL) Publication: http://corlconf.github.io/paper_482/ **Abstract** In this work, we propose a method for integration of temporal logic formulas […]
1638413192_maxresdefault.jpg
0
05:06

CoRL 2020, Spotlight Talk 526: Robust Policies via Mid-Level Visual Representations: An Experimen…

**Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation** Bryan Chen (UC Berkeley)*; Alexander Sax (UC Berkeley); Francis Lewis (Stanford); Iro Armeni (Stanford University); Silvio Savarese (Stanford University); Amir Zamir (Swiss Federal Institute of Technology (EPFL)); Jitendra Malik (University of California at Berkeley); Lerrel Pinto (NYU/Berkeley) Publication: http://corlconf.github.io/paper_526/ **Abstract** Vision-based robotics […]
1638391445_maxresdefault.jpg
2
05:11

CoRL 2020, Spotlight Talk 132: The EMPATHIC Framework for Task Learning from Implicit Human Feedback

“**The EMPATHIC Framework for Task Learning from Implicit Human Feedback** Yuchen Cui (University of Texas at Austin)*; Qiping Zhang (The University of Texas at Austin); Brad Knox (Bosch); Alessandro Allievi (Bosch); Peter Stone (University of Texas at Austin and Sony AI); Scott Niekum (UT Austin) Publication: http://corlconf.github.io/paper_132/ **Abstract** Reactions such as gestures, facial expressions, and […]
1638369376_maxresdefault.jpg
0
04:49

CoRL 2020, Spotlight Talk 126: Learning Predictive Representations for Deformable Objects Using C…

“**Learning Predictive Representations for Deformable Objects Using Contrastive Estimation** Wilson Yan (UC Berkeley)*; Ashwin Vangipuram (UC Berkeley); Pieter Abbeel (UC Berkeley); Lerrel Pinto () Publication: http://corlconf.github.io/paper_126/ **Abstract** Using visual model-based learning for deformable object manipulation is challenging due to difficulties in learning plannable visual representations along with complex dynamic models. In this work, we propose […]
1638347666_maxresdefault.jpg
3
05:02

CoRL 2020, Spotlight Talk 17: LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Rad…

“**LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion** Meet Shah (Uber ATG)*; Zhiling Huang (Uber ATG); Ankit Laddha (Uber); Matthew Langford (UberATG); Blake Barber (Uber ATG); sida zhang (Uber); Carlos Vallespi-Gonzalez (Uber); Raquel Urtasun (Uber ATG) Publication: http://corlconf.github.io/paper_17/ **Abstract** In this paper, we present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor […]
1638326033_maxresdefault.jpg
2
04:57

CoRL 2020, Spotlight Talk 420: Deep Latent Competition: Learning to Race Using Visual Control Pol…

“**Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space** Wilko Schwarting (Massachusetts Institute of Technology)*; Tim Seyde (MIT); Igor Gilitschenski (Massachusetts Institute of Technology); Lucas Liebenwein (Massachusetts Institute of Technology); Ryan Sander (Massachusetts Institute of Technology); Sertac Karaman (Massachusetts Institute of Technology); Daniela Rus (Massachusetts Institute of Technology) Publication: http://corlconf.github.io/paper_420/ **Abstract** […]
1638304384_maxresdefault.jpg
5
05:01

CoRL 2020, Spotlight Talk 346: Learning an Expert Skill-Space for Replanning Dynamic Quadruped Lo…

“**Learning an Expert Skill-Space for Replanning Dynamic Quadruped Locomotion over Obstacles** David Surovik (University of Oxford)*; Oliwier Melon (University of Oxford); Mathieu Geisert (University of Oxford); Maurice Fallon (University of Oxford); Ioannis Havoutis (“”Oxford Robotics Institute, Universtity of Oxford””) Publication: http://corlconf.github.io/paper_346/ **Abstract** Function approximators are increasingly being considered as a tool for generating robot motions […]
1638282729_maxresdefault.jpg
0
04:48

CoRL 2020, Spotlight Talk 49: Action-based Representation Learning for Autonomous Driving

“**Action-based Representation Learning for Autonomous Driving** Yi Xiao (CVC & UAB)*; Felipe Codevilla (MILA); Christopher Pal (École Polytechnique de Montréal ); Antonio Lopez (CVC & UAB) Publication: http://corlconf.github.io/paper_49/ **Abstract** Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end […]