Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Arunkumar Byravan

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes


Nov 03, 2021
Alex X. Lee, Coline Devin, Yuxiang Zhou, Thomas Lampe, Konstantinos Bousmalis, Jost Tobias Springenberg, Arunkumar Byravan, Abbas Abdolmaleki, Nimrod Gileadi, David Khosid, Claudio Fantacci, Jose Enrique Chen, Akhil Raju, Rae Jeong, Michael Neunert, Antoine Laurens, Stefano Saliceti, Federico Casarini, Martin Riedmiller, Raia Hadsell, Francesco Nori

* CoRL 2021. Video: https://dpmd.ai/robotics-stacking-YT . Blog: https://dpmd.ai/robotics-stacking . Code: https://github.com/deepmind/rgb_stacking 

  Access Paper or Ask Questions

Evaluating model-based planning and planner amortization for continuous control


Oct 07, 2021
Arunkumar Byravan, Leonard Hasenclever, Piotr Trochim, Mehdi Mirza, Alessandro Davide Ialongo, Yuval Tassa, Jost Tobias Springenberg, Abbas Abdolmaleki, Nicolas Heess, Josh Merel, Martin Riedmiller

* 9 pages main text, 30 pages with references and appendix including several ablations and additional experiments. Submitted to ICLR 2022 

  Access Paper or Ask Questions

Learning Dynamics Models for Model Predictive Agents


Sep 29, 2021
Michael Lutter, Leonard Hasenclever, Arunkumar Byravan, Gabriel Dulac-Arnold, Piotr Trochim, Nicolas Heess, Josh Merel, Yuval Tassa


  Access Paper or Ask Questions

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning


Jun 15, 2021
Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva TB, Arunkumar Byravan, Konstantinos Bousmalis, Andras Gyorgy, Csaba Szepesvari, Raia Hadsell, Nicolas Heess, Martin Riedmiller


  Access Paper or Ask Questions

Representation Matters: Improving Perception and Exploration for Robotics


Nov 03, 2020
Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, Tejas Kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin Riedmiller


  Access Paper or Ask Questions

Local Search for Policy Iteration in Continuous Control


Oct 12, 2020
Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz, Josh Merel, Arunkumar Byravan, Abbas Abdolmaleki, Jackie Kay, Jonas Degrave, Julian Schrittwieser, Yuval Tassa, Jonas Buchli, Dan Belov, Martin Riedmiller


  Access Paper or Ask Questions

Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB


Oct 30, 2019
Felix Leeb, Arunkumar Byravan, Dieter Fox

* Accepted to IROS 2019 workshop on The Importance of Uncertainty in Deep Learning for Robotics 

  Access Paper or Ask Questions

Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models


Oct 09, 2019
Arunkumar Byravan, Jost Tobias Springenberg, Abbas Abdolmaleki, Roland Hafner, Michael Neunert, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

* To appear at the 3rd annual Conference on Robot Learning, Osaka, Japan (CoRL 2019). 24 pages including appendix (main paper - 8 pages) 

  Access Paper or Ask Questions

Prospection: Interpretable Plans From Language By Predicting the Future


Mar 20, 2019
Chris Paxton, Yonatan Bisk, Jesse Thomason, Arunkumar Byravan, Dieter Fox

* Accepted to ICRA 2019; extended version with appendix containing additional results 

  Access Paper or Ask Questions

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control


Oct 02, 2017
Arunkumar Byravan, Felix Leeb, Franziska Meier, Dieter Fox

* 8 pages, Initial submission to IEEE International Conference on Robotics and Automation (ICRA) 2018 

  Access Paper or Ask Questions

SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks


Mar 30, 2017
Arunkumar Byravan, Dieter Fox

* 8 pages. To appear at the IEEE International Conference on Robotics and Automation (ICRA), 2017. V2 Update: Final version submitted to ICRA with experiments testing the robustness of the system to noise and preliminary results on real world data 

  Access Paper or Ask Questions