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 Florian Shkurti

gradSim: Differentiable simulation for system identification and visuomotor control

Apr 06, 2021
Krishna Murthy Jatavallabhula, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine, Jerome Parent-Levesque, Kevin Xie, Kenny Erleben, Liam Paull, Florian Shkurti, Derek Nowrouzezahrai, Sanja Fidler

* ICLR 2021. Project page (and a dynamic web version of the article): 

  Access Paper or Ask Questions

LOHO: Latent Optimization of Hairstyles via Orthogonalization

Mar 10, 2021
Rohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi

* CVPR 2021 

  Access Paper or Ask Questions

Skill Transfer via Partially Amortized Hierarchical Planning

Nov 27, 2020
Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti

* First two authors contributed equally. Preprint. NeurIPS 2020 Deep RL Workshop and under review 

  Access Paper or Ask Questions

Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models

Nov 02, 2020
Yuchen Wu, Melissa Mozifian, Florian Shkurti

* submitted to ICRA 2021 

  Access Paper or Ask Questions

Conservative Safety Critics for Exploration

Oct 27, 2020
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg

* Preprint. Under review 

  Access Paper or Ask Questions

Continual Model-Based Reinforcement Learning with Hypernetworks

Sep 25, 2020
Yizhou Huang, Kevin Xie, Homanga Bharadhwaj, Florian Shkurti

* 13 pages, 6 figures. Preliminary report, under review 

  Access Paper or Ask Questions

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Jun 29, 2020
Travis Manderson, Juan Camilo Gamboa Higuera, Stefan Wapnick, Jean-François Tremblay, Florian Shkurti, David Meger, Gregory Dudek

* RSS 2020. Video and project details can be found at 

  Access Paper or Ask Questions

LEAF: Latent Exploration Along the Frontier

Jun 18, 2020
Homanga Bharadhwaj, Animesh Garg, Florian Shkurti

* Preprint. Preliminary report 

  Access Paper or Ask Questions

Dynamics-Aware Latent Space Reachability for Exploration in Temporally-Extended Tasks

May 21, 2020
Homanga Bharadhwaj, Animesh Garg, Florian Shkurti

* Preprint. Preliminary report 

  Access Paper or Ask Questions

Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization

Apr 19, 2020
Homanga Bharadhwaj, Kevin Xie, Florian Shkurti

* L4DC 2020; Accepted for presentation in the 2nd Annual Conference on Learning for Dynamics and Control 

  Access Paper or Ask Questions

One-Shot Informed Robotic Visual Search in the Wild

Mar 22, 2020
Karim Koreitem, Florian Shkurti, Travis Manderson, Wei-Di Chang, Juan Camilo Gamboa Higuera, Gregory Dudek

  Access Paper or Ask Questions

Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning

Mar 17, 2020
Ke Dong, Karime Pereida, Florian Shkurti, Angela P. Schoellig

* Paper manuscript submitted to IROS 2020 

  Access Paper or Ask Questions

DIBS: Diversity inducing Information Bottleneck in Model Ensembles

Mar 10, 2020
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti

* Samarth Sinha* and Homanga Bharadhwaj* contributed equally to this work. Code will be released at 

  Access Paper or Ask Questions

Underwater Multi-Robot Convoying using Visual Tracking by Detection

Sep 25, 2017
Florian Shkurti, Wei-Di Chang, Peter Henderson, Md Jahidul Islam, Juan Camilo Gamboa Higuera, Jimmy Li, Travis Manderson, Anqi Xu, Gregory Dudek, Junaed Sattar

* Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017 

  Access Paper or Ask Questions

Benchmark Environments for Multitask Learning in Continuous Domains

Aug 14, 2017
Peter Henderson, Wei-Di Chang, Florian Shkurti, Johanna Hansen, David Meger, Gregory Dudek

* Accepted at Lifelong Learning: A Reinforcement Learning Approach Workshop @ ICML, Sydney, Australia, 2017 

  Access Paper or Ask Questions