Robin Strudel

I am a fourth year PhD student at INRIA and DI ENS, in the Willow team, where I work on computer vision and robotics with Ivan Laptev and Cordelia Schmid. I am currently interning at DeepMind and I will be graduating in Fall 2022.

Before my PhD, I graduated from ENS Paris-Saclay with a Masters degree in mathematics, machine learning and computer vision (MVA) and from ENS Lyon with a Masters degree in probability. I was a visiting student researcher in the UC Berkeley Department of Statistics for a year under the supervision of Steven N. Evans and an intern in the Oxford Department of Statistics with Julien Berestycki.

Email / CV / Google Scholar / Github

Research

I am interested in computer vision, machine learning and robotics. I have been working on scene understanding and learning to perform visually guided manipulation tasks with a robot. My research relates to image segmentation, imitation learning, reinforcement learning and sim-to-real transfer.

Segmentation
	Weakly-supervised segmentation of referring expressions Robin Strudel, Ivan Laptev, Cordelia Schmid arXiV, 2022 arXiv / bibtex Learning segmentation from referring expressions, without pixel-level supervision.
	Segmenter: Transformer for Semantic Segmentation Robin Strudel, Ricardo Garcia, Ivan Laptev, Cordelia Schmid ICCV, 2021 arXiv / code / bibtex Semantic segmentation as a sequence-to-sequence mapping with Vision Transformers.
Robotics
	Assembly Planning from Observations under Physical Constraints Thomas Chabal, Robin Strudel, Etienne Arlaud, Jean Ponce, Cordelia Schmid arXiv, 2022 arXiv / bibtex Assembling structures from a single photograph.
	Learning Obstacle Representations for Neural Motion Planning Robin Strudel, Ricardo Garcia, Justin Carpentier, Jean-Paul Laumond, Ivan Laptev, Cordelia Schmid CoRL, 2020 arXiv / project / code / bibtex Visually guided motion planning in unstructured and dynamically changing environments.
	Learning to combine primitive skills: A step towards versatile robotic manipulation Robin Strudel, Alexander Pashevich, Igor Kalevatykh, Ivan Laptev, Josef Sivic, Cordelia Schmid ICRA, 2020 arXiv / project / code / bibtex Learning to perform manipulation tasks with a hierarchical approach. A vocabulary of simple skills is learned from demonstrations then combined with a planning policy to perform more complex tasks.
	Learning to Augment Synthetic Images for Sim2Real Policy Transfer Alexander Pashevich, Robin Strudel*, Igor Kalevatykh, Ivan Laptev, Cordelia Schmid IROS*, 2019 arXiv / project / code / bibtex Learning sim-to-real data augmentation automatically with MCTS and then transferring policies learned in simulation to a real robot.

Design and source code from Jon Barron's website.