Inventing AI for the future
ELLIS Unit Prague is based at the Czech Institute of Informatics, Robotics and Cybernetics of the Czech Technical University. The unit brings together several lead scientists and their teams with the shared objective to address key scientific challenges in artificial intelligence and to generate innovations with a positive impact on the economy and society.
Explore our research areas and scientific collaborations with industry.
IEEE Robotics and Automation Letters (2021)
Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning
Jonas Kulhanek, Erik Derner, Robert Babuska
Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing, localization, and planning in one module, which can be trained and therefore optimized for a given environment.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)
NCNet: Neighbourhood Consensus Networks for Estimating Image Correspondences
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelovic, Akihiko Torii, Tomas Pajdla, Josef Sivic
We address the problem of finding reliable dense correspondences between a pair of images. This is a challenging task due to strong appearance differences between the corresponding scene elements and ambiguities generated by repetitive patterns. The contributions of this work are threefold. First, inspired by the classic idea of disambiguating feature matches using semi-local …
IEEE Conference on Computer Vision and Pattern Recognition (2021)
How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines
Kunal Chelani, Fredrik Kahl, Torsten Sattler
Visual localization is the problem of estimating the cam-era pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in advanced computer vision applications, including Mixed and Virtual Reality systems. Many algorithms used in practice represent the scene through a Structure-from-Motion (SfM) point cloud and use 2D-3D matches between a query image and the 3D points for camera pose estimation.
Proceedings of the 9th ACM SIGPLAN International Conference on Certified Programs and Proofs (2020)
Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
Qingxiang Wang, Chad Brown, Cezary Kaliszyk, Josef Urban
In this paper we share several experiments trying to automatically translate informal mathematics into formal mathematics. In our context informal mathematics refers to human-written mathematical sentences in the LaTeX format; and formal mathematics refers to statements in the Mizar language.
Robotics and Autonomous Systems (2021)
Change detection using weighted features for image-based localization
Erik Dernera, Clara Gomez, Alejandra C. Hernandez, Ramon Barber, Robert Babuska
Autonomous mobile robots are becoming increasingly important in many industrial and domestic environments. Dealing with unforeseen situations is a difficult problem that must be tackled to achieve long-term robot autonomy. Invision based localization and navigation methods, one of the major issues is the scene dynamics.
Conference on Robot Learning (2020)
Learning Object Manipulation Skills via Approximate State Estimation from Real Videos
Vladimir Petrik, Makarand Tapaswi, Ivan Laptev, Josef Sivic
Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain.In this paper, we explore a method that facilitates learning object manipulation skills directly from videos.
Artificial Life Conference Proceedings (2020)
Visualizing computation in large-scale cellular automata
Hugo Cisneros, Josef Sivic, Tomas Mikolov
Emergent processes in complex systems such as cellular automata can perform computations of increasing complexity, and could possibly lead to artificial evolution. Such a feat would require scaling up current simulation sizes to allow for enough computational capacity. Understanding complex computations happening in cellular automata and other systems capable of emergence poses many challenges, especially in large-scale systems.
International Conference on Computer Vision (2019)
PLMP – Point-Line Minimal Problems in Complete Multi-View Visibility
Timothy Duff, Kathlen Kohn, Anton Leykin, Tomas Pajdla
We present a complete classification of all minimal problems for generic arrangements of points and lines completely observed by calibrated perspective cameras. We show that there are only 30 minimal problems in total, no problems exist for more than 6 cameras, for more than 5points, and for more than 6 lines. We present a sequence of tests for detecting minimality starting with counting degrees of freedom and ending with full symbolic and numeric verification of representative examples