Vision for Robotics and Autonomous Systems (VRAS)
InfoPeopleProjectsNewsDemosStudent topicsTheses
We are interested in machine learning for robot perception. We research algorithms that map RGB, depth, Lidar, and thermal data onto robot behavior. We work with outdoor tracked robots, humanoid robots and also collaborate with automotive – autonomous cars.
We are always looking for strongly motivated Ph.D. students as well as undergraduate students. If you are interested in what we are doing and want to join us, send us your resume to Tomas Svoboda. Currently, we also do have an opening for a pos-doc position.
The group is also a part of Center for Machine Perception, CMP, and involved in Center for robotics and autonomous systems, CRAS. Humanoid and cognitive robotics group also belongs to us.
Group members:
| Name | Team | Rank | Phone | Office | position | ||
|---|---|---|---|---|---|---|---|
| Ing. | Azayev Teymur | VRAS | Researcher and Internal PhD | +420 22435 5757 | E227 |  |
09 |
| Ing. | Cvrček Vojtěch | VRAS | Internal PhD student | +420 22435 5749 | G103 | |
14 |
| Gama Filipe | VRAS | Researcher and Internal PhD | +420 22435 7609 | E209 | |
09 | |
| Ing. | Himmel Bedřich | VRAS | Researcher | +420 22435 7391
+420 602252337 |
E225B | |
08 |
| Bc. | Hoffmann Martin | VRAS | External | |
20 | ||
| Mgr. | Hoffmann Matěj Ph.D. | VRAS | Assistant professor | +420 22435 7387 | E211 | |
07 |
| Lehmann Hagen Ph.D. | VRAS | External | |
20 | |||
| Mgr. | Moravec Jaroslav | VRAS | Internal PhD student | G103 | |
14 | |
| Bc. | Patni Shubhan Parag | VRAS | Research Fellow | +420 22435 7583 | E209 | |
11 |
| Mgr. | Pecka Martin | VRAS | Researcher and External PhD | +420 22435 7269 | E225B | |
10 |
| Ing. | Petříček Tomáš Ph.D. | VRAS | Researcher | +420 22435 7391 | E225B | |
08 |
| Ing. | Reinštein Michal Ph.D. | VRAS | Assistant professor | +420 22435 7269 | E225B | |
07 |
| Ing. | Straka Zdeněk | VRAS | Researcher and Internal PhD | +420 22435 7583 | E209 | |
09 |
| Doc. Ing. | Svoboda Tomáš Ph.D. | VRAS | Associate professor | +420 22435 7448 | E226 | |
06 |
| Ing. | Šalanský Vojtěch | VRAS | Researcher and Internal PhD | +420 22435 5700 | E227 | |
09 |
| Doc. Ing. | Šára Radim Dr. Tech. | VRAS | Associate professor | +420 22435 7203 | G103A | |
06 |
| Ing. Mgr. | Švarný Petr | VRAS | Researcher and Internal PhD | +420 22435 7583 | E209 | |
09 |
| Ing. | Vacek Patrik | VRAS | Researcher and Internal PhD | +420 22435 5700 | E227 | |
09 |
| Doc. Ing. | Zimmermann Karel Ph.D. | VRAS | Associate professor | +420 22435 5733 | E226 | |
06 |
- Whole-body awareness for safe and natural interaction: from brains to collaborative robots. “GAČR EXPRO” project for excellence in fundamental research from the Czech Science Foundation (2020-2024)
- We lead the CTU-CRAS team into the DARPA SubTerranean Challenge (2019-2021).
- Enable-S3 H2020 EU large integrated project, we are working in automotive field. (2016-2019)
- Robot self-calibration and safe physical human-robot interaction inspired by body representations in primate brains Czech Science Foundation. (2017-2019)
(Česky) Členové týmů MRS a VRAS naší katedry připravili spolu s CIIRC ČVUT pipetovací roboty pro testování vzorků na Covid-19
Sorry, this entry is only available in Česky.
(Česky) Matěj Hoffmann a Petr Švarný v podcastu Vše o průmyslu
Sorry, this entry is only available in Česky.
(Česky) Tým CTU-CRAS získal ceny v soutěži AI Awards za úspěch v mezinárodní robotické soutěži
Sorry, this entry is only available in Česky.
Our Roboticists won at the DARPA Subterranean Challenge Urban Circuit among self-funded teams and scored 3rd overall
In the second half of February 2020, ten robotic teams gathered at the nearly-built but unfinished nuclear power plant near Elma, Washington. The robots were sent into the underground maze of the huge concrete-steel in a quest to find and locate predetermined 20 artifacts. Researchers, graduate and undergraduate students of Departments of Cybernetics and Computer …read more
(Česky) DARPA 2020
Sorry, this entry is only available in Česky.
Interview with Matej Hoffmann in Control Engineering Czech Republic
Sorry, this entry is only available in Česky.
Call for Humanoids group PostDoc position
The group of Humanoid and Cognitive Robotics coordinated by Dr Matej Hoffmann opens a PostDoc position in the humanoid, cognitive, neuro-, and collaborative robotics research. The topics are in the context of the newly starting 5-year project entitled “Whole-body awareness for safe and natural interaction: from brains to collaborative robots” for excellence in fundamental research …read more
Call for Humanoids group PhD position
The group of Humanoid and Cognitive Robotics coordinated by Dr Matej Hoffmann opens a PhD position in the humanoid, cognitive, neuro-, and collaborative robotics research. The topics are in the context of the newly starting 5-year project entitled “Whole-body awareness for safe and natural interaction: from brains to collaborative robots” for excellence in fundamental research …read more
Call for Valeo.AI-sponsored PhD student/researcher
We open a PhD position in the university environment while being partially supervised by the top-tier researcher from Valeo.AI research group. Show your research to be meaningful by running your codes on the real self-driving car to improve human safety. The position is sponsored by Valeo.AI. WE SEEK CANDIDATES: who are excellent, self-motivated, and willing …read more
Call for Vision for Robotics and Autonomous Systems group´s Positions
Vision for Robotics and Autonomous Systems group (https://cyber.felk.cvut.cz/vras/) seeks one excellent PhD student and one PostDoc on the following fully-funded positions: DARPA Subterranenan Challenge: Cutting-edge research in the autonomous mapping (SLAM) for mobile robotics. We are expanding the team that just won the DARPA SubT challenge to help us to help us to win again! …read more
NEW GACR EXPRO Project
Matej Hoffmann has been awarded the “GAČR EXPRO” project for excellence in fundamental research from the Czech Science Foundation (https://gacr.cz/grantove-projekty-excelence-v-zakladnim-vyzkumu-expro/) for his proposal entitled “Whole-body awareness for safe and natural interaction: from brains to collaborative robots”. The grant will support him and his group for 5 years (2020-2024). As robots are leaving safety fences and …read more
Success of CTU-CRAS’ robots in US in Main evening news, Czech TV
It doesn’t happen every day that you appear in the main evening broadcasting at Czech TV (Česká televize). It does for example when you win DARPA SubT Challenge among self-funded teams. Amazing success of ČVUT FEL team CTU-CRAS formed by our teams Multi-robot Systems (Martin Saska) and Vision for Robotics and Autonomous Systems (Tomáš Svoboda) and colleagues …read more
Karel Zimmermann received Dean’s Award for Teaching
Doc. Ing. Karel Zimmermann, Ph.D., received the Dean’s Award for teaching in the academic year 2018/19 for the course Robotics Vision. Teachers are awarded for teaching results based on the recommendation of the Dean’s Committee. The committee decision is based on the results of the students´ verbal survey, suggestions of the heads of departments, and …read more
CTU-CRAS from the Department of Cybernetics Won the Darpa Subterranean Challenge Tunnel Circuit Among Non-Sponsored Teams and Took the Overall 3rd Place
The DARPA Subterranean Challenge Tunnel Circuit took place in Pittsburgh, USA on 15-22 August. A team of CTU-CRAS scientists and students from the Department of Cybernetics and Computer Department of the Faculty of Electrical Engineering of the Czech Technical University in Prague demonstrated a multirobotic system for searching the areas affected by the disaster. CTU-CRAS …read more
Tracked vehicle simulation model for Gazebo
The VRAS group has successfully helped the global open-source robotics community by implementing the first plausible simulation model of tracked vehicles. The model has just been made available to everyone as part of the Gazebo simulator Among others, it will help the CRAS-CTU team in the global DARPA SubT challenge where a team of robots …read more
Dean’s Award for the Dissertation thesis was given to Ing. Vladimir Kubelka, Ph.D.
Dean’s Award for the Dissertation thesis was given to
Ing. Vladimír Kubelka defended his Ph.D. thesis
Ing. Vladimír Kubelka successfully defended his Ph.D. thesis entitled Improving perception and locomotion capabilities of mobile robots in urban search and rescue missions (supervisor: doc. Ing. Tomáš Svoboda, Ph.D., supervisor specialist: Ing. Michal Reinštein, Ph.D.). Congratulations!
Interactive Perception-Action-Learning for Modelling Objects
We are partners in a new European research project (CHIST-ERA call) IPALM – Interactive Perception-Action-Learning for Modelling Objects coordinated by Imperial College London. Matej Hoffmann is the PI for our part. The objective of the project is to develop methods for the automatic digitization of objects and their physical properties by exploratory manipulations. The methods …read more
BODIS – workshop at IROS2018
Matěj Hoffmann is co-organizing a workshop at IEEE/RSJ International Conference on Intelligent Robots and Systems IROS2018. BODIS: The utility of body, interaction and self learning in robotics.
Human-robot interaction at HRI 2018
Work in collaboration with IIT Genoa and Yale University on Compact real-time avoidance on a humanoid robot for human-robot interaction appeared at the HRI 2018 Conference held in Chicago. [pdf @ arxiv | youtube video]
The little android with a sense of touch
A typical feature of mammals lies in their ability to experience sensations, something that robots are beginning to imitate. With the help of artificial skins and algorithms, our researchers have managed to make a small humanoid robot aware of human contact and even notice if someone is invading his ‘living’ space. The little android with …read more
Ing. Tomáš Petříček defended his Ph.D. thesis
Ing. Tomáš Petříček successfully defended his Ph.D. thesis entitled Coupled Learning and Planning for Active 3D Mapping (supervisor: doc. Ing. Tomáš Svoboda, Ph.D.). Congratulations!
Kuka Innovation Award 2018
Matěj Hoffmann from the group Vision for Robotics Autonomous Systems (VRAS) was a member of the team who won the Kuka Innovation Award 2018, see the video.
The project RobotBodySchema has become a Partnering project of the Human Brain Project
The project RobotBodySchema (or “Robot self-calibration and safe physical human-robot interaction inspired by body representations in primate brains”), investigated by the team of Mgr. Matej Hoffmann, Ph.D., became a Partnering project of the Human Brain Project. Congratulations!
ICCV 2017 talk of Karel Zimmermann
Karel Zimmermann presents at ICCV 2017 paper K. Zimmermann, T. Petricek, V. Salansky, T. Svoboda. Learning for Active 3D Mapping.
Ing. Kubelka presented a rescue mobile robot Charlie in Czech TV
Ing. Vladimir Kubelka, a PhD. student of Artificial inteligence and biocybernetics, presented a rescue mobile robot Charlie, which is involved in project TRADR, and invited the viewers to the “Night of scientists“(in czech only) in Studio 6, a Czech TV morning show. Many thanks for the representation of our faculty!
ENNS Best Paper Award
Zdenek Straka and Matej Hoffmann were awarded ENNS Best Paper Award at 26th International Conference on Artificial Neural Networks (ICANN17) for their paper Learning a Peripersonal Space Representation as a Visual-Tactile Prediction Task.
Karel Zimmermann has successfully defended his habilitation thesis
Karel Zimmermann has successfully defended his habilitation thesis Safe Adaptive Traversability with Incomplete Data. Congratulation!
Tomáš Svoboda guest on CT24 on the topic: USA: Shared Autonomous Transport in 13 Years?
Assoc. Prof. Tomáš Svoboda (Vision for Robotics and Autonomous Systems) was a guest on CT24 speaking on the topic: USA: Shared Autonomous Transport in 13 Years? (the interview in Czech language only starts at about 0:15:56).
Humanoid robots learn to sense their body
A 4-page cover story about humanoid robotics in Respekt (a major Czech weekly journal), 16/2017. Matej Hoffmann and Zdenek Straka interviewed and photographed with robots. More robots mentioned in the electronic version of the story. The printed version also available at ihned.cz.
Rescue robot goes to Italy
A rescue ground robot is going to Italy after earthquake. Real deployment event featured in Czech TV main news. Department is collaborating with CIIRC within TRADR project.
New EU project, Enable-S3
Enable-S3 is a large ECSEL-JU project called European Initiative to Enable Validation for Highly Automated Safe and Secure Systems. Tomas Svoboda is the PI of the CTU part. We will closely collaborate with ValeoCZ working on boosting rare data into the learning and testing in automatic driving.
Tomáš Svoboda in DVTV about Autonomous Vehicles
Tomáš Svoboda discussed on DVTV with Martin Veselovský the future of transportation systems and autonomous vehicles (in Czech). Many thanks for successful representation of our department!
Learning for Active 3D Mapping
Paper of authors K. Zimmermann, T. Petricek, V. Salansky, and T. Svoboda was accepted as oral presentation at ICCV 2017! We propose an active 3D mapping method for depth sensors, which allow individual control of depth-measuring rays, such as the newly emerging solid-state lidars. The method simultaneously (i) learns to reconstruct a dense 3D occupancy …read more
Non-rigid object detection with local interleaved sequential alignment
The successively evaluated features used in a sliding window detection process to decide about object presence/absence also contain knowledge about object deformation. We exploit these detection features to estimate the object deformation. Estimated deformation is then immediately applied to not yet evaluated features to align them with the observed image data. In our approach, the …read more
Data fusion for localization and mapping
We design and evaluate a data fusion system for localization of a mobile skid-steer robot intended for USAR missions. We exploit a rich sensor suite including both proprioceptive (inertial measurement unit and tracks odometry) and exteroceptive sensors (omnidirectional camera and rotating laser rangefinder). To cope with the specificities of each sensing modality (such as significantly …read more
Adaptive traversability
Adaptive traversability we understand by means of autonomous motion control adapting the robot morphology—configuration of articulated parts and their compliance—to traverse unknown complex terrain with obstacles in an optimal way. The robot measures its state (like: orientation angles, flipper mode, …) and the terrain (digital elevation model). We learn the optimal policy from loosely annotated …read more