Learning for Active 3D Mapping

Učící se aktivní 3D mapování.
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

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).

Rescue robot goes to Italy

Robot jede do Italie
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

Nový EU projekt, 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 v DVTV o autech bez řidiče
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!

Non-rigid object detection with local interleaved sequential alignment

Detekce nerigidních objektů
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

Fúze dat pro lokalizaci a mapování
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

Adaptivní traversabilita
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

David Hurych defended his Ph.D. thesis

David Hurych successfully defended his Ph.D. thesis entitled Linear Predictors for Real-time Object Tracking and Detection (supervisor: Doc. Tomáš Svoboda). Congratulations!

Karel Zimmermann defended his Ph.D. thesis

Karel Zimmermann successfully defended his Ph.D. thesis entitled Fast Learnable Methods for Object Tracking (supervisor: Dr. Jiří Matas). Congratulations! Look at demos of the results!
Responsible person: Petr Pošík