Chronorobotics Lab

Artificial Intelligence Centre, ČVUT, Czech Republic
Projects Publications People

Projects

STRoLL BearNav

By Filip Majer, Lucie Halodová, Tomáš Vintr and Tomáš Krajník

Bearnav is a simple teach-and-repeat visual navigation system robust to appearance changes induced by varying illumination and naturally-occurring environment changes. It's core method is computationally efficient, it does not require camera calibration and it can learn and autonomously traverse arbitrarily-shaped paths. During the teaching phase, where the robot is driven by a human operator, the robot stores its velocities and image features visible from its on-board camera. During autonomous navigation, the method does not perform explicit robot localisation in the 2d/3d space but it simply replays the velocities that it learned during a teaching phase, while correcting its heading relatively to the path based on its camera data.

Available Here

Warped Hypertime (WHyTe)

By Tomáš Vintr, Kerem Eyisoy, Vanda Vintrová, Zhi Yan and Tomáš Krajník

We present a method that allows autonomous systems to detect anomalous events in human-populated environments through understating of their structure and how they change over time. We represent the environment by temporary warped space-hypertime continuous models derived from patterns of changes driven by human activities within the observed space. The ability of the method to detect anomalies is evaluated on real-world datasets gathered by robots over the course of several weeks. An earlier version of this approach was already applied to robots that patrolled offices of a global security company (G4S).

Available Here

Publications

Here is a selection of our publications:

Title Authors
Navigation without localisation: reliable teach and repeat based on the convergence theorem T Krajník, F Majer, L Halodová, T Vintr
Adaptive image processing methods for outdoor autonomous vehicles L Halodová, E Dvořáková, F Majer, J Ulrich, T Vintr, K Kusumam, T Krajník
Spatio-temporal representation for long-term anticipation of human presence in service robotics Tomáš Vintr, Zhi Yan, Tom Duckett, Tomáš Krajnık
Warped hypertime representations for long-term autonomy of mobile robots Tomáš Krajník, Tomáš Vintr, Sergi Molina, Jaime Pulido Fentanes, Grzegorz Cielniak, Oscar Martinez Mozos, George Broughton, Tom Duckett
Spatiotemporal models of human activity for robotic patrolling Tomáš Vintr, Kerem Eyisoy, Vanda Vintrová, Zhi Yan, Yassine Ruichek, Tomáš Krajník

People

Tomáš Krajník ~ Supreme Leader
Tomáš Vintr ~ Lab Manager / PhD Student
George Broughton ~ PhD Student
Filip Majer ~ Master's Student
Tomáš Rouček ~ Master's Student
Jiří Ulrich ~ Bachelor's Student
Jan Blaha ~ Bachelor's Student