CRAS participates on large scale project Research Center Informatics, RCI where it constitutes the Robotic chapter.
CRAS members were quite successful in publishing latest results.
- Miloš Prágr, Petr Čížek, Jan Faigl: Cost of Transport Estimation for Legged Robot Based on Terrain Features Inference from Aerial Scan, IROS 2018.
- Petr Čížek, Jiří Kubík, Jan Faigl: Online Foot-Strike Detection using Inertial Measurements for Multi-Legged Walking Robots, IROS 2018.
- Petr Váňa, Jakub Sláma, Jan Faigl: Any-time Trajectory Planning for Safe Emergency Landing, IROS 2018.
- T. Krajník, F. Majer, L. Halodová, and Tomáš: Navigation without localisation: reliable teach and repeat based on the convergence theorem, in IROS, 2018.
- F.Arvin, A.E.Turgut, T.Krajnı́k, S.Rahimi, I.E.Okay, S.Yue, S.Watson, B.Lennox: ΦClust: Pheromone-based Aggregation for Robotic Swarms, In IROS, 2018.
in IEEE RA-L and to be presented at IROS2018:
- Martin Pecka, Karel Zimmermann, Matěj Petrlík, Tomáš Svoboda. Data-driven Policy Transfer with Imprecise Perception Simulation.
- L Kunze, N Hawes, T Duckett, M Hanheide, T Krajnik: Artificial Intelligence for Long-Term Robot Autonomy: A Survey.
- Lukáš Chrpa, Jose Pinto, Tiago Sa Marques, Manuel A. Ribeiro, Joao Sousa: Mixed-Initiative Planning, Replanning and Execution: From Concept to Field Testing using AUV Fleets
- Jan Faigl, Robert Pěnička: On Close Enough Orienteering Problem with Dubins Vehicle
- Petr Čížek, Diar Masri, Jan Faigl: Foothold Placement Planning with a Hexapod Crawling Robot
- Martin Pecka, Karel Zimmermann, Tomáš Svoboda. Fast Simulation of Vehicles with Non-deformable Tracks. arXiv PDF
We also got an oral presentation at ICCV2017, arguably the most prestigious computer vision conference: K. Zimmermann, T. Petricek, V. Salansky, T. Svoboda. Learning for Active 3D Mapping. arXiv PDF, DemoVideo.
We also have a few new journal publications:
- Tomáš Krajník ; Jaime P. Fentanes ; João M. Santos ; Tom Duckett. FreMEn: Frequency Map Enhancement for Long-Term Mobile Robot Autonomy in Changing Environments. IEEE Transactions on Robotics ( Volume: 33, Issue: 4, Aug. 2017 )
- M. Pecka, K. Zimmermann, M. Reinstein, and T. Svoboda. Controlling Robot Morphology from Incomplete Measurements. In IEEE Transactions on Industrial Electronics, Feb 2017, Vol 64, Issue: 2, pp. 1773-1782
Karel Zimmermann successfully defended his habilitation thesis if front of the scientific council of the Faculty on May 10, and became Associate Professor.
Our team (also Uni Lincoln and UPenn involved) led by Martin Saska won the Mohamed Bin Zayed International Robotic Challenge (MBZIRC) – Challenge 3 that required a team of UAVs to collaborate to search, locate, track, pick and place a set of static and moving objects. The team also took 2nd place in Challenge 1 – landing on a moving platform and 3rd in the Grand Challenge – after joining University of Padua.
CRAS members were very successful in securing new funding from the Czech Science Foundation. The following three-years projects start 01/2017:
- K. Zimmermann. Robust motion planning and control on rough unstructured terrain.
- M. Hoffmann. Robot self-calibration and safe physical human-robot interaction inspired by body representations in primate brains
- M. Saska. Stabilization and control of teams of relatively-localized micro aerial vehicles in high obstacle density areas
- M. Saska. Methods of Identification and Visualization of Tunnels for Flexible Ligands in Dynamic Proteins
- T. Krajník: Spatio-temporal representations for lifelong mobile robot navigation
Scanning of historical buildings with inaccessible areas is difficult task for archaeologists and restorers. Members of CRAS from Multi-robot Systems group (MRS) help with scanning of such inaccessible areas using their own drones.
Nowadays we negotiate with other heritage institutions to scan other historical buildings.
Report about scanning taken by Czech Television (only in czech language).
Team of Czech Technical University in Prague, University of Pennsylvania and University of Lincoln, where members of CRAS play key roles, has been selected for gaining sponsorship for participating in the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) out of 143 applicants from the most prestigious universities in the world. The international team, which is led by Martin Saska, will compete with the worldwide best universities in the field of Micro Aerial Vehicles (MAV) in two Challenges. The first is to autonomously localize a moving vehicle in the arena by a single MAV and then land on a landing platform carried by the vehicle. The second Challenge is to search the arena for various static and moving color objects, then pick them and move them to dedicated area. For more information about our participation in MBZIRC see sites of Multi-Robot Systems group.
CS Seminar series – 14:00, Friday, 12.02.2015, Room KN:E-2015
Tom Krajnik, University of Lincoln, UK
While robotic mapping of static environments has been widely studied, long-term mapping in non-stationary environments is still an open problem. In this talk, we present an approach for long-term representation of populated environments, where many of the observed changes are caused by humans performing their daily activities. We propose to model the environment’s dynamics by its frequency spectrum, as a combination of harmonic functions that correspond to periodic processes influencing the environment.
Such a representation not only allows representation of environment dynamics over arbitrary time-scales with constant memory requirements, but also prediction of future environment states and anomaly detection. The main advantage of the proposed approach is its universality – it can extend most of the environment models used in mobile robotics.
The proposed approach is applied to several environment representations created by a mobile robot autonomously patrolling indoor environments for several months. In particular, we apply the approach to occupancy grids, feature-based representations and topological maps and show that the approach can represent billions of observations with a few spectral components achieving compression rates up to 1:100000, significantly improves localization robustness in dynamic environments, allows for more efficient path planning, speeds-up tasks like object search or activity classification, and allows to perform 4D spatio-temporal exploration.
More details about FreMEn