Description:
The topic is dedicated to autonomous data collection tasks motivated by environmental monitoring missions, such as seismic activity modeling or studying ocean or forest phenomena, to build spatio-temporal models of the studied phenomena. The data collection is considered as the autonomous robotic system (robotic vehicle or sensory network) and the problem is to determine the most suitable sensing locations and a cost efficient path for a mobile robot to periodically visit the locations to create a sufficiently precise model of the observed phenomena. http://comrob.fel.cvut.cz/jf

Description:
The topic is focused on computational intelligence approaches such as neural network, evolutionary and swarm methods in multi-robot exploration, inspection, surveillance and reconnaissance missions. The main challenges are related to cooperation and coordination of robots in distributed environment and decentralized decision-making. http://comrob.fel.cvut.cz/jf

Description:
The topic is to study learning-based methods in solving combinatoric optimization problems, specifically focusing on routing problems motivated by robotics applications such as pick-up and delivery scenarios in intra-factory logistics. The addressed problems are motivated, but not limited to, by a generalization of routing problems to dynamic problems, where instances might change based on online demands. Therefore, new solutions need to be found quickly. Besides, the topic targets increasing the scalability of existing methods, such as combinatoric meta-heuristics, to large problem instances where initial solutions must be found quickly and later improved if a computational time is available.

Description:
The topic is focused on learning dynamics of robotic systems towards model-based feedback control. In particular, the main challenges are related to developing learning techniques to locomote by robot shape changes and interactions with the environments, such as crawling or soft-bodies robots.

Description:
The topic is targeted to robotic planning in the combined motion and task planning. The main challenges are related to the simultaneous solution of the motion planning problems together with efficient task allocation in complex robotic systems such as robotic exploration of unknown rough environment by hexapod walking robots. http://comrob.fel.cvut.cz/jf

Description:
The topic is devoted to study self-organizing principles of Computational Intelligence (e.g., neural network, evolutionary methods, swa rms, and reaction-diffusion systems) in complex computational problems of autonomous systems such as robotic motion planning and task allocation problems. http://comrob.fel.cvut.cz/jf

Description:
The topic is focused on a generalization of trajectory planning considering the possibility of various types of vehicle failure. The addressed problems are motivated, but not limited to, by trajectory planning for aerial vehicles with non-holonomic constraints. The problem being addressed includes challenges related to decision-making and safety adjustment under uncertainty in dynamic environments.

Description:
The topic combines challenges of combinatorial optimization with robotic motion planning in instances motivated by robotic data collection and task planning that requires a solution of multivariable continuous optimization and the solution of the routing problems. The focus of the topic is on a generalization of the existing problem formulations towards solution stability analysis, dynamic and multi-vehicle problems

Description:
In this topic, the main challenges are related to process sensor information to create a model of the operational environment of autonomous agents in autonomous navigation missions. The main goal is to develop methods for improving reliability of the autonomous navigation based on reasoning about the environment model, considering landmarks of the environment utilized for localization and their impact to the precision of the localization in long-term autonomous missions. http://comrob.fel.cvut.cz/jf

Description:
The topic is focused on studying motion planning methods for complex robotics systems with many controllable degrees of freedom, such as multi-legged walking robots in scenarios where it is necessary to plan a sequence of motion steps to reach the goal. The main challenge of the problem is related to sequencing planning, where and in what order to place legs to particular footholds, with motion planning to satisfy complex constraints of robot stability with respect to the required ground reaction forces.

prof. Ing. Jan Faigl, Ph.D.

head_person_supervisor