My research interests are:
- artificial intelligence;
- intelligent control systems;
- intelligent dynamic systems;
- intelligent robotics;
- AI planning;
- path planning, path finding;
- heuristic search;
- multi-agent systems;
- cognitive agents.
I’m passionate and enthusiastic about developing methods and algorithms for controlling intelligent agents (mobile robots, driverless cars, drones, computer game characters etc.) in such a way that these agents are:
- autonomous, i.e. can behave appropriately in complex, dynamic environments without being fully controlled by an operator (human);
- adaptive, i.e. can perform well in unpredictable conditions;
- collaborative, i.e. can interact with each other and humans to safely and effectively accomplish their missions.
Creating intelligent control systems for such agents is a challenging problem. To solve it one needs to use the variety of methods from Artificial Intelligence (incl. machine learning), control theory , computer cognitive modelling etc.
Currently I’m involved in research and development of methods and algorithms tailored to solve such navigation tasks as localization, mapping, path (motion) planning.
The videos provide an insight of what we are doing in the lab.
Methods, algorithms, models
Below one might find an enumeration of a few algorithms, methods and models that were developed with my active involvement. More details on them can be obtained from the publications.
- Methods and algorithms for multi-agent path finding based on a prioritized approach and safe-interval planning paradigm. The key feature of the algorithms is that unlike many other solvers (as in 2018) they do not restrict agents’ moves to be of the uniform duration. This leads to much shorter and natural looking paths.
- AA-SIPP – prioritized multi-agent path planning algorithm that is capable of handling any-angle moves.
- Algorithm for eliminating collisions between any-angle paths for point agents based on local re-planning and wait adjustment.
- Techniques that enhance the performance of the prioritized multi-agent path planning.
- Algorithm for eliminating collisions between any-angle paths by wait adjustment only.
- Algorithm for angle-constrained path planning – LIAN (and its modifications). The algorithm is tailored to find a path composed of straight-line segments, having the property that the angle between any two consecutive segments does not exceed the predefined threshold. Such paths might be more suitable for a number of robotic applications as they do not contain sharp turns.
That’s the paper, describing the algorithm. Here is one more.
- Loop-closure detection procedure for monocular vision-based simultaneous localization and mapping. The procedure is based on a set of heuristic rules that increase the overall performance while keeping the accuracy at the appropriate level.
That’s the paper.
- Algorithm for post-processing of the 3D point-clouds that are the vSLAM output. The algorithm is intended to remove outliers and increase the resolution, contributing to getting more accurate grid-maps for further usage, i.e. for path planning.
That’s the paper.
- Multi-layered architecture of the intelligent control system – STRL (from “Strategic, Tactic, Reactive, Layered). Architecture is composed of the 3 levels of control that integrate methods of computer cognitive modeling, artificial intelligence and control theory.
That’s the paper.
In simple words
My peers and I make robots smarter. Coincidentally we do not deal with the hardware, i.e. we do not construct robots, but rather create software that controls them. As researchers we are interested in the algorithms rather than in robots themselves. That is why we carry on numerous simulation experiments that look like “jumping dots on the screen”. Implementing the algorithms we develop on real robots is a separate, non-trivial task and we don’t have much time (and expertise) to deal with it. This leaves much room for collaboration and we are always happy to work together with the hardware guys to make the things work on real-world machines.
I’m often asked “when the day comes that robots will take over the humanity”, so I have to put my answer here. I think that we are very far away from creating autonomous machines that often become characters of sci-fi movies. It’s an extremely challenging task and many problems are still not solved in that domain, which makes it a very tempting sandbox to play in.