Research

Research

My research interests are:

  • artificial intelligence;
  • 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 for localization, mapping, path and motion planning.


Videos || Methods || In plain English


Videos

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.

  1. Methods and algorithms for multi-agent path finding (MAPF). The key feature of the algorithms is that i) unlike many other solvers they do not restrict agents’ actions to be of the uniform duration, ii) translations into arbitrary directions are naturally handled when planning. This leads to much shorter and natural looking paths.
    • CCBS – an optimal MAPF planner that supports continuous time.
    • Enhanced AA-SIPP(m) algorithm that supports agents of arbitrary size and takes into account rotation actions when building plans (LINK TO APPEAR SOON).
    • AA-SIPP(m) – prioritized multi-agent path planning algorithm that is capable of handling any-angle moves.
    • Techniques that enhance the performance of prioritized multi-agent path planning.
  2. Methods and algorithms for single-agent path finding
    • GAN-finder – finding a path on a grid via image generation (preliminary results).
    • Algorithm for finding a path that does not contain sharp turns – LIAN and its modifications: eLIAN and LP-LIAN.
  3. Methods and algorithms for vision-based navigation
  4. Multi-layered architecture of the intelligent control system – STRL (from “Strategic, Tactic, Reactive, Layered) that integrates the ideas of computer cognitive modeling, artificial intelligence and control theory.

In plain English

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 the 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.