Research

Research

My research interests are:

  • artificial intelligence;
  • intelligent robotics;
  • AI planning, path planning, path finding;
  • heuristic search;
  • multi-agent systems;
  • simultaneous localization and mapping (SLAM);
  • 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;
  • adaptive, i.e. can behave well in changing environments;
  • collaborative, i.e. can interact with each other and humans to safely and effectively accomplish their missions.

Creating intelligent control systems for mobile agents is a challenging problem. To solve it one needs to use the variety of methods from AI, control theory, computer cognitive modelling etc.

Currently I’m involved in research and development of methods and algorithms for path and motion planning and (to a less extent) localization and mapping.

Videos || Methods || In plain English

Videos

The following videos provide an insight of my research activities.

Show description
This video demonstrates the application of the single-agent path finding algorithm that takes into account both the kinodynamic constraints of the agent and the dynamic obstacles that populate the environment (their trajectories are considered to be accurately predicted and passed to the planner as the input).

Show description
This video demonstrates the application of the multi-agent path finding (MAPF) algorithm developed by us to various navigation scenarios in simulated and real-world environments. Unlike many other MAPF algorithms (present at that time) our approach allows actions of arbitrary duration and translations in arbitrary direction. Moreover it explicitly takes into account rotations as well. Being a prioritized planner it scales well to large number of robots (up to hundreds in simulation).

Another video on this line of research is here: https://www.youtube.com/watch?v=1Jrye5S0ZV8.

Show description
This video demonstrates how a map is built by processing the video-stream from a single camera (so-called monocular vSLAM). All processing is done in real time on the embedded computer NVidia Jetson. Fully-convolutional neural network of the original architecture is used to infer depth-maps which are further used by a conventional RGB-D SLAM method, i.e. RTAB-MAP. Resultant map is available both as a point-cloud (top-right of the frame) and as a voxel grid (bottom right) suitable for path planning.

Another video on this line of research is here: https://www.youtube.com/watch?v=piuVq8f61gs.
This video shows how the feature-based vSLAM method is used (ORB2-SLAM) for localization and mapping. Note how sparse the resultant map (red and black dots) is.

Show description
Demonstration of the autonomous flight in GPS-denied environment guided by computer vision. Drone detects markers on the floor (QR-codes) and follows instructions encoded with them, e.g. “pursue in the same direction”. When the landing marker is encountered drone automatically lands on it.

Methods, algorithms, models

Below one might find several examples of the algorithms, methods and models that were developed with my active involvement. More details on them can be found in my publications.

  1. Methods and algorithms for centralized 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.
    • 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 are aimed at making mobile agents, e.g. mobile robots, smarter. Coincidentally we do not deal with the hardware, i.e. we do not construct robots, but rather create the software. 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 various sci-fi movies (like Terminator). It’s an extremely challenging task and many problems are still not solved in that domain, which makes it a very attractive sandbox to play in.