Mobile Robot Algorithms Lab

The ultimate goal of this laboratory is to develop intelligent, fully autonomous mobile robots and adaptive STEM education programs in robotics.

The laboratory works on solving the problem of spatial markup (including solving the subtasks of orientation, navigation, and mapping), primarily for mobile robotic platforms, while also modeling their behavior. The laboratory's research agenda includes:

  • Processing computer vision data (RGB and RGBD cameras, lidars, radars).
  • SLAM algorithms.
  • Extension and application of the ROS platform.
  • Modeling and validation of algorithms for mobile robotic platforms in the Duckietown environment.
  • Building machine learning models for spatial markup problems.
  • Building an approach for coordinated resource management in operating systems.
  • Development of new educational approaches in the field of STEM and industrial robotics.

The laboratory also has extensive experience in developing automatic verification systems and virtual laboratories for technologies in autonomous transport, spatial marking tasks, and other areas.

Projects

K. Chaika, T. Berlenko

Duckietown-Based Projects

Duckietown is an open research project in the autonomous robotics domain developed by Duckietown Foundation. It consists of two parts – robots (“Duckiebots”) and a town ("Duckietown") where these robots roam. A lifelike traffic environment including traffic lights, road signs, road markings, and obstacles are simulated throughout the town. Duckiebots are built on an autonomous chassis and work using a single-board computer with ROS. All of the software is autonomous. The main sensor is used for receiving data from the environment.

K. Krinkin, T. Berlenko

Pattern and Border Detection in 3D TBM SLAM Algorithms

There are several well-known techniques for SLAM: beginning with “classic” SLAM based on the Extended Kalman Filter and ending with modern graph-based algorithms. Our laboratory managed to implement its own SLAM algorithm that uses 3D laser scans as an input.

K. Chaika

SLAM Testing Service (STS)

The SLAM testing service (STS) could help SLAM researchers to automate the evaluation of SLAM methods. STS is based on ROS and uses ROS APIs to launch tests and provide input data to ROS-compatible SLAMs.

K. Krinkin, T. Berlenko

Industrial Software Engineering MOOCs

Massive Open Online Courses (MOOCs) have made the distribution of knowledge accessible and borderless across the world. We wish to harness their power and bring the opportunity to learn effectively to all people regardless of their background.

Publications

May 2022
Paul Schmiedmayer, Robert Chatley, Jan Philip Bernius, Stephan Krusche, Konstantin Chaika, Kirill Krinkin, Bernd Bruegge

Global software engineering in a global classroom

Global Classroom

July 2020
Mikita Sazanovich, Konstantin Chaika, Kirill Krinkin, Aleksei Shpilman

Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously

Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning (ICML2020)

January 2020
Konstantin Chaika

Research Challenges Of Industry 4.0

International Scientific Journal Industry 4.0

See all publications

Seasonal schools

The main goal of the schools is getting experience in research projects development, including work in international teams, and mastering with the newest technologies.

Annual school

Joint Advanced Student School

JASS (Joint Advanced Student School) is an annual international initiative to study emerging technologies using project-driven software development. The school is a place where students and professors from different countries gather for short-term, project-oriented, project-driven education in international teams.

Archive

Group Members

Kirill Krinkin
Head of Research Lab
Tatiana Berlenko
Researcher
Konstantin Chaika
Researcher