I am Dmitri Kovalenko, I write software for robotics. This is a harbour for my thoughts on work and life.

works

  1. Getting in touch: controllers that handle contact

  2. ICRA'24: New results in SLAM and Control

  3. How I didn't go to IROS'23

publications

Pluto: Motion Detection for Navigation in a VR Headset

Pluto Neural Network Architecture

Computer vision-based navigation for virtual reality applications is always at risk of a tracking failure. An extension for a navigation system is proposed, which recognizes agents motion and stillness states from accelerometer data.

Cite with

@inproceedings{kovalenko2021pluto, title={Pluto\: Motion detection for navigation in a vr headset}, author={Kovalenko, Dmitri and Migukin, Artem and Ryabkova, Svetlana and Chernov, Vitaly}, booktitle={2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN)}, pages={1--7}, year={2021}, organization={IEEE} }

Read on

See Pluto: Motion Detection for Navigation in a VR Headset on Arxiv

Sensor Aware Lidar Odometry

Highest neighbor beam distance determination scheme

A lidar odometry method, integrating into the computation the knowledge about the physics of the sensor, is proposed. A model of measurement error enables higher precision in estimation of the point normal covariance. Adjacent laser beams are used in an outlier correspondence rejection scheme.

Cite with

@inproceedings{kovalenko2019sensor, title={Sensor aware lidar odometry}, author={Kovalenko, Dmitri and Korobkin, Mikhail and Minin, Andrey}, booktitle={2019 European Conference on Mobile Robots (ECMR)}, pages={1--6}, year={2019}, organization={IEEE} }

Read on

See Sensor Aware Lidar Odometry on Arxiv

Scene association in endoscopic videos

recall/precision curves from the scene association algorithms

A scene association algorithm is proposed to automate the process of endoscopic surveillance. The algorithm constructs a neighborhood system for visually resemblant frames. An experimental evaluation of the algorithm has been conducted on a set of in vivo endoscopic videos.

Cite with

@article{dmkov2017sceneass, title={Scene association in endoscopic videos}, author={Dmitri Kovalenko, Vitaly Gnatyk}, journal={GraphiCon Proceedings}, volume={27}, pages={269--274}, year={2017} }

Read on