Iaroslav Okunevich

ORCID: 0000-0001-5440-1297
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Sensor and Energy Harvesting Materials
  • Modular Robots and Swarm Intelligence
  • Infection Control and Ventilation
  • Gaze Tracking and Assistive Technology
  • Social Robot Interaction and HRI
  • Reinforcement Learning in Robotics
  • Smart Parking Systems Research
  • Autonomous Vehicle Technology and Safety
  • Robotics and Sensor-Based Localization
  • Evacuation and Crowd Dynamics
  • Energy Harvesting in Wireless Networks
  • Robotics and Automated Systems
  • Virology and Viral Diseases
  • Speech and dialogue systems
  • IoT-based Smart Home Systems

Université de technologie de belfort-montbéliard
2023-2024

Skolkovo Institute of Science and Technology
2021

The paper focuses on the development of autonomous robot UltraBot to reduce COVID-19 transmission and other harmful bacteria viruses. motivation behind research is develop such a that capable performing disinfection tasks without use sprays chemicals can leave residues, require airing room afterward for long time, cause corrosion metal structures. technology has potential offer most optimal performance along with taking care people, keeping them from getting under UV-C radiation. highlights...

10.1109/case49439.2021.9551413 article EN 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) 2021-08-23

DeltaCharger is a novel charging robot with an Inverted Delta structure for 3D positioning of electrodes to achieve robust and safe transferring energy between two mobile robots. The embedded high-fidelity tactile sensors allow estimate the angular, vertical horizontal misalignments on charger mechanism target using pressure data contact surfaces. This crucial preventing short circuit. In this letter, developed prototype evaluation study different machine learning models misalignment...

10.1109/lra.2021.3098838 article EN IEEE Robotics and Automation Letters 2021-07-26

MobileCharger is a novel mobile charging robot with an Inverted Delta actuator for safe and robust energy transfer between two robots. The RGB-D camera-based computer vision system allows to detect the electrodes on target using convolutional neural network (CNN). embedded high-fidelity tactile sensors are applied estimate misalignment charger mechanism main CNN based pressure data contact surfaces. Thus, developed vision-tactile perception precise positioning of end effector ensures...

10.1109/etfa45728.2021.9613366 article EN 2021-09-07

Robot social navigation needs to adapt different human factors and environmental contexts. However, since these contexts are difficult predict cannot be exhaustively enumerated, traditional learning-based methods have difficulty in ensuring the attributes of robots long-term cross-environment deployments. This letter introduces an online context learning method that aims empower new environments online. The proposed adopts a two-layer structure. bottom layer is built using deep reinforcement...

10.48550/arxiv.2406.11495 preprint EN arXiv (Cornell University) 2024-06-17

Perception of human beings is one the basic capabilities service robots and prerequisite for interaction between humans. Although enabling hardware software technologies have made great strides, there are not many open-source solutions that organically integrate two. To address this shortfall, paper introduces an scheme integration robotic embodied perception. The entity includes a robot chassis, computing unit based on ARM architecture, 3D lidar, 2D lidar four RGB-D cameras exterior...

10.1109/arso60199.2024.10557801 article EN 2024-05-20

Social compatibility is one of the most important parameters for service robots. It characterizes quality interaction between a robot and human. In this paper, human-centered benchmarking framework proposed socially-compliant navigation. an end-to-end manner, four open-source navigation methods are benchmarked, two which socially-compliant. All aspects clarified to ensure reproducibility replicability experiments. The social with Robotic Attributes Scale (RoSAS) measured. After that,...

10.1109/ecmr59166.2023.10256378 article EN 2023-09-04

Social compatibility is one of the most important parameters for service robots. It characterizes quality interaction between a robot and human. In this paper, human-centered benchmarking framework proposed socially-compliant navigation. an end-to-end manner, four open-source navigation methods are benchmarked, two which socially-compliant. All aspects clarified to ensure reproducibility replicability experiments. The social with Robotic Attributes Scale (RoSAS) measured. After that,...

10.48550/arxiv.2210.15628 preprint EN other-oa arXiv (Cornell University) 2022-01-01

The paper focuses on the development of autonomous robot UltraBot to reduce COVID-19 transmission and other harmful bacteria viruses. motivation behind research is develop such a that capable performing disinfection tasks without use sprays chemicals can leave residues, require airing room afterward for long time, cause corrosion metal structures. technology has potential offer most optimal performance along with taking care people, keeping them from getting under UV-C radiation. highlights...

10.48550/arxiv.2108.09772 preprint EN other-oa arXiv (Cornell University) 2021-01-01

DeltaCharger is a novel charging robot with an Inverted Delta structure for 3D positioning of electrodes to achieve robust and safe transferring energy between two mobile robots. The embedded high-fidelity tactile sensors allow estimate the angular, vertical horizontal misalignments on charger mechanism target using pressure data contact surfaces. This crucial preventing short circuit. In this paper, developed prototype evaluation study different machine learning models misalignment...

10.48550/arxiv.2107.10710 preprint EN other-oa arXiv (Cornell University) 2021-01-01

MobileCharger is a novel mobile charging robot with an Inverted Delta actuator for safe and robust energy transfer between two robots. The RGB-D camera-based computer vision system allows to detect the electrodes on target using convolutional neural network (CNN). embedded high-fidelity tactile sensors are applied estimate misalignment charger mechanism main CNN based pressure data contact surfaces. Thus, developed vision-tactile perception precise positioning of end effector ensures...

10.48550/arxiv.2107.10585 preprint EN other-oa arXiv (Cornell University) 2021-01-01
Coming Soon ...