Faith Ogunwoye.

SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs

Faith Ogunwoye*, Iana Zhura*, Hajira Amjad, Timofei Kozlov, Didar Seyidov, Dmitrii Plotnikov, Fedor Fedorov, Dzmitry Tsetserukou

First author · Under review, IEEE ICRA 2027 · 2026

A quadruped sent to a named gas leak: open-vocabulary olfactory scene graphs keep gas identity and source estimates, and diffusion planning drives navigation, evaluated across 424 source and wind configurations with matched Gazebo trials. arXiv ↗

Copy@misc{ogunwoye2026smelldiffusion,
  title         = {SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs},
  author        = {Ogunwoye, Faith and Zhura, Iana and Amjad, Hajira and Kozlov, Timofei and Seyidov, Didar and Plotnikov, Dmitrii and Fedorov, Fedor and Tsetserukou, Dzmitry},
  year          = {2026},
  eprint        = {2609.20624},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2609.20624}
}

HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing

Konstantin Gubernatorov*, Mikhail Sannikov*, Ilya Mikhalchuk*, Egor Kuznetsov, Makar Artemov, Faith Ogunwoye, Marcelino Fernando, Artem Asanov, Ziang Guo, Dzmitry Tsetserukou

IEEE/RSJ IROS 2026 · Skoltech Top Paper Award

Tactile capability is distilled into a vision-language-action policy, reaching 86.7% mean success on real contact-rich tasks with no tactile sensor at inference. I collected the real-world dual-arm teleoperation demonstrations the model was trained on. arXiv ↗ · Video ↗

Copy@inproceedings{gubernatorov2026hapticvla,
  title         = {HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing},
  author        = {Gubernatorov, Konstantin and Sannikov, Mikhail and Mikhalchuk, Ilya and Kuznetsov, Egor and Artemov, Makar and Ogunwoye, Faith Oluwatobi and Fernando, Marcelino and Asanov, Artem and Guo, Ziang and Tsetserukou, Dzmitry},
  booktitle     = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year          = {2026},
  eprint        = {2603.15257},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2603.15257}
}

CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain

Chidera Agbasiere*, Mikhail Sannikov*, Faith Ogunwoye, Erik Shaikhiev, Alex Kozinov, Ilya Mikhalchuk, Iana Zhura, Dzmitry Tsetserukou

IEEE SMC 2026

Diffusion-based LiDAR scene completion directly in the point cloud domain. I built the monocular branch, replacing LiDAR input with single-camera depth converted to pseudo-LiDAR, and quantified what that substitution costs. arXiv ↗

Copy@inproceedings{agbasiere2026clouddiffusion,
  title         = {CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain},
  author        = {Agbasiere, Chidera and Sannikov, Mikhail and Ogunwoye, Faith and Shaikhiev, Erik and Kozinov, Alex and Mikhalchuk, Ilya and Zhura, Iana and Tsetserukou, Dzmitry},
  booktitle     = {IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
  year          = {2026},
  eprint        = {2606.16048},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2606.16048}
}

HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing

Mikhail Sannikov*, Ilya Mikhalchuk*, Konstantin Gubernatorov*, Petr Kovalev, Faith Ogunwoye, Dzmitry Tsetserukou

Under review, IEEE ICRA 2027 · 2026

A world action model that predicts future frames, imagined contact and robot actions, distilling tactile knowledge so no fingertip sensor is needed at deployment. arXiv ↗

Copy@misc{sannikov2026hapticwam,
  title         = {HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing},
  author        = {Sannikov, Mikhail and Mikhalchuk, Ilya and Gubernatorov, Konstantin and Kovalev, Petr and Ogunwoye, Faith Oluwatobi and Tsetserukou, Dzmitry},
  year          = {2026},
  eprint        = {2609.23888},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2609.23888}
}

JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation

Faith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov, Dzmitry Tsetserukou

First author · Submitted, ACM/IEEE HRI 2027 (Short Contributions) · 2026

VLA targets reach the robot controller late and irregularly, so a sensible action can still move abruptly near people. JitterVLA replays identical commands and arrival traces through different controllers: interpolation cut modelled p99 jerk by 83% at a 2.0 cm tracking cost, and lowered measured jerk on a real UR3 in all six exploratory pairs. Code and data are withheld until the HRI review is complete. arXiv ↗ · Project page ↗

Copy@misc{ogunwoye2026jittervla,
  title         = {JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation},
  author        = {Ogunwoye, Faith and Seyidov, Didar and Gubernatorov, Konstantin and Tsetserukou, Dzmitry},
  year          = {2026},
  eprint        = {2610.13628},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2610.13628}
}

Exploring the Impact of Diesel-Vegetable Oil Blends as an Alternative Fuel in Combustion Chambers

Biofuels · 2025

Experimental study of diesel and vegetable oil blends as alternative fuels.

Prediction of Impact Strength of TIG Welded Cr-Mo Steel Using Artificial Neural Networks

Metallurgical and Materials Engineering · 2024

ANN-based prediction of mechanical properties for TIG welded chromium-molybdenum steel.

Design and Fabrication of a Mechanical Sweeper

Nigerian Journal of Technological Development · 2024

Design, fabrication, and evaluation of a mechanical sweeping machine.

Predictive Maintenance of Industrial Equipment Using Machine Learning

Intl. Journal of Science and Technology Research Archive · 2023

ML-driven predictive maintenance for industrial equipment in the Awka Metropolis industrial environment.

Creating New Materials and Technologies to Reduce the Environmental Impact of Human Activity

Intl. Journal of Advanced Multidisciplinary Research and Studies, Vol. 3, Issue 6 · 2023

Review of emerging sustainable materials and technologies, including solar cells, batteries, green construction materials, and electric vehicles, that reduce environmental harm. Paper ↗