Hello there!👋 I'm Yaroslav,

A seasoned Robotics Enthusiast with over 3 years of expertise in crafting intelligent machines using advanced AI techniques, including LLMs and RL.
Sometimes I thrive in hackathons, sparking creativity and finding innovative solutions to challenges. From designing autonomous systems to experimenting with cutting-edge tech, I love pushing the boundaries of what robots can do. 🚀

Let's explore the endless possibilities of technology together! 🤖✨

💻 Tech Stack:

⚙️ Technologies:

🤖 Robotics Stack:

frameworks

platforms

hardware

💫 About my experience

🔭 I’m currently working at @SberRobotics
- 🦿 Emodied AI research outdated
- 🎨 Multiplatform AI artist robot based on Kuka and Doosan robots YouTube, YouTube
- 🦾 Smart picking system from moving conveyor
🥼 NUST MISIS, robotics lab
- 🧠 Reinforcement Learning for robot control
- 🌱 Integration of Bullet physics engine into Microsoft BonsAI
🚘 @SetUp team – EuroBot 2020
🖍 @ArtBot is a robot that draws huge pictures on the floor

🔗 Interesting Links

Grounding LLM on robot (post) – read on Habr

🎉 Achievements

💰 Grant Umnik for integration of Large Language Models into robotics
🥇 1st place at NTO Student track 2022: Intelligent Robotics Systems track
🥇 1st place at MAI AviaHack 2022: Storage capacity reservation forecast
🏆 Winner at Moscow City Hack 2022
🏆 Winner at Digital breakthrough 2022: Season AI in the category Robotics and Artificial Intelligence
🥇 1st place at ONTI 2019: Underwater Robotics track

🤙 Contact me at

Yaroslav's Projects

atokagzx

Profile header

deep-rl-grasping

Train deep reinforcement learning model for robotics grasping. Choose from different perception layers raw Depth, RGBD and autoencoder. Test the learned models in different scenes and object datasets

ferm

FERM: A Framework for Efficient Robotic Manipulation

intel-examples

Get started with the Internet of Things & Artificial Intelligence using Intel® technologies and the iotJumpWay.

mraa

Linux Library for low speed IO Communication in C with bindings for C++, Python, Node.js & Java. Supports generic io platforms, as well as Intel Edison, Intel Joule, Raspberry Pi and many more.

pixtrack

PixTrack is a Computer Vision method for Object Tracking which uses NeRF templates and feature-metric alignment to robustly track the 6DoF pose of a known object.

saycan_experimental

Proof of concept of the SayCan project applying on real UR5 robot

simpleai_fixed_response

An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.

strl_robotics

STRL Robotics framework for mobile robots

wsg50-ros-pkg

ROS package for Schunk WSG-50 gripper with high-rate feedback, closed-loop control, up to two FMF finger. Based on https://code.google.com/p/wsg50-ros-pkg/. Fixed: transparent fingers, fingers offset

Recommend Projects