//certain sections of the original thesis have been removed Introduction These set of four blog posts will cover the work I performed for my Master's Thesis at KAIST titled " Accelerating Policy Learning for Robust Control of Robotic Manipulators and Aerial Vehicles via Physics-Informed Guidance " under Professor Dong Eui Chang. The full thesis can be found at KAIST library: THESIS after it is publicly released. It has in-depth explanation of the preliminary concepts, simul

//certain sections of the original thesis have been removed Introduction These set of four blog posts will cover the work I performed for my Master's Thesis at KAIST titled " Accelerating Policy Learning for Robust Control of Robotic Manipulators and Aerial Vehicles via Physics-Informed Guidance " under Professor Dong Eui Chang. The full thesis can be found at KAIST library: THESIS after it is publicly released. It has in-depth explanation of the preliminary concepts, simul

//certain sections of the original thesis have been removed Introduction These set of four blog posts will cover the work I performed for my Master's Thesis at KAIST titled " Accelerating Policy Learning for Robust Control of Robotic Manipulators and Aerial Vehicles via Physics-Informed Guidance " under Professor Dong Eui Chang. The full thesis can be found at KAIST library: THESIS after it is publicly released. It has in-depth explanation of the preliminary concepts, simul

//certain sections of the original thesis have been removed Introduction These set of four blog posts will cover the work I performed for my Master's Thesis at KAIST titled " Accelerating Policy Learning for Robust Control of Robotic Manipulators and Aerial Vehicles via Physics-Informed Guidance " under Professor Dong Eui Chang. My thesis and the thesis defence were well received by the committee members that included my supervisor Professor Dong Eui Chang, Professor Changdon

Check out this game my brother and I made for the Spooktober gamejam on itch.io. I had around 1-2hrs of free time to spare each day and we ended up finishing the visual novel in like a week's time for submission. All the characters, story, mechanics and the visuals are made from scratch. You can play it on your browser, if you are on a PC. Also, it is free! GAME LINK: https://aragakii.itch.io/reverie Some stills from the game:

About the Project This was a global hackathon that I and some of my friends from the lab joined. It was about the use of LeRobot's SO-101 robots and Huggingface's new foundation model, a Vision-Language-Action (VLA) called SmolVLA . We used it for a multi-robot collaboration task where two of these robots come together to pick up a specific object and transfer between them. Two SmolVLA models run together and we fine-tuned them using imitation learning for our this task. We

About the Project I worked on this project in KAIST with Myriam Schonenenberger , AI Dept., for the AI707 course. The project was called SleeperAgent: Dreaming from a Third Perspective , and it was about "dreaming" up a 3rd person view given only the wrist camera view for a manipulator to improve task efficiency and success rates. The github repo is: https://github.com/otoshuki/sleeperagent Note that everything written here was just copy pasted from the original report we wro

About the Project I took a course called EE683: Robot Control by Professor Min Jun Kim at KAIST during my 2nd semester. One good thing about the course was the bi-weekly assignment which had one specific part where the students were free to implement any algorithm and provide simulation results. I ended up implementing a lot of the techniques and models learned in the course. These are a series of blog posts that cover some of those sections since I felt like it was worth sha

About the Project I took a course called EE683: Robot Control by Professor Min Jun Kim at KAIST during my 2nd semester. One good thing about the course was the bi-weekly assignment which had one specific part where the students were free to implement any algorithm and provide simulation results. I ended up implementing a lot of the techniques and models learned in the course. These are a series of blog posts that cover some of those sections since I felt like it was worth sha

About the Project I took a course called EE683: Robot Control by Professor Min Jun Kim at KAIST during my 2nd semester. One good thing about the course was the bi-weekly assignment which had one specific part where the students were free to implement any algorithm and provide simulation results. I ended up implementing a lot of the techniques and models learned in the course. These are a series of blog posts that cover some of those sections since I felt like it was worth sha

About the Project I took a course called EE683: Robot Control by Professor Min Jun Kim at KAIST during my 2nd semester. One good thing about the course was the bi-weekly assignment which had one specific part where the students were free to implement any algorithm and provide simulation results. I ended up implementing a lot of the techniques and models learned in the course. These are a series of blog posts that cover some of those sections since I felt like it was worth sha

About the Project This was a project I started working on but due to time constraints I couldn't fully complete. However, I think it is still worth writing down about it. This was about making a quadruped simulation model in MATLAB which I was planning to use for some downstream research work like RL algorithms. Hence, I started with building the quadruped model from scratch in Simscape multibody and then using ROS to communicate with the true Unitree Go 1 EDU quadruped for a

About the Project During my first semester at KAIST, I had the privilege to work with Eun Hyuck on a flapping wing air vehicle for the Mobile Robotics course project. He was the main expert on the flapping wing system and I mainly worked on the path-planning algorithm that considers the system's kinematics (and some dynamic constraints) in the path planning process. This youtube video explains our work in more detail:

Anyway, back in 2022, I was in my job, and was getting bored when one of my friends decided to produce some songs. I joined him in his quest as the guitarist in two of his originals. I helped compose the music, the intros, and most importantly, all the guitar audible in the song was played by me. Not a technical project per se, but still worth uploading here on my blog.

//certain sections of the original Thesis have been removed Introduction This work was my final year project under Dr. Hanumant Singh Shekhawat at EEE, IITG performed along with Devashish Taneja (ECE, IITG). The research aimed to target defense scenarios and disaster management task where multiple "goal areas" with different "weights" are to be reached and completed by a group of agents within a time limit. The work was primarily on developing a model for this problem, genera

Idea TL;DR: https://github.com/otoshuki/PRML_Project You can try playing one of the results here: Creative arts, the area where new ideas need to be generated is the one field that has been less impacted by AI. This includes graphical art to musical ones, but they have still been affected to a certain extent by the advent of Deep Learning techniques. We wanted to explore this area of creative music generation using these new techniques in our course project for EE626: Pattern

- Guided by Dr. Gaurav Trivedi and Dr. Hanumant Singh Shekhawat Introduction If you read research papers on motion planning or swarm robotics, you would often find that these are performed in controlled environments where complete information of the agents/robots can be obtained easily. While working with Reinforcement Learning simulations, I found the lack of pre-built environments and agents to be quite a drawback for real world testing. Also, the current systems like Vicon

Introduction So around end of 2018 I started learning about Reinforcement Learning from Coursera and from David Silver's UCL course. Over time I focused on implementing the algorithms I learned from scratch, mainly in Tensorflow 1.x and then later in 2.x. I also ended up implementing a lot of them during the Covid lockdowns in India. Check it out at: https://github.com/otoshuki/RL_Projects This repository contains all of my custom implementations for the following: Crossentro

Introduction TL; DR: https://github.com/otoshuki/DIC-Terrace-Farming-Challenge This was my second Inter IIT experience at IIT Roorkee in 2019 during my junior year. This was another project I worked on concurrently with Zenith during the same time. This dealt with an autonomous agricultural robot specifically for terrace farming in remote locations for Design Innovation Center (DIC) . The project was handled mainly by Robotics Club, IITG, where the major work was done by th

Introduction TL;DR: https://github.com/otoshuki/Project-Zenith This was my second Inter IIT experience at IIT Roorkee in 2019 during my junior year. This project dealt with multi-drone system designed to perform search and rescue operations for Defence Research and Development Organization Snow and Avalanche Study Establishment (DRDO SASE) in India. This specific project was handled by Aeromodelling Club IITG and I got the opportunity to work with a new group of people, with