Younghyo Park

I am a first-year Ph.D. student in EECS at MIT CSAIL, advised by Professor Pulkit Agrawal.

I received my Bachelors degree (Summa Cum Laude) in Mechanical Engineering at Seoul National University. Previously, I was a full-time research scientist at NAVER LABS, developing machine/reinforcement learning algorithms to make robot arms like AMBIDEX perform various daily tasks. I also spent some time at Saige Research as an undergraduate research intern.

Email  /  CV  /  Twitter

profile photo
Research Vision

My dream is to see robots performing all sorts of complex, long-horizon and contact-rich manipulation tasks in real-world, just like we humans do everyday. One scalable way to acheive this dream is to pretrain robots with (a) a repertoire of reusable low-level motor control skills and (b) an intelligence that can temporally or spatially compose such skills to complete any given unseen tasks.

What kind of low-level manipulation skills should we pretrain in advance, and how should we train them? With such reusable repertoire of skills, how should we train an intelligence that can orchestrate them to perform longer-horizon tasks? My upcoming works will mainly address these questions!

* denotes equal contribution.

Open-source Projects
Using Apple Vision Pro to Control and Train Robots
Younghyo Park, Pulkit Agrawal
github / App Store / twitter / short paper

An app for Apple Vision Pro that can stream user's head / wrist / finger tracking results to any machines connected to the same network. This can be used to (a) teleoperate robots using human motions and (b) collect datasets of humans navigating and manipulating the real-world!

Publications
Position: Automatic Environment Shaping is the Next Frontier in RL
Younghyo Park*, Gabriel Margolis*, Pulkit Agrawal
ICML, 2024 (Oral Presentation, Top 5%)
project page / video / twitter

Most robotics practitioners spend most time shaping the environments (e.g. rewards, observation/action spaces, low-level controllers, simulation dynamics) than to tune RL algorithms to obtain a desirable controller. We posit that the community should focus more on (a) automating environment shaping procedures and/or (b) developing stronger RL algorithms that can tackle unshaped environments.

Safety-Aware Unsupervised Skill Discovery
Sunin Kim*, Jaewoon Kwon*, Taeyoon Lee*, Younghyo Park*, Julien Perez
ICRA, 2023
project page / video / twitter

An algorithm that can discover diverse and useful set of skills from scratch that is inherently safe to be composed for unseen downstream tasks. Considering safety during skill discovery phase is a must when solving safety-critical downstream tasks.

Robot Learning to Paint from Demonstrations
Younghyo Park*, Seunghoon Jeon*, Taeyoon Lee
IROS, 2022 (Winner: Best Entertainment & Amusement Paper Award)
project page / video / story / interview / paper

Drawing robot ARTO-1 performs complex drawings in real-world by learning low-level stroke drawing skills, requiring delicate force control, from human demonstrations. This approach eases the planning required to actually perform an artistic drawing.

Collision detection for robot manipulators using unsupervised anomaly detection algorithms
Kyumin Park, Younghyo Park, Sangwoong Yoon, Frank C. Park
Transactions on Mechatronics, 2021
paper

We detect collisions for robot manipulators using unsupervised anomaly detection methods. Compared to supervised approach, this approach does not require collisions datasets and even detect unseen collision types.

Deep Learning Based Parking Slot Detection and Tracking: PSDT-Net
Younghyo Park, Joonwoo Ahn, Jaeheung Park
ICRITA, 2022
paper

Performs real-time parking slot detection and tracking for autonomous parking systems.


Check out Jon Barron's repository for the template of this website.