Sangwoon Kim

I am currently a Ph.D. candidate in the Mechanical Engineering department at MIT, where I am mentored by Dr. Alberto Rodriguez. My research interests are primarily in robot manipulation and automation.

My past experience includes an internship as an applied scientist at Amazon Robotics AI. I also hold an M.S. in Mechanical Engineering from MIT, where I had the opportunity to work with Dr. Brian Anthony. My foundational studies were at Seoul National University, where I earned a B.S. in Mechanical and Aerospace Engineering.

Key Research Areas: Robot Manipulation, Reinforcement Learning, Tactile Sensing

Email / Google Scholar / GitHub / LinkedIn / Work

Selected Projects

TEXterity: Tactile Extrinsic deXterity

*Sangwoon Kim, *Antonia Bronars, Parag Patre, and Alberto Rodriguez

In International Conference on Robotics and Automation (ICRA) 2024
skills/keywords: Python, C++, ROS, PyTorch, probabilistic inference

Video Abs PDF Website

We introduce a novel approach that combines tactile estimation and control for in-hand object manipulation. By integrating measurements from robot kinematics and an image-based tactile sensor, our framework estimates and tracks object pose while simultaneously generating motion plans to control the pose of a grasped object. This approach consists of a discrete pose estimator that uses the Viterbi decoding algorithm to find the most likely sequence of object poses in a coarsely discretized grid, and a continuous pose estimator-controller to refine the pose estimate and accurately manipulate the pose of the grasped object. Our method is tested on diverse objects and configurations, achieving desired manipulation objectives and outperforming single-shot methods in estimation accuracy. The proposed approach holds potential for tasks requiring precise manipulation in scenarios where visual perception is limited, laying the foundation for closed-loop behavior applications such as assembly and tool use.
In-bin Manipulation for Item Stowing

Sangwoon Kim, Neel Doshi, and Paul Birkmeyer

In Summer Internship Project at Amazon Robotics 2023
skills/keywords: C++, motion planning, compliant manipulation

Abs

During my summer internship with Amazon Robotics, I was part of the Motion Planning Team inside the Item Stow Team. My primary responsibility was to develop and implement a new motion strategy called ’side blade insertion’, designed as an alternative to the front blade insertion process for item manipulation in Amazon’s fulfillment centers. This required me to dig deep into understanding how Amazon approaches automation in its fulfillment centers and collaborate intensively on a shared code stack. My work predominantly involved coding in C++. (video source: https://www.amazon.science/latest-news/how-amazon-robotics-researchers-are-solving-a-beautiful-problem)
Simultaneous Tactile Estimation and Control of Extrinsic Contact

Sangwoon Kim, Devesh Jha, Diego Romeres, Parag Patre, and Alberto Rodriguez

In International Conference on Robotics and Automation (ICRA) 2023
skill/keywords: Python, C++, ROS, PyTorch, probabilistic inference

Video Abs PDF Code Website

We propose a method that simultaneously estimates and controls extrinsic contact with tactile feedback. The method enables challenging manipulation tasks that require controlling light forces and accurate motions in contact, such as balancing an unknown object on a thin rod standing upright. A factor graph-based framework fuses a sequence of tactile and kinematic measurements to estimate and control the interaction between gripper-object-environment, including the location and wrench at the extrinsic contact between the grasped object and the environment and the grasp wrench transferred from the gripper to the object. The same framework simultaneously plans the gripper motions that make it possible to estimate the state while satisfying regularizing control objectives to prevent slip, such as minimizing the grasp wrench and minimizing frictional force at the extrinsic contact. We show results with sub-millimeter contact localization error and good slip prevention even on slippery environments, for multiple contact formations (point, line, patch contact) and transitions between them. See supplementary video and results at https://sites.google.com/view/sim-tact.
Active extrinsic contact sensing: Application to general peg-in-hole insertion

Sangwoon Kim, and Alberto Rodriguez

In International Conference on Robotics and Automation (ICRA) 2022
skills/keywords: Python, C++, ROS, PyTorch, reinforcement learning, zero-shot sim-to-real transfer

Video Abs PDF Code Website

We propose a method that actively estimates contact location between a grasped rigid object and its environment and uses this as input to a peg-in-hole insertion policy. An estimation model and an active tactile feedback controller work collaboratively to estimate the external contacts accurately. The controller helps the estimation model get a better estimate by regulating a consistent contact mode. The better estimation makes it easier for the controller to regulate the contact. We then train an object-agnostic insertion policy that learns to use the series of contact estimates to guide the insertion of an unseen peg into a hole. In contrast with previous works that learn a policy directly from tactile signals, since this policy is in contact configuration space, it can be learned directly in simulation. Lastly, we demonstrate and evaluate the active extrinsic contact line estimation and the trained insertion policy together in a real experiment. We show that the proposed method inserts various-shaped test objects with higher success rates and fewer insertion attempts than previous work with end-to-end approaches.
Dynamic control of a fiber manufacturing process using deep reinforcement learning

*Sangwoon Kim, *David Donghyun Kim, and Brian W Anthony

IEEE/ASME Transactions on Mechatronics 2021
skills/keywords: Python, Arduino, ROS, Tensorflow, reinforcement learning, feedback control

Abs PDF

This paper presents a model-free deep reinforcement learning (DRL) approach for controlling a fiber drawing system. The custom DRL-based control system predictively regulates fiber diameter and produces a fiber with a desired, constant or non-constant, diameter trajectory, i.e. diameter variation along the fiber length. Physical models of the system are not used. The system was trained and tested on a compact fiber drawing system, which has non-linear delayed dynamics and stochastic behaviors. For a reference trajectory with random step changes, after 1 hour of training, the DRL controller showed the same root mean squared error (RMSE) as an optimized PI controller; after 3 hours of training, it achieved the performance of a quadratic dynamic matrix controller (QDMC). While the PI feedback controller showed 3.5 seconds of time lag in a step response, the DRL controller showed less than a second of time lag. Controller performance tests on trajectories not used in the training process are conducted; for a sine sweep reference trajectory, the DRL controller maintained an RMSE under 40 micron up to a frequency of 45 mHz, compared to 25 mHz for QDMC.
Tactile-rl for insertion: Generalization to objects of unknown geometry

Siyuan Dong, Devesh K Jha, Diego Romeres, Sangwoon Kim, Daniel Nikovski, and Alberto Rodriguez

In IEEE International Conference on Robotics and Automation (ICRA) 2021
skills/keywords: Python, ROS, PyTorch, reinforcement learning, representation learning

Video Abs PDF Website

Object insertion is a classic contact-rich manipulation task. The task remains challenging, especially when considering general objects of unknown geometry, which significantly limits the ability to understand the contact configuration between the object and the environment. We study the problem of aligning the object and environment with a tactile-based feedback insertion policy. The insertion process is modeled as an episodic policy that iterates between insertion attempts followed by pose corrections. We explore different mechanisms to learn such a policy based on Reinforcement Learning. The key contribution of this paper is to demonstrate that it is possible to learn a tactile insertion policy that generalizes across different object geometries, and an ablation study of the key design choices for the learning agent: 1) the type of learning scheme: supervised vs. reinforcement learning; 2) the type of learning schedule: unguided vs. curriculum learning; 3) the type of sensing modality: force/torque vs. tactile; and 4) the type of tactile representation: tactile RGB vs. tactile flow. We show that the optimal configuration of the learning agent (RL + curriculum + tactile flow) exposed to 4 training objects yields an closed-loop insertion policy that inserts 4 novel objects with over 85.0% success rate and within 3 4 consecutive attempts. Comparisons between F/T and tactile sensing, shows that while an F/T-based policy learns more efficiently, a tactile-based policy provides better generalization.