Dong-Ki Kim

I am a graduate student at MIT-LIDS advised by Professor Jonathan P. How. My research focuses on the field of reinforcement learning and robotics. Specifically, I am interested in meta-learning for enabling a robot to adapt fast to unseen situations, hierarchical learning for solving the delayed credit assignments, and multi-agent reinforcement learning for learning to coordinate with other simultaneously learning robots.

Previously, I received my B.S. in Electrical and Computer Engineering (summa cum laude) at Cornell. I have been advised by such wonderful advisors: Professor Jonathan P. How at MIT, Professor Sebastian Scherer at CMU-RI, Professor Matthew R. Walter at TTIC, and Professor Tsuhan Chen at Cornell.

Email  /  CV  /  Google Scholar  /  GitHub



Below is a selection of my research projects related to reinforcement learning and robot perception.

PontTuset A Policy Gradient Theorem for Learning to Learn in Multiagent Reinforcement Learning
Dong-Ki Kim, Miao Liu, Matthew Riemer, Golnaz Habibi, Sebastian Lopez-Cot, Samir Wadhwania, Gerald Tesauro, Jonathan P. How
AAAI-20 Symposium

We demonstrate that our meta-multiagent policy gradient provides the most all-encompassing approach yet for agents to meta-learn about different sources of non-stationarity in the environment to improve their learning performances, and enables fast adaptation with respect to the non-stationary fellow agents.

PontTuset Policy Distillation and Value Matching in Multiagent Reinforcement Learning
Samir Wadhwania, Dong-Ki Kim, Shayegan Omidshafiei, Jonathan P. How
Paper / Video

We introduce a multi-agent algorithm that combines knowledge from agents through distillation and value-matching (DVM). DVM outperforms policy distillation alone and allows faster learning in dynamic tasks.

PontTuset Learning Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning
Dong-Ki Kim, Miao Liu, Shayegan Omidshafiei, Sebastian Lopez-Cot, Matthew Riemer, Golnaz Habibi, Gerald Tesauro, Sami Mourad, Murray Campbell, Jonathan P. How
AAAI-19 Workshop (Oral Presentation)
Paper / WIRED News

We introduce a new learning to teach framework, called Hierarchical MultiagentTeaching (HMAT). Our framework solves difficulties faced by previous learning to teach works when operating in domains with long horizons, large state spaces, and continuous actions.

PontTuset Learning to Teach in Cooperative Multiagent Reinforcement Learning
Shayegan Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro, Matthew Riemer, Christopher Amato, Murray Campbell, Jonathan P. How
AAAI-19 (Outstanding Student Paper Honorable Mention), ICML-18 Workshop
Paper / MIT News

This paper presents Learning to Coordinate and Teach Reinforcement (LeCTR), the first general framework for intelligent agents to learn to teach in a cooperative MARL.

PontTuset Crossmodal Attentive Skill Learner
Shayegan Omidshafiei, Dong-Ki Kim, Jason Pazis, Jonathan P. How
AAMAS-18, NeurIPS-17 Symposium
Paper / Video

This paper introduces the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic architecture to enable hierarchical reinforcement learning across multiple sensory inputs.

PontTuset Decentralized Multi-UAV Package Delivery
Dong-Ki Kim, Jesús Tordesillas Torres, Hao Shen, Samir Wadhwania, Sebastian Lopez-Cot, Alan Osmundson, Hector Castillo, Jesko (Diego) Mueller, Brett Lopez, Shayegan Omidshafiei, Jonathan P. How
Boeing Annual Visit-18

For the Boeing annual visit at MIT, we prepared a demo, a package delivery scenarios with multiple drones. My contributions include the RVO-based collision avoidance, on-board perception system for delivery type classification, and projection system for visualization.

PontTuset Autonomous Off-Road Vehicle
CMU-RI and Yamaha Team-17
Video1 / Video2 / Video3

We developed an autonomous off-road vehicle (video1). My contributions to the project include a ROS-based system that estimates terrain roughness from 3D point cloud in real-time (video2, video3).

PontTuset Season-Invariant Semantic Segmentation with A Deep Multimodal Network
Dong-Ki Kim, Daniel Maturana, Masashi Uenoyama, Sebastian Scherer

We propose a novel multimodal architecture consisting of two streams, image (2D) and LiDAR (3D). By combining the two streams, we achieve a robust season-invariant semantic segmentation.

PontTuset Satellite Image-based Localization via Learned Embeddings
Dong-Ki Kim, Matthew R. Walter
Paper / Video / NVIDIA News

We propose a vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment.

PontTuset You Are Here: Mimicking the Human Thinking Process in Reading Floor-Plans
Hang Chu Dong-Ki Kim, Tsuhan Chen
Paper / Video

We address the problem of locating a user in a floor-plan, by using a camera and a floor-plan.

PontTuset Deep Neural Network for Real-Time Autonomous Indoor Navigation
Dong-Ki Kim, Tsuhan Chen
Technical Report-15
Paper / Video

We propose a vision-based deep learning system in which a drone autonomously navigates indoors and finds a specific target.

Source code credit to Dr. Barron