Home Page for Scott (Seongwon) Lee | Parasol Laboratory


Picture Scott (Seongwon) Lee
PhD Student
Parasol Laboratory url: http://parasollab.web.illinois.edu/~sl148/
Mechanical Science and Engineering email:
University of Illinois at Urbana-Champaign
Urbana, IL 61801, USA


Curriculum Vitae (CV) Google Scholar LinkedIn Personal Webpage

I am a Ph.D. student working with Dr. Nancy Amato, having joined the Parasol Lab in 2022 at UIUC. My research centers on applying task and motion planning algorithms to multi-robot systems.

My current project, Lazy-DaSH, employs a hierarchical structure to link task planning with motion planning with a constraint feedback mechanism, enabling efficient constraint management and adaptability in the constrained environments. I am currently working on integrating this approach into the MiV Project for warehouse-like automation in biology lab settings.


Research

Multi-robot Task and Motion Planning


Motion planning has applications in robotics, games/virtual reality, computer-aided design/virtual prototyping, and bioinformatics. Our research is focused on developing motion planning algorithms and applying them to a wide range of problems.

Factory Automation (Mind in Vitro)


Mind in Vitro project is in NSF Expedition in Computing program developing the science and technology to fabricate, model and program systems based on living neurons. In this project, we develop a warehouse-like biology lab automation system.

Integrated Task and Motion Planning


We explore the integration of the high-level semantic reasoning of task planning with the low-level geometric aware reasoning of motion planning.

Multi-Agent Motion Planning


We use Rapidly-exploring Random Graphs coupled with Mean Curve workspace skeletons to find valid paths for ligand motion into the protein binding site

Publications

Lazy-DaSH: Lazy Approach for Hypergraph-based Multi-robot Task and Motion Planning, Seongwon Lee, James Motes, Isaac Ngui, Marco Morales, Nancy M. Amato, ICRA@40, Oct 2024. DOI: Unpublished
Keywords: Motion Planning, Multi-Agent Systems, Task Planning
Links :

BibTex

Unpublished


Abstract

We introduce Lazy-DaSH, a variant of the multi-robot task and motion planning method DaSH, which scales to more than double the number of robots and objects compared to the original method and achieves three orders of magnitude faster planning time when applied to the multi-manipulator object rearrangement problem. We achieve this improvement by lazily validating motions proposed by a new task planning layer while DaSH instead computes motion feasibility of all possible actions, most of which are irrelevant to the task. Our proposed method uses a high-level task query phase to identify the necessary planning spaces for task completion and lazily computes motion feasibility only within these spaces. This approach creates a hierarchical structure between the task planning layer and motion planning layer, connected by a constraint feedback mechanism that informs the feasibility of both tasks and motions. Our strategy reduces both the time required to construct state space representations and the query time by keeping the representation smaller. We demonstrate our method in four different scenarios to highlight the scalability of an increasing number of robots and objects and the constraint feedback mechanism for conflict adaptations.


A Hierarchical Approach to Workstation-based Task Allocation and Motion Planning, Isaac Ngui, Seongwon Lee, James Motes, Marco Morales, Nancy M. Amato, IROS 2023, May 2024. DOI: Unpublished
Keywords: Multi-Agent Systems, Path Planning, Task Planning
Links :

BibTex

Unpublished


Abstract

This paper introduces a hierarchical approach to workstation-based task allocation and motion planning problems for on-demand and reconfigurable factory environments. This problem is composed of two sub-problems: workstation task planning and payload transportation. This hierarchical approach abstracts away workstation details during payload transportation and payload transportation details away during workstation task planning, enabling scalable planning for large numbers of robots and workstations. This hierarchical approach is expected to offer adaptable solutions for various workstation-based factory scenarios, promoting high throughput while maintaining flexibility.