← Search

Hyun-Jung Kim

7 accepted papers

2026

A Multi-View Attention-Based Encoder-Decoder Framework for Clustered Traveling Salesman Problem

RA-L 2026

Many autonomous mobile robot path planning scenarios require servicing grouped delivery points. Such clustered routing problems are naturally formulated as the clustered traveling salesman problem (CluTSP), which comprises two interdependent subproblems: global inter-cluster routing to determine the

Cited by 0SourceScholar
2025

Optimal Scheduling of Timed Petri Nets With Resource Marking and Ready Times: Application to Robotic Flow Shops

RA-L 2025

Many scheduling problems, especially for automated manufacturing systems, have been addressed with a timed Petri net (TPN) by developing optimal or heuristic algorithms based on it. However, most of them have focused on cyclic scheduling, in which a firing sequence of transitions in a TPN is repeate

Cited by 3SourceScholar
2025

Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling

NeurIPS 2025poster

Reinforcement Learning (RL) has shown promising results in solving Job Scheduling Problems (JSPs), automatically deriving powerful dispatching rules from data without relying on expert knowledge. However, most RL-based methods train only a single decision-maker, which limits exploration capability a…

Cited by 0SourceScholar
2024

Dynamic Crane Scheduling with Reinforcement Learning for a Steel Coil Warehouse

ICRA 2024poster

This paper tackles the dynamic crane scheduling problem in a steel coil warehouse, involving tasks such as coil storage, retrieval, and shuffling. Tasks arrive dynamically with precedence relations, while multiple cranes share a track, necessitating collision avoidance. We aim to minimize the averag…

Cited by 3SourceScholar
2022

A Multi-Manned Assembly Line Worker Assignment and Balancing Problem With Positional Constraints

RA-L 2022

One of main operational issues in assembly lines is to assign tasks and workers to workstations so that the maximum productivity can be achieved. Many previous studies have addressed this problem, but most of them have assumed one worker in each workstation or multiple workers with the same skill le

Cited by 12SourceScholar