← Search

Jongwon Kim

11 accepted papers

2026

Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models

ICLR 2026poster

This paper introduces a methodology for anomaly detection in time series using Time Series Foundation Models (TFMs). While TFMs have achieved strong success in forecasting, their role in anomaly detection remains underexplored. We identify two key challenges when applying TFMs to reconstruction-base…

Cited by 0SourceScholar
2025

GraspSAM: When Segment Anything Model Meets Grasp Detection

ICRA 2025

Grasp detection requires flexibility to handle objects of various shapes without relying on prior object knowledge, while also offering intuitive, user-guided control. In this paper, we introduce GraspSAM, an innovative extension of the Segment Anything Model (SAM) designed for prompt-driven and cat

Cited by 17SourcecodeScholar
2025

MV2: A Large-Scale 360-degree Multi-View Maritime Vision Dataset for Object Detection and Segmentation

IROS 2025

Reliable navigation of autonomous vessels critically depends on robust situational awareness, particularly object detection. For this, an accurate, 360-degree perception of the surrounding environment is essential. However, most existing datasets lack the comprehensive multi-view data required for t

Cited by 0SourceScholar
2025

Robust Maritime Object Detection under Adverse Conditions via Joint Semantic Learning without Extra Computational Overhead

IROS 2025

This study addresses the challenge of robust object detection in maritime environments, where dynamic conditions such as fog, brightness variations, and motion blur can degrade accuracy. We propose a novel framework, Joint Semantic Learning (JSL), which combines ocean scene segmentation and object d

Cited by 1SourcecodeScholar
2020

Polygon-Based Random Tree Search Planning for Variable Geometry Truss Robot

RA-L 2020

This letter proposes the use of a polygon-based random tree path planning algorithm for a variable geometry topology system (VGT). By combining a path planning algorithm and our previous non-impact locomotion algorithm, the proposed VGT system reaches an objective point. The proposed path planning a

Cited by 13SourceScholar
2020

Reconfiguration Solution of a Variable Topology Truss: Design and Experiment

RA-L 2020

In this letter, an active ball joint actuator, called the master node, is developed for the purpose of reconfiguring truss structures. We propose a variable topology truss system, which is an advanced variable geometry truss system that can reconfigure its own topology to expand its functions. Howev

Cited by 13SourceScholar
2019

Design of Compact Variable Gravity Compensator (CVGC) Based on Cam and Variable Pivot of a Lever Mechanism

IROS 2019poster

In this paper, we propose a new compact variable gravity compensation mechanism (CVGC). The CVGC can be used to generate gravity compensation torque by using the cam and lever mechanism and can also amplify the target gravity compensation torque by varying the pivot point of the lever. The feature o…

Cited by 17SourceScholar
2019

Optimization-Based Nonimpact Rolling Locomotion of a Variable Geometry Truss

RA-L 2019

A variable geometry truss (VGT) is a modular truss-structured robot consisting of linear actuators and three-degree-of-freedom joints. Having a sophisticated structure, the VGT can easily be damaged when it rolls and impacts the ground. This letter proposes a nonimpact rolling locomotion scheme to a

Cited by 25SourceScholar
2018

Design and Force-Tracking Impedance Control of a 2-DOF Wall-Cleaning Manipulator Using Disturbance Observer and Sliding Mode Control

ICRA 2018poster

This paper presents design and force-tracking impedance control of 2-degree-of-freedom (DOF) wall-cleaning manipulator equipped with disturbance observer (DOB) and sliding mode control (SMC). In order to keep in contact with various shapes of walls, the proposed manipulator is designed to ensure 2-D…

Cited by 15SourceScholar
2018

Design of Lizard-Inspired Robot with Lateral Body Motion

IROS 2018poster

A new lizard-inspired robot is presented in this paper, which enables to maintain its moving direction by lateral body motions even during high-speed bipedal running. First, a dynamic model for lizard-inspired robot is derived to simulate the lateral body motion of real lizard. Based upon the simula…

Cited by 1SourceScholar
2015

R-Mo: A new mobile robotic platform to reduce variations in height and pitch angle on rugged terrain

IROS 2015poster

This paper presents a new mobile robotic platform (R-Mo) which can reduce unexpected variations in height as well as pitch angle of its main body while traversing rough terrains. As a measure for the smooth movement of mobile platform, the variations in height and pitch angle are chosen in this stud…

Cited by 5SourceScholar