Reinforcement Learning-Based Compliant Locomotion for Sensorless Humanoids in Physical Human-Robot Interaction with Sim-to-Real Force Dispersion Compensation

Yeonsoo Park, Gunwoo Kim, Sung Gwan Park, Chang Joo Lee, Sungsoo Rhim

Humanoid robots operating in human environments must safely respond to physical human-robot interactions while maintaining stable locomotion. Conventional reinf...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.255

Contact Force Estimation-Guided Reinforcement Learning Framework for Compliant Humanoid Bipedal Walking

Yonghyun Jo, Kwanwoo Lee, Gyeongjae Park, Seohyeon Lim, Jaeyong Shin, Hyunjun Choi, Sanghyuk Park, Jaeheung Park, SungMoon Hur

This paper presents a contact force-aware reinforcement learning framework for compliant humanoid bipedal walking. The framework estimates foot contact forces f...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.269

Development of QP Based Posture Controller for Wheeled Bipedal Robot with High DoF

Junyeon Namgung, Baek-Kyu Cho

This paper presents a quadratic programming (QP)-based posture controller for Legway, a wheeled bipedal robot with a 10-DOF configuration in Wheel Mode. A linea...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.283

Whole-Body Inverse-Dynamics Posture Control of a Multi-Legged Robot with Control-Barrier-Function Based Redundant-DoF Constraints

Seong-Hyeon Ryu, Jung-Yup Kim

In this paper, we propose a set-based whole-body inverse-dynamics posture control framework for a multi-legged robot whose legs possess redundant degrees of fre...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.290

Real-Time Pedestrian Trajectory Prediction for Mobile Robots: A Comparative Study of Transformer-Based and Diffusion-Based Models

Ha Jin Park, Ki-In Na

Predicting pedestrian trajectories is essential for safe mobile robot navigation in human-shared environments. Most existing models are trained on Bird’s-Eye-Vi...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.301

A Biomimetic 3-DOF Humanoid Neck Design with Hybrid Gear-Linear Actuator Mechanism

Chanhyuk Moon, Juhyun Kim, Dongjun Kim, Eunho Sung, Woongbae Kim, Jaeheung Park

This paper presents a 3-degree-of-freedom humanoid neck mechanism that mimics human cervical motion using a differential gearbox and a linear actuator (LA). The...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.309

Design of an Independent 3-DOF Flexion Kinesthetic Haptic Interface using Electrostatic Clutches

Nakhyeong Lee, Jihyeong Ma, Seohee Kong, Jongseok Nam, Ki-Uk Kyung

This study presents a kinesthetic haptic interface capable of independently constraining 3-DOF finger flexion using miniaturized electrostatic clutches. Convent...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.317

Context-Driven Task and Motion Planning with Language Models

Jinhwi Lee

This paper presents a task planning framework for autonomous robots that combines Large Language Models (LLMs) and Vision-Language Models (VLMs) to enable conte...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.325

VLM-based Object-centric 6DoF 3D Visual Grounding

Seongyeop Lee, Hyunsoo Shin, Gyubeom Jo, Ji-Hun Bae, Sungon Lee

3D Visual Grounding aims to localize target objects in 3D scenes from natural language descriptions. Existing methods mainly provide object location information...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.333

Adaptive Object Detection with Long- and Short-Term Memory via YOLOE Text–Free Model Collaboration

Jiho Kim, Jeonghoon Kwak, Dohyun Kyoung, Jaewan Koo, Byoung-Woo Gam, Joonwoo Lee, Kap-Ho Seo

Autonomous robots often operate in semi-structured environments such as orchards and warehouses, where unpredictable obstacles frequently appear. Conventional d...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2026.21.3.342