Effective Policy Search Method for Robot Reinforcement Learning with Noisy Reward

Young-Ha Yang, Cheol-Soo Lee

Robots are widely used in industries and services. Traditional robots have been used to perform repetitive tasks in a fixed environment, and it is very difficul...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.001

The Method of Virtual Reality-based Surgical Navigation to Reproduce the Surgical Plan in Spinal Fusion Surgery

Chanho Song, Jaebum Son, Euisung Jung, Hoyul Lee, Young-Sang Park, Yoosoo Jeong

In this paper, we proposed the method of virtual reality-based surgical navigation to reproduce the pre-planned position and angle of the pedicle screw in spina...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.008

Computational Cost Reduction Method for HQP-based Hierarchical Controller for Articulated Robot

Mingyu Park, Dongwhan Kim, Yonghwan Oh, Yisoo Lee

This paper presents a method that can reduce the computational cost of the hierarchical quadratic programming (HQP)-based robot controller. Hierarchical control...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.016

3D Multi-floor Precision Mapping and Localization for Indoor Autonomous Robots

Gyuree Kang, Daegyu Lee, Hyunchul Shim

Moving among multiple floors is one of the most challenging tasks for indoor autonomous robots. Most of the previous researches for indoor mapping and localizat...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.025

Collision Avoidance Based on Null Space Projection for a Nonholonomic Mobile Manipulator

KyeJin Kim, InHwan Yoon, Jae-Bok Song

Since the mobile platform and the manipulator mounted on it move at the same time in a mobile manipulator, the risk of mutual collision increases. Most of the s...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.032

Visual Object Manipulation Based on Exploration Guided by Demonstration

Doo-Jun Kim, HyunJun Jo, Jae-Bok Song

A reward function suitable for a task is required to manipulate objects through reinforcement learning. However, it is difficult to design the reward function i...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.040

Control Strategies for Landing Quadcopters on Ships with Legged Platform Based on Impedance Control

Seonghyeon Hwang, Seunghyeon Lee, Seongho Jin, Inho Lee

In this paper, we propose a legged landing platform for the quadcopter taking off and landing in the ship environment. In the ship environment with waves and wi...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.048

Learning Optimal Trajectory Generation for Low-Cost Redundant Manipulator using Deep Deterministic Policy Gradient(DDPG)

Seunghyeon Lee, Seongho Jin, Seonghyeon Hwang, Inho Lee

In this paper, we propose an approach resolving inaccuracy of the low-cost redundant manipulator workspace with low encoder and low stiffness. When the manipula...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.058

Analytical Approach to Deformation of a Soft Rotary Actuator with Double Curvature Shell Shape

Young min Lee, Hyouk ryeol Choi, Ja choon Koo

In this paper, we considered the deformation shape of the soft rotation actuator as a double curvature shell and proceeded with the analytical development. Sinc...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.068

Online Adaptation of Control Parameters with Safe Exploration by Control Barrier Function

Suyeong Kim, Hungsun Son

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is us...

PDFHTMLPubReaderePub

DOI: https://doi.org/10.7746/jkros.2022.17.1.076