Development of a Swordsmanship Training Robot That Evades Human Attacks by Actively Moving Its Target Areas

In this study, the author proposes a swordsmanship training robot that evades attacks from human opponents by actively moving its target areas (or designated striking targets) on its body. Similar to a human practitioner wearing protective armor in Kendo, the robot is equipped with three target areas corresponding to the head, throat, and torso. They are independently actuated by three AC servo motors mounted in the central or lower parts of the body, which also house the control hardware responsible for motion control. Each target area is driven by a toothed pulley and timing belt mechanism. This transmission system enables precise position control while enhancing operational safety by absorbing excessive loads when large external forces are applied to the robot or when accidental collisions with human users occur. A high-speed camera is installed beneath the robot’s eye. Using visual information captured by the camera, the robot can estimate the likely attack type that an opponent is about to initiate and execute an appropriate defensive maneuver. In addition, a set of push-button switches corresponding to different defensive actions is provided. By observing the opponent’s movement, a human operator can manually trigger the most suitable defensive maneuver through these switches.

Authors

Institutions

Publication Details

Journal
Actuators
Published
2026-09-24
DOI
https://doi.org/10.3390/act15100502
Primary Topic
Teleoperation and Haptic Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Development of a Swordsmanship Training Robot That Evades Human Attacks by Actively Moving Its Target Areas

Kiyoshi Hoshino
Actuators
Teleoperation and Haptic Systems
article

Development of a Swordsmanship Training Robot That Evades Human Attacks by Actively Moving Its Target Areas

Kiyoshi Hoshino
article en

Abstract

In this study, the author proposes a swordsmanship training robot that evades attacks from human opponents by actively moving its target areas (or designated striking targets) on its body. Similar to a human practitioner wearing protective armor in Kendo, the robot is equipped with three target areas corresponding to the head, throat, and torso. They are independently actuated by three AC servo motors mounted in the central or lower parts of the body, which also house the control hardware responsible for motion control. Each target area is driven by a toothed pulley and timing belt mechanism. This transmission system enables precise position control while enhancing operational safety by absorbing excessive loads when large external forces are applied to the robot or when accidental collisions with human users occur. A high-speed camera is installed beneath the robot’s eye. Using visual information captured by the camera, the robot can estimate the likely attack type that an opponent is about to initiate and execute an appropriate defensive maneuver. In addition, a set of push-button switches corresponding to different defensive actions is provided. By observing the opponent’s movement, a human operator can manually trigger the most suitable defensive maneuver through these switches.

ActuatorsVol. 15(10)
Meiji University (JP)
Openalex Percentile: Top 21%
Teleoperation and Haptic Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Development of a Swordsmanship Training Robot That Evades Human Attacks by Actively Moving Its Target Areas — Kiyoshi Hoshino · Actuators (2026) | TGRS Research Map | TGRS