A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots

Abstract Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment. With the aim to conveniently and accurately segment demonstration trajec...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingshan Chi, Yaxin Liu, Qiang Zhang, Chao Zeng
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:CAAI Transactions on Intelligence Technology
Subjects:
Online Access:https://doi.org/10.1049/cit2.12358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850121672563097600
author Mingshan Chi
Yaxin Liu
Qiang Zhang
Chao Zeng
author_facet Mingshan Chi
Yaxin Liu
Qiang Zhang
Chao Zeng
author_sort Mingshan Chi
collection DOAJ
description Abstract Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment. With the aim to conveniently and accurately segment demonstration trajectories, a novel demonstration trajectory segmentation approach is proposed based on the beta process autoregressive hidden Markov model (BP‐AR‐HMM) algorithm and generalised time warping (GTW) algorithm aiming to enhance the segmentation accuracy utilising acquired demonstration data. This approach first adopts the GTW algorithm to align the multiple demonstration trajectories for the same task. Then, it adopts the BP‐AR‐HMM algorithm to segment the demonstration trajectories, acquire the contained motion primitives, and establish the related task library. This segmentation approach is validated on the 6‐degree‐of‐freedom JACO robotic arm by assisting users to accomplish a holding water glass task and an eating task. The experimental results show that the motion primitives within the trajectories can be correctly segmented with a high segmentation accuracy.
format Article
id doaj-art-a55142d3d84848918bf122cb5b22672d
institution OA Journals
issn 2468-2322
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series CAAI Transactions on Intelligence Technology
spelling doaj-art-a55142d3d84848918bf122cb5b22672d2025-08-20T02:35:01ZengWileyCAAI Transactions on Intelligence Technology2468-23222025-06-0110373875410.1049/cit2.12358A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robotsMingshan Chi0Yaxin Liu1Qiang Zhang2Chao Zeng3School of Navigation and Shipping Shandong Jiaotong University Weihai ChinaState Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin ChinaSchool of Navigation and Shipping Shandong Jiaotong University Weihai ChinaTAMS (Technical Aspects of Multimodal Systems) Group University of Hamburg Hamburg GermanyAbstract Segmentation of demonstration trajectories and learning the contained motion primitives can effectively enhance the assistive robot's intelligence to flexibly reproduce learnt tasks in an unstructured environment. With the aim to conveniently and accurately segment demonstration trajectories, a novel demonstration trajectory segmentation approach is proposed based on the beta process autoregressive hidden Markov model (BP‐AR‐HMM) algorithm and generalised time warping (GTW) algorithm aiming to enhance the segmentation accuracy utilising acquired demonstration data. This approach first adopts the GTW algorithm to align the multiple demonstration trajectories for the same task. Then, it adopts the BP‐AR‐HMM algorithm to segment the demonstration trajectories, acquire the contained motion primitives, and establish the related task library. This segmentation approach is validated on the 6‐degree‐of‐freedom JACO robotic arm by assisting users to accomplish a holding water glass task and an eating task. The experimental results show that the motion primitives within the trajectories can be correctly segmented with a high segmentation accuracy.https://doi.org/10.1049/cit2.12358assistive robotsmotion primitivespersonal caretrajectory segmentationwheelchair‐mounted robotic arm
spellingShingle Mingshan Chi
Yaxin Liu
Qiang Zhang
Chao Zeng
A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
CAAI Transactions on Intelligence Technology
assistive robots
motion primitives
personal care
trajectory segmentation
wheelchair‐mounted robotic arm
title A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
title_full A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
title_fullStr A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
title_full_unstemmed A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
title_short A demonstration trajectory segmentation approach for wheelchair‐mounted assistive robots
title_sort demonstration trajectory segmentation approach for wheelchair mounted assistive robots
topic assistive robots
motion primitives
personal care
trajectory segmentation
wheelchair‐mounted robotic arm
url https://doi.org/10.1049/cit2.12358
work_keys_str_mv AT mingshanchi ademonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT yaxinliu ademonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT qiangzhang ademonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT chaozeng ademonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT mingshanchi demonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT yaxinliu demonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT qiangzhang demonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots
AT chaozeng demonstrationtrajectorysegmentationapproachforwheelchairmountedassistiverobots