Study on quality evaluation of human motion dataset in manufacturing scenario

This study presents a comprehensive framework for evaluating the quality of human manipulation datasets in contributing to efficient human-robot collaboration (HRC) in manufacturing settings. Recognizing the importance of safety and efficiency, we want to achieve the development of robotic systems c...

Full description

Bibliographic Details
Main Author: Nabeel Muhammad Bin Abu Bakar
Other Authors: Su Rong
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/177211
_version_ 1826128818294751232
author Nabeel Muhammad Bin Abu Bakar
author2 Su Rong
author_facet Su Rong
Nabeel Muhammad Bin Abu Bakar
author_sort Nabeel Muhammad Bin Abu Bakar
collection NTU
description This study presents a comprehensive framework for evaluating the quality of human manipulation datasets in contributing to efficient human-robot collaboration (HRC) in manufacturing settings. Recognizing the importance of safety and efficiency, we want to achieve the development of robotic systems capable of planning safe trajectories in anticipation of human actions. We assert that the quality of human motion prediction is contingent upon the quality of the underlying datasets, and thus our work proposes methodologies for appraising human manipulation video datasets based on their adequacy for human landmark extraction, which ultimately impacts their transferability to subsequent analytical models. We examine several intricate assembly operations, then extract relevant human skeletal data and implement a spatiotemporal analysis for effective sample validation and scenario categorization. From this, we extract out the duration taken to complete assembly tasks in an attempt to predict the next task completion duration, allowing for better HRC.
first_indexed 2024-10-01T07:31:03Z
format Final Year Project (FYP)
id ntu-10356/177211
institution Nanyang Technological University
language English
last_indexed 2024-10-01T07:31:03Z
publishDate 2024
publisher Nanyang Technological University
record_format dspace
spelling ntu-10356/1772112024-05-31T15:44:39Z Study on quality evaluation of human motion dataset in manufacturing scenario Nabeel Muhammad Bin Abu Bakar Su Rong School of Electrical and Electronic Engineering Schaeffler Hub for Advanced REsearch (SHARE) Lab RSu@ntu.edu.sg Engineering Dataset quality evaluation Human manipulation This study presents a comprehensive framework for evaluating the quality of human manipulation datasets in contributing to efficient human-robot collaboration (HRC) in manufacturing settings. Recognizing the importance of safety and efficiency, we want to achieve the development of robotic systems capable of planning safe trajectories in anticipation of human actions. We assert that the quality of human motion prediction is contingent upon the quality of the underlying datasets, and thus our work proposes methodologies for appraising human manipulation video datasets based on their adequacy for human landmark extraction, which ultimately impacts their transferability to subsequent analytical models. We examine several intricate assembly operations, then extract relevant human skeletal data and implement a spatiotemporal analysis for effective sample validation and scenario categorization. From this, we extract out the duration taken to complete assembly tasks in an attempt to predict the next task completion duration, allowing for better HRC. Bachelor's degree 2024-05-27T01:45:58Z 2024-05-27T01:45:58Z 2024 Final Year Project (FYP) Nabeel Muhammad Bin Abu Bakar (2024). Study on quality evaluation of human motion dataset in manufacturing scenario. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177211 https://hdl.handle.net/10356/177211 en application/pdf Nanyang Technological University
spellingShingle Engineering
Dataset quality evaluation
Human manipulation
Nabeel Muhammad Bin Abu Bakar
Study on quality evaluation of human motion dataset in manufacturing scenario
title Study on quality evaluation of human motion dataset in manufacturing scenario
title_full Study on quality evaluation of human motion dataset in manufacturing scenario
title_fullStr Study on quality evaluation of human motion dataset in manufacturing scenario
title_full_unstemmed Study on quality evaluation of human motion dataset in manufacturing scenario
title_short Study on quality evaluation of human motion dataset in manufacturing scenario
title_sort study on quality evaluation of human motion dataset in manufacturing scenario
topic Engineering
Dataset quality evaluation
Human manipulation
url https://hdl.handle.net/10356/177211
work_keys_str_mv AT nabeelmuhammadbinabubakar studyonqualityevaluationofhumanmotiondatasetinmanufacturingscenario