Pub Date : 1900-01-01DOI: 10.1109/MetroAutomotive50197.2021.9502873
S. Rahman
A human-robot collaborative system was developed where a human co-worker and a collaborative robot collaborated to perform assembly tasks. We assumed such assembly tasks as the representative assembly tasks in the automotive manufacturing industry. We assumed that the collaborative assembly system would be a part of an industrial control system (ICS) in actual industrial environment. We recruited 20 human subjects to perform the assembly tasks in collaboration with the robot. We trained the subjects to enable them to perform the collaborative assembly tasks, and evaluate cybersecurity conditions (status) of the collaborative system. Each subject performed the collaborative assembly separately with the robot. At the end of the assembly task, each subject was asked to brainstorm, write down the cybersecurity assessment criteria as best as he/she could perceive or realize through his/her experiences with the collaborative system, and rate the cybersecurity status of the collaborative system for each of the criteria (i.e., how capable the collaborative system was in fulfilling the cybersecurity requirements for each criterion) using a five-point subjective rating scale (a Likert scale), where 1 indicated the least and 5 indicated the most secured system. We then analyzed the responses and determined a list of the tentative cybersecurity assessment criteria with their relative importance (the total frequency of each criterion proposed by the subjects was to indicate the importance level for that criterion). We also proposed how machine learning and data analytics could be applied to analyze the cybersecurity metrics and enhance cybersecurity in the collaborative system. The proposed cybersecurity metrics can serve as the preliminary effort towards developing comprehensive cybersecurity metrics and methods for human-robot collaborative assembly in automotive manufacturing in particular and for human-robot collaborative systems in general.
{"title":"Cybersecurity Metrics for Human-Robot Collaborative Automotive Manufacturing","authors":"S. Rahman","doi":"10.1109/MetroAutomotive50197.2021.9502873","DOIUrl":"https://doi.org/10.1109/MetroAutomotive50197.2021.9502873","url":null,"abstract":"A human-robot collaborative system was developed where a human co-worker and a collaborative robot collaborated to perform assembly tasks. We assumed such assembly tasks as the representative assembly tasks in the automotive manufacturing industry. We assumed that the collaborative assembly system would be a part of an industrial control system (ICS) in actual industrial environment. We recruited 20 human subjects to perform the assembly tasks in collaboration with the robot. We trained the subjects to enable them to perform the collaborative assembly tasks, and evaluate cybersecurity conditions (status) of the collaborative system. Each subject performed the collaborative assembly separately with the robot. At the end of the assembly task, each subject was asked to brainstorm, write down the cybersecurity assessment criteria as best as he/she could perceive or realize through his/her experiences with the collaborative system, and rate the cybersecurity status of the collaborative system for each of the criteria (i.e., how capable the collaborative system was in fulfilling the cybersecurity requirements for each criterion) using a five-point subjective rating scale (a Likert scale), where 1 indicated the least and 5 indicated the most secured system. We then analyzed the responses and determined a list of the tentative cybersecurity assessment criteria with their relative importance (the total frequency of each criterion proposed by the subjects was to indicate the importance level for that criterion). We also proposed how machine learning and data analytics could be applied to analyze the cybersecurity metrics and enhance cybersecurity in the collaborative system. The proposed cybersecurity metrics can serve as the preliminary effort towards developing comprehensive cybersecurity metrics and methods for human-robot collaborative assembly in automotive manufacturing in particular and for human-robot collaborative systems in general.","PeriodicalId":193358,"journal":{"name":"International Workshop on Metrology for Automotive","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114368395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/MetroAutomotive50197.2021.9502881
S. Rahman
A human-robot collaborative system in the form of a power and skill assist robotic system was developed where a human and a robot could collaborate to perform object manipulation for targeted assembly tasks in automotive manufacturing. We assumed such assembly tasks as the representative assembly tasks in automotive manufacturing. We reflected human’s weight perception in the dynamics and control of the power and skill assist system following a psychophysical method using a reinforcement learning scheme. We recruited 20 human subjects who separately performed assembly tasks with the system in human-robot collaboration (HRC). We then observed the collaborative assembly tasks, conducted extensive literature reviews, reviewed our previous and ongoing related works and brainstormed with the subjects and other relevant researchers, and then proposed HRC performance assessment metrics and methods for collaborative automotive manufacturing. The proposed metrics comprised of assessment criteria and methods related to both human-robot interaction (HRI) and manufacturing performance. We then verified the proposed performance metrics in pilot studies in the laboratory environment using the same collaborative system and subjects. The verification results proved the effectiveness of the assessment metrics and methods in terms of usability, practicability and reliability. We then proposed to apply classification and regression type machine learning approaches under supervised and reinforcement learning setups to learn different classes and decision-making rules respectively regarding HRC performance. The proposed performance metrics and methods can serve as the preliminary efforts towards developing comprehensive assessment metrics for HRC in general and for human-robot collaborative automotive manufacturing in particular.
{"title":"Performance Metrics for Human-Robot Collaboration: An Automotive Manufacturing Case","authors":"S. Rahman","doi":"10.1109/MetroAutomotive50197.2021.9502881","DOIUrl":"https://doi.org/10.1109/MetroAutomotive50197.2021.9502881","url":null,"abstract":"A human-robot collaborative system in the form of a power and skill assist robotic system was developed where a human and a robot could collaborate to perform object manipulation for targeted assembly tasks in automotive manufacturing. We assumed such assembly tasks as the representative assembly tasks in automotive manufacturing. We reflected human’s weight perception in the dynamics and control of the power and skill assist system following a psychophysical method using a reinforcement learning scheme. We recruited 20 human subjects who separately performed assembly tasks with the system in human-robot collaboration (HRC). We then observed the collaborative assembly tasks, conducted extensive literature reviews, reviewed our previous and ongoing related works and brainstormed with the subjects and other relevant researchers, and then proposed HRC performance assessment metrics and methods for collaborative automotive manufacturing. The proposed metrics comprised of assessment criteria and methods related to both human-robot interaction (HRI) and manufacturing performance. We then verified the proposed performance metrics in pilot studies in the laboratory environment using the same collaborative system and subjects. The verification results proved the effectiveness of the assessment metrics and methods in terms of usability, practicability and reliability. We then proposed to apply classification and regression type machine learning approaches under supervised and reinforcement learning setups to learn different classes and decision-making rules respectively regarding HRC performance. The proposed performance metrics and methods can serve as the preliminary efforts towards developing comprehensive assessment metrics for HRC in general and for human-robot collaborative automotive manufacturing in particular.","PeriodicalId":193358,"journal":{"name":"International Workshop on Metrology for Automotive","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125926460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：