Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209435
Victoria Buchholz, S. Kopp
With the introduction of more and more autonomous machines into the work environment, the role of a worker changes from the sole executor of a task to the observer and supervisor of a system that carries out tasks on her behalf. Often, the transparency and predictability of these systems decrease, making it difficult to comprehend underlying processes for the worker. Moreover, monitoring tasks can impose different levels of workload on the human operator leading to an increased risk of making serious errors. The present research aims at developing an adaptive assistance system for these types of tasks that is able to monitor a worker’s current level of mental workload and provides support without reducing the worker’s autonomy and sense of responsibility. We report results of an experiment using a monitoring task incorporating repeated event sequences to simulate underlying workings of a complex system. Results show that performance in connection with eye-tracking measures are suitable indicators of the level of mental workload and that making the worker aware of underlying structures may reduce workload. Further steps towards an adaptive assistance system for monitoring tasks are discussed.
{"title":"Towards an Adaptive Assistance System for Monitoring Tasks: Assessing Mental Workload using Eye-Tracking and Performance Measures","authors":"Victoria Buchholz, S. Kopp","doi":"10.1109/ICHMS49158.2020.9209435","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209435","url":null,"abstract":"With the introduction of more and more autonomous machines into the work environment, the role of a worker changes from the sole executor of a task to the observer and supervisor of a system that carries out tasks on her behalf. Often, the transparency and predictability of these systems decrease, making it difficult to comprehend underlying processes for the worker. Moreover, monitoring tasks can impose different levels of workload on the human operator leading to an increased risk of making serious errors. The present research aims at developing an adaptive assistance system for these types of tasks that is able to monitor a worker’s current level of mental workload and provides support without reducing the worker’s autonomy and sense of responsibility. We report results of an experiment using a monitoring task incorporating repeated event sequences to simulate underlying workings of a complex system. Results show that performance in connection with eye-tracking measures are suitable indicators of the level of mental workload and that making the worker aware of underlying structures may reduce workload. Further steps towards an adaptive assistance system for monitoring tasks are discussed.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116925431","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209558
Piotr Fratczak, Y. Goh, P. Kinnell, L. Justham, Andrea Soltoggio
Modern industrial automation may benefit from humans and robots collaborating with each other in a shared workspace. Even though collaborative robots are often designed to be physically safe, mental and emotional well-being of humans working with industrial robots, as well as the fluency of collaboration, are rarely considered. This study uses Pimax 5k+ Virtual Reality headset to study human behaviours in a potential collaborative task, where a human and a robot work at the same time on the same workpiece. The human’s motion and physiological responses were collected from the VR equipment, wearable Zephyr Biomodule sensor and a subjective questionnaire. The results show that some people can easily adapt to the robot and work fluently even when it speeds up, while others fail to keep up with it and give up any attempts to collaborate. It was shown that participants, who fail to keep up with the robot can often be detected before they give up. This study shows not only the need to adapt the robot’s behaviour (especially its speed) to each worker individually, but also the possibility to use human motion and physiological data to predict which worker is going to require additional support to improve the collaboration.
{"title":"Virtual Reality Study of Human Adaptability in Industrial Human-Robot Collaboration","authors":"Piotr Fratczak, Y. Goh, P. Kinnell, L. Justham, Andrea Soltoggio","doi":"10.1109/ICHMS49158.2020.9209558","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209558","url":null,"abstract":"Modern industrial automation may benefit from humans and robots collaborating with each other in a shared workspace. Even though collaborative robots are often designed to be physically safe, mental and emotional well-being of humans working with industrial robots, as well as the fluency of collaboration, are rarely considered. This study uses Pimax 5k+ Virtual Reality headset to study human behaviours in a potential collaborative task, where a human and a robot work at the same time on the same workpiece. The human’s motion and physiological responses were collected from the VR equipment, wearable Zephyr Biomodule sensor and a subjective questionnaire. The results show that some people can easily adapt to the robot and work fluently even when it speeds up, while others fail to keep up with it and give up any attempts to collaborate. It was shown that participants, who fail to keep up with the robot can often be detected before they give up. This study shows not only the need to adapt the robot’s behaviour (especially its speed) to each worker individually, but also the possibility to use human motion and physiological data to predict which worker is going to require additional support to improve the collaboration.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131976947","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209423
Rune Stensrud, Sigmund Valaker, Torgar Haugen
In the paper we briefly discuss principles for designing multi-team collaboration, specifically coordination, which include man and machine components, focusing on interdependence and emergent dynamics of work flow. To shed light on these design principles and discuss it in an empirical context we use a case from military information processing, specifically a NATO Exercise where multiple teams collaborated to do tasking, collection, processing, exploitation and dissemination (TCPED) in support of Joint intelligence, surveillance and reconnaissance (JISR). The case indicated that the interdependencies became increasingly complex over time, but there was not planning tools in place to support the management of the multi-team coordination. Implications for further conceptual and design work is suggested, such as developing further the consideration of soft and hard interdependencies, going from an inward look to consider the influence of the external environment and the role of trust, and development of task assignment tools.
{"title":"Interdependence as an Element of the Design of a Federated Work Process","authors":"Rune Stensrud, Sigmund Valaker, Torgar Haugen","doi":"10.1109/ICHMS49158.2020.9209423","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209423","url":null,"abstract":"In the paper we briefly discuss principles for designing multi-team collaboration, specifically coordination, which include man and machine components, focusing on interdependence and emergent dynamics of work flow. To shed light on these design principles and discuss it in an empirical context we use a case from military information processing, specifically a NATO Exercise where multiple teams collaborated to do tasking, collection, processing, exploitation and dissemination (TCPED) in support of Joint intelligence, surveillance and reconnaissance (JISR). The case indicated that the interdependencies became increasingly complex over time, but there was not planning tools in place to support the management of the multi-team coordination. Implications for further conceptual and design work is suggested, such as developing further the consideration of soft and hard interdependencies, going from an inward look to consider the influence of the external environment and the role of trust, and development of task assignment tools.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134175584","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209450
M. Askarpour, Livia Lestingi, Federico Buran, M. Rossi, F. Vicentini
In human-robot collaboration (HRC), humans and robots share the same workspace while executing hybrid tasks. Their close proximity imposes higher possibility of contacts that could potentially be dangerous. Hence, physical safety and risk analysis become of utmost importance during system design.In this paper, we propose a tool-supported interactive technique that facilitates the design of safe HRC systems for designers by performing iterative risk analysis and suggesting risk reduction measures (RRMs) to mitigate unsafe physical contacts.
{"title":"Model-driven Risk Analysis for the Design of Safe Collaborative Robotic Applications","authors":"M. Askarpour, Livia Lestingi, Federico Buran, M. Rossi, F. Vicentini","doi":"10.1109/ICHMS49158.2020.9209450","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209450","url":null,"abstract":"In human-robot collaboration (HRC), humans and robots share the same workspace while executing hybrid tasks. Their close proximity imposes higher possibility of contacts that could potentially be dangerous. Hence, physical safety and risk analysis become of utmost importance during system design.In this paper, we propose a tool-supported interactive technique that facilitates the design of safe HRC systems for designers by performing iterative risk analysis and suggesting risk reduction measures (RRMs) to mitigate unsafe physical contacts.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133769176","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209457
S. D'amico, Giovanna Stella, S. Gagliano, M. Bucolo, R. Roche
To identify neuroanatomical abnormalities in the brains of people with psychosis, schizophrenia or children experiencing PLEs have been detected atypical activity levels in specific brain regions using fMRI or event-related potentials analysis. Both of these approaches suffer from drawbacks. In this study using EEG signals, the method implemented surpasses the limitations of both. The proposed method combines advanced signal processing, in time and frequency domain, with graph analysis and evaluates the inference across subjects. The first part of the procedure consists of a data preparation phase and of a data analysis phase, based on functional connectivity evaluation using the peak correlation methods. The second part takes into account parametric and topological aspects of the brain network, extracted by the brain connectivity and the graph analysis, obtaining robust and clinically relevant information.
{"title":"Functional Connectivity Analysis by Trial in a Working Memory Task","authors":"S. D'amico, Giovanna Stella, S. Gagliano, M. Bucolo, R. Roche","doi":"10.1109/ICHMS49158.2020.9209457","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209457","url":null,"abstract":"To identify neuroanatomical abnormalities in the brains of people with psychosis, schizophrenia or children experiencing PLEs have been detected atypical activity levels in specific brain regions using fMRI or event-related potentials analysis. Both of these approaches suffer from drawbacks. In this study using EEG signals, the method implemented surpasses the limitations of both. The proposed method combines advanced signal processing, in time and frequency domain, with graph analysis and evaluates the inference across subjects. The first part of the procedure consists of a data preparation phase and of a data analysis phase, based on functional connectivity evaluation using the peak correlation methods. The second part takes into account parametric and topological aspects of the brain network, extracted by the brain connectivity and the graph analysis, obtaining robust and clinically relevant information.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128026668","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209522
Maria Stella de Biase, S. Marrone, F. Marulli
These last years have seen a rapid growth of applications able to interact with humans in a sophisticated way: mood interpretation and adaptation is the next research frontier and it gets closer day by day. This paper introduces a model-driven process able to automate the creation of modern Human-Machine Interfaces. In particular, by proposing a probabilistic extension of Dynamic State Machines, this paper explores the usage of such a formalism in the automatic generation of applications able to understand the mood of the user and to react at the best. The approach is applied to an example case study.
{"title":"Automatic Generation of Smart Human-Machine Interfaces","authors":"Maria Stella de Biase, S. Marrone, F. Marulli","doi":"10.1109/ICHMS49158.2020.9209522","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209522","url":null,"abstract":"These last years have seen a rapid growth of applications able to interact with humans in a sophisticated way: mood interpretation and adaptation is the next research frontier and it gets closer day by day. This paper introduces a model-driven process able to automate the creation of modern Human-Machine Interfaces. In particular, by proposing a probabilistic extension of Dynamic State Machines, this paper explores the usage of such a formalism in the automatic generation of applications able to understand the mood of the user and to react at the best. The approach is applied to an example case study.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133225552","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209449
Yao Guo, Raffaele Gravina, Xiao Gu, G. Fortino, Guang-Zhong Yang
The early detection of gait abnormalities plays a key role in medical applications, where most of the previous abnormal gait recognition methods rely on kinematic data captured with vision-based systems or wearable inertial sensors. This paper, conversely, puts forward the ambitious objective to employ multiple wearable Electromyography (EMG) sensors for gait abnormalities detection. Our proposed approach uses eight wireless EMG sensors attached with skin electrodes on four muscles (i.e., Tibialis Anterior, Peroneus Longus, Gas-trocnemius, and Rectus Femoris) per each leg to measure the muscle response during walking activity. In the recognition stage, both meta-features with SVM and Bidirectional Long Short-Term Machine (BiLSTM) are exploited for gait abnormalities recognition from raw EMG data, Discrete Wavelet Transform (DWT) coefficients, and the reconstructed EMG signals, respectively. Experimental results on our gait dataset demonstrate the efficacy of EMG-based abnormal gait detection and recognition.
{"title":"EMG-based Abnormal Gait Detection and Recognition","authors":"Yao Guo, Raffaele Gravina, Xiao Gu, G. Fortino, Guang-Zhong Yang","doi":"10.1109/ICHMS49158.2020.9209449","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209449","url":null,"abstract":"The early detection of gait abnormalities plays a key role in medical applications, where most of the previous abnormal gait recognition methods rely on kinematic data captured with vision-based systems or wearable inertial sensors. This paper, conversely, puts forward the ambitious objective to employ multiple wearable Electromyography (EMG) sensors for gait abnormalities detection. Our proposed approach uses eight wireless EMG sensors attached with skin electrodes on four muscles (i.e., Tibialis Anterior, Peroneus Longus, Gas-trocnemius, and Rectus Femoris) per each leg to measure the muscle response during walking activity. In the recognition stage, both meta-features with SVM and Bidirectional Long Short-Term Machine (BiLSTM) are exploited for gait abnormalities recognition from raw EMG data, Discrete Wavelet Transform (DWT) coefficients, and the reconstructed EMG signals, respectively. Experimental results on our gait dataset demonstrate the efficacy of EMG-based abnormal gait detection and recognition.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127661913","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209369
C. Castelfranchi
Are we ready for the anthropological revolution grounded on Intelligent Technologies and artificial mixed society? Which also is an economic, social, and political revolution. AI is not just building a new technology but a new Socio-Cognitive-Technical System, a new world and a new form of society and culture. It is an anthropological revolution. You are “social engineers”. Is our Intelligent Technology research only business oriented? AI should be more “science oriented”. As for possible dangers of AI impact there is a dominant limited view, focused only on ethical issues, and on Reliable and Transparent and ExplAInable AI. My question is political not just ethical: the AI revolution is empowering whom? AI can play a very important role “for freedom”. It can also be a revolutionary “Awareness technology”. It can improve not only personal and collective intelligence but collective awareness: understanding what we are doing and why we are doing that; who is “nudging” us.
{"title":"For a Science-oriented, Socially Responsible, and Self-aware AI: beyond ethical issues","authors":"C. Castelfranchi","doi":"10.1109/ICHMS49158.2020.9209369","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209369","url":null,"abstract":"Are we ready for the anthropological revolution grounded on Intelligent Technologies and artificial mixed society? Which also is an economic, social, and political revolution. AI is not just building a new technology but a new Socio-Cognitive-Technical System, a new world and a new form of society and culture. It is an anthropological revolution. You are “social engineers”. Is our Intelligent Technology research only business oriented? AI should be more “science oriented”. As for possible dangers of AI impact there is a dominant limited view, focused only on ethical issues, and on Reliable and Transparent and ExplAInable AI. My question is political not just ethical: the AI revolution is empowering whom? AI can play a very important role “for freedom”. It can also be a revolutionary “Awareness technology”. It can improve not only personal and collective intelligence but collective awareness: understanding what we are doing and why we are doing that; who is “nudging” us.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133155491","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209385
Kentaro Barhydt, Alphonsus Adu-Bredu, Sarah Everhart-Skeels, Gary Bedell, K. Panetta, W. Messner
This paper presents Cartbot, a low-cost assistive mobile manipulator robot with a minimal degree-of-freedom (DOF) design approach that allows people with tetraplegia complete manual control over its kinematics. Most assistive mobile manipulation research focuses on enabling control of complex robots with many DOFs using input devices with limited DOFs by offloading full or partial control onto an autonomous control system. Automating control denies the user complete agency over the robot’s behavior and therefore limits freedom of use. In contrast, our approach aims to allow the user direct-manipulation control over the entire system by minimizing the DOFs of the robot design. The Cartbot consists of a cylindrical manipulator, a differential drive system, and a shopping-cart-based chassis. Feedback from initial user testing was unanimously positive and supported the effectiveness of our design approach in terms of both freedom and ease of use.
{"title":"Cartbot: A Direct-Manipulation Minimal Degrees-of-Freedom Mobile Assistive Robot to Maximize User Agency","authors":"Kentaro Barhydt, Alphonsus Adu-Bredu, Sarah Everhart-Skeels, Gary Bedell, K. Panetta, W. Messner","doi":"10.1109/ICHMS49158.2020.9209385","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209385","url":null,"abstract":"This paper presents Cartbot, a low-cost assistive mobile manipulator robot with a minimal degree-of-freedom (DOF) design approach that allows people with tetraplegia complete manual control over its kinematics. Most assistive mobile manipulation research focuses on enabling control of complex robots with many DOFs using input devices with limited DOFs by offloading full or partial control onto an autonomous control system. Automating control denies the user complete agency over the robot’s behavior and therefore limits freedom of use. In contrast, our approach aims to allow the user direct-manipulation control over the entire system by minimizing the DOFs of the robot design. The Cartbot consists of a cylindrical manipulator, a differential drive system, and a shopping-cart-based chassis. Feedback from initial user testing was unanimously positive and supported the effectiveness of our design approach in terms of both freedom and ease of use.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133154034","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 : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209511
Zongyao Jin, P. Pagilla
In this paper, we propose a novel intent prediction method for shared control applications where the task is modeled via subgoals. The proposed method takes into consideration the human operator’s real-time action and updates the prediction model based on observed subgoal transitions. We describe the transition probabilities update law, its convergence property, and its effectiveness in reflecting observed subgoal transitions with constructed probabilities. Experiments were conducted on a physical platform using a hydraulic excavator for a trenching-and-loading task with human-machine shared control. Results corroborate the proposed method and indicate that it can effectively update the prediction model and better reflect subgoal transition probabilities based on observations.
{"title":"Operator Intent Prediction with Subgoal Transition Probability Learning for Shared Control Applications","authors":"Zongyao Jin, P. Pagilla","doi":"10.1109/ICHMS49158.2020.9209511","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209511","url":null,"abstract":"In this paper, we propose a novel intent prediction method for shared control applications where the task is modeled via subgoals. The proposed method takes into consideration the human operator’s real-time action and updates the prediction model based on observed subgoal transitions. We describe the transition probabilities update law, its convergence property, and its effectiveness in reflecting observed subgoal transitions with constructed probabilities. Experiments were conducted on a physical platform using a hydraulic excavator for a trenching-and-loading task with human-machine shared control. Results corroborate the proposed method and indicate that it can effectively update the prediction model and better reflect subgoal transition probabilities based on observations.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133197187","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：