Pub Date : 2020-09-01DOI: 10.1109/ICHMS49158.2020.9209352
Quentin Houbre, Alexandre Angleraud, R. Pieters
The modelling of cognition is fundamental to designing robots that are increasingly more autonomous. Indeed, researchers take inspiration from human and animal cognition in order to endow robots with the ability to learn and adapt to their environment. In specific cases, the robot has to find the right compromise between exploring the environment, or exploiting its own experience to advance its knowledge of a skill. Our approach considers a neurally-inspired model to learning sensorimotor contingencies based on exploration and exploitation. For the exploration, an inhibition of return mechanism is implemented that generates new actions. In this work, we investigate how the tuning of the inhibition of return affects the exploratory behavior. To do so, we set up an experiment where a 3D printed humanoid robot arm GummiArm has to learn how to move a baby mobile toy with only a visual feedback. The results demonstrate that the tuning of the inhibition of return influences the exploratory behavior, leading to a faster learning of sensorimotor contingencies as well as the exploration of a reduced motor space.
{"title":"An Inhibition of Return Mechanism for the Exploration of Sensorimotor Contingencies","authors":"Quentin Houbre, Alexandre Angleraud, R. Pieters","doi":"10.1109/ICHMS49158.2020.9209352","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209352","url":null,"abstract":"The modelling of cognition is fundamental to designing robots that are increasingly more autonomous. Indeed, researchers take inspiration from human and animal cognition in order to endow robots with the ability to learn and adapt to their environment. In specific cases, the robot has to find the right compromise between exploring the environment, or exploiting its own experience to advance its knowledge of a skill. Our approach considers a neurally-inspired model to learning sensorimotor contingencies based on exploration and exploitation. For the exploration, an inhibition of return mechanism is implemented that generates new actions. In this work, we investigate how the tuning of the inhibition of return affects the exploratory behavior. To do so, we set up an experiment where a 3D printed humanoid robot arm GummiArm has to learn how to move a baby mobile toy with only a visual feedback. The results demonstrate that the tuning of the inhibition of return influences the exploratory behavior, leading to a faster learning of sensorimotor contingencies as well as the exploration of a reduced motor space.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"1 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":"130467537","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/ICHMS49158.2020.9209501
Daniel Alejandro Gonzalez Rueda, D. Mendonça
Recent work on the topic of Interactive Optimization has explored opportunities for exploiting human perceptual and cognitive capabilities within frameworks traditionally associated with mathematical optimization. We flip this perspective in order to consider these same basic issues from a human-centered perspective: that is, we identify the opportunities (and challenges) for exploiting methods associated with mathematical optimization models within a framework of human decision making capabilities, as exemplified by complex, dynamic, and ill-structured problems.The paper examines these issues through the lens of Extreme Event (XE) decision making, where XE are defined as events that are rare and severe and create deep changes in society and are rapidly occurring and must be addressed through careful planning but also ingenuity, with little to no opportunity for revisiting prior decisions. Given this reframing, a human centered taxonomy of opportunities for supporting XE decision making is taken as a starting point. In contrast are cast three different methodological approaches to Interactive Optimization, leading to a discussion of the potential of these approaches to supporting XE decision making. The paper concludes with a discussion of prospects and challenges for future work in this area.
{"title":"A Human-centered Perspective on Interactive Optimization for Extreme Event Decision Making","authors":"Daniel Alejandro Gonzalez Rueda, D. Mendonça","doi":"10.1109/ICHMS49158.2020.9209501","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209501","url":null,"abstract":"Recent work on the topic of Interactive Optimization has explored opportunities for exploiting human perceptual and cognitive capabilities within frameworks traditionally associated with mathematical optimization. We flip this perspective in order to consider these same basic issues from a human-centered perspective: that is, we identify the opportunities (and challenges) for exploiting methods associated with mathematical optimization models within a framework of human decision making capabilities, as exemplified by complex, dynamic, and ill-structured problems.The paper examines these issues through the lens of Extreme Event (XE) decision making, where XE are defined as events that are rare and severe and create deep changes in society and are rapidly occurring and must be addressed through careful planning but also ingenuity, with little to no opportunity for revisiting prior decisions. Given this reframing, a human centered taxonomy of opportunities for supporting XE decision making is taken as a starting point. In contrast are cast three different methodological approaches to Interactive Optimization, leading to a discussion of the potential of these approaches to supporting XE decision making. The paper concludes with a discussion of prospects and challenges for future work in this area.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"45 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":"129655247","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/ICHMS49158.2020.9209393
Jessica Leoni, M. Tanelli, S. Strada, Kaijun Jiang, A. Brusa, A. Proverbio
Brain-computer interfaces (BCIs) are systems initially designed to compensate for motor disabilities affecting people whose control of the muscular system is compromised. However, recent developments open the BCIs market to a wide range of medical and non-medical applications. This raises the need for systems capable of interpreting more and more stimuli, even from different sensory domains. In this work, we design a machine-learning system able to fit both application domains accurately recognizing visual and auditory stimuli starting from the event-related potentials (ERPs) they generate. The obtained results are promising and some practical and realization aspects are discussed.
{"title":"Automatic stimuli classification from ERP data for augmented communication via Brain-Computer Interfaces","authors":"Jessica Leoni, M. Tanelli, S. Strada, Kaijun Jiang, A. Brusa, A. Proverbio","doi":"10.1109/ICHMS49158.2020.9209393","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209393","url":null,"abstract":"Brain-computer interfaces (BCIs) are systems initially designed to compensate for motor disabilities affecting people whose control of the muscular system is compromised. However, recent developments open the BCIs market to a wide range of medical and non-medical applications. This raises the need for systems capable of interpreting more and more stimuli, even from different sensory domains. In this work, we design a machine-learning system able to fit both application domains accurately recognizing visual and auditory stimuli starting from the event-related potentials (ERPs) they generate. The obtained results are promising and some practical and realization aspects are discussed.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"166 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":"132906229","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/ICHMS49158.2020.9209384
F. Villanueva, Óscar Aceña, Javier Dorado, Rubén Cantarero, Jesús Fernández-Bermejo Ruiz, A. Rubio
Inherited from industry 4.0 domain, digital twin concept will represent an important step forward in what we have understood as smart city concept. In this paper we present our ongoing work on extending a monitoring smart city middleware to a digital twin platform for smart cities. The reader will learn some key issues of this new concept in the field of smart cities including some open questions that need to be investigated about the user interaction with digital twin concept.
{"title":"On building support of digital twin concept for smart spaces","authors":"F. Villanueva, Óscar Aceña, Javier Dorado, Rubén Cantarero, Jesús Fernández-Bermejo Ruiz, A. Rubio","doi":"10.1109/ICHMS49158.2020.9209384","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209384","url":null,"abstract":"Inherited from industry 4.0 domain, digital twin concept will represent an important step forward in what we have understood as smart city concept. In this paper we present our ongoing work on extending a monitoring smart city middleware to a digital twin platform for smart cities. The reader will learn some key issues of this new concept in the field of smart cities including some open questions that need to be investigated about the user interaction with digital twin concept.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"50 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":"133618298","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/ICHMS49158.2020.9209380
Steve Mann, Phillip V. Do, D. Garcia, J. Hernandez, Humza Khokhar
The purpose of this work is to harness the creative energy of the subconscious mind, to perform useful work while meditating, daydreaming, lucid dreaming, and the like. One of our ultimate goals is “jobbing on the sleep”, an inverse or reciprocal to “sleeping on the job”. We present, as the first step in this direction, an experimental apparatus for inducing and measuring steady-state visually evoked potentials (SSVEPs), where the subject concentrates on the rotating pattern that is mounted to the shaft of an electric motor. Essentially, we prove that human-in-the-loop meditation and visual attention exercises as a user concentrates on the rotating pattern results in some degree of SSVEP response.
{"title":"Electrical Engineering Design with the Subconscious Mind","authors":"Steve Mann, Phillip V. Do, D. Garcia, J. Hernandez, Humza Khokhar","doi":"10.1109/ICHMS49158.2020.9209380","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209380","url":null,"abstract":"The purpose of this work is to harness the creative energy of the subconscious mind, to perform useful work while meditating, daydreaming, lucid dreaming, and the like. One of our ultimate goals is “jobbing on the sleep”, an inverse or reciprocal to “sleeping on the job”. We present, as the first step in this direction, an experimental apparatus for inducing and measuring steady-state visually evoked potentials (SSVEPs), where the subject concentrates on the rotating pattern that is mounted to the shaft of an electric motor. Essentially, we prove that human-in-the-loop meditation and visual attention exercises as a user concentrates on the rotating pattern results in some degree of SSVEP response.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"1 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":"130148443","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/ICHMS49158.2020.9209526
Diogo Ferreira, M. Antunes, D. Gomes, R. Aguiar
Reinforcement Learning has seen some interesting development over the last years, which made it very attractive to use on recommendation scenarios. In this work, we have extended the previously developed pervasive system, which is aware of the conversational context to suggest documents potentially useful to the users, with the ability to use users’ click data as a way to perform better suggestions over time, through a Reinforcement Learning approach. Furthermore, to assure the real significance of these types of approaches in conversational environments, we also conducted a case study regarding the accuracy of feedback on context limited conversational systems.
{"title":"Applying Reinforcement Learning in Context Limited Environments","authors":"Diogo Ferreira, M. Antunes, D. Gomes, R. Aguiar","doi":"10.1109/ICHMS49158.2020.9209526","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209526","url":null,"abstract":"Reinforcement Learning has seen some interesting development over the last years, which made it very attractive to use on recommendation scenarios. In this work, we have extended the previously developed pervasive system, which is aware of the conversational context to suggest documents potentially useful to the users, with the ability to use users’ click data as a way to perform better suggestions over time, through a Reinforcement Learning approach. Furthermore, to assure the real significance of these types of approaches in conversational environments, we also conducted a case study regarding the accuracy of feedback on context limited conversational systems.","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":"123603566","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/ICHMS49158.2020.9209550
Jiufang Chen, Xin Luo, Mengchu Zhou
Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.
{"title":"A Regularization-adaptive Non-negative Latent Factor Analysis-based Model For Recommender Systems","authors":"Jiufang Chen, Xin Luo, Mengchu Zhou","doi":"10.1109/ICHMS49158.2020.9209550","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209550","url":null,"abstract":"Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"1 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":"128832959","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/ICHMS49158.2020.9209547
K. McClenaghan, Ole Christian Moholth, Jan Dyre Bjerknes
This research explores possibilities of creating software architectures for managing multiple autonomous objects in computational environments, which move away from clouds and use computational power of objects, at the edge of computing and communication networks. The emphasis is on shaping the behaviour of autonomous objects through human involvement in order to manipulate functions and change the purpose and levels of autonomy of these objects. The proposed computational model, generated from the software architectures, which gives rise to serverless and edge computing, should work across problem domain. By collecting relevant data and allowing a variable level of human input, the solution will enable us to choose, merge and combine multiple objects for a variety of tasks and according to environments in which autonomous objects reside.
{"title":"Computational Edge for Multiple Autonomous Objects","authors":"K. McClenaghan, Ole Christian Moholth, Jan Dyre Bjerknes","doi":"10.1109/ICHMS49158.2020.9209547","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209547","url":null,"abstract":"This research explores possibilities of creating software architectures for managing multiple autonomous objects in computational environments, which move away from clouds and use computational power of objects, at the edge of computing and communication networks. The emphasis is on shaping the behaviour of autonomous objects through human involvement in order to manipulate functions and change the purpose and levels of autonomy of these objects. The proposed computational model, generated from the software architectures, which gives rise to serverless and edge computing, should work across problem domain. By collecting relevant data and allowing a variable level of human input, the solution will enable us to choose, merge and combine multiple objects for a variety of tasks and according to environments in which autonomous objects reside.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"10 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":"126366137","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/ICHMS49158.2020.9209582
Giannis Petousakis, Manolis Chiou, Grigoris Nikolaou, R. Stolkin
This paper presents a Cognitive Availability Aware Mixed-Initiative Controller for remotely operated mobile robots. The controller enables dynamic switching between different levels of autonomy (LOA), initiated by either the AI and/or the human operator. The controller leverages a state-of-the-art computer vision method and an off-the-shelf web camera to infer the cognitive availability of the operator and inform the AI-initiated LOA switching. This constitutes a qualitative advancement over previous Mixed-Initiative (MI) controllers. The controller is evaluated in a disaster response experiment, in which human operators have to conduct an exploration task with a remote robot. MI systems are shown to effectively assist the operators, as demonstrated by quantitative and qualitative results in performance and workload. Additionally, some insights into the experimental difficulties of evaluating complex MI controllers are presented.
{"title":"Human operator cognitive availability aware Mixed-Initiative control","authors":"Giannis Petousakis, Manolis Chiou, Grigoris Nikolaou, R. Stolkin","doi":"10.1109/ICHMS49158.2020.9209582","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209582","url":null,"abstract":"This paper presents a Cognitive Availability Aware Mixed-Initiative Controller for remotely operated mobile robots. The controller enables dynamic switching between different levels of autonomy (LOA), initiated by either the AI and/or the human operator. The controller leverages a state-of-the-art computer vision method and an off-the-shelf web camera to infer the cognitive availability of the operator and inform the AI-initiated LOA switching. This constitutes a qualitative advancement over previous Mixed-Initiative (MI) controllers. The controller is evaluated in a disaster response experiment, in which human operators have to conduct an exploration task with a remote robot. MI systems are shown to effectively assist the operators, as demonstrated by quantitative and qualitative results in performance and workload. Additionally, some insights into the experimental difficulties of evaluating complex MI controllers are presented.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"1 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":"127595407","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/ICHMS49158.2020.9209533
A. Zanchettin, M. Marconi, Carlo Ongini, Roberto Rossi, P. Rocco
The increasing interest in collaborative robotics applications is mainly due to the flexibility of these robots and to the possibility of saving space on the production shopfloor. On the other hand, physical collaboration is way far from being a commonly adopted practice, and most of the applications only entails a reduced level of interaction. This work addresses the problem of synchronising human and robot activities and proposes a formal control architecture to govern the execution of collaborative application requiring some degree of coordination between the human and the robot. The control architecture is then validated in a realistic collaborative assembly demonstration.
{"title":"A Formal Control Architecture for Collaborative Robotics Applications","authors":"A. Zanchettin, M. Marconi, Carlo Ongini, Roberto Rossi, P. Rocco","doi":"10.1109/ICHMS49158.2020.9209533","DOIUrl":"https://doi.org/10.1109/ICHMS49158.2020.9209533","url":null,"abstract":"The increasing interest in collaborative robotics applications is mainly due to the flexibility of these robots and to the possibility of saving space on the production shopfloor. On the other hand, physical collaboration is way far from being a commonly adopted practice, and most of the applications only entails a reduced level of interaction. This work addresses the problem of synchronising human and robot activities and proposes a formal control architecture to govern the execution of collaborative application requiring some degree of coordination between the human and the robot. The control architecture is then validated in a realistic collaborative assembly demonstration.","PeriodicalId":132917,"journal":{"name":"2020 IEEE International Conference on Human-Machine Systems (ICHMS)","volume":"103 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":"127657490","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：