Tian Zhou, M. E. Cabrera, J. Wachs, Thomas Low, C. Sundaram
This research presents an exploratory study among touch-based and touchless interfaces selected to teleoperate a highly dexterous surgical robot. The possibility of incorporating touchless interfaces into the surgical arena may provide surgeons with the ability to engage in telerobotic surgery similarly as if they were operating with their bare hands. On the other hand, precision and sensibility may be lost. To explore the advantages and drawbacks of these modalities, five interfaces were selected to send navigational commands to the Taurus robot in the system: Omega, Hydra, and a keyboard. The first represented touch-based, while Leap Motion and Kinect were selected as touchless interfaces. Three experimental designs were selected to test the system, based on standardized surgically related tasks and clinically relevant performance metrics measured to evaluate the user's performance, learning rates, control stability, and interaction naturalness. The current work provides a benchmark and validation framework for the comparison of these two groups of interfaces and discusses their potential for current and future adoption in the surgical setting.
{"title":"A comparative study for telerobotic surgery using free hand gestures","authors":"Tian Zhou, M. E. Cabrera, J. Wachs, Thomas Low, C. Sundaram","doi":"10.5898/JHRI.5.2.Zhou","DOIUrl":"https://doi.org/10.5898/JHRI.5.2.Zhou","url":null,"abstract":"This research presents an exploratory study among touch-based and touchless interfaces selected to teleoperate a highly dexterous surgical robot. The possibility of incorporating touchless interfaces into the surgical arena may provide surgeons with the ability to engage in telerobotic surgery similarly as if they were operating with their bare hands. On the other hand, precision and sensibility may be lost. To explore the advantages and drawbacks of these modalities, five interfaces were selected to send navigational commands to the Taurus robot in the system: Omega, Hydra, and a keyboard. The first represented touch-based, while Leap Motion and Kinect were selected as touchless interfaces. Three experimental designs were selected to test the system, based on standardized surgically related tasks and clinically relevant performance metrics measured to evaluate the user's performance, learning rates, control stability, and interaction naturalness. The current work provides a benchmark and validation framework for the comparison of these two groups of interfaces and discusses their potential for current and future adoption in the surgical setting.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.5.2.Zhou","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218524","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 : 2016-09-01DOI: 10.5898/JHRI.5.2.Van_den_Brule
Rik van den Brule, Gijsbert Bijlstra, R. Dotsch, Pim Haselager, D. Wigboldus
The present research was aimed at investigating whether human-robot interaction (HRI) can be improved by a robot's nonverbal warning signals. Ideally, when a robot signals that it cannot guarantee good performance, people could take preventive actions to ensure the successful completion of the robot's task. In two experiments, participants learned either that a robot's gestures predicted subsequent poor performance, or they did not. Participants evaluated a robot that uses predictive gestures as more trustworthy, understandable, and reliable compared to a robot that uses gestures that are not predictive of their performance. Finally, participants who learned the relation between gestures and performance improved collaboration with the robot through prevention behavior immediately after a predictive gesture. This limits the negative consequences of the robot's mistakes, thus improving the interaction.
{"title":"Warning signals for poor performance improve human-robot interaction","authors":"Rik van den Brule, Gijsbert Bijlstra, R. Dotsch, Pim Haselager, D. Wigboldus","doi":"10.5898/JHRI.5.2.Van_den_Brule","DOIUrl":"https://doi.org/10.5898/JHRI.5.2.Van_den_Brule","url":null,"abstract":"The present research was aimed at investigating whether human-robot interaction (HRI) can be improved by a robot's nonverbal warning signals. Ideally, when a robot signals that it cannot guarantee good performance, people could take preventive actions to ensure the successful completion of the robot's task. In two experiments, participants learned either that a robot's gestures predicted subsequent poor performance, or they did not. Participants evaluated a robot that uses predictive gestures as more trustworthy, understandable, and reliable compared to a robot that uses gestures that are not predictive of their performance. Finally, participants who learned the relation between gestures and performance improved collaboration with the robot through prevention behavior immediately after a predictive gesture. This limits the negative consequences of the robot's mistakes, thus improving the interaction.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.5.2.Van_den_Brule","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218440","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}
Human preferences of distance (proxemics) to a robot significantly impact the performance of the robot's automated speech and gesture recognition during face-to-face, social human-robot interactions. This work investigated how people respond to a sociable robot based on its performance at different locations. We performed an experiment in which the robot's ability to understand social signals was artificially attenuated by distance. Participants (N = 180) instructed the robot using speech and pointing gestures, provided proxemic preferences before and after the interaction, and responded to a questionnaire. Our analysis of questionnaire responses revealed that robot performance factors---rather than human-robot proxemics---are significant predictors of user evaluations of robot competence, anthropomorphism, engagement, likability, and technology adoption. Our behavioral analysis suggests that human proxemic preferences change over time as users interact with and come to understand the needs of the robot, and those changes improve robot performance.
{"title":"Robots have needs too","authors":"Ross Mead, M. Matarić","doi":"10.5898/JHRI.5.2.Mead","DOIUrl":"https://doi.org/10.5898/JHRI.5.2.Mead","url":null,"abstract":"Human preferences of distance (proxemics) to a robot significantly impact the performance of the robot's automated speech and gesture recognition during face-to-face, social human-robot interactions. This work investigated how people respond to a sociable robot based on its performance at different locations. We performed an experiment in which the robot's ability to understand social signals was artificially attenuated by distance. Participants (N = 180) instructed the robot using speech and pointing gestures, provided proxemic preferences before and after the interaction, and responded to a questionnaire. Our analysis of questionnaire responses revealed that robot performance factors---rather than human-robot proxemics---are significant predictors of user evaluations of robot competence, anthropomorphism, engagement, likability, and technology adoption. Our behavioral analysis suggests that human proxemic preferences change over time as users interact with and come to understand the needs of the robot, and those changes improve robot performance.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.5.2.Mead","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218425","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 : 2016-09-01DOI: 10.5898/JHRI.5.2.Yogeeswaran
K. Yogeeswaran, Jakub Złotowski, Megan Livingstone, C. Bartneck, H. Sumioka, H. Ishiguro
The present research examines how a robot's physical anthropomorphism interacts with perceived ability of robots to impact the level of realistic and identity threat that people perceive from robots and how it affects their support for robotics research. Experimental data revealed that participants perceived robots to be significantly more threatening to humans after watching a video of an android that could allegedly outperform humans on various physical and mental tasks relative to a humanoid robot that could do the same. However, when participants were not provided with information about a new generation of robots' ability relative to humans, then no significant differences were found in perceived threat following exposure to either the android or humanoid robots. Similarly, participants also expressed less support for robotics research after seeing an android relative to a humanoid robot outperform humans. However, when provided with no information about robots' ability relative to humans, then participants showed marginally decreased support for robotics research following exposure to the humanoid relative to the android robot. Taken together, these findings suggest that very humanlike robots can not only be perceived as a realistic threat to human jobs, safety, and resources, but can also be seen as a threat to human identity and uniqueness, especially if such robots also outperform humans. We also demonstrate the potential downside of such robots to the public's willingness to support and fund robotics research.
{"title":"The interactive effects of robot anthropomorphism and robot ability on perceived threat and support for robotics research","authors":"K. Yogeeswaran, Jakub Złotowski, Megan Livingstone, C. Bartneck, H. Sumioka, H. Ishiguro","doi":"10.5898/JHRI.5.2.Yogeeswaran","DOIUrl":"https://doi.org/10.5898/JHRI.5.2.Yogeeswaran","url":null,"abstract":"The present research examines how a robot's physical anthropomorphism interacts with perceived ability of robots to impact the level of realistic and identity threat that people perceive from robots and how it affects their support for robotics research. Experimental data revealed that participants perceived robots to be significantly more threatening to humans after watching a video of an android that could allegedly outperform humans on various physical and mental tasks relative to a humanoid robot that could do the same. However, when participants were not provided with information about a new generation of robots' ability relative to humans, then no significant differences were found in perceived threat following exposure to either the android or humanoid robots. Similarly, participants also expressed less support for robotics research after seeing an android relative to a humanoid robot outperform humans. However, when provided with no information about robots' ability relative to humans, then participants showed marginally decreased support for robotics research following exposure to the humanoid relative to the android robot. Taken together, these findings suggest that very humanlike robots can not only be perceived as a realistic threat to human jobs, safety, and resources, but can also be seen as a threat to human identity and uniqueness, especially if such robots also outperform humans. We also demonstrate the potential downside of such robots to the public's willingness to support and fund robotics research.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.5.2.Yogeeswaran","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218477","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}
Alexandre Coninx, Paul E. Baxter, E. Oleari, S. Bellini, Bert P. B. Bierman, O. B. Henkemans, L. Cañamero, P. Cosi, V. Enescu, Raquel Ros Espinoza, Antoine Hiolle, R. Humbert, B. Kiefer, Ivana Kruijff-Korbayová, R. Looije, Marco Mosconi, Mark Antonius Neerincx, G. Paci, G. Patsis, C. Pozzi, Francesca Sacchitelli, H. Sahli, A. Sanna, Giacomo Sommavilla, F. Tesser, Y. Demiris, Tony Belpaeme
Social robots have the potential to provide support in a number of practical domains, such as learning and behaviour change. This potential is particularly relevant for children, who have proven receptive to interactions with social robots. To reach learning and therapeutic goals, a number of issues need to be investigated, notably the design of an effective child-robot interaction (cHRI) to ensure the child remains engaged in the relationship and that educational goals are met. Typically, current cHRI research experiments focus on a single type of interaction activity (e.g. a game). However, these can suffer from a lack of adaptation to the child, or from an increasingly repetitive nature of the activity and interaction. In this paper, we motivate and propose a practicable solution to this issue: an adaptive robot able to switch between multiple activities within single interactions. We describe a system that embodies this idea, and present a case study in which diabetic children collaboratively learn with the robot about various aspects of managing their condition. We demonstrate the ability of our system to induce a varied interaction and show the potential of this approach both as an educational tool and as a research method for long-term cHRI.
{"title":"Towards long-term social child-robot interaction","authors":"Alexandre Coninx, Paul E. Baxter, E. Oleari, S. Bellini, Bert P. B. Bierman, O. B. Henkemans, L. Cañamero, P. Cosi, V. Enescu, Raquel Ros Espinoza, Antoine Hiolle, R. Humbert, B. Kiefer, Ivana Kruijff-Korbayová, R. Looije, Marco Mosconi, Mark Antonius Neerincx, G. Paci, G. Patsis, C. Pozzi, Francesca Sacchitelli, H. Sahli, A. Sanna, Giacomo Sommavilla, F. Tesser, Y. Demiris, Tony Belpaeme","doi":"10.5898/JHRI.5.1.Coninx","DOIUrl":"https://doi.org/10.5898/JHRI.5.1.Coninx","url":null,"abstract":"Social robots have the potential to provide support in a number of practical domains, such as learning and behaviour change. This potential is particularly relevant for children, who have proven receptive to interactions with social robots. To reach learning and therapeutic goals, a number of issues need to be investigated, notably the design of an effective child-robot interaction (cHRI) to ensure the child remains engaged in the relationship and that educational goals are met. Typically, current cHRI research experiments focus on a single type of interaction activity (e.g. a game). However, these can suffer from a lack of adaptation to the child, or from an increasingly repetitive nature of the activity and interaction. In this paper, we motivate and propose a practicable solution to this issue: an adaptive robot able to switch between multiple activities within single interactions. We describe a system that embodies this idea, and present a case study in which diabetic children collaboratively learn with the robot about various aspects of managing their condition. We demonstrate the ability of our system to induce a varied interaction and show the potential of this approach both as an educational tool and as a research method for long-term cHRI.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.5.1.Coninx","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218382","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 : 2015-12-06DOI: 10.5898/JHRI.4.3.Fehlberg
Mark A. Fehlberg, Hamidreza N. Sani, W. Provancher
The Planar Active Handrest (PAHR) is a large workspace assistive device that improves user precision manipulation. The PAHR is restricted in its use, because it does not rotate in the horizontal plane, which limits the workspace size and reduces user comfort. This paper evaluates an improved device, the Enhanced Planar Active Handrest (E-PAHR), which allows lateral/medial rotation of the upper arm. Under the E-PAHR design, the desired hand position can be obtained with redundant arm and device configurations. As such, we gave consideration to controller input choices and resultant device motions that are available. Three experiments evaluated the controller designs to select the most effective method to control our device. We conclude that a rotational DOF (degrees of freedom) allows the E-PAHR to better follow the kinematics of a user's planar arm movements while allowing skill level equal to the PAHR, with reduced user force input and lower perceived exertion.
{"title":"Enhancements to the planar active handrest","authors":"Mark A. Fehlberg, Hamidreza N. Sani, W. Provancher","doi":"10.5898/JHRI.4.3.Fehlberg","DOIUrl":"https://doi.org/10.5898/JHRI.4.3.Fehlberg","url":null,"abstract":"The Planar Active Handrest (PAHR) is a large workspace assistive device that improves user precision manipulation. The PAHR is restricted in its use, because it does not rotate in the horizontal plane, which limits the workspace size and reduces user comfort. This paper evaluates an improved device, the Enhanced Planar Active Handrest (E-PAHR), which allows lateral/medial rotation of the upper arm. Under the E-PAHR design, the desired hand position can be obtained with redundant arm and device configurations. As such, we gave consideration to controller input choices and resultant device motions that are available. Three experiments evaluated the controller designs to select the most effective method to control our device. We conclude that a rotational DOF (degrees of freedom) allows the E-PAHR to better follow the kinematics of a user's planar arm movements while allowing skill level equal to the PAHR, with reduced user force input and lower perceived exertion.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.4.3.Fehlberg","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218333","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 : 2015-12-06DOI: 10.5898/JHRI.4.3.Moualeu
Antonio Moualeu, J. Ueda
Physical contact established during interaction between a human operator and a haptic device creates a coupled system with stability and performance characteristics different than its individual subsystems taken in isolation. Proper incorporation of operator dynamics in physical human-robot interaction (pHRI) conditions requires knowledge of system variables and parameters, some of which are not directly measurable. Operator endpoint impedance, for instance, cannot be directly measured in typical haptic control conditions. Several endpoint impedance estimation techniques have been explored in previous literature, based on measured kinematics and/or other correlated metrics. Arm muscle activity, measured through surface electromyography (sEMG), has been used in previous literature to estimate endpoint stiffness, which is the static component of impedance. Co-activation (co-contraction) of antagonistic arm muscles forming a pair around a joint is known to be the driving factor in modulation of endpoint stiffness. However, previous work employing muscle co-contraction to predict endpoint stiffness has mainly been absent, due in part to the inefficacy of operator models to incorporate muscle co-activation into the prediction scheme. The current study proposes a method for prediction of operator endpoint stiffness based on measured co-contraction levels of a select group of muscles. The proposed methodology incorporates an upper extremity musculoskeletal model that accounts for muscle redundancy and the role of muscle co-contraction on arm stiffness modulation. The study hypothesizes that a free parameter, currently known in the literature to represent the nullspace of the mapping between muscle forces and joint torques, is a random variable of which probability density function can be estimated. Changes in this parameter directly affect changes in operator endpoint stiffness. Ten healthy subjects were asked to resist perturbations induced by a one degree of freedom (DOF) haptic paddle device while measurements, including muscle activities of four arm muscles, were being carried out. Direct derivation of stiffness values at the endpoint was compared to simulated endpoint stiffness values obtained using the proposed predictive methodology. Ten out of forty prediction trials resulted in a statistically significant correlation between predicted and actual stiffness values. Impressive stiffness prediction results, with over 99% peak accuracy in value, were found in only one trial using a combination of the proposed method along with a standard static optimization method for muscle force computation. Though the possibility of using a probabilistic approach to stiffness prediction was shown, robustness and generalizability of the proposed approach to multi-DOF systems remain to be addressed.
{"title":"A model for operator endpoint stiffness prediction during physical human-robot interaction","authors":"Antonio Moualeu, J. Ueda","doi":"10.5898/JHRI.4.3.Moualeu","DOIUrl":"https://doi.org/10.5898/JHRI.4.3.Moualeu","url":null,"abstract":"Physical contact established during interaction between a human operator and a haptic device creates a coupled system with stability and performance characteristics different than its individual subsystems taken in isolation. Proper incorporation of operator dynamics in physical human-robot interaction (pHRI) conditions requires knowledge of system variables and parameters, some of which are not directly measurable. Operator endpoint impedance, for instance, cannot be directly measured in typical haptic control conditions. Several endpoint impedance estimation techniques have been explored in previous literature, based on measured kinematics and/or other correlated metrics. Arm muscle activity, measured through surface electromyography (sEMG), has been used in previous literature to estimate endpoint stiffness, which is the static component of impedance. Co-activation (co-contraction) of antagonistic arm muscles forming a pair around a joint is known to be the driving factor in modulation of endpoint stiffness. However, previous work employing muscle co-contraction to predict endpoint stiffness has mainly been absent, due in part to the inefficacy of operator models to incorporate muscle co-activation into the prediction scheme. The current study proposes a method for prediction of operator endpoint stiffness based on measured co-contraction levels of a select group of muscles. The proposed methodology incorporates an upper extremity musculoskeletal model that accounts for muscle redundancy and the role of muscle co-contraction on arm stiffness modulation. The study hypothesizes that a free parameter, currently known in the literature to represent the nullspace of the mapping between muscle forces and joint torques, is a random variable of which probability density function can be estimated. Changes in this parameter directly affect changes in operator endpoint stiffness. Ten healthy subjects were asked to resist perturbations induced by a one degree of freedom (DOF) haptic paddle device while measurements, including muscle activities of four arm muscles, were being carried out. Direct derivation of stiffness values at the endpoint was compared to simulated endpoint stiffness values obtained using the proposed predictive methodology. Ten out of forty prediction trials resulted in a statistically significant correlation between predicted and actual stiffness values. Impressive stiffness prediction results, with over 99% peak accuracy in value, were found in only one trial using a combination of the proposed method along with a standard static optimization method for muscle force computation. Though the possibility of using a probabilistic approach to stiffness prediction was shown, robustness and generalizability of the proposed approach to multi-DOF systems remain to be addressed.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.4.3.Moualeu","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218354","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}
Natural motion produced by the biological motor control system presents movement smoothness, but neurological disorders or injuries severely deteriorates motor functions. This paper proposes a robot-aided training methodology focusing on smooth transient trajectory generation by the arm while performing a complex task (i.e., virtual curling). The aim of the proposed approach is that a trainee should be taught a reference velocity profile with high movement smoothness in the complex task via the interaction with a robotic device while improving coordination ability for natural arm movements. In the virtual curling training, a trainee manipulates the handle of an impedance-controlled robot to move a virtual stone to the center of a circular target on ice while predicting transient behaviors of the released stone. First, a reference hand motion is clarified through a set of preliminary experiments for different task conditions carried out with four well-trained subjects, and the characteristics of skilled hand velocity profiles are coded with a set of quantitative factors as task-related constraints. The skilled hand motions according to task conditions are successfully simulated in the framework of a minimum-jerk model with the task-related constraints. Next, the training program for enhancing movement smoothness is developed using the computational model, which has four training modes of operation: 1) diagnosis, 2) teaching with active-assistance by the robot, 3) training with passive-assistance, and 4) training with no assistance. Finally, training experiments with ten novice healthy volunteers demonstrate that the proposed approach can be utilized in the recovery of motor functions necessary for desired velocity profiles with high motion smoothness.
{"title":"Robot-aided rehabilitation methodology for enhancing movement smoothness by using a human hand trajectory generation model with task-related constraints","authors":"Yoshiyuki Tanaka","doi":"10.5898/JHRI.4.3.Tanaka","DOIUrl":"https://doi.org/10.5898/JHRI.4.3.Tanaka","url":null,"abstract":"Natural motion produced by the biological motor control system presents movement smoothness, but neurological disorders or injuries severely deteriorates motor functions. This paper proposes a robot-aided training methodology focusing on smooth transient trajectory generation by the arm while performing a complex task (i.e., virtual curling). The aim of the proposed approach is that a trainee should be taught a reference velocity profile with high movement smoothness in the complex task via the interaction with a robotic device while improving coordination ability for natural arm movements. In the virtual curling training, a trainee manipulates the handle of an impedance-controlled robot to move a virtual stone to the center of a circular target on ice while predicting transient behaviors of the released stone. First, a reference hand motion is clarified through a set of preliminary experiments for different task conditions carried out with four well-trained subjects, and the characteristics of skilled hand velocity profiles are coded with a set of quantitative factors as task-related constraints. The skilled hand motions according to task conditions are successfully simulated in the framework of a minimum-jerk model with the task-related constraints. Next, the training program for enhancing movement smoothness is developed using the computational model, which has four training modes of operation: 1) diagnosis, 2) teaching with active-assistance by the robot, 3) training with passive-assistance, and 4) training with no assistance. Finally, training experiments with ten novice healthy volunteers demonstrate that the proposed approach can be utilized in the recovery of motor functions necessary for desired velocity profiles with high motion smoothness.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.4.3.Tanaka","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218775","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}
This paper proposes a haptic assistance system that provides momentary steering wheel torque to help the driver choose the steering direction for avoiding collision with a pedestrian. The results of an experiment with a driving simulator showed that reaction time was reduced significantly when using haptic assistance and that the system was effective in enhancing appropriate selection of a steering direction in many cases. However, there were cases in which the drivers' choice was opposite to the system's proposal. In order for the system to be acceptable to drivers, the drivers' natural choice of direction should be taken into account.
{"title":"Toward trustworthy haptic assistance system for emergency avoidance of collision with a pedestrian","authors":"M. Itoh, Hiroto Tanaka, T. Inagaki","doi":"10.5898/JHRI.4.3.Itoh","DOIUrl":"https://doi.org/10.5898/JHRI.4.3.Itoh","url":null,"abstract":"This paper proposes a haptic assistance system that provides momentary steering wheel torque to help the driver choose the steering direction for avoiding collision with a pedestrian. The results of an experiment with a driving simulator showed that reaction time was reduced significantly when using haptic assistance and that the system was effective in enhancing appropriate selection of a steering direction in many cases. However, there were cases in which the drivers' choice was opposite to the system's proposal. In order for the system to be acceptable to drivers, the drivers' natural choice of direction should be taken into account.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.4.3.Itoh","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218342","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}
In this paper, we present a framework, probabilistic model, and algorithm for learning shared control policies by observing an assistant. This is a methodology we refer to as Learning Assistance by Demonstration (LAD). As a subset of robot Learning by Demonstration (LbD), LAD focuses on the assistive element by explicitly capturing how and when to help. The latter is especially important in assistive scenarios---such as rehabilitation and training---where there exists multiple and possibly conflicting goals. We formalize these notions in a probabilistic model and develop an efficient online mixture of experts (OME) algorithm, based on sparse Gaussian processes (GPs), for learning the assistive policy. Focusing on smart mobility, we couple the LAD methodology with a novel paired-haptic-controllers setup for helping smart wheelchair users navigate their environment. Experimental results with 15 able-bodied participants demonstrate that our learned shared control policy improved driving performance (as measured in lap seconds) by 43 s (a speedup of 191%). Furthermore, survey results indicate that the participants not only performed better quantitatively, but also qualitatively felt the model assistance helped them complete the task.
{"title":"Learning assistance by demonstration","authors":"Harold Soh, Y. Demiris","doi":"10.5898/JHRI.4.3.Soh","DOIUrl":"https://doi.org/10.5898/JHRI.4.3.Soh","url":null,"abstract":"In this paper, we present a framework, probabilistic model, and algorithm for learning shared control policies by observing an assistant. This is a methodology we refer to as Learning Assistance by Demonstration (LAD). As a subset of robot Learning by Demonstration (LbD), LAD focuses on the assistive element by explicitly capturing how and when to help. The latter is especially important in assistive scenarios---such as rehabilitation and training---where there exists multiple and possibly conflicting goals. We formalize these notions in a probabilistic model and develop an efficient online mixture of experts (OME) algorithm, based on sparse Gaussian processes (GPs), for learning the assistive policy. Focusing on smart mobility, we couple the LAD methodology with a novel paired-haptic-controllers setup for helping smart wheelchair users navigate their environment. Experimental results with 15 able-bodied participants demonstrate that our learned shared control policy improved driving performance (as measured in lap seconds) by 43 s (a speedup of 191%). Furthermore, survey results indicate that the participants not only performed better quantitatively, but also qualitatively felt the model assistance helped them complete the task.","PeriodicalId":92076,"journal":{"name":"Journal of human-robot interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5898/JHRI.4.3.Soh","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71218764","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：