Pub Date : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900627
L. Franco, G. Salvietti, Michele Pompilio, S. Rossi, D. Prattichizzo
Supernumerary Robotic Limbs (SRL) represent a new class of wearable robots that can augment human manipulation capabilities. SRL can be controlled through input interfaces worn on the user body and can interact with the environment. Such interaction can be measured and feedback to the human wearer through wearable haptic interfaces. However, human somatotopic arrangement on the central nervous system lacks a location for artificially added limbs. Where is the best location for feedback coming from a robot not directly associated with a part of the wearer’s body?This paper sheds light on the problem of the best body location for the feedback coming from an SRL as well as on the relation between the position of the input interface and the haptic interface. We have tested four different body locations - shoulder, wrist, hip, and ankle - for vibrotactile feedback coming from the simulated interaction with a robotic extra limb activated using an interface consisting of an accelerometer worn on the user’s shoulder. Results from the experiment involving 14 participants demonstrated that the ankle feedback position led to significantly worse performances when having inputs from the shoulder, whereas the other three locations led to comparable results.
{"title":"On the Somatotopic Mapping of Haptic Feedback from Robotic Supernumerary Limbs","authors":"L. Franco, G. Salvietti, Michele Pompilio, S. Rossi, D. Prattichizzo","doi":"10.1109/RO-MAN53752.2022.9900627","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900627","url":null,"abstract":"Supernumerary Robotic Limbs (SRL) represent a new class of wearable robots that can augment human manipulation capabilities. SRL can be controlled through input interfaces worn on the user body and can interact with the environment. Such interaction can be measured and feedback to the human wearer through wearable haptic interfaces. However, human somatotopic arrangement on the central nervous system lacks a location for artificially added limbs. Where is the best location for feedback coming from a robot not directly associated with a part of the wearer’s body?This paper sheds light on the problem of the best body location for the feedback coming from an SRL as well as on the relation between the position of the input interface and the haptic interface. We have tested four different body locations - shoulder, wrist, hip, and ankle - for vibrotactile feedback coming from the simulated interaction with a robotic extra limb activated using an interface consisting of an accelerometer worn on the user’s shoulder. Results from the experiment involving 14 participants demonstrated that the ankle feedback position led to significantly worse performances when having inputs from the shoulder, whereas the other three locations led to comparable results.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114535864","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900745
Mayuka Kojima, Shunsuke Yoshimoto, Akio Yamamoto
A psycho-physical experiment using constant method was conducted to investigate the characteristics of pseudo force sensation caused by pressurization to a palm. Kinesthetic force stimulus and tactile pressure stimulus were given to a subject at the same time, and their effect on force perception was investigated. Previous studies have reported two contradicting results regarding whether the strength of pseudo force sensation depends on the pressure or on the total amount of force. This paper further investigated this aspect using three types of indenters which differ in shape and width. The results suggested that the pseudo force sensation does not depend on total force. This, however, does not simply mean that the sensation depends on the pressure and the need for further investigations remains. The results found significant differences among subjects but also suggested that the narrower indenter with an integrated body is less susceptible to individual differences among subjects.
{"title":"Evaluation of Point of Subject Equality Using Constant Method in Pseudo Force Sensation by Pressure Stimulation to the Palm*","authors":"Mayuka Kojima, Shunsuke Yoshimoto, Akio Yamamoto","doi":"10.1109/RO-MAN53752.2022.9900745","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900745","url":null,"abstract":"A psycho-physical experiment using constant method was conducted to investigate the characteristics of pseudo force sensation caused by pressurization to a palm. Kinesthetic force stimulus and tactile pressure stimulus were given to a subject at the same time, and their effect on force perception was investigated. Previous studies have reported two contradicting results regarding whether the strength of pseudo force sensation depends on the pressure or on the total amount of force. This paper further investigated this aspect using three types of indenters which differ in shape and width. The results suggested that the pseudo force sensation does not depend on total force. This, however, does not simply mean that the sensation depends on the pressure and the need for further investigations remains. The results found significant differences among subjects but also suggested that the narrower indenter with an integrated body is less susceptible to individual differences among subjects.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114746069","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900638
Kayla Matheus, Marynel Vázquez, B. Scassellati
In this paper, we introduce Ommie, a novel robot that supports deep breathing practices for the purposes of anxiety reduction. The robot’s primary function is to guide users through a series of extended inhales, exhales, and holds by way of haptic interactions and audio cues. We present core design decisions during development, such as robot morphology and tactility, as well as the results of a usability study in collaboration with a local wellness center. Interacting with Ommie resulted in a significant reduction in STAI-6 anxiety measures, and participants found the robot intuitive, approachable, and engaging. Participants also reported feelings of focus and companionship when using the robot, often elicited by the haptic interaction. These results show promise in the robot’s capacity for supporting mental health.
{"title":"A Social Robot for Anxiety Reduction via Deep Breathing","authors":"Kayla Matheus, Marynel Vázquez, B. Scassellati","doi":"10.1109/RO-MAN53752.2022.9900638","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900638","url":null,"abstract":"In this paper, we introduce Ommie, a novel robot that supports deep breathing practices for the purposes of anxiety reduction. The robot’s primary function is to guide users through a series of extended inhales, exhales, and holds by way of haptic interactions and audio cues. We present core design decisions during development, such as robot morphology and tactility, as well as the results of a usability study in collaboration with a local wellness center. Interacting with Ommie resulted in a significant reduction in STAI-6 anxiety measures, and participants found the robot intuitive, approachable, and engaging. Participants also reported feelings of focus and companionship when using the robot, often elicited by the haptic interaction. These results show promise in the robot’s capacity for supporting mental health.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127874195","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900727
Heqiu Song, Maria Deetman, P. Markopoulos, Jaap Ham, E. Barakova
In music education, staying motivated has always been a crucial goal, especially for children. Earlier research has demonstrated how social robots could help improve motivation and increase the performance of children practicing music pieces. As important stakeholders, the attitudes and expec- tations of parents and music teachers are important factors that affect children’s and their own acceptance of applying social robots in music education. In this study, a survey was created and used to assess parents’ and music teachers’ attitudes, expectations, and intentions related to using social robots in music education. The survey results suggested that parents and music teachers expect robots to act as assistive and motivating agents, give positive feedback, and schedule and structure practice sessions. Moreover, parents expect a social robot to evaluate student performance, while music teachers focus more on positive encouragement. The biggest concerns of these stakeholders are whether the robots can convey the emotional aspects of music and demonstrate how to play the instrument. The intention of using robots is positively correlated with positive attitudes towards robots in general and the positive attitude towards robots specifically in the context of music education. The current study contributes insights into parents’ and music teachers’ attitudes and expectations as determinants of their acceptance of of social robots in music education, and provides a method for measuring these attitudes and expectations.
{"title":"Learning Musical Instrument with the Help of Social Robots: Attitudes and Expectations of Teachers and Parents","authors":"Heqiu Song, Maria Deetman, P. Markopoulos, Jaap Ham, E. Barakova","doi":"10.1109/RO-MAN53752.2022.9900727","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900727","url":null,"abstract":"In music education, staying motivated has always been a crucial goal, especially for children. Earlier research has demonstrated how social robots could help improve motivation and increase the performance of children practicing music pieces. As important stakeholders, the attitudes and expec- tations of parents and music teachers are important factors that affect children’s and their own acceptance of applying social robots in music education. In this study, a survey was created and used to assess parents’ and music teachers’ attitudes, expectations, and intentions related to using social robots in music education. The survey results suggested that parents and music teachers expect robots to act as assistive and motivating agents, give positive feedback, and schedule and structure practice sessions. Moreover, parents expect a social robot to evaluate student performance, while music teachers focus more on positive encouragement. The biggest concerns of these stakeholders are whether the robots can convey the emotional aspects of music and demonstrate how to play the instrument. The intention of using robots is positively correlated with positive attitudes towards robots in general and the positive attitude towards robots specifically in the context of music education. The current study contributes insights into parents’ and music teachers’ attitudes and expectations as determinants of their acceptance of of social robots in music education, and provides a method for measuring these attitudes and expectations.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128132648","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900763
Anita Paas, Emily B. J. Coffey, G. Beltrame, D. St-Onge
The use of multi-robot systems is increasing in disaster response, industry, transport, and logistics. Humans will remain indispensable to control and manage these fleets of robots, particularly in safety-critical applications. However, a human operator’s cognitive capacities can be challenged and exceeded as the sizes of autonomous fleets grow, and more sophisticated AI techniques can lead to opaque robot control programs. In a user study (n = 40), we explore how autonomous swarm intelligence algorithms and novel tangible interaction modalities relate to subjective and physiological indices of operator cognitive load (i.e., NASA Task Load Index, heart rate variability). Our findings suggest that there are differences in workload across conditions; however, subjective and cardiac measures appear to be sensitive to different aspects of cognitive state. The results hint at the potential of both tangible interfaces and automation to engage operators and reduce cognitive load, yet show the need for further validation of workload measures for use in studying and optimizing human-swarm interactions.
{"title":"Towards evaluating the impact of swarm robotic control strategy on operators’ cognitive load","authors":"Anita Paas, Emily B. J. Coffey, G. Beltrame, D. St-Onge","doi":"10.1109/RO-MAN53752.2022.9900763","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900763","url":null,"abstract":"The use of multi-robot systems is increasing in disaster response, industry, transport, and logistics. Humans will remain indispensable to control and manage these fleets of robots, particularly in safety-critical applications. However, a human operator’s cognitive capacities can be challenged and exceeded as the sizes of autonomous fleets grow, and more sophisticated AI techniques can lead to opaque robot control programs. In a user study (n = 40), we explore how autonomous swarm intelligence algorithms and novel tangible interaction modalities relate to subjective and physiological indices of operator cognitive load (i.e., NASA Task Load Index, heart rate variability). Our findings suggest that there are differences in workload across conditions; however, subjective and cardiac measures appear to be sensitive to different aspects of cognitive state. The results hint at the potential of both tangible interfaces and automation to engage operators and reduce cognitive load, yet show the need for further validation of workload measures for use in studying and optimizing human-swarm interactions.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128168789","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}
During human-robot conversation, it is critical for robots to be able to answer users’ questions accurately and provide a suitable explanation for why they arrive at the answer they provide. Depth is a crucial component in producing more intelligent robots that can respond correctly as some questions might rely on spatial relations within the scene, for which 2D RGB data alone would be insufficient. Due to the lack of existing depth datasets for the task of VQA, we introduce a new dataset, VQA-SUNRGBD. When we compare our proposed model on this RGB-D dataset against the baseline VQN network on RGB data alone, we show that ours outperforms, particularly in questions relating to depth such as asking about the proximity of objects and relative positions of objects to one another. We also provide Grad-CAM activations to gain insight regarding the predictions on depth-related questions and find that our method produces better visual explanations compared to Grad-CAM on RGB data. To our knowledge, this work is the first of its kind to leverage depth and an explainability module to produce an explainable Visual Question Answering (VQA) system.
{"title":"Improving Visual Question Answering by Leveraging Depth and Adapting Explainability","authors":"Amrita Panesar, Fethiye Irmak Dogan, Iolanda Leite","doi":"10.1109/RO-MAN53752.2022.9900586","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900586","url":null,"abstract":"During human-robot conversation, it is critical for robots to be able to answer users’ questions accurately and provide a suitable explanation for why they arrive at the answer they provide. Depth is a crucial component in producing more intelligent robots that can respond correctly as some questions might rely on spatial relations within the scene, for which 2D RGB data alone would be insufficient. Due to the lack of existing depth datasets for the task of VQA, we introduce a new dataset, VQA-SUNRGBD. When we compare our proposed model on this RGB-D dataset against the baseline VQN network on RGB data alone, we show that ours outperforms, particularly in questions relating to depth such as asking about the proximity of objects and relative positions of objects to one another. We also provide Grad-CAM activations to gain insight regarding the predictions on depth-related questions and find that our method produces better visual explanations compared to Grad-CAM on RGB data. To our knowledge, this work is the first of its kind to leverage depth and an explainability module to produce an explainable Visual Question Answering (VQA) system.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125697815","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900691
Ada V Taylor, R. Kaufman, Michael Huang, H. Admoni
Enabling robots to identify when humans need assistance is key to being able to provide help that is both proactive and efficient. This challenge is particularly difficult for humans eating a meal in a restaurant, a context which is dense with interlaced social elements such as conversation in addition to functional tasks such as eating. We investigated the challenge of identifying human dining activities from single-viewpoint footage by collecting and annotating the individual activities of five two-person meals. From this process, we found that addressing the question of identifying meal phases and overall neediness requires identifying an underlying group state for the table as a whole. We report on the individual activities and group states, as well as the interdependencies between these factors that can be leveraged to both provide and measure effective robotic restaurant service. In addition to the insights revealed by this dataset, we describe preliminary attempts to create an automated classification system for these activities.
{"title":"Group Activity Recognition in Restaurants to Address Underlying Needs: A Case Study","authors":"Ada V Taylor, R. Kaufman, Michael Huang, H. Admoni","doi":"10.1109/RO-MAN53752.2022.9900691","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900691","url":null,"abstract":"Enabling robots to identify when humans need assistance is key to being able to provide help that is both proactive and efficient. This challenge is particularly difficult for humans eating a meal in a restaurant, a context which is dense with interlaced social elements such as conversation in addition to functional tasks such as eating. We investigated the challenge of identifying human dining activities from single-viewpoint footage by collecting and annotating the individual activities of five two-person meals. From this process, we found that addressing the question of identifying meal phases and overall neediness requires identifying an underlying group state for the table as a whole. We report on the individual activities and group states, as well as the interdependencies between these factors that can be leveraged to both provide and measure effective robotic restaurant service. In addition to the insights revealed by this dataset, we describe preliminary attempts to create an automated classification system for these activities.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131722777","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900578
Maria Mannone, V. Seidita, A. Chella
Data sonification enhance and enrich information understanding with an additional sensory dimension. Sonification also opens the way to more creative applications, joining arts and sciences. In this study, we present sequences of chords obtained as auditory feedback from the trajectories of a robotic swarm. The swarm behavior is an emerging effect from simple local interactions and autonomous decisions of each robot. The swarm effect can be identified through sonification outcomes in terms of voice leading patterns. Thus, chord patterns represent behavior patterns. The convergence to the target is represented by the convergence to a specific pitch. The swarm decision process is based upon quantum computing. We first present logic gates and their implementations as quantum circuits, describing examples with 2- and 3-dimensional motion of a 3-robot toy swarm. The considered scenarios are ant foraging (2D) and underwater search and rescue (3D). Then, we provide and discuss some examples of the harmonic sequences that can be obtained as feedback from robotic motion.
{"title":"Quantum RoboSound: Auditory Feedback of a Quantum-Driven Robotic Swarm","authors":"Maria Mannone, V. Seidita, A. Chella","doi":"10.1109/RO-MAN53752.2022.9900578","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900578","url":null,"abstract":"Data sonification enhance and enrich information understanding with an additional sensory dimension. Sonification also opens the way to more creative applications, joining arts and sciences. In this study, we present sequences of chords obtained as auditory feedback from the trajectories of a robotic swarm. The swarm behavior is an emerging effect from simple local interactions and autonomous decisions of each robot. The swarm effect can be identified through sonification outcomes in terms of voice leading patterns. Thus, chord patterns represent behavior patterns. The convergence to the target is represented by the convergence to a specific pitch. The swarm decision process is based upon quantum computing. We first present logic gates and their implementations as quantum circuits, describing examples with 2- and 3-dimensional motion of a 3-robot toy swarm. The considered scenarios are ant foraging (2D) and underwater search and rescue (3D). Then, we provide and discuss some examples of the harmonic sequences that can be obtained as feedback from robotic motion.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128919621","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900865
Melissa Donnermann, Philipp Schaper, Birgit Lugrin
Learning in universities challenges students to engage in self-directed learning, which requires a high degree of self-motivation while individual support by teachers is limited. Research on social robots has already demonstrated their potential to support students in their learning process. In this paper, we focus on the benefits of adaptivity of a robotic tutor in a higher education scenario. To this end, we conducted a field study over three sessions over the course of a semester and implemented two conditions (adaptive and non-adaptive) of a robotic tutor to support students with exam preparation. After participant learned with both version in random order in the first two sessions, their preferred condition was used in the third session. Our results show that significantly more students preferred to learn with the adaptive robotic tutor. Additionally, participation resulted in significantly better exam performance compared to the average of the course. However, there was no significant difference in the learning experience such as motivation or need satisfaction between conditions.
{"title":"Investigating Adaptive Robot Tutoring in a Long-Term Interaction in Higher Education","authors":"Melissa Donnermann, Philipp Schaper, Birgit Lugrin","doi":"10.1109/RO-MAN53752.2022.9900865","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900865","url":null,"abstract":"Learning in universities challenges students to engage in self-directed learning, which requires a high degree of self-motivation while individual support by teachers is limited. Research on social robots has already demonstrated their potential to support students in their learning process. In this paper, we focus on the benefits of adaptivity of a robotic tutor in a higher education scenario. To this end, we conducted a field study over three sessions over the course of a semester and implemented two conditions (adaptive and non-adaptive) of a robotic tutor to support students with exam preparation. After participant learned with both version in random order in the first two sessions, their preferred condition was used in the third session. Our results show that significantly more students preferred to learn with the adaptive robotic tutor. Additionally, participation resulted in significantly better exam performance compared to the average of the course. However, there was no significant difference in the learning experience such as motivation or need satisfaction between conditions.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130891637","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 : 2022-08-29DOI: 10.1109/RO-MAN53752.2022.9900856
Alap Kshirsagar, Rahul Ravi, H. Kress-Gazit, G. Hoffman
We develop and evaluate two human-robot handover controllers that allow end-users to specify timing parameters for the robot reach motion, and that provide feedback if the robot cannot satisfy those constraints. End-user tuning with feedback is a useful controller feature in settings where robots have to be re-programmed for varying task requirements but end-users do not have programming knowledge. The two controllers we propose are both receding-horizon controllers that differ in their objective function, and their user specified parameters, and subsequently their user-interface: One controller uses a minimum cumulative jerk (MCJ) objective function, and the other a minimum cumulative error (MCE) objective function. We implemented the controllers on a collaborative robot and conducted two controlled experiments to compare the user experience and performance of these controllers vis-à-vis a baseline proportional velocity (PV) controller. In each experiment, participants (n = 30) interactively tuned the controller parameters, and collaborated with a robot to perform a time-constrained repetitive task. We found that the timing controller with the MCE implementation can provide a better user experience, both while setting the parameters (p =0.011) and performing the handovers with the robot (p < 0.001), and fewer failures (p =0.016) compared to the PV controller, however the MCJ implementation did not provide better user experience compared to the PV controller. The MCJ controller also resulted in more failures than the PV controller. These results could inform the design of usable and effective end-user configurable controllers for human-robot interaction.
{"title":"Timing-Specified Controllers with Feedback for Human-Robot Handovers","authors":"Alap Kshirsagar, Rahul Ravi, H. Kress-Gazit, G. Hoffman","doi":"10.1109/RO-MAN53752.2022.9900856","DOIUrl":"https://doi.org/10.1109/RO-MAN53752.2022.9900856","url":null,"abstract":"We develop and evaluate two human-robot handover controllers that allow end-users to specify timing parameters for the robot reach motion, and that provide feedback if the robot cannot satisfy those constraints. End-user tuning with feedback is a useful controller feature in settings where robots have to be re-programmed for varying task requirements but end-users do not have programming knowledge. The two controllers we propose are both receding-horizon controllers that differ in their objective function, and their user specified parameters, and subsequently their user-interface: One controller uses a minimum cumulative jerk (MCJ) objective function, and the other a minimum cumulative error (MCE) objective function. We implemented the controllers on a collaborative robot and conducted two controlled experiments to compare the user experience and performance of these controllers vis-à-vis a baseline proportional velocity (PV) controller. In each experiment, participants (n = 30) interactively tuned the controller parameters, and collaborated with a robot to perform a time-constrained repetitive task. We found that the timing controller with the MCE implementation can provide a better user experience, both while setting the parameters (p =0.011) and performing the handovers with the robot (p < 0.001), and fewer failures (p =0.016) compared to the PV controller, however the MCJ implementation did not provide better user experience compared to the PV controller. The MCJ controller also resulted in more failures than the PV controller. These results could inform the design of usable and effective end-user configurable controllers for human-robot interaction.","PeriodicalId":250997,"journal":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","volume":"57 4 Suppl 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133315153","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：