Pub Date : 2017-10-01DOI: 10.1109/IRIS.2017.8250115
Claudia-Adina Bojan-Dragos, R. Precup, Stefania-Persida Hergane, Teodor-Adrian Teban, E. Petriu
The design of an adaptive control scheme (CS) for the control of a sphere in a magnetic levitation system laboratory equipment is presented in this paper. The linearized mathematical model of the process is stabilized by a state feedback controller. The zero steady-state control error is ensured by designing a proportional-integral-derivative controller. A fuzzy proportional-integral-derivative gainscheduling controller is designed to ensure the switching between the linear proportional-integral-derivative controllers. Some simulation results are presented to validate the proposed control structures.
{"title":"Fuzzy logic-based adaptive control scheme for magnetic levitation systems","authors":"Claudia-Adina Bojan-Dragos, R. Precup, Stefania-Persida Hergane, Teodor-Adrian Teban, E. Petriu","doi":"10.1109/IRIS.2017.8250115","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250115","url":null,"abstract":"The design of an adaptive control scheme (CS) for the control of a sphere in a magnetic levitation system laboratory equipment is presented in this paper. The linearized mathematical model of the process is stabilized by a state feedback controller. The zero steady-state control error is ensured by designing a proportional-integral-derivative controller. A fuzzy proportional-integral-derivative gainscheduling controller is designed to ensure the switching between the linear proportional-integral-derivative controllers. Some simulation results are presented to validate the proposed control structures.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114979658","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250107
M. Abouheaf, W. Gueaieb
This paper introduces novel online adaptive Reinforcement Learning approach based on Policy Iteration for multi-agent systems interacting on graphs. The approach uses reduced value functions to solve the coupled Bellman and Hamilton-Jacobi-Bellman equations for multi-agent systems. This done using only partial knowledge about the agents' dynamics. The convergence of the approach is shown to depend on the properties of the communication graph. The Policy Iteration approach is implemented in real-time using neural networks, where reduced value functions are considered to reduce the computational complexity.
{"title":"Multi-agent reinforcement learning approach based on reduced value function approximations","authors":"M. Abouheaf, W. Gueaieb","doi":"10.1109/IRIS.2017.8250107","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250107","url":null,"abstract":"This paper introduces novel online adaptive Reinforcement Learning approach based on Policy Iteration for multi-agent systems interacting on graphs. The approach uses reduced value functions to solve the coupled Bellman and Hamilton-Jacobi-Bellman equations for multi-agent systems. This done using only partial knowledge about the agents' dynamics. The convergence of the approach is shown to depend on the properties of the communication graph. The Policy Iteration approach is implemented in real-time using neural networks, where reduced value functions are considered to reduce the computational complexity.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"356 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123000260","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250150
M. Aldulaimi
In this paper, emotion recognition using frontal electroencephalogram (EEG) asymmetry signals is presented. A total of four channels are used in representing EEG frontal asymmetry, consisting of the left and right hemisphere of the brain. Arousal and valence for two-dimensional emotion models are used in classifying four basic emotions; happy, sad, angry, and relaxed. The mirror neuron system (MNS) for emotion elicitation is utilized in finding correlation between participant's emotion rating and EEG data. This is achieved by showing images and music to each participant. These images are used to elicit emotions in applying the imitation concept. In addition, an emotion recognition method based on a combination of two algorithms, fractal dimension for feature extraction and multidimensional direct information on finding correlation between left and right EEG frontal asymmetry is proposed. Good performances are achieved from the combination and rating process, where it can be utilized to indicate correlation between participants rating and EEG recorded data. The final results of the EEG recorded data are represented as robot emotions. Therefore, the main contribution is to create a real-time emotional interaction based on the analyzed EEG recorded data.
{"title":"A real time emotional interaction between EEG brain signals and robot","authors":"M. Aldulaimi","doi":"10.1109/IRIS.2017.8250150","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250150","url":null,"abstract":"In this paper, emotion recognition using frontal electroencephalogram (EEG) asymmetry signals is presented. A total of four channels are used in representing EEG frontal asymmetry, consisting of the left and right hemisphere of the brain. Arousal and valence for two-dimensional emotion models are used in classifying four basic emotions; happy, sad, angry, and relaxed. The mirror neuron system (MNS) for emotion elicitation is utilized in finding correlation between participant's emotion rating and EEG data. This is achieved by showing images and music to each participant. These images are used to elicit emotions in applying the imitation concept. In addition, an emotion recognition method based on a combination of two algorithms, fractal dimension for feature extraction and multidimensional direct information on finding correlation between left and right EEG frontal asymmetry is proposed. Good performances are achieved from the combination and rating process, where it can be utilized to indicate correlation between participants rating and EEG recorded data. The final results of the EEG recorded data are represented as robot emotions. Therefore, the main contribution is to create a real-time emotional interaction based on the analyzed EEG recorded data.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129123528","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250093
Danish Shaikh, Michael Kjær Schmidt
Three-dimensional acoustic localisation is relevant in personal and social robot platforms. Conventional approaches extract interaural time difference cues via impractically large stationary two-dimensional multi-microphone grids with at least four microphones or spectral cues via head-related transfer functions of stationary KEMAR dummy heads equipped with two microphones. We present a preliminary approach using two sound sensors, whose directed movements resolve the location of a stationary acoustic target in three dimensions. A model of the peripheral auditory system of lizards provides sound direction information in a single plane which by itself is insufficient to localise the acoustic target in three dimensions. Two spatial orientations of this plane by rotating the sound sensors by −45° and +45° along the sagittal axis generate a pair of measurements, each encoding the location of the acoustic target with respect to one plane of rotation. A multi-layer perceptron neural network is trained via supervised learning to translate the combination of the two measurements into an estimate of the relative location of the acoustic target in terms of its azimuth and elevation. The acoustic localisation performance of the system is evaluated in simulation for noiseless as well as noisy sinusoidal auditory signals with a 20 dB signal-to-noise ratio for four different sound frequencies of 1450 Hz, 1650 Hz, 1850 Hz and 2050 Hz that span the response frequency range of the peripheral auditory model. Three different neural networks with respectively one hidden layer with ten neurons, one hidden layer with twenty neurons and two hidden layers with ten neurons are comparatively evaluated. The neural networks are evaluated for varying locations of the acoustic target on the surface of the frontal spherical section in space defined by an azimuth and elevation range of [−90°, +90°] with a resolution of 1° in both planes.
{"title":"Three-dimensional acoustic localisation via directed movements of a two-dimensional model of the lizard peripheral auditory system","authors":"Danish Shaikh, Michael Kjær Schmidt","doi":"10.1109/IRIS.2017.8250093","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250093","url":null,"abstract":"Three-dimensional acoustic localisation is relevant in personal and social robot platforms. Conventional approaches extract interaural time difference cues via impractically large stationary two-dimensional multi-microphone grids with at least four microphones or spectral cues via head-related transfer functions of stationary KEMAR dummy heads equipped with two microphones. We present a preliminary approach using two sound sensors, whose directed movements resolve the location of a stationary acoustic target in three dimensions. A model of the peripheral auditory system of lizards provides sound direction information in a single plane which by itself is insufficient to localise the acoustic target in three dimensions. Two spatial orientations of this plane by rotating the sound sensors by −45° and +45° along the sagittal axis generate a pair of measurements, each encoding the location of the acoustic target with respect to one plane of rotation. A multi-layer perceptron neural network is trained via supervised learning to translate the combination of the two measurements into an estimate of the relative location of the acoustic target in terms of its azimuth and elevation. The acoustic localisation performance of the system is evaluated in simulation for noiseless as well as noisy sinusoidal auditory signals with a 20 dB signal-to-noise ratio for four different sound frequencies of 1450 Hz, 1650 Hz, 1850 Hz and 2050 Hz that span the response frequency range of the peripheral auditory model. Three different neural networks with respectively one hidden layer with ten neurons, one hidden layer with twenty neurons and two hidden layers with ten neurons are comparatively evaluated. The neural networks are evaluated for varying locations of the acoustic target on the surface of the frontal spherical section in space defined by an azimuth and elevation range of [−90°, +90°] with a resolution of 1° in both planes.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121513594","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250095
Laurent Levesque, Scott Pardoel, Zlatko Lovrenovic, Marc Doumit
Walking assistive devices are designed to improve the mobility of the user. Although promising, active devices have a problem: they become uncomfortable after prolonged usage. Large motor torques provided by active devices effectively assist the movements of the user. However, these torques transfer forces to the user's limbs creating significant discomfort and limiting the duration of usefulness. This work used force mapping in an attempt to identify zones of pressure concentration that may cause discomfort as well as examined the effect that various pads had on these zones. The device tested in this research was the K-SRD TM by B-Temia Inc. Force analysis identified certain zones of high force concentration. Possible causes were identified and potential solutions were suggested. Furthermore, the padding testing showed that the force transfer was similar regardless of the thickness of the pads. However, the stiffer padding materials distributed the forces over a greater area and decreased the pressure at the interface. This seems to indicate that the thickness of padding is less important than the distribution of applied forces. In all, interfaces that distribute forces over large surface areas may be beneficial. Further research efforts are needed in order to develop a physical human-machine interface that will ensure the success of exoskeletons in the future.
{"title":"Experimental comfort assessment of an active exoskeleton interface","authors":"Laurent Levesque, Scott Pardoel, Zlatko Lovrenovic, Marc Doumit","doi":"10.1109/IRIS.2017.8250095","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250095","url":null,"abstract":"Walking assistive devices are designed to improve the mobility of the user. Although promising, active devices have a problem: they become uncomfortable after prolonged usage. Large motor torques provided by active devices effectively assist the movements of the user. However, these torques transfer forces to the user's limbs creating significant discomfort and limiting the duration of usefulness. This work used force mapping in an attempt to identify zones of pressure concentration that may cause discomfort as well as examined the effect that various pads had on these zones. The device tested in this research was the K-SRD TM by B-Temia Inc. Force analysis identified certain zones of high force concentration. Possible causes were identified and potential solutions were suggested. Furthermore, the padding testing showed that the force transfer was similar regardless of the thickness of the pads. However, the stiffer padding materials distributed the forces over a greater area and decreased the pressure at the interface. This seems to indicate that the thickness of padding is less important than the distribution of applied forces. In all, interfaces that distribute forces over large surface areas may be beneficial. Further research efforts are needed in order to develop a physical human-machine interface that will ensure the success of exoskeletons in the future.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124352146","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250149
Yusuke Takahashi, Y. Nishida, K. Kitamura, H. Mizoguchi
With an eye toward the reality that elderly persons face declining cognitive and physical capabilities as they advance in years, this paper proposes a handrail-shaped Internet of Things (IoT) sensor as a new type of sensing system to watch over seniors as they go about their daily lives. The system detects changes in mobility using movement velocity information and the degree of dependence the subject develops in relation to the handrail-IoT sensors. Herein, we describe a field experiment of our handrail sensor system that was installed in the home of an 88-year-old female test subject. The results show that the system worked well and unobtrusively in an actual home environment and could monitor behavioral changes over a long time period, thereby indicating that it can be used to detect abnormal statuses of other elderly residents via individualizing long-term monitoring programs.
{"title":"Handrail IoT sensor for precision healthcare of elderly people in smart homes","authors":"Yusuke Takahashi, Y. Nishida, K. Kitamura, H. Mizoguchi","doi":"10.1109/IRIS.2017.8250149","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250149","url":null,"abstract":"With an eye toward the reality that elderly persons face declining cognitive and physical capabilities as they advance in years, this paper proposes a handrail-shaped Internet of Things (IoT) sensor as a new type of sensing system to watch over seniors as they go about their daily lives. The system detects changes in mobility using movement velocity information and the degree of dependence the subject develops in relation to the handrail-IoT sensors. Herein, we describe a field experiment of our handrail sensor system that was installed in the home of an 88-year-old female test subject. The results show that the system worked well and unobtrusively in an actual home environment and could monitor behavioral changes over a long time period, thereby indicating that it can be used to detect abnormal statuses of other elderly residents via individualizing long-term monitoring programs.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126285257","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250103
Hiraku Komura, M. Ohka
We developed a tactile mouse that presents convex dot-patterns on a human palm to obtain the design parameters of haptic devices for virtual reality (VR). In a tactile VR study, we focused on the following issue, “which tactile perception is superior, active or passive touch?”, because it is related to the design of haptic devices that can present detailed information in tactile VR. This study evaluates the differences in perception precision between active and passive touch to clarify the best presentation method in VR through a series of psychophysical experiments using a tactile mouse. Since the presentation precision of virtual figures depends on the sharpness of the edges generated by dot-patterns, our experiment subjects evaluate the slope of the oblique edges. In a psychophysical experiment, two oblique edges of dot-patterns are presented consecutively and subjects compare them to determine which is larger. We evaluate the perception precision using the difference threshold of the edge angles calculated by the simplified constant stimuli method. Experimental results show that the perception precision at low speed (45 and 90 mm/s) of edge movement is better than at high speed (130 and 170 mm/s) and also that there is no significant difference between active and passive touching.
{"title":"Effects of active or passive touch on perception precision of edge direction using tactile mouse exhibiting convex dot-patterns on the palm","authors":"Hiraku Komura, M. Ohka","doi":"10.1109/IRIS.2017.8250103","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250103","url":null,"abstract":"We developed a tactile mouse that presents convex dot-patterns on a human palm to obtain the design parameters of haptic devices for virtual reality (VR). In a tactile VR study, we focused on the following issue, “which tactile perception is superior, active or passive touch?”, because it is related to the design of haptic devices that can present detailed information in tactile VR. This study evaluates the differences in perception precision between active and passive touch to clarify the best presentation method in VR through a series of psychophysical experiments using a tactile mouse. Since the presentation precision of virtual figures depends on the sharpness of the edges generated by dot-patterns, our experiment subjects evaluate the slope of the oblique edges. In a psychophysical experiment, two oblique edges of dot-patterns are presented consecutively and subjects compare them to determine which is larger. We evaluate the perception precision using the difference threshold of the edge angles calculated by the simplified constant stimuli method. Experimental results show that the perception precision at low speed (45 and 90 mm/s) of edge movement is better than at high speed (130 and 170 mm/s) and also that there is no significant difference between active and passive touching.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401658","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250108
M. Al-Shabi, Andrew Cataford, S. Gadsden
In this work, well known Quadrature Kalman Filters (QKFs), namely 2-point QKF (SeQKF), 3-point QKF (ThQKF), and 4-point QKF (FoQKF), were used to monitor a 4- degree of freedom prismatic-revolute-revolute-revolute (PRRR) manipulator. This manipulator represents a well-known industrial arm robot. These methods are applied on a PRRR robot, and are compared in terms of stability, robustness, computation time, complexity, and the quality of the optimality. For completeness, the results were compared to those obtained from the popular Unscented Kalman Filter (UKF) and a special form of the UKF known as the Cubature Kalman Filter (CKF).
{"title":"Quadrature Kalman filters with applications to robotic manipulators","authors":"M. Al-Shabi, Andrew Cataford, S. Gadsden","doi":"10.1109/IRIS.2017.8250108","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250108","url":null,"abstract":"In this work, well known Quadrature Kalman Filters (QKFs), namely 2-point QKF (SeQKF), 3-point QKF (ThQKF), and 4-point QKF (FoQKF), were used to monitor a 4- degree of freedom prismatic-revolute-revolute-revolute (PRRR) manipulator. This manipulator represents a well-known industrial arm robot. These methods are applied on a PRRR robot, and are compared in terms of stability, robustness, computation time, complexity, and the quality of the optimality. For completeness, the results were compared to those obtained from the popular Unscented Kalman Filter (UKF) and a special form of the UKF known as the Cubature Kalman Filter (CKF).","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125476279","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250119
Nursefa Zengin, Halit Zengin, B. Fidan
Intelligent walkers (i-walkers) need to have precise torque generation to sustain safe human-walker motion. Utilizing a recently developed control oriented system model that involves the physical-human walker interaction (pHWI) based on the user gait dynamics and characteristics, this paper studies an adaptive control scheme design for high precision trajectory tracking of the i-walker robust to user gait dynamics, body pose and weight. The proposed control scheme involves a backstepping based kinematic controller to generate reference i-walker velocities that match the pre-defined i-walker trajectories. These desired velocities are tracked applying the torques generated by an adaptive sliding mode control (SMC) scheme that is robust to unknown torque disturbance arising from friction forces, center of gravity displacement and load changes due to pHWI. The proposed SMC scheme design contains a feedback linearization unit based on the computed torque control law, and is fed by the wheel velocity estimates generated by a system-dynamics based sliding mode observer. The designed adaptive control scheme is simulated for the users with symmetric and asymmetric gait patterns.
{"title":"Adaptive control of intelligent walker guided human-walker systems","authors":"Nursefa Zengin, Halit Zengin, B. Fidan","doi":"10.1109/IRIS.2017.8250119","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250119","url":null,"abstract":"Intelligent walkers (i-walkers) need to have precise torque generation to sustain safe human-walker motion. Utilizing a recently developed control oriented system model that involves the physical-human walker interaction (pHWI) based on the user gait dynamics and characteristics, this paper studies an adaptive control scheme design for high precision trajectory tracking of the i-walker robust to user gait dynamics, body pose and weight. The proposed control scheme involves a backstepping based kinematic controller to generate reference i-walker velocities that match the pre-defined i-walker trajectories. These desired velocities are tracked applying the torques generated by an adaptive sliding mode control (SMC) scheme that is robust to unknown torque disturbance arising from friction forces, center of gravity displacement and load changes due to pHWI. The proposed SMC scheme design contains a feedback linearization unit based on the computed torque control law, and is fed by the wheel velocity estimates generated by a system-dynamics based sliding mode observer. The designed adaptive control scheme is simulated for the users with symmetric and asymmetric gait patterns.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115805453","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 : 2017-10-01DOI: 10.1109/IRIS.2017.8250113
Nicolas Pedneault, A. Crétu
Acquisition of tactile data requires a direct contact with the object, and in order to achieve object recognition, the process of moving and positioning the sensor to probe the object surface is often time consuming. The paper explores the use of visual information, in form of features extracted by a visual attention system, to guide the tactile data acquisition process. To reduce the effort and time required by the real data collection, the data acquisition procedure is first simulated. This enables the identification of the most promising selective data acquisition algorithm that allows for the recognition of the probed objects based on the acquired tactile data. Several features and classifiers are tested for this purpose. Among them, an improved version of a computational visual attention model associated with the k-nearest neighbors algorithm obtained the best performance (94.51%) during the simulation, while a performance of 68.75% is obtained with the same visual attention model combined with the Naïve Bayes algorithm when using real measurements collected with a piezo-resistive tactile sensor array.
{"title":"3D object recognition from tactile data acquired at salient points","authors":"Nicolas Pedneault, A. Crétu","doi":"10.1109/IRIS.2017.8250113","DOIUrl":"https://doi.org/10.1109/IRIS.2017.8250113","url":null,"abstract":"Acquisition of tactile data requires a direct contact with the object, and in order to achieve object recognition, the process of moving and positioning the sensor to probe the object surface is often time consuming. The paper explores the use of visual information, in form of features extracted by a visual attention system, to guide the tactile data acquisition process. To reduce the effort and time required by the real data collection, the data acquisition procedure is first simulated. This enables the identification of the most promising selective data acquisition algorithm that allows for the recognition of the probed objects based on the acquired tactile data. Several features and classifiers are tested for this purpose. Among them, an improved version of a computational visual attention model associated with the k-nearest neighbors algorithm obtained the best performance (94.51%) during the simulation, while a performance of 68.75% is obtained with the same visual attention model combined with the Naïve Bayes algorithm when using real measurements collected with a piezo-resistive tactile sensor array.","PeriodicalId":213724,"journal":{"name":"2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114705022","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：