{"title":"Online learning of inverse dynamics via Gaussian Process Regression","authors":"J. Cruz, W. Owen, D. Kulić","doi":"10.1109/IROS.2012.6385817","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385817","url":null,"abstract":"Model-based control strategies for robot manipulators can present numerous performance advantages when an accurate model of the system dynamics is available. In practice, obtaining such a model is a challenging task which involves modeling such physical processes as friction, which may not be well understood and difficult to model. This paper proposes an approach for online learning of the inverse dynamics model using Gaussian Process Regression. The Sparse Online Gaussian Process (SOGP) algorithm is modified to allow for incremental updates of the model and hyperparameters. The influence of initialization on the performance of the learning algorithms, based on any a-priori knowledge available, is also investigated. The proposed approach is compared to existing learning and fixed control algorithms and shown to be capable of fast initialization and learning rate.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"335 1","pages":"3583-3590"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78588425","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}
{"title":"Presenting sharp surface shapes using overlapped vibrotactile stimuli","authors":"T. Sakurai, M. Konyo, S. Tadokoro","doi":"10.1109/IROS.2012.6385975","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385975","url":null,"abstract":"Previous surface shape presenting methods had difficulties in generating high-density tactile information owing to blurriness in tactile images caused by lateral skin deformations. In this study, a new surface shape presenting method is proposed, and it employs overlapping small-amplitude vibrations instead of a single vibration. This method represents the mechanism of stationary boundary contacts (SBCs), a vibrotactile sensitivity enhancement method proposed in a previous research. A series of psychophysical experiments showed that the vibrations overlapping method can significantly enhance the human vibrotactile sensitivity and lead to the production of sharp tactile images. Moreover, the stimuli intensity can be controlled not only by changing the vibration amplitudes but also by changing the phase deviations between vibrations; this enables the presentation of various surface shape patterns that cannot be presented by using the previous SBC method alone.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"100 1","pages":"3300-3307"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73625704","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}
Takehiko Noguchi, Yo Kobayashi, K. Kawamura, Hiroki Watanabe, Yu Tomono, Y. Sekiguchi, Hiroto Seno, Kazutaka Toyoda, M. Hashizume, M. Fujie
{"title":"Application of control modes of a master manipulator for a robotic system to assist with single port endoscopic surgery","authors":"Takehiko Noguchi, Yo Kobayashi, K. Kawamura, Hiroki Watanabe, Yu Tomono, Y. Sekiguchi, Hiroto Seno, Kazutaka Toyoda, M. Hashizume, M. Fujie","doi":"10.1109/IROS.2012.6385581","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385581","url":null,"abstract":"Recently, increased attention has been focused on single port endoscopic surgery (SPS). We have developed a robotic system for SPS with two surgical manipulators: an endoscopic manipulator and a positioning manipulator that moves the endoscope. The robot can manipulate both the position and orientation of the endoscope to achieve the desirable endoscopic field of view. Two methods can be used to operate the endoscopic view: “control corresponding to position” mode and “control corresponding to velocity” mode. Although both are widely used for moving the visual field, the operability of each method has not been examined quantitatively. Thus, we compare the operability of the two methods for adjusting the endoscopic view, and present the results and suitable applications of each method. The results of the quantitative evaluation experiments show that the “control corresponding to position” mode is suitable for short-distance or precise adjustment of the endoscope, whereas the “control corresponding to velocity” mode is better suited to long-distance movement.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"773 1","pages":"1270-1276"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85419867","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}
Yong‐Lae Park, Bor-rong Chen, C. Majidi, R. Wood, R. Nagpal, E. Goldfield
{"title":"Active modular elastomer sleeve for soft wearable assistance robots","authors":"Yong‐Lae Park, Bor-rong Chen, C. Majidi, R. Wood, R. Nagpal, E. Goldfield","doi":"10.1109/IROS.2012.6386158","DOIUrl":"https://doi.org/10.1109/IROS.2012.6386158","url":null,"abstract":"A proposed adaptive soft orthotic device performs motion sensing and production of assistive forces with a modular, pneumatically-driven, hyper-elastic composite. Wrapping the material around a joint will allow simultaneous motion sensing and active force response through shape and rigidity control. This monolithic elastomer sheet contains a series of miniaturized pneumatically-powered McKibben-type actuators that exert tension and enable adaptive rigidity control. The elastomer is embedded with conductive liquid channels that detect strain and bending deformations induced by the pneumatic actuators. In addition, the proposed system is modular and can be configured for a diverse range of motor tasks, joints, and human subjects. This modular functionality is accomplished with a decentralized network of self-configuring nodes that manage the collection of sensory data and the delivery of actuator feedback commands. This paper mainly describes the design of the soft orthotic device as well as actuator and sensor components. The characterization of the individual sensors, actuators, and the integrated device is also presented.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"123 1","pages":"1595-1602"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85690525","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}
{"title":"Iterative smoothing approach using Gaussian mixture models for nonlinear estimation","authors":"Daniel J. Lee, M. Campbell","doi":"10.1109/IROS.2012.6385752","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385752","url":null,"abstract":"An iterative smoothing algorithm is developed using Gaussian mixture models in order to tackle challenging nonlinear estimation problems. Gaussian mixture models naturally capture nonlinear and non-Gaussian systems, while smoothing algorithms provide ability to update using measurements obtained in the past. A tree structure and Gaussian distribution splitting method are proposed to mitigate nonlinearity effects and complexities. Two methods, Children Collapsing and Parent Splitting, are developed to utilize sigma-points smoother for Gaussian mixture model. An indoor localization problem is used to explore and validate the approach. Performance of these new methods is compared to a baseline sigma-points smoother, in both simulation and experiment, and shows much improvement in overall error compared to the truth.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"74 1","pages":"2498-2503"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85792244","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}
{"title":"Bio-inspired visual memory for robot cognitive map building and scene recognition","authors":"K. Rebai, O. Azouaoui, N. Achour","doi":"10.1109/IROS.2012.6385493","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385493","url":null,"abstract":"In this paper, we investigate the feasibility of building a visual memory for robotics spatial cognition without saving visual information. The proposed approach captures some properties of primate brain and especially the view cells. Our bio-inspired visual memory for cognitive map building consists of two main parts. One part is visual information extraction and the other part is the visual memory building using the Fuzzy Art architecture. The results of the current study could contribute to the development of bio-inspired model for cognitive map building which enables the mobile robot to localize itself and build a cognitive representation of its environment simultaneously like primates and humans.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"142 1","pages":"2985-2990"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77791971","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}
{"title":"Planning trajectories on uneven terrain using optimization and non-linear time scaling techniques","authors":"A. Singh, K. Krishna, S. Saripalli","doi":"10.1109/IROS.2012.6385662","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385662","url":null,"abstract":"In this paper we introduce a novel framework of generating trajectories which explicitly satisfies the stability constraints such as no-slip and permanent ground contact on uneven terrain. The main contributions of this paper are: (1) It derives analytical functions depicting the evolution of the vehicle on uneven terrain. These functional descriptions enable us to have a fast evaluation of possible vehicle stability along various directions on the terrain and this information is used to control the shape of the trajectory. (2) It introduces a novel paradigm wherein non-linear time scaling brought about by parametrized exponential functions are used to modify the velocity and acceleration profile of the vehicle so that these satisfy the no-slip and contact constraints. We show that nonlinear time scaling manipulates velocity and acceleration profile in a versatile manner and consequently has exceptional utility not only in uneven terrain navigation but also in general in any problem where it is required to change the velocity of the robot while keeping the path unchanged like collision avoidance.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"33 1","pages":"3538-3545"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78060173","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}
Chaoyang Shi, M. Kojima, C. Tercero, H. Anzai, M. Ohta, K. Ooe, S. Ikeda, T. Fukuda, F. Arai, M. Negoro, K. Irie, Guiryong Kwon
{"title":"A cyber-physical system for strain measurements in the cerebral aneurysm models","authors":"Chaoyang Shi, M. Kojima, C. Tercero, H. Anzai, M. Ohta, K. Ooe, S. Ikeda, T. Fukuda, F. Arai, M. Negoro, K. Irie, Guiryong Kwon","doi":"10.1109/IROS.2012.6385754","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385754","url":null,"abstract":"For the development of artificial intelligent diagnosis for cerebrovascular intervention, it is desirable to forecast the growth of cerebral aneurysms. In order to achieve such purpose, it is needed to evaluate wall shear stress, strain, pressure, deformation and flow velocity in the aneurysm region. In this research, we focus on in-vitro strain and deformation measurements of cerebral aneurysm models, and propose a cyber-physical system, in which a scaled-up membranous silicone model of cerebral aneurysm was built and integrated with a specialized pump for the pulsatile blood flow simulation, and a vision system was constructed to measure the strain on different regions on the model with pulsatile blood flow circulated inside. Experimental results show that both distance and area strain maxima were larger for the aneurysm neck (0.042 and 0.052), followed by the aneurysm dome (0.023 and 0.04) and then by the main blood vessel section (0.01 and 0.014), which were complemented with computer fluid dynamics simulation for the inclusion of wall shear stress, oscillatory shear index and aneurysm formation index. Medical imaging data of the cerebral aneurysm in 2008 and 2011 was obtained. Diagnosis results have concordance with the aneurysm growth in 2011. The presented measurement method offers an option for measuring strain and deformation to be complementary with computer fluid dynamics and photoelastic stress analysis for advanced diagnostic in the endovascular surgery.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"20 1","pages":"4137-4142"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78816144","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}
Yang Bai, James Snyder, Yonatan Silverman, M. Peshkin, M. A. MacIver
{"title":"Sensing capacitance of underwater objects in bio-inspired electrosense","authors":"Yang Bai, James Snyder, Yonatan Silverman, M. Peshkin, M. A. MacIver","doi":"10.1109/IROS.2012.6386174","DOIUrl":"https://doi.org/10.1109/IROS.2012.6386174","url":null,"abstract":"Certain electric fish use a self-generated AC electric field to navigate and hunt. Thousands of sensors on the surface of the fish's body detect the pattern of amplitude and phase distortions of the field caused by nearby objects. Prior research has suggested that phase distortions may be especially useful for recognition of live objects. Here we present the first study of the utility of phase information in a robotic implementation of active electrosense. Using our robotic implementation, we investigated how the phase information depends on the frequency of the emitted field, the conductivity of the surrounding water, and object properties. An analytical model was developed serving as qualitative explanation of the dependency. We show that in certain situations phase information enables discrimination between two objects that are otherwise very similar in the amplitude of their electric images. We also show the utility of probing objects with multiple frequencies.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"358 1","pages":"1467-1472"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76346535","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}
Hongbin Liu, Xiaojing Song, João Bimbo, L. Seneviratne, K. Althoefer
{"title":"Surface material recognition through haptic exploration using an intelligent contact sensing finger","authors":"Hongbin Liu, Xiaojing Song, João Bimbo, L. Seneviratne, K. Althoefer","doi":"10.1109/IROS.2012.6385815","DOIUrl":"https://doi.org/10.1109/IROS.2012.6385815","url":null,"abstract":"Object surface properties are among the most important information which a robot requires in order to effectively interact with an unknown environment. This paper presents a novel haptic exploration strategy for recognizing the physical properties of unknown object surfaces using an intelligent finger. This developed intelligent finger is capable of identifying the contact location, normal and tangential force, and the vibrations generated from the contact in real time. In the proposed strategy, this finger gently slides along the surface with a short stroke while increasing and decreasing the sliding velocity. By applying a dynamic friction model to describe this contact, rich and accurate surface physical properties can be identified within this stroke. This allows different surface materials to be easily distinguished even if when they have very similar texture. Several supervised learning algorithms have been applied and compared for surface recognition based on the obtained surface properties. It has been found that the naïve Bayes classifier is superior to radial basis function network and k-NN method, achieving an overall classification accuracy of 88.5% for distinguishing twelve different surface materials.","PeriodicalId":6358,"journal":{"name":"2012 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"275 1","pages":"52-57"},"PeriodicalIF":0.0,"publicationDate":"2012-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76378025","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}