{"title":"Passing over several steps using a pair of step-climbing units for a manual wheelchair user","authors":"Y. Mori, Kaoru Katsumura","doi":"10.1109/ICAR.2017.8023510","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023510","url":null,"abstract":"We have developed a pair of step-climbing units that can be installed in a standard manual wheelchair. We aim to enable manual wheelchair users to establish an independent life that they can lead without assistance. This mechanism is simpler because it uses the capabilities of the wheelchair user. Each unit comprises two actuators and has two degrees of freedom: telescopic motion and rotational motion. We primarily discuss a strategy that enables wheelchair users to climb stairs comprising multiple steps. We additionally use a pair of portable slopes to achieve this task. Results of experiments where users traveled on a pair of slopes that covered a height of 30 cm over two steps confirm the effectiveness of the design.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"16 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134504680","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":"A dense semantic mapping system based on CRF-RNN network","authors":"Jiyu Cheng, Yuxiang Sun, M. Meng","doi":"10.1109/ICAR.2017.8023671","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023671","url":null,"abstract":"Geometric structure and appearance information of environments are main outputs of Visual Simultaneous Localization and Mapping (Visual SLAM) systems. They serve as the fundamental knowledge for robotic applications in unknown environments. Nowadays, more and more robotic applications require semantic information in visual maps to achieve better performance. However, most of the current Visual SLAM systems are not equipped with the semantic annotation capability. In order to address this problem, we develop a novel system to build 3-D Visual maps annotated with semantic information in this paper. We employ the CRF-RNN algorithm for semantic segmentation, and integrate the semantic algorithm with ORB-SLAM to achieve the semantic mapping. In order to get real-scale 3-D visual maps, we use the RGB-D data as the input of our system. We test our semantic mapping system with our self-generated RGB-D dataset. The experimental results demonstrate that our system is able to reliably annotate the semantic information in the resulting 3-D point-cloud maps.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116194865","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":"Model-based Q-learning for humanoid robots","authors":"Than D. Le, An T. Le, D. Nguyen","doi":"10.1109/ICAR.2017.8023674","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023674","url":null,"abstract":"This paper is proposal with regarding reinforcement learning and robotics. It contains our study so far about reinforcement learning problem and Q-learning — one of the methods to solve it. The method is tested both by running on a simulation and on NAO robot. Both are written in high programming language. Since the testing are also done on NAO robot. This paper also includes our understanding about NAO robot and Robotic Operating System (ROS), and our approach to apply Q-learning on NAO robot. In the end, we have been successfully tested Q-learning method and apply it to NAO robot in real-world environment.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129272430","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}
Ceyue Liu, Jiangong Liu, Rodrigo Moreno, Frank Veenstra, A. Faíña
{"title":"The impact of module morphologies on modular robots","authors":"Ceyue Liu, Jiangong Liu, Rodrigo Moreno, Frank Veenstra, A. Faíña","doi":"10.1109/ICAR.2017.8023524","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023524","url":null,"abstract":"Many different types of modular robots have been designed in the last two decades. However, limited research has been done on analyzing which module morphology is able to create better robots for a given task. To address this issue, this paper investigates how the number and position of available connection faces in a module influence the evolvability of the modular robot. In contrast to previous research on modular robots, an analysis of the morphology of the module is done in order to improve and simplify its mechanical design. To this end, we designed a homogeneous module called EMeRGE, and defined the number of connection faces and their relative positions as morphological parameters. Afterwards, we evolved the morphology and control of robots composed of EMeRGE modules in a robotic simulation platform. Simulation results indicate that robots containing modules with only two available connection faces were able to acquire better performance than robots that contained modules using more connection faces for a locomotion task. Finally, the simulated robots were transferred to the real world in the actual modular robot to verify the simulation results.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132275940","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":"Performance study of single-query motion planning for grasp execution using various manipulators","authors":"J. Meijer, Qujiang Lei, M. Wisse","doi":"10.1109/ICAR.2017.8023648","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023648","url":null,"abstract":"This paper identifies high performing motion planners among three manipulators when carrying out grasp executions. Simultaneously, this paper presents useful benchmarking data. Sampling-based motion planners of OMPL available for use in MoveIt! are compared by performing several grasping-related motion planning problems. The performance of the planners is measured by means of solved runs, computing time and path length. Based on the results, recommendations are made for planner choice that shows high performance for the used manipulators.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"5 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120982271","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":"A distributed multi-agent algorithm for topology control in mobile ad-hoc networks","authors":"A. Konak","doi":"10.1109/ICAR.2017.8023525","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023525","url":null,"abstract":"Without requiring a fixed infrastructure, Mobile Ad Hoc Networks (MANETs) has many application areas, including sensor networks, vehicular networks, robot swarms, and disaster emergency networks. On the other hand, MANETs have dynamic topologies that could be disconnected because of the mobility of nodes. This paper presents an improved flocking algorithm to maintain the connectivity of a MANET using autonomous and intelligent agents. In the proposed flocking algorithm, agents modify their behavior parameters dynamically based on the size of their neighborhoods. A simulation study is conducted to investigate the performance of the new algorithm. Simulation results show that the algorithm outperforms earlier approaches.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"48 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120982814","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":"Kinematics and design of a rigid foldable origami robot","authors":"Chonlatit Sanprueksin, Chanikarn Wongviriyawong","doi":"10.1109/ICAR.2017.8023512","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023512","url":null,"abstract":"“Origami” is an art of paper-folding. Recently, origami has been applied to the design of foldable robot structure. There are various folding techniques including the one we studied — Miura-ori. We designed a Miura-ori of non-zero thickness that 1) was made from rigid materials (rigid origami), and 2) contained self-similar units (modular origami). Our design has a maximum thickness of 6 mm, but can be folded up to 180° (complete fold)—equivalent to a zero-thickness origami. In this paper, we presented a novel design of rigid, foldable, modular origami, as well as derived constraints of joint design that enable a complete fold. Moreover, neodymium magnets were placed in the cores of each rotational axis in certain patterns. This not only allows for the structure to have characteristics of self-folding or self-unfolding, but also gives us the ability to control this robot structure using a current-induced magnetic field. When the magnetic field is on, the robot can switch from an unfolding position to a folding position. Such feature presents a potential for this structure to be used as a dynamic “spring” with an adjustable stiffness. This adjustability could be achieved by varying the input current applied to generate the magnetic field. Another application of this mechanism includes reducing shocks, and vibrations that are perpendicular to the structure.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123489923","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":"Simulation study on supporting condition of a robotic gravity compensation system for the prototype test of spacecraft","authors":"Tomohiro Hirata, K. Tsujita","doi":"10.1109/ICAR.2017.8023627","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023627","url":null,"abstract":"In the field of aerospace engineering, gravity compensation of the prototype test is one of the crucial topics. The target of our research is to develop a prototype test system for deployable membrane space structures by using multi robots. In this study, a robotic supporting system for the spacecraft is proposed and is controlled by the force control so as to compensate gravity and deformation. The gravity compensation system requires appropriate supporting conditions of high fidelity of motion in the space without disturbing deployment motion and deformation. In this study, we investigated suitable positions of supporting points through numerical simulation.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126322497","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":"Active perception model extracting object features from unlabeled data","authors":"M. Gouko, Chyon Hae Kim, Yuichi Kobayashi","doi":"10.1109/ICAR.2017.8023659","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023659","url":null,"abstract":"In this paper, we developed an active perception model for a robot. Active perception is defined as the recognition using categories based on robot's behaviors. The behavior for extracting the object feature is called an exploratory behavior. Several models which acquire exploratory behaviors by learning have been proposed. In the past, we also have proposed a model that is able to learn suitable exploratory behaviors by a reinforcement learning. However, these previous models need the information of the label to which the objects belong during learning. Then, it is difficult to apply these models to acquisition of the category of an unknown object. In this paper, we improve the model that we proposed previously. We develop the model that is able to learn exploratory behaviors without the object's label. Mobile robot simulations are performed to verify the effectiveness of the model. The results indicated that the model can not only acquire the exploratory behavior but also form the categories of the object's features.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129293915","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}
Miguel Angel Bermeo Ayerbe, David S. González, Fabian Andres Merchan Jimenez, Enríque González Guerrero, Alejandra María González Correal
{"title":"AIO robot: A EDI modular robotic dramatization platform","authors":"Miguel Angel Bermeo Ayerbe, David S. González, Fabian Andres Merchan Jimenez, Enríque González Guerrero, Alejandra María González Correal","doi":"10.1109/ICAR.2017.8023528","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023528","url":null,"abstract":"This article presents a logical architecture of a modular robotic platform oriented to dramatization that was implemented and tested in a robotic prototype. The theater play is controlled by a multi-agent system; a director agent synchronizes several robotic actors to perform a theater script. The architectural decisions of the actor agent are based on the BDI model which includes an emotional module that influences the way the agent performs actions. A centralized multi-agent protocol controls the simultaneous motion of several robotic actors. Furthermore, each actor agent has an intermediary module, called SOCA, connecting it with its sensor and action modules. The SOCA module makes flexible and transparent the communication and serves as coordinator and synchronizer; the aim is to make easier to modify the robot physical and logical configuration as required by an actor that must change accordingly to the represented character. A robotic prototype was implemented to validate this architecture and the communication scheme. It includes four modules: processing, mobility, audiovisual and manipulation. The basic experimental results show that the robot actor is well suited to perform drama scripts in educational contexts.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115110959","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}