{"title":"The design of LEO: A 2D bipedal walking robot for online autonomous Reinforcement Learning","authors":"E. Schuitema, M. Wisse, T. Ramakers, P. Jonker","doi":"10.1109/IROS.2010.5650765","DOIUrl":"https://doi.org/10.1109/IROS.2010.5650765","url":null,"abstract":"Real robots demonstrating online Reinforcement Learning (RL) to learn new tasks are hard to find. The specific properties and limitations of real robots have a large impact on their suitability for RL experiments. In this work, we derive the main hardware and software requirements that a RL robot should fulfill, and present our biped robot LEO that was specifically designed to meet these requirements. We verify its aptitude in autonomous walking experiments using a pre-programmed controller. Although there is room for improvement in the design, the robot was able to walk, fall and stand up without human intervention for 8 hours, during which it made over 43; 000 footsteps.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115099585","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":"Kineto-static mechanical synthesis for nonlinear property design of passive stiffness using closed kinematic chain","authors":"M. Okada, Jun Takeishi","doi":"10.1109/IROS.2010.5651126","DOIUrl":"https://doi.org/10.1109/IROS.2010.5651126","url":null,"abstract":"To prevent the human injury or breakage of the robot caused by interaction or collision with the robot and its environment, it is an important issue to introduce robot softness. However, because not only softness but also stiffness is required for precise task execution, the simultaneous realization of softness and stiffness using time varying stiffness is required in the real environment. We focus on the robot motion, and propose a realization method of time varying stiffness using robot motion and nonlinear passive stiffness. To realize the purpose-designed property of the time dependent stiffness, the nonlinear property of the passive stiffness has to be arbitrary designed considering the robot dynamics. In this paper, we propose the nonlinear property design method of passive stiffness based on kineto-statics with closed kinematic chain. The mechanism is synthesized based on the optimization of the generative force or torque, and purpose-designed stiffness is realized. The proposed method is evaluated by simulations and experiments using the prototype of the landing mechanism.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116916900","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}
N. Takesue, T. Ohara, R. Ishibashi, S. Toyama, M. Hoshina, Y. Hirai, N. Fukaya, J. Arata, H. Fujimoto
{"title":"Position control methods of spherical ultrasonic motor","authors":"N. Takesue, T. Ohara, R. Ishibashi, S. Toyama, M. Hoshina, Y. Hirai, N. Fukaya, J. Arata, H. Fujimoto","doi":"10.1109/IROS.2010.5650918","DOIUrl":"https://doi.org/10.1109/IROS.2010.5650918","url":null,"abstract":"In this paper, we investigate the position control of spherical ultrasonic motor (SUSM). The generated torque of SUSM is influenced by the phase difference and the driving frequency of applied AC voltages. Therefore, the control strategy is classified into three types: (a) variable phase and fixed frequency, (b) fixed phase and variable frequency, and (c) variable phase and frequency. We formulate the position control rules for SUSM based on the above three types of control variables, and investigate the performances experimentally.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116993131","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":"Temporal and spatial 3D motion vector filtering based visual odometry for outdoor service robot","authors":"G. Kwon, Yeong Nam Chae, H. Yang","doi":"10.1109/IROS.2010.5651064","DOIUrl":"https://doi.org/10.1109/IROS.2010.5651064","url":null,"abstract":"This paper describes a visual odometry algorithm that deals with the nearly degenerated situation caused by a false motion vector generated by independently moving objects, repetitive patterns and wrong depth information that often arise in visual odometry for outdoor service robots. To filter out these false motion vectors, we use temporal and spatial motion vector filter. The temporal motion vector filter uses the previous motion models to filter out abruptly changed motion vectors, and the spatial motion vector filter uses the motion vector's length information and the motion vector's direction information. The direction information of the motion vectors generated by independently moving objects are different from the direction of the vector generated by camera movement in 3D space, and the length information of the motion vector caused by triangulation error is different from the correctly triangulated points. We uses voting scheme to determine primary motion vectors. This algorithm has been tested on a service robot that works in outdoor environment. By using our method, we can deal with independently moving objects and problem caused by repetitive patterns and triangulation errors.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115991852","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}
Heon-Cheol Lee, Seung-Hwan Lee, Doo-Jin Kim, Beomhee Lee
{"title":"Visual route navigation using an adaptive extension of Rapidly-exploring Random Trees","authors":"Heon-Cheol Lee, Seung-Hwan Lee, Doo-Jin Kim, Beomhee Lee","doi":"10.1109/IROS.2010.5649741","DOIUrl":"https://doi.org/10.1109/IROS.2010.5649741","url":null,"abstract":"This paper proposes an adaptive and probabilistic extension of Rapidly-exploring Random Tree (RRT) for visual route navigation of a mobile robot. Using measurements from cameras and infrared range sensors, a temporary local map is built probabilistically with Gaussian processes and adaptively to the change of the route curvature. Based on the probabilistic map, RRT searches the most robust and efficient local path with the probability of collision, and the robot is controlled along the selected path. The performance of the proposed method was verified by reducing not only centering error and standard deviation in simulations but also travel time in real experiments.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123404891","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}
Jwusheng Hu, Ming-Chih Chien, Yung-Jung Chang, Yen-Chung Chang, S. Su, Jwu-Jiun Yang, Chen-Yu Kai
{"title":"A robotic ball catcher with embedded visual servo processor","authors":"Jwusheng Hu, Ming-Chih Chien, Yung-Jung Chang, Yen-Chung Chang, S. Su, Jwu-Jiun Yang, Chen-Yu Kai","doi":"10.1109/IROS.2010.5648912","DOIUrl":"https://doi.org/10.1109/IROS.2010.5648912","url":null,"abstract":"In this work we present a robotic ball catcher with embedded visual servo processor. The embedded visual servo processor with powerful parallel computing capability is used as the computation platform to track and triangulate a flying ball's position in 3D based on stereo vision. A recursive least squares algorithm for model-based path prediction of the flying ball is used to determine the catch time and position. Experimental results for real time catching of a flying ball are presented by a 6-DOF robot arm. The percentage of success rate of the robotic ball catcher was found to be approximately 60% for the ball thrown to it from five meters away.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123577028","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}
S. Aoi, Tsuyoshi Yamashita, Akira Ichikawa, K. Tsuchiya
{"title":"Hysteresis in gait transition induced by changing waist joint stiffness of a quadruped robot driven by nonlinear oscillators with phase resetting","authors":"S. Aoi, Tsuyoshi Yamashita, Akira Ichikawa, K. Tsuchiya","doi":"10.1109/IROS.2010.5650447","DOIUrl":"https://doi.org/10.1109/IROS.2010.5650447","url":null,"abstract":"In this paper, we investigated the locomotion of a quadruped robot whose front and rear bodies are connected by a roll joint. The legs of the robot are controlled by nonlinear oscillators with phase resetting. Based on numerical simulations, we showed that the robot produces various gait patterns through dynamical interactions among the robot mechanical system, oscillator control system, and environment and establishes gait transition induced by the change of the roll joint stiffness. In addition, we demonstrated that a hysteresis with respect to gait pattern occurs during the gait transition similarly to humans and animals, and we examined the mechanisms of the hysteresis from a dynamic viewpoint.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122000275","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":"Addressing input saturation and kinematic constraints of overactuated undercarriages by predictive potential fields","authors":"C. Connette, A. Pott, M. Hägele, A. Verl","doi":"10.1109/IROS.2010.5652685","DOIUrl":"https://doi.org/10.1109/IROS.2010.5652685","url":null,"abstract":"Currently, pseudo-omnidirectional, wheeled mobile robots with independently steered and driven wheels seem to provide a solid compromise between complexity, flexibility and robustness. Yet, such undercarriages are imposed to the risk of actuator fighting and suffer from singular regions within their configuration space. To address these problems we expand a previously developed potential field (PF) based approach by expanding it with a predictive horizon. The proposed method is based on a model predictive control (MPC) approach, incorporating a gradient descent optimization step via the Pontryagin minimum principle. To enforce adherence to the constraints during optimization, we modify the Lagrange-multipliers within the backpropagation of the costates. The proposed approach is evaluated simulatively w.r.t. the undercarriage of the Care-O-bot ® 3 mobile robot and is compared to the potential field based and a model predictive control approach.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122022234","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}
Sungjun Park, Changhoon Seo, Jong-Phil Kim, J. Ryu
{"title":"An energy-bounding approach to rate-mode bilateral teleoperation of remote vehicles in constant time-delayed environments","authors":"Sungjun Park, Changhoon Seo, Jong-Phil Kim, J. Ryu","doi":"10.1109/IROS.2010.5651575","DOIUrl":"https://doi.org/10.1109/IROS.2010.5651575","url":null,"abstract":"This paper presents an energy-bounding approach to a rate-mode bilateral control of remote vehicles in order to guarantee the system stability in constant time-delayed telecommunication environments. The velocity error between desired and actual remote vehicle velocities is reflected in term of force in order to maintain desired velocities by the operator both during the normal driving in obstacle-free environments and when colliding with a high impedance wall. A rate-mode energy-bounding algorithm is devised for these teleoperation scenarios in order to sensitively feel the velocity difference while keeping interaction stability. Effectiveness of the proposed approach is shown by some experimental results in the simulated constant time-delayed environments for vehicles not only in free space but also in contact motions.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116823086","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":"Motion estimation based on predator/prey vision","authors":"D. V. D. Lijn, G. D. Lopes, Robert Babuška","doi":"10.1109/IROS.2010.5653247","DOIUrl":"https://doi.org/10.1109/IROS.2010.5653247","url":null,"abstract":"We present an unscented Kalman filter based state estimator for a fast moving rigid body (such as a mobile robot) endowed with two video cameras. We focus on forward velocity estimation towards the computation of standard energy cost functions for legged locomotion. Points are chosen as image features and the model of each camera is based on the traditional pinhole projection. The resulting filter's state is composed of the rigid body pose and velocities, together with a measure of depth for each tracked point. By taking inspiration from nature's large predatory and grazing mammals eye configuration, we suggest, via simulation results, a solution for the question of finding the best orientation of two cameras, between side and frontal facing, for velocity estimation in a forward moving robot.","PeriodicalId":420658,"journal":{"name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","volume":"214 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120868242","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}