{"title":"Motion generation for bipedal robot using neuro-musculo-skeletal model and Simulated Annealing","authors":"K. Taki, Y. Itoh, Shohei Kato, H. Itoh","doi":"10.1109/RAMECH.2004.1438003","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438003","url":null,"abstract":"We propose a stochastic approach to CPG-based motion generation of a bipedal robot. We make an extension to a motion control system based on a neuro-musculoskeletal model into three dimensions, and give an optimization of control parameters by simulated annealing. Not only do we obtain walking motion by our approach but provide some empirical verification of various walking patterns adaptive to different link structures. In addition to straight walking, this paper gives the performance results of turning walk to right and left.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"6402 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126380833","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":"Multiple obstacles avoidance for mobile robot in unstructured environments","authors":"Feng Zhang, D. Tan, Zhenwei Wu","doi":"10.1109/RAMECH.2004.1438906","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438906","url":null,"abstract":"This paper focuses on multiple obstacles avoidance for mobile robot and presents novel obstacle avoidance maneuvers mainly by defining degree of risk and using fuzzy method. The methods are based on the relative coordinates and acceleration space in unstructured environments, where there exist not only multiple static obstacles, but also multiple moving ones. The simulation results verify its validity.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125171998","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":"Position and force control of robot manipulators using neural networks","authors":"Yu Zhao, C. Cheah","doi":"10.1109/RAMECH.2004.1438935","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438935","url":null,"abstract":"Most research on force control of robot manipulators has assumed that the kinematics and constraint surface are known exactly. In this paper, the position and force control problem of robots with uncertain kinematics, dynamics and constraint is addressed. An adaptive set point control law based on neural networks is proposed. Sufficient conditions for choosing the feedback gains are presented to guarantee the stability. Simulation results are presented to demonstrate the effectiveness of the proposed controller.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121820457","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}
Yoshihiro Tabuchi, N. Abe, Kazuaki Tanaka, Hiroaki Taki
{"title":"Development of touch sensor with optical positional sensor","authors":"Yoshihiro Tabuchi, N. Abe, Kazuaki Tanaka, Hiroaki Taki","doi":"10.1109/RAMECH.2004.1438917","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438917","url":null,"abstract":"Recently, the news related to robots is often taken up. The research on the mechanism of the robot and its hand finds constant directionality by the average. However, a good method for controlling them is not proposed. If a robot with the complete independence is required for production, it is necessary to incorporate a variety of sense organs into them such as a visual system to recognize the environment, auditory one to react to the voice and sense of touch to detect contact with an object. It is, however, difficult to equip a robot with these five feelings like a human. Then, it is preferable to apply a necessary sensor responding to the system requirements. Thus, it is very important to consider which types of sensors should be applied to the robot. The accuracy of the sensor is very important, but at the same time the cost and size must be regarded to make the robot use and control them. A new touch sensor is introduced in this paper which is most important for the robot to grasp an object and manipulate it. The effectiveness of the sensor is shown. We have succeeded in reducing more than 90% of traditional sensors.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124745797","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":"Parameter tuning of production scheduling rules by an ant system-embedded genetic algorithm","authors":"T. Chiang, L. Fu","doi":"10.1109/RAMECH.2004.1438071","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438071","url":null,"abstract":"In this paper, a search algorithm is proposed for parameter tuning of production rules in job shop scheduling problems. This algorithm is developed based on the genetic algorithm, which is the core for exploration in the search space. Then an ant system is incorporated, which directs the genetic algorithm to search in the potential regions by marking potential genes for changing during reproduction. The improvement of search ability is verified by several experiments.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131340420","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. Khanmohammadi, A. Aghagolzadeh, M. Amjadi, R. Esmaeilzadeh, A. Ghanbari
{"title":"Application of fuzzy controller for a special triangle robot with two degrees of freedom","authors":"S. Khanmohammadi, A. Aghagolzadeh, M. Amjadi, R. Esmaeilzadeh, A. Ghanbari","doi":"10.1109/RAMECH.2004.1438086","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438086","url":null,"abstract":"In this paper a new robot with two degrees of freedom is designed and the dynamic model of the system, based on precise mathematical equations, is determined. It is shown that this new triangle robot can be used in filling taking and sketching applications in industry. A simple controlling rule, based on fuzzy theory, is introduced for application in a robotic system. This robot can be used with different applications in the automobile industry. The laboratory sample that is designed in this work can be developed and used in different production lines, especially in hierarchical and hybrid systems as a pointer, dyer and filling taker robot. The computer based simulation results show that application of fuzzy rules for controlling this type of robot leads to better results than classical PID methods. The characteristics of the introduced robot are studied.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125504229","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":"Formal languages aspects as a tool for representation and implementation of behavior-based robotics","authors":"R. Vieira, M. Roisenberg, Olinto J. V. Furtado","doi":"10.1109/RAMECH.2004.1438048","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438048","url":null,"abstract":"Behavior-based robotics has its foundations on the emergence of robotic behaviors, and aims to providing intelligence and autonomy to actions performed by agents in search of their goals. Although there is a great variety of research in this field, there are not many works about the formalization of the concepts related to the cognitive entity of the autonomous agents (AAs). This paper makes an effort to establish a parallel with natural models in order to achieve insights of how the robotic behaviors can be represented and set up. The Chomsky hierarchy automata are taken into account as sufficient models to represent the features of the live beings' memory. In this way, we consider that a pushdown automata (PDA) can represent the short-term memory, and the Turing machine (TM) can work as a long-term memory. Besides, in order to implement in AAs the concepts concerning to these automata, a new robotic control architecture is proposed, which has its building blocks in the modular and hierarchical functioning of the brain.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130550420","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":"Design of an ultra-precision vibration isolation system by imitating the special organic texture of woodpecker's brain","authors":"Mei Deqing, Yang Keji, Chen Zichen","doi":"10.1109/RAMECH.2004.1438966","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438966","url":null,"abstract":"In this paper, a bionic structure model of ultra-precision vibration isolation system is presented by imitating the special organic texture of woodpecker's brain. The vibration isolation system mainly consists of giant magnetostrictive actuators, air-springs, a pedestal and a rubber layer. The air-springs are used to reduce high frequency vibrations, and the giant magnetostrictive actuators are used to reduce low or ultra-low frequency vibrations. In order to reduce thermal distortion caused by temperature rise of coil, a constant temperature cooling system is developed for giant magnetostrictive actuator. In consideration of complex vibration environment and self-nonlinearity of vibration isolation system, a two dimensional fuzzy active control system with two regulation factors is designed. The experiment results show that the bionic vibration isolation system has good performance against floor disturbances. It can be applied to the vibration isolation system of the ultra-precision measuring and manufacturing devices.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"136 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120851418","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}
Jongbaek Lee, Chang-Woo Park, Joongki Chung, Ha-Gyeong Sung
{"title":"Digital stabilization of fuzzy systems with network-delay","authors":"Jongbaek Lee, Chang-Woo Park, Joongki Chung, Ha-Gyeong Sung","doi":"10.1109/RAMECH.2004.1438974","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438974","url":null,"abstract":"This paper presents the design methodology of digital fuzzy controller (DFC) for the systems with time-delay. We propose the fuzzy feedback controller whose output is delayed with unit sampling period and prediction. The analysis and the design problem considering time-delay become easy because the proposed controller is synchronized with the sampling time. The stabilization problem of the digital fuzzy system with time-delay is solved by linear matrix inequality (LMI) theory. Convex optimization techniques are utilized to solve the stable feedback gains and a common Lyapunov function for the designed fuzzy control system. To show the effectiveness of the proposed control scheme, the network control example is presented.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132715568","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":"Composite rules selection using reinforcement learning for dynamic job-shop scheduling","authors":"Yingzi Wei, Mingyang Zhao","doi":"10.1109/RAMECH.2004.1438070","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438070","url":null,"abstract":"Dispatching rules are usually applied dynamically to schedule the job in the dynamic job-shop. Existing scheduling approaches seldom address the machine selection in the scheduling process. Following the principles of traditional dispatching rules, composite rules, considering both the machine selection and job selection, were proposed in this paper. Reinforcement learning (IRL) is an on-line actor critic method. The dynamic system is trained to enhance its learning and adaptive capability by a RL algorithm. We define the conception of pressure for describing the system feature and determining the state sequence of search space. Designing a reward function should be guided based on the scheduling goal. We present the conception of jobs' estimated mean lateness (EMLT) that is used to determine the amount of reward or penalty. The scheduling system is trained by Q-learning algorithm through the learning stage and then it successively schedules the operations. Competitive results with the RL-agent approach suggest that it can be used as real-time optimal scheduling technology.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133373757","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}