{"title":"Mobile robot navigation: neural Q-learning","authors":"S. Parasuraman, S. Yun","doi":"10.1504/IJCAT.2012.050118","DOIUrl":"https://doi.org/10.1504/IJCAT.2012.050118","url":null,"abstract":"This paper presents the mobile robot navigation technique which utilises Reinforcement Learning (RL) algorithms and Artificial Neural Network (ANN) to learn in an unknown environment for mobile robot navigation. This research study is focused on the integration of multi-layer neural network and Q-learning as online learning control scheme. This process is divided into two stages. In the initial stage, the agent will map the environment through collecting state-action information according to the Q-learning procedure. Second training process involves neural network which utilises the state-action information gathered in the earlier phase of training samples. During final application of the controller, Q-learning would be used as primary navigating tool whereas the trained neural network will be employed when approximation is needed. MATLAB simulation was developed to verify and validate the algorithm before real-time implementation using Team AmigoBot™ robot. The results obtained from both simulation and real world experiments are discussed.","PeriodicalId":322031,"journal":{"name":"International journal of computer application and technology","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127405874","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":"Tool orientation and motion error in microsurgical parallel manipulator","authors":"M. Rashid, Zahi A. Khalil","doi":"10.1504/IJCAT.2004.004159","DOIUrl":"https://doi.org/10.1504/IJCAT.2004.004159","url":null,"abstract":"Positioning error is inherent in normal human hand motion and limits precision in manual microsurgery. A computer-based surgery can reduce human error. This work discuss tool orientation, motion error and computer simulation of a microsurgical end effector based on a parallel spatial manipulator. Among several previously developed parallel manipulators for other applications, the selected architecture for this work is consisting of a moving platform attached to a base through three identical prismatic-revolute-spherical jointed serial linkages. The actuation is conducted through the prismatic joints while the others are passive. These prismatic actuators lie on a common plane and have radial directions of action. A surgical tool of specific length is attached to the moving platform centre. A computer-based simulation is built for the end effector by obtaining the forward and inverse kinematics solutions. The developed relation for tool tip motion with respect to actuators positioning is used to evaluate tool location and orientation. Architectural designs for two arrangements are compared for better design and positioning error.","PeriodicalId":322031,"journal":{"name":"International journal of computer application and technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115582241","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}