FUTURE MOTION DECISIONS USING STATE-ACTION PAIR PREDICTIONS

Robots that works in a dynamic environment must possess, the ability to autonomously cope with the changes in the environment. This paper proposes an approach to predict changes in the state and actions of robots. Further, this approach attempts to apply predicted future actions to current actions. This method predicts the robot’s state and action for the distant future using the states that the robot adopts repeatedly. Using this method, the actions that the robot will take in the future can be predicted. The method proposed in this paper predicts the state and action of a robot each time it decides to perform an action. In particular, this paper focuses on defining weight coefficients, using the characteristics of the future prediction results. Using this method, the compensatory current action will be obtained. This paper presents the results of our study and discusses methods that allow the robot to quickly determine its most desirable action, using state prediction and optimal control methods.

[1]  Mohammed Faisal,et al.  Fuzzy Logic Navigation and Obstacle Avoidance by a Mobile Robot in an Unknown Dynamic Environment , 2013 .

[2]  Robert Babuska,et al.  Control delay in Reinforcement Learning for real-time dynamic systems: A memoryless approach , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Kok Kiong Tan,et al.  Computation delay compensation for real time implementation of robust model predictive control , 2012, IEEE 10th International Conference on Industrial Informatics.

[4]  Ellips Masehian,et al.  Sensor-Based Motion Planning of Wheeled Mobile Robots in Unknown Dynamic Environments , 2013, Journal of Intelligent & Robotic Systems.

[5]  B. Kuipers,et al.  Robot Navigation with MPEPC in Dynamic and Uncertain Environments : From Theory to Practice , 2012 .

[6]  M Abdel Kareem,et al.  REINFORCEMENT BASED MOBILE ROBOT NAVIGATION IN DYNAMIC ENVIRONMENT , 2011 .

[7]  P. Protzel,et al.  Using the Unscented Kalman Filter in Mono-SLAM with Inverse Depth Parametrization for Autonomous Airship Control , 2007, 2007 IEEE International Workshop on Safety, Security and Rescue Robotics.

[8]  Fabrizio Abrate,et al.  Multi-robot Map Updating in Dynamic Environments , 2010, DARS.

[9]  Shunichi Asaka,et al.  Behavior Control of an Autonomous Mobile Robot in Dynamically Changing Environment , 1994 .

[10]  Mohammad Ali Badamchizadeh,et al.  Extended and Unscented Kalman Filtering Applied to a Flexible-Joint Robot with Jerk Estimation , 2010 .

[11]  Foudil Abdessemed,et al.  SVM-Based Control System for a Robot Manipulator , 2012 .

[12]  Nicolas Schweighofer,et al.  Local Online Support Vector Regression for Learning Control , 2007, 2007 International Symposium on Computational Intelligence in Robotics and Automation.

[13]  Gaurav S. Sukhatme,et al.  Mobile Robot Simultaneous Localization and Mapping in Dynamic Environments , 2005, Auton. Robots.

[14]  Mohammad Teshnehlab,et al.  Adaptive Neuro-Fuzzy Extended Kaiman Filtering for robot localization , 2010, Proceedings of 14th International Power Electronics and Motion Control Conference EPE-PEMC 2010.

[15]  Minoru Asada,et al.  Purposive Behavior Acquisition for a Robot by Vision-Based Reinforcement Learning , 1995 .

[16]  Hiroshi Ishiguro,et al.  Mobile Robot Navigation by a Distributed Vision System , 1999 .

[17]  Isao Ohmura,et al.  2A2-C10 A Study on Model-Based Development of Embedded System using Scilab/Scicos : Development of Auto-Code Generator , 2010 .

[18]  J. G. Iossaqui.  SLIP ESTIMATION USING THE UNSCENTED KALMAN FILTER FOR THE TRACKING CONTROL OF MOBILE ROBOTS , 2011 .

[19]  Giancarlo Marafioti,et al.  State Estimation in Nonlinear Model Predictive Control, Unscented Kalman Filter Advantages , 2009 .

[20]  Mohammad A. Jaradat,et al.  Reinforcement based mobile robot navigation in dynamic environment , 2011 .

[21]  Wen-Hua Chen,et al.  Model predictive control for autonomous helicopters with computational delay , 2010 .

[22]  Francesco Parrella.  Online Support Vector Regression , 2007 .

[23]  Blake Hannaford,et al.  Robustness of the Unscented Kalman filter for state and parameter estimation in an elastic transmission , 2009, Robotics: Science and Systems.

[24]  H. Jin Kim,et al.  Model predictive flight control using adaptive support vector regression , 2010, Neurocomputing.

[25]  Kentarou Kurashige,et al.  Real-time sequentially decision for optimal action using prediction of the state-action pair , 2014, 2014 International Symposium on Micro-NanoMechatronics and Human Science (MHS).

[26]  W. Burgard,et al.  Markov Localization for Mobile Robots in Dynamic Environments , 1999, J. Artif. Intell. Res..

[27]  Wolfram Burgard,et al.  Probabilistic Robotics (Intelligent Robotics and Autonomous Agents) , 2005 .

[28]  Tetsuo Ono,et al.  Development of Robovie as a Platform for Everyday-Robot Research , 2002 .

[29]  Chih-Jen Lin,et al.  Training and Testing Low-degree Polynomial Data Mappings via Linear SVM , 2010, J. Mach. Learn. Res..

[30]  Minoru Asada,et al.  Incremental State Space Segmentation for Behavior Learning by Real Robot , 1999 .

[31]  Kentarou Kurashige,et al.  The proposal for deciding effective action using prediction of internal robot state based on internal state and action , 2013, MHS2013.

[32]  Thomas J. Walsh,et al.  Planning and Learning in Environments with Delayed Feedback , 2007, ECML.