Mobile Robots motion planning New Challenges_1 pdf

Mobile Robots motion planning New Challenges Mobi le Rob ots M otio n Planni ng New Challenges Edited by Xing-Jian Jing I-Tech Published by In-Teh In-Teh is Croatian branch of I-Tech Education and Publishing KG, Vienna, Austria. Abstracting and non-profit use of the material is permitted with credit to the source. Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published articles. Publisher assumes no responsibility liability for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained inside. After this work has been published by the In-Teh, authors have the right to republish it, in whole or part, in any publication of which they are an author or editor, and the make other personal use of the work. © 2008 In-teh www.intehweb.com Additional copies can be obtained from: publication@ars-journal.com First published June 2008 Printed in Croatia A catalogue record for this book is available from the University Library Rijeka under no. 111214075 Mobile Robots Motion Planning, Edited by Xing-Jian Jing p. cm. ISBN 978-953-7619-01-5 1. Mobile Robots. 2. Motion Planning. I. Xing-Jian Jing Preface As an important extension of the motor capability of human being, mobile robots are now expected to implement various tasks and have become important tools in all kinds of appli- cation fields, such as manufacturing plants, warehouses, nurse/medical service, tour guider, resource or space exploration, NANO manipulation, national defence and so on. In the fam- ily of mobile robots, humanoid robots, robot pets or toys and robot assistants etc have now been becoming some new research and application trends, and more and more potential applications of mobile robots are emerging. In all these research and applications, a reliable and effective motion planning method plays a considerably important role in the successful completion of the corresponding tasks and purposes. The motion control problem of mobile robots, for example robot-cup competition, is also regarded as an effective platform in many institutes to study, test and demonstrate computationally intelligent methods and advanced control theories. For these reasons, the motion planning problem of mobile robots has been extensively studied in the field of robotics, and many noticeable methods have been pro- posed for different purposes. The motion planning of mobile robots relies greatly on the known information about the involved environment perceived by sensors and the motion constraints of the robotic kine- matics and dynamics. If the environment is static, well structured and completely known, there is usually less difficulty in the motion planning problems, which can be solved by us- ing many existing path planning methods. However, when the environment is partially or totally unknown, unstructured, or dynamic changing, the demand of high autonomy for a mobile robot in such an environment will produce a great challenge for the motion planning task. For example, what sensors or energy supply should be adopted, how to model the en- vironment with limited and noised environmental information from sensors, how to build the on line decision-making system of the robot, and how to find a satisfactory or optimal solution in real time which satisfies both the kinematical or dynamic constraints of the robot and the desired goal of the task, etc. Furthermore, the flexible and friendly interaction be- tween mobile robots and environment including human being is more and more in great demand in many practical applications. All these provide great challenges to robotic tech- niques including sensor or video signal processing and communication, pattern recognition, online intelligent decision making, robust motion control, mechanical structure and sensor device design etc. These problems are all the hot research topics covered by current robotic literature, and lots of efforts have been made to cope with these challenges. In this book, new results or developments from different research backgrounds and ap- plication fields are put together to provide a wide and useful viewpoint on these headed re- search problems mentioned above, focused on the motion planning problem of mobile ro- bots. These results cover a large range of the problems that are frequently encountered in the motion planning of mobile robots both in theoretical methods and practical applications including obstacle avoidance methods, navigation and localization techniques, environ- mental modelling or map building methods, and vision signal processing etc. Different methods such as potential fields, reactive behaviours, neural-fuzzy based methods, motion control methods and so on are studied. Through this book and its references, the reader will definitely be able to get a thorough overview on the current research results for this specific topic in robotics. The book is intended for the readers who are interested and active in the field of robotics and especially for those who want to study and develop their own methods in motion/path planning or control for an intelligent robotic system. Editor Xing-Jian Jing University of Sheffield United Kingdom X.J.Jing@sheffield.ac.uk VII Contents Preface V 1. Local Autonomous Robot Navigation using Potential Fields 001 Miguel A. Padilla Castañeda, Jesús Savage, Adalberto Hernández and Fernando Arámbula Cosío 2. Foundations of Parameterized Trajectories-based Space Transformations for Obstacle Avoidance 023 J.L. Blanco, J. González and J.A. Fernández-Madrigal 3. Text Detection and Pose Estimation for a Reading Robot 039 Marius Bulacu, Nobuo Ezaki and Lambert Schomaker 4. Robust Vision-only Mobile Robot Navigation with Topological Maps 063 Toon Goedemé and Luc Van Gool 5. A Practical Approach for Motion Planning of Wheeled Mobile Robots 089 Luis Gracia and Josep Tornero 6. SOVEREIGN: An Autonomous Neural System for Incrementally Learning to Navigate Towards a Rewarded Goal 099 William Gnadt and Stephen Grossberg 7. Stereo Matching and 3D Reconstruction via an Omnidirectional Stereo Sensor 123 Lei He, Chuanjiang Luo, Feng Zhu and Yingming Hao 8. Motion Estimation of Moving Target using Multiple Images in Intelligent Space 143 TaeSeok Jin and Hideki Hashimoto 9. Robot Tracking using the Particle Filter and SOM in Networked Robotic Space 163 TaeSeok Jin 10. Artificial Coordinating Field based Motion Planning of Mobile Robots 173 Xing-Jian Jing and Yue-Chao Wang 11. Minimum-Energy Motion Planning for Differential-Driven Wheeled Mobile Robot 193 Chong Hui Kim and Byung Kook Kim VIII 12. Performance Evaluation of Potential Field based Distributed Motion Planning Methods for Robot Collectives 227 Leng-Feng Lee and Venkat N. Krovi 13. Motion Planning of Intelligent Explorer for Asteroid Exploration Mission 243 Takashi Kubota, Tatsuaki Hashimoto and Junichiro Kawaguchi 14. Modification of Kohonen Rule for Vehicle Path Planing by Behavioral Cloning 261 Ranka Kuli 15. An Immunological Approach to Mobile Robot Navigation 291 Guan-Chun Luh and Wei-Wen Liu 16. A Mobile Computing Framework for Navigation Tasks 319 Mohammad R. Malek, Mahmoud R. Delavar and Shamsolmolook Aliabady 17. Planning with Discrete Harmonic Potential Fields 335 Ahmad A. Masoud 18. Mobile Robot with Preliminary-announcement and Indication of Scheduled Route and Occupied Area using Projector 361 Takafumi Matsumaru 19. Occupancy Grid Maps for Localization and Mapping 381 Adam Milstein 20. Neuro-Fuzzy Navigation Technique for Control of Mobile Robots 409 Dr. Dayal R. Parhi 21. Spatial Reasoning with Applications to Mobile Robotics 433 Lech Polkowski and Pawel Osmialowski 22. Automated Static and Dynamic Obstacle Avoidance in Arbitrary 3D Polygonal Worlds 455 J.M.P. van Waveren and Drs. dr. L.J.M. Rothkrantz 23. Reactive Motion Planning for Mobile Robots 469 Abraham Sánchez, Rodrigo Cuautle, Maria A. Osorio and René Zapata 24. Integrating Time Performance in Global Path Planning for Autonomous Mobile Robots 487 A. R. Diéguez, R. Sanz and J. L. Fernández 25. Building Internal Maps of a Mobile Robot 503 Branko  ter and Andrej Dobnikar IX 26. Cooperative Indoor Navigation using Environment-Embedded Assistance Devices 517 Tsuyoshi Suzuki, Kuniaki Kawabata, Daisuke Kurabayashi, Igor E. Paromtchik and Hajime Asama 27. Nonlinear Motion Control of Mobile Robot Dynamic Model 529 Jasmin Velagic, Bakir Lacevic and Nedim Osmic 28. Planning for Unraveling Deformable Linear Objects Based on Their Silhouette 551 Hidefumi Wakamatsu, Eiji Arai and Shinichi Hirai 29. Smoothing of Piecewise Linear Paths 563 Michel Waringo and Dominik Henrich 30. A Novel Feature Extraction Algorithm for Outdoor Mobile Robot Localization 583 Sen Zhang, Wendong Xiao and Lihua Xie [...]... Connolly C.I., Burns J.B., and Weiss R (1990), Path planning using Laplace's equation, Proc lEEEConf on Robotics and Automation, pp 2102-2106, Cincinnati, OH Ge S.S And Cui Y.J (2002), “Dynamic motion planning for mobile robots using potential field method”, Autonomous Robots, 13, 207-222 Ge S.S and Cui Y.J (2000), New Potential Functions for Mobile Robot Path Planning, IEEE Transactions on Robotics and Automation,... Algorithms in Search, Optimisation, and Machine Learning, Addison-Wesley, MA 22 Mobile Robots Motion Planning, New Challenges Grefenstette J and Schultz A.C (1994), An evolutionary approach to learning in robots, In Proceedings of the Machine Learning Workshop on Robot Learning, Int Conf on Robot Learning, pp 65-72, New Brunswick, N J Guldner J., Utkin V., Hashimoto H (1997), Robot Obstacle Avoidance... kinematically-constrained, any-shape mobile robots in a planar scenario This problem requires finding movements that approach the target location while avoiding obstacles and fulfilling the robot kinematic restrictions Our main contribution is related to the process for detecting free-space around the robot, which is the basis for a reactive 24 Mobile Robots Motion Planning, New Challenges navigator to decide... electrostatics, where points on the workspace represent point charges within a security zone inside ellipsoidal gradients For a single obstacle, they defined the gradient of the harmonic 8 Mobile Robots Motion Planning, New Challenges potential field for a dipole charge as a security circle with radius R with a unit charge at the target point in the origin of the circle and a positive obstacle charge q=... attraction point only; b) use of auxiliary attraction points of varying force intensity and position allow for the generation of resultant forces which guide the robot around the obstacle 10 Mobile Robots Motion Planning, New Challenges 4 Potential field optimization for obstacle avoidance 4.1 Pre-calculated potential fields When the environment where a robot navigates is of the type of an office or a house,... before Figure 9 shows the attraction and repulsions force map, in which a robot navigates from the upper left corner to the lower right one Figure 9 Attraction and repulsions force map 12 Mobile Robots Motion Planning, New Challenges The use of this kind of repulsion and attraction force maps improves the performance of the robot, because it is not necessary to calculate for each of the robot positions... detect and avoid obstacles as the robot moves towards the goal In Arámbula and Padilla (2004) was reported an scheme for online obstacle detection The robot is represented as a particle 14 R Mobile Robots Motion Planning, New Challenges that moves in the configuration space each cell ci C , modelled as a two dimensional grid, where inside C can be occupied by the robot, the goal or the obstacles There is... and cross the copies (offspring); Reinsert offspring in Pop with a generation gap of 0.8; Calculate f for Pop; Select best chromosome and move the robot to the corresponding position; 16 Mobile Robots Motion Planning, New Challenges Increment step_count; If(d=0) finish end 4.3 Potential Field Optimization in a Partially known environment: Experiments and results The genetic algorithm described above... shown five paths produced by the second approach The average time for path completion on a Pentium III PC at 750MHz is 115s with an average path length of 56 cells (i.e.2.05 s/step) 18 Mobile Robots Motion Planning, New Challenges (1) (2) (3) (4) (5) Figure 12 Paths produced by the navigation algorithm, using auxiliary attraction points placed at variable distance from the goal cell Start-goal positions... selection mechanism and sends it to the robot’s actuators Figure 15 shows this type of architecture with two behaviors, one with potential fields and the other with an state machine 20 Mobile Robots Motion Planning, New Challenges Figure 14 Four additional attraction forces are added to the environment to take the robot out of the local minima Figure 15 Behavior architecture used to control the movements . University Library Rijeka under no. 11 1 214 075 Mobile Robots Motion Planning, Edited by Xing-Jian Jing p. cm. ISBN 978-953-7 619 - 01- 5 1. Mobile Robots. 2. Motion Planning. I. Xing-Jian Jing . Robotic Space 16 3 TaeSeok Jin 10 . Artificial Coordinating Field based Motion Planning of Mobile Robots 17 3 Xing-Jian Jing and Yue-Chao Wang 11 . Minimum-Energy Motion Planning for. by: rep1 rep2 0 0 FF 0 OR RG rep dd U dd +≤ ⎧ =∇ = ⎨ > ⎩ rep nn F(q) (9) where 1 2 0 11 () n goal dd d η − =− rep qq F (10 ) 2 1 2 2 0 11 () 2 n goal dd η − =− − rep Fqq (11 ) OR d=∇n