Word Files
Reference for Downloading Educational Files
  2. Computer Engineering
  3. A selective method for side-to-side walking in humanoid robots

A selective method for side-to-side walking in humanoid robots

Number of pages: 103 File Format: word File Code: 31070
Year: Not Specified University Degree: Master's degree Category: Computer Engineering
Tags/Keywords: artificial intelligence - Artificial intelligence algorithms - Humanoid robot - Humanoid robots - robocop - Robot football - Robot Nao - Robotics - Seafaring robots - Walking from side to side in a robot
  • Part of the Content
  • Contents & Resources

  • Summary of A selective method for side-to-side walking in humanoid robots

    Master's thesis in the field of computer engineering - artificial intelligence

    Abstract

    A selective method for side-to-side walking in humanoid robots

     

     

    Nowadays, humanoid robot walking is one of the interesting fields of research in the field of robotics. The challenges in controlling humanoid robots with high degrees of freedom have placed this problem among the difficult problems in the field of robotics, so that the walking of humanoid robots is still classified as the most important ability of a robot. In this thesis, a new method for humanoid robots to walk from the side has been proposed. In this method, a variable learning automata is mounted on each of the effective joints in the robot's walking, which is updated during the learning process of the probability vectors related to the automata, and the appropriate values ??of the joints for walking are selected according to these vectors. In the following, this learning method is used for straight walking and lateral walking, and the results of the algorithm simulation on Nao humanoid robot in a 3D football simulation environment show good results in straight robot walking compared to previous methods, as well as many advantages of improving the ability to walk from lateral in a humanoid robot.

    Key words

    Robocup, soccer robots, humanoid robots, Nao robot walking, automata Yadgir

     

     

    Chapter One:

    Introduction

    Nowadays, robotics [1] as one of the fields of science and engineering, has attracted the attention of many research institutes and has become one of the most attractive areas of research and research, so that research in the field of robotics is being pursued in various branches. In the field of robotics, three general approaches are considered, and research in these three broad areas is progressing. In the first approach, we try to build artificial robots and make them intelligent by using artificial intelligence algorithms[2], which is a very popular approach and is divided into various branches, some of which we will introduce below. The second approach deals with the use of natural intelligence [3] to control artificial robots. Robots that are guided by manual control are placed in this area, and finally, the last approach is to use natural robots [4] and train them to achieve predetermined goals. The training of animals to perform specific actions is an example of the third approach.

    Robots can be classified into another category in terms of their application, among which are industrial robots[5], household robots, medical robots[6], service robots, military robots, entertainment robots and so on.

    Robots can also be divided in terms of movement system, which can be briefly divided as follows:

    Static robots[7] (immobile)

    Moving robots[8]

    Astronaut robots

    Flying robots

    Sea robots Rolling

    Other robots

    (images are available in the main file)

    The first group are static robots (Figure 1-1). Most of the industrial robots in factories are of this type. Robotic arms[9] as well as processing and supercomputing robots[10] are robots of this kind.

     

    The next category is mobile robots that move on the ground. This group includes a wide variety of robots:

    wheeled robots[11]

    chained robots[12]

    legged robots

    bipedal robots[13] (humanoid)

    three-legged robots

    four-legged robots

    others

    Figure 1-2 shows different examples of mobile robots on the ground. The next category is the astronaut robots, which are specially designed to operate in low-gravity spaces and are specially designed to carry out missions on the surface of other planets or space stations. Space probe robots are examples of this category.

    Flying robots are the next category of robots, which include drones, airplanes, and unmanned helicopters. And finally, the last category, as its name suggests, is designed for moving on the surface or under water.. Sailor robots include submarines, boats, and fish robots. Figures 1-3, 1-4 and 1-5 show examples of astronaut, bird and sailor robots, respectively. As it is clear from the pictures and descriptions, the field of robot performance has a direct role in the design of its movement system.

    Humanoid robots [14]

    Among the various divisions presented in the field of robotics, one of the most widely used and important robots is the humanoid robot, which is classified in the category of bipedal robots. These robots are one of the most interesting and at the same time the most complex fields of research in robotics [1-3]. The high degree of freedom[15], complex dynamics and balance issues have made this robot one of the most complex robots, so that its analysis and modeling is not easily possible. It means that it has two hands, two legs and a head in appearance. Of course, this similarity to the application can be more detailed by adding eyes, mouth, fingers and other parts of the body (Figure 6-1). Also, this robot has advanced sensors [16] to understand its surroundings and has advanced processors to process data received from the environment. By implementing advanced algorithms and using sensors, this robot will be able to imitate the human behavior of seeing, hearing, learning from the environment and other human mental abilities. For example, by using the vision sensor [17] and related algorithms, it can recognize people or objects in the environment, move towards them, move objects, or use the hearing sensor and speech processing algorithms and systems to talk with humans and other similar abilities. For this reason, this branch of robotics has become one of the most interesting and up-to-date branches of this science, which has occupied the minds of many scientists, and also developed countries have made a lot of investments in this field. Challenges of controlling humanoids with high degrees of freedom make it one of the most difficult problems in robotics so that humanoid robot walking is still being considered as the most important ability of a robot. In this study a new lateral walking algorithm is proposed for humanoid robot. This method is based on learning automata thus we put a learning automata on each robot joint. In the learning process, the probability vector of each learning automata is updated and the proper values ??of joints for walking are selected according to the vectors. Then the method is used for humanoid robot straight and lateral walking. Experimental results of algorithm simulation on NAO robot, the latest version of humanoid robot, in 3D soccer simulation environment shows perfect result in contrast with other methods in straight walking and advantages of developing lateral walking ability in a robot.

  • Contents & References of A selective method for side-to-side walking in humanoid robots

    List:

     

    Chapter One: Introduction

    2

    Introduction

    7

    Humanoid robots

    10

    RoboCop, motives and goals

    13

    Simulation software and robot model

    13

               1-4-1- Simulation

    14

               1-4-2- Robot model

    15

             1-4-3- Basic code

    18

    Walking of humanoid robots from the side

    19

    Objectives

    Chapter Second: An overview of previous research and methods used in robot motion analysis 21 2-1 Introduction 22 2-2 Robot balance and zero torque point 25 2-3 Kinematics 27 2-3-1 Kinematics direct

    27

              2-3-2- Inverse kinematics

    31

    2-4- Using Fourier series in robot motion analysis

    34

             2-4-1- Optimizing Fourier series parameters with the help of genetic algorithm

    37

          2-4-2- Optimizing Fourier series parameters With the help of particle swarm algorithm

     

    Chapter three: Proposed plan

    42

    3-1- Introduction

    42

    3-2- Nao humanoid robot and its motion analysis

    45

    3-3- Using kinesiology in walking from the side

    46

               3-3-1- Direct kinesiology

    50

               3-3-2- Inverse kinesiology

    52

    3-4-    Using learning automata for robot walking

    53

               3-4-1- Add-on robots

    54

    3-4-2- Learning Automatas

    55

    3-4-2-1-1- Fixed learning automatically

    58

    3-4-2-2- variable structure

    60-4-4 Navi robot walking

    Chapter 4: Experiments and results

    70

    4-1- Introduction

    71

    4-2- Straight walking

    74

    4-3- Walking from the side

    79

    4-4     Effect of the number of joints used in the convergence of speed and balance of robots

    Chapter 5: Conclusion and future studies

    85

    5-1- Conclusion

    86

    5-2-  Future studies

    List of references

    Source:

    [1] J. Or. ," A hybrid CPG-ZMP controller for the real-time balance of a simulated flexible spine humanoid robot", journalIEEE Transactions on Systems, Man, and Cybernetics 2009.39:p.14

    [2] B. stephens, "control of full body humanoid push recovery using simple models", ph.d thesis proposal 2009

    [3] T.Kanda, T.Miyashita, T.Osada, Y.Haikawa and H.Ishiguro., "Analysis of humanoid appearances in human-robot interaction." , Intelligent Robots and Systems. IEEE/RSJ          International Conference.2008.24:p.11.

    [4] S.Haddadin, t.laue, u.frese, g.hirzinger, "the read to robocup 2050" ieee robotics and automation magazine 2002.p:37-64.

    [5] R.De boer, j.Kok, "The Incremental Development of a Synthetic Multi-Agent System" The UvA Trilearn 2001 Robotic Soccer Simulation Team, master thesis, UVA 2002.

    [6] H.Kitano, M.Asada, Y.Kuniyoshi, I.Noda, E.Osawa."RoboCup: The Robot World Cup Initiative", In proceedings of the Firts National Conference on Autonomous Agents, 1997.

    [7] http://www.robocup.org/

    [8] J. Boedecker, "Humanoid Robot Simulation and Walking Behavior Development in the Spark Simulator Framework", Artificial Intelligence Research University of Koblenz, April 2005.

    [9] N. Shafii, et.al "A truncated fourier series with genetic algorithm for the control of biped locomotion" Advanced Intelligent Mechatronics AIM 2009 IEEE/ASME International conference, pp. 1781-1785, 2009.

    [10] M Vukobratovic, D Juricic, "contribution to the synthesis of biped gait", IEEE Transactions on Biomedical.

    [10]M Vukobratovic, D Juricic, "contribution to the synthesis of biped gait", IEEE Transactions on Biomedical Engineering,Vol.BME-16,pp.1-6,1969

    [11]M. H. Raibert, "Legged Robots That Balance", Cambridge, MA: MIT Press, 1986.

    [12]Q.Li, A.Takanishi, I.Kato, "A biped walking robot having a ZMP measurement system using universal force-moment sensors", IEEE/RSJ Int.Workshop on intelligent robots and systems.1991

    [13]Q.Huang, K.Yokoi, S.Kajita, K. Kaneko, H. Arai, N. Koyachi, K. Tanie "Planning Walking Patterns for a Biped Robot", IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 17, NO. 3, JUNE 2001

    [14] L.Yang, C.M.Chew, T.Zielinska, A.N.Poo, "A uniform biped gait generator with offline optimization and online adjustable parameters", Journal Robotica archive V.25, Pages 549-565, Cambridge University Press New York USA, 2007

    [15]saeed abdolshah

    [16] Y.Kambayashi, M.Takimoto, Y.Kodama, "Controlling biped walking robots using genetic algorithms in mobile agent environment", Computational Cybernetics, 2005. ICCC 2005, IEEE 3rd International Conference on, pp.29-34, April 2005.

    [17] Robotic manipulation book

    [18] J. J. Craig "Introduction to Robotics Mechanics and Control" 3rd Edition, Pearson Education, Inc. 2005.

    [19] H.Geyer, A.Seyfarth, R.Blickhan2, "Compliant leg behavior explains basic dynamics of walking and running", Proc.R.Lond.B, vol.237, pp.2861-2867, 2006.

    [20] E.R. Westervelt, J.W. Grizzle, D.E. Koditschek,   "Hybrid zero dynamics of planar biped walkers", IEEE Transactions on Automatic Control, vol.48, pp.42-56, Jan.2003.

    [21]A.Ben-Israel and T.N.E Greville, Generalized Inverse: Theory and Applications. New York: Springer-verlag, 2003.

    [22]C.L.Shih, "The dynamics and control of a biped walking robot with seven degrees of freedom", ASME Journal of Dynamic Systems, Measurement, and Control vol.118, no.4, pp.683-690, 1996

    [23]W.Zhu, Y.Wang and Sh.Zhou, "Gait Planning and Simulation of Lateral Motion for ROBONOVA-1 Robot", Proceedings of the 8th World Congress on Intelligent Control and Automation, China, July 2010.

    [24] M.Taher Khorsandi, B.Miripour-Fard and A.Bagheri, "Optimal Tracking Control of a Biped Robot Walking in the Lateral Plane", International Symposium on Innovations in Intelligent Systems and Applications, 2011

    [25] M.Ogino, I. Tsukinoki, K. Hosoda and M. Asada, "Controlling Lateral Stepping of a Biped Robot by Swinging Torso Toward Energy Efficient Walking", Proceedings of 1EEE/RSJ International Conference on Intelligent Robots and Systems, Japan, September 2004

    [26] L. Yang, C.M. Chew, A.N. Poo, "Adjustable Bipedal Gait Generation Using Genetic Algorithm Optimized Fourier Series Formulation", In :Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4435-4440, Oct. 2006.

    [27]L. Yang, C.M. Chew, T. Zielinska, A.N. Poo, "A Uniform Bipedal Gait Generator with Offline Optimization and Online Adjustable Parameters", Robotica 2007, Cambridge University Press, United Kingdom, Vol. 25, pp. 549-565, 2007.          

    [28]P. K. Schot, M. J. Decker, "The force driven harmonic oscillator model accurately predicts the preferred stride frequency for backward walking", Human movement science 1998, Vol. 17, pp. 67-76, 1995.

    [29]D.H.Kim, A.Abraham, J.H.Cho, "A hybrid genetic algorithm and bacterial foraging approach for global optimization", Information science 177, pp. 3918-3937, 2007.           

    [30]V.Gazi, K.M.Passino, "Stability analysis of social foraging swarms", IEEE Transactions on Systems, Man and Cybernetics-part B34(1), pp.539-557, 2004.

    [31] M.Dorigo, V.Maniezzo, A.colorni, "The ant system: optimization by colony of cooperating agents", IEEE Transactions on Systems, Man and Cybernetics-Part B 26(1), pp.29-41, 1996

    [32] J.H.

A selective method for side-to-side walking in humanoid robots
How To Access The File
Related Contents:
Number of pages: 162 Category: Facilities - Mechanics

Master's thesis in the field of mechanical engineering (applied design) abstract of dynamics and adaptive fuzzy control of limited-time sliding mode of hexa-parallel robots using the synchronization error of the development and increase of industrial production and the subsequent economic and social growth of a society in the new century is tied to the automation of production ...

Number of pages: 81 Category: Electrical Engineering

Obtaining a master's degree in the field of electrical engineering, electronics, abstract, mechanization of tools is one of the most important and extensive fields used in production processes. Due to the complexity and uncertainty of machining processes, recently soft computing techniques [1] based on physical models have been preferred to predict the performance of machining ...

Number of pages: 79 Category: Electronic Engineering

Seminar for obtaining a master's degree in the field of electrical engineering, electronics, abstract mechanization of tools is one of the most important and extensive fields used in production processes. Due to the complexity and uncertainty of machining processes, recently soft computing techniques [1] based on physical models have been preferred to predict the performance of ...

Number of pages: 112 Category: Computer Engineering

Dissertation for Master's Degree in Computer Engineering-Artificial Intelligence and Robotics Abstract: Every year, many traffic accidents occur all over the world due to driver drowsiness and inattention, which cause a lot of loss of life and money. One of the ways to detect fatigue and lack of concentration is to use driver face monitoring systems. By receiving images from the ...

Number of pages: 89 Category: Computer Engineering

Dissertation for Master's Degree in Computer Engineering - Artificial Intelligence Abstract Image segmentation is a basic process in many applications of image processing and machine vision, which can be considered as the first low-level processing step in digital image processing. Image segmentation has various applications such as medical image processing, face recognition, ...

Number of pages: 118 Category: Computer Engineering

Master's Thesis of Faculty of Technology and Engineering, Department of Computer Abstract: In this thesis, a new method is presented to detect the subtle emotional states of the face. Euler's video zoom method has been used to reveal subtle facial movements. Euler's video zoom method enhances the subtle movements of signals (color change or transition motion) by temporal and ...

Number of pages: 186 Category: Electronic Engineering

Abstract This thesis deals with uncertainty estimation in robust control of robotic arms and presents new methods based on voltage control strategy for uncertainty estimation. The voltage control method is much simpler compared to the conventional torque control method, because it does not require a complex non-linear model of the robot. As a result, the volume of controller ...

Number of pages: 190 Category: Electronic Engineering

Dissertation for Doctoral Degree Abstract This thesis deals with uncertainty estimation in robust control of robotic arms and presents new methods based on voltage control strategy to estimate uncertainty. The voltage control method is much simpler compared to the conventional torque control method, because it does not require a complex non-linear model of the robot. As a ...

Number of pages: 67 Category: Computer Engineering

Master's Thesis in Computer Engineering (M.Sc) Abstract: Today, automatic control is widely used in transportation systems. There are several reasons for using this method, the most important of which are cost reduction, the ability to make devices lighter, more safety for the passengers or to keep them away from danger. The last two cases are more visible in systems that have ...

Number of pages: 109 Category: Electrical Engineering

Dissertation for Master's Degree in Mechatronics Engineering Persian Abstract The purpose of this project is to introduce a new approach for troubleshooting gas transmission pipelines using mechanical waves, which is much cheaper and easier than other methods. who are currently working. These lines are usually located in difficult environmental conditions and far away and in ...