Scorpius Team Description Paper Soccer Simulation 3D league, Graz 2009 Kh. Niki Maleki1 , M. Hadi Valipour1 , R. Yeylaghi Ashra1 , Sadegh Mokari1 , M. ValadBeigi1 , and M. R. Jamali1,2 1

2

Robotic and AI Laboratory, Department of Electrical and Computer Engineering, Shahid Rajaee University, Tehran, Iran Control and Intelligent Processing Center of Excellence, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran {kh.niki, m.h.valipour, r.yeylaghi, s.mokari, m.v.beigi}@sru.ac.ir, [email protected]

Abstract. This paper summarizes some of major processes which have

performed to implement Scorpius simulated humanoid robot, including several detailed specications. This is the third year Scorpius team participates in the world RoboCup competitions3 . Although we spent much time on humanoid skills, there are still lots of optimizations and new skills required to create a more-real soccer player robot. So this year most of our researches are focused on these skills, especially optimization of walking and implementing our platform independent trainer. The other article this paper discusses about is implantation of high level skills. keywords: multi-agent systems, articial intelligence, trajectory based approach, genetic algorithm, tness function, data mining, association rule.

1 Introduction Scorpius team4 was established in 2005 in Shahid Rajaee university robotics an AI laboratory. Our approach to humanoid soccer simulation started with HOAP2 robot. The base code has been developed to work in new simulation environment. During our researches on humanoid skills, some approaches were found proper to be utilized. According to the environment limitations, suitable methods were distinguished in tests to be optimized. Our platform has been changed to Nao since the soccer server changed after German open competitions08. Since then optimizations in our skills using articial intelligence approaches (e.g. genetic algorithm and machine learning) have been one of the most signicant concerns. As declared in our last publication [1] creation of a mechanical machine in human shape, having the same locomotion and even more capabilities has always been one of the human beings desires. Thus research on humanoid robotics is one of the most exciting topics in the eld of robotics [2]. Many researches researches 3 4

In China'08 competitions Scorpius participated with the name of Pat&Tam http://www.scorpius.ir

are focused on biped walking and running [3,4,5]. Despite all these eorts, there are still lots of mysteries about human locomotion nature, which makes these approaches more dicult. walking is involved with many complex processes, such as controlling large numbers of degrees of freedom (DOFs), non-linear dynamics of controlling a humanoid body and wide ranges of interactions with the environment (gravity, landscape, perturbations, etc.) [3]. This paper presents main features of our implemented agents and describes our plans for Graz'09 competition. Section 2 discusses about walking and its optimization process. Section 3 explains some of high level methods. Finally conclusions and future works are presented in section 4.

2 Walking and Its Optimization Process Many dierent solutions have been experimented to achieve stable biped locomotion. In the most widely used also successful techniques, there are some parameters which represent the current robot's condition and let us nd out how the next steps should be. We can recognize Zero Moment Point (ZMP) and Center of Pressure (COP) as the most commonly utilized parameters [6]. Besides there are AI approaches like genetic algorithm which is able to generate walking steps during a learning process while a proper tness function is dened. First we implemented a trajectory based approach using COP factor which is briey discussed in 2.1, then we developed another method using genetic algorithm that is explained in 2.2 and nally we came to conclusion to optimize our methods using Data Mining techniques which is presented in 2.3.

2.1 Trajectory Based Approach Using COP Trajectory based methods use oine generation of trajectories. This can be performed with constraint (e.g. stability, diversion, frequency, joints' restrictions. . . ) satisfaction procedures [3]. The rhythmic component of the gait is described by a coupled oscillators system, modeling the controller and robot phase; respectively φc and φr . Their temporal behavior follows a dierential equations system:

φ˙ c = ωc + Kc sin(φr − φc )

(1)

φ˙ r = ωr + Kr sin(φc − φr )

(2)

These two simple equations are sucient to synchronize the controller and robot dynamics. However, this theoretical model cannot be directly applied to the real controller, as the robot natural phase ωr and coupling constant Kr are usually unknown. They depend on the robot's dynamics (center of mass, posture, physics, etc.). In NAO we have no pressure sensors located under the robot's feet, that's why the COP factor is computed with geometric transformations of vision

information. From its position x and velocity x˙ , the robot phase is obtained by the following transformation (equation 3).

µ ¶ x˙ φr (χ) = −arctan x

(3)

Basically, φr (χ) models the stance and swing leg transitions. Now that the robot dynamics are known, equation 1 can be solved to obtain the corresponding controller phase φc . A last modication is applied to the theoretical equation to obtain several phase dierences, which will be used to generate synchronized and symmetrical limb trajectories [3]. φc is nally expressed as:

π 3π φ˙ic = ωc + Kc sin(φr (χ) − φic + αi ), αi = [0, , π, ] 2 2

(4)

Finally, the joint trajectories will be derived from the controller's dynamics by using simple sinusoidal patterns.

Fig. 1. Position of the center of pressure As it is shown in Fig. 1 achieving COP requires COM to be calculated rst. Following shows how COM is evaluated.

CoM =

n X mi × ri i=1

n m Σi=1 i

(5)

The rst step can easily be derived from vision status. Second step has little complex calculations which are geometric transformations of joints and mussels, for example: Rotate(teta1,j2[0],j2[1],j2[2],j1[0],j1[1],j1[2]); //joint around joint Rotate(teta1,p0[0],p0[1],p0[2],j1[0],j1[1],j1[2]); //mussel around joint Translate(p1[0],p1[1],p1[2],0.0,-l0,-(c1+l2)); //move CoR to new zone

(a)

(b)

Fig. 2. a. NAO joints positions, b. soccerbot joints positions 2.2 Genetic Algorithm Approach Nature has a robust way of evolving successful organisms. The organisms that are ill-suited for an environment die o, whereas the ones that are t live to reproduce. Ospring are similar to their parents, so each new generation has organisms that are similar to the t members of the previous generation [7]. We employed this natural behavior to design a method for walking generation. First every variables (joints' angle) will be initialized with random data, then these variables would be crossed over to create next generation (o-springs) if the new generation was closer to the maximized tness function that would be replaced other wise they would die and their parents try another crossover. After 3 generations a mutation happens which is randomized data in new children were not existed in their parents. So the most important article in our genetic algorithm approach to biped walking is to dene the appropriate tness function. To have the best performance the tness function must be maximized concerning the problem constrains which is totally discussed in sec. 2.1.

F itness F unction = distance robot has walked in 15 second.

(6)

To implement this algorithm a trainer application designed by Scorpius team in MATLAB workbench (g. 3) this is one of fastest application in case of matrix computations. It also gives many capabilities for plotting and analyzing nal results. That gives us a platform independent and more scalable test bed for developing and optimizing walking skill using genetic algorithm approach. This tool can monitor the outcome of genetic algorithm, which helps us to have a visual perception of nal result before having it evaluated on Nao in

Fig. 3. Sample code and run snapshot of Scorpius walk trainer in MATLAB soccer3D simulation environment that makes development process much faster (g.4).

2.3 Data Mining Optimization As mentioned before, there are lots of approaches for walking, but all these methods have common goal "sending proper angle to servomotors in each cycle to keep robot in balance". Analyzing these angles indicates that (g. 5) there are other common items in all bipeds walking. It is obvious these data are repeated over and over in each step. So it would be perceived that they just like periodic functions include: T (period time), F (frequency), W (angular speed), A (domain), and φ (initial phase). Besides there are other kind of parameters; rst are those which gives us feedback information (already discussed in sec. 2.1), the 2nd are those which helps us control the robot behavior such as: walking speed, diversion side and diversion rate. We know for sure that there are relationships between these parameters and nal command to servo motors. But, the question is what kind of association? And how can these correlations help us? Actually, the association information can play the role of training data in prediction process. It also can be exploited to measure the accuracy of our predictions. Our primary data is nothing but current angle of robot's joints' angels and they may seem so irrelevant at rst look, but the promised association appears after basic calculations and analysis! Generally association requires items which are derived from basic analysis on primary data and feedback parameters (e.g. Speed (both instant and average velocity), Diversion side, Diversion speed, Stability, Step length, Step height, Frequency, Left / right step time). The nal goal is to predict what command should be sent to servo motors in order to achieve best robot behavior. We intend to employ supervised learning method for this purpose (g. 6).

Fig. 4. Monitoring walking process by the trainer

(a)

(b)

(c)

Fig. 5. Analyzing joints' angle in walking, a. Ankle, b. Hip2, c. Knee

Linear Speed

Stability

Walk Black Box

Diversion Speed

Diversion Side

Frequency

Step Size, Height, ...

Fig. 6. Prediction diagram

3 High Level Methods Increasing the number of agents in conjunction with server development makes teams think more seriously about Multi Agent Behavior and team work. Cooperation between players would lead to better results therefore, duty dispense have an important role to reach a good result. Our implemented decision making process for 3 agents is divided into 2 parts; one is assigned to goalkeeper and another one is assigned to others players like defender and striker. Some of these roles are implemented mostly about goalkeeper's responsibility such as diving, free kick and so on.

Fig. 7. Portraying goalkeeper reaction

4 Conclusions and Future Works In this paper we showed an overview of the Scorpius soccer 3D agent design. Most eorts focused on developing and optimizing biped locomotion and high level behavior of agents. According to our researches and experiments on trajectory based and genetic algorithm approaches, we came to conclusion that both of

them should be considered to reach the best result. Moreover Mining Association rules and predictive patterns are the main reasons we go through the data mining [8]. The outcome of this idea must be a developing, robust, reliable, extendable, scalable and platform independent pattern for optimizing walking methods. To complete implementation of proper algorithms in both elds of correlation and prediction, adopting them with the problem constrains, besides increasing the performance of high level skills would be our road map.

References 1. Maleki, K.N., Valipour, M.H., Ashra, R.Y., Mokari, S., Jamali, M.R., Locus, C.: A simple method for decision making in robocup soccer simulation 3d environment. Avances en Sistemas e Informatica 5(3) (December 2008) 2. Kajita, S., Nagasaki, T., Kaneko, K., Yokoi, K., Tanie, K.: A hop towards running humanoid biped. In: IEEE International Conference on Robotics and Automation, New Orleans (April 2004) 629635 3. Lathion, C.: Biped locomotion on the hoap2 robot. Master's thesis, Biologically Inspired Robotics Group (December 2006) 4. Gienger, M., Loer, K., Pfeier, F.: Toward the design of a biped jogging robot. In: International Conference on Robotics and Automation. (2001) 414419 5. Inoue, Tachi, Nakamura, Hirai, Ohyu, Hirai, Tanie, Yokoi, Hirukawa: Overview of humanoid robotics project of meti. In: Int. Symp. Robotics. (2001) 14781482 6. Hirai, Hirose, K., HaiLawa, M.: The developnrnt of honda humanoid robot. In: International Conference on Robotics and Automation. (1998) 13211326 7. Russell, S.J., Norvig, P.: Articial Intelligence the modern approach. Prentice Hall (1995) 8. Han, J., Kamber, M.: Data Mining Concepts and Techniques. 2nd edn. Elsevier and Morgan Kaufmann (2006)

Scorpius Team Description Paper Soccer Simulation ...

approach, genetic algorithm, fitness function, data mining, association rule. ... methods using Data Mining techniques which is presented in 2.3. 2.1 Trajectory Based .... Han, J., Kamber, M.: Data Mining Concepts and Techniques. 2nd edn.

437KB Sizes 2 Downloads 216 Views

Recommend Documents

Scorpius Team Description Paper Soccer Simulation ...
shape, having the same locomotion and even more capabilities has always been one of the ... methods using Data Mining techniques which is presented in 2.3.

Scorpius Team Description Paper Soccer Simulation 3D ... - CiteSeerX
ing, tackling, dribbling, and ultimately, since the whole game is a team work thus team coordination and the issues concerning multi agent decision making ... The rhythmic component of the gait is described by a coupled oscillators system, modeling t

Scorpius Virtual Robot Team Description Paper
dangerous situations, vast locations, massive casualties, etc. leads us to employ .... of the IEEE International Conference on Robotics and Automation, 2005. 5.

Scorpius Virtual Robot Team Description Paper
The architecture of server side (A) and client side (B) of connection ... Robots employ wireless communication in order to share some information about ... Occupancy Grids has some benefits; The most important one is that grid-based.

HELIOS2007 Team Description - WrightEagle 2D Soccer Simulation ...
tool. Our positioning mechanism has many advantages than previous methods. 1 Introduction .... training process and enables us to edit the training data easily.

HELIOS2008 Team Description - WrightEagle 2D Soccer Simulation ...
and can be adjusted by human's intuitive operations using GUI tools. .... BI| = n2. 3.3 Feature of Basic Model. The basic model can perform with light-weight ...

Scorpius Virtual Robot Team Description Paper
Current Scorpius virtual robot team uses P2DX and Talon robots equipped by .... Proceedings of the IEEE International Conference on Robotics and Automation, ...

Scorpius 3D Team Description Proposal
The recent RoboCup simulation environment named “spark” is a good platform for implementation of robots and the methods employed for controlling them.

WrightEagle2008 Simulation 2D Team Description ...
We take simulation 2D as a typical problem of multi-agent systems, and our ... of decision-making at the end of the cycle, so he will do nothing in the current .... considered as a potentially good forward and given a high evaluation value. In.

ENBank Team Description Paper
The recent RoboCup simulation environment named spark is a good .... The first formula we need is of course the formula of the position of the CoM for a solid:.

Simulation of a Humanoid Soccer Robot Team ...
Keywords: Zero Moment Point (ZMP),Artificial intelligence, Artificial Neural ... walking patterns is calculated using ZMP and stored in a database. Fig. 1.

Team Description Paper SBCe_Saviour Virtual Robots ...
system and the operator graphical interface respectively. ..... multiple robots' mapping data, sensor data, camera images, battery status and ... Cisco Press., 1998.

Zigorat 2007 Development Team Description
This paper describes the main contributions of the Zigorat. Soccer 3D development team that is going to take part in ... paper describes our studies about achieving a stable walking pattern for legged-sphere agents as well as our works with .... fina

Zigorat 2007 Development Team Description
We plan to use Webots as a simulator for biped modeling. The mobile robotics simulation software named Webots enables convenient and rapid modeling, pro- gramming and simulating various types of mobile robots[2]. In the same paper, the author (and pr

Zigorat 2007 Development Team Description - Chaosscripting
Soccer 3D development team that is going to take part in RoboCup competitions this year. ... attempt to speed up the development of the current simulation environment by encouraging members of .... namics, Stability, Control and Application.

Zigorat 2007 Development Team Description - Chaosscripting
Soccer 3D development team that is going to take part in RoboCup .... design; the developer has to decide on the type (biped, quadruped etc.), size, shape ... Besides the cost aspects compared .... namics, Stability, Control and Application.

Team Blazers Paper
Nov 24, 2013 - Submitted to Colorado Technical University On… Student Paper. Submitted to American Public University System. Student Paper www.tgiltd.

Rocky Mountain College Men's Soccer Named Team ... -
Oct 30, 2016 - ... Corban University • Eastern Oregon University • Multnomah University ... Klamath Falls and Ashland Oregon to take on Oregon Tech and ...

KAIAC RED Soccer Boys - Team Standings
Kim. 17. 9. 16. Scott. Choi. 24. 9. 17. Benjamin. Park. 11. 9. 18. Ryan. Chung. 3. 9 ... Lee. 13. 9. 14. Andrew. Ji. 29. 9. 15. Kevin. Ju. 15. 9. 16. Ethan. Hur. 5. 9. 17.