Humanoid Soccer Player Design Abstract:-Roboticsoccer supersededchess as a challenge problem and benchmark for artificial intelligence researchand poses many challenges for robotics. The international Robocup championshipsgrew to the most important robotic competition worldwide.
After preliminarycompetitions, for the first time soccer games with humanoid robots were playedin Osaka 2005.”1 Introduction:-What “drives thousands of researchersworldwide to devote their creativity and energy to make robots bring a ballinto a goal? The answer lies not only in the fascination of the soccer game,but rather in the quest to advance the fields of artificial intelligenceresearch and robotics. AI researchers started to investigate games early-on.Already in the Fifties of the last century, Simon predicted that computerswould be able to win against the human world champion within ten years. Playingchess was viewed as epitome of intelligence. The dominant view at that time wasthat human intelligence could be simulated by manipulating Symbols. While theworld champion in chess was defeated by a machine in 1997, human intelligenceis still far from being “understood”1.
1RoboCup Competition:-Motivated by”the successes in thechess domain, the RoboCup Federation organizes since 1997 international roboticsoccer competitions. Similar competitions are organized by the competing FIRA.The long-term goal of the RoboCup Federation is to develop by the year 2050 a teamof humanoid soccer robots that wins against the FIFA world champion. The soccergame was selected for the competitions, because, as opposed to chess, multipleplayers of one team must cooperate in a dynamic environment. Sensory signalsmust be interpreted in real-time and must be transformed into appropriate actions.
The soccer competitions do not test isolated components, but two systemscompete with each other””” Figure1: Some of the robots that competed at RoboCup 2005 in the Humanoid League Scored is “an objective performancemeasure that allows comparing systems that implement a large variety ofapproaches to perception, behavior control, and robot construction. Thepresence of opponent teams, which continuously improve their system, makes theproblem harder every year. Such a challenge problem focuses the effort of manyresearch groups worldwide and facilitates the exchange of ideas.”1.2.
RoboCupSoccer:-The “soccer competitions at RoboCup are held infive leagues. Since the beginning, there is a league for simulated agents, a leaguefor small wheeled robots which are observed by cameras above the field (SmallSize), and a league for larger wheeled robots where external sensors are notpermitted (Middle Size). Different research issues are addressed in thedifferent leagues. In the simulation league, team play and learning are mostadvanced. In the wheeled robot leagues, the robot construction (omnidirectionaldrives, ball manipulation devices), the perception of the situation on thefield (omnidirectional vision systems, distance sensors), and theimplementation of basic soccer skills (approaching, controlling, dribbling, andpassing the ball) are still in the center of the activities.
Because the robothardware is fixed in the Four-legged League, the participating teams focus onperception and behavior control.” 1.3.Humanoid Soccer Robots:-In the” Humanoid League, robotswith a human-like body plan compete with each other. The robots must have twolegs, two arms, a head, and a trunk.
Size restrictions make sure that thecenter of mass of the robots is not too low, that the feet are not too large,and so on. The robots are grouped in two size classes: Kid Size (up to 60cm)and Teen Size (65cm-130cm).The humanoid robots must be able to walk on twolegs. The robots may communicate with each other via a wireless network, buthelp from outside the field is not permitted, neither by humans nor bycomputers. The Humanoid League rules have been derived from the FIFA laws. Somesimplifications apply, however. For example, the offside rule is not observed.
Key objects are color-coded in order to simplify the perception of the gamesituation. The playing field is green with white lines, the goals are paintedblue and yellow, the ball is orange, and the robots are mostly black. The twoteams are marked with magenta and cyan patches, respectively.”2.
Mechanical Design:- Figure2: NimbRo 2005 Kid Size robots Jupp and Sepp”Fig. 2 shows on the left our Kid Size robots Jupp andSepp playing soccer and on the right our Teen Size robot Max, ready to kick.These robots are based on their predecessor Toni 2. As can be seen, therobots have human-like proportions. Their mechanical design focused simplicity,robustness, and weight reduction.”3.Electronics:- Figure 3: “Electronic componentsused: (a) ChipS12 microcontroller board; (b) attitude sensor; (c) compass; (d)Pocket PC with ultra-wide-angle CF-camera.
Jupp and Sepp are fully autonomous.They are powered by high-current Lithium-polymer rechargeable batteries, whichare located in their lower back. Two Kokam 2000H cells per robot last for about30 minutes of operation. They can be discharged with 30A and have a weight ofonly 110g.”4.Behavior based architecture for robot applications:-The main “element in the proposed architecture is the component.
This is the basic unit of functionality. Inany time, each component can be active or inactive. This property is set usingthe start/stop interface, as we can observe. When it is active, it is runningand performing a task. When inactive, it is stopped and it does not consumecomputation resources. A component also accepts modulations to its actuation andprovides information of the task it is performing.For example, “let’s suppose a component whose function is perceive thedistance to an object using the ultrasound sensors situated in the robot chest.
The only task of this component is to detect, using the sensor information, ifa obstacle is in front of the robot, on its left, on its right or there is notobstacle in a distance less than D mm. If wewould like to use this functionality, we have to activate this component usingits start/stop interface (Figure 9). We maymodulate the D distance and ask whenever wewant what is this component output (front, left, right or none). When this isinformation is no longer needed, we may deactivate this component to stopcalculating the obstacle position, saving “valuable resources. A “component, when active, can activate anothercomponents to achieve its goal, and these components can also activate anotherones. This is a key idea in our architecture. This let to decompose functionalityin several components that work together. An application is a set of componentswhich some of them are activated and another ones are deactivated.
The subsetof the components that are activated and the activation relations arecalled activation tree. In Figure 10 there is an example of an “activation tree. Two “different components are able to activate thesame child component, as we can observe in Figure 11.
This property lets two components to get thesame information from a component. Any of them may modulate it, and the changesaffect to the result “obtained inboth component. The “main idea of our approach is to decompose therobot functionality in these components, which cooperate among them to makearise more complex behaviors. As we said before, component can be active orinactive. When it is active, a step () function is called iteratively toperform the component “task. As an example, “in Figure 12 weshow an activation tree composed by 3 components. Object Perception is a lowlevel component that determines the position of an interesting object in theimage taken by the robot’s camera. Head is a low level component that moves thehead.
These components functionality is used by a higher level component calledFace Object. This component activates both low level components that executeiteratively. Each time Face Object component performs its step () function, itasks to Face Object for the object position and modulates Head movement toobtain the global behavior: facing the object.
Each module runs iteratively at a configured frequency. It has not sensethat all the components execute at the same frequency. Some information’s areneeded to be refreshed very fast, and some decisions are not needed to be takensuch fast. Some components may need to be configured at the maximum frame rate,but another modules may not need such high rate.
When a step () method iscalled, it checks if the elapsed time since last execution is equal or higherto the established according to its frequency. In that case, it executes 1, 2and 3 parts of the structure the have just described. If the elapsed time islower, it only executes 1 and 3 parts. Typically, higher level components areset up with lower frequency than lower level ones, as we can observe in Figure “13 5.Soccer player design:-The concepts “presented inlast section summarizes the key ideas of this architecture design.
We havepresented the component element, how thesecomponents can be activated in a activation tree and how they execute. Thisarchitecture is focused to develop robot applications using a behavioralapproach. In this section we will present how, using this architecture, wesolve the problem previously introduced in the section 1: play “soccer.5.1. SOCCER PLAYER PERCEPTIONAt RoboCup “competition,the environment is designed to be perceived using vision and all the elementshave a particular color and shape. Nao is equipped with two (non-stereo)cameras because they are the richest sensors available in robotics. Thisparticular robot has also ultrasound sensors to detect obstacles in front ofit, but a image processing could also detect the obstacle and, additionally,recognize whether it is a robot (and what teams it belong) or another element.
This is why we have based the robot perception in “vision.5.2. BASIC MOVEMENTS:-Robot actuation is not trivial in a legged robot. It is even morecomplicated in biped robots. The movement is carried out by moving theprojection of center of mass in the floor (zero moment point, ZMP) to be in thesupport foot.
This involves the coordination of almost all the joints in therobot. In fact, it is common even use the arms to improve the balance. 5.2.
1. BODY COMPONENT:-The”Body component manages the robot walk. Itsmodulation consists in two parameters: straight velocity (v) and rotation velocity (w).
Each parametersaccepts values in the -1,1. If v is 1, therobot walks forward straight; if v is -1, therobot walks backward straight; if v is 0, robotdoesn’t move straight. If w is 1, therobot turn left; if w is -1, therobot turn right; if w is 0, robotdoesn’t turn.
Unfortunately, this movements can’t be combined and only one ofthem is active at the”same time. 5.2.
2. HEAD COMPONENT:-Body “component makes move all the robot but therobot head. Robot head is involved in the perception and attention process andcan be controlled independently from the rest of the robot.
The robot head iscontrolled by the Head component. This component, when active, can be modulatedin velocity and position to control the pan and tilt movement. While the headcontrol in position is quite simple (it sends motion commands to AL Motion toset the joint to the desired angle), the control in velocity is moresophisticated. We developed a PID controller toadjust the movement speed. The modulation parameter for this type of control,in range -1,1 in each pan and tilt, is taken as the input of this controller.
The value -1 means the maximum value in one turn sense, “1 in the other sense, and 0 means to stop thehead in this axe.5.2.3. FIXED MOVEMENT BEHAVIO:-The”last component involved in actuation is the FixMove component.
Sometimes it is required to perform fixed complex movement composed by severaljoint positions in determined times. For example, when we want that robot kicksthe ball we have to made a coordinate movement that involves all the bodyjoints and takes several seconds to complete. These movements are coded inseveral files, one for each fixed movement, that describe the joints involvedin the movement, the positions and when these positions should applied. Let’slook an example of this “file:MovementnameName”joint_1 name _joint_2 name _joint_3..
. name_joint_nangle_1_joint_1 angle_2_joint_1 angle_3_joint_1…angle_m1_joint_1angle_1_joint_2 angle_2_joint_2 angle_3_joint_2…angle_m2_joint_2angle_1_joint_3 angle_2_joint_3 angle_3_joint_3.
..angle_m3_joint_3…angle_1_joint_n angle_2_joint_n angle_3_joint_n…
angle_mn_joint_ntime_1_joint_1 time_2_joint_1 time_3_joint_1…time_m1_joint_1time_1_joint_2 time_2_joint_2 time_3_joint_2.
.. time_m2_joint_2time_1_joint_3time_2_joint_3 time_3_joint_3…
.. time_mn_joint_nIn addition to the desired fixed movement, we can modulate twoparameters that indicates a walking” 5.3. FACE BALL BEHAVIOR:-FaceBall”componenttries to center the ball in the image taken from the camera. To achieve thisgoal, when active, this component activates both Perception and Headcomponents, as we see in Figure “22. 5.
4 SEARCH NET BEHAVIOR:-This”behavioris implemented by the SearchNet component is used to search the net where therobot must kick the ball to. It activates Head and Perception components. Itswork is divided in two states: Scanning and Recovering. When the Scanning statestarts, the head position is stored (it is supposed to be tracking the ball)and the robot modulates Perception component to detect the nets instead of theball. It has not sense continuing doing processing to detect the ball if now itis not the interesting element, saving processing resources. In the Recovering state the Perception componentis modulated to detect the ball, and the head moves to the position storedwhen Scanning state”started. 5.
5. FIELD PLAYER BEHAVIOR:-The Player”componentis the root component of the forward player behavior. Its functionality isdecomposed in five states: LookForBall, Approach, SeekNet,Fallen and Kick. These five states encode all the behavior thatmakes the robot play “soccer. 6.
Conclusions:-Playing “soccer withhumanoid robots is a complex task, and the development has only started. Sofar, there has been significant progress in the Humanoid League, which moved inits few years from remotely controlled robots to soccer games with fullyautonomous humanoids. Indeed, the Humanoid League is currently the most dynamicRoboCupSoccer league. We expect to see the rapid progress continue as moreteams join the league. Many research issues, however, must be resolved beforethe humanoid robots reach the level of play shown in other RoboCupSoccer leagues.For example, the humanoid robots must maintain their balance, even whendisturbed.
Currently, we are working on postural reflexes, which shouldminimize the number of falls. in the next years the speed of walking must beincreased significantly.The higher level component is the Player component. This component is implemented as afinite state machine and activates the previously described components in orderto obtain the forward player behavior.
This behavior, created with this architecture, has been testedin the RoboCup environment, but it is not limited to it. “We want to use this architecture to createrobot behaviors to solve another problems out of this environment.References:-1 Sven Behnke. Online trajectory generation foromnidirectional biped walking. In Proceedings of IEEE InternationalConference on Robotics and Automation (ICRA’06), Orlando,Florida, To appear 05/2006.2 Sven Behnke, J¨urgen M¨uller, and Michael Schreiber.Toni: A soccer playing humanoid robot. In Proceedings of 9thRoboCup Int.
Symp., Osaka, 2005.3 Sven Behnke and Raul Rojas. A hierarchy of reactivebehaviors handles complexity. In Balancing Reactivity and SocialDeliberation in Multi-Agent Systems, pages 125–136.
Springer,2001.4 https://www.intechopen.com/books/robot-soccer/humanoid-soccer-player-design5 Rey JuanCarlos University, Spai