Optimization of parametrised kicking motion for humanoid soccer player
Summary (3 min read)
Introduction
- While competitions involve multiple humanoids, individual agents specialization and optimization are an issue for the enhancement of team play.
- It can enable higher scoring, but it is also a way to pass the ball between players, which can produce lively and interesting game strategies.
- The planning of the ZMP trajectory inside the support polygon was employed for biped gaits, while applying a preview controller for increased stability [8], [9].
- Their aim is not to design accurate nor flexible kicking movements, but to kick and send the ball as far as possible from a fixed position.
II. DESCRIPTION OF THE KICKING MOVEMENT
- A parametrised kick was designed to enable robots to kick the ball far away.
- This provides the kicking foot with more kinetic energy at the time of striking the ball since the distance between the hip and the foot is increased.
- The projection of the center of mass remains at the same position.
- Put the kicking foot forward to accompany the kick movement, while rocking the trunk backward.
- The final position of the leg is called the forward position.
TIME DECOMPOSITION OF KICKING MOVEMENT
- Actually the kicking trajectory is defined thanks to a set of three leg configurations defined in the Cartesian space, which makes 12 parameters in total.
- The inverse kinematics is the same as the one used for the locomotion gaits [16] by the French team L3M-SIM for its participations in the 3D-SSL competitions.
- The backward-to-strike swing trajectory and the strike-to-forward swing trajectories of foot toe and foot rotation are interpolated linearly, and the time of execution was reduced as much as possible to generate the highest acceleration at the time of hitting the ball.
- The authors did not implement any COM or ZMP based stabilizer, since it does not matter if the robots falls after striking the ball away.
III. EVOLUTION PROCESS
- The evolution process to find stronger kicks is based on the Confident Local Optimization technique (CLOP) [15].
- As usual, the process aims to make a set of bounded parameters evolve through a fitness function.
- L defines input parameters with their bounds and H defines the history set where previous results are collected.
- Since the objective consists of finding stable moves, the authors believe that the smooth optimization of expert parameters is a promising policy.
- The SUCCESS RATE allows keeping the process evolution close to stable regions (no fall).
VALUES OF PARAMETERS RESULTING FROM MANUAL TUNING
- S′, m′ and σ′ from ν′), that identify the number of success s, the average distance m between the final ball and the kicker’s positions and its standard deviation σ.
- In order to stay close to real robot motion, the authors limit the falls thanks to the SUCCESS RATE threshold.
- Nevertheless, kicks that produce a 0.25 fall rate or less can be selected if they generate more powerful moves.
IV. EXPERIMENTS
- The humanoid robot used is the NAO robot of the RoboCup 3D Soccer Simulation League (Fig. 5).
- Table II gives the parameter values obtained through manual tuning.
- The distance between ankles in the initial position is 0.1[m].
- Before initiating the kicking motion, the robot bends its torso 17[deg] laterally on the side of the support foot.
- The authors did not take into account the x-z parameters of the backward and forward positions because they are assumed to have less influence on the result, and because a reduced set of parameters is better to speed up the optimization process.
V. RESULTS
- Tests are carried out on a single computer that runs the simulation server rcssserver3d [18], their parametrised player agent rcssagent3d-l3m [19] and a coach that is responsible for starting each trial.
- Figure 3 shows the results for 500 iterations of C2.
- It shows the evolution turning from unstable (at the beginning) to stable (at the end) while kicking results appear to be better than previous ones over the successive iterations.
- After the evolution process, resulting parameters are tested carefully.
PARAMETERS SETS CLASSIFICATION AND EVOLUTIONS RESULTS
- For each experiment, the initial position of the robot on the field is considered as the origin of the global coordinate system.
- Corresponding averages and standard deviations are detailed in table IV.
- It shows that C1 resulting parameters produce a stronger kick that sends the ball 1.34 times farther than expert parameters.
- Similar results are obtained for the C3 parameters.
- By using C2 parameters, the lateral deviation of the ball can be reduced as the related standard deviation is 2 times less than C1, and 4.7 times less than C3 results.
VI. DISCUSSION
- This study shows that the proposed evolution process based on the CLOP technique is useful to increase the kicking range of the ball.
- Each position was defined by two angles, torso and foot sole, and two coordinates of the foot toe, namely x and z.
- The positions of the toe in the backward and the forward positions were not used as evolving parameters in the optimization process.
- These position parameters could be added in the process to change the curvature of the swing trajectory, which may have an influence on the kick strongness.
VII. CONCLUSION
- This paper presented an optimization process designed to increase the kicking range of humanoid players in the 3D-soccer simulation league.
- The proposed anytime process allowed improving the values tuned manually to win 34% ball kicking range.
- The optimization process was divided into a two-classes sequential process, that produces more accurate motion.
- More flexible motion remains to be develop, to produce adaptable kicks capable of sending the ball at various distances.
- This could be achieved by varying parameters such as the foot sole angle.
Did you find this useful? Give us your feedback
Citations
12 citations
11 citations
8 citations
5 citations
References
2,090 citations
"Optimization of parametrised kickin..." refers methods in this paper
...The planning of the ZMP trajectory inside the support polygon was employed for biped gaits, while applying a preview controller for increased stability [8], [9]....
[...]
2,011 citations
"Optimization of parametrised kickin..." refers methods in this paper
...More recent work developments use the Zero Moment Point (ZMP) [7] to keep the dynamic balance of the robot’s executing a kick....
[...]
...The planning of the ZMP trajectory inside the support polygon was employed for biped gaits, while applying a preview controller for increased stability [8], [9]....
[...]
...Yi et al. designed a walk-kick technique using the ZMP preview controller, and applied it on different robotic platforms [10]....
[...]
...Wenk et al. implemented inverse dynamics on the NAO robot to plan the ZMP trajectory, and compared both ZMP planning methods, namely the preview controller and the Linear Quadratic Regulation (LQR) method [11]....
[...]
...We did not implement any COM or ZMP based stabilizer, since it does not matter if the robots falls after striking the ball away....
[...]
96 citations
"Optimization of parametrised kickin..." refers background in this paper
...Other developments include the design of a controlledkicking engine that can adapt to a variety of distances angles through a decision method that can select from among a large set of possible kicks [13], and reinforcement learning techniques to deal with penalty kick scenarios [14]....
[...]
52 citations
"Optimization of parametrised kickin..." refers methods in this paper
...Tests are carried out on a single computer that runs the simulation server rcssserver3d [18], our parametrised player agent rcssagent3d-l3m [19] and a coach that is responsible for starting each trial....
[...]
41 citations
Related Papers (5)
Frequently Asked Questions (12)
Q2. How many parameters are used to define the kicking trajectory?
Actually the kicking trajectory is defined thanks to a set of three leg configurations defined in the Cartesian space, which makes 12 parameters in total.
Q3. Why did the authors not take into account the x-z parameters of the backward and forward?
The authors did not take into account the x-z parameters of the backward and forward positions because they are assumed to have less influence on the result, and because a reduced set of parameters is better to speed up the optimization process.
Q4. What is the objective of the smooth optimization of expert parameters?
Since the objective consists of finding stable moves, the authors believe that the smooth optimization of expert parameters is a promising policy.
Q5. What can be done to modify the lateral position of the toe?
However the lateral position of the toe can be adjustedto modify the kicking direction so as to hit the ball in the center, which can provide more flexibility to the kicking motion.
Q6. What is the function that compares with ′?
Inside the Test function, the pickOut function compares ν with ν′ and returns three possible values BESTAlgorithm 1 evolution < T > (k, L, pickOut) 1: ν′ ← expertKnowledge 2: H ← ∅ 3: while not-interrupted do 4: p← Generate < T > (H, L) 5: ν ← multipleTrials < T > (p, k) 6: (ν′, H) ← Test < T > (ν, ν′, p, H, pickOut) 7: end while 8: return paramsFrom < T > (ν′)(which implies ν′ ← ν), EQUAL and WORST.
Q7. What is the effect of the kicking foot?
This enables to increase the velocity of the kicking foot at the time of hitting the ball, therefore transmitting a larger amount of kinetic energy to the ball, which permits to send the ball farther away.
Q8. How much is the lateral deviation of the ball?
By using C2 parameters, the lateral deviation of the ball can be reduced as the related standard deviation is 2 times less than C1, and 4.7 times less than C3 results.
Q9. What is the definition of a parametrised kick?
The parametrised kick consists of the following phases (Fig. 1): • sway hips to transfer the load above the kicking foot,then lift, swing, and put down the supporting foot.
Q10. What is the time elapsed for the evolution process?
When the time elapsed is considered as sufficient to produce an interesting solution, the evolution process is instantaneously interrupted and the resulting input parameters are returned.
Q11. What were the positions of the toe in the backward and forward positions?
The positions of the toe in the backward and the forward positions were not used as evolving parameters in the optimization process.
Q12. What is the way to optimize a smooth problem?
This iterative maximum-optimization process has been experimentally shown to be less time consuming than classical regression methods for smooth problem optimization; it does not need any reference execution as samples are iteratively selected according to their average win rate.