A learning method for returning ball in robotic table tennis

With the air leakage test methods, the leakage tests of the products that are required to be leakproof are carried out. This leakage test starts with placing the product on a fixture. The in-ternal pressure is increased by filling compressed air into the product placed in the Fixture. The product is filled with compressed air up to a previously calculated test pressure value. After the test pressure value is reached for the desired product, the air filling process is completed, and the stabilization period begins. At the end of this period, information about the leakage of the product is obtained, depending on whether there is a change in the internal pressure of the product. In order to fill the product with compressed air, there must be an air hole on the product. Products without this air hole cannot be tested with these methods. With the new method we will develop, it will be possible to test the leakage of closed products without atmosphere-air connection.

show abstract

“…[2] The life of these products depends on making this stabilization. [3]. The most well-known product can be shown the table tennis ball.…”

Section: Introductionmentioning

confidence: 99%

“…Air leakage of this product causes many problems. In particular, aerodynamic factors must be at a good level [2], [3]. A damaged and leakage ball cannot achieve this.…”

Section: Introductionmentioning

confidence: 99%

Air leakage test system for product without atmosphere air connection

Temiz¹,

Feyzioğlu²,

Çelebi³

et al. 2023

J. mechatron., artif. intell., eng.

View full text Add to dashboard Cite

show abstract

“…Payeur et al [26] used an artificial neural network (ANN) to learn and predict the trajectories of moving objects; however, they merely performed simulation experiments of simple trajectories and did not develop a novel vision system or robot. Nakashima et al Nakashima et al [27] used a back-propagation artificial neural network (BPANN) to learn striking points. The inputs are the initial location and velocity difference of the ball in a free-fall model, and the outputs are the striking point and displacement between striking points estimated using simple physics.…”

Section: Introductionmentioning

confidence: 99%

Ball Tracking and Trajectory Prediction for Table-Tennis Robots

Lin

Huang

2020

Sensors

View full text Add to dashboard Cite

Sports robots have become a popular research topic in recent years. For table-tennis robots, ball tracking and trajectory prediction are the most important technologies. Several methods were developed in previous research efforts, and they can be divided into two categories: physical models and machine learning. The former use algorithms that consider gravity, air resistance, the Magnus effect, and elastic collision. However, estimating these external forces require high sampling frequencies that can only be achieved with high-efficiency imaging equipment. This study thus employed machine learning to learn the flight trajectories of ping-pong balls, which consist of two parabolic trajectories: one beginning at the serving point and ending at the landing point on the table, and the other beginning at the landing point and ending at the striking point of the robot. We established two artificial neural networks to learn these two trajectories. We conducted a simulation experiment using 200 real-world trajectories as training data. The mean errors of the proposed dual-network method and a single-network model were 39.6 mm and 42.9 mm, respectively. The results indicate that the prediction performance of the proposed dual-network method is better than that of the single-network approach. We also used the physical model to generate 330 trajectories for training and the simulation test results show that the trained model achieved a success rate of 97% out of 30 attempts, which was higher than the success rate of 70% obtained by the physical model. A physical experiment presented a mean error and standard deviation of 36.6 mm and 18.8 mm, respectively. The results also show that even without the time stamps, the proposed method maintains its prediction performance with the additional advantages of 15% fewer parameters in the overall network and 54% shorter training time.

show abstract