JP7070874B2 - Tennis artificial intelligence realization method for virtual tennis simulation, virtual tennis simulation system and method using it - Google Patents

Description

In the present invention, a screen is provided in which a virtual opponent's tennis play image is embodied in a predetermined indoor space, and the user hits a tennis ball launched from a ball machine through the screen with a racket to practice tennis or play tennis. The present invention relates to a virtual tennis simulation system that enables the competition, a sensing device and a sensing method used for the virtual tennis simulation system.

In recent years, for sports such as golf and baseball that are enjoyed using balls, so-called virtual content for practice and competition such as playing golf or baseball in an actual field is provided even in a small indoor space. Due to the popular popularity of screen golf and screen baseball and the accompanying technological development, so-called screen tennis systems have also appeared in tennis, which is the most representative sport that uses balls.

In the sport of tennis, unlike golf and baseball, the user does not keep hitting the ball in one place, but the user with a racket moves very dynamically while sustaining the ball with the opponent player. In the sport of exchanging rallies, the characteristics of such tennis sports are appropriately realized by the screen tennis system, and the user who uses screen tennis hits the ball at various positions while sustaining with the opponent in the image. It can be said that the key is to obtain a variety of analytical information that is difficult to easily grasp in actual tennis sports, while realizing the reality of tennis sports by making it possible to give a sense of realism to the rally.

As prior patent documents relating to the conventional screen tennis system and the sensing device used therein, Patent Application No. 10-2015-0010077, Patent Application No. 10-2015-01388876, US Registered Patent No. 6,776,732, US registered patent Nos. 3,989,246 and the like have been published.

However, conventional screen tennis systems have a low level of artificial intelligence that embodies the virtual opponent on the video, which makes virtual tennis play only provide monotonous and boring video content, so tennis sports as described above. There was a problem that it was not possible to fully realize the reality of the game, and there was a limit to performing a realistic rally with the virtual opponent on the video.

The present invention allows the realization of high-level virtual opponent artificial intelligence, which was difficult to realize with the conventional screen tennis system as described above, and then allows the player to practice tennis or play tennis in various situations. This is to provide a method for embodying tennis artificial intelligence for virtual tennis simulation, and a virtual tennis simulation system and method using the method, which can realize a realistic rally by being able to do it.

The method for embodying artificial tennis intelligence for virtual tennis simulation according to an embodiment of the present invention is a virtual tennis simulation of a virtual tennis simulation system that enables a player to play tennis on the bottom of a court based on a virtual tennis simulation image. As a method of embodying tennis artificial intelligence for, as the opposite court corresponding to the bottom of the court, on the virtual court where the virtual opponent player on the image plays, at the position where the virtual opponent player serves or receives the virtual ball. The stage of determining the starting position of a virtual ball, the stage of determining the target position on the bottom of the court where the hit ball of the virtual opponent player reaches, and the stage of determining the target position of the virtual ball from the virtual ball starting position; By determining information on ball motion conditions and storing information on virtual ball departure positions, target positions, and ball motion conditions in a database, the stage of learning about ball motion conditions according to any virtual ball departure position and target position. ,including.

The present invention also includes a recording medium that can be read by a computing device that records a program by the method for embodying artificial intelligence as described above.

On the other hand, the virtual tennis simulation method using tennis artificial intelligence according to an embodiment of the present invention is realized by a virtual tennis simulation system that enables a player to play tennis on the bottom of a court based on a virtual tennis simulation image. As a virtual tennis simulation method using intelligence, the stage where the sensing device senses the movement of the ball hit by the player and calculates the sensing data for the ball movement, and the bottom of the court from the image based on the calculated sensing data. As the opposite court corresponding to, from the stage of implementing a simulation video for the trajectory of the virtual ball moving to the virtual court played by the virtual opponent player on the video, and from the trajectory of the virtual ball moving to the virtual court, virtual The stage of determining the virtual ball departure position, which is the position where the opponent player receives the virtual ball, and the stage of determining the target position on the bottom of the court where the virtual opponent player receives the received ball by tennis artificial intelligence. Have the virtual ball transfer information about the ball movement conditions from the starting position of the virtual ball to reach the target position on the bottom of the court from the database of the server, extract it from the data storage unit, and use the transferred or extracted information. Includes a step of calculating information about the ball motion conditions and allowing the hit ball received by the virtual opponent player to be simulated according to the ball motion conditions.

On the other hand, the virtual tennis simulation system according to the embodiment of the present invention is a virtual tennis simulation system that enables a player to play tennis with a virtual opponent player by tennis artificial intelligence based on the virtual tennis simulation image. Calculated as a projected screen, a ball machine provided on the back of the screen that provides the ball to the player, and a sensing device that senses the movement of the ball hit by the player and calculates sensing data for the ball movement. Based on the sensing data, the simulated image of the trajectory of the virtual ball moving to the virtual court played by the virtual opponent player on the image and the virtual opponent player as the opposite court corresponding to the bottom of the court from the image. The control device includes a control device that generates and processes a simulation image for the trajectory of the virtual ball according to the received hit ball, and the control device is a position where the virtual opponent player receives the virtual ball from the trajectory of the virtual ball moving to the virtual court. The starting position of the virtual ball is determined, and the virtual opponent player is configured to determine the target position on the bottom of the court where the received hit ball arrives, so that the virtual ball reaches the target position from the virtual ball starting position. It is configured to be accessible to a database that determines information about the ball movement conditions to be made and stores information about the virtual ball departure position, target position and ball movement conditions, and the virtual ball departure position according to the play of the player and the virtual opponent. It is characterized by being configured to be equipped with tennis artificial intelligence to learn about ball movement conditions according to a target position.

On the other hand, in the virtual tennis simulation system according to another embodiment of the present invention, the virtual opponent player who is the opponent of the player and the virtual opponent player play as the opposite court corresponding to the bottom of the court where the player plays tennis. A screen on which a virtual tennis simulation image including a virtual ball moved by a virtual opponent player or a virtual opponent player is projected, and a ball machine provided on the back of the screen to provide the ball to the player. A sensing device that senses the movement of the ball hit by the player and calculates sensing data for the ball movement, and generates and processes a virtual tennis simulation image projected on the screen, between the player and the virtual opponent player. Equipped with tennis artificial intelligence that learns the play of the virtual opponent player according to the play, it embodies the image that the virtual ball moves to the virtual opponent player based on the sensing data of the sensing device for the ball hit by the player. , Tennis artificial intelligence determines information about the virtual ball departure position, which is the position where the virtual opponent player receives the virtual ball, and the motion conditions of the virtual ball departing from the virtual ball departure position, and determines the motion of the virtual ball. The direction and speed of the ball provided to the player by the ball machine are set according to the conditions, and the direction and speed of the ball set by the ball machine on an extension of the trajectory of the virtual ball hit by the virtual opponent player. Includes a control device that allows the player and the virtual opponent player on the video to realize a tennis rally in a manner that causes the player to hit the ball fired from the ball machine.

The tennis artificial intelligence realization method for virtual tennis simulation according to the present invention, and the virtual tennis simulation system and method using the same, realize the high-level artificial intelligence of a virtual opponent, which was difficult to realize by the conventional screen tennis system. Since the player can practice tennis and play tennis games in various situations, it is possible to realize a realistic rally, etc., which raises the interest of players who enjoy virtual tennis play, and further high-level play. It has the effect of enabling you to play tennis.

An example in which a screen tennis system is implemented as a virtual tennis simulation system according to an embodiment of the present invention is shown. It is a drawing which showed the structure of the screen of the virtual tennis simulation system shown in FIG. 1 and its periphery. It is a drawing which showed an example of the video content provided by the virtual tennis simulation system shown in FIG. It is a block diagram which showed the structure of the virtual tennis simulation system shown in FIG. It is a flowchart which showed an example of the method for the realization of the tennis artificial intelligence by one Example of this invention. It is a drawing for demonstrating the realization method of the tennis artificial intelligence for the virtual tennis simulation by one Embodiment of this invention. It is a drawing for demonstrating the realization method of the tennis artificial intelligence for the virtual tennis simulation by one Embodiment of this invention. It is a drawing for demonstrating the realization method of the tennis artificial intelligence for the virtual tennis simulation by one Embodiment of this invention. It is a flowchart for demonstrating an example in which the artificial intelligence by the method of embodying the tennis artificial intelligence by one Embodiment of this invention is applied and used in a virtual tennis simulation system. It is a drawing for demonstrating the play between the player (P) and the virtual opponent player (VP) on the image, and the driving of the ball machine accompanying it in the virtual tennis simulation system according to one Embodiment of this invention.

A method for embodying tennis artificial intelligence for virtual tennis simulation according to the present invention, a virtual tennis simulation system using the same, and a specific content of the method will be described with reference to the drawings.

First, the configuration of the virtual tennis simulation system according to the embodiment of the present invention will be described with reference to FIGS. 1 to 4.

FIG. 1 shows an example in which a screen tennis system is embodied as a virtual tennis simulation system according to an embodiment of the present invention, and FIG. 2 is a drawing showing the configuration of the screen of the virtual tennis simulation system shown in FIG. 1 and its surroundings. Yes, FIG. 3 is a drawing showing an example of the video content provided by the virtual tennis simulation system shown in FIG. 1, and FIG. 4 is a block diagram showing the configuration of the virtual tennis simulation system shown in FIG. 1. ..

As shown in FIG. 1, a virtual tennis simulation system according to an embodiment of the present invention comprises a court bottom (30) and a net (32) in a predetermined space, and a screen (20) in front of a player (P). A ball machine (100) is provided behind the screen (20) to provide a ball to a player (P) who plays tennis with a racket so that the player (P) can hit the ball, and the screen (20) is provided on one side of the space. A sensing device (200) is installed to collect sensing data for the ball and player (P) movements hit by the image output unit (420) and the player (P), and the racket used by the player (P). May be configured.

Devices such as the ball machine (100), the sensing device (200), and the video output unit (420) are connected to the control device (300), and the control device (300) receives and processes the sensing data of the sensing device (200). , The user's virtual tennis practice and competition video content is generated and transmitted to the video output unit (420), and the video output unit (420) projects the received video content on the screen (20) and the ball. It controls the ball launch of the machine (100) and the ball launch parameters such as the direction and speed of the launched ball.

The ball machine (100) is provided behind the screen (20) and at a pre-calculated position on the bottom of the court (30) through the ball launch hole (22) formed in the screen (20). ) Is fired, and as shown in FIG. 1, the ball machine (100) is configured to be capable of firing angle control and rate of fire control so that balls (1) of various speeds can be fired at various positions. Will be done.

FIG. 2 shows a photograph of a virtual tennis simulation system according to an embodiment of the present invention, which is actually embodied and the configuration around the screen (20) is taken. As shown in FIG. 2, the ball launch hole (22) is provided at a generally moderate position on the screen (20). Of course, it can be installed at any position on the screen (20), but in order to realize (the opponent player's) receive for a ball having various trajectories, a generally medium position is desirable as shown in 2.

On the front side of the screen (20), after the ball hit by the user toward the screen (20) collides with the screen (20), the ball is collected again on the ball machine (100) side without rolling to the user side again. Therefore, it is desirable that a net (32) and a bottoming net (32a) installed in an inclined structure are provided, and safety nets (33, 34) are provided on both side surfaces so that the ball does not jump out to the outside.

The balls (2) collected by the net (32) and the bottom trawling net (32a) can be configured to be collected on the collection port (40) side at the lower stage of the screen (20) and transferred to the ball machine side again.

On the other hand, FIG. 3 shows an example of video content provided by the virtual tennis simulation system according to the embodiment of the present invention.

As shown in FIG. 3, the entire video (IM) includes a main video (500) and a mini-map video (600).

The main video (500) realizes a virtual environment for the portion opposite to the bottom of the court on which the user plays, and may include content video for a virtual opponent player (VP), referee, and the like.

In the main video (500), the virtual opponent player (VP) uses a preset artificial intelligence (hereinafter referred to as "AI") to play a virtual ball (VB) as if the opponent plays in an actual tennis match. ) Is received (battered), and as shown in FIG. 3, the locus (Tb) of the virtual ball (VB) hit by the virtual opponent player (VP) may be displayed so that it is not displayed. You can also do it. Regardless of whether the locus is displayed or not, the locus of the virtual ball (VB) must be calculated, and the control of the video content and the ball launch parameter in the ball machine can be calculated and embodied according to the locus. .. A specific explanation of this will be described later.

On the other hand, in the mini-map image (600), the part related to the virtual environment at the bottom of the court and the part on the opposite side where the user plays is regarded as one whole tennis court, and this is reduced to a predetermined size as a plan view seen from above. This is the part that is displayed.

In the mini-map image (600) part, various information such as the current position of the user, the set area based on the user, the position and trajectory in the space of the virtual player, the position of the ball, etc. can be displayed. ..

On the other hand, with reference to FIG. 4, the control system of each component constituting the virtual tennis simulation system according to the embodiment of the present invention as shown in FIG. 1 will be described.

As shown in FIG. 4, the virtual tennis simulation system according to the embodiment of the present invention includes a ball machine (100), a sensing device (200), a control device (300), and a video output unit (420). A database (520) and a server for storing data in a database for the realization of tennis artificial intelligence so that the control device (300) can realize the tennis artificial intelligence through a virtual opponent player on the image. The server (500) including the arithmetic unit (510) is configured to be communicably linked to the control device (300).

The control device (300) can include a data storage unit (320), a video processing unit (330), a control unit (310), and the like, and the video output unit (420) is processed by the video processing unit (330). It can be embodied by a projection device or the like that causes the image to be projected on the screen (20).

The data storage unit (320) is a part for storing data for processing a background image related to tennis practice or competition performed by a virtual tennis simulation system, an image for a virtual player, a simulation image for a hit ball, or the like. The data storage unit (320) may be configured to serve as a memory for temporarily storing data transmitted from a server (not shown).

The video processing unit (330) has a background video such as a video about a virtual tennis court, a video about a player and a referee, a spectator, etc., a video of a virtual opponent player hitting a ball, and a simulation video of a trajectory of a ball hit by a player. Generate various simulation-related images such as.

The control unit (310) performs various calculations for realizing the simulation image of the virtual ball based on the sensing data collected from the sensing device (200), and the ball machine (100) responds to the simulation result of the virtual ball. It may also serve to control the ball so that it can be fired.

In particular, the control unit (310) controls the tennis artificial intelligence to be embodied so that the virtual opponent player on the video can play with the tennis artificial intelligence.

Databased data is required for the realization of tennis artificial intelligence, but when these data are stored in the database (520) of the server (500) and the control unit (310) requests the necessary data. The server calculation unit (510) extracts necessary data from the database (520) and transfers it, and the control unit (310) can embody tennis artificial intelligence by using the transmitted data.

Of course, it is also possible to store the data for embodying the artificial intelligence of tennis in the data storage unit (320) of the control device (300) without the server (500), and when the virtual tennis simulation system is started, the server (500). ) Transfers the data for embodying artificial intelligence to the data storage unit (320) of the control device (300) and temporarily stores it, and the control unit (310) is stored in the data storage unit (320). It is also possible to embody the artificial intelligence of tennis by using the data.

More specific content regarding the realization of the above-mentioned tennis artificial intelligence will be described later.

On the other hand, the sensing device (200) continuously captures an image of the player hitting with a racket, and analyzes the shot image to obtain not only the motion information of the hit ball but also the hit. It can be configured as a camera sensing device that accurately senses which part of the screen the ball reaches.

The sensing device (300) may be configured to include a camera unit (210), a sensing processing unit (220), and a camera control unit (230), wherein the camera unit (210) has a constant shooting range including a preset area. The sensing processing unit (220) receives an image from the camera unit (210), performs image analysis according to the set items, and performs tennis practice or tennis competition based on the virtual tennis simulation. Calculate the required information.

The camera unit (210) of the sensing device (200) shoots the same shooting range from different positions, and the first camera (211) and the first camera (211) can calculate the three-dimensional position information for the object on the shot image. By configuring the stereoscopic system including the two cameras (212), the sensing processing unit (220) can obtain three-dimensional coordinate data for the ball from the analysis of the image taken by the camera unit (210). It is desirable to do.

Although not shown in the drawings, the camera unit (210) of the sensing device (200) provided in the system according to the present invention is configured to be tiltable back and forth and left and right with respect to the center of the angle of view. The first camera (211) and the second camera (212) may be configured to automatically zoom in and out, respectively.

The camera control unit (230) allows the player to perform front / rear / left / right tilting and zoom-in / zoom-out of the first camera (211) and the second camera (212) according to the processing result of the image or from the captured image. It may be configured to control according to a preset program according to the detected position.

It is also possible to configure the first camera (211) and the second camera (212) to perform uniaxial tilting in the front-rear direction or the left-right direction, respectively.

With reference to the position information of each camera in the 3D space and the angle of view of the camera, a data table having the pan and zoom values of the camera for each specific area in the 3D space is created and stored in advance, and based on this. When the position information of the player is detected, the camera control unit (230) can control each camera to aim at the corresponding position.

Therefore, it is possible to accurately catch all the hits of the ball launched to various positions while dynamically moving from the bottom of the court, and acquire an image for collecting sensing data.

The sensing processing unit (220) receives images taken from each of the first camera (211) and the second camera (212) of the camera unit (210), analyzes each of the collected images while collecting them, and balls. 3D coordinate data for each ball is extracted, and the extracted 3D coordinate data is used to determine the motion model of the ball for the ball to be hit and moved (by the player's racket), and the motion model of the ball. Is determined, and using this, various information necessary for tennis practice and tennis competition by virtual tennis simulation is calculated.

Here, the motion model of the ball means that it is expressed by the motion equation regarding the trajectory of the ball that is hit and moved in the three-dimensional space, and as shown in FIG. 1, tennis by the system according to the present invention. The space in which the practice or competition is performed is defined as a three-dimensional coordinate system of x-axis, y-axis, and z-axis, and the motion model of the ball can be determined by the defined coordinate system.

That is, the equation of motion of the ball can be defined as the equation of motion in the x-axis direction, the equation of motion in the y-axis direction, and the equation of motion in the z-axis direction.

The calculation of the ball motion model as described above is completely different from that in a conventional screen golf system or the like in which a sensor senses the motion of a ball hit by a golf club and calculates sensing data.

A camera-type sensing device is widely used in conventional screen golf systems, but the sensing device calculates initial motion conditions such as the starting speed, starting direction angle, and height angle when the ball is hit, and is virtual. It was a method of calculating the trajectory of the ball simulated by the physical engine when the ball departed based on the space of, that is, the initial motion condition calculated from the virtual golf course.

However, the motion model of the ball calculated by the sensing device of the virtual tennis simulation system according to the present invention does not calculate the initial motion condition when the ball is hit, but the space in which the actual player plays, that is, the actual motion model. As a motion model of a ball calculated based on an equation of motion in each coordinate axis direction in a three-dimensional space, a model in which an actual ball moves is obtained.

By calculating such a ball motion model, it is possible to provide more diverse and more information than when simply sensing and calculating the initial motion conditions of the ball, and in particular, it is a reality like a virtual tennis simulation. It is a more suitable sensing method when the virtual world intersects frequently and needs to be connected more closely.

On the other hand, the present invention not only calculates the movement of the ball hit by the player as a ball motion model as described above, but also senses the movement of the player and continuously calculates the position of the player, so that the player hits. By enabling virtual tennis play based on both the movement of the ball and the movement of the player, the player can enjoy dynamic tennis play according to various situations and play styles.

The control device is information about at least one of the player's ability level, difficulty level, and play style, and the position of the player detected by the sensing device according to the artificial intelligence of the virtual opponent player embodied as an image. The direction and speed of the ball provided to the player are determined according to the virtual ball hit by the virtual opponent player according to the motion model of the ball calculated by the sensing device, and the ball machine determines the ball accordingly. It is possible to provide it.

For example, if the player's ability level is high, the player may be in a difficult receive situation by identifying a position far away from the player's position detected by the sensing device and allowing the ball machine to provide the ball at that position. It is possible to realize a virtual play that hits the ball.

On the other hand, the present invention not only calculates the movement of the ball hit by the player as a ball motion model as described above, senses the movement of the player, and continuously calculates the position of the player, but also has the player. By detecting even the racket, the player can play virtual tennis based on all the movements of the ball hit by the player, the movement of the player, and the posture information of the player at the time of playing by the racket detection, so that the player can be more diverse. Make it possible to enjoy dynamic tennis play according to the situation and play style.

The control device is information about at least one of the player's ability level, difficulty level, and play style, and the player's position and sensing detected by the sensing device by the artificial intelligence of the virtual opponent player embodied in the video. The ball motion model calculated by the device, the swing posture information for whether the player swings in the backhand posture or the forehand posture, etc. are provided to the player according to the virtual ball hit by the virtual opponent player. It is possible to determine the direction and speed of the ball to be made and allow the ball machine to provide the ball accordingly.

For example, if the player's ability level is high, the position of the player detected by the sensing device and the position far away are specified, and the ball machine provides the ball at that position, but it is determined in advance whether the player is right-handed or left-handed. By grasping and providing the ball to a position that guides the backhand, which is difficult to receive, it is possible to realize a virtual play in which the player hits the ball in a complicated receive situation.

On the other hand, the ball machine (100) is a device installed on the back surface of the screen (20) and launches a ball through a ball launch hole (22) on the screen (20) by rotating two or more wheels. It can be embodied by various methods such as a method in which a ball is positioned between the wheels and the ball is fired by the rotational force of the wheel, and a method in which the ball is fired as if it were a bullet.

The ball machine (100) gives the virtual opponent player on the image a ball under the set hitting conditions according to the hitting conditions determined based on the artificial intelligence of tennis, the trajectory of the hit ball, and the like. It is possible to control the speed, the quality of the ball, etc. so that the ball is launched.

Further, the ball machine (100) is configured so that the portion for launching the ball can be tilted in the vertical direction and the horizontal direction, respectively, and controls the tilting drive of the portion for launching the ball according to the above-mentioned hitting conditions. , The ball can be launched in various directions within a predetermined angle range through the ball launch hole on the screen.

In the virtual tennis simulation system according to the embodiment of the present invention having the above configuration and features, the player can hit the ball provided by the ball machine with a racket while moving at the bottom of the court, and at this time, the hit. The ball is moved to the virtual space on the image (for example, after the ball that actually moves reaches the screen, the virtual ball moves on the image from that position), and the virtual opponent player on the virtual court. Receives (hits) the movement of the virtual ball against the actual ball hit by the ball, thereby embodying the image of the received virtual ball moving.

At this time, how and in which direction the virtual opponent player receives the ball is determined by the tennis artificial intelligence, which can be determined by the control unit embodying the artificial intelligence using various information. .. Further, it is also possible for the control unit to control the ball machine so that the actual ball is provided via the ball machine on the extension line of the trajectory of the virtual ball received by the virtual opponent player.

In order for the virtual opponent player to play according to the above-mentioned tennis artificial intelligence, data is collected so that the tennis artificial intelligence can realize the image of hitting the ball under various ball movement conditions in various situations. It needs to be stored and preserved, and FIG. 5 illustrates an example of such a method for realizing tennis artificial intelligence as a flowchart.

That is, the flowchart shown in FIG. 5 relates to a process of creating a database and storing the results of simulation in advance so that the ball can be sent to the position intended by the artificial intelligence of tennis.

First, the image corresponding to the bottom of the coat and the image for the virtual coat are embodied (S100). That is, as shown in FIG. 6, the image (31) for the bottom of the court and the image for the virtual court (VW) played by the virtual opponent player on the image can be embodied as the court on the opposite side.

Then, a coat grid (Gr) having a large number of grid surfaces is set for the bottom of the coat (31) (S110), and a virtual coat grid (VGr) having a large number of three-dimensional grids is set for the virtual coat (VW). (S120).

The setting of the court grid (Gr) and the setting of the virtual court grid (VGr) are shown in FIGS. 6 and 7.

As shown in FIGS. 6 and 7, a coat grid (Gr) having a large number of grid surfaces is set on the bottom of the coat (31), and a virtual coat grid (VGr) having a large number of three-dimensional grids is set on the virtual coat (VW). ) Is set.

Tennis artificial intelligence can also recognize the starting position and target position of the virtual ball in each grid surface unit of each court grid and each virtual court grid, and can recognize a specific position in each grid surface of each virtual ball. It can also be recognized as a starting position and a target position.

Here, the virtual ball departure position refers to a position where the virtual opponent player serves or receives the virtual ball on the virtual court played by the virtual opponent player on the video (Ap shown in FIG. 6). The target position is the position where the tennis artificial intelligence intends to send the ball on the image (31) at the bottom of the court.

The virtual ball departure position may be one solid grid of the virtual court grid, may be set as a specific position inside the solid grid surface, and the target position may be one grid surface of the court grid. It can also be set as a specific position inside the grid surface.

The size and number of grid surfaces and three-dimensional grids of the court grid (Gr) and virtual court grid (VGr) can be set arbitrarily. The hitting direction of the opponent player may become elaborate.

Returning to FIG. 5 again, the tennis artificial intelligence is set to the court grid (Gr) and the virtual court grid (VGr) as described above, and then any position (any three-dimensional grid or) of the virtual court grid (VGr). An arbitrary position in the three-dimensional grid) or a preset position is determined as the virtual ball starting position (S130).

Then, the tennis artificial intelligence is determined as a target position reminiscent of an arbitrary position (arbitrary grid surface or any position in the grid surface) of the court grid (Gr) or a preset position (S140).

After the virtual ball departure position and the target position are determined as described above, the tennis artificial intelligence determines an arbitrary ball motion condition for simulating the virtual ball from the virtual ball departure position (S150).

Then, a simulation for the virtual ball trajectory is performed from the virtual ball starting position under the ball motion conditions determined as described above (S160).

At this time, as a result of the simulation, if the virtual ball does not reach the predetermined range of the target position (S170), the ball motion condition used in the advanced simulation is corrected (S172), and further from the virtual ball starting position. Perform a simulation for the virtual ball trajectory under the corrected ball motion conditions, determine whether the virtual ball has reached the predetermined range of the target position, and if not, correct the ball motion conditions again and perform the simulation. Is repeated.

As a result of repeatedly modifying and simulating the ball motion conditions in this way, when the simulated virtual ball reaches a predetermined range of the target position, the ball motion condition information that has reached the target position is stored in the database. At this time, the information on the virtual ball departure position and the information on the target position are also stored in the database (S174).

The process of determining the ball motion condition as described above will be described in more detail with reference to FIGS. 6 to 8.

Based on the 3D grid corresponding to the position where the virtual ball bounces on the virtual court (VW) and the position where the virtual ball bounces, a 3D grid corresponding to the position where the virtual opponent player receives the ball is determined (hence, the figure). As shown in 6, the virtual coat grid (VGr) set on the virtual coat (VW) is not a grid on a plane but a three-dimensional grid), and based on this, an effective target position (Tp) is obtained. Allows the ball to be sent to the corresponding opponent's court (ie, the court grid (Gr) on the bottom of the court (31) on the player side).

At this time, the tennis artificial intelligence sets a ball passing area (PR) in advance as a region through which the trajectory of the moving virtual ball passes from the virtual ball departure position (Ap), and reaches the target position or a predetermined range of the target position. It is possible to repeat the simulation by modifying the ball motion condition so that the trajectory of the virtual ball simulated based on the determined ball motion condition passes through the ball passing region (PR).

By setting the ball passing area (PR) as described above, it is possible to prevent an abnormal case such as a simulation in which the ball is too high.

The narrower the ball passing area (PR) is set as described above, the closer the artificial intelligence ball comes to the net, and the more difficult it is to receive the ball.

The ball motion conditions as described above can be defined by a direction vector, a velocity vector, or the like on the locus of the virtual ball.

If the ball cannot reach the target grid (the grid where Tp exists) and the coordinates are out of order, the strength of the ball (the magnitude of the vector, that is, the velocity) is reduced, and the direction is downward (the three-dimensional space of the vector). One axis component of the above coordinates) Lower. If the ball does not reach the target grid, increase the strength of the ball (the size of the vector) and raise the direction.

For each attempt, the direction and strength are adjusted little by little so that the ball approaches the target position, that is, the target grid as described above. As shown in FIG. 8, as in the case of an arbitrary ball trajectory (Tr), the initial direction greatly deviates from the grid at the target point (Tp), but the probability that the ball reaches the target position increases as the simulation progresses.

In FIG. 8A, the trajectory (Trn) of the nth attempt is shown, but as the simulation is continued here, the ball can reach the grid surface which is the target position (Tp) more and more, and the ball can reach the grid surface of FIG. b) shows the case where the ball reaches the grid plane which is the target position (Tp) in this way (the locus at this time is represented by Tb). If the direction in which the ball can reach the target position (Tp) is calculated, the direction and the motion conditions (velocity, direction, height angle, etc.) at this time are saved. These motion condition information can be stored in the form of a direction vector, a velocity vector, or the like, or can be stored as parameters such as the velocity, direction, and height angle of the ball as described above.

When the direction to reach the target grid and the exercise conditions are obtained, the speed of the ball is gradually increased and the direction is adjusted to be lower so that it resembles a swing that threatens the opponent in an actual tennis match. Simulate while doing the simulation. At this time, if the ball passes over the ball passing area (PR), the direction is corrected downward, and if the ball passes below the ball passing area (PR), the direction is raised upward and the next simulation is performed.

When the number of direction vectors that can reach the target position (Tp) is sufficiently found in the preset number or more, the direction vectors are averaged and saved in a file. The direction thus stored is the direction in which the artificial intelligence launches the virtual ball from the virtual ball departure position (AP) to the target position (Tp).

In such a method, the process of determining the above-mentioned virtual ball starting position and target position for all three-dimensional grids of the virtual court grid and all grid surfaces of the court grid, and finding the ball motion conditions while repeating the simulation. The data derived by repeatedly executing is stored in the database.

In addition, by setting artificial intelligence to be able to add random directions when firing the ball at the target position, it is possible to generate more diverse situations. Then, if necessary, the size of the grid surface or the three-dimensional grid can be adjusted, and the swing of the artificial intelligence can be precisely operated to adjust the difficulty level felt by the player.

On the other hand, an example in which tennis artificial intelligence, which searches for and learns appropriate data while repeating a large number of simulations by the above method, is applied to a virtual tennis simulation system and used, will be described in the flowchart of 9. To.

A player's virtual tennis play by the virtual tennis simulation system according to the embodiment of the present invention progresses (S200), and the sensing device calculates sensing data for the ball motion due to the player's hit (S210).

As described above, the sensing device may calculate the ball motion model as sensing data, but it can also calculate the position information of the player and the information regarding the orientation and posture of the racket held by the player.

After the actual ball hit by the player reaches the screen, the image on the screen embodies a simulation image of the trajectory of the virtual ball (which moves on the extension of the actual ball) moving to the virtual court. (S220).

An image in which a virtual opponent player receives a virtual ball on a virtual court is realized on the image, and the departure position of the virtual ball is determined at that time (S230).

Then, the target position on the bottom of the court where the hit ball received by the virtual opponent player reaches is determined by the artificial intelligence of tennis (S240).

Tennis artificial intelligence is the motion model of the ball hit by the player, the position of the player, whether the player's swing is forehand or backhand, and pre-stored player information (eg right-handed or left-handed, player's). The target position as described above can be determined by using the ability level, difficulty level, play style, etc.).

If the player's ability is high, a complicated position can be set as the target position, and if the player's ability is low, a simple position can be set as the target position.

On the other hand, information regarding the ball motion condition for causing the virtual ball to reach the target position on the bottom of the court from the starting position of the virtual ball is determined (S250).

The information about the ball motion condition is the data for the direction vector from the virtual ball departure position to the determined target position stored in the database of the server or the data storage unit of the control device, and the artificial intelligence is the database or the data storage unit. It is possible to use the data extracted from the above as it is so that the virtual ball is received, but the direction vector extracted based on the player's information, the ball motion model, the player's position information, etc. is modified and simulated. You can also do it.

As described above, when the information regarding the ball motion condition is determined, the virtual opponent player on the video receives (hits) the ball, and thereby the simulation of the virtual ball trajectory is performed under the determined ball motion condition. It is (S260).

At this time, it can be said that the above-mentioned "target position" is not intended for the actual coat bottom, but for the coat bottom on the image when the actual coat bottom is similarly visualized. .. That is, even if the simulation proceeds while the virtual opponent player receives and starts the virtual ball toward the target position, the virtual ball cannot reach the actual bottom of the court.

In the virtual tennis simulation system according to the embodiment of the present invention, the ball machine can provide the ball on the extension of the virtual ball trajectory on the image as described above, while the ball providing direction and the ball providing speed of the ball machine can be determined. It can be determined to correspond to the simulation of the virtual ball trajectory (S310) and the ball machine can provide the ball accordingly (S320). By doing so, it is possible to obtain the effect that the actual ball closes the rest of the trajectory of the virtual ball following the trajectory of the virtual ball, and as a player, while playing virtual tennis, it is as if it were actually. You can feel the reality of playing tennis.

This is shown in FIG. 10, which shows a virtual area provided as video content as if it were a physical area.

That is, behind the screen (20) installed in front of the bottom of the court (30) where the player (P) is located, there is a virtual area (VW) that is the same as the video content embodied on the screen (20). Assuming it exists, it shows that part.

As shown in FIG. 10, when a virtual player (VP) hits a ball on a virtual court (VC) of a virtual area (VW), the control unit of the control device calculates the trajectory (Tb), and the calculation is performed. The locus (Tb) is connected to the ball launching portion (22) of the screen (20), and the actual ball (1) is transferred from the ball launching portion (22) to the locus (Tb) according to the locus (Tb) and the motion condition. ) And fired to correspond to the exercise conditions. (It can be fired under the same trajectory and motion conditions, or it can be applied a weighted value to make it fire a little weaker in consideration of the actual space).

The control device stores information about the player (P)'s ability level, difficulty level, play style, etc. in advance, and controls the virtual opponent player (VP) on the virtual tennis simulation image by artificial intelligence.

The control device determines the position (and racket detection) of the player detected by the sensing device according to the information about the player (P)'s ability level, difficulty level, play style, etc. and the artificial intelligence of the virtual opponent player (VP). The direction of the ball (the ball fired by the ball machine as an actual ball) provided to the player (P) according to the virtual ball hit by the virtual opponent player (VP) in response to the accompanying player's swing posture). A ball launch parameter such as speed is determined, and a simulation image of the trajectory of the virtual ball hit by the virtual opponent player (VP) is processed according to the direction of the determined ball (actual ball), and the ball machine ( The ball launch direction of 100) is set to correspond to the determined ball direction, and as shown in FIG. 10, the ball machine (100) is on an extension of the trajectory of the virtual ball hit by the virtual opponent player (VP). ) Can perform virtual tennis play in a manner that controls the ball (1) to be provided in the direction of the determined ball.

On the other hand, returning to FIG. 9, when the simulation for the virtual ball trajectory is performed as the ball motion condition in the S260 stage, the player advances the rally by receiving again the ball machine launching the ball following the simulation. However, from the standpoint of tennis artificial intelligence, if the trajectory of the simulated virtual ball as described above continues to progress, it is confirmed whether the target position on the bottom of the court reaches a predetermined range (S270). ..

If it is determined that the trajectory of the virtual ball continues to advance and reaches the predetermined range of the target position (S280), there is no correction of the data, and if it does not reach the predetermined range of the target position, the database or the data storage unit. The information regarding the ball motion condition at the ball departure position saved in is changed and saved (S290). For example, when the virtual ball locus passes the target position, the direction of the direction vector can be changed to be lower or the velocity can be changed to be lower and saved.

In the conventional screen tennis system, a certain ball is supplied to the player from the ball feeder, so the player does not have a rally by playing tennis, but only practices monotonously. ..

However, the virtual tennis simulation system according to the embodiment of the work of the present invention is equipped with and utilizes tennis artificial intelligence that learns the play of the virtual opponent player according to the play between the player and the virtual opponent player. Then, the ball is provided in a ball direction and quality that cannot be easily predicted by the player (of course, the ball direction and quality can be predicted to some extent depending on the difficulty level), and a virtual opponent on the image corresponding to the player's play. Since the player also plays in a learning manner, it is possible to realize a more dynamic and actual tennis play rally.

That is, it embodies an image in which a virtual ball moves to the virtual opponent player side based on the sensing data of the sensing device for the ball hit by the player (actual ball), and the virtual opponent player receives the virtual ball by tennis artificial intelligence. Information on the starting position of the virtual ball, which is the position to be played, and the motion conditions of the virtual ball departing from the starting position of the virtual ball is determined, and the ball machine provides the player with the motion conditions of the determined virtual ball. The direction and speed are set so that the ball machine provides the ball at the set direction and speed of the ball on an extension of the trajectory of the virtual ball hit by the virtual opponent player, and the player is fired from the ball machine. It is possible to enable the player and the virtual opponent player on the image to realize the tennis rally while straddling the real and the virtual reality by hitting the ball.

In such a method, the tennis artificial intelligence of the virtual tennis simulation system according to the embodiment of the present invention can be further learned by constantly advancing learning such as modifying the existing stored data each time the player plays repeatedly. It has the characteristic that it enables the realization of high-level artificial intelligence.

The method for embodying artificial tennis intelligence for virtual tennis simulation according to the present invention, the virtual tennis simulation system and method using the method, and the recording medium readable by the computing device that recorded the method are balls in an indoor space of a predetermined size. A technical field that enables a user to practice tennis or play a virtual tennis match by hitting a ball provided by a machine with a tennis racket and sensing it by a sensing device to realize a simulation image through a screen in front. Has industrial applicability in .
[Item 1]
As a method of embodying tennis artificial intelligence for virtual tennis simulation of a virtual tennis simulation system that enables players to play tennis on the bottom of the court based on virtual tennis simulation images.
As the opposite court corresponding to the bottom of the court, the starting position of the virtual ball, which is the position where the virtual opponent player serves or receives the virtual ball, is determined on the virtual court played by the virtual opponent player on the image. And the stage to do
The stage of determining the target position on the bottom of the court where the hit ball of the virtual opponent player reaches, and
From the virtual ball departure position, the information regarding the ball motion conditions for causing the virtual ball to reach the target position is determined, and the information regarding the virtual ball departure position, the target position, and the ball motion conditions is stored in the database. At the stage of learning about the ball motion conditions according to any virtual ball departure position and target position,
How to embody tennis artificial intelligence for virtual tennis simulation including.
[Item 2]
The stage to determine the above target position is
At the stage of setting a coat grid having a large number of preset size grid surfaces for the bottom of the coat,
The tennis artificial intelligence for a virtual tennis simulation according to item 1, comprising a step of determining a preset point or an arbitrary point on an arbitrary grid surface of the court grid as the target position. Realization method.
[Item 3]
The stage to determine the virtual ball departure position is
For the above virtual coat, the stage of setting a virtual coat grid with a large number of three-dimensional grids in advance, and
The item 1 is characterized by comprising a step of determining an arbitrary three-dimensional grid of the virtual court grid or a preset position or an arbitrary position in the preset three-dimensional grid as the virtual ball starting position. How to embody tennis artificial intelligence for virtual tennis simulation.
[Item 4]
The stage to learn about the above ball exercise conditions is
The stage of simulating the trajectory of the virtual ball according to any ball motion condition from the virtual ball departure position, and
The stage of repeating the simulation by modifying the ball motion conditions so that the trajectory of the simulated virtual ball reaches the target position or a predetermined range within the target position, and
Item 1 is characterized by including a step of storing information about a ball motion condition when the trajectory of the simulated virtual ball reaches the target position or a predetermined range within the target position in the database. How to embody tennis artificial intelligence for virtual tennis simulation as described in.
[Item 5]
The stage of repeating the simulation by modifying the above ball motion conditions is
A ball passing area is set in advance as a region through which the locus of the virtual ball moving from the virtual ball departure position passes, and the ball movement condition is determined to reach the target position or a predetermined range within the target position. The artificial tennis for the virtual tennis simulation according to item 4, wherein the trajectory of the simulated virtual ball is modified and simulated so as to pass through the ball passing region. How to embody intelligence.
[Item 6]
The stage to determine the above target position is
At the stage of setting a coat grid having a large number of preset size grid surfaces for the bottom of the coat,
Including a step of determining a target grid surface, which is an arbitrary grid surface or a preset grid surface of the front court grid, as the target position.
The stage to learn about the previous ball movement conditions is
It is characterized by including a step of searching for a preset number of direction vectors so that the virtual ball reaches the target grid surface from the virtual ball departure position and storing the ball motion condition in the database. , A method of embodying tennis artificial intelligence for the virtual tennis simulation according to item 1.
[Item 7]
A recording medium readable by a computing device that records the method according to any of items 1 to 6.
[Item 8]
As a virtual tennis simulation method using tennis artificial intelligence embodied in a virtual tennis simulation system that enables players to play tennis on the bottom of the court based on virtual tennis simulation images.
At the stage where the sensing device senses the movement of the ball hit by the player and calculates the sensing data for the ball movement,
Based on the calculated sensing data, a simulation video for the trajectory of a virtual ball moving from the video to the virtual court played by the virtual opponent player on the video is implemented as the opposite court corresponding to the bottom of the court. And the stage to do
From the trajectory of the virtual ball moving to the virtual court, the stage of determining the virtual ball departure position, which is the position where the virtual opponent player receives the virtual ball, and
The stage of determining the target position on the bottom of the court where the hit ball received by the virtual opponent player reaches by the tennis artificial intelligence, and
Information on the ball motion conditions for causing the virtual ball to reach the target position on the bottom of the court from the virtual ball departure position was transferred from the database of the server, extracted from the data storage unit, and transferred or extracted. A stage in which information regarding the ball motion condition is calculated using the information so that the hit ball received by the virtual opponent player is simulated according to the ball motion condition.
A virtual tennis simulation method using tennis artificial intelligence including.
[Item 9]
The virtual tennis simulation system is provided in front of the bottom of the court, is provided on the back of the screen on which the virtual tennis simulation image is projected, and is configured to include a ball machine that provides the ball to the player.
The stage of controlling the ball providing direction of the ball machine according to the target position on the determined court bottom, and
At the stage of making the simulation according to the extracted ball motion conditions, the speed of the ball provided by the ball machine is determined so as to correspond to the motion of the virtual ball according to the hit ball received by the virtual opponent player. The virtual tennis simulation method using the tennis artificial intelligence according to item 8, wherein the ball machine further includes a step of providing the ball on the bottom of the court according to the ball providing direction and the ball speed. ..
[Item 10]
The virtual tennis simulation system is provided in front of the bottom of the court, is provided on the back of the screen on which the virtual tennis simulation image is projected, and is configured to include a ball machine that provides the ball to the player.
At the stage of making the simulation according to the extracted ball motion conditions, the ball machine provides the ball on an extension of the trajectory of the virtual ball corresponding to the hit ball received by the virtual opponent player. The item is characterized in that the ball providing direction and the ball providing speed of the ball are determined, and the ball machine further includes a step of providing the ball on the bottom of the court according to the determined ball providing direction and the ball providing speed. The virtual tennis simulation method using the tennis artificial intelligence according to 8.
[Item 11]
The stage simulated based on the above extracted or calculated ball motion conditions is
Information on the ball movement conditions extracted from the tennis artificial intelligence database that allows the virtual ball to reach the target position on the bottom of the court from the virtual ball departure position, the player's ability level, play difficulty, and environment. The virtual tennis simulation method using tennis artificial intelligence according to item 8, wherein the method includes a step of changing according to at least one of the settings and applying the ball to the hit ball of the virtual opponent player.
[Item 12]
As a result of the simulation by the stage of making the simulation based on the extracted or calculated ball motion condition, the stage of confirming that the virtual ball reaches the target position and the stage of confirming that the virtual ball reaches the target position.
When the virtual ball has not reached the target position, the information about the ball motion conditions applied to the simulation is changed and stored in the database, so that the ball motion is based on the starting position and the target position of the virtual ball. The virtual tennis simulation method using tennis artificial intelligence according to item 8, further comprising a step of learning about a condition.
[Item 13]
As a virtual tennis simulation system that enables players to play tennis with a virtual opponent player by tennis artificial intelligence based on the virtual tennis simulation image.
The screen on which the above virtual tennis simulation image is projected and
A ball machine provided on the back of the screen to provide the ball to the player,
A sensing device that senses the motion of the ball hit by the player and calculates sensing data for the ball motion,
Based on the calculated sensing data, a simulation image of the trajectory of a virtual ball moving from the image to the virtual court played by the virtual opponent player on the image as the opposite court corresponding to the bottom of the court, and a simulation image. Includes a control device that generates and processes a simulation image of the trajectory of a virtual ball according to the hit ball received by the virtual opponent player.
The above control device
From the trajectory of the virtual ball moving to the virtual court, the departure position of the virtual ball, which is the position where the virtual opponent player receives the virtual ball, is determined, and the hit ball received by the virtual opponent player reaches the court. Configured to determine the target position on the bottom,
From the virtual ball departure position, the information regarding the ball motion conditions for causing the virtual ball to reach the target position is determined, and the database for storing the information regarding the virtual ball departure position, the target position, and the ball motion conditions is accessed. Possible to be configured,
A virtual tennis simulation system characterized by being configured to be equipped with tennis artificial intelligence that learns about the ball movement conditions according to the virtual ball departure position and the target position according to the play of the player and the virtual opponent. ..
[Item 14]
The above control device
From the above database, information on the ball motion conditions for causing the virtual ball to reach the target position on the bottom of the court is extracted or calculated from the starting position of the virtual ball, and the hit ball received by the virtual opponent player is extracted. The ball of the ball machine is made to be simulated according to the calculated ball motion condition, and the ball of the ball machine is provided on the extension line of the trajectory of the virtual ball corresponding to the hit ball received by the virtual opponent player. It is configured to determine the delivery direction and ball delivery speed and transfer to the above ball machine.
The virtual tennis simulation according to item 13, wherein the ball machine is configured to provide the ball to the bottom of the court according to the ball providing direction and the ball providing speed transmitted from the control device. system.
[Item 15]
As the opposite court corresponding to the virtual opponent player who is the opponent of the player and the bottom of the court where the player plays tennis, the virtual court played by the virtual opponent player, the virtual opponent player, or the virtual A screen on which a virtual tennis simulation image including a virtual ball moving by the opponent player is projected,
A ball machine provided on the back of the screen to provide the ball to the player,
A sensing device that senses the motion of the ball hit by the player and calculates sensing data for the ball motion,
It is equipped with tennis artificial intelligence that generates and processes a virtual tennis simulation image projected on the screen and learns the play of the virtual opponent player according to the play between the player and the virtual opponent player.
Based on the sensing data of the sensing device for the ball hit by the player, the image of the virtual ball moving to the virtual opponent player is realized, and the virtual opponent player receives the virtual ball by the tennis artificial intelligence. Information on the virtual ball departure position, which is the position to be played, and the motion conditions of the virtual ball departing from the virtual ball departure position is determined, and the ball machine provides the player with the motion conditions of the determined virtual ball. Set the direction and speed of the ball,
On an extension of the trajectory of the virtual ball hit by the virtual opponent player, the ball machine provides the ball in the direction and speed of the set ball, and the ball fired from the ball machine to the player. A control device that enables the above player and the above virtual opponent player on the image to realize a tennis rally by a method of hitting the ball.
Virtual tennis simulation system including.

Claims (11)

As a method of embodying tennis artificial intelligence for virtual tennis simulation of a virtual tennis simulation system that enables players to play tennis on the bottom of the court based on virtual tennis simulation images.
As the opposite court corresponding to the bottom of the court , the stage of embodying the image for the virtual court, which is the virtual space played by the virtual opponent player on the image, and
From the embodied image, a step of determining a virtual ball departure position, which is a position where the virtual opponent player serves or receives the virtual ball, on the virtual court .
The stage of determining the target position on the bottom of the court where the virtual opponent player serves or receives the virtual ball is simulated and reaches .
Information on the ball motion conditions of the virtual ball simulated so that the virtual ball reaches the target position is determined from the virtual ball departure position, and the virtual ball departure position, the target position, and the ball motion conditions are related. By storing the information in the database, the stage of learning about the ball motion conditions according to any virtual ball departure position and target position, and
How to embody tennis artificial intelligence for virtual tennis simulation including. The step of determining the target position is
A step of setting a coat grid having a large number of preset size grid surfaces for the bottom of the coat, and
The method for embodying tennis artificial intelligence for a virtual tennis simulation according to claim 1, which comprises a step of determining a preset point or an arbitrary point on an arbitrary grid surface of the court grid as the target position. The stage of determining the virtual ball departure position is
For the virtual coat, the stage of setting a virtual coat grid having a large number of three-dimensional grids in advance, and
The virtual tennis according to claim 1 or 2, which comprises a step of determining a preset position or an arbitrary position in the virtual grid or the preset three-dimensional grid as the virtual ball starting position. How to embody tennis artificial intelligence for simulation. The stage of learning about the ball movement conditions is
A stage of simulating the trajectory of the virtual ball according to an arbitrary ball motion condition from the virtual ball starting position, and
A step of repeating the simulation by modifying the ball motion condition so that the trajectory of the simulated virtual ball reaches the target position or a predetermined range within the target position.
Any of claims 1 to 3, comprising storing information about the ball motion conditions when the simulated virtual ball trajectory reaches the target position or a predetermined range within the target position in the database. The method of embodying tennis artificial intelligence for the virtual tennis simulation described in item 1. The stage of repeating the simulation by modifying the ball motion condition is
A ball passing area is preset as a region through which the locus of the virtual ball moving from the virtual ball starting position passes, and the ball movement condition is determined to reach the target position or a predetermined range within the target position. The method for embodying tennis artificial intelligence for virtual tennis simulation according to claim 4, wherein the ball motion condition is modified and simulated so that the trajectory of the simulated virtual ball passes through the ball passing region. .. The step of determining the target position is
A step of setting a coat grid having a large number of preset size grid surfaces for the bottom of the coat, and
A step of determining a target grid surface, which is an arbitrary grid surface of the front court grid or a preset grid surface, as the target position is included.
The stage of learning about the ball movement conditions is
The first aspect of the present invention includes a step of searching a preset number of direction vectors for causing the virtual ball to reach the target grid surface from the virtual ball starting position and storing the direction vector in the database as the ball motion condition. How to embody tennis artificial intelligence for the described virtual tennis simulation. As a virtual tennis simulation method using tennis artificial intelligence embodied in a virtual tennis simulation system that enables players to play tennis on the bottom of the court based on virtual tennis simulation images.
At the stage where the sensing device senses the movement of the ball hit by the player and calculates the sensing data for the ball movement.
Based on the calculated sensing data, a virtual ball moving from the virtual tennis simulation image to a virtual court, which is a virtual space played by a virtual opponent player on the image, as a court on the opposite side corresponding to the bottom of the court. At the stage of implementing the simulation video for the trajectory,
From the locus of the virtual ball moving to the virtual court, a step of determining a virtual ball departure position, which is a position where the virtual opponent player receives the virtual ball on the virtual court, which is a virtual space ,
The stage of determining the target position on the bottom of the court where the virtual ball received by the virtual opponent player is simulated and reached by the tennis artificial intelligence.
Information on the ball motion conditions of the virtual ball simulated so that the virtual ball reaches the target position on the bottom of the court from the virtual ball departure position is transferred from the database of the server and extracted from the data storage unit. The transfer or the extracted information is used to calculate information about the ball motion condition, and the virtual ball received by the virtual opponent player is simulated according to the ball motion condition.
The stage simulated based on the extracted or calculated ball motion conditions is
Information on the ball movement conditions extracted from the tennis artificial intelligence database that allows the virtual ball to reach the target position on the bottom of the court from the virtual ball departure position, the player's ability level, play difficulty, and environment. A virtual tennis simulation method using tennis artificial intelligence, which includes a step of changing according to at least one of the settings and applying the ball to the hit ball of the virtual opponent player. As a result of the simulation by the step of making the simulation based on the extracted or calculated ball motion condition, the step of confirming that the virtual ball reaches the target position, and the step of confirming that the virtual ball reaches the target position.
When the virtual ball has not reached the target position, the information about the ball motion condition applied to the simulation is changed and stored in the database, so that the ball motion is based on the starting position and the target position of the virtual ball. The virtual tennis simulation method using the tennis artificial intelligence according to claim 7, further comprising a step of learning about the conditions. As a virtual tennis simulation system that enables players to play tennis with a virtual opponent player by tennis artificial intelligence based on the virtual tennis simulation image.
The screen on which the virtual tennis simulation image is projected and
A ball machine provided on the back of the screen to provide the ball to the player,
A sensing device that senses the motion of the ball hit by the player and calculates sensing data for the ball motion.
Based on the calculated sensing data, the trajectory of a virtual ball moving from the virtual tennis simulation image to a virtual court, which is a virtual space played by a virtual opponent player on the image, as the opposite court corresponding to the bottom of the court. A control device that generates and processes a simulation image for a virtual ball and a simulation image for a trajectory of a virtual ball corresponding to a hit ball received by the virtual opponent player.
The control device is
From the trajectory of the virtual ball moving to the virtual court, the virtual ball departure position, which is the position where the virtual opponent player receives the virtual ball , is determined on the virtual court, which is the virtual space, and the virtual opponent player. Is configured to determine the target position on the bottom of the court where the received virtual ball will be simulated and reached .
Information on the ball motion conditions of the virtual ball simulated so that the virtual ball reaches the target position is determined from the virtual ball departure position, and the virtual ball departure position, the target position, and the ball motion conditions are related. Configured to access the database that stores the information
A virtual tennis simulation system configured to be equipped with tennis artificial intelligence that learns about ball motion conditions according to the virtual ball starting position and the target position according to the play of the player and the virtual opponent. The control device is
From the database, information on ball motion conditions for causing the virtual ball to reach a target position on the bottom of the court is extracted or calculated from the virtual ball starting position, and the hit ball received by the virtual opponent player is extracted. The ball of the ball machine is simulated according to the calculated ball motion condition, and the ball is provided by the ball machine on an extension of the trajectory of the virtual ball corresponding to the hit ball received by the virtual opponent player. It is configured to determine the delivery direction and ball delivery speed and transfer it to the ball machine.
The virtual tennis simulation system according to claim 9, wherein the ball machine is configured to provide a ball to the bottom of the court according to a ball providing direction and a ball providing speed transmitted from the control device. The virtual opponent player who is the opponent of the player, the virtual court which is the virtual space where the virtual opponent player plays as the opposite court corresponding to the bottom of the court where the player plays tennis, and the virtual opponent player. Or a screen on which a virtual tennis simulation image including a virtual ball moving by the virtual opponent player is projected.
A ball machine provided on the back of the screen to provide the ball to the player,
A sensing device that senses the motion of the ball hit by the player and calculates sensing data for the ball motion.
It is equipped with tennis artificial intelligence that generates and processes a virtual tennis simulation image projected on the screen and learns the play of the virtual opponent player according to the play between the player and the virtual opponent player.
Based on the sensing data of the sensing device for the ball hit by the player, an image of the virtual ball moving to the virtual opponent player is realized, and the virtual opponent player is a virtual space by the tennis artificial intelligence. On the virtual court, information regarding the virtual ball departure position, which is the position for receiving the virtual ball, and the motion conditions of the virtual ball departing from the virtual ball departure position is determined, and the motion conditions of the determined virtual ball are determined. Accordingly, the direction and speed of the ball provided by the ball machine to the player are set.
On an extension of the trajectory of the virtual ball hit by the virtual opponent player, the ball machine causes the ball to be provided at the set direction and speed of the ball, and the ball fired from the ball machine to the player. A control device that enables the player and the virtual opponent player on the image to realize a tennis rally by hitting the ball.
Virtual tennis simulation system including.

Images