U.S. Patent No. 10,839,215: Artificial intelligence for emulating human playstyles

Issued November 17, 2020, to Electronic Arts Inc.
Filed/Priority to May 21, 2018

Overview:

U.S. Patent No. 10,839,215 (the ‘215 patent) relates to artificial intelligence (AI) which uses player data to emulate human-like gameplay. The ‘215 patent details instructions executed by one or more computing devices to generate image indicating positional information, and non-positional information, about objects in a video game. A first AI is selected from several, based at least partially on the data, is provided with the data as inputs. The AI is configured to receive the image and data as inputs, process the inputs, and generate control command outputs. The AI executes at least one command to control the computer-controlled character in the video game, during runtime of the game.

The image generated by the ‘215 patent includes a retina image which is a matrix divided into cells, each cell corresponding to a location in the video game and indicating which objects are in which cells. While processing the control operation, the computer-controlled character checks the consequences of the operation and behaves at least partially based on the consequences. The computer-controlled character plays a similar role to a player-controlled character in the video game. The ‘215 patent could make AI controlled characters more human-player-like in some games.

Abstract:

An artificially intelligent entity can emulate human behavior in video games. An AI model can be made by receiving gameplay logs of a video gameplay session, generating, based on the gameplay data, first situational data indicating first states of the video game, generating first control inputs provided by a human, the first control inputs corresponding to the first states of the video game, training a first machine learning system using the first situational data and corresponding first control inputs, and generating, using the first machine learning system, a first artificial intelligence model. The machine learning system can include a convolutional neural network. Inputs to the machine learning system can include a retina image and/or a matrix image.

Illustrative Claim:

1. A non-transitory, computer-readable storage medium storing computer readable instructions that, when executed by one or more computing devices, causes the one or more computing devices to perform operations comprising: generating an image indicating positional information about objects in a virtual environment within a video game, the objects including at least one computer-controlled character; generating data including non-positional information about the objects in the virtual environment; selecting a first artificial intelligence (AI) model from among a plurality of AI models based at least in part on the image and the data; providing the image and the data as inputs to the first AI model, wherein the first AI model is configured to: receive, as model inputs, the image and the data; process the model inputs; and generate, as outputs, at least one command to control operation of the computer-controlled character; executing the at least one command to control operation of the computer-controlled character within the virtual environment; and generating instructions to output the execution of the at least one command by the computer-controlled character within the virtual environment during runtime execution of the video game.

U.S. Patent No. 10,953,330: Reality vs Virtual Reality Racing

Issued March 23, 2021, to Buxton Glob. Enter. Inc.
Filed: July 22, 2019 (claiming priority to July 7, 2017)

Overview:

U.S. Patent No. 10,953,330 (the ‘330 patent) relates to tracking the locations of a physical object and a virtual vehicle on a racetrack and displaying them to merge physical and virtual racing. The ‘330 patent describes a method for displaying a virtual vehicle which takes several points of view of a racecourse, sometimes including one in a physical vehicle, and provides them to a simulation system which creates the virtual vehicle. This system takes the points of view in the real world and mirrors them in the virtual world to allow virtual and real drivers to compete in the “same” space. The points of view in both worlds are also used to display the physical object in the virtual world. As the virtual vehicle moves the virtual points of view are used by the simulation system to calculate which parts of the virtual vehicle are visible from points of view in the real world, including when it is obscured by physical objects. This information is used to provide to a display system the visible parts of the virtual vehicle to a real-life driver or an audience in some versions.

The ‘330 patent aims to allow racers of both the physical and virtual world to compete in the same world. In some versions, the '330 patent provides predictive information to audience members like trajectory information or likelihood of a virtual vehicle overtaking a physical one. This could be an interesting fusion of e-sports and real-life sports for players, drivers, and audiences alike.

Abstract:

A method for displaying a virtual vehicle includes identifying a position of a physical vehicle at a racecourse, identifying a position of a point of view at the racecourse, providing a portion of the virtual vehicle visible from a virtual position of the point of view. The method operates by calculating the virtual position within a virtual world based on the position of the point of view. A system for displaying virtual vehicles includes a first sensor detecting a position of a physical vehicle at a racecourse, a second sensor detecting a position of a point of view at the racecourse, and a simulation system providing a portion of the virtual vehicle visible from a virtual position of the point of view. The simulation system is configured to calculate the virtual position of the point of view within a virtual world based on the position of the point of view.

Illustrative Claim:

The invention claimed is:

1. A method for displaying a virtual vehicle comprising: identifying respective positions of multiple points of view at a racecourse; providing the respective positions of the points of view at the racecourse to a simulation system; providing a position of a physical object at the racecourse to a simulation system; calculating, by the simulation system, a virtual world comprising the virtual vehicle; calculating, by the simulation system, respective virtual positions of the points of view within the virtual world based on the respective positions of the points of view at the racecourse; calculating, by the simulation system, a representation of the physical object in the virtual world between the respective virtual positions of the points of view and the virtual vehicle within the virtual world; calculating, by the simulation system, respective portions of the virtual vehicle within the virtual world that are visible from the corresponding virtual positions of the points of view, wherein the respective portions of the virtual vehicle within the virtual world that are visible from the corresponding virtual positions of the points of view comprise respective portions of the virtual vehicle that are unobscured, from the respective virtual position, by the representation of the physical object; outputting, by the simulation system, the respective portions of the virtual vehicle visible from the virtual positions of the points of view; providing, to a display system, the respective portions of the virtual vehicle visible from the virtual positions of the points of view; generating, at the display system, representations of the respective portions of the virtual vehicle visible from the virtual positions of the points of view; and displaying a series of representations of the virtual vehicle over a period of time to simulate a trajectory of the virtual vehicle on the racecourse, wherein the series of representations comprises the generated representations.