# US 8,280,826 B2 · Combining speculative physics modeling with goal-based artificial intelligence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 8,280,826 B2
- Document ID: US8280826B2
- Status: Granted
- Kind: B2
- Application number: 13/269,664
- Filed: 2011-10-10
- Published: 2012-02-02
- Granted: 2012-10-02
- Earliest claimed: 2008-03-26
- Assignees: Intel Corporation
- Inventors: David Putzolu; Aaron Kunze; Teresa Morrison
- Web page: https://patentgrep.com/patent/US8280826B2

## CPC

- A63F 13/57: Simulating properties, behaviour or motion of objects in the game world, e.g. computing tyre load in a car race game (A63F13/56 takes precedence)
- A63F 13/67: adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
- A63F 2300/6027: using adaptive systems learning from user actions, e.g. for skill level adjustment
- A63F 2300/64: for computing dynamical parameters of game objects, e.g. motion determination or computation of frictional forces for a virtual car
- A63F 2300/6615: using models with different levels of detail [LOD]
- A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR

## Abstract

In one embodiment, the present invention includes a method for identifying a deformable object of a scene of a computer game that is visible by an artificial intelligence (AI) character of the game, requesting a speculative physics simulation associated with the deformable object to determine a result of an action to the deformable object by the AI character, and selecting an action to be performed by the AI character, where the selection is based at least in part on the speculative physics simulation. Other embodiments are described and claimed.

## Claims

### Claim 1

A method comprising:
identifying, by a processor, a deformable object of an environment of a video game that is visible by an artificial intelligence (AI) character of the video game;
requesting, by the processor, at least one speculative physics simulation each for a speculative action to be performed on the deformable object; and
selecting, by the processor, one of a plurality of actions that can be taken by the AI character, wherein the selection is based at least in part on the at least one speculative physics simulation.

### Claim 2 (depends on 1)

The method of claim 1, further comprising selecting the action from the plurality of actions based at least in part on a cost associated with each action.

### Claim 3 (depends on 1)

The method of claim 1, further comprising requesting a plurality of speculative physics simulations, wherein a priority of the speculative physics simulations is based on a distance between the corresponding deformable object and the AI character.

### Claim 4 (depends on 1)

The method of claim 1, further comprising performing the at least one speculative physics simulation using a simulation model having a first accuracy, the first accuracy having a lower accuracy than a simulation model having a second accuracy performed for actual movement of the deformable object.

### Claim 5 (depends on 1)

The method of claim 1, further comprising receiving a result associated with one of the speculative actions and updating a graph of potential actions to be taken by the AI character based on the result.

### Claim 6 (depends on 5)

The method of claim 5, wherein the graph of potential actions prior to the updating includes only pre-programmed actions.

### Claim 7 (depends on 1)

The method of claim 1, further comprising evaluating multiple deformable object manipulation options in an AI subsystem that controls the AI character based on the at least one speculative physics simulation.

### Claim 8 (depends on 7)

The method of claim 7, further comprising evaluating each of the multiple deformable object manipulation options on a different core or subset of cores of a multi-core processor.

### Claim 9 (depends on 1)

The method of claim 1, further comprising limiting available processor resources to perform the at least one speculative physics simulation to a predetermined level.

### Claim 10

An article comprising a non-transitory storage medium including instructions that when executed cause a system to:
identify a deformable object of an environment of a video game that is visible by an artificial intelligence (AI) character, during developmental execution of a prototype version of the video game;
perform at least one speculative physics simulation associated with the deformable object to generate a physics model including an integration stage and a collision detection stage to determine a result associated with a possible action to the deformable object by the AI character;
incorporate the result into a graph of possible actions to be taken by the AI character, wherein the graph includes a plurality of pre-programmed actions; and
store the result in a temporary storage for access by a programmer of the video game.

### Claim 11 (depends on 10)

The article of claim 10, further comprising instructions to select one of a plurality of actions that can be taken by the AI character from the graph of possible actions.

### Claim 12 (depends on 11)

The article of claim 11, further comprising instructions to cause the AI character to select from the graph a dynamically defined action corresponding to the result for execution, wherein a cost associated with the dynamically defined action is greater than a cost associated with the pre-programmed actions.

### Claim 13 (depends on 12)

The article of claim 12, further comprising instructions to store a result occurring due to the selected action in the temporary storage for access by the programmer.

### Claim 14

A system comprising:
a processor including a plurality of cores to independently execute instructions; and
a dynamic random access memory (DRAM) to store a program including instructions, the program having an artificial intelligence (AI) module and a physics module to execute on the processor, the AI module to identify a deformable object of an environment of the program that is visible by an AI character controlled by the AI module, request the physics module to perform a speculative physics simulation for a speculative action to be performed on the deformable object to determine a result, the speculative physics simulation limited to a predetermined level of bandwidth of the processor, and add the action to a set of actions that the AI character can take on the deformable object, wherein others of the set of actions are pre-programmed.

### Claim 15 (depends on 14)

The system of claim 14, wherein the AI module is to add the action to a graph of potential actions, and associate a cost with the action.

### Claim 16 (depends on 15)

The system of claim 15, wherein the instructions enable the AI module to select an action from the set of actions, wherein the selection is based at least in part on a cost for the selected action.

### Claim 17 (depends on 16)

The system of claim 16, wherein the physics module is to perform the speculative physics simulation at a lower accuracy than a physics simulation to be performed if the action is selected.

### Claim 18 (depends on 14)

The system of claim 14, wherein the AI module is to request a plurality of speculative physics simulations, and the physics module is to prioritize the speculative physics simulations based on a distance between the corresponding deformable object and the AI character.

### Claim 19 (depends on 18)

The system of claim 18, wherein the physics module is to execute each of the plurality of speculative physics simulations on a different one of the plurality of cores.

### Claim 20 (depends on 14)

The system of claim 14, wherein at least one of the pre-programmed actions is derived from a request of the AI module for a speculative physics simulation during prototype execution of the program.
