Exercise intensity-driven level design
Balancing an exercise intensity level and a fun factor of a game is non-trivial and challenging. Disclosed herein are aspects and embodiments of an optimization-based approach to address this challenge. The approach can be applied to synthesize a game level with a desired exercise intensity level. By formulating the design problem as an optimization, a level designer can easily balance factors concerning the exercise intensity level of the game as well as other design factors and constraints.
1. A method for generating a design of a level in a user motion-based game, the method comprising:
defining a plurality of different types of chunks to select from to combine to form the game level, each of the different types of chunks having an associated exercise intensity property, at least some of the different types of chunks having different associated exercise intensity properties than others of the different types of chunks; and
performing an optimization including:
assembling the game level with one of different numbers and different types of chunks in different iterations of the optimization;
evaluating the game level assembled in each iteration for a physical difficulty the game level is predicted to impose on a game player performing the game level; and
iteratively updating the number and/or types of chunks in the game level until a desired extent of predicted physical difficulty for the game player performing the game level is obtained.
2. The method of claim 1 , wherein defining the plurality of different types of chunks further includes defining different types of chunks having different respective durations.
3. The method of claim 2 , wherein performing the optimization includes selecting a game level design that minimizes a total cost function including energy intensity cost functions associated with each of a total predicted number of calories that the player would burn to complete the game level, a mean exercise intensity predicted to be experienced by the game player while performing the game level, and a variance in predicted energy intensity among the chunks making up the game level.
4. The method of claim 3 , wherein the total cost function further includes a duration cost function associated with a difference between a calculated duration of the game level and a target duration of the game level.
5. The method of claim 3 , wherein the total cost function further includes an adjacent chunk variation cost function associated with adjacent chunks in the game level being either of the same type or different types.
6. The method of claim 3 , wherein the optimization terminates if a change is the total cost function is less than a predetermined amount for a predetermined number of previous iterations.
7. The method of claim 1 , wherein performing an iteration of the optimization includes determining whether to modify a game level design of an immediately previous iteration by one of adding a chunk to the game level design of the immediately previous iteration, removing a chunk from the game level design of the immediately previous iteration, or modifying a chunk of the game level design of the immediately previous iteration.
8. The method of claim 7 , wherein adding a chunk to the game level design of the immediately previous iteration includes adding a randomly selected type of chunk to a random location within the game level design of the immediately previous iteration.
9. The method of claim 7 , wherein removing a chunk from the game level design of the immediately previous iteration includes removing a randomly selected chunk from the game level design of the immediately previous iteration.
10. The method of claim 7 , wherein modifying a chunk of the game level design of the immediately previous iteration includes modifying a randomly selected of chunk within the game level design of the immediately previous iteration to be a randomly selected different type of chunk.
11. The method of claim 7 , wherein a determination regarding accepting a modification to the game level design in the iteration of the optimization is made based at least partially on a comparison between an evaluation of the total cost function of the modified game level and an evaluation of the total cost function of the game level design of the immediately previous iteration.
12. The method of claim 11 , further comprising reducing the probability of accepting a modification to the game level as the optimization progresses.
13. The method of claim 1 , further comprising limiting a total number of each type of chunk to include in the game level to a predefined number.
14. A computer system including a processor and instructions, which when performed on the processor, cause the processor to perform a method, the method comprising:
defining a plurality of different types of chunks to select from to combine to form the game level, each of the different types of chunks having an associated exercise intensity property, at least some of the different types of chunks having different associated exercise intensity properties than others of the different types of chunks; and
performing an optimization including:
assembling the game level with one of different numbers and different types of chunks in different iterations of the optimization;
evaluating the game level assembled in each iteration for a physical difficulty the game level is predicted to impose on a game player performing the game level; and
iteratively updating the number and/or types of chunks in the game level until a desired extent of predicted physical difficulty for the game player performing the game level is obtained.
15. The computer system of claim 14 , wherein defining the plurality of different types of chunks further includes defining different types of chunks having different respective durations.
16. The computer system of claim 15 , wherein performing the optimization includes selecting a game level design that minimizes a total cost function including energy intensity cost functions associated with each of a total predicted number of calories that the player would burn to complete the game level, a mean exercise intensity predicted to be experienced by the game player while performing the game level, and a variance in predicted energy intensity among the chunks making up the game level.
17. The computer system of claim 16 , wherein the total cost function further includes a duration cost function associated with a difference between a calculated duration of the game level and a target duration of the game level.
18. The computer system of claim 14 , wherein performing an iteration of the optimization includes determining whether to modify a game level design of an immediately previous iteration by one of adding a chunk to the game level design of the immediately previous iteration, removing a chunk from the game level design of the immediately previous iteration, or modifying a chunk of the game level design of the immediately previous iteration.
19. The computer system of claim 14 , wherein the method further comprises limiting a total number of each type of chunk to include in the game level to a predefined number.
20. A computer program product comprising a non-transitory storage medium, the computer program product including code that, when executed by processing circuitry of a computing device, causes the processing circuitry to perform a method, the method comprising:
defining a plurality of different types of chunks to select from to combine to form the game level, each of the different types of chunks having an associated exercise intensity property, at least some of the different types of chunks having different associated exercise intensity properties than others of the different types of chunks; and
performing an optimization including:
assembling the game level with one of different numbers and different types of chunks in different iterations of the optimization;
evaluating the game level assembled in each iteration for a physical difficulty the game level is predicted to impose on a game player performing the game level; and
iteratively updating the number and/or types of chunks in the game level until a desired extent of predicted physical difficulty for the game player performing the game level is obtained.