Mixture model for motion lines in a virtual reality environment
View Patent ↗Improved human-like realism of computer opponents in racing or motion-related games is provided by using a mixture model to determine a dynamically prescribed racing line that the AI driver is to follow for a given segment of the race track. This dynamically prescribed racing line may vary from segment to segment and lap to lap, roughly following an ideal line with some variation. As such, the AI driver does not appear to statically follow the ideal line perfectly throughout the race. Instead, within each segment of the course, the AI driver's path may smoothly follow a probabilistically-determined racing line defined relative to at least one prescribed racing line.
1. A method comprising:
computing a first dynamically prescribed motion line according to a mixture model and based on a probabilistic distribution between a first statically prescribed motion line and a second statically prescribed motion line, wherein the mixture model is defined as function
λ
=
f
(
y
)
=
ⅇ
y
1
+
ⅇ
y
computed wherein λε[0,1];
generating one or more control signals to guide motion of an entity in a virtual reality environment in accordance with the first dynamically prescribed motion line; and
displaying the entity on a display device according to the one or more control signals.
2. The method of claim 1 wherein a mixture parameter of the mixture model controls deviation of the dynamically prescribed motion line from the statically prescribed motion lines.
3. The method of claim 2 , further comprising adjusting the mixture parameter to alter the dynamically prescribed motion line.
4. The method of claim 1 wherein the mixture model is characterized by a mean and the method further comprises:
adjusting the mean to alter the dynamically prescribed motion line.
5. The method of claim 1 wherein the mixture model is characterized by a standard deviation and the method further comprises:
adjusting the standard deviation to alter the dynamically prescribed motion line.
6. The method of claim 1 wherein the first dynamically prescribed motion line is L and is defined by L=λL 0 +(1−λ)L 1 , and the first statically prescribed motion line is L 0 , and the second statically prescribed motion line is L 1 .
7. One or more computer-readable media embodying processor-executable instructions that, when executed by one or more processors, cause the one or more processors to implement a method comprising:
computing a first dynamically prescribed motion line associated with a first course segment according to a mixture model and based on a probabilistic distribution relative to at least a first statically prescribed motion line and a second statically prescribed motion line, wherein the mixture model is defined as function
λ
=
f
(
y
)
=
ⅇ
y
1
+
ⅇ
y
computed wherein λε[0,1];
generating one or more first control signals to guide motion of an entity in a virtual reality environment in accordance with the first dynamically prescribed motion line;
computing a second dynamically prescribed motion line associated with a second course segment and based on the probabilistic distribution relative to the first statically prescribed motion line and the second statically prescribed motion line;
generating one or more second control signals to guide motion of the entity in the virtual reality environment in accordance with the second dynamically prescribed motion line; and
displaying the entity on a display device according to the first and second control signals.
8. The one or more computer-readable media of claim 7 , further comprising displaying the virtual environment on the display device.
9. The one or more computer-readable media of claim 7 wherein a mixture parameter controls deviation of the dynamically prescribed motion lines from the first and second statically prescribed motion lines.
10. The one or more computer-readable media of claim 9 , further comprising adjusting the mixture parameter to alter the dynamically prescribed racing lines.
11. The one or more computer-readable media of claim 7 , further comprising
adjusting the mean to alter the dynamically prescribed racing lines.
12. The one or more computer-readable media of claim 7 , further comprising adjusting the standard deviation to alter the dynamically prescribed racing lines.
13. The one or more computer-readable media of claim 7 , the first dynamically prescribed motion line is L and is defined by L=λL 0 +(1−λ)L 1 , and the first statically prescribed motion line is L 0 , and the second statically prescribed motion line is L 1 .
14. A system comprising: a central-processing unit (CPU); a memory; a mixture model line sampling module configured to compute, according to a mixture model and based on a probabilistic distribution relative to at least two statically prescribed motion lines, a first dynamically prescribed motion line associated with a first course segment and a second dynamically prescribed motion line associated with a second course segment, wherein the mixture model is defined as function
λ
=
f
(
y
)
=
ⅇ
y
1
+
ⅇ
y
computed wherein λε[0,1];
an artificial intelligence motion control system generating at least one control signal to guide motion of an entity in a virtual reality environment in accordance with the dynamically prescribed motion lines.
15. The system of claim 14 further comprising:
a mixture parameter that controls deviation of the dynamically prescribed motion lines from the at least two statically prescribed motion line.
16. The system of claim 15 wherein the mixture parameter is adjustable and adjustment of the mixture parameter alters the dynamically prescribed motion lines.
17. The system of claim 14 wherein the probabilistic distribution is characterized by a mean that is adjustable and adjustment of the mean alters the dynamically prescribed motion lines.
18. The system of claim 14 wherein the probabilistic distribution is characterized by a standard deviation that is adjustable and adjustment of the standard deviation alters the dynamically prescribed motion lines.
19. The system of claim 14 wherein the first dynamically prescribed motion line is L and is defined by L=λL 0 +(1−λ)L 1 , and the first statically prescribed motion line is L 0 , and the second statically prescribed motion line is L 1 .