Scalabale simultaneous localization and mapping (SLAM) in virtual, augmented, and mixed reality (xR) applications
Systems and methods for scalable Simultaneous Localization and Mapping (SLAM) in virtual, augmented, and mixed reality (xR) applications are described. In some embodiments, an Information Handling System (IHS) may include: a host processor; and a memory coupled to the host processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: select a subset of landmarks comprising fewer than all landmarks detected in a physical environment; and manage utilization of an IHS resource during execution of a virtual, augmented, or mixed reality application using the subset of landmarks to the exclusion of other landmarks.
1. An Information Handling System (IHS), comprising:
a host processor; and
a memory coupled to the host processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to:
select a subset of landmarks comprising fewer than all landmarks detected in a physical environment;
manage utilization of an IHS resource during execution of a virtual, augmented, or mixed reality application using the subset of landmarks to the exclusion of other landmarks; and
at least one of:
(a) identify an increase in the utilization of the IHS resource and reduce the number of landmarks in the subset of landmarks to avoid reaching a maximum IHS resource utilization level; or
(b) identify a decrease in the utilization of the IHS resource and increase the number of landmarks in the subset of landmarks without reaching the maximum IHS resource utilization level.
2. The IHS of claim 1 , wherein to select the subset of landmarks, the program instructions, upon execution, further cause the IHS to rank a plurality of landmarks using a confidence level associated with each landmark.
3. The IHS of claim 2 , wherein the program instructions, upon execution, further cause the IHS to calculate the confidence level of each landmark using a Kalman filter.
4. The IHS of claim 3 , wherein the subset of landmarks comprises a number of landmarks selected to maintain the utilization of the IHS resource below a predetermined amount.
5. The IHS of claim 4 , wherein the number of landmarks is selected based upon a calibration curve that associates a change in number of used landmarks with a corresponding change in utilization of the IHS resource.
6. The IHS of claim 1 , wherein the IHS resource comprises the host processor.
7. The IHS of claim 1 , wherein the IHS resource comprises the memory.
8. The IHS of claim 1 , wherein the landmarks are detected via a Head-Mounted Device (HMD) in communications with the IHS.
9. The IHS of claim 8 , wherein the subset of landmarks is usable during execution of the virtual, augmented, or mixed reality application to locate the HMD in the physical environment.
10. A method, comprising:
selecting a subset of landmarks usable by a Simultaneous Localization and Mapping (SLAM) system to locate a Head-Mounted Device (HMD) in a physical environment, wherein subset of landmarks includes a number of landmarks fewer than all detected landmarks;
controlling utilization of a hardware resource by changing the number of landmarks in the subset; and
at least one of:
(a) identifying an increase in the utilization of the hardware processor and reducing the number of landmarks in the subset of landmarks; or
(b) identifying a decrease in the utilization of the hardware processor and increasing the number of landmarks in the subset of landmarks.
11. The method of claim 10 , further comprising ranking the detected landmarks using a confidence level associated with each landmark.
12. The method of claim 10 , wherein the number of landmarks is selected based upon a calibration curve that associates a change in number of landmarks with a corresponding change in utilization of the IHS resource.
13. A hardware memory device having program instructions stored thereon that, upon execution by a hardware processor, cause the hardware processor to:
select a subset of landmarks usable to locate a Head-Mounted Device (HMD) in space, wherein the subset of landmarks comprises fewer than a total number of landmarks available;
control utilization of the hardware processor by dynamically changing a number of landmarks in the subset during execution of a virtual, augmented, or mixed reality applications; and
at least one of:
(a) identify an increase in the utilization of the hardware processor and reduce the number of landmarks in the subset of landmarks; or
(b) identify a decrease in the utilization of the hardware processor and increase the number of landmarks in the subset of landmarks.
14. The hardware memory device of claim 13 , wherein to select the subset of landmarks, the program instructions, upon execution, further cause the hardware processor to rank each of the landmarks detected by the HMD using a confidence level associated with each landmark.