Currently, there are no adequate solutions to the problem of tracking the 3D-pose of small, resource-constrained systems in unknown environments. Specifically, estimating the motion of miniature devices, similar in size to a mobile phone, is difficult. In contrast to medium and large-scale systems, (e.g. mobile robots, UAVs, autonomous cars), small devices have limited computational capabilities and battery life, factors which make the pose-estimation problem challenging. In the absence of GPS, the types of sensors that can be used for pose estimation in small-scale systems are quite restricted.
Researchers at the University of California, Riverside have developed a hybrid estimation method using visual and inertial sensors for real-time pose tracking on devices with limited processing power using at least one processor, a memory, a storage and communications through a protocol and one or more than one software module for a hybrid estimator, real-time algorithm selection to process different measurements, statistical learning for these characteristics to compute the expected device computing cost of any strategy for allocating measurements to algorithms, and algorithm selection based on the statistical learning module.
|United States Of America||Issued Patent||9,798,929||10/24/2017||2013-732|