State-of-the-Art Mobile Intelligence: Enabling Robots to Move Like Humans by Estimating Mobility with Artificial Intelligence

• Published in: Applied sciences 2018-03, Vol.8 (3), p.379
• Main Authors: Jin, Xue-Bo, Su, Ting-Li, Kong, Jian-Lei, Bai, Yu-Ting, Miao, Bei-Bei, Dou, Chao
• Format: Article
• Language: English
• Subjects: Acceleration; Accuracy; adaptive model; Artificial intelligence; Computer applications; Deep learning; estimation; Global positioning systems; GPS; Houses; Indoor environments; interacting multiple model; International conferences; Kalman filter; Localization; Mechanical systems; Miniaturization; mobile intelligence; Navigation; Navigation systems; Neural networks; Optical flow (image analysis); Position measurement; Researchers; Robots; Sensors; tracking; tracking models; Unmanned aerial vehicles; World Wide Web
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app8030379

According to our position relative to that of the house, we also can judge our speed and that of the car, predict the location of the car, and determine whether we need to avoid the car. The disadvantage of the optical flow method is the large computational overhead. [...]it is difficult to find the correct optical flow mode when the robot is moving at a high speed. IMUs have become smaller, lower cost, and consume less power thanks to miniaturization technologies, such as micro-electro-mechanical systems or nano-electro-mechanical systems. Because the measurements of the IMUs have unknown drift, it is difficult to use the acceleration and orientation measurements, to obtain the current position of a pedestrian in an indoor navigation system [5]. [...]in the face of increasingly complex environments and movements, the most important difficulty lies in the fact that a sensor cannot obtain the accurate information in response to the complex environment of the outside world. [...]a method of modeling the measurement sensor should be developed.