Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 49875 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Manzuri, Mohammad Taghi
- Abstract:
- One of the major problems encountered in artificial intelligence is environment interaction. A sensible way for around-interaction is to collect information from sensors and make proper reactions. Generally, in the real world, an intelligent agent needs to know its pose. There are several ways to know the pose of an agent. One of them is based on the fusion of the output of an inertial sensor with the information retrieved from a camera. This leads to enhance the estimation of the pose of an agent. In this research different solutions for this problem are compared. Studies are done with the goal of attitude detection for vehicles and mini-robots, moving on planar surface. For this end, we have implemented different scenarios, among them we combined the information from camera and internal sensor, by means of unscented kalman filter. We observed that the weakness of each sensor can be covered by the information from the other sensor. Here, the most important weakness of camera is its sensitivity to the light intensity and fast movement, and for inertial sensor is its sensitivity to additive errors over time. For example after simultaneous use of these sensors, the effect of camera sensitivity to environment light changes has almost disappeared and effect of inertial sensor additive fault in combination with camera information was reduced to about 10-15 deg/sec
- Keywords:
- Attitude Estimation ; Unscented Kalman Filter ; Inertial Sensor ; Position Estimation ; Vision Sensor
Digital Object List
-
محتواي کتاب
- view
Bookmark