No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Delivery of cargo using autonomous mobile robot
Abstract
The result of research on delivering small cargo using two-wheeled autonomous mobile robot is described in this paper. The experiment equipment, cargo and robot recognition principles and the main algorithm of control system are presented. The purpose of created control system is to control robot so that it would be able to deliver cargo from point A to point B autonomously. Robot and cargo are recognized using information, obtained from video camera and extracted by colored markers. They are interpreted as points and vectors in the projective plane. The control system is implemented on computer. In a program window user sets destination point, then control system calculates robot wheels velocities in real time. For problem solution - finding robot wheels speeds - if-then rules were used. Results show that robot with the implemented control system manages to take cargo to destination point.
ResearchGate has not been able to resolve any citations for this publication.
The result of design and investigation on a human gesture recognition system, which is based on stereo vision are presented in this paper. 3-D space coordinates are recorded from a pair of 2-D images obtained from the stereo pair of cameras. The systems' hardware description and computation method for 3-D human gesture are presented. System also uses the persons' face detection algorithm to compute face coordinate as a reference point for recorded hand gesture. Such approach gives easy adaptation and flexibility for gesture interpretation. In this study there were collected ten specific single hand motion gestures, repeated several times by five different people. The gesture recognition and interpretation is done by use of the trained neural classifier. The structure of classifier was estimated through try – error approach.
Techniques are proposed to support the video based development of systems for indoor exploration with mobile robots. The technique
of redundant programming is often used to improve the reliability of operating systems, but the use of this technique is not
common for CV (computer vision) applications. Also a new technique to create CAD (computer aided design) models from image
data is described. These techniques were used for the development of an RV (robot vision) program. The observed recognition
power exceeds the abilities of sophisticated but conventional programs clearly. This is documented with sample images, which
show a table that has been taken from different distances. The quality of the images is very bad due to the fact that a camera
was taken which has a very low resolution. Additionally the detection of the table was hampered, because the illumination
in the images varied considerably. Sometimes the table was placed very near by a window with strong exposure to sunlight.
Over-exposure of the table complicated the reconstruction because of this problem. Sometimes other objects irritated the detection.
The program handled all these difficulties impressionably although it used no calibration techniques. No other robot-vision
program is documented in the literature that gained the reported recognition rate.