|
|
Determination of variance in measurement of relative angle between infrared beacon and scanner
Krejsa, Jiří ; Růžička, M. ; Vojta, J.
Mobile robot localization is one of essential components for successful robot navigation. Localization techniques based on active landmarks commonly utilize probabilistic state estimation methods, e.g. Extended Kalman filter (EKF). In order to function properly, determination of process and measurement noise variances is essential in EKF. This paper is focused on determination of variance in measurement of relative angle between the active landmark, represented by infrared beacon and device positioned on the robot, beacon scanner. Variance values are determined in a number of environment conditions. The results indicate that for the beacon type used the variance essentially holds with the percentage of unsuccessful readings being the only variable effected by changing environment. This observation justifies the usage of measured variances in EKF based localization system.
|
|
|
Concurrent mapping and localization based on potential fields
Věchet, Stanislav ; Krejsa, Jiří
Presented paper deals with Concurrent Mapping and Localization as a method to build the local map for the autonomous mobile robot. Building accurate local map is necessary for the successful navigation through the crowded environment densely populated with dynamic obstacles. The occupancy grid mapping algorithm was used due to the high uncertainty in the measurements of dynamic obstacles. As the occupancy grid algorithm is of probabilistic nature the implementation is straightforward and is also capable to generate the results in real-time.
|
|
|
Mobile robot motion planner via neural network
Krejsa, Jiří ; Věchet, Stanislav
Motion planning is essential for mobile robot successful navigation. There are many algorithms for motion planning under various constraints. However, in some cases the human can still do a better job, therefore it would be advantageous to create a planner based on data gathered from the robot simulation when humans do the planning. The paper presents the method of using the neural network to transfer the previously gained knowledge into the machine learning based planner. In particular the neural network task is to mimic the planner based on finite state machine. The tests proved that neural network can successfully learn to navigate in constrained environment.
|
|
|
Experimental Determination of Human Arm Force/Elbow Joint Angle Relation
Krejsa, Jiří ; Zezula, M. ; Věchet, Stanislav
The achievable force at the end of human forearm depends on the forearm position. The actual value of this force is one of the most important variables affecting the design of the motorized splint, but reliable data are hard to find. Sophisticated measuring device was constructed to determine this force. The force is measured during the movement of the forearm, as such method yields better results than static measurement. The trajectory of movement is enforced by the measuring device, so the influence of the subject on the trajectory is eliminated.
|
|
|
Rychlá metoda srovnávání skenů pro lokalizaci mobilního robotu
Krejsa, Jiří ; Věchet, Stanislav
Příspěvek je zaměřen na rychlou metodu která používá postupné skeny prostředí mobilního robota proximitními senzory k určení polohy a orientace robotu a k tvorbě lokální mapy. Prostředí je předpokládáno neznámé. Metoda založená na srovnávání potenciálových polí skenů které poskytuje míru shodnosti skenů je kombinována s gradientní metodou k získání odpovídají shody dvou skenů v rozumném čase. Příspěvek obsahuje testy na robustnost metody vůči šumu v senzorech.
|
|
| |
|
| |
|
| |
|
| |
|
| |
host ::
RSS.