Miller Robotic Interface II Manual de usuario descargar pdf (Pagina 33)

robots bumped obstacles in the environment an average of 2.6 times per run. Also, of the 29

total hits that occurred in the study, 12 or 41%, of the hits were on the rear of the robot. We

believe a lack of sensing caused many of the rear hits.

To address the issue of poor situation awareness in the back of the robot, we added a rear-

looking camera to our system. Since the rear-looking camera would only be consulted

occasionally and we did not wish to draw attention away from the main video feed, the rear

video feed is relegated to a smaller window and updated less frequently. The video image in this

panel is mirrored along the vertical center axis to provide a rear view mirror effect. This makes

the objects on the right side of the original stream appear on the left side of the video window.

This is done to align the objects properly, because where the camera is facing backwards, objects

in the frame appear on the wrong side if this mirror effect is not done.

In Automatic Direction Reversal (ADR), we can switch the video displays so that the rear view

is expanded in the larger window. The large display indicates whether the front or rear view is

active. Also, the drive commands automatically remap so that forward becomes reverse and

reverse becomes forward. The command remapping allows an operator to spontaneously reverse

the direction of the robot in place and greatly simplifies the navigation task.

The rear video screen was a new feature to these types of robot interfaces when we first

implemented it. As a result of this work, some newer interfaces in development have

incorporated them into their designs.

There is also a map panel on the interface, shown in figure 9. This panel provides a map of the

environment the robot is in, as well as the robot's current position and orientation within that

environment. As the robot moves throughout the space, it generates a map using the distance

information received by its sensors using a Simultaneous Localization and Mapping (SLAM)

algorithm. This type of mapping algorithm uses a statistical model to compare current distance

readings and odometry information with other readings it has already seen to try to match up

and build a representation environment. This algorithm also can determine the robot's current

location in the map. This is the most widely used and well accepted algorithm for real-time

dynamic mapping using robotic platforms.

1 2 ... 28 29 30 31 32 33 34 35 36 37 38 ... 79 80

Sin comentarios

Miller Robotic Interface II Manual de usuario Pagina 33