ended problems where, for example, there may not be a
single right answer. The developers want the architecture to
STEER WINNING ROBOTS
Perform proportional speed, direction, and steering with
only two Radio/Control channels for vehicles using two
separate brush-type electric motors mounted right and left
with our mixing RDFR dual speed control. Used in many
successful competitive robots. Single joystick operation: up
goes straight ahead, down is reverse. Pure right or left twirls
vehicle as motors turn opposite directions. In between stick
positions completely proportional. Plugs in like a servo to
your Futaba, JR, Hitec, or similar radio. Compatible with gyro
steering stabilization. Various volt and amp sizes available.
The RDFR47E 55V 75A per motor unit pictured above.
learn and use a variety of knowledge bases and problem solving skills. They want it to enable robots to interact intelligently with the world around them. They want to enable robots to
learn more about their own activities, tasks, and behaviors.
SOAR bases perception and action on all existing
knowledge including the latest interpretation of inputs from
the outside world. SOAR follows a robot AI model that
appears to closely resemble how human beings process
information for the purposes of perception and response.
Working forward from version 8, developers are seeking to
store multiple representations and interpretations of acquired
knowledge, as well as to acquire that knowledge in different
ways. SOAR brings all this knowledge to bear on every
perception, decision, and reaction at the software’s runtime.
Developers are turning SOAR into a suite of cognitive capabilities matching those of the human brain. SOAR can retrieve
knowledge and memories of previous perceptions and reactions
and model those to determine how to react in the current state.
In order to make sure the virtual world as perceived and
modeled by the robot and the real world match up, the
robot’s rules test for differences between the two. If there is
a new object, if an object has moved or changed, there are
rules to deal with these differences.
To do this, SOAR and the vision system work to collect
the more vague bottom up information about segments of
visual data, stereo information (there are two cameras), and
The SOAR system applies rules to the robot to force it to
examine the object from the top down by turning its stereovision
to focus on the object more exactly. System rules process the top
down vision data by examining portions
of the object via the object recognition
software. The results of those examinations are stored in SOAR. SV
Pace Robotics Lab
Pace robot clips including
the Pioneer 2
Pace robot clip
Pace robot clip
Large Pace robot clip
(save file before viewing)
12 SERVO 03.2008