|
A research project applying artificial intelligence techniques to
the development of integrated robot systems is described. The experimental
facility consists of an SDS-940 computer and associated programs
controlling a wheeled vehicle that carries a TV camera and other sensors.
The primary emphasis is on the development of a system of programs for
processing sensory data from the vehicle, for storing relevant information
about the environment, and for planning the sequence of motor
actions necessary to accomplish tasks in the environment. A typical task
performed by our present system requires the robot vehicle to rearrange
(by pushing) simple objects in its environment.
A novel feature of our approach is the use of a formal theorem-proving
system to plan the execution of high-level functions as a
sequence of other perhaps lower-level functions. The execution of
these in turn requires additional planning at lower levels. The main
theme of the research is the integration of the necessary planning
systems, models of the world and sensory processing systems into an
efficient whole capable of performing a wide range of tasks in a real
environment.
| 
