Apparatus for multiprocessor-based control of a multiagent robot
OwnerRichard Alan Peters, IIinventor
Life of this patent
Estimating the term…
Abstract
An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a DBAM that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.
Claims4
A system for processing signals received from a plurality of sensors and for producing signals to at least one actuator, said system comprising:
- a plurality of processors for processing sensor signals received from the sensors and producing output signals;
- a sensory database comprising a plurality of records, each record comprising an output signal received from at least one of the plurality of processors;
- a behavior database comprising a plurality of records, each record representing a behavior to be performed by an actuator;
- a first agent for identifying a most active portion of the sensory database;
- and
- a second agent for selecting a behavior from the behavior database and communicating it to an actuator, the selection based, in part, on identification of the most active portion of the sensory database.
Dependencies are inferred from the claim text.