Abstract: A method and system to enable a computer to estimate calibration parameters autonomously so that accurate stereopsis can be performed. The present invention automatically calibrates two or more cameras with unknown parameters with respect to a robot or robotic appendage (e.g., articulated robot arm) with a light source that can be turned on and off at one end. A pair of cameras (e.g., digital cameras) are positioned and aimed so as to give stereoptic coverage of the robot's workspace. The procedure determines the positions and orientations of the pair of cameras with respect to a robot (i.e., exterior orientations) and the focal lengths, optical centers, and distortion coefficients of each camera (i.e., intrinsic parameters) automatically from a set of known positions of the robot arm, and a set of images from the right and left cameras of the robot arm in each position as the light is turned on and off.

Abstract: A method and system to enable a computer to estimate calibration parameters autonomously so that accurate stereopsis can be performed. The present invention automatically calibrates two or more cameras with unknown parameters with respect to a robot or robotic appendage (e.g., articulated robot arm) with a light source that can be turned on and off at one end. A pair of cameras (e.g., digital cameras) are positioned and aimed so as to give stereoptic coverage of the robot's workspace. The procedure determines the positions and orientations of the pair of cameras with respect to a robot (i.e., exterior orientations) and the focal lengths, optical centers, and distortion coefficients of each camera (i.e., intrinsic parameters) automatically from a set of known positions of the robot arm, and a set of images from the right and left cameras of the robot arm in each position as the light is turned on and off.

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.

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.

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.

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.

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.