Abstract: The present invention relates to a method and apparatus for long-range facial and ocular acquisition. One embodiment of a system for acquiring an image of a subject's facial feature(s) includes a steerable telescope configured to acquire the image of the facial feature(s), a first computational imaging element configured to minimize the effect of defocus in the image of the facial feature(s), and a second computational imaging element configured to minimize the effects of motion blur. In one embodiment, the detecting, the acquiring, the minimizing the effect of the motion, and the minimizing the effect of the defocus are performed automatically without a human input.

Abstract: A robotic manipulator has a body and a stereoscopic video system movably coupled to the body. The stereoscopic vision system produces a stereoscopic video of an environment of the robotic manipulator. The robotic manipulator also includes two independently remotely controlled arms coupled to opposite sides of the body. Each arm moves in proprioceptive alignment with the stereoscopic video produced by the stereoscopic video system in response to commands received from a remote control station based on movements performed by an operator at the remote control station.

Abstract: A robotic manipulator has a body and a stereoscopic video system movably coupled to the body. The stereoscopic vision system produces a stereoscopic video of an environment of the robotic manipulator. The robotic manipulator also includes two independently remotely controlled arms coupled to opposite sides of the body. Each arm moves in proprioceptive alignment with the stereoscopic video produced by the stereoscopic video system in response to commands received from a remote control station based on movements performed by an operator at the remote control station.

Abstract: The present invention relates to a method and apparatus for long-range facial and ocular acquisition. One embodiment of a system for acquiring an image of a subject's facial feature(s) includes a steerable telescope configured to acquire the image of the facial feature(s), a first computational imaging element configured to minimize the effect of defocus in the image of the facial feature(s), and a second computational imaging element configured to minimize the effects of motion blur. In one embodiment, the detecting, the acquiring, the minimizing the effect of the motion, and the minimizing the effect of the defocus are performed automatically without a human input.

Abstract: In one embodiment, the present invention is a method and apparatus for error correction in speech recognition applications. In one embodiment, a method for recognizing user speech includes receiving a first utterance from the user, receiving a subsequent utterance from the user, and combining acoustic evidence from the first utterance with acoustic evidence from the subsequent utterance in order to recognize the first utterance. It is assumed that, if the first utterance has been incorrectly recognized on a first attempt, the user will repeat the first utterance (or at least the incorrectly recognized portion of the first utterance) in the subsequent utterance.

Abstract: In one embodiment, the present invention is a method and apparatus for error correction in speech recognition applications. In one embodiment, a method for recognizing user speech includes receiving a first utterance from the user, receiving a subsequent utterance from the user, and combining acoustic evidence from the first utterance with acoustic evidence from the subsequent utterance in order to recognize the first utterance. It is assumed that, if the first utterance has been incorrectly recognized on a first attempt, the user will repeat the first utterance (or at least the incorrectly recognized portion of the first utterance) in the subsequent utterance.