University of Pennsylvania

Other

George J Pappas

Konstantinos Daniilidis

Hamed Hassani

Nikolay Asenov Atanasov

Sean Laurence Bowman

Alexander Robey

Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.

Model-based robust deep learning

A method for simultaneous location and mapping (SLAM) includes receiving, by at least one processor, a set of sensor measurements from a movement sensor of a mobile robot and a set of images captured by a camera on the mobile robot as the mobile robot traverses an environment. The method includes, for each image of at least a subset of the set of images, extracting, by the at least one processor, a plurality of detected objects from the image. The method includes estimating, by the at least one processor, a trajectory of the mobile robot and a respective semantic label and position of each detected object within the environment using the sensor measurements and an expectation maximization (EM) algorithm.

Probabilistic data association for simultaneous localization and mapping

Light is examined utilizing a wide slit and a dispersion means such as a prism to produce two pairs of diverging beams separated by an intermediate converging beam of white light. The light emerging from the dispersion means impinges upon a narrow slit situated between the dispersion means and a point at which the intermediate beam of white light converges. In a monochrometer, the first pair of diverging beams comprise red and yellow rays and emanate from one side of the dispersion means and the second pair of diverging beams comprises blue and violet rays and emanate from the other side of the dispersion means. A narrow slit located between the dispersion means and a point at which the intermediate white beam converges passes rays of a single color, either red, yellow, blue or violet, to a second dispersion means and light emerging from the second dispersion means impinges upon a means for measuring the dispersion of rays passing through the narrow slit with respect to a reference point. In the spectrometer, a narrow slit having a sufficient width to pass red and yellow rays while blocking blue and violet rays and vice versa is located between a dispersion means and a measuring means. The measured displacement of the rays provides a signature for the source of light illuminating the wide slit.

Growing community of inventors

Philadelphia, PA, United States of America

George J Pappas