Harman International Industries, Inc.

Nikhil Patel

Prithvi Kambhampati

Greg Bohl

Gregory Bohl

Mengling Hettinger

Behrouz Saghafi Khadem

Embodiments include a computer-implemented method for interacting with a user. The method comprises utilizing a processor associated with a virtual personal assistance system. The processor is configured to perform the steps of obtaining first sensor data from a first sensor included in a plurality of sensors. The first sensor data comprises audio speech input. The steps further comprise analyzing the audio speech input using a first deep learning model to generate an intended meaning, selecting second sensor data to obtain based on the intended meaning, obtaining the second sensor data from a second sensor included in the plurality of sensors, analyzing the second sensor data and the intended meaning to generate a prediction value, applying a second deep learning model to the prediction value to generate a text segment, and converting the text segment into a natural language audio output; and outputting the natural language audio output to the user.

Two-way in-vehicle virtual personal assistant

Embodiments of the present disclosure set forth techniques for compensating for a roll effect for an optical sensor. The techniques include receiving sensor data from at least one sensor associated with the vehicle, detecting an amount of a roll of the vehicle based on the sensor data, generating a command based on the detected amount of roll, and controlling an orientation of the optical sensor based on the command.

Roll effect correction for optical sensor

One or more embodiments include a virtual personal assistant module executing on a virtual personal assistant system. The virtual personal assistant module obtains first sensor data from a first sensor included in a plurality of sensors. The virtual personal assistant module analyzes the first sensor data to generate a first result. The virtual personal assistant module obtains second sensor data from a second sensor included in the plurality of sensors. The virtual personal assistant module analyzes the second sensor data and the first result to generate a second result. The virtual personal assistant module outputs a natural language audio output to the user based on the second result.

Systems and methods for predictively detecting vehicle failure based on diagnostic trouble codes are provided. In one example, a method is provided, comprising determining a probability of failure of a vehicle based on one or more diagnostic trouble codes (DTCs); and indicating to an operator of the vehicle that failure is likely in response to the probability exceeding a threshold.

Systems and methods for in-vehicle predictive failure detection

Systems and methods that compare a validation image to one or more confirmation data sets, wherein each of the one or more confirmation sets is formed based on matching a document image and a confirmation image. In at least one example, one or more vehicle operability actions may be performed responsive to the validation image matching a confirmation data set of the one or more confirmation data sets. A refusal action may further be performed responsive to the validation image not matching the confirmation data, for example.

Growing community of inventors

Plano, TX, United States of America

Nikhil Patel