Abstract: Vehicle perception techniques include applying a 3D DNN to a set of inputs to generate 3D detection results including a set of 3D objects, transforming the set of 3D objects onto a set of images as a first set of 2D bounding boxes, applying a 2D DNN to the set of images to generate 2D detection results including a second set of 2D bounding boxes, calculating mean average precision (mAP) values based on a comparison between the first and second sets of 2D bounding boxes, identifying a set or corner cases based on the calculated mAP values, and re-training or updating the 3D DNN using the identified set of corner cases, wherein a performance of the 3D DNN is thereby increased without the use of expensive additional manually and/or automatically annotated training datasets.

Abstract: Vehicle perception techniques include obtaining a training dataset represented by N training histograms, in an image feature space, corresponding to N training images, K-means clustering the N training histograms to determine K clusters with respective K respective cluster centers, wherein K and N are integers greater than or equal to one and K is less than or equal to N, comparing the N training histograms to their respective K cluster centers to determine maximum in-class distances for each of K clusters, applying a deep neural network (DNN) to input images of the set of inputs to output detected/classified objects with respective confidence scores, obtaining adjusted confidence scores by adjusting the confidence scores output by the DNN based on distance ratios of (i) minimal distances of input histograms representing the input images to the K cluster centers and (ii) the respective maximum in-class.

Abstract: Vehicle perception techniques include applying a 3D DNN to a set of inputs to generate 3D detection results including a set of 3D objects, transforming the set of 3D objects onto a set of images as a first set of 2D bounding boxes, applying a 2D DNN to the set of images to generate 2D detection results including a second set of 2D bounding boxes, calculating mean average precision (mAP) values based on a comparison between the first and second sets of 2D bounding boxes, identifying a set or corner cases based on the calculated mAP values, and re-training or updating the 3D DNN using the identified set of corner cases, wherein a performance of the 3D DNN is thereby increased without the use of expensive additional manually and/or automatically annotated training datasets.

Abstract: Vehicle perception techniques include obtaining a training dataset represented by N training histograms, in an image feature space, corresponding to N training images, K-means clustering the N training histograms to determine K clusters with respective K respective cluster centers, wherein K and N are integers greater than or equal to one and K is less than or equal to N, comparing the N training histograms to their respective K cluster centers to determine maximum in-class distances for each of K clusters, applying a deep neural network (DNN) to input images of the set of inputs to output detected/classified objects with respective confidence scores, obtaining adjusted confidence scores by adjusting the confidence scores output by the DNN based on distance ratios of (i) minimal distances of input histograms representing the input images to the K cluster centers and (ii) the respective maximum in-class.

Abstract: An engine control system comprises a coolant temperature weighting module that generates a weighting signal based on coolant temperature. A composite temperature generating module generates a composite temperature based on the coolant temperature, an oil temperature and the weighting signal. A delta friction torque module calculates delta friction torque of an engine based on the composite temperature. An engine operating parameter module that adjusts an engine operating parameter based on the delta friction torque.

Abstract: A method for calibrating a physical test cell includes the steps of: determining a set of inputs to be provided to the physical test cell based in part on a set of historical test data; providing the inputs to the physical test cell and receiving a set of outputs associated therewith, wherein the providing includes implementing a sequential space filling sampling procedure to substantially cover a region defined by the set of historical values; creating a virtual test cell comprising one or more response surfaces based on the set of outputs; and interrogating the virtual test cell to determine a calibration relationship between at least one of the inputs and at least one of the outputs. Smooth Kriging may be used to determine the virtual test cell.

Abstract: An engine control system comprises a coolant temperature weighting module that generates a weighting signal based on coolant temperature. A composite temperature generating module generates a composite temperature based on the coolant temperature, an oil temperature and the weighting signal. A delta friction torque module calculates delta friction torque of an engine based on the composite temperature. An engine operating parameter module that adjusts an engine operating parameter based on the delta friction torque.