Abstract: Vehicles can be equipped to operate in both autonomous and occupant piloted mode. While operating in either mode, an array of sensors can be used to pilot the vehicle including stereo cameras and 3D sensors. Stereo camera and 3D sensors can also be employed to assist occupants while piloting vehicles. Deep convolutional neural networks can be employed to determine estimated depth maps from stereo images of scenes in real time for vehicles in autonomous and occupant piloted modes.

Abstract: Method and apparatus are disclosed for responding to HVAC-induced vehicle microphone buffeting. An example disclosed vehicle includes a microphone, a speaker, and a buffeting detector. The example microphone is electrically coupled to an input of a voice-activated system. The example speaker is located on a front driver side of the vehicle. The example buffeting detector, when a button is activated, determines a buffeting factor of a signal captured by the microphone. Additionally, the example buffeting detector, in response to the buffeting factor satisfying a threshold, activates a relay to electrically couple the speaker to the input of the voice-activated system.

Abstract: A system and methods are described for calibrating one sensor with respect to another. A method includes: determining a depth-motion vector using a first sensor; determining an optical-motion vector using a second sensor; and calibrating the first sensor with respect to the second sensor by minimizing a cost function that evaluates a distance between the depth-motion and optical-motion vectors.

Abstract: A high-level vehicle command is determined based on a location of the vehicle with respect to a route including a start location and a finish location. An image is acquired of the vehicle external environment. Steering, braking, and powertrain commands are determined based on inputting the high-level command and the image into a Deep Neural Network. The vehicle is operated by actuating vehicle components based on the steering, braking and powertrain commands.

Abstract: A system and methods are described for generating a super-resolution depth-map. A method includes: determining a plurality of unmeasured depth-map positions using measured depth-elements from a first sensor and spatial-elements from a second sensor; for each of the plurality, calculating estimated depth-elements using a gradient-based optimization; and generating a super-resolution depth-map that comprises the measured and estimated depth-elements.

Abstract: A system, comprising a processor, and a memory, the memory including instructions to be executed by the processor to acquire the images of the vehicle environment, determine a cognitive map, which includes a top-down view of the vehicle environment, based on the image, and operate the vehicle based on the cognitive map.

Abstract: A system, comprising a processor, and a memory, the memory including instructions to be executed by the processor to acquire the images of the vehicle environment, determine a cognitive map, which includes a top-down view of the vehicle environment, based on the image, and operate the vehicle based on the cognitive map.

Abstract: An automatic speech recognition system for a vehicle includes a controller configured to select an acoustic model from a library of acoustic models based on ambient noise in a cabin of the vehicle and operating parameters of the vehicle. The controller is further configured to apply the selected acoustic model to noisy speech to improve recognition of the speech.

Abstract: Techniques and examples pertaining to objection detection and trajectory prediction for autonomous vehicles are described. A processor receives an input stream of image frames and fuses a spatiotemporal input stream of the image frames and an appearance-based stream of the image frames using a deep neural network (DNN) to generate an augmented stream of the image frames. The processor performs object detection and trajectory prediction of one or more objects in the image frames based on the augmented stream.

Abstract: The present invention extends to methods, systems, and computer program products for refining synthetic data with a Generative Adversarial Network (GAN) using auxiliary inputs. Refined synthetic data can be rendered more realistically than the original synthetic data. Refined synthetic data also retains annotation metadata and labeling metadata used for training of machine learning models. GANs can be extended to use auxiliary channels as inputs to a refiner network to provide hints about increasing the realism of synthetic data. Refinement of synthetic data enhances the use of synthetic data for additional applications.

Abstract: A system includes a processor for performing one or more autonomous driving or assisted driving tasks based on a neural network. The neural network includes a base portion for performing feature extraction simultaneously for a plurality of tasks on a single set of input data. The neural network includes a plurality of subtask portions for performing the plurality of tasks based on feature extraction output from the base portion. Each of the plurality of subtask portions comprise nodes or layers of a neutral network trained on different sets of training data, and the base portion comprises nodes or layers of a neural network trained using each of the different sets of training data constrained by elastic weight consolidation to limit the base portion from forgetting a previously learned task.

Abstract: Methods, devices, and systems pertaining to in-vehicle tutorials are described. A method may involve receiving a request for an in-vehicle tutorial of an operational feature of a vehicle from a user and simulating expected driving behavior corresponding to the operational feature in the vehicle. The method may further include monitoring operational behavior of the user, comparing the operational behavior with the expected driving behavior, and providing a feedback to the user based on the comparison.

Abstract: A system includes a head and torso simulation (HATS) system configured to play back pre-recorded audio commands while simulating a driver head location as an output location. The system also includes a vehicle speaker system and a processor configured to engage a vehicle heating, ventilation and air-conditioning (HVAC) system. The processor is also configured to play back audio commands through the HATS system while playing back pre-recorded vehicle environment noises through the speaker system. The processor is further configured to determine if the audio command, recorded by a vehicle microphone, is recognizable in the presence of the environment noises and HVAC noises. Also, the processor is configured to repeat the engagement, playback of commands and noises, and determination, recording the results of the determination for each command in a set of commands.

Abstract: Method and apparatus are disclosed for responding to HVAC-induced vehicle microphone buffeting. An example disclosed vehicle includes a microphone, a speaker, and a buffeting detector. The example microphone is electrically coupled to an input of a voice-activated system. The example speaker is located on a front driver side of the vehicle. The example buffeting detector, when a button is activated, determines a buffeting factor of a signal captured by the microphone. Additionally, the example buffeting detector, in response to the buffeting factor satisfying a threshold, activates a relay to electrically couple the speaker to the input of the voice-activated system.

Abstract: Vehicles can be equipped to operate in both autonomous and occupant piloted mode. While operating in either mode, an array of sensors can be used to pilot the vehicle including stereo cameras and 3D sensors. Stereo camera and 3D sensors can also be employed to assist occupants while piloting vehicles. Deep convolutional neural networks can be employed to determine estimated depth maps from stereo images of scenes in real time for vehicles in autonomous and occupant piloted modes.

Abstract: Training tuples including text and a question and answer corresponding to the text are input to a machine learning algorithm, such as a deep neural network. A Q&A model is obtained that outputs questions and answers given an input text. The training tuples may be obtained from standardized test such that the text is a question prompt and the questions and answers are based on the prompt. Raw text is input to the Q&A model to obtain second training tuples including a question and an answer. An NLU model is trained according to the second training tuples. The NLU model may then be installed on a consumer device, which will then use the model to respond to conversational queries and provide an appropriate response.

Abstract: A method or system that receives a product definition that includes a feature family having data defining one or more product features. The product definition including one or more corresponding rules defining one or more relationships between one or more product features. The method or system receiving input selecting one or more feature families of interest. The method or system identifying the one or more rules that provide a relationship connecting the one or more feature families to the selected feature families of interest. The method or system converting the identified rules to one or more positive logic rule groups. The method or system generating one or more global representations of the product definition by interacting the one or more positive logic rule groups to produce a result that defines the relationship between the interacted positive logic rule groups and storing the results that are determined as being valid.

Abstract: A method or system that receives a product definition that includes a feature family having data defining one or more product features. The product definition including one or more corresponding rules defining one or more relationships between one or more product features. The method or system receiving input selecting one or more feature families of interest. The method or system identifying the one or more rules that provide a relationship connecting the one or more feature families to the selected feature families of interest. The method or system converting the identified rules to one or more positive logic rule groups. The method or system generating one or more global representations of the product definition by interacting the one or more positive logic rule groups to produce a result that defines the relationship between the interacted positive logic rule groups and storing the results that are determined as being valid.

Abstract: At least one spoken utterance and a stored vehicle acoustic impulse response can be provided to a computing device. The computing device is programmed to provide at least one speech file based at least in part on the spoken utterance and the vehicle acoustic impulse response.

Abstract: A processor of a vehicle speech recognition system recognizes speech via domain-specific language and acoustic models. The processor further, in response to the acoustic model having a confidence score for recognized speech falling within a predetermined range defined relative to a confidence score for the domain-specific language model, recognizes speech via the acoustic model only.