Abstract: Methods and systems are provided to detect an instance of a line in a two-dimensional image captured by a vehicle and to determine whether the instance of the line is a lane boundary for a lane that will be used by the vehicle to traverse a route. An instance of a line in a two-dimensional image captured by a vehicle is detected using processing circuitry. The processing circuitry is used to determine that the instance of the line is a lane boundary for a lane associated with the vehicle. A curve fit for the lane boundary based on the instance of the line is determined using the processing circuitry. The processing circuitry is also used to determine a sinuosity of the lane based on the curve fit. Execution of a vehicle action is facilitated using the processing circuitry based on the determined sinuosity.

Abstract: A method for determining event data including: sampling a first data stream within a first time window at a first sensor of an onboard vehicle system coupled to a vehicle, extracting interior activity data from the first data stream; determining an interior event based on the interior activity data; sampling a second data stream within a second time window at a second sensor of the onboard vehicle system; extracting exterior activity data from the second image stream; determining an exterior event based on the exterior activity data; correlating the exterior event and the interior event to generate combined event data; automatically classifying the combined event data to generate an event label; and automatically labeling the first time window of the first data stream and the second time window of the second data stream with the combined event label to generate labeled event data.

Abstract: Methods and systems are provided to detect an instance of a line in a two-dimensional image captured by a vehicle and to determine whether the instance of the line is a lane boundary for a lane that will be used by the vehicle to traverse a route. An instance of a line in a two-dimensional image captured by a vehicle is detected using processing circuitry. The processing circuitry is used to determine that the instance of the line is a lane boundary for a lane associated with the vehicle. A curve fit for the lane boundary based on the instance of the line is determined using the processing circuitry. The processing circuitry is also used to determine a sinuosity of the lane based on the curve fit. Execution of a vehicle action is facilitated using the processing circuitry based on the determined sinuosity.

Abstract: A system and method is disclosed that may employ a set of ensemble methods that comprise a plurality of machine learning algorithms or statistical algorithms for hazard detection. The system and method may combine images, stereo and context information using a plurality of deep learning algorithms to accurately detection hazards. The system and method may incorporate a depth channel to the red, green, and blue (RGB) channels of an image to create a four-channel RGBD image. The system and method may also overlay an RGB image with a color-map of the depth channel. The system and method may further concatenate regions of interest (ROI) to the RGB channels of an image. Lastly, the system and method may incorporate an auxiliary semantic segmentation decoder for a multi-task learning event on a drivable space.

Abstract: A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an “activity vector.” Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.

Abstract: A method and system is disclosed for creating a machine learning model that is reconfigurable. A fixed parameter model is created to include fixed feature values obtained during a training process for the machine learning model. The fixed parameter model may include a fixed base classifier used by the machine learning model to classify objects detected by an ultra-sonic system within a vicinity of a vehicle. A configurable parameter model may be created to include feature values that are different from the fixed feature values, the configurable parameter model including a modified base classifier. A vehicle controller may receive and update the fixed parameter model with the configurable parameter model. The machine learning model may be updated to use the configurable parameter model to classify the objects detected by the ultra-sonic system.

Abstract: A method and system is disclosed for tuning a machine learning classifier. An object class requirement may be provided and include rank thresholds. The object class requirements may also include a range goal that defines a minimum distance from the object the machine learning algorithm should not provide false positive results. A base classifier may be trained using a weighted loss function that includes one or more weight values that are computed using the one or more object class requirements. An output of the weighted loss function may be evaluated using an objective function which may be established using the one or more object class requirements. The one or more weights may also be re-tuned using the weighted loss function if the output of the weighted loss function does not converge within a predetermined loss threshold.

Abstract: A system and method is disclosed for classifying one or more objects within a vicinity of a vehicle. Ultra-sonic data may be received from a plurality of ultra-sonic sensors and may comprise echo signals indicating one or more objects that are proximally located within a vicinity of a vehicle. One or more features may be calculated from the ultra-sonic data using one or more signal processing algorithms unique to each of the plurality of ultra-sonic sensors. The one more features may be combined using a second-level signal processing algorithm to determine geometric relations for the one or more objects. The one or more features may then be statistically aggregated at an object level. The one or more objects may then be classified using a machine learning algorithm that compares an input of each of the one or more features to a trained classifier.

Abstract: A method for determining distraction of a driver of a vehicle, including sampling sensor measurements at an onboard system of the vehicle; generating an output indicative of a distracted state; determining that the driver of the vehicle is characterized by the distracted state, based on the output; generating, at a second distraction detection module of a remote computing system, a second output indicative that the driver is characterized by the distracted state, based on the sensor measurements; computing a distraction score, at a scoring module of the remote computing system, in response to generating the second output and based on the sensor measurements and the distracted state.

Abstract: Systems and methods for driving. A driving data set for each of plurality of human-driven vehicles is determined. For each driving data set, exterior scene features of an exterior scene of the respective vehicle are extracted from the exterior image data. A driving response model is trained based on the exterior scene features and the vehicle control inputs from the selected driving data sets.

Abstract: A method for determining event data including: sampling a first data stream within a first time window at a first sensor of an onboard vehicle system coupled to a vehicle, extracting interior activity data from the first data stream; determining an interior event based on the interior activity data; sampling a second data stream within a second time window at a second sensor of the onboard vehicle system; extracting exterior activity data from the second image stream; determining an exterior event based on the exterior activity data; correlating the exterior event and the interior event to generate combined event data; automatically classifying the combined event data to generate an event label; and automatically labeling the first time window of the first data stream and the second time window of the second data stream with the combined event label to generate labeled event data.

Abstract: A method for determining event data including: sampling a first data stream within a first time window at a first sensor of an onboard vehicle system coupled to a vehicle, extracting interior activity data from the first data stream; determining an interior event based on the interior activity data; sampling a second data stream within a second time window at a second sensor of the onboard vehicle system; extracting exterior activity data from the second image stream; determining an exterior event based on the exterior activity data; correlating the exterior event and the interior event to generate combined event data; automatically classifying the combined event data to generate an event label; and automatically labeling the first time window of the first data stream and the second time window of the second data stream with the combined event label to generate labeled event data.

Abstract: A system and method is disclosed that may employ a set of ensemble methods that comprise a plurality of machine learning algorithms or statistical algorithms for hazard detection. The system and method may combine images, stereo and context information using a plurality of deep learning algorithms to accurately detection hazards. The system and method may incorporate a depth channel to the red, green, and blue (RGB) channels of an image to create a four-channel RGBD image. The system and method may also overlay an RGB image with a color-map of the depth channel. The system and method may further concatenate regions of interest (ROI) to the RGB channels of an image. Lastly, the system and method may incorporate an auxiliary semantic segmentation decoder for a multi-task learning event on a drivable space.

Abstract: A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an “activity vector.” Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.

Abstract: A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an “activity vector.” Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.

Abstract: A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an “activity vector.” Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.

Abstract: A system and method is provided for recommending food items based on a set of instructions. A first set of instructions are executed to receive a first set of input parameters associated with plurality of attributes of the entity. Further, a second set of input parameters are received from a second entity and are associated with the first set of input parameters of the entity. The received first set of input parameters and the received second set of input parameters are analyzed to determine at least one of a health label for the entity. Then, a health score is assigned for at least one of the health label for the entity. The health score is assigned based on a food item to be recommended. Upon, the assigned health score lying within a predefined threshold, the food item is recommended to the entity.

Abstract: A method for determining distraction of a driver of a vehicle, including sampling sensor measurements at an onboard system of the vehicle; generating an output indicative of a distracted state; determining that the driver of the vehicle is characterized by the distracted state, based on the output; generating, at a second distraction detection module of a remote computing system, a second output indicative that the driver is characterized by the distracted state, based on the sensor measurements; computing a distraction score, at a scoring module of the remote computing system, in response to generating the second output and based on the sensor measurements and the distracted state.

Abstract: A method for near-collision detection, including determining a risk map for a vehicle and automatically detecting a near-collision event with an object based on vehicle behavior relative to the risk map.

Abstract: A method for determining distraction of a driver of a vehicle, including sampling sensor measurements at an onboard system of the vehicle; generating an output indicative of a distracted state; determining that the driver of the vehicle is characterized by the distracted state, based on the output; generating, at a second distraction detection module of a remote computing system, a second output indicative that the driver is characterized by the distracted state, based on the sensor measurements; computing a distraction score, at a scoring module of the remote computing system, in response to generating the second output and based on the sensor measurements and the distracted state.