Abstract: A LIDAR-based method of determining an absolute speed of an object at a relatively longer distance from an ego vehicle, including: estimating a self speed of the ego vehicle using a first frame t?1 and a second frame t obtained from a LIDAR sensor by estimating an intervening rotation ? about a z axis and translation in orthogonal x and y directions using a deep learning algorithm over a relatively closer distance range; dividing each of the first frame t?1 and the second frame t into multiple adjacent input ranges and estimating a relative speed of the object at the relatively longer distance by subsequently processing each frame using a network, with each input range processed using a corresponding convolutional neural network; and combining the estimation of the estimating the self speed with the estimation of the estimating the relative speed to obtain an estimation of the absolute speed.

Abstract: Vehicle alert and control systems and methods taking into account a detected road friction at a following vehicle and a predicted road friction by the following vehicle. The detected road friction between the following vehicle tires and the road surface may be assessed using a variety of methodologies and is used to compute a critical safety distance between the following vehicle and the preceding vehicle and a critical safety speed of the following vehicle. The predicted road friction ahead of the following vehicle may also be assessed using a variety of methodologies (lidar, camera, and cloud-based examples are provided) and is used to compute a warning safety distance between the following vehicle and the preceding vehicle and a warning safety speed of the following vehicle. These functionalities may be applied to vehicle/stationary object warning and response scenarios as well.

Abstract: A vehicle control method and system, including: receiving road friction information indicating road friction estimates for a plurality of regions surrounding the vehicle; detecting and determining a predicted trajectory for an object within the plurality of regions surrounding the vehicle; wherein the predicted trajectory for the object is determined based in part on the road friction estimates for the plurality of regions surrounding the vehicle; and modifying operation of the vehicle based on the predicted trajectory for the object. The predicted trajectory for the object is determined based in part on a risk map for the plurality of regions surrounding the vehicle that is generated from a road friction map for the plurality of regions surrounding the vehicle.

Abstract: A system and method for utilizing aggregated weather data (AWD) for deriving road surface condition (RSC) estimates. This system and method supplements road friction estimates (RFEs) made at the vehicle level with AWD in the cloud to form the RSC estimates, which are then transmitted to the vehicles such that more accurate RFEs can be made locally, and so on. Conventional RFE physics-based models are replaced with enhanced RFE trained machine learning (ML) models accordingly. Global RSC estimates are derived for each geographical region using weather and location constraints. Thus, improved autonomous driving and driver assist functions may be implemented, better driver warnings may be provided, and safer road trips may be planned in advance based on a thorough analysis of the drivable conditions.

Abstract: A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.

Abstract: The present disclosure provides systems, methods, and metrics that filter out online visitor behavioral data that represents a potential lead with a high likelihood to convert to a vehicle sale from online visitor behavioral data that does not represent a potential lead with a low likelihood to convert to a vehicle sale, based on a mapping of sales back to observed website and vehicle configurator data. This enables more effective lead generation and the more efficient targeting of online incentive offers and sales “nudges,” for example. Further, the present disclosure enables web analytics data to be combined with sales data for sales forecasting in general.

Abstract: A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.

Abstract: Vehicle alert and control systems and methods taking into account a detected road friction at a following vehicle and a predicted road friction by the following vehicle. The detected road friction between the following vehicle tires and the road surface may be assessed using a variety of methodologies and is used to compute a critical safety distance between the following vehicle and the preceding vehicle and a critical safety speed of the following vehicle. The predicted road friction ahead of the following vehicle may also be assessed using a variety of methodologies (lidar, camera, and cloud-based examples are provided) and is used to compute a warning safety distance between the following vehicle and the preceding vehicle and a warning safety speed of the following vehicle. These functionalities may be applied to vehicle/stationary object warning and response scenarios as well.

Abstract: A framework in which annotated images can be analyzed in small batches to learn and distinguish between higher-quality annotations and lower-quality annotations, especially in the case of manual annotations for which quality assurance is desired. This framework is extremely generalizable and can be used for indoor images, outdoor images, medical images, etc., without limitation. An echo state network (ESN) is provided as a special case of semantic segmentation model that can be trained using as few as tens of annotated images to predict semantic regions and provide metrics that can be used to distinguish between higher-quality annotations and lower-quality annotations.

Abstract: Vehicle alert and control systems and methods taking into account a detected road friction at a following vehicle and a predicted road friction by the following vehicle. The detected road friction between the following vehicle tires and the road surface may be assessed using a variety of methodologies and is used to compute a critical safety distance between the following vehicle and the preceding vehicle and a critical safety speed of the following vehicle. The predicted road friction ahead of the following vehicle may also be assessed using a variety of methodologies (lidar, camera, and cloud-based examples are provided) and is used to compute a warning safety distance between the following vehicle and the preceding vehicle and a warning safety speed of the following vehicle. These functionalities may be applied to vehicle/stationary object warning and response scenarios as well.

Abstract: A LIDAR-based method of determining an absolute speed of an object at a relatively longer distance from an ego vehicle, including: estimating a self speed of the ego vehicle using a first frame t-1 and a second frame t obtained from a LIDAR sensor by estimating an intervening rotation ? about a z axis and translation in orthogonal x and y directions using a deep learning algorithm over a relatively closer distance range; dividing each of the first frame t-1 and the second frame t into multiple adjacent input ranges and estimating a relative speed of the object at the relatively longer distance by subsequently processing each frame using a network, with each input range processed using a corresponding convolutional neural network; and combining the estimation of the estimating the self speed with the estimation of the estimating the relative speed to obtain an estimation of the absolute speed.

Abstract: A system and method for estimating road conditions ahead of a vehicle, including: a LIDAR sensor operable for generating a LIDAR point cloud; a processor executing a road condition estimation algorithm stored in a memory, the road condition estimation algorithm performing the steps including: detecting a ground plane or drivable surface in the LIDAR point cloud; superimposing an M×N matrix on at least a portion of the LIDAR point cloud; for each patch of the LIDAR point cloud defined by the M×N matrix, statistically evaluating a relative position, a feature elevation, and a scaled reflectance index; and, from the statistically evaluated relative position, feature elevation, and scaled reflectance index, determining a slipperiness probability for each patch of the LIDAR point cloud; and a vehicle control system operable for, based on the determined slipperiness probability for each patch of the LIDAR point cloud, affecting an operation of the vehicle.

Abstract: A LIDAR-based method of determining an absolute speed of an object at a relatively longer distance from an ego vehicle, including: estimating a self speed of the ego vehicle using a first frame t-1 and a second frame t obtained from a LIDAR sensor by estimating an intervening rotation ? about a z axis and translation in orthogonal x and y directions using a deep learning algorithm over a relatively closer distance range; dividing each of the first frame t-1 and the second frame t into multiple adjacent input ranges and estimating a relative speed of the object at the relatively longer distance by subsequently processing each frame using a network, with each input range processed using a corresponding convolutional neural network; and combining the estimation of the estimating the self speed with the estimation of the estimating the relative speed to obtain an estimation of the absolute speed.

Abstract: A framework in which annotated images can be analyzed in small batches to learn and distinguish between higher-quality annotations and lower-quality annotations, especially in the case of manual annotations for which quality assurance is desired. This framework is extremely generalizable and can be used for indoor images, outdoor images, medical images, etc., without limitation. An echo state network (ESN) is provided as a special case of semantic segmentation model that can be trained using as few as tens of annotated images to predict semantic regions and provide metrics that can be used to distinguish between higher-quality annotations and lower-quality annotations.

Abstract: A framework in which annotated images can be analyzed in small batches to learn and distinguish between higher-quality annotations and lower-quality annotations, especially in the case of manual annotations for which quality assurance is desired. This framework is extremely generalizable and can be used for indoor images, outdoor images, medical images, etc., without limitation. An echo state network (ESN) is provided as a special case of semantic segmentation model that can be trained using as few as tens of annotated images to predict semantic regions and provide metrics that can be used to distinguish between higher-quality annotations and lower-quality annotations.

Abstract: The present disclosure provides systems, methods, and metrics that filter out online visitor behavioral data that represents a potential lead with a high likelihood to convert to a vehicle sale from online visitor behavioral data that does not represent a potential lead with a low likelihood to convert to a vehicle sale, based on a mapping of sales back to observed website and vehicle configurator data. This enables more effective lead generation and the more efficient targeting of online incentive offers and sales “nudges,” for example. Further, the present disclosure enables web analytics data to be combined with sales data for sales forecasting in general.

Abstract: A vehicle control method and system, including: receiving road friction information indicating road friction estimates for a plurality of regions surrounding the vehicle; detecting and determining a predicted trajectory for an object within the plurality of regions surrounding the vehicle; wherein the predicted trajectory for the object is determined based in part on the road friction estimates for the plurality of regions surrounding the vehicle; and modifying operation of the vehicle based on the predicted trajectory for the object. The predicted trajectory for the object is determined based in part on a risk map for the plurality of regions surrounding the vehicle that is generated from a road friction map for the plurality of regions surrounding the vehicle.

Abstract: A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.

Abstract: Vehicle alert and control systems and methods taking into account a detected road friction at a following vehicle and a predicted road friction by the following vehicle. The detected road friction between the following vehicle tires and the road surface may be assessed using a variety of methodologies and is used to compute a critical safety distance between the following vehicle and the preceding vehicle and a critical safety speed of the following vehicle. The predicted road friction ahead of the following vehicle may also be assessed using a variety of methodologies (lidar, camera, and cloud-based examples are provided) and is used to compute a warning safety distance between the following vehicle and the preceding vehicle and a warning safety speed of the following vehicle. These functionalities may be applied to vehicle/stationary object warning and response scenarios as well.

Abstract: Methods and systems for generating annotated data for training vehicular driver assist (DA) and autonomous driving (AD) active safety (AS) functionalities and the like. More specifically, methods and systems for the fast estimation of three-dimensional (3-D) bounding boxes and drivable surfaces using LIDAR point clouds and the like. These methods and systems provide fast and accurate annotation cluster pre-proposals on a minimally-supervised or unsupervised basis, segment drivable surfaces/ground planes in a bird's-eye-view (BEV) construct, and provide fast and accurate annotation cluster pre-proposal labels based on the feature-based detection of similar objects in already-annotated frames. The methods and systems minimize the expertise, time, and expense associated with the manual annotation of LIDAR point clouds and the like in the generation of annotated data for training machine learning (ML) algorithms and the like.