Abstract: A system and method includes determining uncertainty estimation in an object detection deep neural network (DNN) by retrieving a calibration dataset from a validation dataset that includes scores associated with all classes in an image, including a background (BG) class, determining background ground truth boxes in the calibration dataset by comparing ground truth boxes with detection boxes generated by the object detection DNN using an intersection over union (IoU) threshold, correcting for class imbalance between ground truth boxes and background ground truth boxes in a ground truth class by updating the ground truth class to include a number of background ground truth boxes based on a number of ground truth boxes in the ground truth class, estimating uncertainty of the object detection DNN based on the class imbalance correction, and updating output data sets of the object detection DNN based on the class imbalance correction.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a dataset of images; extract feature data from the images; optimize a number of clusters into which the images are classified based on the feature data; for each cluster, optimize a number of subclusters into which the images in that cluster are classified; determine a metric indicating a bias of the dataset toward at least one of the clusters or subclusters based on the number of clusters, the numbers of subclusters, distances between the respective clusters, and distances between the respective subclusters; and after determining the metric, train a machine-learning program using a training set constructed from the clusters and the subclusters.

Abstract: Image data are input to a machine learning program. The machine learning program is trained with a virtual boundary model based on a distance between a host vehicle and a target object and a loss function based on a real-world physical model. An identification of a threat object is output from the machine learning program. A subsystem of the host vehicle is actuated based on the identification of the threat object.

Abstract: A computer that includes a processor and a memory can predict future status of one or more moving objects by acquiring a plurality of video frames with a sensor included in a device, inputting the plurality of video frames to a first deep neural network to determine one or more objects included in the plurality of video frames, and inputting the objects to a second deep neural network to determine object features and full frame features.

Abstract: At a first timestep, one or more first objects can be determined in a first fusion image based on determining one or more first radar clusters in first radar data and determining one or more first two-dimensional bounding boxes in first camera data. First detected objects and first undetected objects can be determined by inputting the first objects and the first radar clusters into a data association algorithm, which determines first probabilities and adds the first radar clusters and the first objects to one or more of first detected objects or first undetected objects by determining a cost function. The first detected objects and the first undetected objects can be input to a first Poisson multi-Bernoulli mixture (PMBM) filter to determine second detected objects, second undetected objects and second probabilities. The second detected objects and the second undetected objects can be reduced based on the second probabilities determined by the first PMBM filter and the second detected objects can be output.

Abstract: A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to: process vehicle sensor data with a deep neural network to generate a prediction indicative of one or more objects based on the data and determine an object uncertainty corresponding to the prediction and when the object uncertainty is greater than an uncertainty threshold, segment the vehicle sensor data into a foreground portion and a background portion. Classify the foreground portion as including an unseen object class when a foreground uncertainty is greater than a foreground uncertainty threshold; classify the background portion as including unseen background when a background uncertainty is greater than a background uncertainty threshold; and transmit the data and a data classification to a server.

Abstract: A system can include a computer including a processor and a memory, the memory storing instructions executable by the processor to receive point cloud data. The instructions further include instructions to generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data. The instructions further include instructions to aggregate the plurality of feature maps into an aggregated feature map. The instructions further include instructions to generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.

Abstract: Image data are input to a machine learning program. The machine learning program is trained with a virtual boundary model based on a distance between a host vehicle and a target object and a loss function based on a real-world physical model. An identification of a threat object is output from the machine learning program. A subsystem of the host vehicle is actuated based on the identification of the threat object.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to collect a plurality of data sets, each data set from a respective sensor in a plurality of sensors, and each data set including a range, an azimuth angle, and a range rate for a detection point of the respective one of the sensors on an object to determine, for each detection point, a radial component of a ground speed of the detection point based on the data set associated with the detection point and a speed of a vehicle, and to generate a plurality of clusters, each cluster including selected detection points within a distance threshold from each other and having respective radial components of ground speeds that are (1) above a first threshold and (2) within a second threshold of each other.

Abstract: A first computer can operate a first instance of a neural network, receive a first data set input to the first instance of the neural network, determine a first calibration parameter for the neural network in the first instance of the neural network based on the first data set, and send the first calibration parameter to a server computer. A second computer can operate a second instance of the neural network, receive a second data set input to the second instance of the neural network, determine a second calibration parameter for the neural network in the second instance of the neural network based on the second data set, and send the second calibration parameter to the server computer. A server computer can aggregate the first and second calibration parameters to update a model of the neural network and update the neural network model for the first and second instances of the neural network at the first and second computers based on the aggregated first and second calibration parameters.

Abstract: A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to: process vehicle sensor data with a deep neural network to generate a prediction indicative of one or more objects based on the data and determine an object uncertainty corresponding to the prediction and when the object uncertainty is greater than an uncertainty threshold, segment the vehicle sensor data into a foreground portion and a background portion. Classify the foreground portion as including an unseen object class when a foreground uncertainty is greater than a foreground uncertainty threshold; classify the background portion as including unseen background when a background uncertainty is greater than a background uncertainty threshold; and transmit the data and a data classification to a server.

Abstract: A system comprising a computer including a processor and a memory, the memory including instructions such that the processor is programmed to: determine whether a difference between a friction coefficient label and a determined friction coefficient corresponding to an image depicting a surface is greater than a label threshold; modify the determined friction coefficient to equal the friction coefficient label when the difference is greater than the label threshold; and retrain a neural network using the image and the friction coefficient label.

Abstract: A system can include a computer including a processor and a memory, the memory storing instructions executable by the processor to receive point cloud data. The instructions further include instructions to generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data. The instructions further include instructions to aggregate the plurality of feature maps into an aggregated feature map. The instructions further include instructions to generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.

Abstract: Systems, methods, and devices for estimating a shape of an object based on sensor data and determining a presence of a fault or a failure in a perception system. A method of the disclosure includes receiving sensor data from a range sensor and calculating a current shape reconstruction of an object based on the sensor data. The method includes retrieving from memory a prior shape reconstruction of the object based on prior sensor data. The method includes calculating a quality score for the current shape reconstruction by balancing a function of resulted variances of the current shape reconstruction and a similarity between the current shape reconstruction and the prior shape reconstruction.

Abstract: A system comprises a computer that includes a processor and a memory.

Abstract: A vehicle system includes a processor and a memory. The memory stores instructions executable by the processor to identify an area of interest from a plurality of areas on a map, to determine that a detected sound is received in a vehicle audio sensor upon determining that a source of the sound is within the area of interest and not another area in the plurality of areas, and to operate the vehicle based at least in part on the detected sound.

Abstract: Systems, methods, and devices for estimating a shape of an object based on sensor data and determining a presence of a fault or a failure in a perception system. A method of the disclosure includes receiving sensor data from a range sensor and calculating a current shape reconstruction of an object based on the sensor data. The method includes retrieving from memory a prior shape reconstruction of the object based on prior sensor data. The method includes calculating a quality score for the current shape reconstruction by balancing a function of resulted variances of the current shape reconstruction and a similarity between the current shape reconstruction and the prior shape reconstruction.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to collect a plurality of data sets, each data set from a respective sensor in a plurality of sensors, and each data set including a range, an azimuth angle, and a range rate for a detection point of the respective one of the sensors on an object to determine, for each detection point, a radial component of a ground speed of the detection point based on the data set associated with the detection point and a speed of a vehicle, and to generate a plurality of clusters, each cluster including selected detection points within a distance threshold from each other and having respective radial components of ground speeds that are (1) above a first threshold and (2) within a second threshold of each other.

Abstract: The present invention extends to methods, systems, and computer program products for evaluating autonomous vehicle algorithms. Aspects use (e.g., supervised) machine learning techniques to analyze performance of autonomous vehicle algorithms on real world and simulated data. Machine learning techniques can be used to identify scenario features that are more likely to influence algorithm performance. Machine learning techniques can also be used to consolidate insights and automate the generation of relevant test cases over multiple iterations to identify error-prone scenarios.

Abstract: Data from sensors of a vehicle is captured along with data tracking a driver's gaze. The route traveled by the vehicle may also be captured. The driver's gaze is evaluated with respect to the sensor data to determine a feature the driver was focused on. A focus record is created for the feature. Focus records for many drivers may be aggregated to determine a frequency of observation of the feature. A machine learning model may be trained using the focus records to identify a region of interest for a given scenario in order to more quickly identify relevant hazards.