Neural network training using ground truth data augmented with map information for autonomous machine applications

Abstract

In various instances, training sensor data generated by one or more sensors of an autonomous machine may be localized—e.g., automatically, in embodiments—to high-definition (HD) map data to augment and / or generate ground truth data. The ground truth data may be associated with the training sensor data to train one or more deep neural networks (DNNs) to compute outputs corresponding to autonomous machine operation—e.g., object or feature detection, road feature detection and classification, waiting condition identification and classification, etc. As a result, HD map data may be leveraged during training so that the DNNs—during deployment—can help the autonomous machine safely navigate an environment without relying on HD map data.

Description

[Technical field]

[0001] The present invention relates to neural network training using ground truth data augmented with map information for autonomous machine applications. [Background technology]

[0002] In order for an autonomous vehicle to safely navigate an environment, the vehicle may rely on a high definition (HD) map corresponding to the area in which the vehicle intends to operate. Due to the detailed, three-dimensional, and highly accurate nature of HD maps, navigating according to HD map data has proven effective for safe navigation of environments in which HD map information is available. However, there are cases in which HD map information is not available, accurate, or up-to-date, and / or HD maps may not be relied upon - at least exclusively - to aid in navigating the environment. In such instances, conventional approaches leverage the vehicle's on-board sensors - e.g., vision sensors (e.g., cameras, LIDAR, RADAR, etc.) - to detect objects, road features (e.g., lane markings, road edges, etc.), free space boundaries, waiting condition information, intersection structure and pose, and / or the like. For example, a deep neural network (DNN) may be utilized to process sensor data from the on-board sensors and compute an output corresponding to any of the aforementioned actions.

[0003] However, to succeed and perform with the level of accuracy required for autonomous operation, DNNs require large amounts of diverse training data and corresponding ground truth data (e.g., labels, annotations, etc.) during training. Ground truth data may include, for example, polylines that identify lane markings or road edges, bounding boxes around objects or features of the environment, and / or other ground truth data types. The process of generating ground truth data requires a significant amount of manual effort and is typically a significant component of the cost and development time of a product based on a DNN—for example, a single set of ground truth data for a training data instance (e.g., an image) may require more than 20 minutes of labeling or annotation effort. In addition, manual labeling may not result in ground truth data that allows a DNN to perform as accurately as possible—for example, due to human error during labeling or annotation. As a result, if HD maps are not available, a DNN may not perform as accurately as desired for safe autonomous operation and / or may require significant cost and manual effort to do so. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Nonprovisional Patent Application No. 16 / 409,056 [Patent Document 2] U.S. Nonprovisional Patent Application No. 16 / 814,351 [Patent Document 3] U.S. Nonprovisional Patent Application No. 16 / 514,230 Summary of the Invention [Means for solving the problem]

[0005] Embodiments of the present disclosure relate to utilizing map information to generate ground truth data for training neural networks for autonomous machine applications. Systems and methods are disclosed that use localization techniques to determine information corresponding to a high-definition (HD) map that corresponds to training data (e.g., images, confidence maps, LIDAR data, RADAR data, etc.) captured using one or more sensors of an autonomous machine. Information from the HD map can then be utilized to generate training labels, annotations, or other ground truth data corresponding to the training data to train one or more neural networks to perform calculations corresponding to autonomous machine operations (e.g., object detection, waiting condition analysis, road structure determination, localization, feature detection, etc.).

[0006] In contrast to conventional systems, such as those described above, embodiments of the present disclosure combine HD map data with training of a deep neural network (DNN) to account for defects or imperfections in the HD map, as well as conventional training processes for the DNN. For example, a limited range of accurate, up-to-date HD maps may be accounted for with a DNN that is generated using the HD map and trained using ground truth data corresponding to sensor data captured within the region where the HD map is accurate and up-to-date. Furthermore, the costly and potentially inaccurate ground truth generation process of conventional DNN training techniques may be improved using automated generation of accurate ground truth data from HD map information. As a result, training of the DNN may be substantially less costly in terms of time and manual effort, and the resulting DNN that may be used to aid in various operations of an autonomous machine may be more accurate and reliable, particularly in locations where HD map information is unavailable or not up-to-date.

[0007] The present systems and methods that utilize map information to generate ground truth data for training neural networks for autonomous machine applications are described in detail below with reference to the accompanying drawings. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 includes an example data flow diagram of a process for localizing training data into high-resolution (HD) map data to augment or generate labels for training a deep neural network (DNN) in accordance with some embodiments of the present disclosure. [Figure 2A] FIG. 1 illustrates an example visualization of automatically generated ground truth labels corresponding to road features, according to some embodiments of the present disclosure. [Figure 2B] FIG. 13 illustrates an example visualization of automatically generated ground truth labels corresponding to intersection detection and classification, according to some embodiments of the present disclosure. [Figure 2C] FIG. 1 illustrates an example visualization of automatically generated ground truth labels corresponding to environmental features including poles, road markings, lane lines, road lines, and pedestrian crossings, in accordance with some embodiments of the present disclosure. [Diagram 3] 1A-1C show example histograms corresponding to deviations from the center of a lane of travel or from a rail, according to some embodiments of the present disclosure. [Figure 4] 1 is a flow diagram illustrating a method for localizing training data into HD map data to augment or generate labels for training a DNN, according to some embodiments of the present disclosure. [Figure 5A] 1 is an illustration of an example autonomous vehicle, according to some embodiments of the present disclosure. [Figure 5B] 5B is an illustration of camera positions and fields of view for the example autonomous vehicle of FIG. 5A, according to some embodiments of the present disclosure. [Figure 5C]FIG. 5B is a block diagram of an example system architecture of the example autonomous vehicle of FIG. 5A, in accordance with some embodiments of the present disclosure. [Figure 5D] FIG. 5B is a system diagram of communication between a cloud-based server and the example autonomous vehicle of FIG. 5A, according to some embodiments of the present disclosure. [Figure 6] FIG. 1 is a block diagram of an example computing device suitable for use in implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Systems and methods are disclosed that relate to utilizing map information to generate ground truth data for training neural networks for autonomous machine applications. The present disclosure may be described, without limitation, with respect to an exemplary autonomous vehicle 500 (alternatively referred to as a "vehicle 500," "ego vehicle 500," "data collection vehicle 500," or "dynamic actor 500," examples of which are described with respect to FIGS. 5A-5D . For example, the systems and methods described herein may be used, without limitation, with a non-autonomous vehicle, a semi-autonomous vehicle (e.g., a vehicle that is equipped with one or more adaptive driver assistance systems (ADAS)), a vehicle that is equipped with a vehicle navigation system (e.g., a vehicle navigation system), ... The present disclosure may be used by autonomous driving or ADAS systems, robots, warehouse vehicles, off-road vehicles, airships, boats, shuttles, emergency response vehicles, motorcycles, electric or mopeds, aircraft, construction vehicles, submarines, drones, and / or other vehicle types. Additionally, the present disclosure may be described with respect to autonomous driving or ADAS systems, but this is not intended to be limiting. For example, the systems and methods described herein may be used in a simulated environment to generate ground truth data for training deep neural networks (DNNs) for implementation in robotics (e.g., using map information of indoor environments, outdoor environments, warehouses, etc.), aviation systems, marine systems, and / or other technology fields.

[0010] Referring to FIG. 1, FIG. 1 includes an example data flow diagram of a process 100 for localizing training data into high-resolution (HD) map data for augmenting or generating labels for training a deep neural network (DNN), according to some embodiments of the present disclosure. The process 100 may be described with reference to an autonomous vehicle 500 and / or an example computing device 600 (FIG. 6), which is not intended to be limiting. It should be understood that this and other configurations described herein are described by way of example only. Other configurations and elements (e.g., machines, interfaces, functions, sequences, groupings of functions, etc.) may be used in addition to or in place of those illustrated, and some elements may be omitted entirely. Additionally, many of the elements described herein are functional entities that may be implemented as separate or distributed components or in conjunction with other components, and in any suitable combination and location. Various functions described herein as being performed by an entity may be implemented by hardware, firmware, and / or software. For example, various functions may be implemented by a processor executing instructions stored in a memory.

[0011] The process 100 may include generating and / or receiving sensor data 102 from one or more sensors of a data collection vehicle 500 (which may be similar to the vehicle 500 or may include a non-autonomous or semi-autonomous vehicle). The sensor data 102 may be used within the process 100 for localization, correlation, and ground truth generation, as well as for input data for a deep neural network (DNN) 116. The sensor data 102 may include, but is not limited to, sensor data 102 from any type of sensor, such as, but not limited to, those described herein with respect to the vehicle 500 and / or other vehicles or objects, such as, in some instances, a robotic device, a VR system, an AR system, etc. 5A-5C , the sensor data 102 may include, without limitation, data generated by global navigation satellite systems (GNSS) sensors 558 (e.g., global positioning system (GPS) sensors, differential GPS (DGPS) sensors, etc.), RADAR sensors 560, ultrasonic sensors 562, LIDAR sensors 564, inertial measurement unit (IMU) sensors 566 (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones 596, stereo cameras 568, wide-view cameras 570 (e.g., fisheye cameras), infrared cameras 572, surround cameras 574 (e.g., 360-degree cameras), long-range and / or medium-range cameras 598, speed sensors 544 (e.g., for measuring the speed and / or distance traveled of a data collection vehicle), and / or other sensor types.

[0012] In some instances, sensor data 102 may include sensor data generated by one or more forward-facing, side-view, and / or rear-view sensors. This sensor data 102 may be useful for identifying, detecting, classifying, and / or tracking objects around the data collection vehicle in the environment, for example, for localization, correlation with HD map 104, ground truth generation, and / or the like. In an embodiment, any number of sensors may be used to incorporate multiple fields of view (e.g., the fields of view of long-range camera 598, forward-facing stereo camera 568, and / or forward-facing wide-view camera 570 of FIG. 5B) and / or perception fields (e.g., LIDAR sensor 564, RADAR sensor 560, etc.).

[0013] In some examples, the sensor data 102 may include image data representing an image, image data representing a video (e.g., a snapshot of a video), and / or sensor data representing a representation of a sensor's field of perception (e.g., a depth map for a LIDAR sensor, a value graph for an ultrasonic sensor, etc.). When the sensor data 102 includes image data, any type of image data format may be used, including, but not limited to, compressed images, such as Joint Photographic Experts Group (JPEG) or Luminance / Chrominance (YUV) formats, compressed images, such as frames resulting from compressed video formats, such as H.264 / Advanced Video Coding (AVC) or H.265 / High Efficiency Video Coding (HEVC), raw images, such as those derived from Red Clear Blue (RCCB), Red Clear (RCCC), or other types of image sensors, and / or other formats. Additionally, in some instances, the sensor data 102 may be used in the process 100 without preprocessing (e.g., in a raw or captured format), while in other instances, the sensor data 102 may undergo preprocessing (e.g., noise balancing, demosaicing, scaling, cropping, enhancement, white balancing, tone curve adjustment, etc., e.g., using a sensor data preprocessor (not shown)). As used herein, sensor data 102 may refer to raw sensor data, preprocessed sensor data, or a combination thereof.

[0014] Additionally, the process 100 may include generating and / or receiving map data from a map accessible and / or stored by the data collection vehicle 500, such as HD map 104 (which may be similar to HD map 522 of FIG. 5C). In some embodiments, the HD map 104 and / or the localizer 106 may be components of an HD map manager. In some embodiments, the HD map 104 may include centimeter-level or finer precision, such that the data collection vehicle 500 may rely on the HD map 104 for precise command, planning, and localization. The HD map 104 may represent lanes, road boundaries, road geometry, elevation, slope, and / or contours, heading information, waiting conditions, static object locations, and / or other information. As such, the process 100 may use information from the HD map 104, such as lane locations and shapes, to generate ground truth data for training the DNN 116. Although described herein as HD map 104, this is not intended to be limiting and the map data may be generated from any type of map having greater or lesser accuracy than HD map 104. For example, map data generated from a navigation or GPS application may be used in addition to or separately from HD map 104 without departing from the scope of this disclosure.

[0015] The sensor data 102 and map data (e.g., from the HD map 104) may be used by the localizer 106 to localize (e.g., for position and / or orientation) the data collection vehicle 500 with respect to the HD map 104. For example, the sensor data 102 generated by a position-based sensor, such as a GNSS sensor 558, may be used to determine an approximate location of the data collection vehicle 500 on the HD map 104. This information may be used to determine areas of the HD map 104 that should be analyzed to precisely localize the data collection vehicle 500 within the HD map 104. For example, the sensor data 102 generated by a vision-based sensor, such as a camera, a RADAR sensor 560, an ultrasonic sensor 562, a LIDAR sensor 564, and / or other sensors, may be used to identify features and / or objects in the environment that have known and precise locations within areas of the HD map 104 determined using the position-based sensors. After the vehicle 500 is initially localized within the HD map 104, the position and / or orientation of the vehicle 500 over time may be tracked using this same localization technique, e.g., using vision-based sensors to identify objects and / or features with known positions within the HD map 104, and / or using sensor data 102 generated by the vehicle's 500 self-motion sensors (e.g., IMU sensor 566, speed sensor 544, steering sensor 540 tracking steering wheel angle, etc.). For example, after the vehicle 500 is initially localized, the self-motion sensors may be used to accurately track changes in the position and / or orientation of the vehicle 500 over time. However, even when self-motion sensors are used, localization techniques using vision-based sensors may be performed periodically (e.g., every 3 seconds, every 10 seconds, etc.) to recalibrate the system to localize the vehicle 500 within the HD map 104.

[0016] In some non-limiting examples, information from sensor data 102 and / or HD map 104 may be applied to a coordinate transformer to transform sensor data 102 and / or HD map 104 into the coordinate system of vehicle 500 and / or to transform map data from HD map 104 into the coordinate space of sensor data 102 (e.g., to transform 3D world space map data into 2D image or sensor space). In order for coordinate transformer 108 to perform the transformations or shifts described herein, intrinsic parameters of the sensor (e.g., optical center, focal length, etc.) and / or extrinsic parameters (e.g., position, rotation, translation, etc. of the sensor on vehicle 500) may be used to determine a correlation between 2D pixel locations (or other image or sensor space locations) on HD map 104 and 2D or 3D world space locations.

[0017] For example, the coordinate transformer 108 can adapt the HD map 104 with respect to the vehicle 500 and / or with respect to the field of view of the sensor that captured the instance of the sensor data 102. In some embodiments, the coordinate transformer 108 can shift the perspective of the map data with respect to the location and / or orientation of the data collection vehicle 500 and / or its sensor. As such, a portion of the HD map 104 that may be used by the ground truth generator 112 to generate ground truth data may be shifted with respect to the vehicle 500 (e.g., with the data collection vehicle 500 at its center, at (x,y) coordinates of (0,0), where y is the vertical dimension extending from the front to the back of the vehicle and x is the horizontal dimension perpendicular to y and extending from the left to the right of the vehicle) and / or its sensor (e.g., to the field of view or perception field of the sensor that generated the instance of the sensor data 102 corresponding to the HD map 104). In some examples, in addition to or as an alternative to shifting the viewpoint or coordinate system for the vehicle 500 and / or its sensors, the coordinate transformer 108 can shift the viewpoint to the same view for each type of data. For example, if the HD map 104 may generate data from a top-down viewpoint of the environment, the sensors generating the sensor data 102 may do so from a different viewpoint, e.g., forward facing, sideways, angled down, angled up, etc. As such, to generate ground truth data from the same viewpoint, the coordinate transformer 108 can adjust the sensor data 102 and / or the map data to the same viewpoint. In some non-limiting examples, each of the sensor data 102 and the HD map 104 can be shifted to a top-down view viewpoint or coordinate system of the HD map 104, a coordinate system or viewpoint of the sensor data 102, and / or another viewpoint or coordinate system.

[0018] In addition to or as an alternative to the coordinate transformer 108 transforming or converting the coordinate system of the HD map 104 to that of the vehicle 500 and / or its sensors, the coordinate transformer 108 can, in some embodiments, transform or convert the map data to the coordinate system or dimensions of the sensor data 102. For example, if the DNN 116 is trained to compute the output 118 in a 2D image space, the map data can be transformed or translated from 2D or 3D world space coordinates to 2D image or sensor space coordinates. As another example, if the DNN 116 is trained to compute the output 118 in a 3D world space, the map data can not be transformed or translated to the 2D image space even if the sensor data 102 input to the DNN 116 represents a sensor data representation in 2D space. As such, the DNN 116 can be trained to compute the output 118 in 2D or 3D world space coordinates, and as a result, the ground truth generated to train the DNN 116 can correspond to a 2D or 3D world space coordinate system. In at least some embodiments, some or all of the sensor data 102 to which the ground truth corresponds (e.g., the features, objects, etc. represented thereby) may be transformed from the 2D image or sensor space to 2D or 3D world space by a coordinate transformer 108 to generate ground truth that corresponds to the 2D or 3D world space.

[0019] After localization has been performed by the localizer 106 and / or the sensor data 102 and / or map data have been transformed or translated by the coordinate transformer 108, the correlator 110 (which may include or may be referred to herein as the feature determiner 110) may correlate the map data with the sensor data 102. For example, depending on the type of ground truth data to be generated, the correlator may determine correlations between features and / or objects as represented by the map data and features and / or objects as represented by the sensor data 102. As an example, if the DNN 116 is trained to predict the location of lane lines, dividers, and / or other features of a driving surface, the map data representing the lane lines, dividers, and / or other features may be correlated with the sensor data 102 in each sensor data instance (e.g., in each image or frame) (e.g., similar to the visualization 200 of FIG. 2A). As another example, if the DNN 116 is trained to generate trajectories as described herein, the correlator 110 can determine the rails (e.g., centers) of the lanes that correspond to the ground truth trajectories, such that the ground truth generator 112 can generate a final ground truth trajectory that more closely corresponds to or is centered on the rails of the lanes (e.g., similar to visualization 200 of FIG. 2A). As a further example, if the DNN 116 is trained to generate outputs corresponding to intersections (e.g., boundary shape vertices corresponding to a boundary shape that encompasses the intersection), the correlator 110 can determine each feature of the intersection (e.g., traffic signals, traffic signs, labels or marks on the driving surface, etc.) that correspond to the intersection, such that the ground truth generator 112 can generate a boundary shape that encompasses the respective features (e.g., similar to visualization 240 of FIG. 2B).

[0020] The ground truth generator 112 may generate ground truth data using the sensor data 102 and / or map data from the HD map 104 according to the output 118 that the DNN 116 was trained to compute and the format of the output 118. For example, if the DNN 116 was trained to generate outputs corresponding to points of a polyline defining lanes, the ground truth generator 112 may generate ground truth data from the map data by determining points along the lane markings (at some increment) from the map data and associating those points with the points of the polyline. As such, if the DNN 116 generates outputs 118 corresponding to points of the polyline, the ground truth data generated by the ground truth generator 112 may be compared by the training engine 114 - e.g., using one or more loss functions - to the points from the output 118 to determine updates to the parameters (e.g., weights and biases) of the DNN 116.

[0021] Similarly, if the DNN 116 is trained to predict an output 118 corresponding to a boundary shape of an intersection, the ground truth generator 112 can generate the ground truth boundary shape according to the format of the prediction of the DNN 116. For example, the DNN 116 can be trained to output boundary shape coordinates as pixel locations of multiple vertices of the boundary shape in 2D image space, and as a result, the ground truth generator 112 can generate the ground truth data according to this format, e.g., by generating ground truth data corresponding to the locations of multiple vertices of the boundary shape. As another example, the DNN 116 can be trained to output boundary shape coordinates as pixel locations of the centroid of the boundary shape and dimensions (e.g., height and width) in 2D image space, and as a result, the ground truth generator 112 can generate the ground truth data according to this format, e.g., by generating ground truth data corresponding to the locations of the centroid and dimensions of the boundary shape. As a further illustration, the DNN 116 may be trained to output bounding shape coordinates as the positions of multiple vertices of the bounding shape in 3D world space, and as a result, the ground truth generator 112 may generate ground truth data according to this format - for example, by generating ground truth data corresponding to the positions of multiple vertices of the bounding shape in 3D world space.

[0022] In some embodiments, depending on any pre-processing of the sensor data 102, the ground truth generator 112 can compensate for the pre-processing in generating the ground truth data. For example, if an instance of the sensor data 102 (e.g., an image, a depth map, etc.) is pre-processed - e.g., by adjusting spatial resolution, flipping, rotating, cropping, zooming, augmenting, etc. - the ground truth generator 112 can account for these changes in generating the ground truth data. For example, in some embodiments, each instance of the sensor data 102 can be adjusted in some manner. In such instances, the ground truth generator 112 can adjust the ground truth data accordingly for each instance of the ground truth data (e.g., if each image represented by the sensor data 102 is cropped, each instance of the ground truth data can be adjusted to account for the crop). In other instances, some instances of sensor data 102 may be adjusted and other instances may not be adjusted - e.g., to train the DNN 116 not to overfit and to accurately calculate the output 118 across any sensor data instance variation. In such instances, the ground truth generator 112 may receive data representing adjustments to instances of sensor data 102 and may compensate for the adjustments when generating the ground truth data. For example, if a first instance of sensor data 102 is unchanged, the ground truth data may be generated normally, but if a second instance of sensor data 102 is rotated prior to input to the DNN 116, the ground truth generator 112 may account for this by similarly rotating the ground truth data to correspond to the rotated instance of sensor data 102.

[0023] After the ground truth data is generated—automatically, in an embodiment—the ground truth data may be used by the training engine 114 to train the DNN 116. For example, the sensor data 102 may be applied to the DNN 116, which may generate an output 118, the training engine 114 may analyze the output 118 in light of the ground truth data from the ground truth generator 112 using one or more loss functions, and the results of the training engine 114 computations may be used to update the DNN 116 until it converges to a desired or acceptable accuracy.

[0024] DNN 116 may include any type of DNN or machine learning model, depending on the embodiment. For example, and without limitation, DNN 116 may include any type of machine learning model, such as linear regression, logistic regression, decision trees, support vector machines (SVMs), naive Bayes, k-nearest neighbors (Knn), K-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutional, recurrent, perceptrons, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machines, etc.), lane detection algorithms, machine learning models using computer vision algorithms, and / or other types of machine learning models.

[0025] As an example, such as when the DNN 116 includes a CNN, the DNN 116 may include any number of layers. One or more of the layers may include an input layer. The input layer may hold values ​​associated with the sensor data 102 (e.g., before or after post-processing). For example, when the sensor data 102 is an image, the input layer may hold values ​​representing the raw pixel values ​​of the image as a volume (e.g., width, height, and color channels (e.g., RGB), e.g., 32x32x3).

[0026] One or more layers may include a convolutional layer. A convolutional layer may compute the output of neurons connected to a local region in the input layer, where each neuron computes the dot product between their weights and the small region to which they are connected in the input capacitance. The result of a convolutional layer may be another capacitance, with one of the dimensions based on the number of filters applied (e.g., width, height, and number of filters, e.g., 32x32x12, where 12 is the number of filters).

[0027] One or more of the layers may include a rectified linear unit (ReLU) layer. The ReLU layer may, for example, apply an element-wise activation function, e.g., max(0,x), that is thresholded at zero. The resulting capacity of the ReLU layer may be the same as the capacity of the input of the ReLU layer.

[0028] One or more of the layers may include a pooling layer, which may perform a down-sampling operation along spatial dimensions (e.g., height and width) that may result in a capacity smaller than the pooling layer's input (e.g., 16x16x12 from a 32x32x12 input capacity).

[0029] One or more of the layers may include one or more fully connected layers. Each neuron in a fully connected layer may be connected to a respective neuron in the previous capacity. The fully connected layers may compute class scores, and the resulting capacity may be 1x1x the number of classes. In some instances, a CNN may include a fully connected layer, such that the output of one or more of the layers of the CNN may be provided as input to a fully connected layer of the CNN. In some instances, one or more convolutional streams may be implemented by the DNN 116, and some or all of the convolutional streams may include respective fully connected layers.

[0030] In some non-limiting examples, the DNN 116 may include a series of convolution and max-pooling layers to facilitate image feature extraction, followed by multi-scale dilated convolution and up-sampling layers to facilitate global context feature extraction.

[0031] Although input layers, convolutional layers, pooling layers, ReLU layers, and fully connected layers are discussed herein with respect to the DNN 116, this is not intended to be limiting. For example, additional or alternative layers may be used in the DNN 116, such as normalization layers, SoftMax layers, and / or other layer types.

[0032] In embodiments where the DNN 116 includes a CNN, different orders and numbers of layers of the CNN may be used depending on the embodiment, in other words, the order and number of layers of the DNN 116 is not limited to any one architecture.

[0033] In addition, some of the layers may include parameters (e.g., weights and / or biases), e.g., convolutional layers and fully connected layers, while other layers, e.g., ReLU layers and pooling layers, may not. In some instances, the parameters may be learned by the DNN 116 during training. Furthermore, some of the layers may include additional hyperparameters (e.g., learning rate, stride, epoch, etc.), e.g., convolutional layers, fully connected layers, and pooling layers, while other layers, e.g., ReLU layers, may not. The parameters and hyperparameters are not limited and may vary depending on the embodiment.

[0034] 2A-2C, which include example visualizations representing various instances of automatic ground truth generation with process 100. The visualizations described herein are merely for illustrative purposes and are not intended to limit the scope of the present disclosure. Referring to FIG. 2A, FIG. 2A illustrates an example visualization 200 of automatically generated ground truth labels corresponding to road features, according to some embodiments of the present disclosure. Visualization 200 may represent instances of sensor data 102 (e.g., images) and corresponding ground truth data that may be generated using map data from HD map 104 and / or trajectory information from ego-motion sensor data. For example, if DNN 116 is trained to predict road features, such as lane rails or centers, lane dividers, road boundaries, etc., the ground truth data generated from the map data may include the respective ground truth labels in visualization 200. In one or more embodiments, the ground truth labels may include all labels except for the ego-trajectory 202 (described in more detail herein). For example, after the vehicle 500 is localized in the HD map 104, the coordinate transformer 108 orients the map data with respect to the coordinate system or dimensional space of the vehicle 500, its sensors, and / or the sensor data 102, and the correlator 110 can determine each road boundary 204 (e.g., 204A and 204B), each lane divider 206 (e.g., 206A-206D), each lane rail 210 (e.g., 210A-210C, 208), and / or other features of the road and their corresponding positions with respect to instances of the sensor data, as described herein. The ground truth generator 112 can then generate ground truth data from the respective labels corresponding to these features in a format that the DNN 116 was trained to predict output for, as described herein.

[0035] As another example, and again with reference to FIG. 2A , map data from an HD map may be used to augment other ground truth data. For example, if the ego trajectory 202 is generated automatically using an ego motion sensor, the ego trajectory 202 may be adjusted to more closely correspond to the lane rail 208 corresponding to the lane of travel of the vehicle 500. As such, the ground truth generator 112 may generate a final ground truth trajectory—or data representative thereof, e.g., points along a polyline that defines the final ground truth trajectory—that corresponds to the lane rail 208 instead of the ego trajectory 202. In some non-limiting examples, the ego trajectory may be generated using methods and systems such as those described in U.S. Nonprovisional Patent Application No. 16 / 409,056, filed May 10, 2019, which is incorporated herein by reference in its entirety. For example, referring to FIG. 3 , the ego trajectory 202 may be generated based on the driving path of a human driver, such that the ego trajectory may deviate from the center or rail of the lane of travel. Graph 300 of FIG. 3 illustrates the amount of shift corresponding to the generated self-trajectories, which show trajectories that deviate from the center or rail of the lane of travel by more than half a meter. If these self-trajectories are used directly to train the DNN 116 to calculate the vehicle's future trajectory, the calculated trajectory during deployment may similarly include a shift from the rail or center of the lane of travel. As such, by extending the self-trajectory using map data to generate ground truth data that more closely follows the center or rail of the lane of travel, the calculated trajectory of the vehicle during deployment may also more closely follow the center or rail of the lane of travel. In addition, since the trajectory may include lane changes, turns, and / or the like, the adjustment of the self-trajectory for ground truth generation also allows for turns, lane changes, and / or other manipulations of the calculated trajectory of the DNN 116 to shift from the center or rail of the lane of travel to the center or rail of another lane of travel. As a result, the calculated trajectory can position the deploying vehicle at a safer distance from surrounding objects as the vehicle traverses the driving surface more closely along the center or rail of the lane of travel.

[0036] 2B, which illustrates an example visualization 240 of automatically generated ground truth labels corresponding to intersection detection and classification, according to some embodiments of the present disclosure. For example, the DNN 116 may be trained to generate an output 118 representing a boundary shape corresponding to an intersection (e.g., boundary shape 242 of visualization 240), a classification corresponding to the intersection (e.g., intersection, controlled stop signal), a distance to the intersection, and / or other information corresponding to the intersection. Map data from an HD map may represent features of the intersection and its location, so the map data may be used to generate the ground truth data. For example, if the boundary shape 242 is to encompass each feature of the intersection, such as traffic signal 244, crosswalks 246A and 246B, intersection entrance line 248, etc., the location and presence of these features may be determined from the map data, and the correlator 110 may determine the dimensions of the boundary shape 242 that encompasses all of them, the classification of the intersection, and the distance to the intersection (e.g., from intersection entrance line 248 to the entrance line). As such, the ground truth generator 212 may generate ground truth data corresponding to classification information, boundary shape dimensions and / or vertices, and / or distances to intersections. In some non-limiting examples, the ground truth generated for intersections may be similar to that of the ground truth data generated in U.S. Non-Provisional Patent Application No. 16 / 814,351, filed March 10, 2020, which is incorporated by reference in its entirety.

[0037] 2C, which illustrates an example visualization 280 of automatically generated ground truth labels corresponding to features of the environment including poles, road markings, lane markings, road boundary lines, and crosswalks, according to some embodiments of the present disclosure. For example, the DNN 116 may be trained to compute outputs 118 corresponding to features of the environment, such as lines, marks, poles, etc. As such, map data from the HD map 104 may be used to generate ground truth data that may represent poles 282, crosswalks 284, lane markings 286, road markings 288, and / or other features of the environment. As such, after localization, coordinate transformation, and / or correlation, the ground truth generator 112 may generate ground truth data corresponding to each of the features of the environment that the DNN 116 was trained to compute. In a non-limiting example, the generated ground truth may be similar to that described in U.S. Non-Provisional Patent Application No. 16 / 514,230, filed July 17, 2019, which is incorporated by reference in its entirety.

[0038] Referring now to FIG. 4, each block of method 400 described herein includes computational processes that may be performed using any combination of hardware, firmware, and / or software. For example, various functions may be performed by a processor executing instructions stored in a memory. Method 400 may also be implemented as computer usable instructions stored on a computer storage medium. Method 400 may be provided by a standalone application, a service, or a hosted service (standalone or in combination with another hosted service), or a plug-in to another product, to name a few. Additionally, method 400 is described with respect to process 100 of FIG. 1 and autonomous vehicle 500 of FIGS. 5A-5D, by way of example. However, these methods may additionally or alternatively be performed by or within any system or process, or within any combination of systems and processes, including, but not limited to, those described herein.

[0039] 4 is a flow diagram illustrating a method 400 for localizing training data in HD map data to augment or generate labels for training a DNN, according to some embodiments of the present disclosure. The method 400 includes, at block B402, receiving HD map data corresponding to an area that includes locations of dynamic actors at a time. For example, map data corresponding to an area of ​​the HD map 104 that includes a data collection vehicle 500 may be generated and / or received, e.g., using an HD map manager.

[0040] The method 400 includes localizing the dynamic actors with respect to the HD map data at block B404. For example, the localizer 106 may localize the data collection vehicle 500 within the HD map 104.

[0041] The method 400 includes receiving sensor data generated by a sensor of a dynamic actor at a time, at block B406. For example, an instance of sensor data 102 generated by a sensor of a data collection vehicle 500 may be generated and / or received.

[0042] The method 400 includes generating ground truth data corresponding to the sensor data based at least in part on the HD map data and the localization at block B408. For example, the ground truth generator 112 can use the map data to generate ground truth data corresponding to instances of the sensor data 102. In some embodiments, this can include transforming or transferring a coordinate system of the HD map 104 to a coordinate system of the vehicle 500, correlating the map data with the sensor data 102, and / or other processes described herein with respect to the coordinate transformer 108, the correlator 110, and / or the ground truth generator 112.

[0043] The method 400 includes training a neural network using the sensor data and the ground truth data at block B410. For example, the DNN 116 may be trained (e.g., using the training engine 114) using the sensor data 102 and the ground truth data generated using the ground truth generator 112.

[0044] Exemplary Autonomous Vehicle 5A is a diagram of an example autonomous vehicle 500 according to some embodiments of the present disclosure. Autonomous vehicle 500 (alternatively referred to herein as “vehicle 500”) may include, but is not limited to, passenger vehicles, such as cars, trucks, buses, first responder vehicles, shuttles, electric or mopeds, motorcycles, fire engines, police vehicles, ambulances, boats, construction vehicles, submarines, drones, and / or other types of vehicles (e.g., unmanned and / or carrying one or more passengers). Autonomous vehicles are generally described in terms of automation levels as defined by the National Highway Traffic Safety Administration (NHTSA), a division of the U.S. Department of Transportation, and the Society of Automotive Engineers (SAE) "Taxonomy and Definitions for Terms Related to Driving Automation Systems for On-Road Motor Vehicle" (Standard No. J3016-201806 published June 15, 2018, Standard No. J3016-201609 published September 30, 2016, and previous and future versions of this standard). Vehicle 500 may be capable of functioning according to one or more of autonomous driving levels 3 through 5. For example, vehicle 500 may be capable of conditional automation (Level 3), highly automated (Level 4), and / or fully automated (Level 5), depending on the embodiment.

[0045] The vehicle 500 may include components such as a vehicle chassis, body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other components. The vehicle 500 may include a propulsion system 550, such as an internal combustion engine, a hybrid power plant, a fully electric engine, and / or another propulsion system type. The propulsion system 550 may be connected to a drive train of the vehicle 500, which may include a transmission, to enable propulsion of the vehicle 500. The propulsion system 550 may be controlled in response to receiving a signal from a throttle / accelerator 552.

[0046] Steering system 554, which may include a steering wheel, may be used to steer vehicle 500 (e.g., along a desired course or route) when propulsion system 550 is operating (e.g., when the vehicle is moving). Steering system 554 may receive signals from steering actuator 556. The steering wheel may be an option for fully automated (Level 5) functionality.

[0047] Brake sensor system 546 may be used to operate the vehicle brakes in response to receiving a signal from a brake actuator 548 and / or a brake sensor.

[0048] A controller 536, which may include one or more system on chip (SoC) 504 (FIG. 5C) and / or a GPU, may provide signals (e.g., representations of commands) to one or more components and / or systems of the vehicle 500. For example, the controller may send signals to operate vehicle brakes via one or more brake actuators 548, operate a steering system 554 via one or more steering actuators 556, and operate a propulsion system 550 via one or more throttle / accelerators 552. The controller 536 may include one or more on-board (e.g., integrated) computing devices (e.g., supercomputers) that process sensor signals and output operational commands (e.g., signals representing commands) to enable autonomous driving and / or assist a driver in driving the vehicle 500. The controllers 536 may include a first controller 536 for autonomous driving functions, a second controller 536 for functional safety functions, a third controller 536 for artificial intelligence functions (e.g., computer vision), a fourth controller 536 for infotainment functions, a fifth controller 536 for redundancy in emergency situations, and / or other controllers. In some instances, a single controller 536 may handle two or more of the aforementioned functions, and two or more controllers 536 may handle a single function, and / or any combination thereof.

[0049] The controller 536 may provide signals to control one or more components and / or systems of the vehicle 500 in response to sensor data (e.g., sensor inputs) received from one or more sensors. The sensor data may be received from, for example, and without limitation, global navigation satellite system sensors 558 (e.g., global positioning system sensors), RADAR sensors 560, ultrasonic sensors 562, LIDAR sensors 564, inertial measurement unit (IMU) sensors 566 (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones 596, stereo cameras 568, wide-view cameras 570 (e.g., fisheye cameras), infrared cameras 572, surround cameras 574 (e.g., 360 degree cameras), long-range and / or medium-range cameras 598, speed sensors 544 (e.g., for measuring the speed of the vehicle 500), vibration sensors 542, steering sensors 540, brake sensors (e.g., as part of a brake sensor system 546), and / or other sensor types.

[0050] One or more of the controllers 536 may receive input (e.g., represented by input data) from the instrument cluster 532 of the vehicle 500 and provide output (e.g., represented by output data, display data, etc.) via a human-machine interface (HMI) display 534, an audible annunciator, a loudspeaker, and / or other components of the vehicle 500. The output may include information such as vehicle velocity, speed, time, map data (e.g., HD map 522 of FIG. 5C), position data (e.g., the position of the vehicle 500 on a map, etc.), direction, the positions of other vehicles (e.g., occupancy grid), information regarding objects and object situations as known by the controller 536, etc. For example, the HMI display 534 may display information regarding the presence of one or more objects (e.g., road signs, warning signs, changing traffic signals, etc.) and / or a driving maneuver that the vehicle has performed, is performing, or will perform (e.g., changing lanes now, taking exit 34B in 2 miles, etc.).

[0051] Vehicle 500 further includes a network interface 524 that can communicate over one or more networks using one or more wireless antennas 526 and / or a modem. For example, network interface 524 can be capable of communication over LTE, WCDMA, UMTS, GSM, CDMA2000, etc. Wireless antenna 526 can also enable communication between objects in the environment (e.g., vehicles, mobile devices, etc.) using local area networks such as Bluetooth, Bluetooth LE, Z-Wave, ZigBee, etc., and / or low power wide-area networks (LPWANs) such as LoRaWAN, SigFox, etc.

[0052] 5B is an illustration of camera positions and fields of view of the example autonomous vehicle 500 of FIG. 5A, according to some embodiments of the present disclosure. The cameras and their respective fields of view are one example embodiment and are not intended to be limiting. For example, additional and / or alternative cameras may be included and / or the cameras may be located in different locations on the vehicle 500.

[0053] The camera type of the camera may include, but is not limited to, a digital camera that may be adapted for use with components and / or systems of the vehicle 500. The camera may be capable of operating at automotive safety integrity level (ASIL) B and / or at another ASIL. The camera type may be capable of any image capture rate, such as 60 frames per second (fps), 520 fps, 240 fps, etc., depending on the embodiment. The camera may be capable of using a rolling shutter, a global shutter, another type of shutter, or a combination thereof. In some instances, the color filter array may include a red clear clear clear (RCCC) color filter array, a red clear clear blue (RCCB) color filter array, a red blue green clear (RBGC) color filter array, a Foveon X3 color filter array, a Bayer sensor (RGGB) color filter array, a monochrome sensor color filter array, and / or another type of color filter array. In some embodiments, clear pixel cameras, such as cameras with RCCC, RCCB, and / or RBGC color filter arrays, may be used in an effort to increase light sensitivity.

[0054] In some instances, one or more of the cameras may be used to perform advanced driver assistance system (ADAS) functions (e.g., as part of a redundant or fail-safe design). For example, a multi-function mono camera may be installed to provide functions including lane departure warning, traffic sign assist, and intelligent headlamp control. One or more of the cameras (e.g., all of the cameras) may simultaneously record and provide image data (e.g., video).

[0055] One or more of the cameras may be mounted in a mounting part, such as a custom designed (3D printed) part, to filter out stray light and reflections from within the vehicle (e.g., reflections from the dashboard reflected in the windshield mirror) that may interfere with the camera's image data capture capabilities. With reference to a side mirror mounting part, the side mirror part may be custom 3D printed such that the camera mounting plate fits the shape of the side mirror. In some instances, the camera may be integrated into the side mirror. For side view cameras, the cameras may also be integrated into four posts at each corner of the cabin.

[0056] A camera (e.g., a forward-facing camera) with a field of view that includes a portion of the environment in front of the vehicle 500 may be used for surround view to help identify the forward path and obstacles and, with the aid of one or more controllers 536 and / or control SoCs, provide information essential to generating an occupancy grid and / or determining a preferred vehicle path. Forward-facing cameras may be used to perform many of the same ADAS functions as LIDAR, including emergency braking, pedestrian detection, and collision avoidance. Forward-facing cameras may also be used for ADAS functions and systems, including other functions such as lane departure warning ("LDW"), autonomous cruise control ("ACC"), and / or traffic sign recognition.

[0057] A variety of cameras may be used in a forward-facing configuration, including, for example, a monocular camera platform including a complementary metal oxide semiconductor (CMOS) color imager. Another example may be a wide-view camera 570 that may be used to capture objects entering the view from the periphery (e.g., pedestrians, crossing traffic, or bicycles). Although only one wide-view camera is shown in FIG. 5B, there may be any number of wide-view cameras 570 in the vehicle 500. In addition, a long-range camera 598 (e.g., a long-view stereo camera pair) may be used for depth-based object detection, especially for objects for which a neural network has not yet been trained. The long-range camera 598 may also be used for object detection and classification, as well as basic object tracking.

[0058] One or more stereo cameras 568 may also be included in the forward-facing configuration. The stereo camera 568 may include an integrated control unit with an extensible processing unit that may provide programmable logic (FPGA) and a multi-core microprocessor with CAN or Ethernet interfaces integrated on a single chip. Such a unit may be used to generate a 3D map of the vehicle's environment, including distance estimates for all points in the image. An alternative stereo camera 568 may include a compact stereo vision sensor that may include two camera lenses (one on the left and one on the right) and an image processing chip that can measure distances from the vehicle to objects of interest and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning functions. Other types of stereo cameras 568 may be used in addition to or instead of those described herein.

[0059] A camera having a field of view that includes a portion of the environment to the side of the vehicle 500 (e.g., a side-view camera) may be used for surround view, providing information used to create and update the occupancy grid and to generate side impact collision warnings. For example, surround cameras 574 (e.g., four surround cameras 574 as shown in FIG. 5B) may be positioned on the vehicle 500. The surround cameras 574 may include a wide-view camera 570, a fisheye camera, a 360-degree camera, and / or the like. For example, four fisheye cameras may be positioned at the front, rear, and sides of the vehicle. In an alternative arrangement, the vehicle may use three surround cameras 574 (e.g., left, right, and rear) and may utilize one or more other cameras (e.g., a forward-facing camera) as a fourth surround view camera.

[0060] A camera having a field of view that includes the portion of the environment behind the vehicle 500 (e.g., a rear-view camera) may be used for parking assistance, surround view, rear collision warning, and creating and updating an occupancy grid. As described herein, a wide variety of cameras may be used, including, but not limited to, cameras that are also suitable as forward-facing cameras (e.g., long-range and / or mid-range camera 598, stereo camera 568, infrared camera 572, etc.).

[0061] FIG. 5C is a block diagram of an example system architecture of the example autonomous vehicle 500 of FIG. 5A, according to some embodiments of the present disclosure. It should be understood that this and other arrangements described herein are merely illustrative. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, groupings of functions, etc.) may be used in addition to or instead of those shown, and some elements may be omitted altogether. Furthermore, many of the elements described herein are functional entities that may be implemented as separate or distributed components or in conjunction with other components, and in any suitable combination and location. Various functions described herein as being performed by entities may be implemented by hardware, firmware, and / or software. For example, various functions may be implemented by a processor executing instructions stored in a memory.

[0062] Each of the components, features, and systems of the vehicle 500 of FIG. 5C are shown as being connected via a bus 502. The bus 502 may include a controller area network (CAN) data interface (alternatively referred to as a “CAN bus”). The CAN may be a network within the vehicle 500 used to help control various features and functions of the vehicle 500, such as actuation of brakes, acceleration, braking, steering, windshield wipers, etc. The CAN bus may be configured to have dozens or even hundreds of nodes, each with its own unique identifier (e.g., CAN ID). The CAN bus may be read to find steering angle, ground speed, engine revolutions per minute (RPM), button positions, and / or other vehicle status indicators. The CAN bus may be ASIL B compliant.

[0063] The bus 502 is described herein as being a CAN bus, although this is not intended to be limiting. For example, FlexRay and / or Ethernet may be used in addition to or as an alternative to a CAN bus. Additionally, a single line is used to represent the bus 502, although this is not intended to be limiting. There may be any number of buses 502, which may include, for example, one or more CAN buses, one or more FlexRay buses, one or more Ethernet buses, and / or one or more other types of buses using different protocols. In some instances, two or more buses 502 may be used to perform different functions and / or may be used for redundancy. For example, a first bus 502 may be used for collision avoidance functions and a second bus 502 may be used for operational control. In any instance, each bus 502 may communicate with any of the components of the vehicle 500, and two or more buses 502 may communicate with the same component. In some examples, each SoC 504, each controller 536, and / or each computer in the vehicle may have access to the same input data (e.g., input from sensors in the vehicle 500) and may be connected to a common bus, such as a CAN bus.

[0064] 5A. The controller 536 may be used for a variety of functions. The controller 536 may be coupled to any of a variety of other components and systems of the vehicle 500 and may be used for control of the vehicle 500, artificial intelligence of the vehicle 500, infotainment for the vehicle 500, and / or the like.

[0065] The vehicle 500 may include a system on a chip (SoC) 504. The SoC 504 may include a CPU 506, a GPU 508, a processor 510, a cache 512, an accelerator 514, a data store 516, and / or other components and features not shown. The SoC 504 may be used to control the vehicle 500 in a variety of platforms and systems. For example, the SoC 504 may be combined in a system (e.g., the system of the vehicle 500) having an HD map 522 that can obtain map refreshes and / or updates via a network interface 524 from one or more servers (e.g., server 578 of FIG. 5D ).

[0066] CPU 506 may include a CPU cluster or CPU complex (alternatively referred to as a "CCPLEX"). CPU 506 may include multiple cores and / or L2 caches. For example, in some embodiments, CPU 506 may include eight cores in a coherent multiprocessor configuration. In some embodiments, CPU 506 may include four dual-core clusters, each with its own dedicated L2 cache (e.g., a 2MBL2 cache). CPU 506 (e.g., CCPLEX) may be configured to support concurrent cluster operation allowing any combination of CPU 506 clusters to be active at any given time.

[0067] The CPU 506 may implement power management capabilities including one or more of the following features: individual hardware blocks may be automatically clock gated when idle to conserve dynamic power, each core clock may be gated when the core is not actively executing instructions by execution of WFI / WFE instructions, each core may be independently power gated, each core cluster may be independently clock gated when all cores are clock gated or power gated, and / or each core cluster may be independently power gated when all cores are power gated. The CPU 506 may further implement an enhanced algorithm for managing power states where allowed power states and expected wake-up times are specified and the hardware / microcode determines the best power state for entering the cores, clusters, and CCPLEXes. The processing cores may support simplified power state entry sequences in software where work is offloaded to the microcode.

[0068] The GPU 508 may include an integrated GPU (alternatively referred to herein as an "iGPU"). The GPU 508 may be programmable and efficient for parallel workloads. In some instances, the GPU 508 may use an enhanced tensor instruction set. The GPU 508 may include one or more streaming microprocessors, where each streaming microprocessor may include an L1 cache (e.g., an L1 cache having at least 96 KB storage capacity) and two or more of the streaming microprocessors may share a cache (e.g., an L2 cache having 512 KB storage capacity). In some embodiments, the GPU 508 may include at least eight streaming microprocessors. The GPU 508 may use a computational application programming interface (API). In addition, the GPU 508 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA's CUDA).

[0069] The GPU 508 may be power optimized for best performance in automotive and embedded use cases. For example, the GPU 508 may be fabricated on FinFETs (Fin field-effect transistors). However, this is not intended to be limiting and the GPU 508 may be fabricated using other semiconductor fabrication processes. Each streaming microprocessor may incorporate several mixed-precision processing cores partitioned into multiple blocks. For example, and without limitation, 64 PF32 cores and 32 PF64 cores may be partitioned into four processing blocks. In such an example, each processing block may be assigned 16 FP32 cores, 8 FP64 cores, 16 INT32 cores, two mixed-precision NVIDIA tensor cores for deep learning matrix operations, an L0 instruction cache, a warp scheduler, a dispatch unit, and / or a 64KB register file. In addition, the streaming microprocessor may include independent parallel integer and floating-point data paths to provide efficient execution of workloads having a mix of computational and addressing operations. Streaming microprocessors may include independent thread scheduling capabilities to allow finer grain synchronization and coordination among concurrent threads. Streaming microprocessors may include a combined L1 data cache and shared memory unit to improve performance while simplifying programming.

[0070] The GPU 508 may include high bandwidth memory (HBM) and / or a 16GB HBM2 memory subsystem to provide about 900GB / sec peak memory bandwidth in some instances. In some instances, synchronous graphics random-access memory (SGRAM), such as graphics double data rate type five synchronous random-access memory (GDDR5), may be used in addition to or in place of the HBM memory.

[0071] The GPU 508 may include unified memory technology including access counters to enable more accurate movement of memory pages to the processors that access them most frequently, thereby improving the efficiency of storage ranges shared between processors. In some instances, address translation service (ATS) support may be used to enable the GPU 508 to directly access the CPU 506 page tables. In such instances, when the GPU 508 memory management unit (MMU) experiences a miss, an address translation request may be sent to the CPU 506. In response, the CPU 506 may consult its page tables for a virtual-to-real mapping of the address and send the translation back to the GPU 508. As such, the unified memory technology may enable a single unified virtual address space for both the CPU 506 and GPU 508 memories, thereby simplifying GPU 508 programming and porting of applications to the GPU 508.

[0072] In addition, GPU 508 may include access counters that can record the frequency of accesses of GPU 508 to the memory of other processors. The access counters can help ensure that memory pages are moved to the physical memory of the processors that are accessing the pages most frequently.

[0073] The SoC 504 may include any number of caches 512, including those described herein. For example, the cache 512 may include an L3 cache available to both the CPU 506 and the GPU 508 (e.g., connected to both the CPU 506 and the GPU 508). The cache 512 may include a write-back cache that can record line state, such as by using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). The L3 cache may include 4 MB or more, depending on the embodiment, although smaller cache sizes may be used.

[0074] The SoC 504 may include an arithmetic logic unit (ALU) that may be utilized in performing processing for any of the various tasks or operations (e.g., processing DNNs) of the vehicle 500. In addition, the SoC 504 may include a floating point unit (FPU) (or other math co-processor or numeric co-processor type) for performing mathematical operations within the system. For example, the SoC 504 may include one or more FPUs integrated as execution units within the CPU 506 and / or GPU 508.

[0075] The SoC 504 may include one or more accelerators 514 (e.g., hardware accelerators, software accelerators, or a combination thereof). For example, the SoC 504 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. The large on-chip memory (e.g., 4MB of SRAM) may enable the hardware acceleration cluster to accelerate neural networks and other operations. The hardware acceleration cluster may be used to complement the GPU 508 and to offload some of the tasks of the GPU 508 (e.g., to free up more cycles of the GPU 508 to perform other tasks). As an example, the accelerator 514 may be used for target workloads that are stable enough to be suitable for acceleration (e.g., perception, convolutional neural networks (CNNs), etc.). As used herein, the term "CNN" may include all types of CNNs, including region-based or regional convolutional neural networks (RCNNs) and Faster RCNNs (e.g., as used for object detection).

[0076] The accelerator 514 (e.g., a hardware acceleration cluster) may include a deep learning accelerator (DLA). The DLA may include one or more tensor processing units (TPUs) that may be configured to provide an additional 10 trillion operations per second for deep learning applications and inference. The TPU may be an accelerator configured and optimized to perform image processing functions (e.g., CNN, RCNN, etc.). The DLA may further be optimized for a specific set of neural network types and floating point operations, as well as inference. The design of the DLA may provide more performance per millimeter than a general-purpose GPU, greatly exceeding the performance of a CPU. The TPU may perform several functions, including, for example, single instance convolution functions, supporting INT8, INT16, and FP16 data types for both features and weights, as well as post-processor functions.

[0077] The DLA can quickly and efficiently run neural networks, in particular CNNs, on processed or unprocessed data for any of a variety of functions, including but not limited to: CNNs for object identification and detection using data from camera sensors, CNNs for distance estimation using data from camera sensors, CNNs for emergency vehicle detection and identification using data from microphones, CNNs for face recognition and vehicle owner identification using data from camera sensors, and / or CNNs for security and / or safety related events.

[0078] The DLA can perform any function of the GPU 508, and by using an inference accelerator, for example, a designer can target either the DLA or the GPU 508 for any function. For example, a designer can focus on processing CNNs and floating point operations on the DLA, and offload other functions to the GPU 508 and / or other accelerators 514.

[0079] The accelerator 514 (e.g., hardware acceleration cluster) may include a programmable vision accelerator (PVA), which may alternatively be referred to herein as a computer vision accelerator. The PVA may be designed and configured to accelerate computer vision algorithms for advanced driver assistance systems (ADAS), autonomous driving, and / or augmented reality (AR) and / or virtual reality (VR) applications. The PVA may provide a balance between performance and flexibility. For example, each PVA may include, but is not limited to, any number of reduced instruction set computer (RISC) cores, direct memory access (DMA), and / or any number of vector processors, for example.

[0080] The RISC cores may interact with an image sensor (e.g., an image sensor of any of the cameras described herein), an image signal processor, and / or the like. Each RISC core may include any amount of memory. The RISC cores may use any of a number of protocols, depending on the embodiment. In some instances, the RISC cores may run a real-time operating system (RTOS). The RISC cores may be implemented using one or more integrated circuit devices, application specific integrated circuits (ASICs), and / or memory devices. For example, the RISC cores may include an instruction cache and / or tightly coupled RAM.

[0081] The DMA may allow components of the PVA to access system memory independent of the CPU 506. The DMA may support any number of features used to provide optimizations to the PVA, including but not limited to supporting multi-dimensional addressing and / or circular addressing. In some instances, the DMA may support up to six or more dimensions of addressing, which may include block width, block height, block depth, horizontal block stepping, vertical block stepping, and / or depth stepping.

[0082] The vector processor may be a programmable processor that may be designed to efficiently and flexibly execute computer vision algorithm programming and provide signal processing capabilities. In some instances, the PVA may include a PVA core and two vector processing subsystem partitions. The PVA core may include a processor subsystem, a DMA engine (e.g., two DMA engines), and / or other peripherals. The vector processing subsystem may act as the primary processing engine of the PVA and may include a vector processing unit (VPU), an instruction cache, and / or a vector memory (e.g., VMEM). The VPU core may include a digital signal processor, such as, for example, a single instruction, multiple data (SIMD), very long instruction word (VLIW) digital signal processor. The combination of SIMD and VLIW may increase throughput and speed.

[0083] Each vector processor may include an instruction cache and may be coupled to dedicated memory. As a result, in some instances, each vector processor may be configured to execute independently of other vector processors. In other instances, the vector processors included in a particular PVA may be configured to employ data parallelism. For example, in some embodiments, multiple vector processors included in a single PVA may execute the same computer vision algorithm, but on different regions of an image. In other instances, the vector processors included in a particular PVA may execute different computer vision algorithms simultaneously on the same image, or even execute different algorithms on sequential images or portions of an image. In particular, any number of PVAs may be included in a hardware accelerated cluster, and any number of vector processors may be included in each PVA. In addition, the PVAs may include additional error correcting code (ECC) memory to increase overall system security.

[0084] The accelerator 514 (e.g., a hardware acceleration cluster) may include a computer vision network-on-chip and SRAM to provide high bandwidth, low latency SRAM for the accelerator 514. In some instances, the on-chip memory may include, for example and without limitation, at least 4 MB of SRAM consisting of eight field configurable memory blocks that may be accessible by both the PVA and DLA. Each pair of memory blocks may include an advanced peripheral bus (APB) interface, configuration circuitry, controllers, and multiplexers. Any type of memory may be used. The PVA and DLA may access the memory through a backbone that provides the PVA and DLA with high speed access to the memory. The backbone may include a computer vision network-on-chip that interconnects the PVA and DLA to the memory (e.g., using the APB).

[0085] The computer vision network-on-chip may include an interface that determines, prior to transmission of any control signals / addresses / data, that both the PVA and DLA provide ready and valid signals. Such an interface may provide separate phases and separate channels for transmitting control signals / addresses / data, as well as burst type communication for continuous data transfer. This type of interface may follow ISO26262 or IEC61508 standards, although other standards and protocols may be used.

[0086] In some instances, the SoC 504 may include a real-time ray tracing hardware accelerator, such as described in U.S. Patent Application Serial No. 16 / 101,232, filed August 10, 2018. The real-time ray tracing hardware accelerator may be used to quickly and efficiently determine the location and scale of objects (e.g., within a world model) to generate real-time visualization simulations for RADAR signal interpretation, for acoustic propagation synthesis and / or analysis, for simulation of SONAR systems, for general wave propagation simulation, for comparison against LIDAR data for localization and / or other functions, and / or for other uses. In some examples, one or more tree traversal units (TTUs) may be used to perform one or more ray tracing related operations.

[0087] The accelerator 514 (e.g., a hardware accelerator cluster) has a variety of applications for autonomous driving. The PVA may be a programmable vision accelerator that can be used for critical processing stages in ADAS and autonomous vehicles. The capabilities of the PVA are suited to the domain of algorithms that require predictable processing at low power and low latency. In other words, the PVA works well with semi-dense or dense regular computations on small data sets that require predictable execution times with low latency and low power. Hence, in the context of a platform for autonomous vehicles, the PVA is designed to run classical computer vision algorithms, since the PVA is efficient in object detection and operating on integer computations.

[0088] For example, according to one embodiment of the present technology, the PVA is used to perform computer stereo vision. A semi-global matching based algorithm may be used in some instances, but this is not intended to be limiting. Many applications for Level 3-5 autonomous driving require motion estimation / stereo matching on the fly (e.g., structure from motion, pedestrian recognition, lane detection, etc.). The PVA can perform computer stereo vision functions with input from two monocular cameras.

[0089] In some instances, PVA may be used to perform dense optical flow by processing raw RADAR data (e.g., using a 4D Fast Fourier Transform) to provide processed RADAR. In other instances, PVA is used for time of flight depth processing, for example, by processing raw time of flight data to provide processed time of flight data.

[0090] DLA can be used to implement any type of network to enhance control and driving safety, including, for example, a neural network that outputs a measure of the confidence of each object detection. Such confidence value can be interpreted as a probability or as providing a relative "weight" of each detection compared to other detections. This confidence value allows the system to make further decisions regarding which detections should be considered true positive detections rather than false positive detections. For example, the system can set a confidence threshold and consider only detections above the threshold as true positive detections. In an automatic emergency braking (AEB) system, a false positive detection would cause the vehicle to automatically perform emergency braking, which is clearly undesirable. Therefore, only the most confident detections should be considered as triggers for AEB. DLA can implement a neural network that regresses the confidence value. The neural network may receive as its inputs at least some subset of parameters, such as bounding box dimensions, ground plane estimates obtained (e.g., from another subsystem), inertial measurement unit (IMU) sensor 566 outputs that correlate with vehicle 500 orientation, range, and 3D position estimates of objects obtained from the neural network and / or other sensors (e.g., LIDAR sensor 564 or RADAR sensor 560), and others.

[0091] The SoC 504 may include a data store 516 (e.g., memory). The data store 516 may be an on-chip memory of the SoC 504 and may store the neural network to be executed by the GPU and / or DLA. In some instances, the data store 516 may have a capacity large enough to store multiple instances of the neural network for redundancy and safety. The data store 512 may comprise an L2 or L3 cache 512. References to the data store 516 may include references to memory associated with the PVA, DLA, and / or other accelerators 514, as described herein.

[0092] The SoC 504 may include one or more processors 510 (e.g., embedded processors). The processors 510 may include a boot and power management processor, which may be a dedicated processor and subsystem for handling boot power and management capabilities and associated security enforcement. The boot and power management processor may be part of the SoC 504 boot sequence and may provide run-time power management services. The boot power and management processor may provide clock and voltage programming, assist with system low power state transitions, manage the SoC 504 thermal and temperature sensors, and / or manage the SoC 504 power states. Each temperature sensor may be implemented as a ring oscillator whose output frequency is proportional to temperature, and the SoC 504 may use the ring oscillator to detect the temperature of the CPU 506, the GPU 508, and / or the accelerator 514. If the temperature is determined to exceed a threshold, the boot and power management processor may enter a temperature fault routine, place the SoC 504 in a lower power state and / or place the vehicle 500 in a Chauffeur safe shutdown mode (e.g., bring the vehicle 500 to a safe shutdown).

[0093] The processor 510 may further include a set of embedded processors that may perform the functions of an audio processing engine. The audio processing engine may be an audio subsystem that allows full hardware support of multi-channel audio through multiple interfaces and a wide and flexible range of audio I / O interfaces. In some instances, the audio processing engine is a dedicated processor core that includes a digital signal processor with dedicated RAM.

[0094] The processor 510 may further include an always-on processor engine that can provide the necessary hardware features to support low power sensor management and wake use cases. The always-on processor engine may include a processor core, tightly coupled RAM, support peripherals (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0095] The processor 510 may further include a safety cluster engine that includes a processor subsystem dedicated to handling safety management of automotive applications. The safety cluster engine may include two or more processor cores, tightly coupled RAM, supporting peripherals (e.g., timers, interrupt controllers, etc.), and / or routing logic. In a safety mode, the two or more cores may operate in lockstep mode and function as a single core with comparison logic to detect any differences between their operations.

[0096] The processor 510 may further include a real-time camera engine, which may include a dedicated processor subsystem for handling real-time camera management.

[0097] The processor 510 may further include a high dynamic range signal processor, which may include an image signal processor, which is a hardware engine that is part of the camera processing pipeline.

[0098] The processor 510 may include a video image compositor, which may be a processing block (e.g., implemented in a microprocessor) that implements video post-processing functions required by the video playback application to produce a final image for the player window. The video image compositor may perform lens distortion correction on the wide-view camera 570, on the surround camera 574, and / or on the in-cabin surveillance camera sensor. The in-cabin surveillance camera sensor is preferably monitored by a neural network running on another instance of the advanced SoC, configured to identify in-cabin events and respond appropriately. The in-cabin system may perform lip reading to activate cellular service and make phone calls, dictate emails, change the vehicle's destination, activate or change the vehicle's infotainment system and settings, or provide voice-activated web surfing. Certain features are only available to the driver when operating in autonomous mode and are disabled otherwise.

[0099] The video image synthesizer may include enhanced temporal noise reduction for both spatial and temporal noise reduction. For example, when motion occurs in the video, the noise reduction reduces the weight of information provided by adjacent frames and appropriately weights the spatial information. When an image or part of an image does not contain motion, the temporal noise reduction performed by the video image synthesizer may use information from previous images to reduce noise in the current image.

[0100] The video image composer may also be configured to perform stereo rectification on the input stereo lens frames. The video image composer may further be used for user interface compositing when the operating system desktop is in use and the GPU 508 is not required to continuously render new surfaces. Even when the GPU 508 is powered on and actively performing 3D rendering, the video image composer may be used to offload the GPU 508 for improved performance and responsiveness.

[0101] The SoC504 may further include a mobile industry processor interface (MIPI) camera serial interface for receiving video and input from a camera, a high-speed interface, and / or a video input block that may be used for camera and related pixel input functions. The SoC504 may further include an input / output controller that may be controlled by software and that may be used to receive I / O signals that are not committed to a specific role.

[0102] The SoC 504 may further include a wide range of peripheral interfaces to enable peripherals, audio codecs, power management, and / or communication with other devices. The SoC 504 may be used to process data from cameras (e.g., connected via gigabit multimedia serial links and Ethernet), sensors (e.g., LIDAR sensor 564, RADAR sensor 560, etc., which may be connected via Ethernet), data from bus 502 (e.g., speed of vehicle 500, steering wheel position, etc.), and data from GNSS sensor 558 (e.g., connected via Ethernet or CAN bus). The SoC 504 may further include a dedicated high-performance mass storage controller, which may include its own DMA engine and may be used to offload the CPU 506 from routine data management tasks.

[0103] The SoC504 may be an end-to-end platform with a flexible architecture that spans levels 3-5 of automation, thereby providing a comprehensive functional safety architecture that leverages and efficiently uses computer vision and ADAS techniques for diversity and redundancy, and provides a platform for a flexible, reliable driving software stack along with deep learning tools. The SoC504 may be faster, more reliable, and more energy- and space-efficient than traditional systems. For example, when the accelerator 514 is combined with the CPU 506, the GPU 508, and the data store 516, the SoC504 may provide a fast and efficient platform for levels 3-5 of autonomous vehicles.

[0104] Thus, the present technology provides capabilities and functionality that cannot be achieved by conventional systems. For example, computer vision algorithms may be executed on a CPU, which may be configured using a high-level programming language, such as the C programming language, to execute a wide variety of processing algorithms across a wide variety of visual data. However, CPUs often cannot meet the performance requirements of many computer vision applications, such as those related to execution time and power consumption. In particular, many CPUs cannot execute complex object detection algorithms in real time, which is a requirement for in-vehicle ADAS applications and for practical Level 3-5 autonomous vehicles.

[0105] In contrast to conventional systems, by providing a CPU complex, a GPU complex, and a hardware acceleration cluster, the techniques described herein allow multiple neural networks to run simultaneously and / or sequentially and the results to be combined to enable Level 3-5 autonomous driving capabilities. For example, the CNN running on the DLA or dGPU (e.g., GPU520) can include text and word recognition that allows the supercomputer to read and understand traffic signs, including signs for which the neural network was not specifically trained. The DLA can further include neural networks that can identify, interpret, and provide a semantic understanding of the signs and pass the semantic understanding to a route planning module running on the CPU complex.

[0106] As another example, multiple neural networks may be run simultaneously, as required for level 3, 4, or 5 driving. For example, a warning sign consisting of "Caution: Flashing lights indicate icy conditions" along with a lightning flash may be interpreted by several neural networks, independently or collectively. The sign itself may be identified as a traffic sign by a first deployed neural network (e.g., a trained neural network), and the text "Flashing lights indicate icy conditions" may be interpreted by a second deployed neural network that informs the vehicle's route planning software (preferably running on the CPU complex) that icy conditions exist when a flashing light is detected. The flashing light may be identified by running a third deployed neural network through multiple frames, informing the vehicle's route planning software of the presence (or absence) of the flashing light. All three neural networks may be run simultaneously, such as within the DLA and / or on the GPU 508.

[0107] In some instances, a CNN for facial recognition and vehicle owner identification can use data from the camera sensors to identify the presence of a legitimate driver and / or owner of the vehicle 500. An always-on sensor processing engine can be used to unlock the vehicle and turn on the lights when the owner approaches the driver's door, and in security mode, to disable vehicle operation when the owner leaves the vehicle. In this manner, the SoC 504 provides security against theft and / or carjacking.

[0108] In another example, a CNN for emergency vehicle detection and identification can detect and identify emergency vehicle sirens using data from microphone 596. In contrast to conventional systems that use general classifiers to detect sirens and manually extract features, SoC 504 uses CNNs for classification of environmental and urban sounds, as well as classification of visual data. In a preferred embodiment, the CNN running on the DLA is trained to identify the relative terminal velocity of emergency vehicles (e.g., by using the Doppler effect). The CNN can also be trained to identify emergency vehicles specific to the local area in which the vehicle is operating, as identified by the GNSS sensor 558. Thus, for example, when operating in Europe, the CNN will attempt to detect European sirens, and when in the United States, the CNN will attempt to identify only North American sirens. After an emergency vehicle is detected, a control program can be used to perform emergency vehicle safety routines, such as slowing the vehicle down, stopping at the side of the road, parking the vehicle, and / or idling the vehicle, with the assistance of ultrasonic sensor 562, until the emergency vehicle has passed.

[0109] The vehicle may include a CPU 518 (e.g., a separate CPU, or a dCPU) that may be coupled to the SoC 504 via a high-speed interconnect (e.g., PCIe). The CPU 518 may include, for example, an X86 processor. The CPU 518 may be used to perform any of a variety of functions, including, for example, reconciling potentially inconsistent results between the ADAS sensors and the SoC 504, and / or monitoring the status and health of the controller 536 and / or the infotainment SoC 530.

[0110] Vehicle 500 may include a GPU 520 (e.g., a discrete GPU, or a dGPU) that may be coupled to SoC 504 via a high-speed interconnect (e.g., NVIDIA's NVLINK). GPU 520 may provide additional artificial intelligence capabilities, such as by running redundant and / or different neural networks, and may be used to train and / or update neural networks based on inputs (e.g., sensor data) from sensors of vehicle 500.

[0111] The vehicle 500 may further include a network interface 524, which may include one or more wireless antennas 526 (e.g., one or more wireless antennas for different communication protocols, such as a cellular antenna, a Bluetooth antenna, etc.). The network interface 524 may be used to enable wireless connections with the cloud over the Internet (e.g., with a server 578 and / or other network devices), with other vehicles, and / or with computing devices (e.g., passenger client devices). To communicate with other vehicles, a direct link may be established between the two vehicles and / or an indirect link may be established (e.g., through a network and via the Internet). A direct link may be provided using a vehicle-to-vehicle communication link. The vehicle-to-vehicle communication link may provide the vehicle 500 information about vehicles in close proximity to the vehicle 500 (e.g., vehicles in front of, beside, and / or behind the vehicle 500). This function may be part of a cooperative adaptive cruise control function of the vehicle 500.

[0112] The network interface 524 may include a SoC that provides modulation and demodulation functions and enables the controller 536 to communicate over a wireless network. The network interface 524 may include a radio frequency front end for upconversion from baseband to radio frequency and downconversion from radio frequency to baseband. The frequency conversion may be performed through well known processes and / or may be performed using a superheterodyne process. In some instances, the radio frequency front end functions may be provided by a separate chip. The network interface may include wireless functions for communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-Wave, ZigBee, LoRaWAN, and / or other wireless protocols.

[0113] The vehicle 500 may further include a data store 528, which may include off-chip (e.g., off-SoC 504) storage. The data store 528 may include one or more memory elements, including RAM, SRAM, DRAM, VRAM, flash, hard disk, and / or other components and / or devices capable of storing at least one bit of data.

[0114] The vehicle 500 may further include a GNSS sensor 558. The GNSS sensor 558 (e.g., a GPS and / or an assisted GPS sensor) aids in mapping, perception, occupancy grid generation, and / or route planning functions. Any number of GNSS sensors 558 may be used, including, but not limited to, a GPS using a USB connector with an Ethernet to serial (RS-232) bridge.

[0115] The vehicle 500 may further include a RADAR sensor 560. The RADAR sensor 560 may be used by the vehicle 500 for long-range vehicle detection, even in darkness and / or severe weather conditions. The RADAR functional safety level may be ASIL B. In some instances, the RADAR sensor 560 may use the CAN and / or bus 502 for control and to access object tracking data (e.g., to transmit data generated by the RADAR sensor 560), with access to Ethernet to access raw data. A wide variety of RADAR sensor types may be used. For example, and without limitation, the RADAR sensor 560 may be suitable for front, rear, and side RADAR use. In some instances, a pulsed Doppler RADAR sensor is used.

[0116] The RADAR sensor 560 may include different configurations, such as long range with a narrow field of view, short range with a wide field of view, and short range side coverage. In some instances, the long range RADAR may be used for adaptive cruise control functions. Long range RADAR systems may provide a wide field of view achieved by two or more independent scans, such as within a 250m range. The RADAR sensor 560 may help distinguish between static and moving objects and may be used by ADAS systems for emergency brake assist and forward collision warning. The long range RADAR sensor may include a monostatic multimodal RADAR with multiple (e.g., six or more) fixed RADAR antennas and high speed CAN and FlexRay interfaces. In one instance with six antennas, the center four antennas may create a focused beam pattern designed to record the surroundings of the vehicle 500 at high speeds with minimal interference from traffic in adjacent lanes. The other two antennas may increase the field of view, allowing for quick detection of vehicles entering or leaving the lane of the vehicle 500.

[0117] As an example, a mid-range RADAR system may include a range of up to 560m (front) or 80m (rear) and a field of view of up to 42 degrees (front) or 550 degrees (rear). A short-range RADAR system may include, but is not limited to, a RADAR sensor designed to be mounted on either end of the rear bumper. When mounted on either end of the rear bumper, such a RADAR sensor system can create two beams that constantly monitor the blind spots behind and next to the vehicle.

[0118] Short-range RADAR systems may be used in ADAS systems for blind spot detection and / or lane change assist.

[0119] The vehicle 500 may further include ultrasonic sensors 562. The ultrasonic sensors 562, which may be located at the front, rear, and / or sides of the vehicle 500, may be used for parking assist and / or for creating and updating an occupancy grid. A wide variety of ultrasonic sensors 562 may be used, with different ultrasonic sensors 562 being used for different ranges of detection (e.g., 2.5m, 4m). The ultrasonic sensors 562 may operate at a functional safety level of ASIL B.

[0120] The vehicle 500 may include a LIDAR sensor 564. The LIDAR sensor 564 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. The LIDAR sensor 564 may be functional safety level ASIL B. In some instances, the vehicle 500 may include multiple (e.g., 2, 4, 6, etc.) LIDAR sensors 564 that may use Ethernet (e.g., to provide data to a Gigabit Ethernet switch).

[0121] In some instances, the LIDAR sensor 564 may have the ability to provide a list of objects and their distances in a 360-degree field of view. A commercially available LIDAR sensor 564 may have an advertised range of about 500m, for example, with an accuracy of 2cm to 3cm, and with support for a 500Mbps Ethernet connection. In some instances, one or more non-protruding LIDAR sensors 564 may be used. In such instances, the LIDAR sensor 564 may be implemented as a small device that may be integrated into the front, rear, sides, and / or corners of the vehicle 500. In such instances, the LIDAR sensor 564 may have a range of 200m even for low-reflecting objects and provide up to a 520-degree horizontal and 35-degree vertical field of view. A front-mounted LIDAR sensor 564 may be configured for a horizontal field of view between 45 and 135 degrees.

[0122] In some instances, LIDAR technology such as 3D flash LIDAR may also be used. 3D flash LIDAR uses a laser flash as a transmitter to illuminate the surroundings of the vehicle up to about 200 m. The flash LIDAR unit includes a receptor that records the laser pulse transit time and the reflected light on each pixel, which in turn corresponds to the range from the vehicle to the object. Flash LIDAR may allow a highly accurate and undistorted image of the surroundings to be generated with every laser flash. In some instances, four flash LIDAR sensors may be deployed, one on each side of the vehicle 500. Available 3D flash LIDAR systems include solid-state 3D steering array LIDAR cameras that have no moving parts other than the blower (e.g., non-scanning LIDAR devices). Flash LIDAR devices may use 5 nanosecond Class I (eye-safe) laser pulses per frame and may capture reflected laser light in the form of a 3D range point cloud and coregistered intensity data. By using flash LIDAR, and because flash LIDAR is a solid-state device with no moving parts, the LIDAR sensor 564 may be less susceptible to motion blur, vibration, and / or shock.

[0123] The vehicle may further include an IMU sensor 566. In some instances, the IMU sensor 566 may be positioned at the center of the rear axle of the vehicle 500. The IMU sensor 566 may include, for example, but not limited to, an accelerometer, a magnetometer, a gyroscope, a magnetic compass, and / or other sensor types. In some instances, such as in a 6-axis application, the IMU sensor 566 may include an accelerometer and a gyroscope, while in a 9-axis application, the IMU sensor 566 may include an accelerometer, a gyroscope, and a magnetometer.

[0124] In some embodiments, the IMU sensor 566 may be implemented as a miniature, high-performance GPS-Aided Inertial Navigation System (GPS / INS) that combines micro-electro-mechanical system (MEMS) inertial sensors, highly sensitive GPS receivers, and advanced Kalman filtering algorithms to provide estimates of position, velocity, and attitude. As such, in some instances, the IMU sensor 566 may enable the vehicle 500 to estimate heading without requiring input from a magnetic sensor by directly observing and correlating changes in velocity from the GPS to the IMU sensor 566. In some instances, the IMU sensor 566 and the GNSS sensor 558 may be combined in a single integrated unit.

[0125] The vehicle may include microphones 596 placed in and / or around the vehicle 500. The microphones 596 may be used for emergency vehicle detection and identification, among other things.

[0126] The vehicle may further include any number of camera types, including stereo cameras 568, wide view cameras 570, infrared cameras 572, surround cameras 574, long and / or mid-range cameras 598, and / or other camera types. The cameras may be used to capture image data around the entire exterior of the vehicle 500. The type of cameras used depends on the embodiment and requirements of the vehicle 500, and any combination of camera types may be used to achieve the required coverage around the vehicle 500. Additionally, the number of cameras may vary depending on the embodiment. For example, the vehicle may include six cameras, seven cameras, ten cameras, twelve cameras, and / or another number of cameras. The cameras may support, by way of example only, Gigabit Multimedia Serial Link (GMSL) and / or Gigabit Ethernet. Each camera is described in further detail herein with respect to FIGS. 5A and 5B.

[0127] The vehicle 500 may further include a vibration sensor 542. The vibration sensor 542 may measure vibrations of vehicle components, such as an axle. For example, a change in vibration may indicate a change in the surface of the road. In another example, when two or more vibration sensors 542 are used, the difference in vibration may be used to determine friction or slippage of the road surface (e.g., when the difference in vibration is between a powered axle and a free-running axle).

[0128] The vehicle 500 may include an ADAS system 538. In some instances, the ADAS system 538 may include a SoC. The ADAS system 538 may include autonomous / adaptive / automatic cruise control (ACC), cooperative adaptive cruise control (CACC), forward crash warning (FCW), automatic emergency braking (AEB), lane departure warning (LDW), lane keep assist (LKA), blind spot warning (BSW), rear cross-traffic warning (RCTW), collision warning system (CWS), lane centering (LC), and / or other features and functions.

[0129] The ACC system may use a RADAR sensor 560, a LIDAR sensor 564, and / or a camera. The ACC system may include longitudinal ACC and / or lateral ACC. Longitudinal ACC monitors and controls the distance to the vehicle directly ahead of the vehicle 500 and automatically adjusts the vehicle speed to maintain a safe distance from the vehicle ahead. Lateral ACC performs distance keeping and advises the vehicle 500 to change lanes when necessary. Lateral ACC is related to other ADAS applications such as LCA and CWS.

[0130] CACC uses information from other vehicles, which may be received from other vehicles via a wireless link via the network interface 524 and / or the wireless antenna 526, or indirectly via a network connection (e.g., via the Internet). A direct link may be provided by a vehicle-to-vehicle (V2V) communication link, while an indirect link may be an infrastructure-to-vehicle (I2V) communication link. In general, a V2V communication concept provides information about the immediately preceding vehicle (e.g., the vehicle directly ahead of the vehicle 500, in the same lane as the vehicle 500), while an I2V communication concept provides information about the traffic further ahead. A CACC system may include either or both I2V and V2V information sources. Given the information of the vehicles ahead of the vehicle 500, CACC may be more reliable and may potentially allow traffic to flow more smoothly and reduce congestion on the roads.

[0131] The FCW system is designed to warn the driver of hazards so that the driver can take corrective action. The FCW system uses a forward-facing camera and / or RADAR sensor 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback such as a display, speaker, and / or vibration components. The FCW system can provide warnings in the form of audio, visual alerts, vibrations, and / or quick brake pulses.

[0132] An AEB system can detect an imminent forward collision with another vehicle or other object and automatically apply the brakes if the driver does not take corrective action within specified time or distance parameters. The AEB system can use a forward-facing camera and / or RADAR sensor 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC. When the AEB system detects a hazard, the AEB system typically first alerts the driver to take corrective action to avoid the collision, and if the driver does not take corrective action, the AEB system can automatically apply the brakes as part of an effort to prevent, or at least mitigate, the effects of the predicted collision. The AEB system can include techniques such as Dynamic Brake Support and / or Collision Imminent Braking.

[0133] The LDW system provides visual, audible, and / or tactile warnings, such as vibrations in the steering wheel or seat, to alert the driver when the vehicle 500 crosses a lane marking. The LDW system is not activated when the driver indicates an intentional lane departure by activating a turn signal. The LDW system may use a forward-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback, such as a display, speaker, and / or vibration components.

[0134] The LKA system is a modification of the LDW system, which provides steering input or braking to correct the vehicle 500 if it begins to drift out of its lane.

[0135] The BSW system detects and warns the vehicle driver in the vehicle's blind spot. The BSW system can provide visual, audible, and / or tactile warnings to indicate that merging or changing lanes is unsafe. The system can provide additional warnings when the driver uses a turn signal. The BSW system can use rear-facing cameras and / or RADAR sensors 560 coupled to dedicated processors, DSPs, FPGAs, and / or ASICs electrically coupled to driver feedback, e.g., displays, speakers, and / or vibration components.

[0136] The RCTW system may provide visual, audible, and / or tactile notifications when an object is detected outside the range of the rear camera when the vehicle 500 is backing up. Some RCTW systems include AEB to ensure vehicle brakes are applied to avoid a collision. The RCTW system may use one or more rear-facing RADAR sensors 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, electrically coupled to driver feedback, e.g., a display, speaker, and / or vibration components.

[0137] Because conventional ADAS systems alert the driver and allow the driver to determine whether a safety condition truly exists and act accordingly, conventional ADAS systems can be prone to producing false positive results that are usually not catastrophic but can be annoying and distracting to the driver. However, in an autonomous vehicle 500, the vehicle 500 itself must decide whether to listen to the results from the primary computer or the secondary computer (e.g., the first controller 536 or the second controller 536) when the results are conflicting. For example, in some embodiments, the ADAS system 538 may be a backup and / or secondary computer to provide perception information to a backup computer rationality module. The backup computer rationality monitor may run redundant and diverse software on hardware components to detect impairments in perception and dynamic driving tasks. Output from the ADAS system 538 may be provided to a supervisory MCU. When the outputs from the primary and secondary computers conflict, the supervisory MCU must decide how to reconcile the conflict to ensure safe operation.

[0138] In some instances, the primary computer may be configured to provide a reliability score to the overseer MCU indicating the reliability of the primary computer in a selected outcome. If the reliability score exceeds a threshold, the overseer MCU may follow the instructions of the primary computer regardless of whether the secondary computers provide conflicting or inconsistent results. If the reliability score does not meet the threshold, and if the primary and secondary computers show different (e.g., conflicting) results, the overseer MCU may arbitrate between the computers to determine the appropriate outcome.

[0139] The supervisory MCU may be configured to execute a neural network that is trained and configured to determine conditions under which the secondary computer provides a false alarm based on the outputs from the primary and secondary computers. Thus, the neural network in the supervisory MCU may learn when the output of the secondary computer may be trusted and when it may not be trusted. For example, when the secondary computer is a RADAR-based FCW system, the neural network in the supervisory MCU may learn when the FCW identifies a metal object that is not actually a hazard, such as a sewer grate or manhole cover, that triggers an alarm. Similarly, when the secondary computer is a camera-based LDW system, the neural network in the supervisory MCU may learn to ignore the LDW when a bicyclist or pedestrian is present and lane departure is, in fact, the safest maneuver. In embodiments that include a neural network executing on the supervisory MCU, the supervisory MCU may include at least one of a DLA or a GPU suitable for executing the neural network with associated memory. In a preferred embodiment, the director MCU may comprise and / or be included as a component of the SoC 504 .

[0140] In other instances, the ADAS system 538 may include a secondary computer that performs ADAS functions using classical rules of computer vision. As such, the secondary computer may use classical computer vision rules (if-then) and the presence of a neural network in the supervisory MCU may improve reliability, safety and performance. For example, the diverse implementations and intentional non-identity may make the overall system more fault-tolerant, especially to failures caused by software (or software-hardware interface) functions. For example, if there is a software bug or error in the software running on the primary computer and non-identical software code running on the secondary computer provides the same overall result, the supervisory MCU may have greater confidence that the overall result is correct and that a bug in the software or hardware on the primary computer has not caused a critical error.

[0141] In some instances, the output of the ADAS system 538 may be fed to the perception block of the primary computer and / or the dynamic driving task block of the primary computer. For example, if the ADAS system 538 indicates a forward collision warning due to an object directly ahead, the perception block may use this information when identifying the object. In other instances, the secondary computer may have its own neural network that is trained as described herein, thus reducing the risk of false positives.

[0142] Vehicle 500 may further include an infotainment SoC 530 (e.g., an in-vehicle infotainment system (IVI)). Although shown and described as an SoC, the infotainment system need not be an SoC and may include two or more separate components. Infotainment SoC 530 may include a combination of hardware and software that may be used to provide audio (e.g., music, personal digital assistant, navigation instructions, news, radio, etc.), video (e.g., TV, movies, streaming, etc.), telephony (e.g., hands-free calling), network connectivity (e.g., LTE, Wi-Fi, etc.), and / or information services (e.g., navigation system, rear park assist, wireless data system, vehicle related information such as fuel level, total distance traveled, brake fuel level, oil level, door open / close, air filter information, etc.) to vehicle 500. For example, the infotainment SoC 530 may be a radio, a disc player, a navigation system, a video player, USB and Bluetooth connectivity, a car computer, in-car entertainment, Wi-Fi, steering wheel audio controls, hands-free voice control, a heads-up display (HUD), an HMI display 534, a telematics device, a control panel (e.g., for controlling and / or interacting with various components, features, and / or systems), and / or other components. The infotainment SoC 530 may further be used to provide information (e.g., visual and / or audible) to a user of the vehicle, such as information from an ADAS system 538, autonomous driving information such as planned vehicle maneuvers, trajectory, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.), and / or other information.

[0143] The infotainment SoC 530 may include GPU functionality. The infotainment SoC 530 may communicate with other devices, systems, and / or components of the vehicle 500 via the bus 502 (e.g., CAN bus, Ethernet, etc.). In some instances, the infotainment SoC 530 may be coupled to the supervisor MCU such that the infotainment system's GPU may perform some self-drive functions in the event that the primary controller 536 (e.g., the vehicle's 500 primary and / or backup computer) fails. In such instances, the infotainment SoC 530 may place the vehicle 500 in a Chauffeur safe shutdown mode, as described herein.

[0144] The vehicle 500 may further include an instrument cluster 532 (e.g., a digital dash, an electronic instrument cluster, a digital instrument panel, etc.). The instrument cluster 532 may include a controller and / or a supercomputer (e.g., a separate controller or a supercomputer). The instrument cluster 532 may include a set of instruments such as a speedometer, a fuel level, an oil pressure, a tachometer, an odometer, a turn signal, a gear shift position indicator, a seat belt warning light, a parking brake warning light, an engine malfunction light, an airbag (SRS) system information, lighting controls, safety system controls, navigation information, etc. In some instances, information may be displayed and / or shared between the infotainment SoC 530 and the instrument cluster 532. In other words, the instrument cluster 532 may be included as part of the infotainment SoC 530, or vice versa.

[0145] 5D is a system diagram of communication between a cloud-based server and an example autonomous vehicle 500 of FIG. 5A according to some embodiments of the disclosure. System 576 may include a server 578, a network 590, and a vehicle including vehicle 500. Server 578 may include multiple GPUs 584(A)-584(H) (collectively referred to herein as GPUs 584), PCIe switches 582(A)-582(H) (collectively referred to herein as PCIe switches 582), and / or CPUs 580(A)-580(B) (collectively referred to herein as CPUs 580). GPUs 584, CPUs 580, and PCIe switches may be interconnected with a high-speed interconnect, such as, but not limited to, an NVLink interface 588 developed by NVIDIA and / or a PCIe connection 586. In some instances, the GPUs 584 are connected via an NVLink and / or NVSwitch SoC, and the GPUs 584 and PCIe switch 582 are connected via a PCIe interconnect. Although eight GPUs 584, two CPUs 580, and two PCIe switches are illustrated, this is not intended to be limiting. Depending on the embodiment, each server 578 may include any number of GPUs 584, CPUs 580, and / or PCIe switches. For example, the servers 578 may each include 8, 16, 32, and / or more GPUs 584.

[0146] Server 578 may receive image data from the vehicle over network 590, the image data representing images showing unexpected or changed road conditions, such as recently started road construction. Server 578 may transmit neural network 592, updated neural network 592, and / or map information 594, including information about traffic and road conditions, to the vehicle over network 590. Updates to map information 594 may include updates to HD map 522, such as information about construction sites, potholes, detours, flooding, and / or other obstacles. In some instances, neural network 592, updated neural network 592, and / or map information 594 may have arisen from new training and / or experience represented in data received from any number of vehicles in the environment and / or based on training performed at a data center (e.g., using server 578 and / or other servers).

[0147] The server 578 may be used to train a machine learning model (e.g., a neural network) based on the training data. The training data may be generated by the vehicle and / or generated in a simulation (e.g., using a game engine). In some instances, the training data is tagged (e.g., if the neural network benefits from supervised learning) and / or undergoes other pre-processing, while in other instances, the training data is not tagged and / or pre-processed (e.g., if the neural network does not require supervised learning). The training may be performed according to any one or more classes of machine learning techniques, including, but not limited to, the following classes: supervised training, semi-supervised training, unsupervised training, self-learning, reinforcement learning, federated learning, transfer learning, feature learning (including principal component and cluster analysis), multi-linear subspace learning, manifold learning, representation learning (including preliminary dictionary learning), rule-based machine learning, anomaly detection, and variations or combinations thereof. After the machine-learned model has been traced, the machine-learned model may be used by the vehicle (e.g., transmitted to the vehicle via network 590) and / or the machine-learned model may be used by server 578 to remotely monitor the vehicle.

[0148] In some instances, server 578 can receive data from vehicles and apply the data to state-of-the-art real-time neural networks for real-time intelligent inference. Server 578 can include deep learning supercomputers and / or dedicated AI computers powered by GPU 584, such as DGX and DGX Station machines developed by NVIDIA. However, in some instances, server 578 can include a deep learning infrastructure that uses only CPU-powered data centers.

[0149] The deep learning infrastructure of server 578 may be capable of rapid real-time inference and may use that capability to evaluate and validate the health of the processor, software, and / or associated hardware within vehicle 500. For example, the deep learning infrastructure may receive periodic updates from vehicle 500, such as a sequence of images and / or objects where vehicle 500 was located within the sequence of images (e.g., via computer vision and / or other machine learning object classification techniques). The deep learning infrastructure may run its own neural networks to identify objects and compare them to objects identified by vehicle 500, and if the results do not match and the infrastructure concludes that the AI ​​within vehicle 500 is not functioning properly, server 578 may send a signal to vehicle 500 that infers control, notifies passengers, and commands the failsafe computer of vehicle 500 to complete a safe parking maneuver.

[0150] For inference, the server 578 may include a GPU 584 and one or more programmable inference accelerators (e.g., NVIDIA's TensorRT). The combination of a GPU-powered server and inference acceleration can enable real-time responsiveness. In other instances, such as when less performance is required, servers powered by CPUs, FPGAs, and other processors may be used for inference.

[0151] Exemplary Computing Device 6 is a block diagram of an example computing device 600 suitable for use in implementing some embodiments of the present disclosure. The computing device 600 may include a bus 602 that indirectly or directly couples the following devices: memory 604, one or more central processing units (CPUs) 606, one or more graphic processing units (GPUs) 608, a communication interface 610, input / output (I / O) ports 612, input / output components 614, a power supply 616, and one or more presentation components 618 (e.g., a display).

[0152] Although the various blocks in FIG. 6 are shown connected by lines via bus 602, this is not intended to be limiting and is merely for clarity. For example, in some embodiments, a presentation component 618, such as a display device, may be considered an I / O component 614 (e.g., where the display is a touch screen). As another example, the CPU 606 and / or the GPU 608 may include memory (e.g., memory 604 may represent a storage device in addition to the memory of the GPU 608, the CPU 606, and / or other components). In other words, the computing devices of FIG. 6 are merely exemplary. Categories such as "workstations," "servers," "laptops," "desktops," "tablets," "client devices," "mobile devices," "handheld devices," "gaming consoles," "electronic control units (ECUs)," "virtual reality systems," and / or other device or system types are all intended to be within the scope of the computing devices of FIG. 6 and therefore are not to be distinguished.

[0153] Bus 602 may represent one or more buses, such as an address bus, a data bus, a control bus, or a combination thereof. Bus 602 may include one or more bus types, such as an industry standard architecture (ISA) bus, an extended industry standard architecture (EISA) bus, a video electronics standards association (VESA) bus, a peripheral component interconnect (PCI) bus, a peripheral component interconnect express (PCIe) bus, and / or another type of bus.

[0154] Memory 604 may include any of a variety of computer readable media. Computer readable media may be any available media that can be accessed by computing device 600. Computer readable media may include both volatile and nonvolatile media, and removable and non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media.

[0155] Computer storage media may include both volatile and nonvolatile media and / or removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, and / or other data types. For example, memory 604 may store computer readable instructions (e.g., representing programs and / or program elements), such as an operating system. Computer storage media may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and that may be accessed by computing device 600. As used herein, computer storage media does not include the signals themselves.

[0156] Communication media may embody computer-readable instructions, data structures, program modules, and / or other data types in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term "modulated data signal" may refer to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer-readable media.

[0157] The CPU 606 may be configured to execute at least some of the computer readable instructions to control one or more components of the computing device 600 to perform one or more of the methods and / or processes described herein. The CPU 606 may include one or more (e.g., 1, 2, 4, 8, 28, 72, etc.) cores each capable of simultaneously processing multiple software threads. The CPU 606 may include any type of processor and may include different types of processors depending on the type of computing device 600 implemented (e.g., a processor with fewer cores for a mobile device and a processor with more cores for a server). For example, depending on the type of computing device 600, the processor may be an ARM processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). The computing device 600 may include one or more CPUs 606 in one or more microprocessors or auxiliary coprocessors, such as computational coprocessors.

[0158] GPU 608 may be used by computing device 600 to render graphics (e.g., 3D graphics). GPU 608 may include hundreds or thousands of cores capable of processing hundreds or thousands of software threads simultaneously. GPU 608 may generate pixel data for an output image in response to a rendering command (e.g., a rendering command from CPU 606 received via a host interface). GPU 608 may include graphics memory, e.g., display memory, for storing the pixel data or any other suitable data, e.g., GPGPU data. The display memory may be included as part of memory 604. GPU 608 may include two or more GPUs operating in parallel (e.g., via links). When coupled together, each GPU 608 may generate pixel data for a different portion of an output image or for different output images (e.g., a first GPU for a first image and a second GPU for a second image). Each GPU may include its own memory or may share memory with the other GPUs.

[0159] In instances where the computing device 600 does not include a GPU 608, the CPU 606 may be used to render graphics.

[0160] The communications interface 610 may include one or more receivers, transmitters, and / or transceivers that enable the computing device 700 to communicate with other computing devices over electronic communications networks, including wired and / or wireless communications. The communications interface 610 may include components and functionality to enable communication over any of a number of different networks, such as a wireless network (e.g., Wi-Fi, Z-Wave, Bluetooth, Bluetooth LE, ZigBee, etc.), a wired network (e.g., communicating over Ethernet), a low power wide area network (e.g., LoRaWAN, SigFox, etc.), and / or the Internet.

[0161] The I / O ports 612 may enable the computing device 600 to be logically coupled to other devices, including I / O components 614, presentation components 618, and / or other components, some of which may be built-in (e.g., integrated) to the computing device 600. Exemplary I / O components 614 include a microphone, a mouse, a keyboard, a joystick, a game pad, a game controller, a satellite dish, a scanner, a printer, a wireless device, and the like. The I / O components 614 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological input generated by a user. In some cases, the input may be sent to an appropriate network element for further processing. The NUI may implement any combination of voice recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition on and next to the screen, air gestures, head and eye tracking, and touch recognition in conjunction with the display of the computing device 600 (as described in more detail below). Computing device 600 may include a depth camera, such as a stereoscopic camera system, an infrared camera system, an RGB camera system, touch screen technology, and combinations thereof, for gesture detection and recognition. Additionally, computing device 600 may include an accelerometer or gyroscope (e.g., as part of an inertia measurement unit (IMU)) to enable detection of motion. In some instances, the output of the accelerometer or gyroscope may be used by computing device 600 to render immersive augmented or virtual reality.

[0162] The power supply 616 may include a hardwired power supply, a battery power supply, or a combination thereof. The power supply 616 may provide power to the computing device 600 to enable the components of the computing device 600 to operate.

[0163] The presentation component 618 may include a display (e.g., a monitor, a touch screen, a television screen, a heads-up display (HUD), other display types, or a combination thereof), speakers, and / or other presentation components. The presentation component 618 can receive data from other components (e.g., GPU 608, CPU 606, etc.) and output data (e.g., as images, video, sound, etc.).

[0164] The present disclosure may be described in the general context of computer code or machine usable instructions, including computer executable instructions, such as program modules, being executed by a computer or other machine, such as a personal digital assistant or other handheld device. Generally, program modules, including routines, programs, objects, components, data structures, etc., refer to code that performs particular tasks or implements particular abstract data types. The present disclosure may be implemented in a variety of configurations, including handheld devices, consumer electronics, general purpose computers, more specialized computing devices, etc. The present disclosure may also be implemented in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.

[0165] As used herein, the statement "and / or" with respect to two or more elements should be interpreted to mean only one element or a combination of elements. For example, "element A, element B, and / or element C" may include element A only, element B only, element C only, elements A and element B, elements A and element C, elements B and element C, or elements A, B, and C. In addition, "at least one of element A or element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B. Furthermore, "at least one of element A and element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B.

[0166] The subject matter of the present disclosure has been described with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of the present disclosure. Instead, the inventors intend that the claimed subject matter may be implemented in other ways, including different steps or combinations of steps similar to those described in this document, in conjunction with other current or future technologies. Furthermore, although the terms "step" and / or "block" may be used herein to connote different elements of the method used, these terms should not be construed as implying any particular order between the various steps disclosed herein unless and when the order of the individual steps is explicitly described.

Claims

1. receiving high definition (HD) map data corresponding to an area containing the locations of the dynamic actors at one time; localizing the dynamic actors with respect to the HD map data; receiving sensor data generated by sensors of said dynamic actors at one time; transforming the HD map data from a first coordinate system of the HD map data to a second coordinate system of the sensor data based at least in part on the HD map data and the localization to correlate the HD map data with the sensor data; generating ground truth data corresponding to the sensor data for training a neural network based on the correlating; training the neural network using the sensor data and the ground truth data; wherein the generating step of the ground truth data includes transforming the HD map data into a coordinate system of the dynamic actor, determining one or more features represented by the HD map data, and generating labels or annotations in the coordinate system corresponding to the one or more features, the ground truth data representing the labels or annotations; The method, wherein the ground truth data corresponds to the second coordinate system.

2. 10. The method of claim 1, further comprising determining the region that includes the location based at least in part on at least one of Global Navigation Satellite System (GNSS) data, Global Positioning System (GPS) data, or Differential GPS (DGPS) data generated by one or more position-based sensors of the dynamic actor.

3. 2. The method of claim 1 , wherein the training the neural network comprises training the neural network to perform inference for at least one of object detection, feature detection, road feature detection, waiting condition detection or classification, or generation of future trajectories.

4. 2. The method of claim 1 , further comprising receiving data representing a trajectory of the dynamic actor through at least a portion of a field of view represented by the sensor data, and wherein the generating step comprises adjusting the trajectory based at least in part on the HD map data.

5. The method of claim 4 , wherein the adjusting the trajectory comprises shifting the trajectory toward a rail of a lane of movement of the dynamic actor.

6. The method of claim 1 , wherein the sensor data comprises at least one of image data, LIDAR data, RADAR data, SONAR data, or ultrasound data.

7. The method of claim 1 , wherein the first coordinate system is a three-dimensional (3D) world space coordinate system and the second coordinate system is a two-dimensional (2D) image space coordinate system.

8. receiving high resolution (HD) map data representing an HD map; receiving first sensor data generated by at least one first sensor of a dynamic actor; localizing the dynamic actors with respect to the HD map data based at least in part on the first sensor data; receiving second sensor data generated by a second sensor of the dynamic actor; transforming the HD map data from a first coordinate system of the HD map data to a second coordinate system of the sensor data and correlating the map data with the second sensor data based at least in part on the localization; generating, based at least in part on the correlating, ground truth data corresponding to the second sensor data for training a neural network; wherein the generating step of the ground truth data includes transforming the HD map data into a coordinate system of the dynamic actor, determining one or more features represented by the HD map data, and generating labels or annotations in the coordinate system corresponding to the one or more features, the ground truth data representing the labels or annotations; The method, wherein the ground truth data corresponds to the second coordinate system.

9. The method of claim 8 , wherein the correlating step includes transforming the map data into a coordinate space adapted for the dynamic actor.

10. 10. The method of claim 9, wherein the correlating step further comprises, after the converting step, converting the map data from world space coordinates to sensor space coordinates corresponding to the second sensor data.

11. 9. The method of claim 8, wherein the first sensor data represents one or more features within a field of view of the one or more first sensors, and the step of localizing the dynamic actor comprises correlating the one or more features with one or more corresponding features represented by the HD map.

12. 10. The method of claim 8, further comprising receiving third sensor data generated by one or more third sensors of the dynamic actor and representing a trajectory of the dynamic actor through at least a portion of a field of view represented by the second sensor data, and wherein the generating step comprises adjusting the trajectory based at least in part on the map data.

13. The method of claim 8 , wherein the ground truth data and outputs of the neural network are generated in three-dimensional (3D) world space coordinates.

14. A computing device including a processor, a sensor for generating sensor data representing a sensor data representation, one or more processing devices, and one or more memory devices communicatively coupled to the one or more processing devices that store programmed instructions, the programmed instructions, when executed by the processor, causing instantiation of a map manager for localizing dynamic actors with respect to high definition (HD) map data; a feature determiner for determining one or more features represented by the HD map data; and a feature determiner for determining one or more features represented by the HD map data. a ground truth generator for transforming D map data from a first coordinate system of the HD map data to a second coordinate system of the sensor data representation to correlate first positions of the one or more features with second positions of the one or more features in the sensor data representation and generating ground truth data corresponding to the second positions of the one or more features based at least in part on the correlating; and a training engine for training a neural network using the sensor data and the ground truth data; the ground truth generator for generating the ground truth data includes means for transforming the HD map data into a coordinate system of the dynamic actor; means for determining one or more features represented by the HD map data; and means for generating labels or annotations in the coordinate system corresponding to the one or more features, the ground truth data representing the labels or annotations; The ground truth data corresponds to the second coordinate system.

15. The system of claim 14 , wherein the one or more features include an object, a road feature, or a waiting condition.

16. 15. The system of claim 14, further comprising a trajectory generator for generating a trajectory corresponding to a field of view of the sensor represented by the sensor data, wherein generating the ground truth data includes adjusting the trajectory based at least in part on the one or more features.

17. The system of claim 16 , wherein the one or more features include rails for a lane of travel for the dynamic actor.

18. The system of claim 14 , wherein the map manager is further adapted to adapt the HD map with respect to the position and orientation of the dynamic actor.

Images