Neural network based determination of gaze direction using spatial models

Abstract

To provide systems and methods for determining the gaze direction of a subject and projecting the gaze direction onto specific regions of an arbitrary three-dimensional geometry.SOLUTION: In an exemplary embodiment, the gaze direction may be determined by a regression-based machine learning model. The determined gaze direction is then projected onto a three-dimensional map or a set of surfaces that may represent any desired object or system. Maps may represent any three-dimensional layout or geometry, whether actual or virtual. Gaze vectors can thus be used to determine an object being gazed at within any environment. Systems can also readily and efficiently adapt to the use in different environments by retrieving a different set of surfaces or regions for each environment.SELECTED DRAWING: Figure 2A

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Application No. 62 / 948,796, filed December 16, 2019, the disclosure of which is incorporated herein by reference in its entirety. This application also incorporates herein by reference U.S. Patent Application No. 17 / 004,252, filed August 27, 2020, in its entirety. [Background technology]

[0002] Recently, convolutional neural networks (CNNs) have been developed to estimate a subject's gaze direction. Such CNNs can, for example, determine the direction a subject is looking from an input image of the subject. This enables systems using such CNNs to track the subject's gaze and react accordingly in real time.

[0003] However, conventional gaze determination systems are not without drawbacks. In particular, while conventional systems can generally determine gaze direction, they cannot specifically identify what a subject is actually looking at. For example, some conventional in-vehicle gaze determination systems can determine that a driver is looking in a particular direction, such as straight ahead or to one side, but such systems do not determine the specific object or item that the driver is looking at, such as the dashboard, road, or radio.

[0004] Thus, systems and methods for performing machine learning-based gaze analysis in a more specific manner are described herein. Accordingly, embodiments of the present disclosure describe systems and methods for more specific, efficient, and flexible determination of gaze regions. In an exemplary embodiment, gaze vectors are determined by a regression-based machine learning model. The determined gaze vectors are then projected onto a three-dimensional map of a surface, which may represent any object or system of interest. The map can represent any three-dimensional layout or shape. In this manner, gaze vectors can be used to determine objects under the gaze of a subject in any environment. Furthermore, systems can be easily and efficiently generated to determine the gaze of a subject operating within any system and perform any action accordingly.

[0005] In one embodiment of the present disclosure, a machine learning model is used to determine a subject's gaze direction. The model may have input features determined from the subject's image data, which may include relevant portions of the subject's image, such as eye cropping, one or more facial landmarks of the subject, etc. The input may also include quantities determined from the subject's image, such as head pose, confidence values, etc. In response, the model generates the subject's gaze direction as its output.

[0006] The system also obtains a set of spatial regions, i.e., defined areas or volumes. These regions may be defined in any manner to correspond to real spatial objects. For example, a set of spatial regions may correspond to the positions and orientations of various interior surfaces of a vehicle. The system can then determine, from the gaze direction and the positions of the spatial regions, whether the subject's line of sight intersects with one or more spatial regions. If so, the system initiates an action accordingly. All such actions are contemplated. For example, if the subject is a vehicle driver and the spatial regions correspond to interior surfaces of the vehicle, the system can determine that the driver is looking at a surface corresponding to the vehicle's entertainment console and perform a corresponding action, such as activating an interface, turning the display on or off, or adjusting the volume.

[0007] The machine learning model may be any one or more models suitable for determining a subject's gaze direction from image data of the subject. As an example, the machine learning model may use a regression model to determine gaze direction as a function of its various inputs.

[0008] As described above, a set of spatial regions can represent various positions and orientations of an arbitrary set of surfaces. These spatial regions can therefore represent any three-dimensional surface positioned and oriented in any desired manner. These surfaces can therefore model any real-world or virtual-world environment or object of interest, and the disclosed system can therefore be used to determine the exact object or portion of the environment (i.e., its three-dimensional surface) that a subject is currently viewing. For example, the surfaces may be three-dimensional surfaces seen from the interior of a particular vehicle, which may include representations of the vehicle's various windows, as well as elements such as particular equipment, components, or features of the vehicle, such as the radio, air conditioning system, dashboard display, etc. In this way, the system can determine whether the driver's line of sight currently intersects with a surface representing a particular component and perform the appropriate action by initiating some operation of the vehicle. As an example, the system can determine that the driver is currently looking at the climate control dial and cause the vehicle to respond in various ways, such as changing the temperature setting or turning the climate control on or off. As another example, the system may determine that the driver is currently distracted or asleep and may initiate an alarm to warn the driver, initiate an emergency steering maneuver to pull the vehicle to the side of the road, or initiate a braking maneuver. The spatial regions may be determined in any manner, such as by selecting regions obtained from a computer-aided design (CAD) or other computer-based three-dimensional model of one or more objects, by measuring the objects directly, by determining the location of points or regions of the object from an image of the object, or via a machine learning model trained to select and determine the location and orientation of regions of the object.

[0009] As described above, the machine learning model may have any suitable inputs for determining the subject's gaze direction, including, but not limited to, one or more landmark points on the subject's face, the subject's head pose information, one or more gaze directions of the subject's eyes, one or more eye crops, or any confidence values ​​associated with these inputs.

[0010] It should also be noted that the image data used by the system may be in any format, whether or not corresponding to visible light imagery, and may be received or generated from any type of sensor. It should also be noted that using a set of distinct spatial regions creates a modular system that can be used in conjunction with many different environments by simply adding a new set of spatial regions. That is, multiple different sets of spatial regions can be stored, each corresponding to any desired environment. The system can then retrieve the appropriate set of spatial regions and repeat the above process with the new region. In this manner, the system can adaptively determine the subject's interaction with any desired environment.

[0011] These and other objects and advantages of the present disclosure will become apparent from the following detailed description considered in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout. [Brief explanation of the drawings]

[0012] [Figure 1A] 10 is a photograph illustrating the operation of a system according to an embodiment of the present disclosure. [Figure 1B] 10 is another photograph illustrating the operation of a system according to an embodiment of the present disclosure. [Figure 1C] 10 is yet another photograph illustrating the operation of a system according to an embodiment of the present disclosure. [Figure 2A] FIG. 1 is a block diagram illustrating an exemplary machine learning system for determining gaze direction and mapping this gaze direction to a region of an arbitrary three-dimensional shape, according to an embodiment of the present disclosure. [Figure 2B]FIG. 2B is a block diagram illustrating further details of the gaze vector estimation module of FIG. 2A. [Figure 3] 1 is a generalized embodiment of an exemplary electronic computing system constructed for use in accordance with embodiments of the present disclosure. [Figure 4A] FIG. 1 is a diagram of an exemplary autonomous vehicle, according to some embodiments of the present disclosure. [Figure 4B] 4B is an example of camera positions and fields of view for the exemplary autonomous vehicle of FIG. 4A, according to some embodiments of the present disclosure. [Figure 4C] FIG. 4B is a block diagram of an example system architecture of the example autonomous vehicle of FIG. 4A, in accordance with some embodiments of the present disclosure. [Figure 4D] FIG. 4B is a system diagram for communication between a cloud-based server and the example autonomous vehicle of FIG. 4A, according to some embodiments of the present disclosure. [Figure 5] FIG. 1 is a block diagram of an exemplary computing device suitable for use in implementing some embodiments of the present disclosure. [Figure 6] FIG. 1 illustrates training and deployment of a machine learning model according to an embodiment of the present disclosure. [Figure 7] 1 is a flowchart illustrating the process steps for determining a line of sight and mapping the line of sight to a region of an arbitrary three-dimensional shape, according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] In one embodiment, the present disclosure relates to a system and method for determining a subject's gaze direction and projecting this gaze direction onto a specific region of an arbitrary three-dimensional shape. In an exemplary embodiment, the gaze direction may be determined by a regression-based machine learning model. The determined gaze direction is then projected onto a three-dimensional map or set of surfaces that can represent any desired object or system. The map can represent any three-dimensional layout or shape, whether real or virtual. Thus, the gaze vector can be used to determine the object under the gaze in any environment. The system can also be easily and efficiently adapted for use in different environments by acquiring a different set of surfaces or regions for each environment.

[0014] 1A-1C are photographs illustrating the operation of a system according to embodiments of the present disclosure. In FIG. 1A, FIG. 110 is an interior view of a vehicle with an occupant looking toward an entertainment console according to some embodiments of the present disclosure. An occupant 116 is seated in the driver's seat of the vehicle and momentarily directs their gaze 116 (e.g., eyes) toward an entertainment console 119. An interior camera sensor 112 is mounted on the interior roof, while a microphone sensor 114 is mounted within the entertainment console. A processing circuit can receive image data from the camera sensor 112 to determine the occupants and their respective lines of sight at the entertainment console.

[0015] As described herein, the processing circuitry can calculate a gaze vector based on data indicative of the occupant's line of sight. In some embodiments, the parallel processing circuitry may implement a machine learning model (e.g., a neural network) to calculate the gaze vector as described herein. The gaze vector may be a straight line in three-dimensional space with one intersection point at the eye of the occupant 117 and a second intersection point at a point on the surface of the entertainment console 119.

[0016] The processing circuitry can determine an intersection point between the line of sight vector and the entertainment console 119. In particular, the processing circuitry can retrieve from memory a set of stored spatial coordinates representing regions in three-dimensional space corresponding to various surfaces within the vehicle. One of these regions outlines the orientation and position of the entertainment console 119 within the vehicle. In this example, the processing circuitry extends the line of sight vector from the determined origin (e.g., the three-dimensional position of the eyes of the driver 117) to intersect with the region corresponding to the entertainment console 119.

[0017] Upon determining an intersection between the line of sight vector and the entertainment console 119, the processing circuitry may cause an action to be performed within the vehicle. The action may be performed by one or more hardware components of the vehicle. For example, the vehicle may be equipped with various hardware components that can provide a particular action related to the entertainment console 119 when the intersection is determined to be at the location of the entertainment console 119.

[0018] FIG. 1B shows a diagram 120 illustrating the execution of a vehicle action in response to determining that the driver is looking at the entertainment console 119, according to some embodiments of the present disclosure. After determining that the driver is looking at the entertainment console 119, the processing circuitry sends a command to the entertainment console 119 to switch modes from “sleep” to “engage.” The entertainment console’s engage mode provides an enhanced brightness screen 122 that allows for further queries or requests from the occupant for specific actions. For example, the entertainment console responds by tuning in to a specific radio station with the brightness and UI enabled. As a result, the system changes the operating mode of the entertainment console 119 when it recognizes that the driver is looking at the entertainment console 119. In this way, the system can use gaze as an action trigger or “wake-up word” for a multimodal system (e.g., a virtual or digital personal assistant, a conversational user interface, or other similar interface).

[0019] In some embodiments, the processing circuitry can receive other data from the occupant from sensors within the vehicle. For example, the interior camera 112 can receive lip movements of the occupant. The lip movements can be converted into text information (e.g., processing the lip movements can provide text information being spoken by the occupant). In some embodiments, the other data can be audio data received by a microphone sensor 114 within the vehicle. The processing circuitry can determine a service action associated with the other data. For example, the processing circuitry can determine that the occupant is saying "increase the treble to level 4." The processing circuitry can determine that the corresponding action in the entertainment console is to increase the treble of the audio / video playback. The processing circuitry can then cause the service action to be performed within the vehicle.

[0020] Embodiments of the present disclosure contemplate multiple contextual processes and operations performed in parallel for multiple actors. For example, the internal camera 200 can detect eye movements of vehicle occupants at a predetermined point of interest (e.g., the camera) and correlate the detected eye movements with corresponding lip movements and / or voice data for that occupant. Under such circumstances, the processing circuitry can maintain separate context streams for each occupant based on the determined source of the eye movements. Such individual context streams can be timed or semi-persistent. That is, a context stream can be maintained even if it is interrupted or made non-continuous by movements corresponding to other context streams or by multimodal movements of other vehicle occupants. If the context is determined to be the same, a dialogue system as contemplated by the present disclosure incorporates voice data from different occupants to perform the same service operation. Thus, embodiments of the present disclosure contemplate the combination of user input detection of multiple modalities (e.g., visual and audio) to implement a dialogue system for conversational artificial intelligence operations and to maintain multiple separate contexts within the dialogue system within the context of the vehicle cabin. Embodiments of the present disclosure also contemplate applications in other settings. For example, visual information (e.g., without limitation, any or all of gaze / body pose detection, gaze / body pose mapping, and / or object detection) can be combined with audio information (e.g., without limitation, automatic speech recognition or natural language processing) to perform machine learning-assisted operations in the context of a retail store, business office, medical facility, etc. To apply sensor fusion combined with a multi-context system to other use cases, modifiable / customizable use case diagrams are used. Embodiments of the present disclosure also contemplate feedback mechanisms to notify a subject when their gaze is determined to intersect a particular spatial region. For example, visual, tactile, or other feedback may be generated at a particular vehicle component when the system determines that the driver is looking at that component. Such feedback can also further inform the driver, for example, of actions the driver may take.

[0021] FIG. 1C shows a diagram 130 illustrating multi-context analysis of user actions according to some embodiments of the present disclosure. The processing circuitry can further receive camera sensor information from the camera 112 about the occupant 116 silently or whispering the words "change to heads-up display" after instructing the entertainment console 119 to switch modes from "sleep" to "engage." The processing circuitry provides visual processing on the video and / or image frames of the silent / whispered words to determine the specific words used. The occupant may, for example, mouth the words or whisper them to avoid waking another occupant sleeping in the back seat of the vehicle. The system projects the entertainment console's user interface onto the windshield 132 based on the occupant's gaze direction and the determined subsequent words.

[0022] FIG. 2A is a block diagram illustrating an exemplary machine learning system for determining gaze direction and mapping the gaze direction to a region of an arbitrary three-dimensional shape. The system includes a camera 200, a face detection module 210, a gaze vector estimation module 220, a facial landmark detection 230 and gaze origin estimation 240 module, and a mapping module 250. The camera 200 captures an image of a subject, such as a person, for which gaze direction is to be determined. The camera 200 transmits image data from the captured image to the face detection module 210, which detects the subject's face in the image. The face detection module 210 may be any software module or set of instructions capable of locating the subject's face in an image using any method or process, and may be similar to the face detection module 210 of FIG. 2A described above. The system of FIG. 2A may be implemented and executed on any computing device, such as computing device 300.

[0023] The faces detected by this face detection module 210 may be cropped, and the cropped face image is sent to gaze vector estimation module 220. Cropping the face may be determined by locating the subject's face in the image from camera 200 and cropping the image accordingly. Face localization may be performed in any manner, such as known computer vision-based face detection processes, including the non-neural network-based techniques mentioned above, neural network-based face recognition methods, etc.

[0024] The gaze vector estimation module 220 may implement any one or more machine learning models capable of determining a subject's gaze direction from an input image of the subject's face. In an exemplary embodiment, the gaze vector estimation module 220 implements a regression model that estimates a direction vector value from input gaze-related variables, as described further below. The gaze vector estimation module 220 may implement any suitable regression model, such as a DNN-based linear regression model, a statistical regression model, a gradient boosting model, or the like, that may be configured to determine a gaze vector from any input variables.

[0025] The input facial crop is also input to a facial landmark detection module 230, which determines facial landmarks from the input image of the subject's face. The facial landmark module 230 can implement any machine learning network, e.g., any one or more machine learning models, capable of determining facial landmarks from the input image of the face. The module 230 may include machine learning models constructed according to holistic methods for representing global facial appearance and shape information, as well as models constructed according to constrained local model methods that build local appearance models in addition to utilizing global shape models, generative networks, CNNs, and regression-based models for determining landmark locations as a function of facial shape and appearance information. Many such models are known, and embodiments of the present disclosure contemplate using any one or more such models, or any other suitable model or method, to determine facial landmarks from the input image of the face. The model can be constructed using any architecture and method suitable for determining facial landmarks from the input image of the face. For example, a CNN-based facial landmark network can be constructed using any convolutional kernel and pooling layer suitable for extracting facial features to determine corresponding landmark points.

[0026] The facial landmarks output by the facial landmark detection module 230 are then sent to the gaze origin estimation module 240, which determines the origin of the gaze direction vector therefrom. The gaze origin estimation module 240 can implement any machine learning network, such as any one or more machine learning models that can determine the gaze origin from an input set of facial landmarks. Such networks include CNNs, classification models, regression models, etc.

[0027] The estimated gaze vector and its origin are then input to mapping module 250, which determines the three-dimensional region the subject is viewing by mapping the gaze vector from its origin to a set of three-dimensional regions. Mapping module 250 implements a mapping routine that stores, for example, in storage 408, a set of three-dimensional regions describing a set of surfaces in three dimensions, projects the determined gaze vector from its origin, and determines whether the gaze vector intersects with one of the surfaces. Any intersecting surface is then output as the output gaze region or the three-dimensional surface the subject is currently viewing. Data representing the set of three-dimensional regions may be input to, stored in, or accessible by mapping module 250. In this manner, any set of three-dimensional regions representing any one or more objects can be input to mapping module 250, and mapping module 250 can determine the intersection of the projected gaze vector with any stored three-dimensional region. This enables the system of FIG. 2A to determine the gaze direction for any three-dimensional region representing any object. Furthermore, the system does not need to retrain machine learning models for each different object. Rather, a set of new 3D regions is simply made available to mapping module 250, which can determine the intersection of gaze directions with these new 3D regions without retraining its machine learning models.

[0028] A three-dimensional region can be any three-dimensional representation determined in any manner. For example, a three-dimensional region can be determined by directly measuring the spatial positions of various points of one or more objects. A three-dimensional region can also be determined by fitting a CAD model or other computer-based three-dimensional model of one or more objects that includes position information for various positions of the objects. This approach is suitable for use with complex three-dimensional shapes that are difficult or cumbersome to measure directly, such as the interior of a vehicle. Another approach is to determine the positions of points or regions of an object using one or more sensors capable of conveying position information, such as image sensors, distance or position sensors, etc. For example, the sensors can capture images of the object (at any wavelength, including visible light images, infrared images, etc.), from which the positions of points or regions of the object can be determined in any manner. A further approach uses one or more known machine learning models trained to select and determine the positions and orientations of regions of an object from inputs such as images of the object.

[0029] 2B is a block diagram illustrating further details of the gaze vector estimation module 220. In one embodiment, the gaze vector estimation module 220 includes an adaptive inference fusion module 280 that implements a regression model as described above. The regression model takes as input variables a set of facial landmarks representing the subject's head pose, a set of confidence values ​​corresponding to the facial landmarks, a left eye gaze direction, a right eye gaze direction, and a corresponding confidence value for each gaze direction. The gaze directions are then output according to the regression scheme, as described above. The facial landmarks and associated confidence values ​​may be determined according to any suitable method or system.

[0030] The illustrated gaze networks 260, 270 take as input crops of the subject's left and right eyes and output estimates of gaze direction for each eye. The eye crops may be determined by locating the subject's eyes in the image from camera 200 and cropping the image accordingly. Eye localization may be performed in any manner, such as by known computer vision-based eye detection processes, including the non-neural network-based techniques described above, neural network-based eye recognition methods, etc. Eye localization by these processes may generate confidence values ​​corresponding to the confidence that the eyes have been correctly identified, and these confidence values ​​may also be input to an adaptive inference fusion module. The gaze networks 260, 270 may be any network capable of determining gaze from input eye crops.

[0031] The adaptive inference fusion module 280 can implement any regression model suitable for determining gaze vectors, as described above. The gaze vectors output from the adaptive inference fusion module 280 are then sent to the gaze region mapping module 250, which maps the gaze vectors to a three-dimensional shape. It can be observed that any three-dimensional shape, or set of surfaces, can be stored for use by the computing system 300. Thus, the system of FIGS. 2A and 2B can determine the intersection of a subject's gaze with any set of surfaces. Accordingly, embodiments of the present disclosure enable an efficient and modular approach to determining a subject's gaze region in any environment. By characterizing any environment as a set of three-dimensional surfaces and storing those surfaces, for example, in storage 408, the system of FIGS. 2A and 2B can determine, at any time, which parts of the environment are capturing the subject's attention. If the subject changes their environment, their interaction with this new environment can be determined by inputting the surfaces of the new environment for use by the system of FIGS. 2A and 2B.

[0032] This system can be applied to any environment. As an example, the environment may be the cabin of a vehicle, and the system of FIGS. 2A and 2B can be used to determine the portion or area of ​​the vehicle to which the driver is currently directing his or her attention. In this example, the camera 200 described above may be installed in the vehicle to capture images of the vehicle occupant's face. Embodiments of the present disclosure can determine the gaze vector and origin of the vehicle occupant's gaze. As shown in FIG. 2A , relevant portions of the vehicle's cabin may be identified and characterized as three-dimensional surfaces. These surfaces may include, for example, the left and right windshields, the left and right exterior (e.g., side windows), the vehicle's information cluster, and the vehicle's entertainment center. As described above, the system of FIGS. 2A and 2B can determine which of these surfaces the determined gaze vector intersects and perform one or more actions accordingly. For example, upon determining that the vehicle occupant is the driver of the vehicle and that the driver is looking at the information cluster, the vehicle may project specific important information or warnings onto the information cluster or highlight specific measurements or indicators. As another example, if the vehicle determines that the driver is looking at an area other than the left windshield for more than a threshold amount of time, the vehicle may issue a warning to the driver to focus on the road. Embodiments of the present disclosure contemplate any action initiated in response to a determined line-of-sight area.

[0033] 3 is a block diagram representation of one exemplary gaze determination system according to an embodiment of the present disclosure. Here, a computing device 300, which may correspond to camera 200 of FIG. 2A and include processing circuitry capable of performing the gaze determination and mapping operations of an embodiment of the present disclosure, is in electronic communication with both a camera 310 and a gaze assistance system 320. In operation, camera 310, which may correspond to camera 200 of FIG. 2A, captures an image of a subject and transmits it to computing device 300. Computing device 300 then implements the machine learning model of FIGS. 2A-2B, for example, to determine an output gaze vector from the image of camera 310 and its intersection with a particular region of space. Computing device 300 transmits this intersection information to gaze assistance system 320, which, in response, performs an action or performs one or more operations.

[0034] The gaze assistance system 320 may be any system capable of performing one or more actions based on spatial domain intersection information received from the computing device 300, such as initiating a system action corresponding to the intersecting spatial domain. Any configuration of the camera 310, computing device 300, and gaze assistance system 320 is contemplated. As an example, the gaze assistance system 320 may be an autonomous vehicle capable of determining and reacting to the gaze direction of a driver or another occupant, such as the autonomous vehicle of FIGS. 4A-4D described further below. In this example, the camera 310 and computing device 300 may be located within the vehicle, while the gaze assistance system 320 may represent the vehicle itself. The camera 310 may be located anywhere within the vehicle from which the driver or occupant can be viewed. Thus, the camera 310 may capture images of the driver and transmit them to the computing device 300, which calculates the corresponding subject's gaze vector and determines the intersection of the gaze vector with the spatial domain corresponding to the portion of the vehicle. This intersection information may then be transmitted, for example, to another software module that determines the action the vehicle can take in response. For example, the vehicle may determine that the line of sight intersects with the side window and therefore represents a distracted driver or a driver not paying attention to the road, and may initiate any type of action accordingly. Such action may include any type of warning issued to the driver (e.g., visual or audible warning, warning on a head-up display, etc.), initiating autopilot, braking or turning, or other action. Computing device 300 may be located within the vehicle of gaze assist system 320 as a local processor, or may be a remote processor that receives images from camera 310 and wirelessly transmits intersection information or instructions to the vehicle of gaze assist system 320.

[0035] As another example, the gaze assistance system 320 may be a virtual reality or augmented reality system capable of displaying images in response to a user's movements and gaze. In this example, the gaze assistance system 320 includes a virtual reality or augmented reality display, such as a headset worn by a user and configured to project images thereon. The camera 310 and computing device 300 may be located within the headset, with the camera 310 capturing an image of the user's eyes, from which the computing device 300 determines landmarks and confidence values, as well as the user's gaze direction. This gaze direction may then be projected onto a set of captured spatial regions within the virtual environment, and the system 320 may perform various actions based on the particular spatial region the user may be looking at. For example, the spatial region may represent a virtual object responsive to the user's gaze, such as a heads-up display region that displays information to the user as the user looks. Similar to the autonomous vehicle example above, the computing device 300 of the virtual reality or augmented reality system may be located within the system 320, e.g., within the headset itself, or may be located remotely such that images are wirelessly transmitted to the computing device 300 and a calculated gaze direction is wirelessly transmitted to the headset, which then performs various actions accordingly.

[0036] As yet another example, the gaze assistance system 320 may be a computer-based advertising system that determines which advertisements a user is viewing. More specifically, the gaze assistance system 320 may be any electronic computing system or device, such as a desktop computer, a laptop computer, a smartphone, or a server computer. The camera 310 and the computing device 300 may be incorporated into this system, such that the camera 310 detects a user when the user is looking at or in close proximity to the display of the computing device. The camera 310 may capture an image of the user, from which the computing device 300 may determine the user's gaze direction. The determined gaze direction may then be transmitted to the gaze assistance system 320, e.g., the computing device 300 that displays advertisements to the user, a remote computing device, or the like. The computing device 300 may then retrieve stored spatial regions, each of which may correspond to a specific portion of the display of the system 320. The calculated gaze direction may then be used to determine the area where the gaze vectors intersect, i.e., which advertisements the user is focusing on, and provide information about the effectiveness of various advertisements.

[0037] The gaze assistance system 320 may further function as a user interface system for controlling any computing system. As described above, a spatial region corresponding to the display of a computing device can be used to determine a user's gaze relative to any region of a displayed computing output. In this manner, the system 320 can function as a graphical or visual user interface system similar to a computer mouse or touchpad, allowing a user to move a cursor and select items according to their gaze position. That is, a user can move a cursor or other item selection icon by looking at different regions of the displayed information. A user can also use their gaze to select items (e.g., by looking at a corresponding spatial region for longer than a predetermined time), select / press a button, and perform any other user input to the computing system. Embodiments of the present disclosure contemplate using any stored spatial region arranged according to a region of any displayed computing output to select portions of the computing output according to the user's gaze direction.

[0038] 4A is a diagram of an example autonomous vehicle 400 according to some embodiments of the present disclosure. The autonomous vehicle 400 (sometimes referred to herein as “vehicle 400”) may include, but is not limited to, a passenger vehicle such as a car, a truck, a bus, a first responder vehicle, a shuttle, an electric bicycle or moped, a motorcycle, a fire engine, a police vehicle, an ambulance, a boat, a construction vehicle, an underwater vehicle, a drone, and / or another type of vehicle (e.g., a vehicle that is unmanned and / or accommodates one or more occupants). Autonomous vehicles are generally described in terms of levels of automation, 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) in their “Level Classification and Definition of Driving Automation Systems for Motor Vehicles” (Standard No. J3016-201806, issued June 15, 2018, Standard No. J3016-201609, issued September 30, 2016, and previous and future versions of this standard). Vehicle 400 may be capable of functioning according to one or more of levels of automation, from Level 3 to Level 5. For example, vehicle 400 may be capable of conditional automation (Level 3), high automation (Level 4), and / or full automation (Level 5), depending on the embodiment.

[0039] Vehicle 400 may include components such as a chassis, a body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other vehicle components. Vehicle 400 may include a propulsion system 450, such as an internal combustion engine, a hybrid power plant, an all-electric engine, and / or another propulsion system type. Propulsion system 450 may be connected to a drivetrain of vehicle 400, which may include a transmission, to enable propulsion of vehicle 400. Propulsion system 450 may be controlled in response to receiving a signal from a throttle / accelerator 452.

[0040] A steering system 454, which may include a steering wheel, may be used to steer the vehicle 400 (e.g., along a desired path or road) when the propulsion system 450 is operating (e.g., when the vehicle is moving). The steering system 454 may receive signals from a steering actuator 456. The steering wheel may be optional for fully automated (Level 5) functionality.

[0041] Brake sensor system 446 may be used to operate vehicle brakes in response to receiving signals from brake actuator 448 and / or brake sensors.

[0042] A controller 436, which may include one or more CPUs, system-on-chip (SoC) 404 (FIG. 4C), and / or GPUs, may provide signals (e.g., representing commands) to one or more components and / or systems of the vehicle 400. For example, the controller may send signals to operate the vehicle's brakes via one or more brake actuators 448, the steering system 454 via one or more steering actuators 456, and / or the propulsion system 450 via one or more throttles / accelerators 452. The controller 436 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 human driver in driving the vehicle 400. The controllers 436 may include a first controller 436 for autonomous driving functions, a second controller 436 for functional safety functions, a third controller 436 for artificial intelligence functions (e.g., computer vision), a fourth controller 436 for infotainment functions, a fifth controller 436 for redundancy in emergency situations, and / or other controllers. In some examples, a single controller 436 may govern two or more of the above functions, and two or more controllers 436 may govern a single function and / or any combination thereof.

[0043] Controller 436 may provide signals to control one or more components and / or systems of vehicle 400 in response to sensor data (e.g., sensor inputs) received from one or more sensors. The sensor data may be received from, by way of example and not limitation, global navigation satellite system sensors 458 (e.g., global positioning system sensors), radar sensors 460, ultrasonic sensors 462, lidar sensors 464, inertial measurement unit (IMU) sensors 466 (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones 496, stereo cameras 468, wide-view cameras 470 (e.g., fisheye cameras), infrared cameras 472, surround cameras 474 (e.g., 360-degree cameras), long-range and / or medium-range cameras 498, speed sensors 444 (e.g., measuring the speed of vehicle 400), vibration sensors 442, steering sensors 440, brake sensors 446 (e.g., as part of brake sensor system 446), and / or other sensor types.

[0044] One or more controllers 436 may receive input (e.g., represented by input data) from the instrument cluster 432 of the vehicle 400 and provide output (e.g., represented by output data, display data, etc.) via a human-machine interface (HMI) display 434, an audible annunciator, a speaker, and / or other components of the vehicle 400. The output may include information such as vehicle speed, velocity, time, map data (e.g., HD map 422 of FIG. 4C ), position data (e.g., the location of the vehicle 400 on a map, etc.), direction, the location of other vehicles (e.g., an occupancy grid), information about objects, and the state of objects as perceived by the controller 436. For example, the HMI display 434 may display information about the presence of one or more objects (e.g., road signs, caution signs, traffic light switches, etc.) and / or information about a driving maneuver the vehicle has performed, is performing, or is about to perform (e.g., change lanes here, take exit 34B in 2 miles, etc.).

[0045] Vehicle 400 further includes a network interface 424 capable of communicating over one or more networks using one or more wireless antennas 426 and / or a modem. For example, network interface 424 may be capable of communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, etc. Wireless antenna 426 may 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.

[0046] 4B is an example of camera positions and fields of view for the exemplary autonomous vehicle 400 of FIG. 4A, according to some embodiments of the present disclosure. The cameras and their respective fields of view are an exemplary 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 at different locations on the vehicle 400.

[0047] The camera type may include, but is not limited to, a digital camera that may be adapted for use with components and / or systems of vehicle 400. The camera may be capable of operating at Automotive Safety Integrity Level (ASIL) B and / or another ASIL. The camera type may be capable of any image capture rate, such as 60 frames per second (fps), 120 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 examples, 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, a clear pixel camera, such as a camera with an RCCC, RCCB, and / or RBGC color filter array, may be used to improve light sensitivity.

[0048] In some examples, one or more 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 features such as lane departure warning, traffic sign assist, intelligent headlamp control, etc. One or more cameras (e.g., all cameras) may simultaneously record and provide image data (e.g., video).

[0049] To block stray light and reflections from the interior of the vehicle (e.g., reflections from the dashboard reflected in the windshield mirror) that may interfere with the camera's image data capture function, one or more cameras may be mounted on a mounting assembly, such as a custom-designed (3D printed) assembly. With respect to wing mirror mounting assemblies, the wing mirror assembly may be custom 3D printed so that the camera mounting plate matches the shape of the wing mirror. In some examples, the camera may be integrated into the wing mirror. In the case of side-view cameras, the cameras may be integrated into four pillars at each corner of the cabin.

[0050] A camera (e.g., a forward-facing camera) with a field of view that includes a portion of the environment ahead of the vehicle 400 can be used to obtain a surround view to help identify the path and obstacles ahead and, with the aid of one or more controllers 436 and / or control SoCs, to help provide important information for generating an occupancy grid and / or determining a preferred vehicle path. Forward-facing cameras can be used to perform many of the same ADAS functions as lidar, such as emergency braking, pedestrian detection, and collision avoidance. Forward-facing cameras can 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.

[0051] Various cameras can be used in a forward-facing configuration, such as a monocular camera platform including a CMOS (complementary metal-oxide semiconductor) color imager. Another example can be a wide-view camera 470 that can be used to perceive objects (e.g., pedestrians, crossing vehicles, or bicyclists) that enter the field of view from the surroundings. While only one wide-view camera is shown in FIG. 4B, there can be any number of wide-view cameras 470 on the vehicle 400. Additionally, a long-range camera 498 (e.g., a long-field-of-view stereo camera pair) can be used for depth-based object detection, particularly for objects for which a neural network has not yet been trained. The long-range camera 498 can also be used for object detection and classification, as well as basic object tracking.

[0052] One or more stereo cameras 468 may also be included in the forward-facing configuration. The stereo camera 468 may include an integrated control unit with a scalable processing unit that may provide programmable logic (e.g., FPGA) and a multi-core microprocessor with an integrated CAN or Ethernet interface 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 468 may include a miniature stereo vision sensor that includes two camera lenses (one on each side) and an image processing chip that can measure the distance from the vehicle to target objects and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning features. Other types of stereo cameras 468 may be used in addition to or instead of those described herein.

[0053] Cameras having a field of view that includes a portion of the environment to the sides of the vehicle 400 (e.g., side-view cameras) can be used for surround view to provide information used to create and update the occupancy grid and generate side impact collision warnings. For example, surround cameras 474 (e.g., four surround cameras 474 as shown in FIG. 4B ) can be positioned around the vehicle 400. The surround cameras 474 can include wide-view cameras 470, fisheye cameras, 360-degree cameras, etc. For example, four fisheye cameras can be positioned at the front, rear, and sides of the vehicle. In an alternative configuration, the vehicle may use three surround cameras 474 (e.g., left, right, and rear) and utilize one or more other cameras (e.g., a forward-facing camera) as a fourth surround view camera.

[0054] A camera having a field of view that includes a portion of the environment behind vehicle 400 (e.g., a rearview camera) may be used for parking assistance, surround view, rear collision warning, and creating and updating an occupancy grid. A wide variety of cameras can 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 498, stereo camera 468, infrared camera 472, etc.), as described herein.

[0055] A camera having a field of view that includes a portion of the interior or cabin of vehicle 400 may be used to monitor one or more conditions of the driver, passengers, or objects within the cabin. Any type of camera may be used, including but not limited to cabin camera 441, which may be any type of camera described herein and may be located anywhere in vehicle 400 to provide a field of view of the cabin or interior of vehicle 400. For example, cabin camera 441 may be located within or part of the dashboard, rearview mirror, side mirror, seat, or door of vehicle 400 and oriented to capture an image of any driver, passenger, or other object or portion of vehicle 400.

[0056] FIG. 4C is a block diagram of an example system architecture for the example autonomous vehicle 400 of FIG. 4A , in accordance with some embodiments of the present disclosure. It should be understood that this and other configurations described herein are presented 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 shown, and some elements may be omitted entirely. Furthermore, many of the elements described herein are functional entities that may be implemented as individual or distributed components, or in combination with other components, in any suitable combination and location. Various functions described herein as performed by entities may be performed by hardware, firmware, and / or software. For example, various functions may be performed by a processor executing instructions stored in a memory.

[0057] Each of the components, features, and systems of the vehicle 400 in FIG. 4C is shown as connected via a bus 402. The bus 402 may include a controller area network (CAN) data interface (alternatively sometimes referred to herein as a “CAN bus”). The CAN may be a network internal to the vehicle 400 used to help control various features and functions of the vehicle 400, such as brake application, acceleration, braking, steering, windshield wipers, etc. The CAN bus may be configured to have tens or hundreds of nodes, each with its own unique identifier (e.g., a CAN ID). The CAN bus may be read to find steering wheel angle, ground speed, engine revolutions per minute (RPM), button position, and other vehicle status indicators. The CAN bus may be ASIL B compliant.

[0058] Although the bus 402 is described herein as being a CAN bus, this is not intended to be limiting. For example, FlexRay and / or Ethernet may be used in addition to or instead of a CAN bus. Furthermore, although a single line is used to represent the bus 402, this is not intended to be limiting. There may be any number of buses 402, 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 examples, two or more buses 402 may be used to perform different functions and / or for redundancy. For example, a first bus 402 may be used for collision avoidance functions and a second bus 402 may be used for actuation control. In any example, each bus 402 may communicate with any of the components of the vehicle 400, or two or more buses 402 may communicate with the same component. In some examples, each SoC 404, each controller 436, and / or each computer in the vehicle may have access to the same input data (e.g., input from sensors in the vehicle 400) and may be connected to a common bus, such as a CAN bus.

[0059] Vehicle 400 may include one or more controllers 436, such as those described herein with respect to FIG. 4A. Controller 436 may be used for a variety of functions. Controller 436 may be coupled to any of a variety of other components and systems of vehicle 400 and may be used for control of vehicle 400, artificial intelligence of vehicle 400, infotainment of vehicle 400, etc.

[0060] Vehicle 400 may include a system on a chip (SoC) 404. SoC 404 may include a CPU 406, a GPU 408, a processor 410, a cache 412, an accelerator 414, a data store 416, and / or other components and features not shown. SoC 404 may be used to control vehicle 400 in a variety of platforms and systems. For example, SoC 404 may be combined in a system (e.g., that of vehicle 400) with an HD map 422 that can obtain map refreshes and / or updates from one or more servers (e.g., server 478 of FIG. 4D ) via a network interface 424.

[0061] CPU 406 may include a CPU cluster or CPU complex (also sometimes referred to herein as a "CCPLEX"). CPU 406 may include multiple cores and / or L2 caches. For example, in some embodiments, CPU 406 may include eight cores in a coherent multiprocessor configuration. In some embodiments, CPU 406 may include four dual-core clusters, each with its own dedicated L2 cache (e.g., 2 MB of L2 cache). CPU 406 (e.g., a CCPLEX) may be configured to support simultaneous cluster operation, allowing any combination of clusters of CPUs 406 to be active at a given time.

[0062] The CPU 406 can implement power management features including one or more of the following features: individual hardware blocks can be automatically clock gated when idle to conserve dynamic power; each core clock can be gated when the core is not actively executing instructions by executing a WFI / WFE instruction; each core can be independently power gated; if all cores are clock gated or power gated, each core cluster can be independently clock gated; and / or if all cores are power gated, each core cluster can be independently power gated. The CPU 406 can further implement an enhanced algorithm for managing power states, where allowable power states and desired wake-up times are specified and hardware / microcode determines the best power state to enter for the cores, clusters, and CCPLEX. Processing cores can offload work to microcode to support simplified power state entry sequences in software.

[0063] GPU 408 may include an integrated GPU (also sometimes referred to herein as an "iGPU"). GPU 408 may be programmable and efficient for parallel workloads. In some examples, GPU 408 may use an extended tensor instruction set. GPU 408 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 of storage capacity) and two or more streaming microprocessors may share an L2 cache (e.g., an L2 cache having 512 KB of storage capacity). In some embodiments, GPU 408 may include at least eight streaming microprocessors. GPU 408 may use a computer-based application programming interface (API). Additionally, GPU 408 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA's CUDA).

[0064] The GPU 408 may be power-optimized for best performance in automotive and embedded use cases. For example, the GPU 408 may be fabricated on Fin Field Effect Transistors (FinFETs). However, this is not intended to be limiting, and the GPU 408 may be fabricated using other semiconductor manufacturing processes. Each streaming microprocessor may incorporate several mixed-precision processing cores divided into multiple blocks. By way of example and not limitation, 64 PF32 cores and 32 PF64 cores may be divided 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. Additionally, the streaming microprocessor may include independent parallel integer and floating-point data paths to efficiently execute workloads that combine computation and addressing calculations. Streaming microprocessors may include independent thread scheduling capabilities to allow finer synchronization and coordination between parallel threads. Streaming microprocessors may include a combination of an L1 data cache and a shared memory unit to improve performance while simplifying programming.

[0065] The GPU 408 may include a high-bandwidth memory (HBM) and / or 16 GB HBM2 memory subsystem to provide a peak memory bandwidth of approximately 900 GB / s in some examples. In some examples, synchronous graphics random access memory (SGRAM), such as graphics double data rate type 5 synchronous random access memory (GDDR5), may be used in addition to or instead of the HBM memory.

[0066] The GPU 408 may include unified memory technology, including access counters that enable more accurate migration of memory pages to the processor that accesses them most frequently, thereby improving the efficiency of memory ranges shared between processors. In some examples, address translation services (ATS) support may be used to allow the GPU 408 to directly access the CPU 406 page tables. In such examples, if the GPU 408 memory management unit (MMU) experiences a failure, an address translation request may be sent to the CPU 406. In response, the CPU 406 may consult its page table for virtual-to-physical mapping of addresses and send the translation back to the GPU 408. The unified memory technology thus enables a single, unified virtual address space for both the CPU 406 and GPU 408 memories, thereby simplifying programming the GPU 408 and porting applications to the GPU 408.

[0067] Additionally, GPU 408 may include access counters that can track the frequency of GPU 408's accesses to the memory of other processors, which can help ensure that memory pages are moved to the physical memory of the processor that is accessing the pages most frequently.

[0068] The SoC 404 may include any number of caches 412, including those described herein. For example, the cache 412 may include an L3 cache available to both the CPU 406 and the GPU 408 (e.g., connected to both the CPU 406 and the GPU 408). The cache 412 may include a write-back cache that can track line states, such as by using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). In some embodiments, the L3 cache may include 4 MB or more, although smaller cache sizes may also be used.

[0069] The SoC 404 may include an arithmetic logic unit (ALU) that may be utilized in performing processing related to any of various tasks or operations of the vehicle 400, such as processing DNNs. Additionally, the SoC 404 may include a floating-point unit (FPU) or other type of mathematical or numeric co-processor that performs mathematical operations within the system. For example, the SoC 104 may include one or more FPUs integrated as execution units within the CPU 406 and / or GPU 408.

[0070] The SoC 404 may include one or more accelerators 414 (e.g., hardware accelerators, software accelerators, or a combination thereof). For example, the SoC 404 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. Using large on-chip memory (e.g., 4 MB of SRAM), the hardware acceleration cluster can accelerate neural networks and other calculations. The hardware acceleration cluster can be used to complement the GPU 408 and offload some of the GPU 408's tasks (e.g., freeing up more cycles of the GPU 408 to perform other tasks). As an example, the accelerator 414 can be used for target workloads (e.g., perception, convolutional neural networks (CNNs), etc.) that are stable enough to accommodate acceleration. As used herein, the term “CNN” may include all types of CNNs, including region-based or region-convolutional neural networks (RCNNs) and Fast RCNNs (e.g., used for object detection).

[0071] The accelerator 414 (e.g., a hardware acceleration cluster) may include a deep learning accelerator (DLA). The DLA may include one or more tensor processing units (TPUs), which can 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., for CNN, RCNN, etc.). The DLA may be further optimized for a specific set of neural network types and floating-point operations and inference. The DLA's design provides higher performance per millisecond than general-purpose GPUs and significantly exceeds the performance of CPUs. The TPU can execute several functions, such as single-instance convolution functions, supporting INT8, INT16, and FP16 data types for both features and weights, as well as post-processor functions.

[0072] The DLA can quickly and efficiently run neural networks, particularly CNNs, on processed or unprocessed data for any of a variety of functions, including, by way of example and not limitation, CNNs for object recognition and detection using data from camera sensors, CNNs for distance estimation using data from camera sensors, CNNs for emergency vehicle detection, identification and location 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.

[0073] The DLA can perform any function of the GPU 408, and by using an inference accelerator, for example, a designer can direct either the DLA or the GPU 408 to any function. For example, a designer may focus CNN and floating-point processing in the DLA, and offload other functions to the GPU 408 and / or other accelerators 414.

[0074] The accelerator 414 (e.g., a hardware acceleration cluster) may include programmable vision accelerators (PVAs), which may also be referred to herein as computer vision accelerators. The PVAs 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 PVAs may provide a balance of performance and flexibility. For example, each PVA may include, by way of example and not limitation, any number of reduced instruction set computer (RISC) cores, direct memory access (DMA), and / or any number of vector processors.

[0075] The RISC cores may interact with an image sensor (e.g., an image sensor in any of the cameras described herein), an image signal processor, etc. Each RISC core may include any amount of memory. The RISC cores may use any of several protocols, depending on the embodiment. In some examples, the RISC cores may execute 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.

[0076] The DMA may allow components of the PVA to access system memory independent of the CPU 406. The DMA may support any number of features used to provide optimizations to the PVA, including, but not limited to, support for multi-dimensional addressing and / or circular addressing. In some examples, 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.

[0077] A vector processor may be a programmable processor that can be designed to efficiently and flexibly program computer vision algorithms and provide signal processing functions. In some examples, a 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 PVA's main processing engine 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 a single instruction, multiple data (SIMD), very long instruction word (VLIW) digital signal processor. The combination of SIMD and VLIW can improve throughput and speed.

[0078] Each of the vector processors may include an instruction cache and may be coupled to dedicated memory. As a result, in some examples, each of the vector processors may be configured to execute independently of the other vector processors. In other examples, the vector processors included in a particular PVA may be configured to use data parallelism. For example, in some embodiments, multiple vector processors included in a single PVA may execute the same computer vision algorithm on different regions of an image. In other examples, 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 consecutive images or portions of an image. Notably, a hardware acceleration cluster may include any number of PVAs, and each PVA may include any number of vector processors. Furthermore, the PVAs may include additional error-correcting code (ECC) memory to increase the overall security of the system.

[0079] The accelerator 414 (e.g., a hardware acceleration cluster) may include a computer vision network on-chip and SRAM that provides the accelerator 414 with high-bandwidth, low-latency SRAM. In some examples, the on-chip memory may include, by way of example and not limitation, at least 4 MB of SRAM consisting of eight field-configurable memory blocks accessible by both the PVA and DLA. Each pair of memory blocks may include an advanced peripheral bus (APB) interface, configuration circuitry, a controller, and a multiplexer. 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 an on-chip computer vision network that interconnects the PVA and DLA to the memory (e.g., using the APB).

[0080] The on-chip computer vision network may include an interface that verifies that both the PVA and DLA are providing ready and valid signals before transmitting control signals, addresses, and data. Such an interface may provide separate phases and separate channels for transmitting control signals, addresses, and data, as well as burst-type communication for continuous data transfer. This type of interface may conform to ISO 26262 or IEC 61508 standards, but may also use other standards and protocols.

[0081] In some examples, SoC 404 may include a real-time ray tracing hardware accelerator, such as that described in U.S. patent application Ser. No. 16 / 101,232, filed Aug. 10, 2018. The real-time ray tracing hardware accelerator may be used to quickly and efficiently determine the location and range of objects (e.g., within a world model) and generate real-time visualization simulations that may be used for radar signal interpretation, synthesis and / or analysis of sound propagation, simulation of sonar systems, general wave propagation simulation, comparison with lidar data for localization and / or other functions, and / or other uses. In some embodiments, one or more tree traversal units (TTUs) may be used to perform one or more ray tracing-related operations.

[0082] The accelerator 414 (e.g., a hardware accelerator cluster) has a wide range of applications in autonomous driving. The PVA can be a programmable vision accelerator that can be used for key processing stages in ADAS and autonomous vehicles. The PVA's capabilities are ideally suited to algorithm domains that require predictable processing with low power and low latency. In other words, the PVA works well for semi-dense or dense regular computations, even on small datasets that require predictable runtime with low latency and low power. Therefore, in the context of an autonomous vehicle platform, the PVA is designed to run classical computer vision algorithms due to its efficiency in object detection and operating on integer arithmetic.

[0083] For example, according to one embodiment of the present technology, PVA is used to perform computer stereo vision. In some examples, a semi-global matching-based algorithm may be used, but this is not intended to be limiting. Many applications for Level 3-5 autonomous driving require on-the-fly motion estimation / stereo matching (structure derived from motion, pedestrian recognition, lane detection, etc.). PVA can perform computer stereo vision functions with input from two monocular cameras.

[0084] In some examples, PVAs may be used to perform dense optical flow. For example, PVAs may be used to process raw radar data (e.g., using a 4D fast Fourier transform) to provide a processed radar signal before emitting the next radar pulse. In other examples, PVAs may be used to perform time-of-flight depth processing, for example, by processing raw time-of-flight data to provide processed time-of-flight data.

[0085] DLA can be used to implement any type of network that enhances control and driving safety, such as a neural network that outputs a confidence value for each object detection. Such a confidence value can be interpreted as a probability or as providing the relative "weight" of each detection compared to other detections. This confidence value allows the system to make further decisions regarding which detections are considered true positives rather than false positives. For example, the system can set a confidence threshold and only consider detections above the threshold as true positives. 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 reliable detections should be considered to trigger AEB. DLA can implement a neural network that regresses a confidence value. The neural network can use as input at least a subset of parameters, such as bounding box dimensions, an estimate of the ground plane obtained (e.g., from another subsystem), the orientation of the vehicle 400, the output of an inertial measurement unit (IMU) sensor 466 that correlates with distance, and a 3D position estimate of the object obtained from the neural network and / or other sensors (e.g., a lidar sensor 464 or a radar sensor 460), among others.

[0086] The SoC 404 may include a data store 416 (e.g., memory). The data store 416 may be on-chip memory of the SoC 404 and may store neural networks running on the GPU and / or DLA. In some examples, the data store 416 may be large enough to store multiple instances of the neural network for redundancy and safety. The data store 416 may include an L2 or L3 cache 412. As described herein, references to the data store 416 may include references to memory associated with the GPU, DLA, and / or other accelerators 414.

[0087] The SoC 404 may include one or more processors 410 (e.g., embedded processors). The processors 410 may include a startup and power management processor, which may be a dedicated processor and subsystem for handling startup power and management functions and associated security enforcement. The startup and power management processor may be part of the SoC 404 boot sequence and may provide runtime power management services. The startup power and management processor may provide clock and voltage programming, assist in system low-power state transitions, manage the SoC 404's thermal and temperature sensors, and / or manage the SoC 404's power state. Each temperature sensor may be implemented as a ring oscillator whose output frequency is proportional to temperature, and the SoC 404 may use the ring oscillator to detect the temperature of the CPU 406, GPU 408, and / or accelerator 414. If the temperature is determined to exceed a threshold, the startup and power management processor may enter a temperature fault routine and place the SoC 404 in a low-power state and / or place the vehicle 400 in a driver safety shutdown mode (e.g., safely shut down the vehicle 400).

[0088] The processor 410 may further include a set of embedded processors that can function as an audio processing engine. The audio processing engine can be an audio subsystem that enables full hardware support for multi-channel audio through multiple interfaces and a wide and flexible range of audio I / O interfaces. In some examples, the audio processing engine is a dedicated processor core with a digital signal processor with dedicated RAM.

[0089] The processor 410 may further include an always-on processor engine that can provide the necessary hardware functionality to support low-power sensor management and wake use cases. The always-on processor engine may include a processor core, tightly coupled RAM, supporting peripherals (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0090] The processor 410 may further include a safety cluster engine that includes a dedicated processor subsystem for handling safety management for 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 safety mode, the two or more cores operate in lockstep mode and function as a single core with comparison logic to detect differences between operations.

[0091] The processor 410 may further include a real-time camera engine, which may include a dedicated processor subsystem for handling real-time camera management.

[0092] The processor 410 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.

[0093] The processor 410 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 generate the final image in the player window. The video image compositor may perform lens distortion correction on the wide-view camera 470, the surround camera 474, and / or the in-cabin surveillance camera sensor. The in-cabin surveillance camera sensor is preferably monitored by a neural network running on another instance of a high-performance SoC and configured to identify in-cabin events and respond accordingly. The in-cabin system may perform lip reading to activate and place calls to mobile phone services, 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 the vehicle is operating in autonomous mode and are disabled otherwise.

[0094] The video image synthesizer may include enhanced temporal noise reduction that reduces both spatial and temporal noise. For example, when motion occurs in the video, the noise reduction appropriately weights spatial information and reduces the weight of information provided by adjacent frames. When an image or portion of an image does not contain motion, the temporal noise reduction performed by the video image synthesizer can use information from previous images to reduce noise in the current image.

[0095] The video image compositor may also be configured to perform stereo correction on the input stereo lens frames. The video image compositor may further be used for user interface composition when the operating system desktop is in use, and the GPU 408 does not need to continuously render new surfaces. Even when the GPU 408 is driven and actively performing 3D rendering, the video image compositor can be used to offload the GPU 408, improving performance and responsiveness.

[0096] The SoC 404 may further include a Mobile Industrial Processor Interface (MIPI) camera serial interface to receive 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 SoC 404 may further include an input / output controller that may be controlled by software and that may be used to receive I / O signals not associated with a specific role. The SoC 404 may further include peripherals, audio codecs, power management, and / or a wide range of peripheral interfaces to enable communication with other devices. The SoC 404 may be used to process data from cameras (e.g., connected via gigabit multimedia serial links and Ethernet), sensors (e.g., lidar sensors 464, radar sensors 460, etc., which may be connected via Ethernet), data from bus 402 (e.g., vehicle 400 speed, steering wheel position, etc.), and GNSS sensors 458 (e.g., connected via Ethernet or a CAN bus). The SoC 404 may further include a dedicated high-performance mass storage controller, which may include its own DMA engine, that may be used to offload routine data management tasks from the CPU 406.

[0097] The SoC 404 can be an end-to-end platform with a flexible architecture spanning levels 3-5 of automation, providing a comprehensive functional safety architecture that leverages and efficiently uses computer vision and ADAS technologies for diversity and redundancy, along with deep learning tools, to provide a platform for a flexible and reliable driving software stack. The SoC 404 can be faster, more reliable, and potentially more energy- and space-efficient than traditional systems. For example, the accelerator 414, when combined with the CPU 406, GPU 408, and data store 416, can provide a fast and efficient platform for a level 3-5 autonomous vehicle.

[0098] This technology therefore offers capabilities not possible with conventional systems. For example, computer vision algorithms can be executed on a CPU, which can be configured using a high-level programming language, such as the C programming language, to perform 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, a requirement for in-vehicle ADAS applications and practical Level 3-5 autonomous vehicles.

[0099] In contrast to conventional systems, by providing a CPU complex, a GPU complex, and a hardware acceleration cluster, the technology described herein allows multiple neural networks to run simultaneously and / or sequentially and combine the results to enable Level 3-5 autonomous driving capabilities. For example, a CNN running on the DLA or dGPU (e.g., GPU 420) may include text and word recognition, enabling the supercomputer to read and understand traffic signs, including signs for which the neural network was not specifically trained. The DLA may further include a neural network that can identify, interpret, and understand the meaning of signs and pass that semantic understanding to a path planning module running on the CPU complex.

[0100] As another example, multiple neural networks required for Level 3, 4, or 5 driving can be run simultaneously. For example, a warning sign reading "Caution: Flashing lights indicate icy conditions," along with a light, can be interpreted individually or jointly by several neural networks. The sign itself can 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" can be interpreted by a second deployed neural network, which notifies the vehicle's route planning software (preferably running on the CPU complex) that icy conditions exist if a flashing light is detected. The flashing light can be identified by running a third deployed neural network over multiple frames and notifying the vehicle's route planning software of the presence (or absence) of the flashing light. All three neural networks can run simultaneously, such as within the DLA and / or on the GPU 408.

[0101] In some examples, a CNN for facial recognition and vehicle owner identification can use data from a camera sensor to identify the presence of an authorized driver and / or owner of the vehicle 400. An always-on sensor processing engine can be used to unlock the vehicle when the owner approaches the driver's door and turns on the lights, and in security mode, disable the vehicle when the owner leaves the vehicle. In this way, the SoC 404 provides security against theft and / or carjacking.

[0102] In another example, a CNN for emergency vehicle detection and identification can use data from microphone 496 to detect and identify emergency vehicle sirens. Unlike conventional systems that use general classifiers to detect sirens and manually extract features, SoC 404 uses a CNN to classify ambient and urban sounds, as well as visual data. In a preferred embodiment, the CNN running on the DLA is trained to identify the relative closing speed of an emergency vehicle (e.g., using the Doppler effect). The CNN may also be trained to identify emergency vehicles specific to the local area in which the vehicle is operating, as identified by GNSS sensor 458. Thus, for example, when operating in Europe, the CNN attempts to detect European sirens, and when operating in the United States, the CNN attempts to identify only North American sirens. Once an emergency vehicle is detected, with the assistance of ultrasonic sensor 462, the control program can execute emergency vehicle safety routines, such as slowing the vehicle, pulling over to the side of the road, parking, and / or idling the vehicle until the emergency vehicle has passed.

[0103] The vehicle may include a CPU 418 (e.g., a discrete CPU, or dCPU), which may be coupled to the SoC 404 via a high-speed interconnect (e.g., PCIe). The CPU 418 may include, for example, an X86 processor. The CPU 418 may be used to perform any of a variety of functions, such as reconciling potentially inconsistent results between the ADAS sensors and the SoC 404 and / or monitoring the status and health of the controller 436 and / or infotainment SoC 430.

[0104] Vehicle 400 may include a GPU 420 (e.g., a discrete GPU, or dGPU), which may be coupled to SoC 404 via a high-speed interconnect (e.g., NVIDIA NVLINK). GPU 420 may provide additional artificial intelligence functionality, such as by running redundant and / or different neural networks, and may be used to train and / or update neural networks based on input (e.g., sensor data) from sensors of vehicle 400.

[0105] Vehicle 400 may further include a network interface 424, which may include one or more wireless antennas 426 (e.g., one or more wireless antennas for different communication protocols, such as a cellular antenna, a Bluetooth antenna, etc.). Network interface 424 may be used to enable wireless connectivity over the Internet with the cloud (e.g., server 478 and / or other network devices), other vehicles, and / or 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., between networks 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 vehicle 400 with information about vehicles in proximity to vehicle 400 (e.g., vehicles in front of, to the sides of, and / or behind vehicle 400). This functionality may be part of a cooperative adaptive cruise control function of vehicle 400.

[0106] The network interface 424 may include an SoC that provides modulation and demodulation functionality, enabling the controller 436 to communicate over a wireless network. The network interface 424 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 via well-known processes and / or may be performed using a superheterodyne process. In some examples, the radio frequency front end functionality may be provided by a separate chip. The network interface may include radio functionality for communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-Wave, ZigBee, LoRaWAN, and / or other wireless protocols. The vehicle 400 may further include a data store 428, which may include off-chip (e.g., off-SoC 404) storage. The data store 428 may include one or more storage 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.

[0107] Vehicle 400 may further include GNSS sensors 458 (e.g., GPS and / or assisted GPS sensors) to assist in mapping, perception, occupancy grid generation, and / or route planning functions. Any number of GNSS sensors 458 may be used, including, by way of example and not limitation, a GPS using a USB connector with an Ethernet to serial (RS232) bridge. Vehicle 400 may further include radar sensor 460. Radar sensor 460 may be used in vehicle 400 for long-range vehicle detection, even in darkness and / or severe weather conditions. The radar functional safety level may be ASIL B. Radar sensor 460 may access control and object tracking data using CAN and / or bus 402 (e.g., transmitting data generated by radar sensor 460), and in some examples, access Ethernet to access raw data. A wide variety of radar sensor types may be used. By way of example and not limitation, radar sensor 460 may be suitable for use with front, rear, and side radar. In some examples, pulse Doppler radar sensors are used.

[0108] The radar sensor 460 may include different configurations, such as long-range with a narrow field of view, short-range with a wide field of view, or short-range lateral coverage. In some examples, 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 250-meter range. The radar sensor 460 may help distinguish between stationary and moving objects and may be used by ADAS systems for emergency brake assistance and forward collision warning. Long-range radar sensors may include monostatic multimodal radar with multiple (e.g., six or more) fixed radar antennas and high-speed CAN and FlexRay interfaces. In an example with six antennas, the center four antennas may generate a focused beam pattern designed to record the vehicle 400's surroundings at higher speeds while minimizing interference from traffic in adjacent lanes. The other two antennas may expand the field of view, allowing for quick detection of vehicles entering and exiting the vehicle's 400 lane.

[0109] A medium-range radar system may include, by way of example, a range of up to 460 meters (forward) or 80 meters (rearward) and a field of view of up to 42 degrees (forward) or 450 degrees (rearward). 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 installed on either end of the rear bumper, such a radar sensor system can generate two beams and constantly monitor the blind spots behind and adjacent to the vehicle.

[0110] ADAS systems may use short-range radar systems for blind spot detection and / or lane change assistance.

[0111] Vehicle 400 may further include ultrasonic sensors 462. The ultrasonic sensors 462, which may be located on the front, rear, and / or sides of vehicle 400, may be used for parking assistance and / or creating and updating an occupancy grid. A variety of ultrasonic sensors 462 may be used, and different ultrasonic sensors 462 may be used for different detection ranges (e.g., 2.5 m, 4 m). Ultrasonic sensors 462 may operate at an ASIL B functional safety level.

[0112] The vehicle 400 may include a lidar sensor 464. The lidar sensor 464 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. The lidar sensor 464 may be functional safety level ASIL B. In some examples, the vehicle 400 may include multiple lidar sensors 464 (e.g., 2, 4, 6, etc.) that can use Ethernet (e.g., to provide data to a Gigabit Ethernet switch).

[0113] In some examples, the lidar sensor 464 may be capable of providing a list of objects and their distances for a 360-degree field of view. Commercially available lidar sensors 464 may have an advertised range of approximately 100 meters, with an accuracy of 2 cm to 3 cm, supporting, for example, a 100 Mbps Ethernet connection. In some examples, one or more non-protruding lidar sensors 464 may be used. In such examples, the lidar sensor 464 may be implemented as a small device that can be embedded in the front, rear, sides, and / or corners of the vehicle 400. In such examples, the lidar sensor 464 may provide a horizontal field of view of up to 120 degrees and a vertical field of view of up to 35 degrees, with a range of 200 meters, even for objects with low reflectivity. A forward-mounted lidar sensor 464 may be configured to obtain a horizontal field of view of 45 degrees to 135 degrees.

[0114] In some examples, lidar technology such as 3D flash lidar may also be used. 3D flash lidar uses a laser flash as a transmitter to illuminate the vehicle's surroundings up to approximately 200 meters. Flash lidar includes a receptor that records the transit time of the laser pulse and the reflected light for each pixel, which corresponds to the distance from the vehicle to the object. Flash lidar enables high-precision, distortion-free images of the surroundings to be generated with every laser flash. In some examples, four flash lidar sensors may be placed, one on each side of the vehicle 400. Available 3D flash lidar systems include solid-state 3D staring array lidar cameras (e.g., non-scanning lidar devices) with no moving parts other than a fan. Flash lidar devices use Class I (eye-safe) laser pulses of 5 nanoseconds per frame and can capture reflected laser light in the form of a 3D range point cloud and co-registered intensity data. By using flash lidar, the lidar sensor 464 may be less susceptible to motion blur, vibration, and / or shock because flash lidar is a solid-state device with no moving parts.

[0115] The vehicle may further include an IMU sensor 466. In some examples, the IMU sensor 466 may be located at the center of the rear axle of the vehicle 400. The IMU sensor 466 may include, by way of example and not limitation, an accelerometer, a magnetometer, a gyroscope, a magnetic compass, and / or other types of sensors. In some examples, such as a six-axis application, the IMU sensor 466 may include an accelerometer and a gyroscope, while in a nine-axis application, the IMU sensor 466 may include an accelerometer, a gyroscope, and a magnetometer.

[0116] In some embodiments, the IMU sensor 466 may be implemented as a compact, high-performance GPS-aided Inertial Navigation System (GPS / INS) that combines microelectromechanical systems (MEMS) inertial sensors, a highly sensitive GPS receiver, and advanced Kalman filtering algorithms to provide estimates of position, velocity, and attitude. Thus, in some examples, the IMU sensor 466 may enable the vehicle 400 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 466. In some examples, the IMU sensor 466 and the GNSS sensor 458 may be combined into a single integrated unit. The vehicle may include microphones 496 positioned within and / or around the vehicle 400. The microphones 496 may be used for, among other things, emergency vehicle detection and identification.

[0117] The vehicle may further include any number of camera types, including stereo cameras 468, wide-view cameras 470, infrared cameras 472, surround cameras 474, long-range and / or mid-range cameras 498, and / or other camera types. The cameras may be used to capture image data around the entire perimeter of the vehicle 400. The types of cameras used depend on the embodiment and requirements of the vehicle 400, and any combination of camera types may be used to provide the necessary coverage around the vehicle 400. The number of cameras may also 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 Gigabit Multimedia Serial Link (GMSL) and / or Gigabit Ethernet, by way of example and not limitation. Each of the cameras is described in more detail herein with respect to FIGS. 4A and 4B.

[0118] The vehicle 400 may further include a vibration sensor 442. The vibration sensor 442 may measure vibrations of vehicle components, such as axles. For example, changes in vibration may indicate changes in the road surface. In another example, when two or more vibration sensors 442 are used, the difference between the vibrations (e.g., when there is a difference in vibration between a powered axle and a free-spinning axle) may be used to determine friction or slippage of the road surface.

[0119] The vehicle 400 may include an ADAS system 438. In some examples, the ADAS system 438 may include an SoC. The ADAS system 438 may include autonomous / adaptive / automatic cruise control (ACC), cooperative adaptive cruise control (CACC), forward collision warning (FCW), automatic emergency braking (AEB), lane departure warning (LDW), lane keeping assist (LKA), blind spot warning (BSW), rear cross traffic warning (RCTW), collision warning system (CWS), lane centering (LC), and / or other features and functions.

[0120] The ACC system may use radar sensors 460, lidar sensors 464, and / or cameras. The ACC system may include longitudinal ACC and / or lateral ACC. Longitudinal ACC monitors and controls the distance to the vehicle immediately preceding the vehicle 400 and automatically adjusts vehicle speed to maintain a safe distance from the vehicle ahead. Lateral ACC performs distance maintenance and advises the vehicle 400 to change lanes if necessary. Lateral ACC is relevant to other ADAS applications such as LC and CWS.

[0121] CACC uses information from other vehicles, which may be received from other vehicles via a wireless link or indirectly via a network connection (e.g., via the Internet) via network interface 424 and / or wireless antenna 426. 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. Generally, the V2V communication concept provides information about the immediately preceding vehicle (e.g., a vehicle immediately preceding and in the same lane as vehicle 400), while the I2V communication concept provides information about traffic further ahead. A CACC system may include either or both I2V and V2V information sources. Information about vehicles ahead of vehicle 400 may make CACC more reliable, potentially improving traffic flow and reducing road congestion.

[0122] 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 460 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which are electrically coupled to driver feedback such as a display, speaker, and / or vibration components. The FCW system can provide warnings such as in the form of an audible, visual warning, vibration, and / or quick brake pulse.

[0123] 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 460 coupled to a dedicated processor, DSP, FPGA, and / or ASIC. When the AEB system detects a hazard, it typically first alerts the driver to take corrective action to avoid the collision. If the driver does not take corrective action, the AEB system automatically applies the brakes to attempt to prevent or at least mitigate the effects of the predicted collision. The AEB system can include technologies such as dynamic brake support and / or crash imminent braking.

[0124] The LDW system provides visual, audible, and / or tactile warnings, such as vibration of the steering wheel or seat, to alert the driver if the vehicle 400 crosses a lane marking. If the driver indicates an intentional lane departure by activating a turn signal, the LDW system will not activate. The LDW system may use a forward-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which is electrically coupled to driver feedback such as a display, speaker, and / or vibration components.

[0125] An LKA system is a variation of an LDW system, which provides steering input or braking to correct the vehicle 400 if it begins to drift out of its lane. The BSW system detects vehicles in the vehicle's blind spot and alerts the driver. The BSW system can provide visual, audible, and / or tactile warnings to indicate that merging or changing lanes is unsafe. If the driver uses a turn signal, the system can provide an additional warning. The BSW system can use a rear-facing camera and / or radar sensor 460 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which is electrically coupled to driver feedback such as a display, speaker, and / or vibration component.

[0126] 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 400 is backing up. Some RCTW systems include AEB to ensure vehicle braking is applied to avoid a collision. The RCTW system may use one or more rear-facing radar sensors 460 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which are electrically coupled to driver feedback such as a display, speaker, and / or vibration component.

[0127] Conventional ADAS systems are prone to false-positive detection results, which can be annoying and distracting to the driver, but are typically not fatal because the ADAS system alerts the driver, allowing the driver to determine whether a truly safe condition exists and act accordingly. However, in autonomous vehicle 400, when results conflict, vehicle 400 itself must decide whether to heed the results from the primary computer or the secondary computer (e.g., first controller 436 or second controller 436). For example, in some embodiments, ADAS system 438 may be a backup and / or secondary computer that provides perception information to a backup computer rationality module. The backup computer rationality monitor may run redundant and diverse software on hardware components to detect failures in perception and dynamic driving tasks. Output from ADAS system 438 may be provided to a supervisory MCU. When the outputs from the primary and secondary computers conflict, the supervisory MCU must determine how to reconcile the conflict to ensure safe operation.

[0128] In some examples, the primary computer can be configured to provide a confidence score to the monitor MCU, indicating the primary computer's reliability for the selected result. If the confidence score exceeds a threshold, the monitor MCU can follow the primary computer's instructions regardless of whether the secondary computer provides a conflicting or contradictory result. If the confidence score does not meet the threshold, and if the primary and secondary computers indicate different results (e.g., conflicting), the monitor MCU can arbitrate between the computers to determine the appropriate result.

[0129] The monitoring MCU may be configured to execute a neural network trained and configured to determine, based on outputs from the primary and secondary computers, conditions under which the secondary computer will provide a false alarm. Thus, the monitoring MCU's neural network can learn when the secondary computer's output can be trusted and when it cannot. For example, if the secondary computer is a radar-based FCW system, the monitoring MCU's neural network can learn when the FCW system is identifying a metal object that is not actually a hazard, such as a drain grate or manhole cover that triggers an alarm. Similarly, if the secondary computer is a camera-based LDW system, the monitoring MCU's neural network can learn to disable LDW when a bicyclist or pedestrian is present and lane departure is actually the safest maneuver. In embodiments including a neural network executing on the monitoring MCU, the monitoring MCU may include at least one of a DLA or GPU suitable for executing the neural network with associated memory. In preferred embodiments, the monitoring MCU may be provided and / or included as a component of the SoC 404.

[0130] In other examples, the ADAS system 438 may include a secondary computer that performs ADAS functions using traditional rules of computer vision. Thus, the secondary computer may use traditional computer vision rules, in which case the presence of a neural network in the supervisory MCU may improve reliability, safety, and performance. For example, diverse implementations and intentional non-identity may make the overall system more fault-tolerant, particularly to faults caused by software (or software-hardware interface) functions. For example, if software running on the primary computer has a software bug or error, and non-identical software code running on the secondary computer provides the same overall result, the supervisory MCU may have higher confidence that the overall result is correct and that a bug in the software or hardware used by the primary computer did not cause a critical error.

[0131] In some examples, the output of the ADAS system 438 may be provided to a perception block of the primary computer and / or a dynamic driving task block of the primary computer. For example, if the ADAS system 438 indicates a forward collision warning due to an immediately preceding object, the perception block can use this information when identifying the object. In other examples, the secondary computer may have its own neural network that is trained, as described herein, thus reducing the risk of false positives.

[0132] Vehicle 400 may further include an infotainment SoC 430 (e.g., an in-vehicle infotainment system (IVI)). While illustrated and described as an SoC, an infotainment system need not be an SoC and may include two or more separate components. Infotainment SoC 430 may include a combination of hardware and software that may be used to provide audio (e.g., music, personal digital assistants, navigation instructions, news, radio, etc.), video (e.g., TV, movies, streaming, etc.), telephony (e.g., hands-free calling, etc.), network connectivity (e.g., LTE, Wi-Fi, etc.), and / or information services (e.g., navigation systems, rear park assist, wireless data systems, and vehicle-related information such as fuel level, total mileage, brake fuel level, oil level, door opening / closing, air filter information, etc.) to vehicle 400. For example, the infotainment SoC 430 may include a radio, a disc player, a navigation system, a video player, USB and Bluetooth connectivity, a computer, in-car entertainment, Wi-Fi, steering wheel audio controls, hands-free voice control, a head-up display (HUD), an HMI display 434, telematics devices, a control panel (e.g., for controlling and / or interacting with various components, functions, and / or systems), and / or other components. The infotainment SoC 430 may further be used to provide information (e.g., visually and / or audibly) to a user of the vehicle, such as information from an ADAS system 438, automated driving information such as planned vehicle maneuvers, trajectories, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.), and / or other information.

[0133] The infotainment SoC 430 may include GPU functionality. The infotainment SoC 430 may communicate with other devices, systems, and / or components of the vehicle 400 via the bus 402 (e.g., a CAN bus, Ethernet, etc.). In some examples, the infotainment SoC 430 may be coupled to a supervisory MCU so that the infotainment system's GPU can perform some self-driving functions even if the primary controller 436 (e.g., the vehicle's 400 primary and / or backup computer) fails. In such examples, the infotainment SoC 430 may put the vehicle 400 into a safe shutdown mode from the driver, as described herein.

[0134] The vehicle 400 may further include an instrument cluster 432 (e.g., a digital dashboard, an electronic instrument cluster, a digital instrument panel, etc.). The instrument cluster 432 may include a controller and / or a supercomputer (e.g., a separate controller or supercomputer). The instrument cluster 432 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 control, safety system control, navigation information, etc. In some examples, information may be displayed and / or shared between the infotainment SoC 430 and the instrument cluster 432. In other words, the instrument cluster 432 may be included as part of the infotainment SoC 430, or vice versa.

[0135] 4D is a system diagram for communication between a cloud-based server and the example autonomous vehicle 400 of FIG. 4A , according to some embodiments of the present disclosure. System 476 may include a server 478, a network 490, and a vehicle including vehicle 400. Server 478 may include multiple GPUs 484(A)-484(H) (collectively referred to herein as GPUs 484), PCIe switches 482(A)-482(H) (collectively referred to herein as PCIe switches 482), and / or CPUs 480(A)-480(B) (collectively referred to herein as CPUs 480). GPUs 484, CPUs 480, and PCIe switches may be interconnected with a high-speed interconnect, such as an NVLink interface 488 developed by NVIDIA and / or PCIe connections 486, by way of example and not limitation. In some examples, the GPUs 484 are connected via NVLink and / or NVSwitch SoCs, and the GPUs 484 and PCIe switches 482 are connected via PCIe interconnects. While eight GPUs 484, two CPUs 480, and two PCIe switches are shown, this is not intended to be limiting. Depending on the embodiment, each of the servers 478 may include any number of GPUs 484, CPUs 480, and / or PCIe switches. For example, the servers 478 may each include 8, 16, 32, and / or more GPUs 484.

[0136] Server 478 may receive image data from the vehicle via network 490, representing images showing unexpected or changed road conditions, such as recently started road construction. Server 478 may transmit neural network 492, updated neural network 492, and / or map information 494, including information about traffic and road conditions, to the vehicle via network 490. Updates to map information 494 may include updates to HD map 422, such as information about construction sites, potholes, detours, flooding, and / or other obstacles. In some examples, neural network 492, updated neural network 492, and / or map information 494 may result from new training and / or experience represented by data received from any number of vehicles in the environment and / or based on training performed at a data center (e.g., using server 478 and / or other servers).

[0137] The server 478 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 examples, the training data is tagged (e.g., if the neural network benefits from supervised learning) and / or otherwise preprocessed, while in other examples, the training data is not tagged and / or preprocessed (e.g., if the neural network does not require supervised learning). The training may be performed according to one or more classes of machine learning techniques, including, but not limited to, classes such as supervised training, semi-supervised training, unsupervised training, self-learning, reinforcement learning, federated learning, transfer learning, feature learning (including principal component analysis and cluster analysis), multilinear subspace learning, manifold learning, representation learning (including preliminary dictionary learning), rule-based machine learning, anomaly detection, and variations or combinations thereof. Once the machine learning model is trained, it may be used in the vehicle (e.g., transmitted to the vehicle via the network 490) and / or the machine learning model may be used by the server 478 to remotely monitor the vehicle.

[0138] In some examples, server 478 can receive data from vehicles and apply the data to state-of-the-art real-time neural networks for real-time intelligent inference. Server 478 can include deep learning supercomputers and / or dedicated AI computers powered by GPUs 484, such as the DGX and DGX Station machines developed by NVIDIA. However, in some examples, server 478 can include deep learning infrastructure that uses only CPU-powered data centers.

[0139] The deep learning infrastructure of server 478 is capable of rapid real-time inference and can use that capability to evaluate and verify the state of processors, software, and / or associated hardware within vehicle 400. For example, the deep learning infrastructure can receive periodic updates from vehicle 400, such as a series of images and / or objects that vehicle 400 has located in the series of images (e.g., via computer vision and / or other machine learning object classification techniques). The deep learning infrastructure can run its own neural network to identify objects and compare those objects to those identified by vehicle 400; if the results do not match and the infrastructure concludes that vehicle 400's AI is malfunctioning, server 478 can send a signal to vehicle 400 instructing vehicle 400's failsafe computer to assume control, notify the occupants, and complete a safe parking maneuver.

[0140] For inference, server 478 may include a GPU 484 and one or more programmable inference accelerators (e.g., NVIDIA's TensorRT). Combining a GPU-powered server with inference acceleration can enable real-time responsiveness. In other instances, such as when performance is less critical, servers powered by CPUs, FPGAs, and other processors may be used for inference.

[0141] 5 is a block diagram of an exemplary computing device 500 suitable for use in implementing some embodiments of the present disclosure. Computing device 500 may include an interconnection system 502 that directly or indirectly couples the following devices: memory 504, one or more central processing units (CPUs) 506, one or more graphics processing units (GPUs) 508, a communications interface 510, I / O ports 512, input / output components 514, a power supply 516, one or more presentation components 518 (e.g., a display), and one or more logic units 520.

[0142] While the various blocks in FIG. 5 are shown connected by lines via interconnection system 502, this is not intended to be limiting and is for clarity only. For example, in some embodiments, a presentation component 518, such as a display device, may be considered an I / O component 514 (e.g., if the display is a touchscreen). As another example, CPU 506 and / or GPU 508 may include memory (e.g., memory 504 may represent storage in addition to memory for GPU 508, CPU 506, and / or other components). In other words, the computing devices of FIG. 5 are merely exemplary. Categories such as “workstation,” “server,” “laptop,” “desktop,” “tablet,” “client device,” “mobile device,” “handheld device,” “game console,” “electronic control unit (ECU),” “virtual reality system,” “augmented reality system,” and / or other device or system types are not distinguished, as they are all contemplated within the scope of the computing devices of FIG. 5.

[0143] Interconnect system 502 may represent one or more links or buses, such as an address bus, a data bus, a control bus, or a combination thereof. Interconnect system 502 may include 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 or link. In some embodiments, there are direct connections between components. As an example, CPU 506 may be directly connected to memory 504. Further, CPU 506 may be directly connected to GPU 508. When there are direct or point-to-point connections between components, interconnect system 502 may include a PCIe link to effectuate the connections. In these examples, a PCI bus need not be included in computing device 500.

[0144] Memory 504 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 500. 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 include computer storage media and communication media.

[0145] 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 504 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 disks (DVDs) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by computing device 500. As used herein, computer storage media does not itself comprise signals.

[0146] Computer storage 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, computer storage 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.

[0147] The CPUs 506 may be configured to execute at least some of the computer-readable instructions and to control one or more components of the computing device 500 to perform one or more of the methods and / or processes described herein. The CPUs 506 may each include one or more cores (e.g., 1, 2, 4, 8, 28, 72, etc.) capable of simultaneously processing multiple software threads. The CPUs 506 may include any type of processor, and may include different types of processors depending on the type of computing device 500 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 500, the processor may be an Advanced RISC Machine (ARM) processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). The computing device 500 may include one or more CPUs 506 in addition to one or more microprocessors or auxiliary coprocessors, such as mathematical coprocessors.

[0148] In addition to, or as an alternative to, the CPU 506, the GPU 508 may be configured to execute at least some of the computer-readable instructions and control one or more components of the computing device 500 to perform one or more of the methods and / or processes described herein. One or more of the GPUs 508 may be integrated GPUs (e.g., with one or more CPUs 506) and / or one or more of the GPUs 508 may be discrete GPUs. In an embodiment, one or more of the GPUs 508 may be coprocessors of one or more of the CPUs 506. The GPU 508 may be used by the computing device 500 to render graphics (e.g., 3D graphics) or perform general-purpose computations. For example, the GPU 508 may be used for GPU-generated general-purpose computing (GPGPU). The GPU 508 may include hundreds or thousands of cores capable of simultaneously processing hundreds or thousands of software threads. The GPU 508 may generate pixel data for an output image in response to a rendering command (e.g., a rendering command from the CPU 506 received via a host interface). GPU 508 may include graphics memory, such as display memory, for storing pixel data or any other suitable data, such as GPGPU data. The display memory may be included as part of memory 504. GPU 508 may include two or more GPUs operating in parallel (e.g., via links). The links may connect the GPUs directly (e.g., using NVLINK) or through a switch (e.g., using NVSwitch). When combined together, each GPU 508 may generate pixel data or GPGPU data for a different portion of the output or for a different output (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 other GPUs.

[0149] In addition to, or as an alternative to, the CPU 506 and / or GPU 508, the logic unit 520 may be configured to execute at least some of the computer-readable instructions and control one or more components of the computing device 500 to perform one or more of the methods and / or processes described herein. In an embodiment, the CPU 506, the GPU 508, and / or the logic unit 520 may individually or jointly execute any combination of methods, processes, and / or portions thereof. One or more of the logic units 520 may be part of and / or integrated with one or more of the CPUs 506 and / or GPUs 508, and / or one or more of the logic units 520 may be separate components or otherwise external to the CPUs 506 and / or GPUs 508. In an embodiment, one or more of the logic units 520 may be a co-processor of one or more of the CPUs 506 and / or one or more of the GPUs 508.

[0150] Examples of logic unit 520 include one or more processing cores and / or components thereof, such as tensor cores (TCs), tensor processing units (TPUs), pixel visual cores (PVCs), vision processing units (VPUs), graphics processing clusters (GPCs), texture processing clusters (TPCs), streaming multiprocessors (SMs), tree traversal units (TTUs), artificial intelligence accelerators (AIAs), deep learning accelerators (DLAs), arithmetic logic units (ALUs), application specific integrated circuits (ASICs), floating point units (FPUs), I / O elements, peripheral component interconnect (PCI) or peripheral component interconnect express (PCIe) elements, etc.

[0151] The communications interface 510 may include one or more receivers, transmitters, and / or transceivers that enable the computing device 500 to communicate with other computing devices over electronic communications networks, including wired and / or wireless communications. The communications interface 510 may include components and functionality that enable communication over any of several different networks, such as a wireless network (e.g., Wi-Fi, Z-Wave, Bluetooth, Bluetooth LE, ZigBee, etc.), a wired network (e.g., communication over Ethernet or InfiniBand), a low-power wide area network (e.g., LoRaWAN, SigFox, etc.), and / or the Internet.

[0152] The I / O ports 512 may enable the computing device 500 to be logically coupled to other devices, including an I / O component 514, a presentation component 518, and / or other I / O components, some of which may be built-in (e.g., integrated) to the computing device 500. Exemplary I / O components 514 include a microphone, mouse, keyboard, joystick, gamepad, game controller, satellite dish, scanner, printer, wireless device, etc. The I / O component 514 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological input generated by the user. In some cases, the input may be sent to an appropriate network element for further processing. The NUI may implement any combination of speech recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition both on-screen and adjacent to the screen, air gestures, head and eye tracking, and touch recognition (described in more detail below) associated with the display of the computing device 500. Computing device 500 may include a depth camera, such as a stereoscopic camera system, an infrared camera system, an RGB camera system, touchscreen technology, and combinations thereof, for gesture detection and recognition. Additionally, computing device 500 may include an accelerometer or gyroscope (e.g., as part of an inertial measurement unit (IMU)) that enables detection of movement. In some examples, the output of the accelerometer or gyroscope may be used by computing device 500 to render immersive augmented or virtual reality.

[0153] The power supply 516 may include a hardwired power supply, a battery power supply, or a combination thereof. The power supply 516 may provide power to the computing device 500 to enable the components of the computing device 500 to operate. The presentation component 518 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 518 can receive data from other components (e.g., the GPU 508, the CPU 506, etc.) and output data (e.g., as images, video, sound, etc.).

[0154] The present disclosure may be described in the general context of computer code or machine-usable instructions executed by a computer or other machine, such as a personal data assistant or other handheld device, including computer-executable instructions such as program modules. 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 practiced in a variety of system configurations, including handheld devices, consumer electronics, general-purpose computers, more specialized computing devices, etc. The present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.

[0155] FIG. 6 illustrates training and deployment of a machine learning model according to an embodiment of the present disclosure. In at least one embodiment, the machine learning model may include a neural network such as a CNN. An untrained neural network 606 is trained using a training dataset 602, which, in some embodiments of the present disclosure, may be a set of subject images assuming various head poses. In at least one embodiment, the training framework 604 is the PyTorch framework, while in other embodiments, the training framework 604 is TensorFlow, Boost, Caffe, Microsoft Cognitive Toolkit / CNTK, MXNet, Chainer, Keras, Deeplearning4j, or other training frameworks. The training framework 604 trains the untrained neural network 606 using processing resources described herein to generate a trained neural network 608. In at least one embodiment, the initial weights may be selected randomly or by pre-training using a deep belief network. Training may be performed in a supervised, partially supervised, or unsupervised manner.

[0156] In at least one embodiment, such as when a regression classifier is used, the untrained neural network 606 can be trained using supervised learning, where the training dataset 602 includes inputs paired with desired outputs, or the training dataset 602 includes inputs with known outputs, and the neural network's outputs are manually evaluated. In at least one embodiment, the untrained neural network 606 is trained in a supervised manner. The training framework 604 processes inputs from the training dataset 602 and compares the resulting outputs to a set of expected or desired outputs. In at least one embodiment, errors are then backpropagated through the untrained neural network 606. The training framework 604 adjusts the weights that control the untrained neural network 606. The training framework 604 may include tools to monitor how well the untrained neural network 606 is converging toward a model, such as the trained neural network 608, that is suitable for generating correct answers, such as in the results 614, based on known input data, such as the new data 612. In at least one embodiment, the training framework 604 iteratively trains the untrained neural network 606 using a loss function and tuning process, such as stochastic gradient descent, adjusting the weights to refine the output of the untrained neural network 606. In at least one embodiment, the training framework 604 trains the untrained neural network 606 until the untrained neural network 606 achieves a desired accuracy. The trained neural network 608 can then be deployed to implement any number of machine learning operations.

[0157] In at least one embodiment, the untrained neural network 606 can be trained using unsupervised learning, where the untrained neural network 606 attempts to train itself using unlabeled data. In at least one embodiment, the unsupervised learning training dataset 602 can include input data without associated output or “ground truth” data. The untrained neural network 606 can learn groupings within the training dataset 602 and determine how individual inputs are associated with the untrained dataset 602. In at least one embodiment, unsupervised training can be used to generate self-organizing maps, a type of trained neural network 608 that can perform operations useful for reducing the dimensionality of new data 612. Unsupervised training can also be used to perform anomaly detection, which allows for the identification of data points in the new dataset 612 that deviate from normal or existing patterns in the new dataset 612.

[0158] In at least one embodiment, semi-supervised learning may be used, which is a technique in which the training dataset 602 includes a mixture of labeled and unlabeled data. Thus, the training framework 604 may be used to perform incremental learning, such as via transfer learning techniques. Such incremental learning allows the trained neural network 608 to adapt to new data 612 without forgetting the knowledge instilled into the network during initial training.

[0159] FIG. 7 is a flowchart illustrating process steps for determining gaze direction and mapping this gaze direction to a region of an arbitrary three-dimensional shape, according to an embodiment of the present disclosure. The process of FIG. 7 may begin with the computing device 300 receiving a set of three-dimensional surfaces corresponding to the subject's surrounding environment (step 700). The computing device 300 also receives images of the subject captured by a camera (step 710). Next, the computing device 300 identifies the subject's face and eyes in the received images and determines facial landmark values, associated confidence values, and eye cropping as described above (step 720). These quantities are then used as input variables for regression-based estimation of gaze vectors by the adaptive inference fusion module 280 of FIG. 2B (step 730), as well as input to the gaze origin estimation module 240 of FIG. 2A to determine the origin of the gaze vector (step 740). As described above, the gaze origin is determined, inter alia, from facial landmarks.

[0160] Once the line of sight vector and its origin have been determined, mapping module 250 of Figure 2A determines the intersection, if any, of the line of sight vector with the three-dimensional surface of step 700 (step 750). The surface or area intersecting the line of sight vector is then output and any responsive action may be initiated (step 760).

[0161] It should be noted that the systems and processes of the presently disclosed embodiments can be used to determine the intersection of the line of sight with surfaces both within / on an object and outside the object. In particular, the three-dimensional surfaces imported into the mapping module 250 can include the surface of the object as well as surfaces external or distant from the object, and the mapping module 250 can determine the intersection of the line of sight vector with both the surface of the object and surfaces distant from the object. For example, the set of three-dimensional surfaces can include surfaces inside the vehicle as well as objects external to the vehicle, such as stop signs, traffic lights, and simulated pedestrians. The mapping module 250 can then determine both the vehicle window through which the driver is looking and whether the driver is looking at a particular object, such as a stop sign. To do this, the vehicle's sensors (e.g., cameras or other image sensors, light detection and ranging (LIDAR) sensors, other remote sensing devices, etc.) can determine the location and shape of objects near the vehicle. The vehicle's processor then converts the sensor outputs into three-dimensional surfaces in the same coordinate system as the stored three-dimensional vehicle surfaces and stores them as additional surfaces in the set of three-dimensional surfaces. The mapping module 250 can then determine the intersection of the calculated line of sight vector with both the surface of the vehicle and with any stored surfaces of objects external to the vehicle. In this way, the system can determine, for example, whether the driver is aware of, or looking in the direction of, various potential road hazards or other items that should draw the driver's attention.

[0162] As used herein, the listing of "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" can 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. Furthermore, "at least one of element A or element B" can 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" can 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.

[0163] The subject matter of the present disclosure is described with specificity herein to satisfy statutory requirements. However, the description itself is not intended to limit the scope of this disclosure. Rather, the inventors contemplate that the claimed subject matter may be embodied in other ways and may include different steps or combinations of steps similar to those described in this specification, 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 a method used, these terms should not be construed as implying a particular order among the various steps disclosed herein unless and until the order of individual steps is explicitly stated.

[0164] The foregoing description, for purposes of explanation, used specific terminology to provide a thorough understanding of the present disclosure. However, it will be apparent to those skilled in the art that specific details are not required to implement the method and system of the present disclosure. Accordingly, the foregoing description of specific embodiments of the present invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the present invention to the precise forms disclosed. Many modifications and variations are possible in light of the above teachings. For example, facial landmarks and confidence values ​​can be determined in any manner, and gaze vectors can be determined using any regression or other suitable approach. Furthermore, embodiments of the present disclosure contemplate using any three-dimensional surface or volume, determined and characterized in any manner, to determine their intersection with a gaze vector. The embodiments have been chosen and described to best explain the principles of the present invention and its practical applications, so that others skilled in the art can optimally utilize the method and system of the present disclosure, as well as various embodiments with various modifications as appropriate for the particular applications contemplated. Furthermore, different features of the various embodiments, whether disclosed or not, can be mixed and matched or otherwise combined to create further embodiments contemplated by the present disclosure.

Claims

1. 1. A method for determining a line of sight direction over a specified area, comprising: using parallel processing circuitry to determine a gaze direction of the subject, the gaze direction being determined according to the output of a machine learning model having as input one or more features determined from image data corresponding to an image of the subject; obtaining a set of spatial regions corresponding to a spatial model of one or more fields of view from the subject's position; determining from the gaze direction whether the subject's gaze intersects at least one of the spatial regions; If the line of sight of the subject intersects at least one of the spatial regions, initiating an action based on the at least one spatial region intersected by the line of sight of the subject; A method comprising:

2. The method of claim 1 , wherein the machine learning model further comprises a regression model.

3. The method of claim 1 , wherein the spatial region comprises a three-dimensional surface corresponding to a surface of an object.

4. The method of claim 3 , wherein the object is a vehicle.

5. The method of claim 4 , wherein the spatial region comprises a three-dimensional surface visible from inside the vehicle.

6. The machine learning model receives as input: one or more facial landmark points of the subject; the subject's head posture; cropping one or more eyes of the image of the subject; at least one gaze direction of the subject; or a confidence value of at least one gaze direction of the subject; The method of claim 1 , further comprising at least one of:

7. 2. The method of claim 1, further comprising determining a gaze origin, and wherein determining whether the subject's gaze intersects one of the spatial regions further comprises determining whether the subject's gaze intersects one of the spatial regions based on at least the gaze direction and the gaze origin.

8. The method of claim 1 , further comprising receiving the image data generated using a sensor.

9. The method of claim 1 , wherein the initiating further comprises initiating operation of the vehicle.

10. The method of claim 1 , wherein determining whether the subject's line of sight intersects one of the spatial regions further comprises projecting the determined line of sight direction onto at least one of the spatial regions.

11. the set of spatial regions is a first set of spatial regions corresponding to a first field of view from the position of the subject, and the method further comprises: acquiring a second set of spatial regions corresponding to a second field of view from the position of the subject; determining from the determined gaze direction whether the subject's gaze intersects at least one of the second set of spatial regions; if the line of sight of the subject intersects at least one region of the second set of spatial regions, initiating an action based on the at least one region of the second set of spatial regions intersected by the line of sight of the subject; The method of claim 1 , comprising:

12. 10. The method of claim 1, wherein the spatial model is determined according to one of a computer-based model of one or more objects, measurements of the one or more objects, one or more images of the one or more objects, or a machine learning model trained to determine the locations of portions of the one or more objects.

13. The method of claim 1 , wherein the output of the machine learning model further comprises a gaze vector, and the gaze direction is further determined according to the gaze vector.

14. 1. A system for determining a line of sight direction over a specified area, comprising: Memory and 1. A parallel processing circuit, comprising: determining a gaze direction of the subject, the gaze direction being determined according to the output of a machine learning model having as input one or more features determined from image data corresponding to an image of the subject; obtaining a set of spatial regions corresponding to a spatial model of one or more fields of view from the subject's position; determining from the gaze direction whether the subject's gaze intersects at least one of the spatial regions; and a parallel processing circuit configured to initiate an action based on at least one spatial region intersected by the subject's line of sight if the subject's line of sight intersects at least one of the spatial regions; Including, the system.

15. The system of claim 14 , wherein the machine learning model further comprises a regression model.

16. The system of claim 14 , wherein the spatial region comprises a three-dimensional surface corresponding to a surface of an object.

17. The system of claim 16 , wherein the object is a vehicle.

18. The system of claim 17 , wherein the volume of space includes a three-dimensional surface visible from inside the vehicle.

19. The machine learning model receives as input: one or more facial landmark points of the subject; the subject's head posture; cropping one or more eyes of the image of the subject; at least one gaze direction of the subject; or a confidence value of at least one gaze direction of the subject; The system of claim 14 further comprising at least one of:

20. 15. The system of claim 14, wherein the parallel processing circuitry is further configured to determine a gaze origin, and determining whether the subject's gaze intersects one of the spatial regions further comprises determining whether the subject's gaze intersects one of the spatial regions based on at least the gaze direction and the gaze origin.

21. The system of claim 14 , wherein the parallel processing circuitry is further configured to receive the image data generated using a sensor.

22. The system of claim 14 , wherein the initiating further comprises initiating operation of the vehicle.

23. 15. The system of claim 14, wherein determining whether the subject's line of sight intersects one of the spatial regions further comprises projecting the determined line of sight direction onto at least one of the spatial regions.

24. the set of spatial regions is a first set of spatial regions corresponding to a first field of view from the position of the subject, and the parallel processing circuitry: obtaining a second set of spatial regions corresponding to a second field of view from the position of the subject; determining from the determined gaze direction whether the subject's gaze intersects at least one of the second set of spatial regions; and 15. The system of claim 14, further configured to, if the subject's line of sight intersects at least one region of the second set of spatial regions, initiate an action based on the at least one region of the second set of spatial regions intersected by the subject's line of sight.

25. 15. The system of claim 14, wherein the spatial model is determined according to one of a computer-based model of one or more objects, measurements of the one or more objects, one or more images of the one or more objects, or a machine learning model trained to determine the locations of portions of the one or more objects.

26. The system of claim 14 , wherein the output of the machine learning model further comprises a gaze vector, and the gaze direction is further determined according to the gaze vector.

Images