Simulating realistic test data from transformed real-world sensor data for autonomous machine applications

Abstract

In various instances, sensor data recorded in the real world may be utilized to generate transformed sensor data to test one or more functions of a vehicle, such as the functions of an AEB, CMW, LDW, ALC, or ACC system. The sensor data recorded by the sensors may be enhanced, transformed, or otherwise updated to represent sensor data corresponding to state information defined by a simulation test profile for testing the vehicle function. After the test data is generated, the test data may be processed by the vehicle's systems to determine the system's effectiveness with respect to any number of test criteria. As a result, test sets containing additional or alternative instances of sensor data may be generated from the sensor data recorded in the real world to test the vehicle in various test scenarios, including those that may be dangerous to test in the real world.

Description

[Background technology]

[0001] Autonomous driving systems and advanced driver assistance systems (ADAS) may utilize various sensors to perform various tasks, such as lane keeping, lane changing, lane designation, camera calibration, turning, stopping, path planning, and localization. For example, in order for autonomous and ADAS systems to operate independently and efficiently, a real-time or near real-time understanding of the vehicle's surroundings may be provided. This understanding may include information regarding the location of objects, obstacles, lanes and / or intersections in the environment relative to various demarcations, such as lanes, road boundaries, intersections, and / or the like. The surroundings information may be used by the vehicle when making decisions, such as when and / or where to brake, where and for how long to stop, when and whether to change lanes, how fast to go, etc.

[0002] As an example, an ADAS system may use an automatic emergency braking (AEB) system (and / or a collision mitigation warning (CMW) system) to help safely navigate an environment by automatically applying brakes in various situations to avoid potential collisions - and / or providing an indication that the brakes should be applied. For example, an AEB system may be configured to perform a task, such as precharging the brakes, slowing and / or stopping the vehicle, when triggered. Information regarding the location and attributes of objects and / or lanes in the autonomous or semi-autonomous vehicle's environment may prove beneficial to the AEB system when making obstacle avoidance and / or related control decisions, such as where to stop, when to brake, where to initiate braking, and / or the like. Due to the safety-critical nature of AEB systems, these systems must be rigorously tested to verify safe operation during deployment. For example, tests may be performed to determine whether the AEB system accurately triggers the brakes at the correct time or location when the vehicle is traveling toward an object at any of a variety of speeds. However, testing a vehicle's AEB system in a real-world environment can prove dangerous, and simulating a real-world environment for testing can be time consuming and expensive without producing accurate and reliable results.

[0003] For example, some conventional AEB and / or CMW systems may be tested by using playback of sensor data recorded while a vehicle is driven on a test course. The test course may include targets, such as balloons, foam, and / or cardboard cutouts to represent objects, such as vehicles, pedestrians, road signs, etc. Sensor data may be recorded as the vehicle drives towards the targets, and this sensor data may be used to test the AEB system for accuracy, reliability, and safety. However, to accurately and fully test the operability of the AEB system, a large amount of sensor data must be collected in different operating conditions. Collecting such a large and diverse set of sensor data using field testing may be very time-consuming and expensive - for example, the test objects may appear differently and be registered differently by the sensors than real objects (e.g., foam, cardboard, or object cutouts may not yield the same reflective and / or appearance feature image data, LIDAR data, and / or SONAR data that the respective real-world objects yield) - and may ultimately not accurately reflect the real-world performance of the AEB system.

[0004] In some other conventional AEB and / or CMW systems, testing may be performed using simulations created using entirely synthetically generated sensor data in a virtual environment. Such conventional systems allow for a large amount of sensor data to be synthetically generated, but by its very nature, the synthetically generated sensor data may not be as reliable as sensor data collected in a real-world environment. Thus, the performance of the AEB system in the real world may not be accurately reflected in tests performed with synthetically generated sensor data. As a result, these conventional systems may not provide an accurate assessment of the performance of the AEB and / or CMW system and / or may prove erroneously reliable based on synthetic test data but may not operate safely when deployed or tested in a real-world environment. Summary of the Invention [Means for solving the problem]

[0005] Embodiments of the present disclosure relate to simulating realistic test data from transformed real-world sensor data for autonomous machine applications. Systems and methods are disclosed that utilize real-world sensor data captured from vehicle sensors to generate transformed or updated test data corresponding to desired vehicle conditions for testing vehicle functionality, such as the functionality of an automatic emergency braking (AEB) system, a collision mitigation warning (CMW) system, an automatic lane departure warning (ALDW or LDW) system, an automatic lane change (ALC) system, and / or an adaptive cruise control (ACC) system.

[0006] In contrast to conventional systems, such as those described above, the systems and methods of the present disclosure can leverage recorded sensor data from a vehicle operating in the real world with respect to real-world objects to generate test data for use in testing various functions of an autonomous machine, such as an autonomous or semi-autonomous vehicle. For example, the test data can be generated by augmenting, transforming, and / or updating instances of the recorded sensor data that correspond to actual state information that closely resembles the desired state information of the vehicle at a particular simulation point. The simulation point and the corresponding desired state information can be associated with a simulation profile that is generated or determined based on a physical model of the vehicle, a desired initial speed for testing the autonomous vehicle's functions, and / or other criteria. In some instances, the instances of the recorded sensor data selected to correspond to the simulation points of the profile can be transformed using one or more transformations, such as a viewport transformation, to generate the corresponding updated instances. In an embodiment, for example, if an instance of the recorded sensor data has actual state information within a threshold similarity to the desired state information of the simulation point, the recorded instance can be used without transformation, augmentation, or the like. After a test set of data is generated from the recorded sensor data, the test set may be used to test the functionality of the vehicle, and the test results may be used directly or indirectly (e.g., via decoding) to determine the accuracy of the autonomous machine application.

[0007] As a result of converting real-world sensor data to generate test data for testing the functionality of the vehicle, valuable time and computational resources that would have been used - in a conventional system - to record and process additional real-world data can be saved. As such, the process of converting real-world sensor data based on a simulation profile to generate test data can be relatively less expensive, computationally less intensive, and scalable than conventional systems, since the system can increase the amount of test data - more accurate, reliable, and more similar to real-world sensor data - without requiring the use of simulated or virtual data or the recording of large amounts of sensor data in real-world staged test situations. In addition, the test data can be captured while the vehicle is driving backwards from a position close to the object, thereby allowing the test data to be used to simulate a close encounter with the object while maximizing the safety of the data collection (e.g., in this case, a conventional system would have been required to drive toward the object and attempt to stop ahead of the object, which could have been dangerous).

[0008] The present systems and methods for transforming real-world sensor data based on a simulated profile to generate test data for autonomous machine applications are described in detail below with reference to the accompanying drawings. [Brief description of the drawings]

[0009] [Figure 1] 1 is an example data flow diagram illustrating an example process for generating test data for testing one or more functions of an autonomous machine, according to some embodiments of the present disclosure. [Diagram 2] 11 is an illustrative illustration of determining a closest instance of sensor data based on a comparison of actual state information and desired state information of a vehicle, according to some embodiments of the present disclosure. [Figure 3A]1 is an exemplary illustration of a recorded image generated by a sensor of a vehicle, according to some embodiments of the present disclosure. [Figure 3B] 3B is an illustrative illustration of an updated image generated by transforming the recorded image of FIG. 3A according to some embodiments of the present disclosure. [Figure 4] 4 is a flow diagram illustrating an example process for testing functionality of a vehicle, according to some embodiments of the present disclosure. [Diagram 5] 4 is a flow diagram illustrating an example process for testing functionality of a vehicle, according to some embodiments of the present disclosure. [Figure 6A] 1 is an illustration of an example autonomous vehicle, according to some embodiments of the present disclosure. [Figure 6B] 6B is an illustration of camera positions and fields of view for the example autonomous vehicle of FIG. 6A, according to some embodiments of the present disclosure. [Figure 6C] FIG. 6B is a block diagram of an example system architecture of the example autonomous vehicle of FIG. 6A in accordance with some embodiments of the present disclosure. [Figure 6D] FIG. 6B is a system diagram of communication between a cloud-based server and the example autonomous vehicle of FIG. 6A, according to some embodiments of the present disclosure. [Figure 7] FIG. 1 is a block diagram of an example computing device suitable for use in implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Systems and methods are disclosed that relate to transforming real-world sensor data based on a simulated profile to generate test data for an autonomous machine application. The present disclosure may be described with respect to an exemplary autonomous vehicle 600 (alternatively referred to as "vehicle 600" or "ego vehicle 600", examples of which are described with respect to FIGS. 6A-6D), but this is not intended to be limiting. For example, the systems and methods described herein may be used by, without limitation, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more adaptive driver assistance systems (ADAS)), robots, warehouse vehicles, off-road vehicles, flying ships, boats, shuttles, emergency response vehicles, motorcycles, electric or mopeds, aircraft, construction vehicles, submarines, drones, and / or other vehicle types. Further, although testing of automatic emergency braking (AEB) systems is primarily described herein, this is not intended to be limiting and any system of a vehicle may be tested, such as, but not limited to, AEB, collision mitigation warning (CMW), adaptive cruise control (ACC), blind spot monitoring (BSM), cross traffic warning (CTW), etc. Additionally, although the present disclosure may be described with respect to testing of vehicle applications, this is not intended to be limiting and the systems and methods described herein may be used in augmented reality, virtual reality, robotics, security and surveillance, autonomous or semi-autonomous machine applications, and / or any other technology space where generating additional sensor data from recorded sensor data may be useful for testing various functions and / or processes of a respective vehicle or actor type.

[0011] The present systems and methods provide techniques for transforming, enhancing, or otherwise updating recorded sensor data to simulate different conditions, such as different vehicle speeds, different vehicle orientations, different surrounding actor speeds, etc. Additionally, the sensor data can be updated so that initial sensor data can be generated in a real-world environment and / or on a test course using real objects. For example, a vehicle can be driven toward and / or away from real-world objects at a low and safe speed, and the generated sensor data can be enhanced or transformed to simulate less safe driving scenarios, such as when the vehicle is driving toward an object at a high speed. The performance of AEB, CMW, ACC, and / or other systems associated with the vehicle can then be tested using the transformed or updated sensor data.

[0012] To generate transformed sensor data, the sensor data generated during data collection may be tagged with associated state information, such as position, speed, and / or attitude or orientation information (collectively referred to herein as “state information”). During testing, a simulation profile or trajectory may be generated to determine conditions for testing a system of the vehicle, or its functions. A simulation profile may include any number of points, and each point may be associated with desired state information. In some instances, a simulation profile may be generated based on a desired speed and distance for testing the AEB system of the vehicle, such as the starting speed of the ego vehicle and the distance to an ahead object or vehicle. A comparison of the actual state information of a particular point with the state information from the sensor data may be performed, and an instance of sensor data having associated state information that most closely resembles the desired state information of the point, and in an embodiment, corresponds to a previous position in space, may be selected. The closest (previous) instance of recorded sensor data for each point of the simulation profile may then be used to generate transformed sensor data for testing the performance of the AEB system. In some embodiments, a viewport transformation of each pixel may be performed based on intrinsic and / or extrinsic parameters of the sensor that captured the sensor data to generate transformed sensor data from the recorded sensor data. In some embodiments, in addition to or as an alternative to updating the sensor data, the instance of recorded sensor data associated with state information that most closely resembles desired state information for a given point on the simulation profile may be used as the sensor data instance for that point.

[0013] Thus, live perception from sensor data recorded in a real-world environment can be leveraged to generate transformed sensor data for testing a vehicle under changing state conditions. This can allow for an increase in the amount of test data for a vehicle's systems while simultaneously generating test data that is more accurate, reliable, and closer to real-world sensor data than traditional approaches, e.g., where test data is generated using fake objects or synthetic data from a simulated test environment. As a result, the time required to generate test data or perform tests, as well as the cost of generating and simulating a virtual and / or real-world test environment, are reduced.

[0014] Transformed test data generation system The recorded sensor data (e.g., image data, LIDAR data, RADAR data, etc.) may be received and / or generated using sensors (e.g., cameras, RADAR sensors, LIDAR sensors, etc.) located or otherwise disposed on the autonomous or semi-autonomous vehicle. The recorded sensor data may include sensor data recorded as various instances while the vehicle is moving toward, away from, adjacent to, or otherwise in relation to the object. Other sensors (e.g., GNSS, Inertial Measurement Unit (IMU), speed sensors, steering sensors, etc.) may be used to receive and / or generate state information for the vehicle at each of the various instances of the sensor data. Thus, each instance of the sensor data may represent a sensor's perceptual field and associated state information for the vehicle and / or the object. In some instances, the state information may be actual state information of the vehicle, e.g., position, speed, acceleration, orientation, attitude, etc.

[0015] To test an AEB system, various test conditions may be used to determine how the AEB system will perform. These various test conditions may be represented by a simulation profile or trajectory generated for testing the AEB system. In some examples, the simulation profile may include any number of points, and each point may have associated (or desired) state information. The desired state information may include a desired or expected speed, position, acceleration, orientation, and / or attitude of the vehicle for a particular test case scenario. In some instances, the desired state information may be determined based on a desired initial speed of the vehicle and / or a desired distance to another object in the environment.

[0016] In some examples, different sensors may have different frequencies - e.g., a camera may have a frequency of 30 Hz, an IMU sensor may have a frequency of 100-200 Hz, a RADAR sensor may have a frequency of 15-30 Hz, etc. - so a simulation profile may be generated to correspond to the particular frequency of the sensor. As a result, each point along the profile may be associated with a particular sensor (e.g., camera, then RADAR, then IMU, then IMU, then IMU, then camera, then RADAR, then IMU, etc.). Thus, if the recorded sensor data represents actual state information generated from any of several different sensor types having different frequencies, the simulation profile may correspond to one or more of the sensors having several sampling frequencies at each point. Additionally, in some examples, a simulated profile may be generated with more or fewer points to simulate the effect of a lower or higher sampling frequency of a particular sensor and / or to simulate a sensor dropout (e.g., fewer points over several portions of the simulated profile to simulate one or more of the sensor malfunctions). As such, the simulation profile may capture sensor dropouts, noise in the sensor data, jitter in the timing of sensor data generation, and / or other aspects that may allow for further diversification of test scenarios.

[0017] After the profiles are generated, the desired state information is known to the system, and an instance of sensor data having actual state information that most closely resembles that of the desired state information at each point may be selected for association with each point. This instance of sensor data may be referred to as the closest instance of sensor data and may be used - with or without updating - as the sensor data for the point. If the sensor data is to be transformed or expanded, the closest instance of each point may be transformed to align with the desired state information. In some embodiments, a zoom operation may be used to transform the closest instance. In other instances, a viewport transformation may be applied to each pixel of the closest instance to update the sensor data so that the sensor data - referred to herein as the transformed or updated sensor data - more closely aligns with the desired state information. In embodiments in which a viewport transformation is performed, a planar assumption may be used.

[0018] In this way, test data that more closely resembles real-world data can be automatically generated in an efficient and accurate manner for testing vehicle functionality in various scenarios. As such, by utilizing and modifying a limited amount of recorded sensor data, a larger pool of accurate and reliable test data can be generated while saving the cost and time of generating test data on fake or simulated objects and / or in virtual environments.

[0019] Referring to FIG. 1, FIG. 1 is an example data flow diagram illustrating an example process 100 for generating test data for testing various functions of an autonomous machine, according to some embodiments of the present disclosure. It should be understood that this and other configurations described herein are set forth merely as examples, and that the order of components and / or processes may be adjusted without departing from the scope of the present disclosure. Furthermore, additional or alternative components and / or processes other than those described herein may be implemented. In some embodiments, the features, functionality, and / or components used within the process 100 may be similar to those of the autonomous vehicle 600 (FIGS. 6A-6D) and / or the example computing device 700 (FIG. 7). Additionally, in some embodiments, additional and / or alternative features, functionality, and / or components may be used within the process 100 other than those described herein without departing from the scope of the present disclosure.

[0020] The process 100 may include generating and / or receiving recorded data 102 from one or more sensors. The recorded sensor data 102 may be received from one or more sensors of a vehicle (e.g., vehicle 600 of FIGS. 6A-6C and described herein), as a non-limiting example. The recorded sensor data 102 may be used by the vehicle, within the process 100, to test functionality of one or more systems of the vehicle using test data generated by transforming, augmenting, or otherwise updating real-world sensor data based on a simulation profile. For example, the recorded sensor data 102 may include, but is not limited to, sensor data recorded at various instances while the vehicle is moving toward, away from, adjacent to, or otherwise moving toward an object. As another example, the recorded sensor data 102 may include virtual sensor data generated from any number of sensors of a virtual vehicle or other virtual object. In such instances, the virtual sensors may correspond to virtual vehicles or other virtual objects within a simulated environment (e.g., used to test, train, and / or validate neural network performance), and the virtual sensor data may represent sensor data captured by the virtual sensors within the simulated or virtual environment.

[0021] The recorded sensor data 102 may include recorded instances 102A (e.g., recorded instances of sensor data, e.g., images, depth maps, point clouds, etc.) and corresponding recorded state information 102B recorded by one or more sensors of a vehicle moving in the real world. The recorded instances 102A may include, for example, but are not limited to, image data from any of the sensors of the vehicle 600, including, with reference to FIGS. 6A-6C, a stereo camera 668, a wide view camera 670 (e.g., a fisheye camera), an infrared camera 672, a surround camera 674 (e.g., a 360-degree camera), and / or a long-range and / or mid-range camera 678. In some examples, the recorded instances 102A may be generated by other sensor types, such as, without limitation, a RADAR sensor 660, an ultrasonic sensor 662, a LIDAR sensor 664, etc.

[0022] In some embodiments, the recorded instances 102A may correspond to image data representing an image, image data representing a video (e.g., a snapshot of a video), and / or sensor data representing a representation of a sensor's perception field (e.g., a depth map or point cloud for a LIDAR sensor, a value graph for an ultrasonic sensor, etc.). With respect to the recorded instances 102A corresponding to image data, any type of image data format may be used, such as, without limitation, compressed images such as frames resulting from compressed video formats such as H.264 / AVC (Advanced Video Coding) or H.265 / HEVC (High Efficiency Video Coding), raw images originating from Red Clear Blue (RCCB), Red Clear (RCCC), or other types of image sensors, and / or other formats. Additionally, in some instances, the recorded instance 102A may be used in the process 100 without preprocessing (e.g., in raw or captured format), and in other instances, the recorded instance 102A may undergo preprocessing (e.g., noise balancing, demosaicing, scaling, cropping, enhancement, white balancing, tone curve adjustment, etc., e.g., using a sensor data preprocessor (not shown)). As used herein, the recorded instance 102A may refer to raw image data, preprocessed image data, or a combination thereof. The recorded instance 102A may include an original image (e.g., as captured by one or more image sensors), a downsampled image, an upsampled image, a cropped or region of interest (ROI) image, an image that has been otherwise enhanced, and / or a combination thereof.

[0023] The recorded state information 102B may include state information data from any of the sensors of the vehicle 600, including, for example, but not limited to, steering sensor 640, speed sensor 644, brake sensor system 646, throttle / accelerator 652, GNSS sensor 658, IMU sensor 666, and / or any other sensor type that may generate, acquire, and / or record state information for the vehicle at various instances, with reference to FIGS. 6A-6C. For example, the recorded state information 102B may include, but is not limited to, data representing the vehicle state at a time instance corresponding to the capture of the recorded instance 102A of the recorded sensor data 102. As such, as the vehicle 600 is moving toward, away from, adjacent to, or otherwise moving toward an object, state information may be recorded using various sensors, and the state information may be associated with the corresponding recorded instance (e.g., the recorded instance 102A may be tagged - e.g., as metadata). In some instances, the recorded state information 102B may include actual state information of the vehicle 600 (and / or of other detected objects in the environment), such as position, velocity, acceleration, attitude (e.g., orientation), and / or other state information. In this manner, each recorded instance 102A of recorded sensor data 102 may have associated recorded state information 102B that may represent a sensor's field of perception and may be used within the process 100 to generate a transformed or updated instance 110 of the recorded sensor data 102.

[0024] The process 100 may include a simulation profile generator 104 that receives one or more inputs, such as the vehicle physics model 116, a desired speed 118, a distance to one or more objects, a function to be tested, a system to be tested, and / or other inputs, and generates one or more outputs. For example, using the one or more inputs, the simulation profile generator 104 may generate a simulation profile that includes simulation points 104A and corresponding desired state information 104B. The desired state information 104B at each simulation point 104A may include one or more of a desired speed, position, acceleration (e.g., angle, scalar, etc.), orientation, attitude, and / or other state information (e.g., as determined using the vehicle physics model 116) of the vehicle 600 with respect to the underlying test conditions or scenarios of the simulation profile.

[0025] The simulation profile may be used to test the vehicle function (or system) 112 for several test conditions simulated in the simulation profile and for the recorded instance 102A and / or the updated instance 110. For example, various test conditions may be used to determine how the vehicle function 112 performs. A simulation profile (e.g., a trajectory of the vehicle 600) may be generated for each test condition to test the vehicle function (or system) 112 (e.g., a function of the AEB, ACC, or CMW system). When connected, the simulation point 104A may represent a desired trajectory of the vehicle 600 through an environment (e.g., an environment represented in the recorded instance 102A). However, the recorded instances 102A may not directly correspond to the desired state information 104B for each simulation point 104A, and thus the converter 108 may be utilized to convert or otherwise update the closest instance 106 - e.g., the recorded instance 102A having associated recorded state information 102B that most closely resembles the desired state information 104B - to an updated instance 110 that more closely resembles the perceptual field (e.g., field of view) of the sensor that captured the closest instance 106, if a sensor captured an instance of recorded sensor data 102 while the state of the vehicle 600 corresponds to the desired state information 104B.

[0026] As described herein, in some instances, the desired state information 104B and / or the simulation point 104A may be determined based on the vehicle physics model 116 (e.g., received from the vehicle manufacturer), the desired speed 118 of the vehicle 600, the distance to one or more objects in the environment, road geometry or other road information (e.g., surface material or friction coefficient, slope, curvature, etc.), weather information, etc. The vehicle physics model 116 may include information regarding one or more sensors of the vehicle, such as the sensor's location, orientation, function, technical specifications, etc. For example, the vehicle physics model 116 may also include information regarding one or more vehicle functions, such as maximum acceleration or deceleration supported by the vehicle, trigger functionality of an AEB system, alert triggers of a CMW system, the effect of environmental conditions on various functions of the vehicle, tire size, tire wear (e.g., friction coefficient), etc. In some instances, the vehicle physics model 116 may also include vehicle information, such as passenger mass, inertia number, total weight requirement, etc. The vehicle physics model 116 may be used to generate a simulation profile of the test conditions, for example, to determine points in the simulation profile (e.g., when the vehicle 600 is at a certain distance from an object) at which the vehicle must trigger the AEB system to come to a complete stop in time. In such an instance, if the recorded instances 102A do not reflect the desired state information 104B when the vehicle 600 should decide to activate AEB, the recorded instances 102A may not be useful for testing the accuracy of the AEB system. As a result, a recorded instance 102A--e.g., the closest instance 106--may be selected and transformed to generate an updated instance 110 that corresponds to the desired point in space or time at which the vehicle 600 should activate the AEB system. When running a test, if the vehicle 600 does not activate the AEB at the appropriate time, the problem may be diagnosed and corrected. As such, the simulation points 104A and their respective desired state information 104B may be derived from the vehicle physics model 116.

[0027] In another example, the desired speed 118 may be used to generate a simulation profile for the test condition. The desired speed 118 may be a desired initial speed of the vehicle and may be used to determine simulation points 104A at which simulation instances or data are required to test the vehicle function 112. The simulation points 104A may be locations of the simulated vehicle at which updated instances 110 for testing should be generated. The desired initial speed of the vehicle may be used to determine desired state information 104B (e.g., desired position, orientation, speed, acceleration) of the vehicle at any one of the simulation points 104A that defines the vehicle's trajectory for the test condition (e.g., desired initial vehicle speed).

[0028] The simulation profile, e.g., corresponding desired state information 104B, may be utilized to determine a recorded instance 102A to select for transformation of each simulation point 104A. In some instances, the closest instance 106 may be determined based on a comparison of the recorded state information 102B and the desired state information 104B. As such, the closest instance 106 may represent the recorded instance 102A having the smallest deviation from the desired state information 104B. This calculation may include calculating the difference between various state metrics represented by the recorded state information 102B and the desired state information 104B, e.g., velocity difference, orientation or attitude difference, position difference, acceleration difference, etc.

[0029] For example, a percentage difference for each state criterion may be calculated, and the recorded instance 102A with the smallest combined percentage difference may be selected as the closest instance 106. In some instances, various state criteria may be weighted such that having a smaller difference in position may be more important than a difference in velocity, or having a smaller difference in orientation may be more important than having a smaller difference in position, and so on. In such instances, the differences in various state criteria may be weighted differently, and the calculated difference between the recorded state information 102B and the desired state information 104B may factor into the weighting. In yet another instance, various state criteria that require the greatest transformation to the recorded sensor data 102 may be weighted as more important than state criteria that require less transformation. In such instances, a change in pose may be more difficult to calculate an updated instance 110 than for a change in velocity or position, and thus the closest instance 106 may be determined by weighting the difference in pose more heavily. In some instances, the weighting may be different for different sensors that generated the recorded sensor data.

[0030] In some instances, the closest instance 106 may correspond to a location prior to a location from the desired state information 104B, such that sufficient sensor data, e.g., sensor data sufficiently representative of the sensory field, is available to accurately perform the transformation. However, in other instances, the closest instance 106 may be selected at a location prior to or after a location relative to the desired state information 104B. In any instance, the closest instance 106 may be selected based on some criteria and used to generate an updated instance 110 for association with the simulation point 104A corresponding to the desired state information 104B. Once determined, the closest instance 106 may be associated with the respective simulation point 104A and used as a test or updated instance of sensor data for that simulation point, with or without extension, transformation, etc.

[0031] As an example of determining the closest instance 106, referring to the visualization 200 of FIG. 2, the recorded sensor data 210 may represent a recorded trajectory or actual profile of the vehicle as the vehicle moves from an actual state 212A to an actual state 212D with intermediate actual states 212B-212C. The desired sensor data 220 may represent a desired trajectory or simulation profile of the vehicle as the vehicle moves from a desired state 220A to a desired state 222E with intermediate desired states 222B-222D at stimulus points corresponding to the desired states 222A-222E. The actual state information and the desired state information may include vehicle position, orientation, speed, acceleration, attitude, etc. at each recorded instance and the desired instance, respectively. As a non-limiting example, the recorded sensor data 210 may correspond to a vehicle sensor capturing sensor data at the sensor's frame rate when the vehicle is moving toward an object at a speed higher than the desired simulation speed corresponding to the desired sensor data 220. In such instances, the recorded sensor data 210 may include fewer recorded instances or images of the desired sensor data needed to simulate the lower speeds.

[0032] For each desired state 222A-222E, the closest (most similar) instance from the recorded instance may be determined or selected based on the actual states 212A-212D. For example, the closest instance of the desired state 222A may be determined to be the recorded instance of the actual state 212A based on the recorded state information of the actual state 212A that most closely resembles the desired state information at the simulation point corresponding to the state 222A. The actual state 212A may be closest in distance, orientation, speed, and / or combinations thereof to the desired state 222A--and the desired state 222A may be prior to the actual state 212A. Similarly, the closest instances of the desired states 222B, 222C, 222D, and 222E may be determined to be the actual states 212A, 212B, 212C, and 212C, respectively, based on a comparison of the desired state information of each desired state with the actual recorded state information for each recorded state. In some instances, the desired state information may correspond exactly to or be within some predetermined threshold similarity to the actual state information, such that transformation may be unnecessary - e.g., the closest instance may be used as the updated instance without being transformed, expanded, or otherwise updated. For example, the closest instance having a corresponding recorded location within a threshold distance of the desired location may be used as the updated instance for application to vehicle function 112. In some examples, one or more recorded instances may not be used as the closest instance of any desired point, such as, for example, if the recorded instances include a larger number of instances than necessary for the simulated profile.

[0033] In other instances, not shown, the recorded sensor data 210 may be recorded at a slower vehicle speed so that there is a larger number of recorded instances or images recorded by the vehicle sensors. In some embodiments, to have a larger number of recorded sensor data available, the vehicle may travel very slowly during sensor data capture in order to have a more robust set of recorded sensor data from which to select the closest instance.

[0034] When the closest instance 106 is selected or determined, the process 100 may include transforming the closest instance 106 using a transformer 108 to generate an updated instance 110 that more closely aligns with the desired state information 104B at each simulation point 104A. The transformer 108 may be configured to enhance or transform the closest instance 106 for each simulation point 104A based on differences between the desired state information 104B and the recorded state information 102B, e.g., to simulate sensor data (e.g., updated instance 110) that resembles the sensor data as if it were captured from a desired state of the vehicle.

[0035] In some examples, the converter 108 may apply a transformation function to the closest instance 106 based on intrinsic and / or extrinsic parameters of the sensor that captured the closest instance 106. In a non-limiting example, the transformation function may include a viewport transformation that may transform some or all of the pixels of the closest instance 106 to more accurately reflect the desired state information 104B. In such an example, for example, if an imaging sensor is used, a flat ground assumption may be used to estimate the distance of the pixel from the recording sensor. In other examples, for example, if a LIDAR sensor, RADAR sensor, and / or other sensor type is used, a flat ground assumption may be used.

[0036] In some embodiments, rather than applying a transformation function, the converter 108 may use a magnification operation (e.g., zoom in, zoom out), a crop operation, a rotation operation, and / or another operation to transform the closest instance 106. For example, if the closest instance 106 is in a position behind the desired position, the converter 108 may zoom in slightly on the closest instance 106 to compensate for the recorded forward motion of the vehicle. Similarly, if the closest instance 106 is in a position ahead of the desired position, the converter 108 may zoom out slightly on the closest instance 106 to compensate for the recorded backward motion of the vehicle. In other instances, the converter 108 may slow down or speed up the playback of the recorded sensor data 102 to determine the updated instance 110 without transforming, zooming, cropping, rotating, or otherwise.

[0037] 3A and 3B, as an illustrative example, a recorded image 300 may be transformed to generate an updated image 320 using the transformer 108. For example, the recorded image 300 may be recorded by a vehicle sensor while the vehicle 302 is moving toward the utility pole 304 and the van 306 (e.g., a breakdown in the roadway that would require the AEB system to be activated as the vehicle 302 approaches if the driver has not applied the brakes, or in an autonomous application, when the system has not yet begun to slow down and obstacle avoidance functionality is activated). The recording sensor may be a forward-facing camera on the vehicle 302. A viewport transformation may be applied to the recorded image 300 by applying the transformation to some or all of the pixels of the recorded image 300. As shown, the updated image 320 represents the vehicle closer to the van 306 and the utility pole 304 than in the recorded image 300. However, a viewport transformation is performed instead of a simple zoom operation, and the view of the van 306 and the utility pole 304 is altered to more accurately reflect the sensor's perceived field at the desired state. In some instances, the viewport transformation, or other transformation types, may adjust the appearance of the objects, but the resulting updated instances 110 still provide more accurate test data because the majority of the instances of the sensor data more accurately reflect the sensor field at the desired state.

[0038] Referring back to FIG. 1 , the updated instance 110 may be applied to the vehicle function 112 according to the simulation profile to generate test results 114 indicative of the performance of the vehicle function 112 in a desired test scenario. The vehicle function 112 may include any function and / or any system of the vehicle to be tested, such as, but not limited to, an AEB system, a CMW system, an ACC system, and / or the like. The updated instance 110 may be applied to the vehicle function 112 to determine whether the vehicle function 112 is performing in an expected, acceptable, and / or safe manner. In some instances, after testing the vehicle function 112, test results 114 indicative of the performance of the vehicle function (or system) 112 in a test set that includes the updated instance 110 may be generated. For example, the test results 114 of a vehicle function 112 that is an AEB system may include an indication of whether the AEB system was triggered correctly, when the AEB system was triggered, whether the AEB system was triggered at the correct time and / or distance from the object, when / where the brakes were precharged, whether the brakes were precharged, when the vehicle began to decelerate or stop, and / or the like. In some instances, the test results 114 may indicate whether the vehicle function 112 was correctly triggered or actuated. In some other instances, the test results 114 may further simulate the effect of the vehicle function 112 controlling the navigation of the vehicle. In such instances, the passenger vehicle physics model 116 may be used to define the simulation profile of the test scenario and to accurately generate the test results 114 (e.g., if the physics model 116 indicates the stopping capability of the vehicle, this information may be leveraged to determine whether the vehicle came to a stop in time from the point at which the vehicle function 112 was actuated based on processing the updated instance 110). In addition, other criteria may be used, such as those described herein, including road conditions, vehicle conditions, weather, etc.

[0039] 4 and 5, each block of the methods 400 and 500 described herein includes computational processes that may be performed using any combination of hardware, firmware, and / or software. For example, various functions may be performed by a processor executing instructions stored in a memory. The methods 400 and 500 may also be implemented as computer usable instructions stored on a computer storage medium. The methods may be provided by a standalone application, a service, or a hosted service (standalone or in combination with another hosted service), or a plug-in to another product, to name a few. Additionally, the methods 400 and 500 are described with respect to the process and vehicle 600 of FIG. 1 as an example. However, these methods 400 and 500 may additionally or alternatively be performed by any system or process, or any combination of systems and processes, including but not limited to those described herein.

[0040] 4 is a flow diagram illustrating a method 400 for testing a functionality of a vehicle, according to some embodiments of the disclosure. The method 400 includes receiving, at block B402, first sensor data representative of a plurality of instances of a sensor field of a vehicle and second sensor data representative of state information corresponding to the vehicle at each instance of the sensor field. For example, recorded instances 102A representative of a plurality of instances of a sensor field of a vehicle 600 and recorded state information 102B representative of state information corresponding to the vehicle 600 at each instance of the recorded instances 102A may be received, accessed, and / or generated.

[0041] The method 400 includes generating a simulated profile for testing a function of a vehicle at block B404, the simulated profile including desired state information for the vehicle at a plurality of points along the simulated profile. For example, a simulation profile may be generated for testing a vehicle function 112 of a vehicle 600. The simulation profile may include desired state information 104B for the vehicle at a simulation point 104A along the simulation profile.

[0042] The method 400 includes, at block B 406, determining, for a point of the plurality of points, a closest instance of the plurality of instances based at least in part on a comparison of the state information of the point to the respective desired state information. For example, for each of the simulation points 104A, a closest instance 106 of the recorded instances 102A may be determined based at least in part on a comparison of the recorded state information 102A to the respective desired state information 104B of the simulation points 104A.

[0043] The method 400 includes computing a transformation of the closest instance to generate an updated instance corresponding to each desired state information at block B 408. For example, the transformer 108 may compute a transformation of the closest instance 106 to generate an updated instance 110 corresponding to each desired state information 104B.

[0044] The method 400 includes, at block B410, performing a test of the function based at least in part on the updated instance. For example, a test of the vehicle function 112 may be performed based at least in part on the updated instance 110 to generate test results 114. The test of the vehicle function 112 may include loading and / or executing any or all of the updated instance 110, the sensor data, the recorded instances 102A and state information 102B, the simulation profile, the simulation points 104A, and the desired state information 104B into a simulation system to perform a test of the function in a simulated environment.

[0045] 5, which is a flow diagram illustrating a method 500 for testing a functionality of a vehicle, according to some embodiments of the present disclosure. The method 500 includes, at block B502, receiving first sensor data representative of a plurality of instances of a perception field of a sensor of the vehicle and second sensor data representative of state information corresponding to the vehicle at each instance of the perception field. For example, recorded instances 102A representative of a plurality of instances of a perception field of a sensor of a vehicle 600 and recorded state information 102B representative of state information corresponding to the vehicle 600 at each instance of the recorded instances 102A may be received, accessed, and / or generated.

[0046] The method 500 includes generating a simulated profile for testing a function of a vehicle at block B 504, the simulated profile including desired state information for the vehicle at a plurality of points along the simulated profile. For example, a simulation profile may be generated for testing a vehicle function 112 of a vehicle 600. The simulation profile may include desired state information 104B for the vehicle at a simulation point 104A along the simulation profile.

[0047] The method 500 includes, for each of the points, determining an instance of the plurality of instances having respective state information that is most similar to the respective desired state information of the point, at block B 506. For example, for each of the simulation points 104A, a closest instance 106 of the recorded instances 102A having respective recorded state information 102B that is most similar to the respective desired state information 104B of the point may be determined.

[0048] The method 500 includes generating a set of instances from the plurality of instances based at least in part on the determination, at block B 508. For example, the updated instance 110 may be selected (e.g., without transformation or other operations) from the closest instance 106 and / or from an instance generated by the converter 108 based at least in part on the closest instance 106.

[0049] The method 500 includes performing tests of the functions based at least in part on the set of instances at block B 510. For example, tests of the vehicle functions 112 may be performed based at least in part on the updated instances 110 to generate test results 114.

[0050] Exemplary Autonomous Vehicle 6A is an illustration of an example autonomous vehicle 600 according to some embodiments of the present disclosure. Autonomous vehicle 600 (alternatively referred to herein as “vehicle 600”) may include, but is not limited to, passenger vehicles, such as cars, trucks, buses, first responder vehicles, shuttles, electric or mopeds, motorcycles, fire engines, police vehicles, ambulances, boats, construction vehicles, submarines, drones, and / or other types of vehicles (e.g., unmanned and / or carrying one or more passengers). Autonomous vehicles are generally described in terms of automation levels as defined by the National Highway Traffic Safety Administration (NHTSA), a division of the U.S. Department of Transportation, and the Society of Automotive Engineers (SAE) "Taxonomy and Definitions for Terms Related to Driving Automation Systems for On-Road Motor Vehicle" (Standard No. J3016-201806 published June 15, 2018, Standard No. J3016-201609 published September 30, 2016, and previous and future versions of this standard). Vehicle 600 may be capable of functioning according to one or more of levels 3 through 5 of autonomous driving. For example, vehicle 600 may be capable of conditional automation (Level 3), highly automated (Level 4), and / or fully automated (Level 5), depending on the embodiment.

[0051] Vehicle 600 may include components such as a vehicle chassis, body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other components. Vehicle 600 may include a propulsion system 650, such as an internal combustion engine, a hybrid power plant, a fully electric engine, and / or another propulsion system type. Propulsion system 650 may be connected to a drive train of vehicle 600, which may include a transmission, to enable propulsion of vehicle 600. Propulsion system 650 may be controlled in response to receiving a signal from a throttle / accelerator 652.

[0052] A steering system 654, which may include a steering wheel, may be used to steer the vehicle 600 (e.g., along a desired course or route) when the propulsion system 650 is operating (e.g., when the vehicle is moving). The steering system 654 may receive signals from a steering actuator 656. The steering wheel may be an option for fully automated (Level 5) functionality.

[0053] The brake sensor system 646 may be used to operate the vehicle brakes in response to receiving a signal from a brake actuator 648 and / or a brake sensor.

[0054] A controller 636, which may include one or more system on chip (SoC) 604 (FIG. 6C) and / or a GPU, may provide signals (e.g., representations of commands) to one or more components and / or systems of the vehicle 600. For example, the controller may send signals to operate vehicle brakes via one or more brake actuators 648, operate a steering system 654 via one or more steering actuators 656, and operate a propulsion system 650 via one or more throttle / accelerators 652. The controller 636 may include one or more on-board (e.g., integrated) computing devices (e.g., supercomputers) that process sensor signals and output operational commands (e.g., signals representing commands) to enable autonomous driving and / or assist a driver in driving the vehicle 600. The controllers 636 may include a first controller 636 for autonomous driving functions, a second controller 636 for functional safety functions, a third controller 636 for artificial intelligence functions (e.g., computer vision), a fourth controller 636 for infotainment functions, a fifth controller 636 for redundancy in emergency situations, and / or other controllers. In some instances, a single controller 636 may handle two or more of the aforementioned functions, and two or more controllers 636 may handle a single function, and / or any combination thereof.

[0055] Controller 636 may provide signals to control one or more components and / or systems of vehicle 600 in response to sensor data (e.g., sensor inputs) received from one or more sensors. The sensor data may be received from, for example, and without limitation, global navigation satellite system sensors 658 (e.g., global positioning system sensors), RADAR sensors 660, ultrasonic sensors 662, LIDAR sensors 664, inertial measurement unit (IMU) sensors 666 (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones 696, stereo cameras 668, wide-view cameras 670 (e.g., fisheye cameras), infrared cameras 672, surround cameras 674 (e.g., 360 degree cameras), long-range and / or medium-range cameras 698, speed sensors 644 (e.g., for measuring the speed of the vehicle 600), vibration sensors 642, steering sensors 640, brake sensors (e.g., as part of a brake sensor system 646), and / or other sensor types.

[0056] One or more of the controllers 636 may receive input (e.g., represented by input data) from the instrument cluster 632 of the vehicle 600 and provide output (e.g., represented by output data, display data, etc.) via a human-machine interface (HMI) display 634, an audible annunciator, a loudspeaker, and / or other components of the vehicle 600. The output may include information such as vehicle velocity, speed, time, map data (e.g., HD map 622 of FIG. 6C ), position data (e.g., the position of the vehicle 600 on a map, etc.), direction, the positions of other vehicles (e.g., occupancy grid), information regarding objects and the status of objects as perceived by the controller 636, etc. For example, the HMI display 634 may display information regarding the presence of one or more objects (e.g., road signs, warning signs, changing traffic signals, etc.) and / or a driving maneuver that the vehicle has performed, is performing, or will perform (e.g., changing lanes now, taking exit 34B in 2 miles, etc.).

[0057] Vehicle 600 further includes a network interface 624 that can communicate over one or more networks using one or more wireless antennas 626 and / or a modem. For example, network interface 624 can be capable of communication over LTE, WCDMA, UMTS, GSM, CDMA2000, etc. Wireless antenna 626 can also enable communication between objects (e.g., vehicles, mobile devices, etc.) in the environment 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.

[0058] 6B is an illustration of camera positions and fields of view of the example autonomous vehicle 600 of FIG. 6A, according to some embodiments of the present disclosure. The cameras and their respective fields of view are one example embodiment and are not intended to be limiting. For example, additional and / or alternative cameras may be included and / or the cameras may be located in different positions on the vehicle 600.

[0059] The camera type of the camera may include, but is not limited to, a digital camera that may be adapted for use with components and / or systems of the vehicle 600. The camera may be capable of operating at automotive safety integrity level (ASIL) B and / or at another ASIL. The camera type may be capable of any image capture rate, such as 60 frames per second (fps), 620 fps, 240 fps, etc., depending on the embodiment. The camera may be capable of using a rolling shutter, a global shutter, another type of shutter, or a combination thereof. In some instances, the color filter array may include a red clear clear clear (RCCC) color filter array, a red clear clear blue (RCCB) color filter array, a red blue green clear (RBGC) color filter array, a Foveon X3 color filter array, a Bayer sensor (RGGB) color filter array, a monochrome sensor color filter array, and / or another type of color filter array. In some embodiments, clear pixel cameras, such as cameras with RCCC, RCCB, and / or RBGC color filter arrays, may be used in an effort to increase light sensitivity.

[0060] In some instances, one or more of the cameras may be used to perform advanced driver assistance system (ADAS) functions (e.g., as part of a redundant or fail-safe design). For example, a multi-function mono camera may be installed to provide functions including lane departure warning, traffic sign assist, and intelligent headlamp control. One or more of the cameras (e.g., all of the cameras) may simultaneously record and provide image data (e.g., video).

[0061] One or more of the cameras may be mounted in a mounting part, such as a custom designed (3D printed) part, to filter out stray light and reflections from within the vehicle (e.g., reflections from the dashboard reflected in the windshield mirror) that may interfere with the camera's image data capture capabilities. With reference to a side mirror mounting part, the side mirror part may be custom 3D printed such that the camera mounting plate fits the shape of the side mirror. In some instances, the camera may be integrated into the side mirror. For side view cameras, the cameras may also be integrated into four posts at each corner of the cabin.

[0062] A camera (e.g., a forward-facing camera) with a field of view that includes a portion of the environment in front of the vehicle 600 may be used for surround view to help identify the forward path and obstacles and, with the aid of one or more controllers 636 and / or control SoCs, provide information essential to generating an occupancy grid and / or determining a preferred vehicle path. Forward-facing cameras may be used to perform many of the same ADAS functions as LIDAR, including emergency braking, pedestrian detection, and collision avoidance. Forward-facing cameras may also be used for ADAS functions and systems, including other functions such as lane departure warning ("LDW"), autonomous cruise control ("ACC"), and / or traffic sign recognition.

[0063] A variety of cameras may be used in a forward-facing configuration, including, for example, a monocular camera platform including a complementary metal oxide semiconductor (CMOS) color imager. Another example may be a wide-view camera 670 that may be used to capture objects entering the view from the periphery (e.g., pedestrians, crossing traffic, or bicycles). Although only one wide-view camera is shown in FIG. 6B, there may be any number of wide-view cameras 670 in the vehicle 600. In addition, a long-range camera 698 (e.g., a long-view stereo camera pair) may be used for depth-based object detection, especially for objects for which a neural network has not yet been trained. The long-range camera 698 may also be used for object detection and classification, as well as basic object tracking.

[0064] One or more stereo cameras 668 may also be included in the forward-facing configuration. The stereo camera 668 may include an integrated control unit with an extensible processing unit that may provide programmable logic (FPGA) and a multi-core microprocessor with CAN or Ethernet interfaces integrated on a single chip. Such a unit may be used to generate a 3D map of the vehicle's environment, including distance estimates for all points in the image. An alternative stereo camera 668 may include a compact stereo vision sensor that may include two camera lenses (one on the left and one on the right) and an image processing chip that can measure distances from the vehicle to objects of interest and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning functions. Other types of stereo cameras 668 may be used in addition to or instead of those described herein.

[0065] A camera having a field of view that includes a portion of the environment to the side of the vehicle 600 (e.g., a side-view camera) may be used for surround view, providing information used to create and update the occupancy grid and to generate side impact collision warnings. For example, surround cameras 674 (e.g., four surround cameras 674 as shown in FIG. 6B) may be positioned on the vehicle 600. The surround cameras 674 may include a wide-view camera 670, a fish-eye camera, a 360-degree camera, and / or the like. For example, four fish-eye cameras may be positioned at the front, rear, and sides of the vehicle. In an alternative arrangement, the vehicle may use three surround cameras 674 (e.g., left, right, and rear) and may utilize one or more other cameras (e.g., a forward-facing camera) as a fourth surround view camera.

[0066] A camera having a field of view that includes a portion of the environment behind the vehicle 600 (e.g., a rear-view camera) may be used for parking assistance, surround view, rear collision warning, and creating and updating an occupancy grid. As described herein, a wide variety of cameras may be used, including, but not limited to, cameras that are also suitable as forward-facing cameras (e.g., long-range and / or mid-range camera 698, stereo camera 668, infrared camera 672, etc.).

[0067] FIG. 6C is a block diagram of an example system architecture of the example autonomous vehicle 600 of FIG. 6A, according to some embodiments of the present disclosure. It should be understood that this and other arrangements described herein are merely illustrative. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, groupings of functions, etc.) may be used in addition to or instead of those shown, and some elements may be omitted altogether. Furthermore, many of the elements described herein are functional entities that may be implemented as separate or distributed components or in conjunction with other components, and in any suitable combination and location. Various functions described herein as being performed by entities may be implemented by hardware, firmware, and / or software. For example, various functions may be implemented by a processor executing instructions stored in a memory.

[0068] Each of the components, features, and systems of the vehicle 600 of FIG. 6C are shown as being connected via a bus 602. The bus 602 may include a controller area network (CAN) data interface (alternatively referred to as a “CAN bus”). The CAN may be a network within the vehicle 600 used to help control various features and functions of the vehicle 600, such as actuation of brakes, acceleration, braking, steering, windshield wipers, etc. The CAN bus may be configured to have dozens or even hundreds of nodes, each with its own unique identifier (e.g., CAN ID). The CAN bus may be read to find steering angle, ground speed, engine revolutions per minute (RPM), button position, and / or other vehicle status indicators. The CAN bus may be ASIL B compliant.

[0069] The bus 602 is described herein as being a CAN bus, although this is not intended to be limiting. For example, FlexRay and / or Ethernet may be used in addition to or as an alternative to a CAN bus. Additionally, a single line is used to represent the bus 602, although this is not intended to be limiting. There may be any number of buses 602, which may include, for example, one or more CAN buses, one or more FlexRay buses, one or more Ethernet buses, and / or one or more other types of buses using different protocols. In some instances, two or more buses 602 may be used to perform different functions and / or may be used for redundancy. For example, a first bus 602 may be used for collision avoidance functions and a second bus 602 may be used for operational control. In any instance, each bus 602 may communicate with any of the components of the vehicle 600, and two or more buses 602 may communicate with the same component. In some examples, each SoC 604, each controller 636, and / or each computer in the vehicle may have access to the same input data (e.g., input from sensors in the vehicle 600) and may be connected to a common bus, such as a CAN bus.

[0070] Vehicle 600 may include one or more controllers 636, such as those described herein with respect to FIGURE 6A. Controller 636 may be used for a variety of functions. Controller 636 may be coupled to any of a variety of other components and systems of vehicle 600 and may be used for control of vehicle 600, artificial intelligence of vehicle 600, infotainment for vehicle 600, and / or the like.

[0071] Vehicle 600 may include a system on a chip (SoC) 604. SoC 604 may include a CPU 606, a GPU 608, a processor 610, a cache 612, an accelerator 614, a data store 616, and / or other components and features not shown. SoC 604 may be used to control vehicle 600 in a variety of platforms and systems. For example, SoC 604 may be combined in a system (e.g., that of vehicle 600) having an HD map 622 that can obtain map refreshes and / or updates via a network interface 624 from one or more servers (e.g., server 678 of FIG. 6D ).

[0072] CPU 606 may include a CPU cluster or CPU complex (alternatively referred to as a "CCPLEX"). CPU 606 may include multiple cores and / or L2 caches. For example, in some embodiments, CPU 606 may include eight cores in a coherent multiprocessor configuration. In some embodiments, CPU 606 may include four dual-core clusters, each with its own dedicated L2 cache (e.g., a 2M B L2 cache). CPU 606 (e.g., CCPLEX) may be configured to support concurrent cluster operation allowing any combination of CPU 606 clusters to be active at any given time.

[0073] CPU 606 may implement power management capabilities including one or more of the following features: individual hardware blocks may be automatically clock gated when idle to conserve dynamic power, each core clock may be gated when the core is not actively executing instructions by execution of WFI / WFE instructions, each core may be independently power gated, each core cluster may be independently clock gated when all cores are clock gated or power gated, and / or each core cluster may be independently power gated when all cores are power gated. CPU 606 may further implement an enhanced algorithm for managing power states where allowed power states and expected wake-up times are specified and hardware / microcode determines the best power state for entering the cores, clusters, and CCPLEXes. Processing cores may support simplified power state entry sequences in software where work is offloaded to microcode.

[0074] GPU 608 may include an integrated GPU (alternatively referred to herein as an "iGPU"). GPU 608 may be programmable and efficient for parallel workloads. In some instances, GPU 608 may use an enhanced tensor instruction set. GPU 608 may include one or more streaming microprocessors, where each streaming microprocessor may include an L1 cache (e.g., an L1 cache having at least 96 KB storage capacity) and two or more of the streaming microprocessors may share a cache (e.g., an L2 cache having 512 KB storage capacity). In some embodiments, GPU 608 may include at least eight streaming microprocessors. GPU 608 may use a computational application programming interface (API). In addition, GPU 608 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA's CUDA).

[0075] The GPU 608 may be power optimized for best performance in automotive and embedded use cases. For example, the GPU 608 may be fabricated on FinFETs (Fin field-effect transistors). However, this is not intended to be limiting and the GPU 608 may be fabricated using other semiconductor fabrication processes. Each streaming microprocessor may incorporate several mixed-precision processing cores partitioned into multiple blocks. For example, and without limitation, 64 PF32 cores and 32 PF64 cores may be partitioned into four processing blocks. In such an example, each processing block may be assigned 16 FP32 cores, 8 FP64 cores, 16 INT32 cores, two mixed-precision NVIDIA tensor cores for deep learning matrix operations, an L0 instruction cache, a warp scheduler, a dispatch unit, and / or a 64KB register file. In addition, the streaming microprocessor may include independent parallel integer and floating point data paths to provide efficient execution of workloads having a mix of computational and addressing operations. Streaming microprocessors may include independent thread scheduling capabilities to allow finer grain synchronization and coordination among concurrent threads. Streaming microprocessors may include a combined L1 data cache and shared memory unit to improve performance while simplifying programming.

[0076] The GPU 608 may include high bandwidth memory (HBM) and / or a 16GB HBM2 memory subsystem to provide about 900GB / sec peak memory bandwidth in some instances. In some instances, synchronous graphics random-access memory (SGRAM), such as graphics double data rate type five synchronous random-access memory (GDDR5), may be used in addition to or in place of the HBM memory.

[0077] The GPU 608 may include unified memory technology including access counters to enable more accurate movement of memory pages to the processors that access them most frequently, thereby improving the efficiency of storage ranges shared between processors. In some instances, address translation service (ATS) support may be used to enable the GPU 608 to directly access the CPU 606 page tables. In such instances, when the GPU 608 memory management unit (MMU) experiences a miss, an address translation request may be sent to the CPU 606. In response, the CPU 606 may consult its page tables for a virtual-to-real mapping of the address and send the translation back to the GPU 608. As such, the unified memory technology may enable a single unified virtual address space for both the CPU 606 and GPU 608 memories, thereby simplifying GPU 608 programming and porting of applications to the GPU 608.

[0078] In addition, GPU 608 may include access counters that can record the frequency of accesses of GPU 608 to the memory of other processors. The access counters can help ensure that memory pages are moved to the physical memory of the processors that are accessing the pages most frequently.

[0079] The SoC 604 may include any number of caches 612, including those described herein. For example, the cache 612 may include an L3 cache available to (e.g., connected to) both the CPU 606 and the GPU 608. The cache 612 may include a write-back cache that can record line state, such as by using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). The L3 cache may include 4 MB or more, depending on the embodiment, although smaller cache sizes may be used.

[0080] The SoC 604 may include an arithmetic logic unit (ALU) that may be utilized in performing processing for any of the various tasks or operations (e.g., processing DNNs) of the vehicle 600. In addition, the SoC 604 may include a floating point unit (FPU) (or other math co-processor or numeric co-processor type) for performing mathematical operations within the system. For example, the SoC 104 may include one or more FPUs integrated as execution units within the CPU 606 and / or GPU 608.

[0081] The SoC 604 may include one or more accelerators 614 (e.g., hardware accelerators, software accelerators, or a combination thereof). For example, the SoC 604 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. The large on-chip memory (e.g., 4MB of SRAM) may enable the hardware acceleration cluster to accelerate neural networks and other operations. The hardware acceleration cluster may be used to complement the GPU 608 and to offload some of the tasks of the GPU 608 (e.g., to free up more cycles of the GPU 608 to perform other tasks). As an example, the accelerator 614 may be used for target workloads that are stable enough to be suitable for acceleration (e.g., perception, convolutional neural networks (CNNs), etc.). As used herein, the term "CNN" may include all types of CNNs, including region-based or regional convolutional neural networks (RCNNs) and Faster RCNNs (e.g., as used for object detection).

[0082] The accelerator 614 (e.g., a hardware acceleration cluster) may include a deep learning accelerator (DLA). The DLA may include one or more tensor processing units (TPUs) that may be configured to provide an additional 10 trillion operations per second for deep learning applications and inference. The TPU may be an accelerator configured and optimized to perform image processing functions (e.g., CNN, RCNN, etc.). The DLA may further be optimized for a specific set of neural network types and floating point operations, as well as inference. The design of the DLA may provide more performance per millimeter than a general-purpose GPU, greatly exceeding the performance of a CPU. The TPU may perform several functions, including, for example, single instance convolution functions, supporting INT8, INT16, and FP16 data types for both features and weights, as well as post-processor functions.

[0083] The DLA can quickly and efficiently run neural networks, in particular CNNs, on processed or unprocessed data for any of a variety of functions, including but not limited to: CNNs for object identification and detection using data from camera sensors, CNNs for distance estimation using data from camera sensors, CNNs for emergency vehicle detection and identification using data from microphones, CNNs for face recognition and vehicle owner identification using data from camera sensors, and / or CNNs for security and / or safety related events.

[0084] The DLA can perform any function of the GPU 608, and by using an inference accelerator, for example, a designer can target either the DLA or the GPU 608 for any function. For example, a designer can focus on processing CNNs and floating point operations on the DLA, and offload other functions to the GPU 608 and / or other accelerators 614.

[0085] The accelerator 614 (e.g., hardware acceleration cluster) may include a programmable vision accelerator (PVA), which may alternatively be referred to herein as a computer vision accelerator. The PVA may be designed and configured to accelerate computer vision algorithms for advanced driver assistance systems (ADAS), autonomous driving, and / or augmented reality (AR) and / or virtual reality (VR) applications. The PVA may provide a balance between performance and flexibility. For example, each PVA may include, but is not limited to, any number of reduced instruction set computer (RISC) cores, direct memory access (DMA), and / or any number of vector processors, for example.

[0086] The RISC cores may interact with an image sensor (e.g., an image sensor of any of the cameras described herein), an image signal processor, and / or the like. Each RISC core may include any amount of memory. The RISC cores may use any of a number of protocols, depending on the embodiment. In some instances, the RISC cores may run a real-time operating system (RTOS). The RISC cores may be implemented using one or more integrated circuit devices, application specific integrated circuits (ASICs), and / or memory devices. For example, the RISC cores may include an instruction cache and / or tightly coupled RAM.

[0087] The DMA may allow components of the PVA to access system memory independent of the CPU 606. The DMA may support any number of features used to provide optimizations to the PVA, including but not limited to supporting multi-dimensional addressing and / or circular addressing. In some instances, the DMA may support up to six or more dimensions of addressing, which may include block width, block height, block depth, horizontal block stepping, vertical block stepping, and / or depth stepping.

[0088] The vector processor may be a programmable processor that may be designed to efficiently and flexibly execute computer vision algorithm programming and provide signal processing capabilities. In some instances, the PVA may include a PVA core and two vector processing subsystem partitions. The PVA core may include a processor subsystem, a DMA engine (e.g., two DMA engines), and / or other peripherals. The vector processing subsystem may act as the primary processing engine of the PVA and may include a vector processing unit (VPU), an instruction cache, and / or a vector memory (e.g., VMEM). The VPU core may include a digital signal processor, such as, for example, a single instruction, multiple data (SIMD), very long instruction word (VLIW) digital signal processor. The combination of SIMD and VLIW may increase throughput and speed.

[0089] Each vector processor may include an instruction cache and may be coupled to dedicated memory. As a result, in some instances, each vector processor may be configured to execute independently of other vector processors. In other instances, the vector processors included in a particular PVA may be configured to employ data parallelism. For example, in some embodiments, multiple vector processors included in a single PVA may execute the same computer vision algorithm, but on different regions of an image. In other instances, the vector processors included in a particular PVA may execute different computer vision algorithms simultaneously on the same image, or even execute different algorithms on sequential images or portions of an image. In particular, any number of PVAs may be included in a hardware accelerated cluster, and any number of vector processors may be included in each PVA. In addition, the PVAs may include additional error correcting code (ECC) memory to increase overall system security.

[0090] The accelerator 614 (e.g., a hardware acceleration cluster) may include a computer vision network-on-chip and SRAM to provide high bandwidth, low latency SRAM for the accelerator 614. In some instances, the on-chip memory may include, for example and without limitation, at least 4 MB of SRAM consisting of eight field configurable memory blocks that may be accessible by both the PVA and DLA. Each pair of memory blocks may include an advanced peripheral bus (APB) interface, configuration circuitry, controllers, and multiplexers. Any type of memory may be used. The PVA and DLA may access the memory through a backbone that provides the PVA and DLA with high speed access to the memory. The backbone may include a computer vision network-on-chip that interconnects the PVA and DLA to the memory (e.g., using the APB).

[0091] The computer vision network-on-chip may include an interface that determines, prior to transmission of any control signals / addresses / data, that both the PVA and DLA provide ready and valid signals. Such an interface may provide separate phases and separate channels for transmitting control signals / addresses / data, as well as burst type communication for continuous data transfer. This type of interface may follow ISO26262 or IEC61508 standards, although other standards and protocols may be used.

[0092] In some instances, the SoC 604 may include a real-time ray tracing hardware accelerator, such as described in U.S. Patent Application Serial No. 16 / 101,232, filed August 10, 2018. The real-time ray tracing hardware accelerator may be used to quickly and efficiently determine the location and scale of objects (e.g., within a world model) to generate real-time visualization simulations for RADAR signal interpretation, for acoustic propagation synthesis and / or analysis, for simulation of SONAR systems, for general wave propagation simulation, for comparison against LIDAR data for localization and / or other functions, and / or for other uses. In some examples, one or more tree traversal units (TTUs) may be used to perform one or more ray tracing related operations.

[0093] The accelerator 614 (e.g., a hardware accelerator cluster) has a variety of applications for autonomous driving. The PVA may be a programmable vision accelerator that can be used for critical processing stages in ADAS and autonomous vehicles. The capabilities of the PVA are well suited to the domain of algorithms that require predictable processing at low power and low latency. In other words, the PVA works well with semi-dense or dense regular computations on small data sets that require predictable execution times with low latency and low power. Hence, in the context of a platform for autonomous vehicles, the PVA is designed to run classical computer vision algorithms, since the PVA is efficient in object detection and operating on integer computations.

[0094] For example, according to one embodiment of the present technology, the PVA is used to perform computer stereo vision. A semi-global matching based algorithm may be used in some instances, but this is not intended to be limiting. Many applications for Level 3-5 autonomous driving require motion estimation / stereo matching on the fly (e.g., structure from motion, pedestrian recognition, lane detection, etc.). The PVA can perform computer stereo vision functions with input from two monocular cameras.

[0095] In some instances, PVA may be used to perform dense optical flow by processing raw RADAR data (e.g., using a 4D Fast Fourier Transform) to provide processed RADAR. In other instances, PVA is used for time of flight depth processing, for example, by processing raw time of flight data to provide processed time of flight data.

[0096] DLA can be used to implement any type of network to enhance control and driving safety, including, for example, a neural network that outputs a measure of the confidence of each object detection. Such confidence value can be interpreted as a probability or as providing a relative "weight" of each detection compared to other detections. This confidence value allows the system to make further decisions regarding which detections should be considered true positive detections rather than false positive detections. For example, the system can set a confidence threshold and consider only detections above the threshold as true positive detections. In an automatic emergency braking (AEB) system, a false positive detection would cause the vehicle to automatically perform emergency braking, which is clearly undesirable. Therefore, only the most confident detections should be considered as triggers for AEB. DLA can implement a neural network that regresses the confidence value. The neural network may receive as its inputs at least some subset of parameters, such as bounding box dimensions, ground plane estimates obtained (e.g., from another subsystem), inertial measurement unit (IMU) sensor 666 outputs that correlate with vehicle 600 orientation, range, and 3D position estimates of objects obtained from the neural network and / or other sensors (e.g., LIDAR sensor 664 or RADAR sensor 660), and others.

[0097] The SoC 604 may include a data store 616 (e.g., a memory). The data store 616 may be an on-chip memory of the SoC 604 and may store the neural network to be executed on the GPU and / or DLA. In some instances, the data store 616 may have a capacity large enough to store multiple instances of the neural network for redundancy and safety. The data store 612 may comprise an L2 or L3 cache 612. References to the data store 616 may include references to memory associated with the PVA, DLA, and / or other accelerators 614, as described herein.

[0098] The SoC 604 may include one or more processors 610 (e.g., embedded processors). The processors 610 may include a boot and power management processor, which may be a dedicated processor and subsystem for handling boot power and management capabilities and associated security enforcement. The boot and power management processor may be part of the SoC 604 boot sequence and may provide run-time power management services. The boot power and management processor may provide clock and voltage programming, assist with system low power state transitions, manage the SoC 604 thermal and temperature sensors, and / or manage the SoC 604 power states. Each temperature sensor may be implemented as a ring oscillator whose output frequency is proportional to temperature, and the SoC 604 may use the ring oscillator to detect the temperature of the CPU 606, the GPU 608, and / or the accelerator 614. If the temperature is determined to exceed a threshold, the boot and power management processor may enter a temperature fault routine, place the SoC 604 in a lower power state and / or place the vehicle 600 in a Chauffeur safe shutdown mode (e.g., bring the vehicle 600 to a safe shutdown).

[0099] The processor 610 may further include a set of embedded processors that may perform the functions of an audio processing engine. The audio processing engine may be an audio subsystem that allows full hardware support of multi-channel audio through multiple interfaces and a wide and flexible range of audio I / O interfaces. In some instances, the audio processing engine is a dedicated processor core that includes a digital signal processor with dedicated RAM.

[0100] The processor 610 may further include an always-on processor engine that can provide the necessary hardware features to support low power sensor management and wake use cases. The always-on processor engine may include a processor core, tightly coupled RAM, support peripherals (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0101] The processor 610 may further include a safety cluster engine that includes a processor subsystem dedicated to handling safety management of automotive applications. The safety cluster engine may include two or more processor cores, tightly coupled RAM, supporting peripherals (e.g., timers, interrupt controllers, etc.), and / or routing logic. In a safety mode, the two or more cores may operate in lockstep mode and function as a single core with comparison logic to detect any differences between their operations.

[0102] The processor 610 may further include a real-time camera engine, which may include a dedicated processor subsystem for handling real-time camera management.

[0103] The processor 610 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.

[0104] The processor 610 may include a video image compositor, which may be a processing block (e.g., implemented in a microprocessor) that implements video post-processing functions required by the video playback application to produce a final image for the player window. The video image compositor may perform lens distortion correction on the wide-view camera 670, on the surround camera 674, and / or on the in-cabin surveillance camera sensor. The in-cabin surveillance camera sensor is preferably monitored by a neural network running on another instance of the advanced SoC, configured to identify in-cabin events and respond appropriately. The in-cabin system may perform lip reading to activate cellular service and make phone calls, dictate emails, change the vehicle's destination, activate or change the vehicle's infotainment system and settings, or provide voice-activated web surfing. Certain features are only available to the driver when operating in autonomous mode and are disabled otherwise.

[0105] The video image synthesizer may include enhanced temporal noise reduction for both spatial and temporal noise reduction. For example, when motion occurs in the video, the noise reduction reduces the weight of information provided by adjacent frames and appropriately weights the spatial information. When an image or part of an image does not contain motion, the temporal noise reduction performed by the video image synthesizer may use information from previous images to reduce noise in the current image.

[0106] The video image composer may also be configured to perform stereo rectification on the input stereo lens frames. The video image composer may further be used for user interface compositing when the operating system desktop is in use and the GPU 608 is not required to continuously render new surfaces. Even when the GPU 608 is powered on and actively performing 3D rendering, the video image composer may be used to offload the GPU 608 for improved performance and responsiveness.

[0107] The SoC 604 may further include a mobile industry processor interface (MIPI) camera serial interface, a high-speed interface for receiving video and input from a camera, and / or a video input block that may be used for camera and related pixel input functions. The SoC 604 may further include an input / output controller that may be controlled by software and that may be used to receive I / O signals that are not committed to a specific role.

[0108] The SoC 604 may further include a wide range of peripheral interfaces to enable peripherals, audio codecs, power management, and / or communication with other devices. The SoC 604 may be used to process data from cameras (e.g., connected via gigabit multimedia serial links and Ethernet), sensors (e.g., LIDAR sensors 664, RADAR sensors 660, etc., which may be connected via Ethernet), data from the bus 602 (e.g., vehicle 600 speed, steering wheel position, etc.), and data from a GNSS sensor 658 (e.g., connected via Ethernet or CAN bus). The SoC 604 may further include a dedicated high-performance mass storage controller, which may include its own DMA engine and may be used to offload the CPU 606 from routine data management tasks.

[0109] The SoC 604 may be an end-to-end platform with a flexible architecture that spans levels 3-5 of automation, thereby providing a comprehensive functional safety architecture that leverages and efficiently uses computer vision and ADAS techniques for diversity and redundancy, and provides a platform for a flexible, reliable driving software stack along with deep learning tools. The SoC 604 may be faster, more reliable, and more energy- and space-efficient than traditional systems. For example, when the accelerator 614 is combined with the CPU 606, the GPU 608, and the data store 616, the SoC 604 may provide a fast and efficient platform for levels 3-5 of autonomous vehicles.

[0110] Thus, the present technology provides capabilities and functionality that cannot be achieved by conventional systems. For example, computer vision algorithms may be executed on a CPU, which may be configured using a high-level programming language, such as the C programming language, to execute a wide variety of processing algorithms across a wide variety of visual data. However, CPUs often cannot meet the performance requirements of many computer vision applications, such as those related to execution time and power consumption. In particular, many CPUs cannot execute complex object detection algorithms in real time, which is a requirement for in-vehicle ADAS applications and for practical Level 3-5 autonomous vehicles.

[0111] In contrast to conventional systems, by providing a CPU complex, a GPU complex, and a hardware acceleration cluster, the techniques described herein allow multiple neural networks to run simultaneously and / or sequentially and the results to be combined to enable Level 3-5 autonomous driving capabilities. For example, a CNN running on the DLA or dGPU (e.g., GPU620) can include text and word recognition that allows the supercomputer to read and understand traffic signs, including signs for which the neural network was not specifically trained. The DLA can further include neural networks that can identify, interpret, and provide a semantic understanding of the signs and pass the semantic understanding to a route planning module running on the CPU complex.

[0112] As another example, multiple neural networks may be run simultaneously, as required for Level 3, 4, or 5 driving. For example, a warning sign consisting of "Caution: Flashing lights indicate icy conditions" along with a lightning flash may be interpreted by several neural networks, independently or collectively. The sign itself may be identified as a traffic sign by a first deployed neural network (e.g., a trained neural network), and the text "Flashing lights indicate icy conditions" may be interpreted by a second deployed neural network, which informs the vehicle's route planning software (preferably running on the CPU complex) that icy conditions exist when a flashing light is detected. The flashing light may be identified by running a third deployed neural network through multiple frames, informing the vehicle's route planning software of the presence (or absence) of the flashing light. All three neural networks may be run simultaneously, such as within the DLA and / or on the GPU 608.

[0113] In some instances, a CNN for facial recognition and vehicle owner identification can use data from the camera sensors to identify the presence of a legitimate driver and / or owner of the vehicle 600. An always-on sensor processing engine can be used to unlock the vehicle and turn on the lights when the owner approaches the driver's door, and in security mode, to disable vehicle operation when the owner leaves the vehicle. In this manner, the SoC 604 provides security against theft and / or carjacking.

[0114] In another example, a CNN for emergency vehicle detection and identification can detect and identify emergency vehicle sirens using data from microphone 696. In contrast to conventional systems that use general classifiers to detect sirens and manually extract features, SoC 604 uses CNNs for classification of environmental and urban sounds, as well as classification of visual data. In a preferred embodiment, the CNN running on the DLA is trained to identify the relative terminal velocity of emergency vehicles (e.g., by using the Doppler effect). The CNN can also be trained to identify emergency vehicles specific to the local area in which the vehicle is operating, as identified by the GNSS sensor 658. Thus, for example, when operating in Europe, the CNN will attempt to detect European sirens, and when in the United States, the CNN will attempt to identify only North American sirens. After an emergency vehicle is detected, a control program can be used to perform emergency vehicle safety routines, such as slowing the vehicle down, stopping at the side of the road, parking the vehicle, and / or idling the vehicle, with the assistance of ultrasonic sensor 662, until the emergency vehicle has passed.

[0115] The vehicle may include a CPU 618 (e.g., a separate CPU, or a dCPU) that may be coupled to the SoC 604 via a high-speed interconnect (e.g., PCIe). The CPU 618 may include, for example, an X86 processor. The CPU 618 may be used to perform any of a variety of functions, including, for example, reconciling potentially inconsistent results between the ADAS sensors and the SoC 604, and / or monitoring the status and health of the controller 636 and / or the infotainment SoC 630.

[0116] Vehicle 600 may include GPU 620 (e.g., a discrete GPU, or a dGPU), which may be coupled to SoC 604 via a high-speed interconnect (e.g., NVIDIA's NVLINK). GPU 620 may provide additional artificial intelligence capabilities, such as by running redundant and / or different neural networks, and may be used to train and / or update neural networks based on input (e.g., sensor data) from sensors of vehicle 600.

[0117] The vehicle 600 may further include a network interface 624, which may include one or more wireless antennas 626 (e.g., one or more wireless antennas for different communication protocols, such as a cellular antenna, a Bluetooth antenna, etc.). The network interface 624 may be used to enable wireless connections with the cloud over the Internet (e.g., with the server 678 and / or other network devices), with other vehicles, and / or with computing devices (e.g., passenger client devices). To communicate with other vehicles, a direct link may be established between the two vehicles and / or an indirect link may be established (e.g., through a network and via the Internet). A direct link may be provided using a vehicle-to-vehicle communication link. The vehicle-to-vehicle communication link may provide the vehicle 600 information about vehicles in close proximity to the vehicle 600 (e.g., vehicles in front of, beside, and / or behind the vehicle 600). This function may be part of a cooperative adaptive cruise control function of the vehicle 600.

[0118] The network interface 624 may include a SoC that provides modulation and demodulation functions and enables the controller 636 to communicate over a wireless network. The network interface 624 may include a radio frequency front end for upconversion from baseband to radio frequency and downconversion from radio frequency to baseband. The frequency conversion may be performed through well known processes and / or may be performed using a superheterodyne process. In some instances, the radio frequency front end functions may be provided by a separate chip. The network interface may include wireless functions for communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-Wave, ZigBee, LoRaWAN, and / or other wireless protocols.

[0119] The vehicle 600 may further include a data store 628, which may include off-chip (e.g., off-SoC 604) storage. The data store 628 may include one or more memory elements, including RAM, SRAM, DRAM, VRAM, flash, hard disk, and / or other components and / or devices capable of storing at least one bit of data.

[0120] The vehicle 600 may further include a GNSS sensor 658. The GNSS sensor 658 (e.g., a GPS, an aided GPS sensor, a differential GPS (DGPS) sensor, etc.) aids in mapping, perception, occupancy grid generation, and / or route planning functions. Any number of GNSS sensors 658 may be used, including, but not limited to, a GPS using a USB connector with an Ethernet to serial (RS-232) bridge, for example.

[0121] The vehicle 600 may further include a RADAR sensor 660. The RADAR sensor 660 may be used by the vehicle 600 for long-range vehicle detection, even in darkness and / or severe weather conditions. The RADAR functional safety level may be ASIL B. In some instances, the RADAR sensor 660 may use the CAN and / or bus 602 for control and to access object tracking data (e.g., to transmit data generated by the RADAR sensor 660), with access to Ethernet to access raw data. A wide variety of RADAR sensor types may be used. For example, and without limitation, the RADAR sensor 660 may be suitable for front, rear, and side RADAR use. In some instances, a pulsed Doppler RADAR sensor is used.

[0122] The RADAR sensor 660 may include different configurations, such as long range with a narrow field of view, short range with a wide field of view, and short range side coverage. In some instances, the long range RADAR may be used for adaptive cruise control functions. Long range RADAR systems may provide a wide field of view achieved by two or more independent scans, such as within a 250m range. The RADAR sensor 660 may help distinguish between static and moving objects and may be used by ADAS systems for emergency brake assist and forward collision warning. The long range RADAR sensor may include a monostatic multimodal RADAR with multiple (e.g., six or more) fixed RADAR antennas and high speed CAN and FlexRay interfaces. In one instance with six antennas, the center four antennas may create a focused beam pattern designed to record the surroundings of the vehicle 600 at high speeds with minimal interference from traffic in adjacent lanes. The other two antennas may increase the field of view, allowing for rapid detection of vehicles entering or leaving the lane of the vehicle 600.

[0123] As an example, a medium-range RADAR system may include a range of up to 660 meters (front) or 80 meters (rear) and a field of view of up to 42 degrees (front) or 650 degrees (rear). A short-range RADAR system may include, but is not limited to, a RADAR sensor designed to be mounted on either end of the rear bumper. When mounted on either end of the rear bumper, such a RADAR sensor system can create two beams that constantly monitor the blind spots behind and next to the vehicle.

[0124] Short-range RADAR systems may be used in ADAS systems for blind spot detection and / or lane change assist.

[0125] The vehicle 600 may further include ultrasonic sensors 662. The ultrasonic sensors 662, which may be located at the front, rear, and / or sides of the vehicle 600, may be used for parking assist and / or for creating and updating an occupancy grid. A wide variety of ultrasonic sensors 662 may be used, with different ultrasonic sensors 662 being used for different ranges of detection (e.g., 2.5m, 4m). The ultrasonic sensors 662 may operate at a functional safety level of ASIL B.

[0126] The vehicle 600 may include a LIDAR sensor 664. The LIDAR sensor 664 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. The LIDAR sensor 664 may be functional safety level ASIL B. In some instances, the vehicle 600 may include multiple (e.g., 2, 4, 6, etc.) LIDAR sensors 664 that may use Ethernet (e.g., to provide data to a Gigabit Ethernet switch).

[0127] In some instances, the LIDAR sensor 664 may have the ability to provide a list of objects and their distances in a 360-degree field of view. A commercially available LIDAR sensor 664 may have an advertised range of about 600 m, for example, with an accuracy of 2 cm to 3 cm, and with support for a 600 Mbps Ethernet connection. In some instances, one or more non-protruding LIDAR sensors 664 may be used. In such instances, the LIDAR sensor 664 may be implemented as a small device that may be integrated into the front, rear, sides, and / or corners of the vehicle 600. In such instances, the LIDAR sensor 664 may have a range of 200 m even for low-reflecting objects and provide up to a 620-degree horizontal and 35-degree vertical field of view. A front-mounted LIDAR sensor 664 may be configured for a horizontal field of view between 45 and 135 degrees.

[0128] In some instances, LIDAR technology such as 3D flash LIDAR may also be used. 3D flash LIDAR uses a laser flash as a transmitter to illuminate the surroundings of the vehicle up to about 200 m. The flash LIDAR unit includes a receptor that records the laser pulse transit time and the reflected light on each pixel, which in turn corresponds to the range from the vehicle to the object. Flash LIDAR may allow a highly accurate and undistorted image of the surroundings to be generated with every laser flash. In some instances, four flash LIDAR sensors may be deployed, one on each side of the vehicle 600. Available 3D flash LIDAR systems include solid-state 3D steering array LIDAR cameras with no moving parts other than the blower (e.g., non-scanning LIDAR devices). Flash LIDAR devices may use 5 nanosecond Class I (eye-safe) laser pulses per frame and may capture reflected laser light in the form of a 3D range point cloud and coregistered intensity data. By using flash LIDAR, and because flash LIDAR is a solid-state device with no moving parts, the LIDAR sensor 664 may be less susceptible to motion blur, vibration, and / or shock.

[0129] The vehicle may further include an IMU sensor 666. In some instances, the IMU sensor 666 may be positioned at the center of the rear axle of the vehicle 600. The IMU sensor 666 may include, for example, but not limited to, an accelerometer, a magnetometer, a gyroscope, a magnetic compass, and / or other sensor types. In some instances, such as in a 6-axis application, the IMU sensor 666 may include an accelerometer and a gyroscope, while in a 9-axis application, the IMU sensor 666 may include an accelerometer, a gyroscope, and a magnetometer.

[0130] In some embodiments, the IMU sensor 666 may be implemented as a miniature, high-performance GPS-Aided Inertial Navigation System (GPS / INS) that combines micro-electro-mechanical system (MEMS) inertial sensors, highly sensitive GPS receivers, and advanced Kalman filtering algorithms to provide estimates of position, velocity, and attitude. As such, in some instances, the IMU sensor 666 may enable the vehicle 600 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 666. In some instances, the IMU sensor 666 and the GNSS sensor 658 may be combined in a single integrated unit.

[0131] The vehicle may include microphones 696 placed in and / or around the vehicle 600. The microphones 696 may be used for emergency vehicle detection and identification, among other things.

[0132] The vehicle may further include any number of camera types, including stereo cameras 668, wide view cameras 670, infrared cameras 672, surround cameras 674, long and / or mid-range cameras 698, and / or other camera types. The cameras may be used to capture image data around the entire exterior of the vehicle 600. The type of cameras used depends on the embodiment and requirements of the vehicle 600, and any combination of camera types may be used to achieve the required coverage around the vehicle 600. Additionally, the number of cameras may vary depending on the embodiment. For example, the vehicle may include six cameras, seven cameras, ten cameras, twelve cameras, and / or another number of cameras. The cameras may support, by way of example only, Gigabit Multimedia Serial Link (GMSL) and / or Gigabit Ethernet. Each camera is described in further detail herein with respect to FIG. 6A and FIG. 6B.

[0133] The vehicle 600 may further include a vibration sensor 642. The vibration sensor 642 may measure vibrations of vehicle components, such as an axle. For example, a change in vibration may indicate a change in the surface of the road. In another example, when two or more vibration sensors 642 are used, the difference in vibration may be used to determine friction or slippage of the road surface (e.g., when the difference in vibration is between a powered axle and a free-running axle).

[0134] The vehicle 600 may include an ADAS system 638. In some instances, the ADAS system 638 may include a SoC. The ADAS system 638 may include autonomous / adaptive / automatic cruise control (ACC), cooperative adaptive cruise control (CACC), forward crash warning (FCW), automatic emergency braking (AEB), lane departure warning (LDW), lane keep assist (LKA), blind spot warning (BSW), rear cross-traffic warning (RCTW), collision warning system (CWS), lane centering (LC), and / or other features and functions.

[0135] The ACC system may use a RADAR sensor 660, a LIDAR sensor 664, and / or a camera. The ACC system may include longitudinal ACC and / or lateral ACC. Longitudinal ACC monitors and controls the distance to the vehicle directly ahead of the vehicle 600 and automatically adjusts the vehicle speed to maintain a safe distance from the vehicle ahead. Lateral ACC performs distance keeping and advises the vehicle 600 to change lanes when necessary. Lateral ACC is related to other ADAS applications such as LCA and CWS.

[0136] CACC uses information from other vehicles, which may be received from other vehicles via a wireless link via the network interface 624 and / or the wireless antenna 626, or indirectly via a network connection (e.g., via the Internet). A direct link may be provided by a vehicle-to-vehicle (V2V) communication link, while an indirect link may be an infrastructure-to-vehicle (I2V) communication link. In general, a V2V communication concept provides information about the immediately preceding vehicle (e.g., the vehicle directly ahead of the vehicle 600, in the same lane as the vehicle 1100), while an I2V communication concept provides information about the traffic further ahead. A CACC system may include either or both I2V and V2V information sources. Given the information of the vehicles ahead of the vehicle 600, CACC may be more reliable and may potentially allow traffic to flow more smoothly and reduce congestion on the roads.

[0137] 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 660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback such as a display, speaker, and / or vibration components. The FCW system can provide warnings in the form of audio, visual alerts, vibrations, and / or quick brake pulses.

[0138] 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 660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC. When the AEB system detects a hazard, the AEB system typically first alerts the driver to take corrective action to avoid the collision, and if the driver does not take corrective action, the AEB system can automatically apply the brakes as part of an effort to prevent, or at least mitigate, the effects of the predicted collision. The AEB system can include techniques such as Dynamic Brake Support and / or Collision Imminent Braking.

[0139] The LDW system provides visual, audible, and / or tactile warnings, such as vibrations in the steering wheel or seat, to alert the driver when the vehicle 600 crosses a lane marking. The LDW system does not activate when the driver indicates an intentional lane departure by activating a turn signal. The LDW system may use a forward-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback, such as a display, speaker, and / or vibration components.

[0140] The LKA system is a modification of the LDW system, which provides steering input or braking to correct the vehicle 600 if it begins to drift out of its lane.

[0141] The BSW system detects and warns the vehicle driver in the vehicle's blind spot. The BSW system can provide visual, audible, and / or tactile warnings to indicate that merging or changing lanes is unsafe. The system can provide additional warnings when the driver uses a turn signal. The BSW system can use rear-facing cameras and / or RADAR sensors 660 coupled to dedicated processors, DSPs, FPGAs, and / or ASICs electrically coupled to driver feedback, e.g., displays, speakers, and / or vibration components.

[0142] An RCTW system can provide visual, audible, and / or tactile notifications when an object is detected outside the range of the rear camera when the vehicle 600 is backing up. Some RCTW systems include AEB to ensure vehicle brakes are applied to avoid a collision. An RCTW system can use one or more rear-facing RADAR sensors 660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, electrically coupled to driver feedback, e.g., a display, speaker, and / or vibration components.

[0143] Because conventional ADAS systems alert the driver and allow the driver to determine whether a safety condition truly exists and act accordingly, conventional ADAS systems can be prone to producing false positive results that are usually not catastrophic but can be annoying and distracting to the driver. However, in an autonomous vehicle 600, the vehicle 600 itself must decide whether to listen to the results from the primary computer or the secondary computer (e.g., the first controller 636 or the second controller 636) when the results are conflicting. For example, in some embodiments, the ADAS system 638 may be a backup and / or secondary computer to provide perception information to a backup computer rationality module. The backup computer rationality monitor can run redundant and diverse software on hardware components to detect impairments in perception and dynamic driving tasks. Output from the ADAS system 638 may be provided to a supervisory MCU. When the outputs from the primary and secondary computers conflict, the supervisory MCU must decide how to reconcile the conflict to ensure safe operation.

[0144] In some instances, the primary computer may be configured to provide a reliability score to the overseer MCU indicating the reliability of the primary computer in a selected outcome. If the reliability score exceeds a threshold, the overseer MCU may follow the instructions of the primary computer regardless of whether the secondary computers provide conflicting or inconsistent results. If the reliability score does not meet the threshold, and if the primary and secondary computers show different (e.g., conflicting) results, the overseer MCU may arbitrate between the computers to determine the appropriate outcome.

[0145] The supervisory MCU may be configured to execute a neural network that is trained and configured to determine conditions under which the secondary computer provides a false alarm based on the outputs from the primary and secondary computers. Thus, the neural network in the supervisory MCU may learn when the output of the secondary computer may be trusted and when it may not be trusted. For example, when the secondary computer is a RADAR-based FCW system, the neural network in the supervisory MCU may learn when the FCW identifies a metal object that is not actually a hazard, such as a sewer grate or manhole cover, that triggers an alarm. Similarly, when the secondary computer is a camera-based LDW system, the neural network in the supervisory MCU may learn to ignore the LDW when a bicyclist or pedestrian is present and lane departure is, in fact, the safest maneuver. In embodiments that include a neural network executing on the supervisory MCU, the supervisory MCU may include at least one of a DLA or a GPU suitable for executing the neural network with associated memory. In a preferred embodiment, the director MCU may comprise a component of SoC1104 and / or may be included as a component of SoC604.

[0146] In other instances, the ADAS system 638 may include a secondary computer that performs ADAS functions using classical rules of computer vision. As such, the secondary computer may use classical computer vision rules (if-then) and the presence of a neural network in the supervisory MCU may improve reliability, safety and performance. For example, the diverse implementations and intentional non-identity may make the overall system more fault-tolerant, especially to failures caused by software (or software-hardware interface) functions. For example, if there is a software bug or error in the software running on the primary computer and non-identical software code running on the secondary computer provides the same overall result, the supervisory MCU may have greater confidence that the overall result is correct and that a bug in the software or hardware on the primary computer has not caused a critical error.

[0147] In some instances, the output of the ADAS system 638 may be fed 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 638 indicates a forward collision warning due to an object directly ahead, the perception block may use this information when identifying the object. In other instances, the secondary computer may have its own neural network that is trained as described herein, thus reducing the risk of false positives.

[0148] Vehicle 600 may further include an infotainment SoC 630 (e.g., an in-vehicle infotainment system (IVI)). Although illustrated and described as an SoC, the infotainment system may not be an SoC and may include two or more separate components. Infotainment SoC 630 may include a combination of hardware and software that may be used to provide audio (e.g., music, personal digital assistant, navigation instructions, news, radio, etc.), video (e.g., TV, movies, streaming, etc.), telephony (e.g., hands-free calling), network connectivity (e.g., LTE, Wi-Fi, etc.), and / or information services (e.g., navigation system, rear park assist, wireless data system, vehicle related information such as fuel level, total distance traveled, brake fuel level, oil level, door open / close, air filter information, etc.) to vehicle 600. For example, the infotainment SoC 630 may be a radio, a disc player, a navigation system, a video player, USB and Bluetooth connectivity, a car computer, in-car entertainment, Wi-Fi, steering wheel audio controls, hands-free voice control, a heads-up display (HUD), an HMI display 634, a telematics device, a control panel (e.g., for controlling and / or interacting with various components, features, and / or systems), and / or other components. The infotainment SoC 630 may further be used to provide information (e.g., visual and / or audible) to a user of the vehicle, such as information from an ADAS system 638, autonomous driving information such as planned vehicle maneuvers, trajectory, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.), and / or other information.

[0149] The infotainment SoC 630 may include GPU functionality. The infotainment SoC 630 may communicate with other devices, systems, and / or components of the vehicle 600 via the bus 602 (e.g., CAN bus, Ethernet, etc.). In some instances, the infotainment SoC 630 may be coupled to the supervising MCU such that the infotainment system's GPU can perform some self-drive functions in the event that the primary controller 636 (e.g., the vehicle's 600 primary and / or backup computer) fails. In such instances, the infotainment SoC 630 may place the vehicle 600 in a Chauffeur safe shutdown mode, as described herein.

[0150] The vehicle 600 may further include an instrument cluster 632 (e.g., a digital dash, an electronic instrument cluster, a digital instrument panel, etc.). The instrument cluster 632 may include a controller and / or a supercomputer (e.g., a separate controller or a supercomputer). The instrument cluster 632 may include a set of instruments such as a speedometer, a fuel level, an oil pressure, a tachometer, an odometer, a turn signal, a gear shift position indicator, a seat belt warning light, a parking brake warning light, an engine malfunction light, an airbag (SRS) system information, lighting controls, safety system controls, navigation information, etc. In some instances, information may be displayed and / or shared between the infotainment SoC 630 and the instrument cluster 632. In other words, the instrument cluster 632 may be included as part of the infotainment SoC 630, or vice versa.

[0151] 6D is a system diagram of communication between a cloud-based server and an example autonomous vehicle 600 of FIG. 6A according to some embodiments of the disclosure. System 676 may include a server 678, a network 690, and a vehicle including vehicle 600. Server 678 may include multiple GPUs 684(A)-684(H) (collectively referred to herein as GPUs 684), PCIe switches 682(A)-682(H) (collectively referred to herein as PCIe switches 682), and / or CPUs 680(A)-680(B) (collectively referred to herein as CPUs 680). GPUs 684, CPUs 680, and PCIe switches may be interconnected with a high-speed interconnect, such as, but not limited to, an NVLink interface 688 developed by NVIDIA and / or a PCIe connection 686. In some instances, the GPUs 684 are connected via an NVLink and / or NVSwitch SoC, and the GPUs 684 and PCIe switch 682 are connected via a PCIe interconnect. Although eight GPUs 684, two CPUs 680, and two PCIe switches are illustrated, this is not intended to be limiting. Depending on the embodiment, each server 678 may include any number of GPUs 684, CPUs 680, and / or PCIe switches. For example, the servers 678 may each include eight, sixteen, thirty-two, and / or more GPUs 684.

[0152] Server 678 may receive image data from the vehicle over network 690, the image data representing images showing unexpected or changed road conditions, such as recently started road construction. Server 678 may transmit neural network 692, updated neural network 692, and / or map information 694, including information about traffic and road conditions, to the vehicle over network 690. Updates to map information 694 may include updates to HD map 622, such as information about construction sites, potholes, detours, flooding, and / or other obstacles. In some instances, neural network 692, updated neural network 692, and / or map information 694 may have arisen from new training and / or experience represented in data received from any number of vehicles in the environment and / or based on training performed at a data center (e.g., using server 678 and / or other servers).

[0153] The server 678 may be used to train a machine learning model (e.g., a neural network) based on the training data. The training data may be generated by the vehicle and / or generated in a simulation (e.g., using a game engine). In some instances, the training data is tagged (e.g., if the neural network benefits from supervised learning) and / or undergoes other pre-processing, while in other instances, the training data is not tagged and / or pre-processed (e.g., if the neural network does not require supervised learning). The training may be performed according to any one or more classes of machine learning techniques, including, but not limited to, the following classes: supervised training, semi-supervised training, unsupervised training, self-learning, reinforcement learning, federated learning, transfer learning, feature learning (including principal component and cluster analysis), multi-linear subspace learning, manifold learning, representation learning (including preliminary dictionary learning), rule-based machine learning, anomaly detection, and variations or combinations thereof. After the machine-learned model has been traced, the machine-learned model may be used by the vehicle (e.g., transmitted to the vehicle via network 690) and / or the machine-learned model may be used by server 678 to remotely monitor the vehicle.

[0154] In some instances, the server 678 can receive data from the vehicles and apply the data to state-of-the-art real-time neural networks for real-time intelligent inference. The server 678 can include deep learning supercomputers and / or dedicated AI computers powered by GPUs 684, such as the DGX and DGX Station machines developed by NVIDIA. However, in some instances, the server 678 can include a deep learning infrastructure that uses only CPU-powered data centers.

[0155] The deep learning infrastructure of server 678 may be capable of rapid real-time inference and may use that capability to evaluate and validate the health of the processor, software, and / or associated hardware within vehicle 600. For example, the deep learning infrastructure may receive periodic updates from vehicle 600, such as a sequence of images and / or objects that vehicle 600 has located within the sequence of images (e.g., via computer vision and / or other machine learning object classification techniques). The deep learning infrastructure may run its own neural networks to identify objects and compare them to objects identified by vehicle 600, and if the results do not match and the infrastructure concludes that the AI ​​within vehicle 600 is not functioning properly, server 678 may send a signal to vehicle 600 that infers control, notifies passengers, and commands the vehicle's 600 failsafe computer to complete a safe parking maneuver.

[0156] For inference, the server 678 may include a GPU 684 and one or more programmable inference accelerators (e.g., NVIDIA's TensorRT). The combination of a GPU-powered server and inference acceleration can enable real-time responsiveness. In other instances, such as when less performance is required, servers powered by CPUs, FPGAs, and other processors may be used for inference.

[0157] Exemplary Computing Device 7 is a block diagram of an example computing device 700 suitable for use in implementing some embodiments of the present disclosure. The computing device 700 may include an interconnection system 702 that indirectly or directly couples the following devices: memory 704, one or more central processing units (CPUs) 706, one or more graphic processing units (GPUs) 708, a communication interface 710, input / output (I / O) ports 712, input / output components 714, a power supply 716, one or more presentation components 718 (e.g., displays), and one or more logic units 720.

[0158] Although the various blocks in FIG. 7 are shown connected via interconnect system 702 with lines, this is not intended to be limiting and is merely for ease of understanding. For example, in some embodiments, a presentation component 718, such as a display device, may be considered an I / O component 714 (e.g., if the display is a touch screen). As another example, CPU 706 and / or GPU 708 may include memory (e.g., memory 704 may represent a storage device in addition to the memory of GPU 708, CPU 706, and / or other components). In other words, the computing devices of FIG. 7 are merely exemplary. Categories such as "workstations," "servers," "laptops," "desktops," "tablets," "client devices," "mobile devices," "handheld devices," "gaming machines," "electronic control units (ECUs)," "virtual reality systems," and / or other device or system types are all intended to be within the scope of the computing devices of FIG. 7 and therefore are not to be distinguished.

[0159] The interconnect system 702 may represent one or more links or buses, such as an address bus, a data bus, a control bus, or a combination thereof. The interconnect system 702 may include one or more bus or link types, such as an industry standard architecture (ISA) bus, an extended industry standard architecture (EISA) bus, a video electronics standards association (VESA) bus, a peripheral component interconnect (PCI) bus, a peripheral component interconnect express (PCIe) bus, and / or another type of bus or link. In some embodiments, there are direct connections between components. As an example, the CPU 706 may be directly connected to the memory 704. Additionally, the CPU 706 may be directly connected to the GPU 708. When there are direct or point-to-point connections between components, the interconnect system 702 may include a PCIe link to implement the connections. In these examples, a PCI bus need not be included in the computing device 700.

[0160] Memory 704 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 700. Computer readable media may include both volatile and nonvolatile media, and removable and non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media.

[0161] 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 704 may store computer readable instructions (e.g., representing programs and / or program elements), such as an operating system. Computer storage media may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and that may be accessed by computing device 700. As used herein, computer storage media does not include the signals themselves.

[0162] 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 include 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.

[0163] The CPU 706 may be configured to execute at least some of the computer readable instructions to control one or more components of the computing device 700 to perform one or more of the methods and / or processes described herein. The CPU 706 may include one or more (e.g., 1, 2, 4, 8, 28, 72, etc.) cores each capable of processing multiple software threads simultaneously. The CPU 706 may include any type of processor, and may include different types of processors depending on the type of computing device 700 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 700, the processor may be an Advanced RISC Machines (ARM) processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). Computing device 700 may include one or more CPUs 706 within one or more microprocessors or auxiliary coprocessors, such as computational coprocessors.

[0164] In addition to or in lieu of the CPU 706, the GPU 708 may be configured to execute at least some of the computer readable instructions to control one or more components of the computing device 700 to perform one or more of the methods and / or processes described herein. One or more of the GPUs 708 may be integrated GPUs (e.g., with one or more of the CPUs 706 and / or one or more of the GPUs 708 may be discrete GPUs. In an embodiment, one or more of the GPUs 708 may be coprocessors of one or more of the CPUs 706. The GPUs 708 may be used by the computing device 700 to render graphics (e.g., 3D graphics) or perform general purpose computations. For example, the GPUs 708 may be configured to perform general purpose computing on a GPU (GPGPU). A graphics processing unit (GPU) 708 may be used for processing graphics data. The GPU 708 may include hundreds or thousands of cores capable of processing hundreds or thousands of software threads simultaneously. The GPU 708 may generate pixel data for an output image in response to rendering commands (e.g., rendering commands from the CPU 706 received via a host interface). The GPU 708 may include graphics memory, e.g., display memory, for storing the pixel data or any other suitable data, e.g., GPGPU data. The display memory may be included as part of the memory 704. GPU 708 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 may connect the GPUs via a switch (e.g., using NVSwitch). When coupled together, each GPU 708 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 the other GPUs.

[0165] In addition to or instead of the CPU 706 and / or GPU 708, the logic unit 720 may be configured to execute at least some of the computer readable instructions to control one or more of the computing devices 700 to perform one or more of the methods and / or processes described herein. In an embodiment, the CPU 706, the GPU 708, and / or the logic unit 720 may execute any combination of the methods, processes and / or portions thereof, either discretely or jointly. One or more of the logic units 720 may be part of and / or integrated with one or more of the CPU 706 and / or GPU 708, and / or one or more of the logic units 720 may be a discrete component to or otherwise external to the CPU 706 and / or GPU 708. In an embodiment, one or more of the logic units 720 may be a co-processor of one or more of the CPU 706 and / or GPU 708.

[0166] Examples of logic unit 720 include one or more processing cores and / or components thereof, such as, for example, a Tensor Core (TC), a Tensor Processing Unit (TPU), a Pixel Visual Core (PVC), a Vision Processing Unit (VPU), a Graphics Processing Cluster (GPC), a Texture Processing Cluster (TPC), a Streaming Multiprocessor (SM), a Tree Traversal Unit (TTU), an Artificial Intelligence Accelerator (AIA), a Deep Learning Accelerator (DLA), an Arithmetic Logic Unit (ALU), an Application Specific Integrated Circuit (ASIC), a Floating Point Unit (FPU), an Input / Output (I / O) element, a Peripheral Component Interconnect (PCI) or Peripheral Component Interconnect Express (PCIe) element, and / or the like.

[0167] The communications interface 710 may include one or more receivers, transmitters, and / or transceivers that enable the computing device 700 to communicate with other computing devices over electronic communications networks, including wired and / or wireless communications. The communications interface 710 may include components and functionality to enable communication over any of a number of different networks, such as a wireless network (e.g., Wi-Fi, Z-Wave, Bluetooth, Bluetooth LE, ZigBee, etc.), a wired network (e.g., communicating over Ethernet or InfiniBand), a low power wide area network (e.g., LoRaWAN, SigFox, etc.), and / or the Internet.

[0168] The I / O ports 712 may enable the computing device 700 to be logically coupled to other devices, including I / O components 714, presentation components 718, and / or other components, some of which may be built-in (e.g., integrated) to the computing device 700. Exemplary I / O components 714 include a microphone, a mouse, a keyboard, a joystick, a game pad, a game controller, a satellite dish, a scanner, a printer, a wireless device, and the like. The I / O components 714 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological input generated by a user. In some cases, the input may be sent to an appropriate network element for further processing. The NUI may implement any combination of voice recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition on and next to the screen, air gestures, head and eye tracking, and touch recognition in conjunction with the display of the computing device 700 (as described in more detail below). The computing device 700 may include a depth camera, such as a stereoscopic camera system, an infrared camera system, an RGB camera system, touch screen technology, and combinations thereof, for gesture detection and recognition. Additionally, the computing device 700 may include an accelerometer or gyroscope (e.g., as part of an inertia measurement unit (IMU)) to enable detection of motion. In some instances, the output of the accelerometer or gyroscope may be used by the computing device 700 to render immersive augmented or virtual reality.

[0169] Power supply 716 may include a hardwired power supply, a battery power supply, or a combination thereof. Power supply 716 may provide power to computing device 700 to enable components of computing device 700 to operate.

[0170] The presentation component 718 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 718 can receive data from other components (e.g., GPU 708, CPU 706, etc.) and output data (e.g., as images, video, sound, etc.).

[0171] The present disclosure may be described in the general context of computer code or machine usable instructions, including computer executable instructions, such as program modules, being executed by a computer or other machine, such as a personal digital assistant or other handheld device. Generally, program modules, including routines, programs, objects, components, data structures, etc., refer to code that performs particular tasks or implements particular abstract data types. The present disclosure may be implemented in a variety of configurations, including handheld devices, consumer electronics, general purpose computers, more specialized computing devices, etc. The present disclosure may also be implemented in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.

[0172] As used herein, the statement "and / or" with respect to two or more elements should be interpreted to mean only one element or a combination of elements. For example, "element A, element B, and / or element C" may include element A only, element B only, element C only, elements A and element B, elements A and element C, elements B and element C, or elements A, B, and C. In addition, "at least one of element A or element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B. Furthermore, "at least one of element A and element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B.

[0173] The subject matter of the present disclosure has been described with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of the present disclosure. Instead, the inventors intend that the claimed subject matter may be implemented in other ways, including different steps or combinations of steps similar to those described in this document, in conjunction with other current or future technologies. Furthermore, although the terms "step" and / or "block" may be used herein to connote different elements of the method used, these terms should not be construed as implying any particular order between the various steps disclosed herein unless and when the order of the individual steps is explicitly described.

Claims

1. receiving first sensor data representative of a plurality of instances of a perception field of a sensor of a vehicle and second sensor data representative of state information corresponding to the vehicle in each instance of the plurality of instances of the perception field; generating a simulated profile for testing functionality of the vehicle, the simulated profile including desired state information of the vehicle at a plurality of points along the simulated profile; determining, for a point of the plurality of points, an instance of the plurality of instances of first sensor data corresponding to the second sensor data representing respective state information most similar to desired state information of each of the points as a closest instance; computing a transformation of the closest instances to generate updated instances corresponding to the respective desired state information; performing the test of the functionality based at least in part on the updated instance; A method comprising:

2. The method of claim 1 , wherein the state information and the desired state information represent at least one of a velocity, a position, or an attitude of the vehicle.

3. The method of claim 1 , wherein the first sensor data is captured as the vehicle approaches or moves away from an object at a substantially constant velocity.

4. 2. The method of claim 1, wherein the function corresponds to at least one of an automatic emergency braking (AEB) system, a collision mitigation warning (CMW) system, an automatic lane departure warning system, an automatic lane change system, or an adaptive cruise control (ACC) system.

5. The method of claim 1 , wherein the transformation comprises a viewport transformation of each pixel that corresponds to the nearest instance of the perceptual field.

6. The method of claim 1 , wherein the transformation comprises a magnification operation.

7. 2. The method of claim 1, wherein for each point of the plurality of points, a respective closest instance is determined from the plurality of instances of the first sensor data, the transformation is calculated for the respective closest instances to generate a set of updated instances, and further wherein the set of updated instances is used for the step of performing the test of the function.

8. 2. The method of claim 1, wherein when the desired state information is within a predetermined range relative to the state information, the closest instance is used for the step of performing the test of the function without computing the transformation.

9. The method of claim 1 , wherein the step of performing the test of the functionality is further based at least in part on a physical model corresponding to the vehicle.

10. The method of claim 1 , wherein the desired state information is determined based at least in part on a desired initial velocity of the vehicle for the execution of the test.

11. a first sensor for generating first sensor data representative of a plurality of instances of a perception field of the sensor of the vehicle; one or more second sensors for generating second sensor data representative of state information corresponding to the vehicle in each instance of the plurality of instances of the perception field; one or more processors; When executed by the one or more processors, the one or more processors are generating a simulated trajectory for testing functionality of the vehicle, the simulated trajectory including desired state information of the vehicle at a plurality of points along the simulated trajectory; generating, for each point of the plurality of points, an updated instance of the first sensor data based at least in part on the plurality of instances of the first sensor data and a difference between the state information and the desired state information; performing the test of the functionality based at least in part on the updated instance; and one or more memory devices having programmable instructions stored thereon for performing operations including A system comprising:

12. 12. The system of claim 11, wherein generating the updated instance of the first sensor data includes: for each point of the plurality of points, determining as a closest instance an instance of the plurality of instances of the first sensor data that corresponds to the second sensor data representing respective state information that is most similar to desired state information of each of the points; and generating the updated instance based at least in part on the closest instance.

13. The system of claim 11 , wherein the state information and the desired state information represent at least one of a speed, a position, or an orientation of the vehicle.

14. 13. The system of claim 12, wherein generating the updated instance of the first sensor data includes computing a transform for each of a plurality of closest instances, the plurality of closest instances being a subset of the closest instances for each of the plurality of points.

15. 15. The system of claim 14, wherein the transformation comprises, for each point, a viewport transformation of each pixel corresponding to the nearest instance of the perceptual field based at least in part on the difference between the state information and the desired state information.

16. 13. The system of claim 12, wherein when the desired state information is within a predetermined range for the state information, the closest instance is used as the updated instance for each point for the performing the test of the function.

17. 12. The system of claim 11, wherein the function corresponds to at least one of an automatic emergency braking (AEB) system, a collision mitigation warning (CMW) system, an automatic lane departure warning system, an automatic lane change system, or an adaptive cruise control (ACC).

18. receiving first sensor data representative of a plurality of instances of a perception field of a sensor of a vehicle and second sensor data representative of state information corresponding to the vehicle in each instance of the plurality of instances of the perception field; generating a simulated profile for testing functionality of the vehicle, the simulated profile including desired state information of the vehicle at a plurality of points along the simulated profile; determining, for each of the plurality of points, an instance of the plurality of instances of first sensor data corresponding to the second sensor data representing respective state information that is most similar to desired state information of each of the points as a closest instance; generating a set of instances from the plurality of instances of the first sensor data based at least in part on the determination; performing the test of the functionality based at least in part on the set of instances; A method comprising:

19. The method of claim 18 , wherein the generating the set of instances from the plurality of instances of the first sensor data further comprises transforming the closest instances.

20. The method of claim 18 , wherein the desired state information of the vehicle is determined based at least in part on a desired initial velocity of the vehicle for the execution of the test.

Images