System and method for pedestrian crossing risk assessment and directional warning - Patents.com

Abstract

To provide systems and methods for a pedestrian crossing warning system that use multi-modal technology to determine attributes of a person and provide a warning to the person in response to a calculated risk level to effect a reduction of the risk level.SOLUTION: The system may utilize sensors to receive data indicative of a trajectory of a person external to the vehicle. Specific attributes of the person such as age or walking aids are determined. Based on the trajectory data and the specific attributes, a risk level is determined by the system using a machine learning model. The system causes emission of a warning to the person in response to the risk level.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present disclosure is directed to techniques for operating a vehicle, and in particular, for providing a pedestrian crossing risk assessment and directional warning system. [Background technology]

[0002] Vehicle operation has an inherent collision risk for all objects within the field of vehicle operation, including, for example, objects in the vicinity of a pedestrian crosswalk. This risk may be heightened for a pedestrian attempting to cross a pedestrian crosswalk who has a lack of sensory awareness, e.g., hearing loss, or if the pedestrian is distracted, e.g., engaged with a mobile smartphone. In one current approach, a system may determine an estimate of when a pedestrian may be in danger from a vehicle and provide an alert to the pedestrian. However, the alert provided is generally phrased and perceptible by anyone in the general vicinity, and may actually distract other people on the roadway who are not in danger when the subject in danger is not immediately apparent. Summary of the Invention [Problem to be solved by the invention]

[0003] Therefore, to overcome the limitations of current pedestrian crossing warning systems, a system and method for a pedestrian crossing warning system is described herein that may use multimodal techniques to determine a calculated risk level for a person and to provide a warning to the person to result in a reduction in the risk level. The system may receive data using sensors indicative of a trajectory of a person outside of a vehicle. For example, an elderly person may be approaching a crosswalk at a slow walking speed. In some embodiments, the system receives camera and LIDAR sensor data of an elderly person approaching a crosswalk in several separate frames and calculates the trajectory of the person based on velocity and posture. Certain attributes of the person, such as age or walking aid, may be determined. Continuing with the previous example, the system determines that the elderly person is using a cane and wearing a hearing aid. Based on the trajectory data and the certain attributes, a risk level may be determined by the system using a machine learning model or any other suitable model. For example, given that the elderly person is determined to have a hearing impairment based on the detection of a hearing aid, the risk level may be high, and given the detection of a walking cane, the system may slow down mobility and change the trajectory. The system may issue a warning to the person depending on the risk level. In this scenario, the vehicle emits a beamformed audio signal towards the senior's current location with a magnitude corresponding to the determined danger level to ensure that the senior can perceive the alarm. When the alarm is beamformed, the disturbance to their activities experienced by the rest of the environment is reduced. [Means for solving the problem]

[0004] In some embodiments of the present disclosure, the machine learning model may include a hardware accelerator to at least partially calculate the risk level. In other embodiments of the present disclosure, the risk level calculation implements a neural network that may receive inputs from data indicative of a person's trajectory and attributes of the person to determine the likelihood that the vehicle is on a collision course with the person.

[0005] In some embodiments of the present disclosure, the system may determine attributes that extend beyond people and include environmental attributes such as weather conditions, location specific attributes (e.g., proximity to school zones, traffic signs and signals), and / or driving conditions for calculating risk levels.

[0006] The action to be taken depending on the danger level to reduce the danger level may be implemented in various techniques disclosed herein. In some embodiments of the present disclosure, a directional audio signal is emitted from the vehicle to the object based on the danger level, and the audio signal includes distinct frequency components (e.g., one component may be in the frequency range of human hearing and another component may be in a different frequency range for service dog hearing). In other embodiments of the present disclosure, the warning of the person may be implemented by the emission of a directional light signal from the vehicle towards the object.

[0007] The foregoing and other objects and advantages of the present disclosure will become apparent when considered in conjunction with the following detailed description, in which like reference characters refer to like parts throughout, and in which: [Brief description of the drawings]

[0008] [Figure 1A] FIG. 2 illustrates an example scenario of a distracted person approaching a pedestrian crosswalk, in accordance with some embodiments of the present disclosure. [Figure 1B] FIG. 2 illustrates an example scenario of people running towards a pedestrian crosswalk, according to some embodiments of the present disclosure. [Figure 1C] FIG. 1 illustrates an example scenario of children approaching a pedestrian crosswalk in a school zone, in accordance with some embodiments of the present disclosure. [Figure 1D] FIG. 2 illustrates an example scenario of an elderly person with a dog approaching a pedestrian crosswalk, in accordance with some embodiments of the present disclosure. [Diagram 2] FIG. 2 is a risk calculation block diagram according to some embodiments of the present disclosure. [Figure 3A]FIG. 1 illustrates a risk assessment awareness module according to some embodiments of the present disclosure. [Figure 3B] FIG. 1 illustrates a risk assessment pedestrian attribute module according to some embodiments of the present disclosure. [Figure 3C] FIG. 2 illustrates a pedestrian crossing intent module, according to some embodiments of the present disclosure. [Figure 4] FIG. 2 illustrates an example beamformed audio signal emission in accordance with some embodiments of the present disclosure. [Figure 5A] 1 is an illustration of an example autonomous vehicle, according to some embodiments of the present disclosure. [Figure 5B] 5B is an illustration of camera positions and fields of view for the example autonomous vehicle of FIG. 5A, according to some embodiments of the present disclosure. [Figure 5C] FIG. 5B is a block diagram of an example system architecture of the example autonomous vehicle of FIG. 5A, in accordance with some embodiments of the present disclosure. [Figure 5D] FIG. 5B is a system diagram of communication between a cloud-based server and the example autonomous vehicle of FIG. 5A, according to some embodiments of the present disclosure. [Figure 6] FIG. 1 is a block diagram of an example computing device suitable for use in implementing some embodiments of the present disclosure. [Figure 7] 1 is an example flow diagram of a process for operating a vehicle, according to some embodiments of the present disclosure. [Figure 8] 1 is an example flow diagram of a process for determining a trajectory of an object external to a vehicle, according to some embodiments of the present disclosure. [Figure 9] 4 is an example flow diagram of a process for determining attributes of an object external to a vehicle, according to some embodiments of the present disclosure. [Figure 10] 1 is an example flow diagram of a process for causing emission of a beamformed audio signal, according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] 1A illustrates an example scenario 100 of a distracted person approaching a pedestrian crosswalk, according to some embodiments of the present disclosure. An advanced vehicle 102 is driving on a trajectory approaching a pedestrian crosswalk 106 that intersects with a roadway 104. The vehicle includes processing circuitry that may implement functions requiring processing, including, for example, parallel processing, and / or any other function requiring computer analysis. The processing circuitry may receive data indicative of the trajectory of the person outside the vehicle from sensors implemented in the vehicle. The vehicle's sensors may include any type of sensor, including, but not limited to, global navigation satellite system ("GNSS") sensors (e.g., global positioning system sensors), RADAR sensors, ultrasonic sensors, LIDAR sensors, inertial measurement unit ("IMU") sensors (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones, stereo cameras, wide-view cameras (e.g., fish-eye cameras), infrared cameras, surround cameras (e.g., 360-degree cameras), long-range cameras, mid-range cameras, speed sensors, vibration sensors, steering sensors, brake sensors (e.g., as part of a brake sensor system), and / or other sensor types. Returning to FIG. 1A, the processing circuitry may receive information from one or more camera devices (e.g., without limitation, one or more stereo cameras, one or more monocular cameras, and / or one or more infrared cameras) to detect a crosswalk sign 108 warning for an approaching crosswalk. The cameras may also determine an upcoming crosswalk 106 and an approaching person 105. Data received from these cameras (e.g., a series of images) may indicate the trajectory of a pedestrian, e.g., a teenage boy 105.

[0010] In some embodiments, the processing circuitry receives one or more images of an object (e.g., a person) received from a sensor. The processing circuitry may determine the directionality of the object based on one or more of the images received from the camera sensor. Continuing with the example of FIG. 1A, as a vehicle approaches a crosswalk, multiple images may be taken by the camera. As a teenage boy approaches a crosswalk perpendicular to the trajectory of the vehicle, these images may include the boy in various different locations. Three images show the teenage boy approaching the crosswalk. The processing circuitry determines a directionality consistent with crossing the crosswalk based on the location of the teenage boy approaching the crosswalk. Additionally, the processing circuitry may determine a velocity of the object based on these images. For example, three images are taken at respective timestamps. Based on the relative distance of the boy between one or more images and the difference in time between the images, the velocity may be calculated by the processing circuitry using corresponding calculations of distance and time. The processing circuitry may determine the trajectory of the object based on the velocity and directionality of the object. For example, the vehicle's processing circuitry may determine that a teenage boy is walking on a track for crosswalks at a walking velocity (eg, 3 miles per hour).

[0011] FIG. 1B illustrates an example scenario 111 of people 112 running toward a pedestrian crosswalk 106, according to some embodiments of the present disclosure. In this example, the processing circuitry of the vehicle 102 may determine that the people 112 are running on a trajectory to cross the crosswalk 106 with a running velocity of 13 miles per hour. FIG. 1C illustrates an example scenario 121 of children 122 approaching a pedestrian crosswalk 106 in a school zone, according to some embodiments of the present disclosure. In this example, the processing circuitry of the vehicle 102 may determine that the children 122 are walking on a trajectory to cross the crosswalk 106 with a walking velocity of, for example, 2 miles per hour. FIG. 1D illustrates an example scenario 131 of an elderly person 134 with a dog 135 approaching a pedestrian crosswalk 106, according to some embodiments of the present disclosure. In this example, the processing circuitry of the vehicle 102 may determine separate trajectories of each entity 134 and 135 walking on a trajectory for crossing the crosswalk 106 at a walking velocity of 4023 m / h (2·5 mph) for people and dogs.

[0012] The processing circuitry may determine one or more attributes of the person. In some embodiments, the determination of the one or more attributes of the person may be implemented by the processing circuitry using a machine learning model (e.g., a neural network implemented by parallel processing circuitry). The image or information derived from the image may be used as input to the machine learning model. For example, the object may be a person, and the attributes of the person may include at least one of the following: the person's head pose, the person's body position, the person's clothing or other items, or gestures made by the person. In some embodiments, other considerations, such as environmental attributes, may be used as input to the machine learning model. The machine learning model may be trained with a training data set that includes a myriad of body positions, body types (including age differences), clothing or other items, gestures, accessories, or environmental attributes.

[0013] Returning to Figure 1A, the processing circuitry may determine from the received image that the teenage boy 105 is looking at a cell phone, which is visible in the image. The processing circuitry may further determine that the teenage boy's head pose is facing down relative to a neutral head pose. The processing circuitry may further determine the brand and type of clothing and backpack worn by the teenage boy. The processing circuitry may further determine that a warning sign for a pedestrian crossing 108 is present.

[0014] Returning to Figure 1B, the processing circuitry may determine that the people 112 are wearing athletic clothing and shoes. Returning to Figure 1C, the processing circuitry may determine that there is a school sign 124 that suggests environmental attributes. Other example environmental attributes may include current weather conditions, the current time of day, or the relative level of local activity (such as a number of pedestrians on the sidewalk). Returning to Figure 1D, the processing circuitry may determine the breed and type of dog 135. The processing circuitry may further determine physical aids used by the people 134, such as wheelchairs and walking sticks.

[0015] The processing circuitry may determine a classification of the person's attributes based on a machine learning model. The machine learning model may be trained with an existing library of all types of attributes (e.g., head pose, posture, clothing, etc.). Based on all the determined attributes, the machine learning model may determine a particular classification of the object. The classification may be in the form of data about the determined object in the received image.

[0016] 1A, the processing circuitry may determine, via a machine learning model, that teenage boy 105 has a likelihood of being in the age range of 13-18 years old based on the height, body type, clothing type, backpack, and any one or more other attributes determined for the teenage boy. The processing circuitry may determine that any type of audio-based alert may be received by teenage boy 105 (e.g., no possible hearing impairment, no headphones obscuring hearing, etc.) based on the classification of the teenage boy exhibiting no impairment to receiving audio alerts. The processing circuitry may store this classification in storage (local or network-based) as metadata associated with the object.

[0017] Returning to Figure 1C, the processing circuitry may classify children 122 as potentially being in the 7 to 11 year old age range and, according to their attributable comprehension skills as members of that age group, may require simple audio alerts to understand. Returning to Figure 1D, the processing circuitry may classify seniors 134 as potentially being in the 80+ age range and may require louder audio alerts to understand, as may be appropriate for their attributable age group and sensor perception level.

[0018] In some examples, the processing circuitry may determine attributes of an object based on receiving data indicative of a depiction of at least a portion of the object (e.g., a portion of a person. For example, if the processing circuitry determines from a received image that a person is using a walking stick, this may factor into a determination of the person's age (e.g., may result in an inference that the person is elderly).

[0019] The processing circuitry may calculate a risk level based on the data indicative of the trajectory and the one or more attributes using parallel processing circuitry implementing a machine learning model. In some embodiments, the processing circuitry may calculate the risk level by implementing a three-dimensional pose of the pedestrian. The processing circuitry may determine the three-dimensional pose of the pedestrian in one or more frames of an image or video capture from a camera sensor. The processing circuitry may implement Kalman filtering in the machine learning model to estimate the three-dimensional pose of the pedestrian.

[0020] 2 illustrates a risk calculation block diagram 200 according to some embodiments of the present disclosure. In some embodiments, the risk calculation block diagram includes two modules, including a risk module 202 and a crossing intent module 204. The risk calculation block diagram may be used to calculate a risk level. The risk module 202 further includes sub-modules corresponding to four factors used to determine at least a portion of the risk calculation. The four factors include awareness, situation criticality, pedestrian alert, and pedestrian attributes.

[0021] The processing circuitry may determine the pedestrian's awareness based on the calculated head pose. The head pose may be estimated using the neck's primary joint determined by the body posture. The machine learning model may implement a head bounding box that is passed to the head pose estimation. For example, the head pose estimation may be used to estimate whether the pedestrian's head is down or whether the pedestrian's head is oriented to glance at the vehicle in a one second window. In some embodiments, the head pose estimation may be determined in a relative orientation to the vehicle. In some embodiments, the processing circuitry may determine the pedestrian's awareness by determining a social and technological distraction index (e.g., whether the pedestrian is distracted via cell phone use).

[0022] FIG. 3A illustrates a risk assessment awareness module 310 according to some embodiments of the present disclosure. The risk assessment awareness module may include at least three distinct types of networks. First, a body posture convolutional neural network 312 may input a pedestrian bounding box of the pedestrian. The body posture convolutional neural network is used to determine the specific kinematic values, movements and / or postures of the pedestrian. Second, an object convolutional neural network 314 may input a hand bounding box of the pedestrian. The object convolutional neural network is used to determine the specific objects interacting with the pedestrian. The hand bounding box may be estimated based on the wrist joint position calculated by the body posture, and its size may be proportional to the height of the pedestrian. Third, a head pose convolutional neural network 316 may input a head bounding box of the pedestrian. The head pose convolutional neural network is used to determine the orientation of the pedestrian's head to estimate the attention level of the pedestrian. The head bounding box may be estimated based on the position of the pedestrian's neck joint calculated by the body posture, and its size may be proportional to the pedestrian's height. In some embodiments, these three networks calculate as output: a kinematic feature vector (e.g., 3D body posture joints), an object feature vector that is a fully connected layer of an object convolutional neural network, and a head pose feature vector that is a fully connected layer of a head pose estimation convolutional neural network. The processing circuitry may concatenate these three feature vectors to fit a support-vector machine classifier ("SVM") 318 to predict whether the pedestrian is performing a particular action (e.g., texting, talking, etc.). In some embodiments, the head pose feature vector may output the pitch, yaw, and roll 320 of the pedestrian's head. This information may be used by the processing circuitry to determine whether the pedestrian is looking up at the vehicle (e.g., estimating the pedestrian is aware of the vehicle).

[0023] The processing circuitry may determine the pedestrian's situation criticality based on the calculated vertical distance of the vehicle to the pedestrian. For example, the distance may be the vertical distance of the vehicle to the pedestrian in each frame. This estimation of the distance is performed by the processing circuitry by calculating the average value of the pedestrian's 3D body joint "Z" coordinate (e.g., in meters) relative to the vehicle.

[0024] The processing circuitry can determine a pedestrian alert for a pedestrian based on the pedestrian's "X" coordinate horizontal distance change and horizontal distance velocity change estimate in every frame, where the X coordinate is calculated by the processing circuitry based on the average value of the pedestrian's 3D body joint "X" coordinate.

[0025] 3B illustrates a risk assessment pedestrian attribute module 320 according to some embodiments of the present disclosure. Attribute recognition may be performed by the processing circuitry by implementing a human convolutional neural network 322 that may input a pedestrian bounding box. The human convolutional neural network may output a person vector that is a fully connected layer of the human convolutional neural network. This person vector may be input to a classifier 324 to classify the pedestrian as one of the following classes: child, adult, elderly, etc.

[0026] The crossing intent module may be implemented by the processing circuitry to determine the intent of a pedestrian to cross an intersection and / or path in the trajectory of the vehicle, for example, in certain scenarios, a pedestrian may be very close to the edge of the road and thus in danger, but may not intend to cross the road (e.g., a pedestrian removing baggage from the track of a respective vehicle).

[0027] 3C illustrates a pedestrian crossing intent module 330, according to some embodiments of the present disclosure. The processing circuitry may implement a posture convolutional neural network 332 that inputs into a Long-Short Term Memory (LTSM) recurrent neural network 334. The LTSM may learn body movement patterns and torso orientation. The output from the LTSM is input to a classifier 336 (e.g., a SoftMax classifier) ​​that may predict whether the pedestrian is crossing or performing some other activity.

[0028] The risk level may be a quantitative or qualitative measure derived from a computer analysis performed by the processing circuitry using, at least in some embodiments, one or more machine learning models. For example, the machine learning model may be trained with a data set including combinations of trajectories and attribute classifications of various objects. The machine learning model may be further trained with safety data associated with each combination. The safety data may specify, for each combination, data regarding the likelihood or likelihood of a crash outcome and other dangerous outcomes (e.g., specific velocities and directionality of the vehicles and objects). The machine learning model may be able to determine a risk level associated with each of these combinations. In some embodiments, the processing circuitry may calculate the risk level based on a look-up table having a corresponding risk level output based on the trajectory and one or more attributes.

[0029] In some embodiments, the processing circuitry may include, at least in part, one or more hardware accelerators for calculating the danger level. For example, a programmable vision accelerator ("PVA") may be used to calculate the computer vision calculations. In another example, a deep learning accelerator ("DLA") may be used to perform calculations for deep neural network operations used in parallel processing. In particular, the DLA may receive inputs such as data indicative of object trajectories and / or object attributes, and implements these inputs in a machine learning model (e.g., one or more deep neural networks) to calculate the danger level. In some embodiments, the processing circuitry uses, at least in part, one or more neural networks to calculate the danger level. The neural network uses data indicative of the trajectory and one or more attributes as inputs. The neural network outputs whether the vehicle is on a collision course with the object.

[0030] The processing circuitry may provide the attributes as one or more inputs to the machine learning model. Non-limiting examples of suitable attributes may include one or more of location attributes, weather attributes, or driving condition attributes. In some examples, the machine learning model may be separate from the machine learning model used to determine other attributes of the object. In other examples, the same machine learning model is used to determine both sets of attributes of the object. The processing circuitry may use the machine learning model to calculate a danger level based on at least one of the attributes. For example, if adverse weather conditions, such as rain, are detected, which require pedestrians and moving vehicles to stop longer distances. In another example, the danger level may be higher when driving conditions are severe, such as a vehicle moving up a steep uphill grade, which also results in longer stopping distances. In yet another example, the danger level may be higher during low light conditions (e.g., at night). In this example, pedestrians generally have reduced vision, which increases the danger level.

[0031] The risk level may be a quantitative value generated by a machine learning model that is used by the processing circuitry to determine the corresponding action to be taken. The risk level may also be a classification based on a quantitative value (e.g., high risk, medium risk, low risk). In some embodiments, the risk level may be based on various mathematical, statistical, and / or fuzzy logic operations used by the machine learning model. The risk level may be stored by the processing circuitry in association with one or more corresponding objects.

[0032] Returning to FIG. 1A, based on the trajectory in which the teenage boy 105 is determined to be facing the crosswalk and about to cross the crosswalk, and based on the classification that the teenage boy is not physically impaired from receiving the audio alert but is distracted with a low head pose, the processing circuitry may calculate a danger level of “medium risk.”

[0033] Returning to FIG. 1B, based on the determined trajectory that people 112 are moving with a driving velocity in a direction that will result in them crossing the crosswalk, as well as based on the classification that the people have no physical impairment to receiving the audio alert and that their head posture allows for full awareness of the surrounding environment, the processing circuitry may calculate a risk level of “low to medium risk.”

[0034] Returning to FIG. 1C, based on the determined trajectory that the children 122 are walking slowly in the direction that will result in them crossing the crosswalk, and based on the classification that the children are in a school zone and may have a low level of understanding based on their likely age range, the processing circuitry may calculate a risk level of “medium to high risk.”

[0035] Returning to FIG. 1D , based on the determined trajectory that elderly person 134 is walking slowly in the direction that he will cross the crosswalk and that dog 135 is moving in an unpredictable direction near the start of the crosswalk, as well as based on the classification that elderly people may have reduced hearing levels based on their likely age group, the processing circuitry may calculate a risk level of “high risk.”

[0036] The processing circuitry may cause an action to be performed in response to the hazard level to result in a reduction in the hazard level. The action to be performed may be performed by one of a larger number of hardware components of the vehicle. For example, the vehicle may include various hardware components capable of providing a transmission medium such as a speaker providing an audio signal output (e.g., a speaker capable of directional output of audio output such as a beamformed audio signal) or a directional light providing a light-based output (e.g., via headlights, tail lights, or other lights incorporated into the vehicle and / or dedicated light hardware for directional output).

[0037] In other embodiments, the vehicle may provide instructions, via data communication over the communications network, to nearby environmental hardware to facilitate an alert. For example, the vehicle may send instructions wirelessly or via a data network to a traffic light pole by a crosswalk to emit an audio and / or light signal for pedestrians approaching the crosswalk. The vehicle may include hardware that interfaces with various communications networks to enable communication with the environmental hardware. The environmental hardware may include traffic lights, traffic light poles, networked benches, buildings, or other types of hardware within the environment that may be communicated with via the communications network.

[0038] Causing an action may include determining trajectory and magnitude. In some embodiments, the processing circuitry may determine a real-time trajectory from the vehicle to the object. The real-time trajectory may be based on data from the vehicle, such as velocity and directionality. Additional data, such as a determined trajectory of an object external to the vehicle to a location point (e.g., a pedestrian crosswalk), may also be used in the calculations by the processing circuitry. The processing circuitry may use this determined data in one or more mathematical models to determine the trajectory of the vehicle to the object. For example, the processing circuitry may determine the likelihood that the vehicle is on a collision course with the object.

[0039] In some embodiments, the processing circuitry may determine a magnitude of the audio signal based on the calculated hazard level. For example, a low hazard level may be associated with an audio alert at a lower magnitude. A high hazard level may be associated with an audio alert at a higher magnitude with a light-based alert having a high intensity level. In some embodiments, the corresponding magnitude may be associated with the intensity of the light source of a directional light-based alert. In some embodiments, the magnitude may be a combination of both the audio magnitude and the light-based intensity. In some embodiments, the association of the magnitude and the hazard level may be based on a predefined table stored in the memory. In some embodiments, the association of the magnitude and the hazard level may be determined in real time based on a predefined calculation based on inputs including at least the determined trajectory of an object external to the vehicle and the trajectory of the vehicle.

[0040] In some embodiments, the determination of the association between the magnitude of the emission signal and the danger level may be based, at least in part, on real-time information received by the processing circuitry regarding historical information regarding the object. For example, if the object (e.g., a person) was previously flagged by a vehicle with high magnitude audio, the same magnitude (or an increased magnitude) may be used. In some embodiments, the same magnitude (or an increased magnitude) may be used if the object (e.g., a person) was previously flagged by one or more other vehicles.

[0041] In some embodiments, the association between the magnitude of the emitted signal and the danger level may be determined based, at least in part, on environmental information received by the processing circuitry regarding the location of the vehicle and / or object. For example, if the vehicle is traveling within a school zone, the magnitude of the emitted audio signal may be higher than if the vehicle was not traveling within a school zone. Returning to FIG. 1C, given that the vehicle is within a school environment, the magnitude of the audio signal directed to children will be at a higher volume.

[0042] In some embodiments, the association between the magnitude of the emitted signal and the danger level may be determined based, at least in part, on auxiliary environmental information received by the processing circuitry regarding the location of the vehicle and / or object. For example, if the processing circuitry of one or more camera sensors determines that there are a large number of pedestrians in close proximity to the object, the magnitude of the emitted signal may be beamformed larger and narrower specifically toward the object.

[0043] In some embodiments, the processing circuitry may send instructions to at least the speaker sensor to trigger the emission of a beamformed audio signal based on the real-time trajectory and the magnitude of the audio signal. The beamformed audio signal is generated by the processing circuitry determining the corresponding phase and amplitude of the acoustic signal such that a corresponding pattern of constructive and destructive interference is produced in the wavefront. The target area within the transmission of the beamformed signal receives the full magnitude of the signal. Outside the target area of ​​the transmission of the beamformed signal, the signal is attenuated. Thus, only the intended target of the beamformed transmission receives the signal at the intended magnitude. In some embodiments, the processing circuitry may use an array of speaker sensors on the vehicle to emit the beamformed audio signal. The array of speakers is each configured with a respective phase and amplitude value to direct the beamformed audio speaker with a particular directionality to an object outside the vehicle. In some embodiments, the array of speakers may include speaker sensors of networked environmental hardware (e.g., a traffic light pole with one or more speaker sensors at an intersection). In other embodiments, the speaker array includes one or more speaker sensors of another vehicle communicatively coupled to the current vehicle operated by the processing circuit. For example, a first vehicle driving in close proximity to a second vehicle may send a command to the second vehicle over a shared network to emit an audio signal (with corresponding phase and amplitude values) for emission to a common object. Returning to FIG. 1A, the beamformed audio signal 109 is directed to a teenage boy. The beamformed audio signal 109 is attenuated outside the shaded zone. Similarly, in FIGS. 1B and 1C, the beamformed audio signal 109 is directed to running people 112 and walking children 122, respectively. As previously mentioned, the emission of the beamformed audio signal may be from a vehicle or network communication environment hardware (e.g., a traffic light with an embedded speaker sensor). In some embodiments, a directional audio signal is directed to an object (e.g., a person).

[0044] FIG. 4 illustrates an exemplary beamformed audio signal emission 400 according to some embodiments of the present disclosure. The processing circuitry determines the location of the at-risk pedestrian relative to the vehicle as described above. The processing circuitry emits the beamformed audio signal via the speaker sensor that implements a beamforming algorithm to steer the beam in the direction of the at-risk pedestrian. Beam steering will be achieved by playing the same audio signal with different delays from different speakers. This technique allows for steering of the audio signal at any determined distance within range. This will ensure that only the at-risk pedestrian will hear the audio signal with full intensity, while anyone else in the area will hear a tone with a smaller amplitude. In some embodiments, if the pedestrian continues to move forward without a change in behavior (e.g., head pose, body position, continues to follow the same movement path), the audio signal magnitude may be increased.

[0045] In some embodiments, the processing circuitry may at least send instructions to the light source to trigger a directional light emission based on the real-time trajectory and the intensity of the light base. In some embodiments, the directional light signal is directed toward an object (e.g., a person).

[0046] In some embodiments, the directional audio signal includes multiple distinct frequency components. For example, the distinct frequency components may be determined based on determined attributes, characteristics, or type of the intended signal recipient to achieve maximum reception based on the object's unique reception frequency range. Returning to FIG. 1D, an elderly person 134 is approaching a crosswalk 106 with a dog 135. The intended recipients include an elderly person (inferred) who can receive audio signals typically in the range of 20 Hz to 20 kHz, while the dog is an intended recipient with a unique hearing frequency response typically in the range of 40 Hz to 60 kHz. For example, the processing circuitry may send instructions to a speaker sensor to emit two distinct frequency components: (1) an 80-100 Hz "beep" intended for the human recipient, and (2) a 40 kHz whistle-type emission intended for the dog as the recipient. As shown in FIG. 1D, multiple emissions are produced, with a first emission 132 directed toward the elderly person and a second emission directed toward the dog 136. In some embodiments, the separate frequency components are emitted simultaneously. In other embodiments, the separate frequency components are emitted non-simultaneously.

[0047] In some embodiments, the processing circuitry may send a command to the speaker sensor to cause emission of an audio signal of various types of audio signals. In some embodiments, the audio signal may be a warning tone (e.g., a beep, a horn, a sustained tone, etc.). In some embodiments, the audio signal may be a warning voice message (e.g., "Alert!", "Caution!", "Danger!", "Wait at the crosswalk!", "Stop!", etc.). In some embodiments, the audio signal may be based on a determined attribute of the object. Returning to FIG. 1A, the audio signal emitted by the vehicle may be a voice message directed to a teenage boy stating, "Look up from your phone and be aware of your surroundings!" The voice message may be generated from a text to speech generator, the keywords of which may be based on the determined attribute of the object.

[0048] 5A is a diagram of an example autonomous vehicle 500 according to some embodiments of the present disclosure. Autonomous vehicle 500 (alternatively referred to herein as “vehicle 500”) may include, but is not limited to, passenger vehicles, such as cars, trucks, buses, first responder vehicles, shuttles, electric or mopeds, motorcycles, fire engines, police vehicles, ambulances, boats, construction vehicles, submarines, drones, and / or other types of vehicles (e.g., unmanned and / or carrying one or more passengers). Autonomous vehicles are generally described in terms of automation levels as defined by the National Highway Traffic Safety Administration (NHTSA), a division of the U.S. Department of Transportation, and the Society of Automotive Engineers (SAE) "Taxonomy and Definitions for Terms Related to Driving Automation Systems for On-Road Motor Vehicle" (Standard No. J3016-201806 published June 15, 2018, Standard No. J3016-201609 published September 30, 2016, and previous and future versions of this standard). Vehicle 500 may be capable of functioning according to one or more of autonomous driving levels 3 through 5. For example, vehicle 500 may be capable of conditional automation (Level 3), highly automated (Level 4), and / or fully automated (Level 5), depending on the embodiment.

[0049] The vehicle 500 may include components such as a vehicle chassis, body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other components. The vehicle 500 may include a propulsion system 550, such as an internal combustion engine, a hybrid power plant, a fully electric engine, and / or another propulsion system type. The propulsion system 550 may be connected to a drive train of the vehicle 500, which may include a transmission, to enable propulsion of the vehicle 500. The propulsion system 550 may be controlled in response to receiving a signal from a throttle / accelerator 552.

[0050] Steering system 554, which may include a steering wheel, may be used to steer vehicle 500 (e.g., along a desired course or route) when propulsion system 550 is operating (e.g., when the vehicle is moving). Steering system 554 may receive signals from steering actuator 556. The steering wheel may be an option for fully automated (Level 5) functionality.

[0051] Brake sensor system 546 may be used to operate the vehicle brakes in response to receiving a signal from a brake actuator 548 and / or a brake sensor. The controller 536, which may include one or more CPUs, system on chip (SoC) 504 (FIG. 5C), and / or GPUs, may provide signals (e.g., representations of commands) to one or more components and / or systems of the vehicle 500. For example, the controller may send signals to operate vehicle brakes via one or more brake actuators 548, to operate a steering system 554 via one or more steering actuators 556, and / or to operate a propulsion system 550 via one or more throttle / accelerators 552. The controller 536 may include one or more on-board (e.g., integrated) computing devices (e.g., supercomputers) that process sensor signals and output operational commands (e.g., signals representing commands) to enable autonomous driving and / or assist a driver in driving the vehicle 500. The controllers 536 may include a first controller 536 for autonomous driving functions, a second controller 536 for functional safety functions, a third controller 536 for artificial intelligence functions (e.g., computer vision), a fourth controller 536 for infotainment functions, a fifth controller 536 for redundancy in emergency situations, and / or other controllers. In some instances, a single controller 536 may handle two or more of the aforementioned functions, and two or more controllers 536 may handle a single function, and / or any combination thereof.

[0052] The controller 536 may provide signals to control one or more components and / or systems of the vehicle 500 in response to sensor data (e.g., sensor inputs) received from one or more sensors. The sensor data may be received from, for example, and without limitation, global navigation satellite system sensors 558 (e.g., global positioning system sensors), RADAR sensors 560, ultrasonic sensors 562, LIDAR sensors 564, inertial measurement unit (IMU) sensors 566 (e.g., accelerometers, gyroscopes, magnetic compasses, magnetometers, etc.), microphones 596, stereo cameras 568, wide-view cameras 570 (e.g., fisheye cameras), infrared cameras 572, surround cameras 574 (e.g., 360 degree cameras), long-range and / or medium-range cameras 598, speed sensors 544 (e.g., for measuring the speed of the vehicle 500), vibration sensors 542, steering sensors 540, brake sensors 546 (e.g., as part of a brake sensor system 546), and / or other sensor types.

[0053] One or more of the controllers 536 may receive input (e.g., represented by input data) from the instrument cluster 532 of the vehicle 500 and provide output (e.g., represented by output data, display data, etc.) via a human-machine interface (HMI) display 534, an audible annunciator, a loudspeaker, and / or other components of the vehicle 500. The output may include information such as vehicle velocity, speed, time, map data (e.g., HD map 522 of FIG. 5C), position data (e.g., the position of the vehicle 500 on a map, etc.), direction, the positions of other vehicles (e.g., occupancy grid), information regarding objects and object situations as known by the controller 536, etc. For example, the HMI display 534 may display information regarding the presence of one or more objects (e.g., road signs, warning signs, changing traffic signals, etc.) and / or a driving maneuver that the vehicle has performed, is performing, or will perform (e.g., changing lanes now, taking exit 34B in 2 miles, etc.).

[0054] Vehicle 500 further includes a network interface 524 capable of communicating over one or more networks using one or more wireless antennas 526 and / or a modem. For example, network interface 524 may be capable of communicating over LTE, WCDMA, UMTS, GSM, CDMA2000, etc. Wireless antenna 526 may 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.

[0055] 5B is an illustration of camera positions and fields of view of the example autonomous vehicle 500 of FIG. 5A, according to some embodiments of the present disclosure. The cameras and their respective fields of view are one example embodiment and are not intended to be limiting. For example, additional and / or alternative cameras may be included and / or the cameras may be located in different locations on the vehicle 500.

[0056] The camera type of the camera may include, but is not limited to, a digital camera that may be adapted for use with components and / or systems of the vehicle 500. The camera may be capable of operating at automotive safety integrity level (ASIL) B and / or at another ASIL. The camera type may be capable of any image capture rate, such as 60 frames per second (fps), 120 fps, 240 fps, etc., depending on the embodiment. The camera may be capable of using a rolling shutter, a global shutter, another type of shutter, or a combination thereof. In some 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.

[0057] 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).

[0058] 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.

[0059] A camera (e.g., a forward-facing camera) with a field of view that includes a portion of the environment in front of the vehicle 500 may be used for surround view to help identify the forward path and obstacles and, with the aid of one or more controllers 536 and / or control SoCs, provide information essential to generating an occupancy grid and / or determining a preferred vehicle path. Forward-facing cameras may be used to perform many of the same ADAS functions as LIDAR, including emergency braking, pedestrian detection, and collision avoidance. Forward-facing cameras may also be used for ADAS functions and systems, including other functions such as lane departure warning ("LDW"), autonomous cruise control ("ACC"), and / or traffic sign recognition.

[0060] A variety of cameras may be used in a forward-facing configuration, including, for example, a monocular camera platform including a complementary metal oxide semiconductor (CMOS) color imager. Another example may be a wide-view camera 570 that may be used to capture objects entering the view from the periphery (e.g., pedestrians, crossing traffic, or bicycles). Although only one wide-view camera is shown in FIG. 5B, there may be any number of wide-view cameras 570 in the vehicle 500. In addition, a long-range camera 598 (e.g., a long-view stereo camera pair) may be used for depth-based object detection, especially for objects for which a neural network has not yet been trained. The long-range camera 598 may also be used for object detection and classification, as well as basic object tracking.

[0061] One or more stereo cameras 568 may also be included in the forward-facing configuration. The stereo camera 568 may include an integrated control unit with an extensible processing unit that may provide programmable logic (e.g., FPGA) and a multi-core microprocessor with a CAN or Ethernet interface integrated on a single chip. Such a unit may be used to generate a 3D map of the vehicle's environment, including distance estimates for all points in the image. An alternative stereo camera 568 may include a compact stereo vision sensor that may include two camera lenses (one on the left and one on the right) and an image processing chip that can measure distances from the vehicle to objects of interest and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning functions. Other types of stereo cameras 568 may be used in addition to or instead of those described herein.

[0062] A camera having a field of view that includes a portion of the environment to the side of the vehicle 500 (e.g., a side-view camera) may be used for surround view, providing information used to create and update the occupancy grid and to generate side impact collision warnings. For example, surround cameras 574 (e.g., four surround cameras 574 as shown in FIG. 5B) may be positioned around the vehicle 500. The surround cameras 574 may include wide-view cameras 570, fisheye cameras, 360-degree cameras, and / or the like. For example, four fisheye cameras may be positioned at the front, rear, and sides of the vehicle. In an alternative arrangement, the vehicle may use three surround cameras 574 (e.g., left, right, and rear) and may utilize one or more other cameras (e.g., a forward-facing camera) as a fourth surround view camera.

[0063] A camera having a field of view that includes the portion of the environment behind the vehicle 500 (e.g., a rear-view camera) may be used for parking assistance, surround view, rear collision warning, and creating and updating an occupancy grid. As described herein, a wide variety of cameras may be used, including, but not limited to, cameras that are also suitable as forward-facing cameras (e.g., long-range and / or mid-range camera 598, stereo camera 568, infrared camera 572, etc.).

[0064] A camera having a view that includes a portion of the interior or cabin of the vehicle 500 may be used to monitor one or more conditions of the driver, passengers, or objects within the cabin. Any type of camera may be used, including, but not limited to, a cabin camera 541, which may be any type of camera described herein and may be located anywhere on or within the vehicle 500 that provides a view of the cabin or interior. For example, the cabin camera 541 may be located in or on some portion of the dashboard, rear view mirror, side view mirror, seat, or door of the vehicle 500 and may be oriented to capture an image of any driver, passenger, or any other object or portion of the vehicle 500.

[0065] FIG. 5C is a block diagram of an example system architecture of the example autonomous vehicle 500 of FIG. 5A, according to some embodiments of the present disclosure. It should be understood that this and other arrangements described herein are merely illustrative. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, groupings of functions, etc.) may be used in addition to or instead of those shown, and some elements may be omitted altogether. Furthermore, many of the elements described herein are functional entities that may be implemented as separate or distributed components or in conjunction with other components, and in any suitable combination and location. Various functions described herein as being performed by entities may be implemented by hardware, firmware, and / or software. For example, various functions may be implemented by a processor executing instructions stored in a memory.

[0066] Each of the components, features, and systems of the vehicle 500 of FIG. 5C are shown as being connected via a bus 502. The bus 502 may include a controller area network (CAN) data interface (alternatively referred to as a “CAN bus”). The CAN may be a network within the vehicle 500 used to help control various features and functions of the vehicle 500, such as actuation of brakes, acceleration, braking, steering, windshield wipers, etc. The CAN bus may be configured to have dozens or even hundreds of nodes, each with its own unique identifier (e.g., CAN ID). The CAN bus may be read to find steering angle, ground speed, engine revolutions per minute (RPM), button positions, and / or other vehicle status indicators. The CAN bus may be ASIL B compliant.

[0067] The bus 502 is described herein as being a CAN bus, although this is not intended to be limiting. For example, FlexRay and / or Ethernet may be used in addition to or as an alternative to a CAN bus. Additionally, a single line is used to represent the bus 502, although this is not intended to be limiting. There may be any number of buses 502, which may include, for example, one or more CAN buses, one or more FlexRay buses, one or more Ethernet buses, and / or one or more other types of buses using different protocols. In some instances, two or more buses 502 may be used to perform different functions and / or may be used for redundancy. For example, a first bus 502 may be used for collision avoidance functions and a second bus 502 may be used for operational control. In any instance, each bus 502 may communicate with any of the components of the vehicle 500, and two or more buses 502 may communicate with the same component. In some examples, each SoC 504, each controller 536, and / or each computer in the vehicle may have access to the same input data (e.g., input from sensors in the vehicle 500) and may be connected to a common bus, such as a CAN bus.

[0068] 5A. The controller 536 may be used for a variety of functions. The controller 536 may be coupled to any of a variety of other components and systems of the vehicle 500 and may be used for control of the vehicle 500, artificial intelligence of the vehicle 500, infotainment for the vehicle 500, and / or the like.

[0069] The vehicle 500 may include a system on a chip (SoC) 504. The SoC 504 may include a CPU 506, a GPU 508, a processor 510, a cache 512, an accelerator 514, a data store 516, and / or other components and features not shown. The SoC 504 may be used to control the vehicle 500 in a variety of platforms and systems. For example, the SoC 504 may be combined in a system (e.g., the system of the vehicle 500) having an HD map 522 that can obtain map refreshes and / or updates via a network interface 524 from one or more servers (e.g., server 578 of FIG. 5D ).

[0070] CPU 506 may include a CPU cluster or CPU complex (alternatively referred to as a "CCPLEX"). CPU 506 may include multiple cores and / or L2 caches. For example, in some embodiments, CPU 506 may include eight cores in a coherent multiprocessor configuration. In some embodiments, CPU 506 may include four dual-core clusters, each with its own dedicated L2 cache (e.g., a 2MBL2 cache). CPU 506 (e.g., CCPLEX) may be configured to support concurrent cluster operation allowing any combination of CPU 506 clusters to be active at any given time.

[0071] The CPU 506 may implement power management capabilities including one or more of the following features: individual hardware blocks may be automatically clock gated when idle to conserve dynamic power, each core clock may be gated when the core is not actively executing instructions by execution of WFI / WFE instructions, each core may be independently power gated, each core cluster may be independently clock gated when all cores are clock gated or power gated, and / or each core cluster may be independently power gated when all cores are power gated. The CPU 506 may further implement an enhanced algorithm for managing power states where allowed power states and expected wake-up times are specified and the hardware / microcode determines the best power state for entering the cores, clusters, and CCPLEXes. The processing cores may support simplified power state entry sequences in software where work is offloaded to the microcode.

[0072] The GPU 508 may include an integrated GPU (alternatively referred to herein as an "iGPU"). The GPU 508 may be programmable and efficient for parallel workloads. In some instances, the GPU 508 may use an enhanced tensor instruction set. The GPU 508 may include one or more streaming microprocessors, where each streaming microprocessor may include an L1 cache (e.g., an L1 cache having at least 96 KB storage capacity) and two or more of the streaming microprocessors may share a cache (e.g., an L2 cache having 512 KB storage capacity). In some embodiments, the GPU 508 may include at least eight streaming microprocessors. The GPU 508 may use a computer-based application programming interface (API). In addition, the GPU 508 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA's CUDA).

[0073] The GPU 508 may be power optimized for best performance in automotive and embedded use cases. For example, the GPU 508 may be fabricated on FinFETs (Fin field-effect transistors). However, this is not intended to be limiting and the GPU 508 may be fabricated using other semiconductor fabrication processes. Each streaming microprocessor may incorporate several mixed-precision processing cores partitioned into multiple blocks. For example, and without limitation, 64 PF32 cores and 32 PF64 cores may be partitioned into four processing blocks. In such an example, each processing block may be assigned 16 FP32 cores, 8 FP64 cores, 16 INT32 cores, two mixed-precision NVIDIA tensor cores for deep learning matrix operations, an L0 instruction cache, a warp scheduler, a dispatch unit, and / or a 64KB register file. In addition, the streaming microprocessor may include independent parallel integer and floating-point data paths to provide efficient execution of workloads having a mix of computational and addressing operations. Streaming microprocessors may include independent thread scheduling capabilities to allow finer grain synchronization and coordination among concurrent threads. Streaming microprocessors may include a combined L1 data cache and shared memory unit to improve performance while simplifying programming.

[0074] The GPU 508 may include high bandwidth memory (HBM) and / or a 16GB HBM2 memory subsystem to provide about 900GB / sec peak memory bandwidth in some instances. In some instances, synchronous graphics random-access memory (SGRAM), such as graphics double data rate type five synchronous random-access memory (GDDR5), may be used in addition to or in place of the HBM memory.

[0075] The GPU 508 may include unified memory technology including access counters to enable more accurate movement of memory pages to the processors that access them most frequently, thereby improving the efficiency of storage ranges shared between processors. In some instances, address translation service (ATS) support may be used to enable the GPU 508 to directly access the CPU 506 page tables. In such instances, when the GPU 508 memory management unit (MMU) experiences a miss, an address translation request may be sent to the CPU 506. In response, the CPU 506 may consult its page tables for a virtual-to-real mapping of the address and send the translation back to the GPU 508. As such, the unified memory technology may enable a single unified virtual address space for both the CPU 506 and GPU 508 memories, thereby simplifying GPU 508 programming and porting of applications to the GPU 508.

[0076] In addition, GPU 508 may include access counters that can record the frequency of accesses of GPU 508 to the memory of other processors. The access counters can help ensure that memory pages are moved to the physical memory of the processors that are accessing the pages most frequently.

[0077] The SoC 504 may include any number of caches 512, including those described herein. For example, the cache 512 may include an L3 cache available to both the CPU 506 and the GPU 508 (e.g., connected to both the CPU 506 and the GPU 508). The cache 512 may include a write-back cache that can record line state, such as by using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). The L3 cache may include 4 MB or more, depending on the embodiment, although smaller cache sizes may be used.

[0078] The SoC 504 may include an arithmetic logic unit (ALU) that may be utilized in performing processing for any of the various tasks or operations (e.g., processing DNNs) of the vehicle 500. In addition, the SoC 504 may include a floating point unit (FPU) (or other math co-processor or numeric co-processor type) for performing mathematical operations within the system. For example, the SoC 104 may include one or more FPUs integrated as execution units within the CPU 506 and / or GPU 508.

[0079] The SoC 504 may include one or more accelerators 514 (e.g., hardware accelerators, software accelerators, or a combination thereof). For example, the SoC 504 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. The large on-chip memory (e.g., 4MB of SRAM) may enable the hardware acceleration cluster to accelerate neural networks and other operations. The hardware acceleration cluster may be used to complement the GPU 508 and to offload some of the tasks of the GPU 508 (e.g., to free up more cycles of the GPU 508 to perform other tasks). As an example, the accelerator 514 may be used for target workloads that are stable enough to be suitable for acceleration (e.g., perception, convolutional neural networks (CNNs), etc.). As used herein, the term "CNN" may include all types of CNNs, including region-based or regional convolutional neural networks (RCNNs) and Faster RCNNs (e.g., as used for object detection).

[0080] The accelerator 514 (e.g., a hardware acceleration cluster) may include a deep learning accelerator (DLA). The DLA may include one or more tensor processing units (TPUs) that may be configured to provide an additional 10 trillion operations per second for deep learning applications and inference. The TPU may be an accelerator configured and optimized to perform image processing functions (e.g., CNN, RCNN, etc.). The DLA may further be optimized for a specific set of neural network types and floating point operations, as well as inference. The design of the DLA may provide more performance per millimeter than a general-purpose GPU, greatly exceeding the performance of a CPU. The TPU may perform several functions, including, for example, single instance convolution functions, supporting INT8, INT16, and FP16 data types for both features and weights, as well as post-processor functions.

[0081] 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.

[0082] The DLA can perform any function of the GPU 508, and by using an inference accelerator, for example, a designer can target either the DLA or the GPU 508 for any function. For example, a designer can focus on processing CNNs and floating point operations on the DLA, and offload other functions to the GPU 508 and / or other accelerators 514.

[0083] The accelerator 514 (e.g., hardware acceleration cluster) may include a programmable vision accelerator (PVA), which may alternatively be referred to herein as a computer vision accelerator. The PVA may be designed and configured to accelerate computer vision algorithms for advanced driver assistance systems (ADAS), autonomous driving, and / or augmented reality (AR) and / or virtual reality (VR) applications. The PVA may provide a balance between performance and flexibility. For example, each PVA may include, but is not limited to, any number of reduced instruction set computer (RISC) cores, direct memory access (DMA), and / or any number of vector processors, for example.

[0084] 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.

[0085] The DMA may allow components of the PVA to access system memory independent of the CPU 506. The DMA may support any number of features used to provide optimizations to the PVA, including but not limited to supporting multi-dimensional addressing and / or circular addressing. In some instances, the DMA may support up to six or more dimensions of addressing, which may include block width, block height, block depth, horizontal block stepping, vertical block stepping, and / or depth stepping.

[0086] 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.

[0087] 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.

[0088] The accelerator 514 (e.g., a hardware acceleration cluster) may include a computer vision network-on-chip and SRAM to provide high bandwidth, low latency SRAM for the accelerator 514. In some instances, the on-chip memory may include, for example and without limitation, at least 4 MB of SRAM consisting of eight field configurable memory blocks that may be accessible by both the PVA and DLA. Each pair of memory blocks may include an advanced peripheral bus (APB) interface, configuration circuitry, controllers, and multiplexers. Any type of memory may be used. The PVA and DLA may access the memory through a backbone that provides the PVA and DLA with high speed access to the memory. The backbone may include a computer vision network-on-chip that interconnects the PVA and DLA to the memory (e.g., using the APB).

[0089] 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.

[0090] In some instances, the SoC 504 may include a real-time ray tracing hardware accelerator, such as described in U.S. Patent Application Serial No. 16 / 101,232, filed August 10, 2018. The real-time ray tracing hardware accelerator may be used to quickly and efficiently determine the location and scale of objects (e.g., within a world model) to generate real-time visualization simulations for RADAR signal interpretation, for acoustic propagation synthesis and / or analysis, for simulation of SONAR systems, for general wave propagation simulation, for comparison against LIDAR data for localization and / or other functions, and / or for other uses. In some examples, one or more tree traversal units (TTUs) may be used to perform one or more ray tracing related operations.

[0091] The accelerator 514 (e.g., a hardware accelerator cluster) has a variety of applications for autonomous driving. The PVA may be a programmable vision accelerator that can be used for critical processing stages in ADAS and autonomous vehicles. The capabilities of the PVA are suited to the domain of algorithms that require predictable processing at low power and low latency. In other words, the PVA works well with semi-dense or dense regular computations on small data sets that require predictable execution times with low latency and low power. Hence, in the context of a platform for autonomous vehicles, the PVA is designed to run classical computer vision algorithms, since the PVA is efficient in object detection and operating on integer computations.

[0092] 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.

[0093] In some instances, the PVA may be used to perform dense optical flow. For example, the PVA may be used to process raw RADAR data (e.g., using a 4D Fast Fourier Transform) to provide a processed RADAR signal before emitting the next RADAR pulse. In other instances, the 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.

[0094] 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 values. The neural network may receive as its inputs at least some subset of parameters, such as bounding box dimensions, ground plane estimates obtained (e.g., from another subsystem), inertial measurement unit (IMU) sensor 566 outputs that correlate with vehicle 500 orientation, range, and 3D position estimates of objects obtained from the neural network and / or other sensors (e.g., LIDAR sensor 564 or RADAR sensor 560), and others.

[0095] The SoC 504 may include a data store 516 (e.g., a memory). The data store 516 may be an on-chip memory of the SoC 504 and may store the neural network to be executed by the GPU and / or DLA. In some instances, the data store 516 may have a capacity large enough to store multiple instances of the neural network for redundancy and safety. The data store 516 may comprise an L2 or L3 cache 512. References to the data store 516 may include references to memory associated with the PVA, DLA, and / or other accelerators 514, as described herein.

[0096] The SoC 504 may include one or more processors 510 (e.g., embedded processors). The processors 510 may include a boot and power management processor, which may be a dedicated processor and subsystem for handling boot power and management capabilities and associated security enforcement. The boot and power management processor may be part of the SoC 504 boot sequence and may provide run-time power management services. The boot power and management processor may provide clock and voltage programming, assist with system low power state transitions, manage the SoC 504 thermal and temperature sensors, and / or manage the SoC 504 power states. Each temperature sensor may be implemented as a ring oscillator whose output frequency is proportional to temperature, and the SoC 504 may use the ring oscillator to detect the temperature of the CPU 506, the GPU 508, and / or the accelerator 514. If the temperature is determined to exceed a threshold, the boot and power management processor may enter a temperature fault routine, place the SoC 504 in a lower power state and / or place the vehicle 500 in a Chauffeur safe shutdown mode (e.g., bring the vehicle 500 to a safe shutdown).

[0097] The processor 510 may further include a set of embedded processors that may perform the functions of an audio processing engine. The audio processing engine may be an audio subsystem that allows full hardware support of multi-channel audio through multiple interfaces and a wide and flexible range of audio I / O interfaces. In some instances, the audio processing engine is a dedicated processor core that includes a digital signal processor with dedicated RAM.

[0098] The processor 510 may further include an always-on processor engine that can provide the necessary hardware features to support low power sensor management and wake use cases. The always-on processor engine may include a processor core, tightly coupled RAM, support peripherals (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0099] The processor 510 may further include a safety cluster engine that includes a processor subsystem dedicated to handling safety management of automotive applications. The safety cluster engine may include two or more processor cores, tightly coupled RAM, supporting peripherals (e.g., timers, interrupt controllers, etc.), and / or routing logic. In a safety mode, the two or more cores may operate in lockstep mode and function as a single core with comparison logic to detect any differences between their operations.

[0100] The processor 510 may further include a real-time camera engine, which may include a dedicated processor subsystem for handling real-time camera management.

[0101] The processor 510 may further include a high dynamic range signal processor, which may include an image signal processor, which is a hardware engine that is part of the camera processing pipeline.

[0102] The processor 510 may include a video image compositor, which may be a processing block (e.g., implemented in a microprocessor) that implements video post-processing functions required by the video playback application to produce a final image for the player window. The video image compositor may perform lens distortion correction on the wide-view camera 570, on the surround camera 574, and / or on the in-cabin surveillance camera sensor. The in-cabin surveillance camera sensor is preferably monitored by a neural network running on another instance of the advanced SoC, configured to identify in-cabin events and respond appropriately. The in-cabin system may perform lip reading to activate cellular service and make phone calls, dictate emails, change the vehicle's destination, activate or change the vehicle's infotainment system and settings, or provide voice-activated web surfing. Certain features are only available to the driver when operating in autonomous mode and are disabled otherwise.

[0103] 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.

[0104] The video image composer may also be configured to perform stereo rectification on the input stereo lens frames. The video image composer may further be used for user interface compositing when the operating system desktop is in use and the GPU 508 is not required to continuously render new surfaces. Even when the GPU 508 is powered on and actively performing 3D rendering, the video image composer may be used to offload the GPU 508 for improved performance and responsiveness.

[0105] The SoC504 may further include a mobile industry processor interface (MIPI) camera serial interface for receiving video and input from a camera, a high-speed interface, and / or a video input block that may be used for camera and related pixel input functions. The SoC504 may further include an input / output controller that may be controlled by software and that may be used to receive I / O signals that are not committed to a specific role. The SoC 504 may further include a wide range of peripheral interfaces to enable peripherals, audio codecs, power management, and / or communication with other devices. The SoC 504 may be used to process data from cameras (e.g., connected via gigabit multimedia serial links and Ethernet), sensors (e.g., LIDAR sensor 564, RADAR sensor 560, etc., which may be connected via Ethernet), data from bus 502 (e.g., speed of vehicle 500, steering wheel position, etc.), and data from GNSS sensor 558 (e.g., connected via Ethernet or CAN bus). The SoC 504 may further include a dedicated high-performance mass storage controller, which may include its own DMA engine and may be used to offload the CPU 506 from routine data management tasks.

[0106] The SoC504 may be an end-to-end platform with a flexible architecture that spans levels 3-5 of automation, thereby providing a comprehensive functional safety architecture that leverages and efficiently uses computer vision and ADAS techniques for diversity and redundancy, and provides a platform for a flexible, reliable driving software stack along with deep learning tools. The SoC504 may be faster, more reliable, and more energy- and space-efficient than traditional systems. For example, when the accelerator 514 is combined with the CPU 506, the GPU 508, and the data store 516, the SoC504 may provide a fast and efficient platform for levels 3-5 of autonomous vehicles.

[0107] 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.

[0108] In contrast to conventional systems, by providing a CPU complex, a GPU complex, and a hardware acceleration cluster, the techniques described herein allow multiple neural networks to run simultaneously and / or sequentially and the results to be combined to enable Level 3-5 autonomous driving capabilities. For example, the CNN running on the DLA or dGPU (e.g., GPU520) can include text and word recognition that allows the supercomputer to read and understand traffic signs, including signs for which the neural network was not specifically trained. The DLA can further include neural networks that can identify, interpret, and provide a semantic understanding of the signs and pass the semantic understanding to a route planning module running on the CPU complex.

[0109] As another example, multiple neural networks may be run simultaneously, as required for level 3, 4, or 5 driving. For example, a warning sign consisting of "Caution: Flashing lights indicate icy conditions" along with a lightning flash may be interpreted by several neural networks, independently or collectively. The sign itself may be identified as a traffic sign by a first deployed neural network (e.g., a trained neural network), and the text "Flashing lights indicate icy conditions" may be interpreted by a second deployed neural network that informs the vehicle's route planning software (preferably running on the CPU complex) that icy conditions exist when a flashing light is detected. The flashing light may be identified by running a third deployed neural network through multiple frames, informing the vehicle's route planning software of the presence (or absence) of the flashing light. All three neural networks may be run simultaneously, such as within the DLA and / or on the GPU 508.

[0110] In some instances, a CNN for facial recognition and vehicle owner identification can use data from the camera sensors to identify the presence of a legitimate driver and / or owner of the vehicle 500. An always-on sensor processing engine can be used to unlock the vehicle and turn on the lights when the owner approaches the driver's door, and in security mode, to disable vehicle operation when the owner leaves the vehicle. In this manner, the SoC 504 provides security against theft and / or carjacking.

[0111] In another example, a CNN for emergency vehicle detection and identification can detect and identify emergency vehicle sirens using data from microphone 596. In contrast to conventional systems that use general classifiers to detect sirens and manually extract features, SoC 504 uses CNNs for classification of environmental and urban sounds, as well as classification of visual data. In a preferred embodiment, the CNN running on the DLA is trained to identify the relative terminal velocity of emergency vehicles (e.g., by using the Doppler effect). The CNN can also be trained to identify emergency vehicles specific to the local area in which the vehicle is operating, as identified by the GNSS sensor 558. Thus, for example, when operating in Europe, the CNN will attempt to detect European sirens, and when in the United States, the CNN will attempt to identify only North American sirens. After an emergency vehicle is detected, a control program can be used to perform emergency vehicle safety routines, such as slowing the vehicle down, stopping at the side of the road, parking the vehicle, and / or idling the vehicle, with the assistance of ultrasonic sensor 562, until the emergency vehicle has passed.

[0112] The vehicle may include a CPU 518 (e.g., a separate CPU, or a dCPU) that may be coupled to the SoC 504 via a high-speed interconnect (e.g., PCIe). The CPU 518 may include, for example, an X86 processor. The CPU 518 may be used to perform any of a variety of functions, including, for example, reconciling potentially inconsistent results between the ADAS sensors and the SoC 504, and / or monitoring the status and health of the controller 536 and / or the infotainment SoC 530.

[0113] Vehicle 500 may include a GPU 520 (e.g., a discrete GPU, or a dGPU) that may be coupled to SoC 504 via a high-speed interconnect (e.g., NVIDIA's NVLINK). GPU 520 may provide additional artificial intelligence capabilities, such as by running redundant and / or different neural networks, and may be used to train and / or update neural networks based on inputs (e.g., sensor data) from sensors of vehicle 500.

[0114] The vehicle 500 may further include a network interface 524, which may include one or more wireless antennas 526 (e.g., one or more wireless antennas for different communication protocols, such as a cellular antenna, a Bluetooth antenna, etc.). The network interface 524 may be used to enable wireless connections with the cloud over the Internet (e.g., with a server 578 and / or other network devices), with other vehicles, and / or with computing devices (e.g., passenger client devices). To communicate with other vehicles, a direct link may be established between the two vehicles and / or an indirect link may be established (e.g., through a network and via the Internet). A direct link may be provided using a vehicle-to-vehicle communication link. The vehicle-to-vehicle communication link may provide the vehicle 500 information about vehicles in close proximity to the vehicle 500 (e.g., vehicles in front of, beside, and / or behind the vehicle 500). This function may be part of a cooperative adaptive cruise control function of the vehicle 500.

[0115] The network interface 524 may include a SoC that provides modulation and demodulation functions and enables the controller 536 to communicate over a wireless network. The network interface 524 may include a radio frequency front end for upconversion from baseband to radio frequency and downconversion from radio frequency to baseband. The frequency conversion may be performed through well known processes and / or may be performed using a superheterodyne process. In some instances, the radio frequency front end functions may be provided by a separate chip. The network interface may include wireless functions for communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-Wave, ZigBee, LoRaWAN, and / or other wireless protocols. The vehicle 500 may further include a data store 528, which may include off-chip (e.g., off-SoC 504) storage. The data store 528 may include one or more memory elements, including RAM, SRAM, DRAM, VRAM, flash, hard disk, and / or other components and / or devices capable of storing at least one bit of data.

[0116] The vehicle 500 may include GNSS sensors 558 (e.g., GPS and / or assisted GPS sensors) to aid in mapping, perception, occupancy grid generation, and / or route planning functions. Any number of GNSS sensors 558 may be used, including, but not limited to, a GPS using a USB connector with an Ethernet to serial (RS-232) bridge. The vehicle 500 may further include a RADAR sensor 560. The RADAR sensor 560 may be used by the vehicle 500 for long-range vehicle detection, even in darkness and / or severe weather conditions. The RADAR functional safety level may be ASIL B. In some instances, the RADAR sensor 560 may use the CAN and / or bus 502 for control and to access object tracking data (e.g., to transmit data generated by the RADAR sensor 560), with access to Ethernet to access raw data. A wide variety of RADAR sensor types may be used. For example, and without limitation, the RADAR sensor 560 may be suitable for front, rear, and side RADAR use. In some instances, a pulsed Doppler RADAR sensor is used.

[0117] The RADAR sensor 560 may include different configurations, such as long range with a narrow field of view, short range with a wide field of view, and short range side coverage. In some instances, the long range RADAR may be used for adaptive cruise control functions. Long range RADAR systems may provide a wide field of view achieved by two or more independent scans, such as within a 250m range. The RADAR sensor 560 may help distinguish between static and moving objects and may be used by ADAS systems for emergency brake assist and forward collision warning. The long range RADAR sensor may include a monostatic multimodal RADAR with multiple (e.g., six or more) fixed RADAR antennas and high speed CAN and FlexRay interfaces. In one instance with six antennas, the center four antennas may create a focused beam pattern designed to record the surroundings of the vehicle 500 at high speeds with minimal interference from traffic in adjacent lanes. The other two antennas may increase the field of view, allowing for quick detection of vehicles entering or leaving the lane of the vehicle 500.

[0118] As an example, a mid-range RADAR system may include a range of up to 560m (front) or 80m (rear) and a field of view of up to 42 degrees (front) or 550 degrees (rear). A short-range RADAR system may include, but is not limited to, a RADAR sensor designed to be mounted on either end of the rear bumper. When mounted on either end of the rear bumper, such a RADAR sensor system can create two beams that constantly monitor the blind spots behind and next to the vehicle.

[0119] Short-range RADAR systems may be used in ADAS systems for blind spot detection and / or lane change assist.

[0120] The vehicle 500 may further include ultrasonic sensors 562. The ultrasonic sensors 562, which may be located at the front, rear, and / or sides of the vehicle 500, may be used for parking assist and / or for creating and updating an occupancy grid. A wide variety of ultrasonic sensors 562 may be used, with different ultrasonic sensors 562 being used for different ranges of detection (e.g., 2.5m, 4m). The ultrasonic sensors 562 may operate at a functional safety level of ASIL B.

[0121] The vehicle 500 may include a LIDAR sensor 564. The LIDAR sensor 564 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. The LIDAR sensor 564 may be functional safety level ASIL B. In some instances, the vehicle 500 may include multiple (e.g., 2, 4, 6, etc.) LIDAR sensors 564 that may use Ethernet (e.g., to provide data to a Gigabit Ethernet switch).

[0122] In some instances, the LIDAR sensor 564 may have the ability to provide a list of objects and their distances in a 360-degree field of view. A commercially available LIDAR sensor 564 may have an advertised range of about 100 m, for example, with an accuracy of 2 cm to 3 cm, and with support for a 100 Mbps Ethernet connection. In some instances, one or more non-protruding LIDAR sensors 564 may be used. In such instances, the LIDAR sensor 564 may be implemented as a small device that may be integrated into the front, rear, sides, and / or corners of the vehicle 500. In such instances, the LIDAR sensor 564 may have a range of 200 m even for low-reflecting objects, and provide up to a 120-degree horizontal and 35-degree vertical field of view. A front-mounted LIDAR sensor 564 may be configured for a horizontal field of view between 45 and 135 degrees.

[0123] In some instances, LIDAR technology such as 3D flash LIDAR may also be used. 3D flash LIDAR uses a laser flash as a transmitter to illuminate the surroundings of the vehicle up to about 200 m. The flash LIDAR unit includes a receptor that records the laser pulse transit time and the reflected light on each pixel, which in turn corresponds to the range from the vehicle to the object. Flash LIDAR may allow a highly accurate and undistorted image of the surroundings to be generated with every laser flash. In some instances, four flash LIDAR sensors may be deployed, one on each side of the vehicle 500. Available 3D flash LIDAR systems include solid-state 3D steering array LIDAR cameras that have no moving parts other than the blower (e.g., non-scanning LIDAR devices). Flash LIDAR devices may use 5 nanosecond Class I (eye-safe) laser pulses per frame and may capture reflected laser light in the form of a 3D range point cloud and coregistered intensity data. By using flash LIDAR, and because flash LIDAR is a solid-state device with no moving parts, the LIDAR sensor 564 may be less susceptible to motion blur, vibration, and / or shock.

[0124] The vehicle may further include an IMU sensor 566. In some instances, the IMU sensor 566 may be positioned at the center of the rear axle of the vehicle 500. The IMU sensor 566 may include, for example, but not limited to, an accelerometer, a magnetometer, a gyroscope, a magnetic compass, and / or other sensor types. In some instances, such as in a 6-axis application, the IMU sensor 566 may include an accelerometer and a gyroscope, while in a 9-axis application, the IMU sensor 566 may include an accelerometer, a gyroscope, and a magnetometer.

[0125] In some embodiments, the IMU sensor 566 may be implemented as a miniature, high-performance GPS-Aided Inertial Navigation System (GPS / INS) that combines micro-electro-mechanical system (MEMS) inertial sensors, highly sensitive GPS receivers, and advanced Kalman filtering algorithms to provide estimates of position, velocity, and attitude. As such, in some instances, the IMU sensor 566 may enable the vehicle 500 to estimate heading without requiring input from a magnetic sensor by directly observing and correlating changes in velocity from the GPS to the IMU sensor 566. In some instances, the IMU sensor 566 and the GNSS sensor 558 may be combined in a single integrated unit. The vehicle may include microphones 596 placed in and / or around the vehicle 500. The microphones 596 may be used for emergency vehicle detection and identification, among other things.

[0126] The vehicle may further include any number of camera types, including stereo cameras 568, wide view cameras 570, infrared cameras 572, surround cameras 574, long and / or mid-range cameras 598, and / or other camera types. The cameras may be used to capture image data around the entire exterior of the vehicle 500. The type of cameras used depends on the embodiment and requirements of the vehicle 500, and any combination of camera types may be used to achieve the required coverage around the vehicle 500. Additionally, the number of cameras may vary depending on the embodiment. For example, the vehicle may include six cameras, seven cameras, ten cameras, twelve cameras, and / or another number of cameras. The cameras may support, by way of example only, Gigabit Multimedia Serial Link (GMSL) and / or Gigabit Ethernet. Each camera is described in further detail herein with respect to FIGS. 5A and 5B. The vehicle 500 may further include a vibration sensor 542. The vibration sensor 542 may measure vibrations of vehicle components, such as an axle. For example, a change in vibration may indicate a change in the surface of the road. In another example, when two or more vibration sensors 542 are used, the difference in vibration may be used to determine friction or slippage of the road surface (e.g., when the difference in vibration is between a powered axle and a free-running axle).

[0127] The vehicle 500 may include an ADAS system 538. In some instances, the ADAS system 538 may include a SoC. The ADAS system 538 may include autonomous / adaptive / automatic cruise control (ACC), cooperative adaptive cruise control (CACC), forward crash warning (FCW), automatic emergency braking (AEB), lane departure warning (LDW), lane keep assist (LKA), blind spot warning (BSW), rear cross-traffic warning (RCTW), collision warning system (CWS), lane centering (LC), and / or other features and functions.

[0128] The ACC system may use a RADAR sensor 560, a LIDAR sensor 564, and / or a camera. The ACC system may include longitudinal ACC and / or lateral ACC. Longitudinal ACC monitors and controls the distance to the vehicle directly ahead of the vehicle 500 and automatically adjusts the vehicle speed to maintain a safe distance from the vehicle ahead. Lateral ACC performs distance keeping and advises the vehicle 500 to change lanes when necessary. Lateral ACC is related to other ADAS applications such as LC and CWS.

[0129] CACC uses information from other vehicles, which may be received from other vehicles via a wireless link via the network interface 524 and / or the wireless antenna 526, or indirectly via a network connection (e.g., via the Internet). A direct link may be provided by a vehicle-to-vehicle (V2V) communication link, while an indirect link may be an infrastructure-to-vehicle (I2V) communication link. In general, a V2V communication concept provides information about the immediately preceding vehicle (e.g., the vehicle directly ahead of the vehicle 500, in the same lane as the vehicle 500), while an I2V communication concept provides information about the traffic further ahead. A CACC system may include either or both I2V and V2V information sources. Given the information of the vehicles ahead of the vehicle 500, CACC may be more reliable and may potentially allow traffic to flow more smoothly and reduce congestion on the roads.

[0130] The FCW system is designed to warn the driver of hazards so that the driver can take corrective action. The FCW system uses a forward-facing camera and / or RADAR sensor 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback such as a display, speaker, and / or vibration components. The FCW system can provide warnings in the form of audio, visual alerts, vibrations, and / or quick brake pulses.

[0131] An AEB system can detect an imminent forward collision with another vehicle or other object and automatically apply the brakes if the driver does not take corrective action within specified time or distance parameters. The AEB system can use a forward-facing camera and / or RADAR sensor 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC. When the AEB system detects a hazard, the AEB system typically first alerts the driver to take corrective action to avoid the collision, and if the driver does not take corrective action, the AEB system can automatically apply the brakes as part of an effort to prevent, or at least mitigate, the effects of the predicted collision. The AEB system can include techniques such as Dynamic Brake Support and / or Collision Imminent Braking.

[0132] The LDW system provides visual, audible, and / or tactile warnings, such as vibrations in the steering wheel or seat, to alert the driver when the vehicle 500 crosses a lane marking. The LDW system is not activated when the driver indicates an intentional lane departure by activating a turn signal. The LDW system may use a forward-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC electrically coupled to driver feedback, such as a display, speaker, and / or vibration components.

[0133] The LKA system is a modification of the LDW system, which provides steering input or braking to correct the vehicle 500 if it begins to drift out of its lane. The BSW system detects and warns the vehicle driver in the vehicle's blind spot. The BSW system can provide visual, audible, and / or tactile warnings to indicate that merging or changing lanes is unsafe. The system can provide additional warnings when the driver uses a turn signal. The BSW system can use rear-facing cameras and / or RADAR sensors 560 coupled to dedicated processors, DSPs, FPGAs, and / or ASICs electrically coupled to driver feedback, e.g., displays, speakers, and / or vibration components.

[0134] The RCTW system may provide visual, audible, and / or tactile notifications when an object is detected outside the range of the rear camera when the vehicle 500 is backing up. Some RCTW systems include AEB to ensure vehicle brakes are applied to avoid a collision. The RCTW system may use one or more rear-facing RADAR sensors 560 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, electrically coupled to driver feedback, e.g., a display, speaker, and / or vibration components.

[0135] Because conventional ADAS systems alert the driver and allow the driver to determine whether a safety condition truly exists and act accordingly, conventional ADAS systems can be prone to producing false positive results that are usually not catastrophic but can be annoying and distracting to the driver. However, in an autonomous vehicle 500, the vehicle 500 itself must decide whether to listen to the results from the primary computer or the secondary computer (e.g., the first controller 536 or the second controller 536) when the results are conflicting. For example, in some embodiments, the ADAS system 538 may be a backup and / or secondary computer to provide perception information to a backup computer rationality module. The backup computer rationality monitor may run redundant and diverse software on hardware components to detect impairments in perception and dynamic driving tasks. Output from the ADAS system 538 may be provided to a supervisory MCU. When the outputs from the primary and secondary computers conflict, the supervisory MCU must decide how to reconcile the conflict to ensure safe operation.

[0136] 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.

[0137] The supervisory MCU may be configured to execute a neural network that is trained and configured to determine conditions under which the secondary computer provides a false alarm based on the outputs from the primary and secondary computers. Thus, the neural network in the supervisory MCU may learn when the output of the secondary computer may be trusted and when it may not be trusted. For example, when the secondary computer is a RADAR-based FCW system, the neural network in the supervisory MCU may learn when the FCW identifies a metal object that is not actually a hazard, such as a sewer grate or manhole cover, that triggers an alarm. Similarly, when the secondary computer is a camera-based LDW system, the neural network in the supervisory MCU may learn to ignore the LDW when a bicyclist or pedestrian is present and lane departure is, in fact, the safest maneuver. In embodiments that include a neural network executing on the supervisory MCU, the supervisory MCU may include at least one of a DLA or a GPU suitable for executing the neural network with associated memory. In a preferred embodiment, the director MCU may comprise and / or be included as a component of the SoC 504 .

[0138] In other instances, the ADAS system 538 may include a secondary computer that performs ADAS functions using classical rules of computer vision. As such, the secondary computer may use classical computer vision rules (if-then) and the presence of a neural network in the supervisory MCU may improve reliability, safety and performance. For example, the diverse implementations and intentional non-identity may make the overall system more fault-tolerant, especially to failures caused by software (or software-hardware interface) functions. For example, if there is a software bug or error in the software running on the primary computer and non-identical software code running on the secondary computer provides the same overall result, the supervisory MCU may have greater confidence that the overall result is correct and that a bug in the software or hardware used by the primary computer has not caused a critical error.

[0139] In some instances, the output of the ADAS system 538 may be fed to the perception block of the primary computer and / or the dynamic driving task block of the primary computer. For example, if the ADAS system 538 indicates a forward collision warning due to an object directly ahead, the perception block may use this information when identifying the object. In other instances, the secondary computer may have its own neural network that is trained as described herein, thus reducing the risk of false positives.

[0140] Vehicle 500 may further include an infotainment SoC 530 (e.g., an in-vehicle infotainment system (IVI)). Although shown and described as an SoC, the infotainment system need not be an SoC and may include two or more separate components. Infotainment SoC 530 may include a combination of hardware and software that may be used to provide audio (e.g., music, personal digital assistant, navigation instructions, news, radio, etc.), video (e.g., TV, movies, streaming, etc.), telephony (e.g., hands-free calling), network connectivity (e.g., LTE, Wi-Fi, etc.), and / or information services (e.g., navigation system, rear park assist, wireless data system, vehicle related information such as fuel level, total distance traveled, brake fuel level, oil level, door open / close, air filter information, etc.) to vehicle 500. For example, the infotainment SoC 530 may be a radio, a disc player, a navigation system, a video player, USB and Bluetooth connectivity, a car computer, in-car entertainment, Wi-Fi, steering wheel audio controls, hands-free voice control, a heads-up display (HUD), an HMI display 534, a telematics device, a control panel (e.g., for controlling and / or interacting with various components, features, and / or systems), and / or other components. The infotainment SoC 530 may further be used to provide information (e.g., visual and / or audible) to a user of the vehicle, such as information from an ADAS system 538, autonomous driving information such as planned vehicle maneuvers, trajectory, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.), and / or other information.

[0141] The infotainment SoC 530 may include GPU functionality. The infotainment SoC 530 may communicate with other devices, systems, and / or components of the vehicle 500 via the bus 502 (e.g., CAN bus, Ethernet, etc.). In some instances, the infotainment SoC 530 may be coupled to the supervisor MCU such that the infotainment system's GPU may perform some self-drive functions in the event that the primary controller 536 (e.g., the vehicle's 500 primary and / or backup computer) fails. In such instances, the infotainment SoC 530 may place the vehicle 500 in a Chauffeur safe shutdown mode, as described herein.

[0142] The vehicle 500 may further include an instrument cluster 532 (e.g., a digital dash, an electronic instrument cluster, a digital instrument panel, etc.). The instrument cluster 532 may include a controller and / or a supercomputer (e.g., a separate controller or a supercomputer). The instrument cluster 532 may include a set of instruments such as a speedometer, a fuel level, an oil pressure, a tachometer, an odometer, a turn signal, a gear shift position indicator, a seat belt warning light, a parking brake warning light, an engine malfunction light, an airbag (SRS) system information, lighting controls, safety system controls, navigation information, etc. In some instances, information may be displayed and / or shared between the infotainment SoC 530 and the instrument cluster 532. In other words, the instrument cluster 532 may be included as part of the infotainment SoC 530, or vice versa.

[0143] 5D is a system diagram of communication between a cloud-based server and an example autonomous vehicle 500 of FIG. 5A according to some embodiments of the disclosure. System 576 may include a server 578, a network 590, and a vehicle including vehicle 500. Server 578 may include multiple GPUs 584(A)-584(H) (collectively referred to herein as GPUs 584), PCIe switches 582(A)-582(H) (collectively referred to herein as PCIe switches 582), and / or CPUs 580(A)-580(B) (collectively referred to herein as CPUs 580). GPUs 584, CPUs 580, and PCIe switches may be interconnected with a high-speed interconnect, such as, but not limited to, an NVLink interface 588 developed by NVIDIA and / or a PCIe connection 586. In some instances, the GPUs 584 are connected via an NVLink and / or NVSwitch SoC, and the GPUs 584 and PCIe switch 582 are connected via a PCIe interconnect. Although eight GPUs 584, two CPUs 580, and two PCIe switches are illustrated, this is not intended to be limiting. Depending on the embodiment, each server 578 may include any number of GPUs 584, CPUs 580, and / or PCIe switches. For example, the servers 578 may each include 8, 16, 32, and / or more GPUs 584.

[0144] Server 578 may receive image data from the vehicle over network 590, the image data representing images showing unexpected or changed road conditions, such as recently started road construction. Server 578 may transmit neural network 592, updated neural network 592, and / or map information 594, including information about traffic and road conditions, to the vehicle over network 590. Updates to map information 594 may include updates to HD map 522, such as information about construction sites, potholes, detours, flooding, and / or other obstacles. In some instances, neural network 592, updated neural network 592, and / or map information 594 may have arisen from new training and / or experience represented in data received from any number of vehicles in the environment and / or based on training performed at a data center (e.g., using server 578 and / or other servers).

[0145] The server 578 may be used to train a machine learning model (e.g., a neural network) based on the training data. The training data may be generated by the vehicle and / or generated in a simulation (e.g., using a game engine). In some instances, the training data is tagged (e.g., if the neural network benefits from supervised learning) and / or undergoes other pre-processing, while in other instances, the training data is not tagged and / or pre-processed (e.g., if the neural network does not require supervised learning). The training may be performed according to any one or more classes of machine learning techniques, including, but not limited to, the following classes: supervised training, semi-supervised training, unsupervised training, self-learning, reinforcement learning, federated learning, transfer learning, feature learning (including principal component and cluster analysis), multi-linear subspace learning, manifold learning, representation learning (including preliminary dictionary learning), rule-based machine learning, anomaly detection, and variations or combinations thereof. After the machine-learned model has been traced, the machine-learned model may be used by the vehicle (e.g., transmitted to the vehicle via network 590) and / or the machine-learned model may be used by server 578 to remotely monitor the vehicle.

[0146] In some instances, server 578 can receive data from vehicles and apply the data to state-of-the-art real-time neural networks for real-time intelligent inference. Server 578 can include deep learning supercomputers and / or dedicated AI computers powered by GPU 584, such as DGX and DGX Station machines developed by NVIDIA. However, in some instances, server 578 can include a deep learning infrastructure that uses only CPU-powered data centers.

[0147] The deep learning infrastructure of server 578 may be capable of rapid real-time inference and may use that capability to evaluate and validate the health of the processor, software, and / or associated hardware within vehicle 500. For example, the deep learning infrastructure may receive periodic updates from vehicle 500, such as a sequence of images and / or objects where vehicle 500 was located within the sequence of images (e.g., via computer vision and / or other machine learning object classification techniques). The deep learning infrastructure may run its own neural networks to identify objects and compare them to objects identified by vehicle 500, and if the results do not match and the infrastructure concludes that the AI ​​within vehicle 500 is not functioning properly, server 578 may send a signal to vehicle 500 that infers control, notifies passengers, and commands the failsafe computer of vehicle 500 to complete a safe parking maneuver.

[0148] For inference, the server 578 may include a GPU 584 and one or more programmable inference accelerators (e.g., NVIDIA's TensorRT). The combination of a GPU-powered server and inference acceleration can enable real-time responsiveness. In other instances, such as when less performance is required, servers powered by CPUs, FPGAs, and other processors may be used for inference.

[0149] 5 is a block diagram of an example computing device 500 suitable for use in implementing some embodiments of the present disclosure. The computing device 500 may include an interconnect system 502 that indirectly or directly couples the following devices: memory 504, one or more central processing units (CPUs) 506, one or more graphic processing units (GPUs) 508, a communication interface 510, I / O ports 512, input / output components 514, a power supply 516, one or more presentation components 518 (e.g., a display), and one or more logic units 520.

[0150] Although the various blocks in FIG. 5 are shown as connected via interconnect system 502 with lines, this is not intended to be limiting and is merely for clarity. For example, in some embodiments, a presentation component 518, such as a display device, may be considered an I / O component 514 (e.g., where the display is a touch screen). As another example, CPU 506 and / or GPU 508 may include memory (e.g., memory 504 may represent a storage device in addition to the memory of GPU 508, CPU 506, and / or other components). In other words, the computing devices of FIG. 5 are merely exemplary. Categories such as "workstations," "servers," "laptops," "desktops," "tablets," "client devices," "mobile devices," "handheld devices," "gaming consoles," "electronic control units (ECUs)," "virtual reality systems," "augmented reality systems," and / or other device or system types are all intended to be within the scope of the computing devices of FIG. 5 and therefore are not to be differentiated.

[0151] The interconnect system 502 may represent one or more links or buses, such as an address bus, a data bus, a control bus, or a combination thereof. The interconnect system 502 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 506 may be directly connected to the memory 504. Additionally, the CPU 506 may be directly connected to the GPU 508. When there are direct or point-to-point connections between components, the interconnect system 502 may include a PCIe link to implement the connections. In these examples, a PCI bus need not be included in the computing device 500.

[0152] Memory 504 may include any of a variety of computer readable media. Computer readable media may be any available media that can be accessed by computing device 500. Computer readable media may include both volatile and nonvolatile media, and removable and non-removable media. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media.

[0153] Computer storage media may include both volatile and nonvolatile media and / or removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, and / or other data types. For example, memory 504 may store computer readable instructions (e.g., representing programs and / or program elements), such as an operating system. Computer storage media may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile 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 500. As used herein, computer storage media does not include the signals themselves.

[0154] 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.

[0155] The CPU 506 may be configured to execute at least some of the computer readable instructions to control one or more components of the computing device 500 to perform one or more of the methods and / or processes described herein. The CPU 506 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 506 may include any type of processor, and may include different types of processors depending on the type of computing device 500 implemented (e.g., a processor with fewer cores for a mobile device and a processor with more cores for a server). For example, depending on the type of computing device 500, the processor may be an Advanced RISC Machines (ARM) processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). Computing device 500 may include one or more CPUs 506 within one or more microprocessors or auxiliary coprocessors, such as computational coprocessors.

[0156] In addition to or in lieu of CPU 506, GPU 508 may be configured to execute at least some of the computer readable instructions to control one or more components of computing device 500 to perform one or more of the methods and / or processes described herein. One or more of GPUs 508 may be integrated GPUs (e.g., with one or more of CPUs 506 and / or one or more of GPUs 508 may be discrete GPUs. In an embodiment, one or more of GPUs 508 may be coprocessors of one or more of CPUs 506. GPU 508 may be used by computing device 500 to render graphics (e.g., 3D graphics) or perform general purpose computations. For example, GPU 508 may be configured to perform general purpose computing on a GPU (GPGPU). A graphics processing unit (GPU) may be used for processing graphics data. GPU 508 may include hundreds or thousands of cores capable of processing hundreds or thousands of software threads simultaneously. GPU 508 may generate pixel data for an output image in response to rendering commands (e.g., rendering commands from CPU 506 received via a host interface). GPU 508 may include graphics memory, e.g., display memory, for storing the pixel data or any other suitable data, e.g., GPGPU data. The display memory may be included as part of memory 504. GPU 508 may include two or more GPUs operating in parallel (e.g., via links). The links may connect the GPUs directly (e.g., using NVLINK) or may connect the GPUs via a switch (e.g., using NVSwitch). When coupled together, each GPU 508 may generate pixel data or GPGPU data for a different portion of the output or for a different output (e.g., a first GPU for a first image and a second GPU for a second image). Each GPU may include its own memory or may share memory with the other GPUs. In addition to or instead of the CPU 506 and / or GPU 508, the logic unit 520 may be configured to execute at least some of the computer readable instructions to control one or more of the computing devices 500 to perform one or more of the methods and / or processes described herein. In an embodiment, the CPU 506, the GPU 508, and / or the logic unit 520 may execute any combination of the methods, processes and / or portions thereof, either discretely or jointly. One or more of the logic units 520 may be part of and / or integrated with one or more of the CPU 506 and / or GPU 508, and / or one or more of the logic units 520 may be a discrete component to or otherwise external to the CPU 506 and / or GPU 508. In an embodiment, one or more of the logic units 520 may be a co-processor of one or more of the CPU 506 and / or GPU 508.

[0157] Examples of logic unit 520 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 I / O element, a Peripheral Component Interconnect (PCI) or Peripheral Component Interconnect Express (PCIe) element, and / or the like.

[0158] The communications interface 510 may include one or more receivers, transmitters, and / or transceivers that enable the computing device 500 to communicate with other computing devices over electronic communications networks, including wired and / or wireless communications. The communications interface 510 may include components and functionality 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.

[0159] The I / O ports 512 may enable the computing device 500 to be logically coupled to other devices, including I / O components 514, presentation components 518, and / or other components, some of which may be built-in (e.g., integrated) to the computing device 500. Exemplary I / O components 514 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 514 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 500 (as described in more detail below). Computing device 500 may include a depth camera, such as a stereoscopic camera system, an infrared camera system, an RGB camera system, touch screen technology, and combinations thereof, for gesture detection and recognition. Additionally, computing device 500 may include an accelerometer or gyroscope (e.g., as part of an inertia measurement unit (IMU)) to enable detection of motion. In some instances, the output of the accelerometer or gyroscope may be used by computing device 500 to render immersive augmented or virtual reality.

[0160] The power supply 516 may include a hardwired power supply, a battery power supply, or a combination thereof. The power supply 516 may provide power to the computing device 500 to enable the components of the computing device 500 to operate. The presentation component 518 may include a display (e.g., a monitor, a touch screen, a television screen, a heads-up display (HUD), other display types, or a combination thereof), speakers, and / or other presentation components. The presentation component 518 can receive data from other components (e.g., GPU 508, CPU 506, etc.) and output data (e.g., as images, video, sound, etc.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] FIG. 7 is an example flow diagram of a process for operating a vehicle according to some embodiments of the present disclosure. Process 700, and any of the following processes, may be performed by a processing circuit. The processing circuit may include inference and / or training logic. The processing circuit may also include one or more processors 518 and / or a graphical processor unit 520. The processing circuit may also include one or more hardware accelerators (e.g., DLA and / or PLA). As described herein, a processing circuit should be understood to mean a circuit based on one or more microprocessors, microcontrollers, digital signal processors, programmable logic devices, systems on chips (SoCs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc., and may include a multi-core processor (e.g., dual-core, quad-core, hexa-core, or any suitable number of cores). In some embodiments, the processing circuit may be distributed across multiple separate processors or processing units, e.g., multiple of the same type of processing units or multiple different processors. Any type and structure of processing circuitry may be used. For example, the processing circuitry may include a multi-core processor, a multi-core processor structured as a graphics or computation pipeline for performing operations in parallel, a neuromorphic processor, any other parallel processor or graphics processor, or the like. In at least one embodiment, the processing circuitry may include, but is not limited to, a Complex Instruction Set Computer ("CISC") microprocessor, a Reduced Instruction Set Computing ("RISC") microprocessor, a Very Long Instruction Word ("VLIW") microprocessor, a processor implementing a combination of instruction sets, or any other processor device, such as a digital signal processor or a graphics processor.

[0165] Referring now to Figures 7-10, each block of the methods described in Figures 7-10 described herein includes computational processes that may be performed using any combination of hardware, firmware, and / or software. For example, various functions may be implemented by processor-executed instructions stored in memory. The methods 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 of Figures 7-10 are described with respect to the exemplary autonomous vehicle system of Figures 5A-5D, by way of example. However, these methods may additionally or alternatively be performed by any one system or any combination of systems, including but not limited to those described herein.

[0166] At 702, the processing circuitry receives data from one or more sensors indicative of a trajectory of an object external to the vehicle. In some embodiments, the processing circuit receives data from at least one of a global navigation satellite system ("GNSS") sensor 558 (e.g., a global positioning system sensor), a RADAR sensor 560, an ultrasonic sensor 562, a LIDAR sensor 564, an inertial measurement unit ("IMU") sensor 566 (e.g., an accelerometer, a gyroscope, a magnetic compass, a magnetometer, etc.), a microphone 596, a stereo camera 568, a wide view camera 570 (e.g., a fisheye camera), an infrared camera 572, a surround camera 574 (e.g., a 360 degree camera), a long-range camera (not shown in FIG. 5A ), a mid-range camera (not shown in FIG. 5A ), a speed sensor 544 (e.g., for measuring the speed of the vehicle 500), a vibration sensor 542, a steering sensor 540, a brake sensor (e.g., as part of a brake sensor system 546), and / or other sensor types.

[0167] At 704, the processing circuitry determines one or more attributes of the object external to the vehicle. In some embodiments, the processing circuitry is communicatively coupled via network 590 to one or more neural networks 592 to determine the one or more attributes of the object. In some embodiments, the processing circuitry determines an additional attribute including at least one of a location attribute, a weather attribute, or a driving condition attribute. In some embodiments, the processing circuitry receives the additional attribute, at least in part, from server 578. In some embodiments, the processing circuit receives, at least in part, from at least one of a Global Navigation Satellite System ("GNSS") sensor 558 (e.g., a global positioning system sensor), a RADAR sensor 560, an ultrasonic sensor 562, a LIDAR sensor 564, an inertial measurement unit ("IMU") sensor 566 (e.g., an accelerometer, a gyroscope, a magnetic compass, a magnetometer, etc.), a microphone 596, a stereo camera 568, a wide view camera 570 (e.g., a fisheye camera), an infrared camera 572, a surround camera 574 (e.g., a 360 degree camera), a long-range camera (not shown in FIG. 5A ), a mid-range camera (not shown in FIG. 5A ), a speed sensor 544 (e.g., for measuring the speed of the vehicle 500), a vibration sensor 542, a steering sensor 540, a brake sensor (e.g., as part of a brake sensor system 546), and / or other sensor types. In some embodiments, the processing circuitry receives data indicative of a representation of at least a portion of a person from at least one or more of the sensors of the vehicle 500 listed above. The processing circuitry determines one or more attributes of the person based on the data indicative of a representation of at least a portion of an object (e.g., clothing of the person). In some embodiments, the processing circuitry makes this determination by implementing a hardware accelerator that uses the neural network 592. For example, the hardware accelerator may be one or more modules from a hardware acceleration cluster. The modules from the hardware acceleration cluster include one or more DLAs, one or more PVAs, and / or one or more TPUs.In some embodiments, the hardware acceleration cluster is part of server 578. In this embodiment, data is exchanged between the processing circuitry of the vehicle and the server. In other embodiments, the processing circuitry includes the processing circuitry of the server. In other embodiments, the hardware cluster is part of SoC 504.

[0168] At 706, the processing circuitry calculates the risk level based on the data indicative of the trajectory and the one or more attributes. In some embodiments, the processing circuitry implements a machine learning model that implements one or more of the operations using the neural network 592. In some embodiments, the machine learning model performs the training of the neural network and the interference modeling using the inference and / or training logic 515. The training of the neural network uses a training dataset 602 of various object trajectories in various environments. The training framework 604 uses the training dataset 602 to facilitate learning of the neural network. In some embodiments, the processing circuitry implements a hardware accelerator to calculate the risk level and / or perform one or more of the operations using the neural network 592. For example, the hardware accelerator is a module from a hardware acceleration cluster. The modules from the hardware acceleration cluster include one or more DLAs, one or more PVAs, and / or one or more TPUs. In some embodiments, the hardware acceleration cluster is part of the server 578. In this embodiment, data is exchanged between the vehicle's processing circuitry and the server. In another embodiment, the processing circuitry includes the server's processing circuitry. In another embodiment, the hardware cluster is part of the SoC 504.

[0169] At 708, the processing circuitry causes an action to be performed in response to the calculated risk level to effect a reduction in the risk level. In some embodiments, the processing circuitry implements a machine learning model that implements one or more of the actions using the neural network 592 to cause the action to be performed. In some embodiments, the machine learning model performs neural network training and interference modeling using the inference and / or training logic 515. The training of the neural network uses a training dataset 602 of different actions based on different environments of the determined risk level. The training framework 604 facilitates learning of the neural network using the training dataset 602. In some embodiments, the processing circuitry provides instructions to the vehicle's sensors. In particular, the processing circuitry provides instructions to at least one of a global navigation satellite system ("GNSS") sensor 558 (e.g., a global positioning system sensor), a RADAR sensor 560, an ultrasonic sensor 562, a LIDAR sensor 564, an inertial measurement unit ("IMU") sensor 566 (e.g., an accelerometer, a gyroscope, a magnetic compass, a magnetometer, etc.), a microphone 596, a stereo camera 568, a wide view camera 570 (e.g., a fisheye camera), an infrared camera 572, a surround camera 574 (e.g., a 360 degree camera), a long-range camera (not shown in FIG. 5A ), a mid-range camera (not shown in FIG. 5A ), a speed sensor 544 (e.g., for measuring the speed of the vehicle 500), a vibration sensor 542, a steering sensor 540, a brake sensor (e.g., as part of a brake sensor system 546), and / or other sensor types. In some embodiments, the processing circuitry provides instructions to environmental hardware (e.g., networked traffic light poles) via network 590. In some embodiments, the processing circuitry provides instructions to a speaker sensor in a vehicle to trigger the emission of an audio signal directed toward an object. In some embodiments, the processing circuitry generates a beamformed audio signal by determining the phase and amplitude of the audio signal.In some embodiments, the processing circuitry determines a number of distinct frequencies for different objects based on the object frequency data from the data store 516.

[0170] 8 is an example flow diagram of a process 800 for determining a trajectory of an object external to a vehicle, according to some embodiments of the disclosure. At 802, a processing circuit receives one or more images of an object received from a camera sensor (e.g., stereo camera 568, infrared camera 572, etc.).

[0171] At 804, the processing circuitry determines a directionality of the object based on one or more images received from the camera sensor. The processing circuitry determines a difference in time between the one or more images and a difference in relative distance of the object. At 806, the processing circuitry determines a velocity of the object based on one or more images received from the camera sensor (e.g., using the difference in time and relative distance).

[0172] At 808, the processing circuitry determines a trajectory of an object external to the vehicle based on the object's velocity and directionality. The processing circuitry uses one or more mathematical models to determine whether the object is on a collision course with the vehicle.

[0173] 9 is an example flow diagram of a process 900 for determining attributes of an object external to a vehicle, according to some embodiments of the disclosure. At 902, a processing circuit receives an image of the object received from a camera sensor (e.g., stereo camera 568, infrared camera 572, etc.).

[0174] At 904, the processing circuitry determines attributes of the object, which is a person, based on at least one of the following: the person's head pose, the person's body posture, the person's clothing, gestures made by the person, or environmental attributes. The processing circuitry determines the attributes using a machine learning model. In some embodiments, the machine learning model uses inference and / or training logic 515 to perform neural network training and interference modeling. The training of the neural network uses a training dataset 602 of a myriad of object types and different orientations and / or attributes (e.g., people of all ages, body types, and in different poses and different clothing). The training framework 604 facilitates learning of the neural network using the training dataset 602.

[0175] At 906, the processing circuitry determines a classification of the person's attributes based on the machine learning model. The determined attributes are provided to the machine learning model, which provides a classification based on these attributes.

[0176] 10 is an example flow diagram of a process for triggering emission of a beamformed audio signal according to some embodiments of the present disclosure. At 1002, a processing circuit determines a real-time trajectory from a vehicle to an object. The processing circuit determines the real-time trajectory from the vehicle to the object based on one or more images of the object received from a camera sensor (e.g., stereo camera 568, infrared camera 572, etc.).

[0177] At 1004, the processing circuit determines a magnitude of the audio signal based on the calculated danger level. In some embodiments, the processing circuit determines the attributes using a machine learning model. In some embodiments, the processing circuit retrieves a mapping table from the data store 516, the mapping table having corresponding magnitudes for the danger level calculation. In some embodiments, the processing circuit retrieves the additional attributes from environmental information (e.g., environmental signs) received by the processing circuit regarding the location of the vehicle and / or object. In some embodiments, the processing circuit retrieves the additional attributes from auxiliary information (e.g., location information, weather information, and / or driving conditions) received by the processing circuit regarding the location of the vehicle and / or object. The processing circuitry receives additional attributes from the network 590 and / or from at least one of a global navigation satellite system ("GNSS") sensor 558 (e.g., a global positioning system sensor), a RADAR sensor 560, an ultrasonic sensor 562, a LIDAR sensor 564, an inertial measurement unit ("IMU") sensor 566 (e.g., an accelerometer, a gyroscope, a magnetic compass, a magnetometer, etc.), a microphone 596, a stereo camera 568, a wide view camera 570 (e.g., a fisheye camera), an infrared camera 572, a surround camera 574 (e.g., a 360 degree camera), a long-range camera (not shown in FIG. 5A ), a mid-range camera (not shown in FIG. 5A ), a speed sensor 544 (e.g., for measuring the speed of the vehicle 500), a vibration sensor 542, a steering sensor 540, a brake sensor (e.g., as part of a brake sensor system 546), and / or other sensor types.

[0178] At 1006, the processing circuitry sends instructions to a speaker sensor to cause emission of a beamformed audio signal based on the real-time trajectory and the magnitude of the audio signal. In some embodiments, the processing circuitry sends instructions to the environmental hardware to transmit a beamformed audio signal based on the real-time trajectory and the magnitude of the audio signal. In some embodiments, the processing circuitry sends instructions to a light source sensor (e.g., a headlight or a dedicated light source) of the vehicle to emit a light signal at the object. In some embodiments, the processing circuitry accesses the data store 516 to obtain a language based on the audio emission to be emitted at the object.

[0179] It is contemplated that any suitable steps or suitable descriptions of Figures 7-10 may be used with other suitable embodiments of the present disclosure. In addition, any suitable steps and descriptions described in connection with Figures 7-10 may be implemented in an alternative order or in parallel to further the objectives of the present disclosure. For example, any suitable steps may be performed in any order or in parallel or substantially simultaneously to reduce lag or increase the speed of the system or method. Any suitable steps may also be omitted or removed from the process. Additionally, it is noted that any suitable device or apparatus discussed in connection with Figures 5A-6 may be used to perform one or more of the steps in Figures 7-10.

[0180] The above process is intended to be illustrative and not limiting. Those skilled in the art will understand that the steps of the processes discussed herein may be omitted, modified, combined, and / or rearranged, and any additional steps may be performed without departing from the scope of the present invention. More generally, the above disclosure is intended to be illustrative and not limiting. Only the claims that follow are intended to set boundaries as to what the invention includes. Furthermore, it should be noted that features and limitations described in any one embodiment may be applied to any other embodiment described herein, and that flow charts or illustrations related to one embodiment may be combined with any other embodiment in an appropriate manner, performed in a different order, or performed in parallel. In addition, the systems and methods described herein may be performed in real time. It should also be noted that the above systems and / or methods may be applied to or used in accordance with other systems and / or methods.

Claims

1. A method for determining a first feature vector corresponding to a pedestrian's posture using one or more first machine learning models and based at least on a first portion of the machine-generated sensor data; determining a second feature vector responsive to a head pose of the pedestrian using one or more second machine learning models and based at least on a second portion of the sensor data; determining one or more actions associated with the pedestrian based at least on the first feature vector and the second feature vector; determining a likelihood of a collision between the pedestrian and the machine based at least on the one or more actions; taking one or more control actions for the machine based at least in part on the likelihood of a collision; A computer-implemented method comprising:

2. The method of claim 1, wherein the likelihood of collision is based at least on a danger level, the danger level comprising one of low risk, medium risk, or high risk, as determined at least based on a reference table indicating the danger levels corresponding to the one or more actions.

3. The method of claim 1, further comprising determining a third feature vector corresponding to the pedestrian's object interactions using one or more third machine learning models and based at least on a third portion of the sensor data.

4. The method of claim 1, wherein the one or more control actions include emitting a directional audio signal from the machine that is directed toward the pedestrian's location.

5. The method of claim 4, wherein the directional audio signal comprises at least one audio signal beamformed toward the location of the pedestrian.

6. The method of claim 1, wherein the step of determining one or more actions comprises a step of determining the one or more actions using one or more third machine learning models and based at least on the first feature vector and the second feature vector. determining at least one of yaw, pitch, or roll corresponding to the head of the pedestrian; and estimating whether the pedestrian is aware of the machine based at least on at least one of the yaw, the pitch, or the roll; The method of claim 1 , wherein the determining one or more actions is at least further based on the estimating step.

8. The method of claim 1, wherein the one or more control actions comprise emitting a directional light signal from the machine directed toward the pedestrian's location.

9. The method according to claim 8, further comprising the step of determining an intent of the pedestrian to cross a path of the machine; The method of claim 1 , wherein determining the one or more actions is based at least further on the intent.

10. The method further comprising the step of determining a classification of the pedestrian, The method of claim 1 , wherein determining the one or more actions is based at least further on the classification of a pedestrian.

11. The method of claim 1, wherein the step of determining the likelihood of a collision is based at least further on the vertical distance of the machine to the pedestrian.

12. The one or more first machine learning models further comprise at least one of a first long short-term memory (LSTM) recurrent neural network or a convolutional neural network (CNN); 2. The method of claim 1, wherein the one or more second machine learning models further comprise at least one of a second LSTM recurrent neural network or a second CNN.

13. The method of claim 12, wherein the first portion of the sensor data represents a first portion of an image depicting the pedestrian; The method of claim 1 , wherein the second portion of the sensor data represents a second portion of the image depicting the head of the pedestrian.

14. The method of claim 1, further comprising: determining first data representing a first bounding box associated with the first portion of the sensor data, wherein determining the first feature vector is at least further based on the first data; determining second data representative of a second bounding box associated with the second portion of the sensor data, wherein determining the second feature vector is at least further based on the second data; The method of claim 1 further comprising: generating a first feature vector representing a body posture associated with the person using one or more first machine learning models and based at least on a first portion of the machine-generated sensor data; generating a second feature vector representing a head pose associated with the person using one or more second machine learning models and based at least on a second portion of the sensor data; determining a risk level associated with the person based at least on the first feature vector and the second feature vector; and issuing an alert directed to the person based at least on the danger level. A system comprising one or more processing units.

16. The system described in claim 15, wherein the system is included in an autonomous or semi-autonomous machine.

17. The system of claim 15, wherein the risk level is further determined based at least on one or more attributes of an environment associated with the machine.

18. The system of claim 17, wherein the one or more attributes of the environment include at least one of location attributes, weather attributes, or driving situation attributes.

19. The system of claim 15, wherein the alarm comprises a directional audio signal directed to the person's location.

20. Determining a first feature vector responsive to a pedestrian's posture using one or more first machine learning models and based at least on a first portion of sensor data generated using one or more sensors of the machine; determining a second feature vector responsive to a head pose of the pedestrian using one or more second machine learning models and based at least on a second portion of the sensor data; determining a level of danger associated with the pedestrian based at least on the first feature vector and the second feature vector; and taking one or more control actions for the machine based at least on the level of risk. A processor comprising one or more circuits.

Images