Method for training / tuning driving scenario sampling of machine learning model of vehicle

Abstract

A method for training / tuning driving scenario sampling of a machine learning model of a vehicle is provided. Embodiments for sampling a driving scenario to train a machine learning model are disclosed. In one embodiment, a method includes assigning, using at least one processor, a set of initial physical states to a set of objects in a map for a set of simulated driving scenarios, where the set of initial physical states is assigned according to one or more outputs of a random number generator; generating, using the at least one processor, the set of simulated driving scenarios in the map using initial physical states of objects in the set of objects; selecting, using the at least one processor, a sample of the simulated driving scenario; training, using the at least one processor, a machine learning model with the selected samples; and operating the vehicle in the environment using the trained machine learning model using the control circuit.

Description

[0001] This application is a divisional application of the application with application date of October 19, 2020, application number 2020111171790, and invention name “Driving scenario sampling for training / tuning machine learning models for vehicles”. Technical Field

[0002] The instructions that follow generally involve generating training and / or tuning data for machine learning models. Background Art

[0003] Autonomous vehicles (AVs) typically include machine learning models that require training and tuning using training data. The accuracy of a machine learning model is highly dependent on the quality of the training and / or tuning data. For example, if a machine learning model is to be used to predict the behavior of an AV in an operating environment with many static and dynamic objects (such as other vehicles), it is important that the training and / or tuning data include a large dataset of different driving scenarios that qualitatively captures the normal behavior of the objects in order to ensure the accuracy of the machine learning model. Summary of the Invention

[0004] Techniques are provided for sampling driving scenarios to provide training and / or tuning data for machine learning models.

[0005] In an embodiment, a method includes: using at least one processor to assign a set of initial physical states to a set of objects (e.g., virtual vehicles, pedestrians, cyclists) in a map for a set of simulated driving scenarios (e.g., crossing an intersection, lane change), wherein the set of initial physical states are assigned based on one or more outputs of a random number generator; using the at least one processor to generate the set of simulated driving scenarios in the map using the initial physical states of the objects; using the at least one processor to select samples of the simulated driving scenarios; using the at least one processor to train a machine learning model (e.g., a deep neural network) using the selected samples; and using control circuitry to operate a vehicle in an environment using the trained machine learning model.

[0006] In an embodiment, at least one object in the group of objects is a virtual vehicle, and the method further comprises: assigning a psychological state of a virtual driver of the virtual vehicle (e.g., a tendency to accelerate quickly from a stopped position, a tendency to follow closely); and simulating a driving scenario using the map, the initial physical state of each object in the group of objects, and the psychological state of the virtual driver of the virtual vehicle.

[0007] In an embodiment, the virtual driver's mental state includes the driver's acceleration preference (eg, a preference for rapid acceleration from a stopped position).

[0008] In an embodiment, the virtual driver's mental state includes a preference to maintain a gap between another virtual vehicle and other objects (eg, a preference to follow closely).

[0009] In an embodiment, the psychological state of the virtual driver includes a preference for a particular route.

[0010] In an embodiment, the virtual driver's mental state includes the driver's goal (eg, reaching a destination quickly).

[0011] In an embodiment, the psychological state of the virtual driver includes a courtesy factor (eg, a weighting factor) that is used to determine the extent to which the driver is willing to inconvenience other virtual drivers in the driving scenario.

[0012] In an embodiment, the method further includes: determining one or more failed driving scenarios (e.g., a collision between two or more objects) in a set of driving scenarios; and excluding the one or more failed driving scenarios from training the machine learning model (e.g., the one or more failed driving scenarios are not included in the training data).

[0013] In an embodiment, a failed driving scenario includes a driving scenario in which a collision is predicted between two or more objects.

[0014] In an embodiment, failing driving scenarios include driving scenarios where the acceleration or deceleration values of one or more objects are above or below one or more specified thresholds (eg, accelerations that would cause a vehicle to lose control).

[0015] In an embodiment, the initial physical state of an object in the group of objects includes an initial position and an initial acceleration, and the initial position and the initial acceleration are assigned according to different random numbers output by the random number generator.

[0016] In an embodiment, generating the simulated driving scenarios further comprises: predicting each driving scenario forward in time for a specified period of time before selecting the sample (eg, to allow various objects to traverse their respective trajectories without failure).

[0017] In an embodiment, the driving scenario includes one or more traffic lights or traffic signs that the subject obeys.

[0018] In an embodiment, the machine learning model is a deep learning neural network for motion prediction.

[0019] In an embodiment, the one or more objects include at least one pedestrian.

[0020] In an embodiment, each sampled driving scenario includes multiple timestamps and associated positions, velocities, or tags for each object.

[0021] In an embodiment, the method further comprises: embedding the sampled scenario into a pseudo image (eg, a BEV image); and training the machine learning model (eg, training an image semantic neural network) using the pseudo image.

[0022] In an embodiment, the method further comprises: selecting a unique seed from a statistical distribution (eg, a normal distribution); and initializing the random number generator using the seed.

[0023] In an embodiment, the statistical distribution is a joint distribution over driving scenarios.

[0024] In an embodiment, the driving scenario is generated based on at least one of a specified density of objects (eg, urban vs. rural), a specified day, and a specified time of day (eg, simulating rush hour traffic).

[0025] One or more of the disclosed embodiments provide one or more of the following advantages. The disclosed systems and methods allow a user to select, randomly initialize, simulate, and sample the physical and psychological states of a subject for a plurality of different driving scenarios via a user interface. The sampled driving scenarios can be used alone as training and / or tuning data for a machine learning model or to augment actual driving log data. Simulated driving scenarios can provide more comprehensive training and / or tuning data that can then be actually collected by a vehicle in the real world. Additional improvements to the training and / or tuning data include the ability to assign psychological states to subjects to better model real-world driving scenarios, where the driver's preferences can significantly influence the driving scenario.

[0026] These and other aspects, features and implementations may be expressed as methods, devices, systems, components, program products, methods or steps for performing functions, and other means. These and other aspects, features and implementations will become apparent from the following description, including the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 An example of an autonomous vehicle (AV) having autonomous capabilities is shown in accordance with one or more embodiments.

[0028] Figure 2 An example "cloud" computing environment is illustrated in accordance with one or more embodiments.

[0029] Figure 3 A computer system according to one or more embodiments is illustrated.

[0030] Figure 4An example architecture of an AV is shown in accordance with one or more embodiments.

[0031] Figure 5 An example system for sampling driving scenarios is shown in accordance with one or more embodiments.

[0032] Figure 6 An example system for training and / or tuning a machine learning model using sample driving scenarios is shown in accordance with one or more embodiments.

[0033] Figure 7 is a flow chart of an example process for sampling driving scenarios in accordance with one or more embodiments. DETAILED DESCRIPTION

[0034] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent that the present invention may be practiced without these specific details. In other instances, well-known configurations and devices are shown in block diagram form to avoid unnecessarily obscuring the present invention.

[0035] In the accompanying drawings, for ease of description, the specific arrangement or order of schematic elements, such as those representing devices, modules, instruction blocks, and data elements, is shown. However, it will be understood by those skilled in the art that the specific ordering or arrangement of schematic elements in the accompanying drawings does not necessarily require a specific processing order or sequence, or separation of processing processes. Furthermore, the inclusion of schematic elements in the accompanying drawings does not mean that such elements are required in all embodiments, nor does it mean that the features represented by such elements cannot be included in some embodiments or cannot be combined with other elements in some embodiments.

[0036] In addition, in the accompanying drawings, connecting elements, such as solid or dotted lines or arrows, are used to illustrate the connection, relationship or association between two or more other schematic elements, and the absence of any such connecting elements does not mean that there can be no connection, relationship or association. In other words, the connection, relationship or association between some elements are not shown in the accompanying drawings so as not to obscure the present invention. In addition, for ease of explanation, a single connecting element is used to represent multiple connections, relationships or associations between elements. For example, if a connecting element represents the communication of a signal, data or instruction, it will be understood by those skilled in the art that the element represents one or more signal paths (e.g., buses) that may be needed to affect the communication.

[0037] Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various embodiments described. However, it will be apparent to one of ordinary skill in the art that the various embodiments described may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0038] Several of the features described below can be used independently of each other or in combination with any other features. However, any individual feature may not address all of the above problems, or may address only one of the above problems. Some of the problems discussed above may not be fully addressed by any one of the features described herein. Although headings are provided, information related to a heading but not found in that heading may be found elsewhere in this description. This document describes embodiments according to the following summary:

[0039] 1. General Overview

[0040] 2. System Overview

[0041] 3. Autonomous Vehicle Architecture

[0042] 4. Sampling driving scenarios

[0043] General Overview

[0044] A technique for sampling driving scenarios for use in training and / or tuning machine learning models is provided. In one embodiment, a scenario initializer randomly selects one or more parameters to be initialized related to the physical and / or psychological state of one or more objects in a simulated driving scenario. The scenario initializer initializes a driving scenario simulator using the one or more randomly selected parameters. The driving scenario simulator generates an object track for each of the one or more objects in the driving scenario. A scenario sampling module samples the one or more object tracks and stores the samples in a database. These samples are then used to train and / or tune one or more machine learning models.

[0045] System Overview

[0046] Figure 1 An example of an autonomous vehicle 100 having autonomous capabilities is shown.

[0047] As used herein, the term "autonomous capability" refers to a function, feature, or facility that enables a vehicle to operate partially or fully without real-time human intervention, including but not limited to fully autonomous vehicles, highly autonomous vehicles, partially autonomous vehicles, and conditionally autonomous vehicles.

[0048] As used herein, an autonomous vehicle (AV) is a vehicle with autonomous capabilities.

[0049] As used herein, "vehicle" includes any mode of transport for goods or people, such as a car, bus, train, airplane, drone, truck, boat, ship, submersible, or spacecraft. An unmanned car is an example of a vehicle.

[0050] As used herein, a "trajectory" refers to a path or route that an AV follows from a first spatiotemporal location to a second spatiotemporal location. In embodiments, the first spatiotemporal location is referred to as an initial location or starting location, and the second spatiotemporal location is referred to as a destination, final location, target, target position, or target location. In some examples, a trajectory is comprised of one or more road segments (e.g., sections of a road), and each road segment is comprised of one or more blocks (e.g., a lane or portion of an intersection). In embodiments, a spatiotemporal location corresponds to a real-world location. For example, a spatiotemporal location is a pickup or drop-off location for picking up or dropping off people or cargo.

[0051] As used herein, "sensor(s)" includes one or more hardware components for detecting information related to the sensor's surroundings. Some hardware components may include sensing components (e.g., image sensors, biometric sensors), transmitting and / or receiving components (e.g., laser or radio frequency wave transmitters and receivers), electronic components (e.g., analog-to-digital converters), data storage devices (e.g., RAM and / or non-volatile memory), software or firmware components and data processing components (e.g., application specific integrated circuits), microprocessors, and / or microcontrollers.

[0052] As used herein, a “scene description” is a data structure (e.g., a list) or data stream that includes one or more classified or labeled objects detected by one or more sensors on an AV vehicle, or one or more classified or labeled objects provided by a source external to the AV.

[0053] As used herein, a "road" is a physical area that can be traversed by a vehicle and can correspond to a named thoroughfare (e.g., a city street, an interstate highway, etc.) or can correspond to an unnamed thoroughfare (e.g., a driveway within a house or office building, a section of a parking lot, a section of a vacant parking lot, a dirt road in a rural area, etc.). Because some vehicles (e.g., four-wheel drive pickup trucks, off-road vehicles (SUVs), etc.) can traverse a variety of physical areas that are not particularly suitable for vehicle travel, a "road" can be any physical area that has not been formally defined as a thoroughfare by a municipality or other governmental or administrative agency.

[0054] As used herein, a "lane" is a portion of a road that can be traversed by vehicles and may correspond to most or all of the space between lane markings, or only a portion of the space between lane markings (e.g., less than 50%). For example, a road with lane markings that are far apart may accommodate two or more vehicles, such that one vehicle can pass another without crossing the lane markings and thus may be interpreted as having a lane narrower than the space between the lane markings, or as having two lanes between the lanes. Lanes may also be interpreted in the absence of lane markings. For example, lanes may be defined based on physical features of the environment (e.g., rocks in a rural area and trees along an avenue).

[0055] “One or more” includes a function performed by one element, a function performed by multiple elements, such as in a distributed manner, several functions performed by one element, several functions performed by several elements, or any combination of the foregoing.

[0056] It will also be understood that although in some cases the terms "first," "second," etc. are used to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first contact may be referred to as a second contact, and similarly, a second contact may be referred to as a first contact without departing from the scope of the various described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.

[0057] The terms used in the description of the various embodiments described herein are for describing specific embodiments only and are not intended to be limiting. As used in the description of the various embodiments described and in the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and includes any and all possible combinations of one or more of the associated list items. It will also be understood that the terms "comprises," "comprising," "having," and / or "having" as used in this description specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0058] As used herein, the term "if" may alternatively be understood as meaning in that case, at that time, or in response to being detected, or in response to being determined, as the context requires. Similarly, the phrase "if it has been determined" or "if [the condition or event] has been detected" may be understood as meaning "upon determination" or "in response to being determined" or "upon detection of [the condition or event]" or "in response to detecting [the condition or event]," as the context requires.

[0059] As used herein, an AV system refers to an AV and the hardware, software, stored data, and data generated in real time to support AV operations. In an embodiment, the AV system is incorporated into the AV. In an embodiment, the AV system is distributed across multiple locations. For example, some software of the AV system is combined in a similar manner to the following: Figure 3 The described cloud computing environment 300 is implemented in a cloud computing environment.

[0060] In general, this document describes technologies applicable to any vehicle with one or more autonomous capabilities, including fully autonomous vehicles, highly autonomous vehicles, and conditionally autonomous vehicles, such as so-called Level 5, Level 4, and Level 3 vehicles (see SAE International Standard J3016: Classification and Definitions of Terms Relating to Automated Driving Systems for Road-Based Motor Vehicles, which is incorporated herein by reference in its entirety for more details on vehicle autonomy levels). The technologies described in this document are also applicable to partially autonomous vehicles and driver-assisted vehicles, such as so-called Level 2 and Level 1 vehicles (see SAE International Standard J3016: Classification and Definitions of Terms Relating to Automated Driving Systems for Road-Based Motor Vehicles). In embodiments, one or more Level 1, Level 2, Level 3, Level 4, and Level 5 vehicle systems may automatically perform certain vehicle operations (e.g., steering, braking, and using maps) under certain operating conditions based on processing of sensor inputs. The technologies described in this document can benefit vehicles at all levels, from fully autonomous vehicles to human-operated vehicles.

[0061] refer to Figure 1 , the AV system 120 causes the AV 100 to operate along a trajectory 198 through an environment 190 to a destination 199 (sometimes referred to as a final location) while avoiding objects (e.g., natural obstacles 191, vehicles 193, pedestrians 192, cyclists, and other obstacles) and obeying the rules of the road (e.g., operating rules or driving preferences).

[0062] In an embodiment, the AV system 120 includes means 101 for receiving and operating commands from a computer processor 146. In an embodiment, the computer processor 146 is associated with the following reference Figure 3 The processor 304 is similarly described. Examples of devices 101 include steering controls 102, brakes 103, gears, an accelerator pedal or other acceleration control mechanism, windshield wipers, side door locks, window controls, and turn indicators.

[0063] In an embodiment, the AV system 120 includes sensors 121 for measuring or inferring attributes of the state or condition of the AV 100, such as the AV's position, linear and angular velocity and acceleration, and heading (e.g., the direction of the front end of the AV 100). Examples of sensors 121 are a Global Navigation Satellite System (GNSS) receiver, an Inertial Measurement Unit (IMU) for measuring vehicle linear acceleration and angular rate, wheel rate sensors for measuring or estimating wheel slip, wheel brake pressure or brake torque sensors, engine torque or wheel torque sensors, and steering angle and angular rate sensors.

[0064] In an embodiment, the sensors 121 also include sensors for sensing or measuring properties of the AV's environment, such as a monocular or stereo camera 122 in the visible, infrared, or thermal (or both) spectrum, a LiDAR 123, a RADAR, an ultrasonic sensor, a time-of-flight (TOF) depth sensor, a velocity sensor, a temperature sensor, a humidity sensor, and a precipitation sensor.

[0065] In an embodiment, the AV system 120 includes a data storage unit 142 and a memory 144 for storing machine instructions related to the computer processor 146 or data collected by the sensor 121. In an embodiment, the data storage unit 142 is combined with the following Figure 3 ROM 308 or storage device 310 described above. In an embodiment, memory 144 is similar to main memory 306 described below. In an embodiment, data storage unit 142 and memory 144 store historical, real-time, and / or predictive information about environment 190. In an embodiment, the stored information includes maps, driving performance, traffic congestion updates, or weather conditions. In an embodiment, data related to environment 190 is transmitted to AV 100 via a communication channel from remote database 134.

[0066] In an embodiment, the AV system 120 includes communication devices 140 for transmitting measured or inferred attributes of the state and condition of other vehicles (such as position, linear and angular velocity, linear and angular acceleration, and linear and angular heading) to the AV 100. These devices include vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication devices, as well as devices for wireless communication via point-to-point or ad hoc networks, or both. In an embodiment, the communication devices 140 communicate across the electromagnetic spectrum (including radio and optical communications) or other media (e.g., air and acoustic media). The combination of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications (and in some embodiments, one or more other types of communications) is sometimes referred to as vehicle-to-everything (V2X) communication. V2X communications typically conform to one or more communication standards for communication with and between autonomous vehicles.

[0067] In an embodiment, the communication device 140 includes a communication interface. For example, a wired, wireless, WiMAX, Wi-Fi, Bluetooth, satellite, cellular, optical, near-field, infrared, or radio interface. The communication interface transmits data from the remote database 134 to the AV system 120. In an embodiment, the remote database 134 is embedded in the cloud computing environment 200, such as Figure 2The communication interface 140 transmits data collected from the sensors 121 or other data related to the operation of the AV 100 to the remote database 134. In an embodiment, the communication interface 140 transmits information related to remote operation to the AV 100. In some embodiments, the AV 100 communicates with other remote (e.g., "cloud") servers 136.

[0068] In an embodiment, the remote database 134 also stores and transmits digital data (e.g., data storing roads and street locations, etc.) This data is stored in the memory 144 on the AV 100 or transmitted from the remote database 134 to the AV 100 via a communication channel.

[0069] In an embodiment, the remote database 134 stores and transmits historical information regarding driving attributes (e.g., speed and acceleration rate profiles) of vehicles that have previously traveled along the trajectory 198 at similar times of day. In one implementation, such data may be stored in the memory 144 on the AV 100 or transmitted from the remote database 134 to the AV 100 via a communication channel.

[0070] The computing device 146 located on the AV 100 algorithmically generates control actions based on real-time sensor data and a priori information, enabling the AV system 120 to perform its autonomous driving capabilities.

[0071] In an embodiment, the AV system 120 includes a computer peripheral device 132 connected to a computing device 146 for providing information and reminders to a user of the AV 100 (e.g., an occupant or a remote user) and receiving input from the user. In an embodiment, the peripheral device 132 is similar to the one described below with reference to Figure 3 The display 312, input device 314 and cursor control 316 are discussed. The connection can be wireless or wired. Any two or more interface devices can be integrated into a single device.

[0072] Sample cloud computing environment

[0073] Figure 2 Illustrate an example "cloud" computing environment. Cloud computing is a service delivery model that provides convenient, on-demand access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) over a network. In a typical cloud computing system, one or more large cloud data centers house the machines used to deliver the services provided by the cloud. Now refer to Figure 2, cloud computing environment 200 includes cloud data centers 204a, 204b, and 204c interconnected by a cloud 202. Data centers 204a, 204b, and 204c provide cloud computing services to computer systems 206a, 206b, 206c, 206d, 206e, and 206f connected to cloud 202.

[0074] The cloud computing environment 200 includes one or more cloud data centers. Typically, a cloud data center (e.g. Figure 2 The cloud data center 204a shown in FIG refers to a cloud (eg Figure 2 The physical arrangement of servers in a cloud 202 (or a specific portion of a cloud) as shown in FIG. For example, servers are physically arranged into rooms, groups, rows, and racks in a cloud data center. A cloud data center has one or more zones, which include one or more server rooms. Each room has one or more rows of servers, and each row includes one or more racks. Each rack includes one or more individual server nodes. In some implementations, servers in zones, rooms, racks, and / or rows are divided into groups based on the physical infrastructure requirements of the data center facility, including power, energy, heat, heat sources, and / or other requirements. In an embodiment, the server nodes are similar to Figure 3 The data center 204a has many computing systems distributed across multiple racks.

[0075] Cloud 202 includes cloud data centers 204a, 204b, and 204c, as well as networks and network resources (e.g., network devices, nodes, routers, switches, and network cables) used to connect cloud data centers 204a, 204b, and 204c and facilitate access to cloud computing services by computing systems 206a-f. In embodiments, the network represents any combination of one or more local networks, wide area networks, or internetworks connected by wired or wireless links deployed using terrestrial or satellite connections. Data exchanged over the network is transmitted using a variety of network layer protocols, such as Internet Protocol (IP), Multiprotocol Label Switching (MPLS), Asynchronous Transfer Mode (ATM), Frame Relay, etc. Furthermore, in embodiments where the network represents a combination of multiple subnetworks, different network layer protocols are used on each underlying subnetwork. In some embodiments, the network represents one or more interconnected internetworks (e.g., the public Internet, etc.).

[0076] Computing systems 206a-f, or cloud computing service consumers, are connected to the cloud 202 via network links and network adapters. In embodiments, computing systems 206a-f are implemented as various computing devices, such as servers, desktops, laptops, tablets, smartphones, Internet of Things (IoT) devices, autonomous vehicles (including cars, drones, space shuttles, trains, buses, etc.), and consumer electronics. In embodiments, computing systems 206a-f are implemented in other systems or as part of other systems.

[0077] Computer system

[0078] Figure 3 Illustrated is a computer system 300. In implementation, the computer system 300 is a special-purpose computing device. The special-purpose computing device is hard-wired to perform these techniques, or includes a digital electronic device such as one or more application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs) that is permanently programmed to perform the above-mentioned techniques, or may include one or more general-purpose hardware processors that are programmed to perform these techniques according to program instructions in firmware, memory, other memory, or a combination thereof. Such a special-purpose computing device may also combine customized hard-wired logic, ASICs, or FPGAs with customized programming to perform these techniques. In various embodiments, the special-purpose computing device is a desktop computer system, a portable computer system, a handheld device, a network device, or any other device that includes hard-wired and / or program logic to implement these techniques.

[0079] In an embodiment, computer system 300 includes a bus 302 or other communication mechanism for communicating information, and a hardware processor 304 coupled to bus 302 for processing information. Hardware processor 304 is, for example, a general-purpose microprocessor. Computer system 300 also includes a main memory 306, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 302 to store information and instructions for execution by processor 304. In one implementation, main memory 306 is used to store temporary variables or other intermediate information during the execution of instructions to be executed by processor 304. When these instructions are stored in a non-transitory storage medium accessible to processor 304, computer system 300 becomes a special-purpose machine customized to perform the operations specified in the instructions.

[0080] In an embodiment, computer system 300 also includes a read-only memory (ROM) 308 or other static storage device connected to bus 302 for storing static information and instructions for processor 304. A storage device 310, such as a magnetic disk, optical disk, solid-state drive, or three-dimensional cross-point memory, is provided and connected to bus 302 for storing information and instructions.

[0081] In an embodiment, the computer system 300 is coupled via a bus 302 to a display 312, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a plasma display, a light emitting diode (LED) display, or an organic light emitting diode (OLED) display, for displaying information to a computer user. An input device 314, including alphanumeric and other keys, is coupled to the bus 302 for communicating information and command selections to the processor 304. Another type of user input device is a cursor controller 316, such as a mouse, a trackball, a touch-sensitive display, or cursor direction keys, for communicating direction information and command selections to the processor 304 and for controlling movement of a cursor on the display 312. Such input devices typically have two degrees of freedom along two axes, a first axis (e.g., an x-axis) and a second axis (e.g., a y-axis), which allow the device to specify a position on a plane.

[0082] According to one embodiment, the techniques herein are performed by computer system 300 in response to processor 304 executing one or more sequences of one or more instructions contained in main memory 306. These instructions are read into main memory 306 from another storage medium, such as storage device 310. Execution of the sequences of instructions contained in main memory 306 causes processor 304 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry is used in place of or in combination with software instructions.

[0083] As used herein, the term "storage medium" refers to any non-transitory medium that stores data and / or instructions that cause a machine to operate in a specific manner. Such storage media include non-volatile media and / or volatile media. Non-volatile media include, for example, optical disks, magnetic disks, solid-state drives, or three-dimensional cross-point memories, such as storage device 310. Volatile media include dynamic memories, such as main memory 306. Common forms of storage media include, for example, floppy disks, disks, hard disks, solid-state drives, magnetic tape or any other magnetic data storage medium, CD-ROMs, any other optical data storage medium, any physical medium with a hole pattern, RAM, PROM and EPROM, FLASH-EPROM, NV-RAM, or any other memory chip or storage cartridge.

[0084] Storage media are distinct from transmission media, but can be used in conjunction with them. Transmission media participate in the transmission of information between storage media. Examples of transmission media include coaxial cables, copper wires, and optical fibers, including the wires that comprise bus 302. Transmission media can also take the form of acoustic or optical waves, such as those generated during radio wave and infrared data communications.

[0085] In one embodiment, various forms of media are involved in carrying one or more sequences of instructions to processor 304 for execution. For example, the instructions are initially executed on a disk or solid-state drive of a remote computer. The remote computer loads the instructions into its dynamic memory and sends the instructions over a telephone line using a modem. The local modem of computer system 300 receives the data on the telephone line and uses an infrared transmitter to convert the data to an infrared signal. An infrared detector receives the data carried in the infrared signal, and appropriate circuitry places the data on bus 302. Bus 302 carries the data to main memory 306, from which processor 304 retrieves and executes the instructions. The instructions received by main memory 306 may optionally be stored on storage device 310 before or after execution by processor 304.

[0086] Computer system 300 also includes a communication interface 318 connected to bus 302. Communication interface 318 provides two-way data communications coupled to a network link 320 connected to a local network 322. For example, communication interface 318 is an integrated services digital network (ISDN) card, a cable modem, a satellite modem, or a modem for providing a data communication connection with a corresponding type of telephone line. As another example, communication interface 318 is a local area network (LAN) card for providing a data communication connection with a compatible LAN. In some implementations, a wireless link is also implemented. In any such implementation, communication interface 318 sends and receives electrical, electromagnetic, or optical signals carrying digital data streams representing various information.

[0087] Network link 320 typically provides data communication to other data devices through one or more networks. For example, network link 320 provides a connection to a host computer 324 or to a cloud data center or facility operated by an Internet Service Provider (ISP) 326 via a local network 322. ISP 326, in turn, provides data communication services via the worldwide packet data communication network now commonly referred to as the "Internet." Local network 322 and Internet 328 both use electrical, electromagnetic, or optical signals that carry digital data streams. The signals passing through the various networks and the signals on network link 320 and through communication interface 318 are example forms of transmission media, where communication interface 318 carries digital data to and from computer system 300. In an embodiment, network 320 comprises cloud 202, or a portion of cloud 202, as described above.

[0088] Computer system 300 sends messages and receives data, including program code, through network(s), network link 320, and communication interface 318. In an embodiment, computer system 300 receives code for processing. The received code is executed by processor 304 upon receipt and / or stored in storage device 310 or other non-volatile storage for later execution.

[0089] Autonomous Vehicle Architecture

[0090] Figure 4 Shown for autonomous vehicles (e.g., Figure 1 100). The architecture 400 includes a sensing module 402 (sometimes referred to as sensing circuitry), a planning module 404 (sometimes referred to as planning circuitry), a control module 406 (sometimes referred to as control circuitry), a positioning module 408 (sometimes referred to as positioning circuitry), and a database module 410 (sometimes referred to as database circuitry). Each module plays a role in the operation of the AV 100. Collectively, the modules 402, 404, 406, 408, and 410 may be Figure 1 4 and 5. In some embodiments, any of modules 402, 404, 406, 408, and 410 is a combination of computer software (e.g., executable code stored on a computer-readable medium) and computer hardware (e.g., one or more microprocessors, microcontrollers, application-specific integrated circuits [ASICs], hardware memory devices, other types of integrated circuits, other types of computer hardware, or a combination of any or all of these).

[0091] In use, the planning module 404 receives data representing a destination 412 and determines data representing a trajectory 414 (sometimes referred to as a route) that the AV 100 may travel in order to reach (e.g., arrive at) the destination 412. In order for the planning module 404 to determine the data representing the trajectory 414, the planning module 404 receives data from the perception module 402, the positioning module 408, and the database module 410.

[0092] The perception module 402 uses, for example, Figure 1 One or more sensors 121 are shown to identify nearby physical objects, classify the objects (e.g., into types such as pedestrians, bicycles, cars, traffic signs, etc.), and provide a scene description including the classified objects 416 to the planning module 404.

[0093] The planning module 404 also receives data representing the AV's position 418 from the positioning module 408. The positioning module 408 determines the AV's position by using data from the sensor 121 and data from the database module 410 (e.g., geographic data) to calculate the position. For example, the positioning module 408 uses data from the GNSS receiver and the geographic data to calculate the longitude and latitude of the AV. In an embodiment, the data used by the positioning module 408 includes a high-precision map with lane geometry, a map describing the road network connectivity attributes, a map describing the physical attributes of the lanes (such as traffic speed, traffic volume, the number of vehicle and bicycle lanes, lane width, lane traffic direction, or lane marking type and location, or a combination thereof), and a map describing the spatial location of road features (such as intersections, traffic signs, or various types of other driving signals, etc.).

[0094] The control module 406 receives data representing the trajectory 414 and data representing the AV's position 418 and operates the AV's control functions 420 a - 420 c (e.g., steering, throttle, brakes, ignition) in a manner that will cause the AV 100 to travel the trajectory 414 to reach the destination 412. For example, if the trajectory 414 includes a left turn, the control module 406 will operate the control functions 420 a - 420 c in such a manner that the steering angle of the steering function will cause the AV 100 to turn left, and the throttle and brakes will cause the AV 100 to pause and wait for a passing pedestrian or vehicle before executing the turn.

[0095] Sampling driving scenarios

[0096] Figure 5 5 is an example system 500 for sampling driving scenarios according to one or more embodiments. The system 500 includes a seed generator 501, a pseudo-random number generator 502, a scenario database 503, a scenario initializer 504, a simulator 505, a user interface (UI) 506, and a scenario sample database 507.

[0097] In an embodiment, UI 506 may be a graphical user interface (GUI), text, or voice interface that allows a user to select a driving scenario from a plurality of driving scenarios stored in scenario database 503. The user may also use UI 506 to select one or more parameters from scenario database 503 to randomly initialize the physical and psychological states of one or more objects in the selected driving scenario. The user's input is received by scenario initializer 504, which initializes the physical and psychological states of one or more objects to be simulated by simulator 505. In an embodiment, UI 506 allows a user to create a scenario by specifying the physical and psychological states of one or more objects and a road network (map), even if the exact parameters are not stored in database 503.

[0098] As used herein, the "physical state" of an object, for example, includes the position, speed, acceleration, direction or towards and object type (for example, vehicle, pedestrian, cyclist) of the object. The "psychological state" of an object refers to the psychological state of a virtual driver of a vehicle, motorcycle, bicycle or any other vehicle, or a pedestrian. Some examples of psychological parameters include, but are not limited to: the driver's acceleration preference (for example, a preference for rapidly accelerating from a stopped position), the preference for maintaining a specific distance with other objects (for example, a preference for following closely), the preference for a specific route, the driver's target (for example, arriving at a destination quickly), the tendency to use steering or hand signals, and a courtesy factor (for example, a weighting factor) that determines to what extent the virtual driver has the willingness to inconvenience other drivers by adopting, for example, an overly aggressive or overly passive driving style in a driving scenario.

[0099] In an embodiment, a user can use UI 506 to select a statistical distribution (e.g., a normal distribution) to be used by PRNG 502 to generate pseudo-random numbers according to the selected distribution. In an embodiment, the statistical distribution can be a joint probability distribution over two or more scenario parameters. The random number is used to randomly generate or assign the scenario parameters stored in the scenario database 503. For example, the random number can be a real number in a specified range, and the parameter can be the acceleration of an object (e.g., a vehicle). In this example, the random number is used to randomly select an initial acceleration from a set of initial accelerations stored in the scenario database 504. In an embodiment, a true random number generator (e.g., a hardware RNG) seeded with a true random seed provided by, for example, hardware or a physical phenomenon can be used.

[0100] After initialization, the simulator 505 simulates the movement of objects in the map based on the initialized physical state and psychological state to generate object traces. For example, the simulator 505 can implement a dynamic model and motion equations to generate object traces within a simulation time period specified by the user, for example, via UI 506. The user can also select a sample data rate via UI 506. For example, the user may want to sample object traces at 1 Hz. The object traces are output by the simulator 505 and stored in the scenario sample database 507. In an embodiment, each stored sample includes at least a timestamp and physical state (e.g., position, velocity, and acceleration) of each object in the driving scenario. If the object has a psychological state that will also be stored together with the sample, the user can use UI 506 to view and select samples from the scenario sample database 507.

[0101] In an embodiment, the simulator 505 determines whether a particular driving scenario is a "failure" driving scenario. Examples of "failure" scenarios include, but are not limited to, scenarios where two or more objects collide, or where the acceleration or deceleration values of one or more of the objects are above or below one or more specified thresholds (e.g., where the acceleration is too high to cause a loss of control of the vehicle).

[0102] In one embodiment, before outputting samples to the scenario sample database 507, each driving scenario is simulated forward in time for a specified number of time units, allowing one or more objects to traverse their respective trajectories without failure. For example, depending on the randomized initial states of two or more objects, these objects may collide within the first few seconds of the simulation, thereby generating a failed driving scenario. By running the simulation for a specified period of time (e.g., 2-3 seconds) before sampling, these failed scenarios can be avoided or reduced in number.

[0103] In an embodiment, the subject obeys the rulebook and / or traffic regulations (eg, stopping at stop signs and traffic lights, driving within posted speed limits).

[0104] In an embodiment, the simulator 505 simulates any desired driving scenario, including, but not limited to, sensor failure scenarios, adverse weather conditions, adverse road conditions, low or high object or traffic density, and communication failure scenarios. The simulated driving scenario can be for any desired road characteristics or conditions, including, but not limited to, intersection scenarios, lane change scenarios, collision avoidance scenarios, etc. In an embodiment, the driving scenario is generated based on at least one of a specified density of objects (e.g., urban vs. rural), a specified day, and a specified time of day (e.g., to simulate rush hour traffic or compare urban vs. rural performance).

[0105] In an embodiment, for a given scenario, the "physical state" of one or more objects is fixed, and the "mental state" of the virtual driver is varied, e.g., changing intended route, courtesy, headway to the vehicle ahead, etc.

[0106] Figure 6 6 is an example system 600 for training and tuning a machine learning model using sample driving scenarios generated by the system 500 according to one or more embodiments. The system 600 includes a scenario sample database 507, a data splitter 601, a training database 602a, a tuning database 602b, a machine learning model 603 (e.g., a motion prediction model), a tuning module 604, and an AV log database 605.

[0107] In an embodiment, the scenario samples in the scenario sample database 507 are split into training data 602a and tuning data 602b. In training mode, the training data 602a is used to train the machine learning model 603. Supervised, unsupervised, or reinforcement methods can be used to train and / or tune the machine learning model 603. The machine learning model 603 includes, but is not limited to, artificial neural networks, decision trees, support vector machines, regression analysis, Bayesian networks, and genetic algorithms. In an embodiment, the sampled driving scenarios are embedded in pseudo images, such as bird's-eye view images (BEVs), which are used to train the machine learning model (e.g., to train an image-based deep neural network).

[0108] In the tuning mode, the machine learning model 603 is tuned using the tuning data 602b and / or the AV log data from the database 605. The tuning module 604 tunes the machine learning model 603 by iteratively optimizing the loss function of the predictions output by the machine learning model 603 and the ground truth data. For example, through iterative optimization of the loss function, the machine learning model 603 learns the optimal function that can be used to predict the output associated with the new input. The optimal function allows the machine learning algorithm to correctly determine the output for the tuning data 602b and / or the AV log data. In an embodiment, the machine learning model 603 is a deep neural network, and the tuning module 604 uses a stochastic gradient descent or Adam optimizer to calculate the updated weights of the deep neural network to iteratively optimize the mean squared error (MSE) loss function. The trained machine learning model 603 is stored and subsequently used for inference of real-world autonomous driving, such as motion prediction for one or more of positioning, planning, perception, and control tasks.

[0109] Example Processing

[0110] Figure 7 is a flow chart of a process 700 for sampling a driving scenario according to one or more embodiments. The process 700 may be performed using, for example, a reference Figure 3 The computer system is implemented.

[0111] The process 700 begins by assigning a set of initial physical states to a set of objects in a map for a set of simulated driving scenarios, wherein the set of initial physical states is assigned based on one or more outputs of a random number generator (701). For example, the random number or pseudo-random number generator can be initialized with a seed and configured to generate random numbers or pseudo-random numbers that can be used to generate or assign initialization parameters for the physical and psychological states of one or more objects. In an embodiment, for a given scenario, the "physical state" of one or more objects is fixed, and the "psychological state" of the virtual driver is varied, for example, to change the intended route, courtesy, headway to the vehicle ahead, etc.

[0112] Process 700 continues with generating a simulated driving scenario using the initialized physical state and optional psychological state of one or more objects 702. For example, a dynamic model and equations of motion may be used to move the one or more objects in a map starting from their randomly initialized physical states.

[0113] Process 700 continues with selecting a sample of simulated driving scenarios (703). For example, the user may refer to Figure 6 The driving scenario samples are selected from the driving sample database 507 and the data rate of the simulation data output may also be specified.

[0114] Process 700 continues with training and / or tuning the machine learning model using the selected samples (704). Figure 6 As described above, a deep neural network can be trained using driving scenario samples selected by a user via a user interface.

[0115] Process 700 continues with using the trained and / or tuned machine learning model to operate the vehicle in the environment (705).For example, the trained deep neural network can be used by the perception module of the AV to infer the motion of one or more objects.

[0116] In the foregoing description, embodiments of the present invention have been described with reference to many specific details, which may vary from implementation to implementation. Therefore, the description and drawings should be regarded as illustrative, not restrictive. The sole and exclusive indication of the scope of the invention, and what the applicants expect to be the scope of the invention, is the literal and equivalent scope of the claims authorized from this application in the specific form of the authorized claims, including any subsequent amendments. Any definitions of terms expressly set forth herein for being included in such claims should be based on the meaning of such terms as used in the claims. In addition, when the term "also includes" is used in the previous description or the appended claims, the phrase may be followed by additional steps or entities, or sub-steps / sub-entities of the previously described steps or entities.

Claims

1. A method comprising: assigning, using at least one processor, a set of initial physical states to a set of objects in a map for a set of simulated driving scenarios, wherein the set of initial physical states is assigned based on one or more outputs of a random number generator; generating, using the at least one processor, the set of simulated driving scenarios in the map using initial physical states of objects in the set of objects; selecting, using the at least one processor, a sample of the simulated driving scenario; training a machine learning model using the selected samples, using the at least one processor; as well as Use control circuits to operate the vehicle in the environment using the trained machine learning model.

2. The method according to claim 1, wherein At least one object in the set of objects is a virtual vehicle, the method further comprising: assigning, using the at least one processor, a mental state of a virtual driver of the virtual vehicle; and A driving scenario is simulated using the map, initial physical states of objects, and the psychological state of the virtual driver of the virtual vehicle.

3. The method according to claim 2, wherein: The mental state of the virtual driver includes an acceleration preference of the virtual driver.

4. The method according to claim 2, wherein: The mental state of the virtual driver includes a preference to maintain a gap between another virtual vehicle and at least one other object in the set of objects.

5. The method according to claim 2, wherein: The virtual driver's mental state includes a preference for a particular route.

6. The method according to claim 2, wherein: The mental state of the virtual driver includes a goal of the virtual driver.

7. The method according to claim 2, wherein: The virtual driver's mental state includes a courtesy factor that is used to determine the extent to which the virtual driver is willing to inconvenience other virtual drivers of other virtual vehicles in the driving scenario.

8. The method according to claim 1, wherein The initial physical states of the objects in the group of objects include an initial position and an initial acceleration, and the initial position and the initial acceleration are assigned according to different random numbers output by the random number generator.

9. The method according to claim 1, further comprising: determining, using the at least one processor, one or more failed driving scenarios from a set of driving scenarios; as well as The at least one processor is used to exclude the one or more failed driving scenarios from training the machine learning model.

10. The method according to claim 9, wherein: The one or more failed driving scenarios include a driving scenario in which a collision occurs between two or more objects in the set of objects.

Images