Method for a vehicle, a vehicle, and a storage medium

Abstract

The present invention relates to a method, a vehicle, and a storage medium for a vehicle. A method, apparatus, and system for adaptive point cloud filtering for an autonomous vehicle are disclosed. At least one processor receives a plurality of LiDAR points from a LiDAR system. The plurality of LiDAR points represent at least one object in an environment in which the vehicle is traveling. The at least one processor determines a Euclidean distance for each of the plurality of LiDAR points. The at least one processor compares the Euclidean distance of each LiDAR point with a corresponding sampled Euclidean distance from a standard normal distribution of Euclidean distances. In response to the Euclidean distance of a LiDAR point being less than the corresponding sampled Euclidean distance, the at least one processor removes the LiDAR point from the plurality of LiDAR points to generate a point cloud. The at least one processor operates the vehicle based on the point cloud.

Description

Technical Field

[0001] The present application relates generally to vehicle operation and, more particularly, to adaptive point cloud generation for autonomous vehicles. Background Art

[0002] Autonomous vehicles often use LiDAR sensors and systems for localization and object perception. However, LiDAR point clouds acquired using LiDAR systems sometimes contain redundant information and non-uniform density distribution. As a result, the computational complexity for processing such LiDAR point clouds can increase, posing a challenge to the efficient and safe operation of autonomous vehicles. Summary of the Invention

[0003] Methods, devices, and systems for adaptive point cloud generation for an autonomous vehicle are disclosed. In one embodiment, at least one processor of a vehicle receives a plurality of LiDAR points from a LiDAR system of the vehicle. The plurality of LiDAR points represent at least one object in an environment in which the vehicle is traveling. The at least one processor determines a Euclidean distance for each of the plurality of LiDAR points. The at least one processor compares the Euclidean distance for each of the plurality of LiDAR points to a corresponding sampled Euclidean distance from a standard normal distribution of Euclidean distances. In response to the Euclidean distance for each of the plurality of LiDAR points being less than the corresponding sampled Euclidean distance, the at least one processor removes the LiDAR point from the plurality of LiDAR points to generate a point cloud. The at least one processor operates the vehicle based on the point cloud.

[0004] In an embodiment, the plurality of LiDAR points have a first density variation, and the point cloud has a second density variation that is less than the first density variation.

[0005] In an embodiment, generating the point cloud includes downsampling, by the at least one processor, the plurality of LiDAR points to provide the second density variation.

[0006] In an embodiment, removing the LiDAR point from the plurality of LiDAR points is based on the first density change.

[0007] In an embodiment, the at least one processor determines a likelihood of adding the LiDAR point to the point cloud based on the first density change.

[0008] In an embodiment, the at least one processor compares a measured range of the LiDAR system to a distance from the LiDAR system to the at least one object.

[0009] In an embodiment, the LiDAR system includes at least one LiDAR. The at least one processor determines a measurement range of the LiDAR system based on the speed of light and a pulse repetition frequency of the at least one LiDAR.

[0010] In an embodiment, said at least one processor determines said respective sampled Euclidean distances as random numbers.

[0011] In an embodiment, the at least one processor segments the point cloud based on the second density variation to identify the at least one object.

[0012] In an embodiment, operating the vehicle to avoid collision with the at least one object is further based on the segmented point cloud.

[0013] In an embodiment, the at least one processor reduces an amount of noise in the point cloud based on the second density variation.

[0014] In an embodiment, the at least one processor smoothes the point cloud based on the second density variation.

[0015] According to one aspect of the present invention, a method for a vehicle includes: receiving, by at least one processor of the vehicle, a plurality of LiDAR points from a LiDAR system of the vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determining, by the at least one processor, a Euclidean distance of each of the plurality of LiDAR points; comparing, by the at least one processor, the Euclidean distance of each of the plurality of LiDAR points with a corresponding sampled Euclidean distance of a Euclidean distance from a standard normal distribution; in response to the Euclidean distance of each of the plurality of LiDAR points being less than the corresponding sampled Euclidean distance, removing, by the at least one processor, the LiDAR point from the plurality of LiDAR points to generate a point cloud; and operating, by the at least one processor, the vehicle based on the point cloud.

[0016] According to another aspect of the present invention, a vehicle comprises: at least one computer processor; and at least one non-transitory storage medium storing instructions, wherein the instructions, when executed by the at least one computer processor, cause the at least one computer processor to: receive a plurality of LiDAR points from a LiDAR system of the vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determine a Euclidean distance of each of the plurality of LiDAR points; compare the Euclidean distance of each of the plurality of LiDAR points with a corresponding sampled Euclidean distance of a Euclidean distance from a standard normal distribution; in response to the Euclidean distance of each of the plurality of LiDAR points being less than the corresponding sampled Euclidean distance, remove the LiDAR point from the plurality of LiDAR points to generate a point cloud; and operate the vehicle based on the point cloud.

[0017] According to another aspect of the present invention, at least one non-transitory storage medium stores instructions that, when executed by at least one computing device, cause the at least one computing device to: receive a plurality of LiDAR points from a LiDAR system of a vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determine a Euclidean distance of each of the plurality of LiDAR points; compare the Euclidean distance of each of the plurality of LiDAR points with corresponding sampled Euclidean distances of Euclidean distances from a standard normal distribution; in response to the Euclidean distance of each of the plurality of LiDAR points being less than the corresponding sampled Euclidean distance, remove the LiDAR point from the plurality of LiDAR points to generate a point cloud; and operate the vehicle based on the point cloud.

[0018] These and other aspects, features, and implementations may be expressed as methods, apparatus, systems, components, program products, means or steps, and other means for performing the functions.

[0019] These and other aspects, features, and implementations will be apparent from the following description, including the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a block diagram illustrating an example of an autonomous vehicle (AV) having autonomous capabilities according to one or more embodiments.

[0021] Figure 2 is a block diagram illustrating an example "cloud" computing environment in accordance with one or more embodiments.

[0022] Figure 3 is a block diagram illustrating a computer system according to one or more embodiments.

[0023] Figure 4 is a block diagram illustrating an example architecture of an AV in accordance with one or more embodiments.

[0024] Figure 5 is a block diagram illustrating examples of inputs and outputs that a perception module may use in accordance with one or more embodiments.

[0025] Figure 6 is a block diagram illustrating an example of a LiDAR system according to one or more embodiments.

[0026] Figure 7 is a block diagram illustrating a LiDAR system in operation according to one or more embodiments.

[0027] Figure 8 is a block diagram illustrating the operation of a LiDAR system in more detail, according to one or more embodiments.

[0028] Figure 9 is a block diagram illustrating the relationship between inputs and outputs of a planning module in accordance with one or more embodiments.

[0029] Figure 10 A directed graph used in path planning according to one or more embodiments is shown.

[0030] Figure 11 is a block diagram illustrating inputs and outputs of a control module according to one or more embodiments.

[0031] Figure 12 is a block diagram illustrating inputs, outputs, and components of a controller according to one or more embodiments.

[0032] Figure 13 is a diagram illustrating an example of adaptive point cloud generation for an autonomous vehicle in accordance with one or more embodiments.

[0033] Figure 14 is a diagram illustrating an example LiDAR point cloud for an autonomous vehicle in accordance with one or more embodiments.

[0034] Figure 15 An example process for adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0035] Figure 16 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0036] Figure 17An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0037] Figure 18 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0038] Figure 19 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0039] Figure 20 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0040] Figure 21 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0041] Figure 22 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0042] Figure 23 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an autonomous vehicle is shown in accordance with one or more embodiments.

[0043] Figure 24 is a flow diagram illustrating a process for adaptive point cloud generation for an autonomous vehicle in accordance with one or more embodiments. DETAILED DESCRIPTION

[0044] In the following description, for the purpose 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 can be practiced without these specific details. In other examples, well-known configurations and devices are shown in block diagram form to avoid unnecessarily obscuring the present invention.

[0045] 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 order or arrangement of the schematic elements in the accompanying drawings is not intended to mean that a specific processing order or sequence, or separation of processing processes is required. In addition, the inclusion of a schematic element in the accompanying drawings is not intended to mean that such an element is required in all embodiments, nor is it intended to mean that the features represented by such an element cannot be included in an embodiment or cannot be combined with other elements in an embodiment.

[0046] 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 without any such connecting elements it is not intended to 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 disclosure. In addition, for ease of illustration, a single connecting element is used to represent multiple connections, relationships or associations between elements. For example, if the communication of connecting element representation signal, data or instruction, it will be understood by those skilled in the art that this element representation affects one or more signal paths (for example, bus) that may be needed for communication.

[0047] 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.

[0048] The several features described below can each be used independently of one another or in combination with any other features. However, any individual feature may not solve any of the problems discussed above, or may only solve one of the problems discussed above. Some of the problems discussed above may not be fully solved by any one of the features described herein. Although headings are provided, information related to a specific heading but not found in the section with that heading may also be found elsewhere in this specification. This article describes an embodiment according to the following summary:

[0049] 1. General Overview

[0050] 2. System Overview

[0051] 3. Autonomous Vehicle Architecture

[0052] 4. Autonomous Vehicle Input

[0053] 5. Autonomous Vehicle Planning

[0054] 6. Autonomous Vehicle Control

[0055] 7. Autonomous Vehicle Operations Using Adaptive Point Cloud Generation

[0056] 8. Processing for Adaptive Point Cloud Generation

[0057] General Overview

[0058] Provided herein are methods, systems, and apparatus for adaptive point cloud generation for autonomous vehicles (AVs). A goal of the disclosed adaptive point cloud generation techniques is to obtain a low-variance LiDAR point cloud that is more efficient for further processing and AV operation. In some embodiments, statistical processing is used to determine whether to include (e.g., add) or discard individual LiDAR points included in a LiDAR point cloud generated by a LiDAR system in a point cloud output for use by one or more systems in the AV. In an example, the determination of whether to include or discard individual points is based on distribution characteristics of the LiDAR points included in the LiDAR point cloud. Since many (if not most) LiDAR points are associated with distances closer to the LiDAR sensor (e.g., grouped at distance), closer LiDAR points have more redundant information. The LiDAR points are downsampled by distance such that closer LiDAR points are more likely to be removed than more distant LiDAR points.

[0059] Advantages and benefits of adaptive point cloud generation for AVs using the described embodiments include filtering raw LiDAR point clouds to generate point clouds representing a portion of the environment while requiring less computation by downstream systems during the AV's operation. The described implementation also improves the overall robustness of the LiDAR data while eliminating the need for additional parameters. The method is computationally efficient and therefore enables real-time point cloud processing. The implementation improves the localization, perception, and prediction of objects based on LiDAR point clouds. Furthermore, the described system for point cloud generation provides efficient pre-processing steps, such as point cloud segmentation, denoising, and smoothing, for applications used in the operation of AVs.

[0060] System Overview

[0061] Figure 1 is a block diagram illustrating an example of an autonomous vehicle 100 having autonomous capabilities according to one or more embodiments.

[0062] 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, and conditionally autonomous vehicles.

[0063] As used herein, an autonomous vehicle (AV) is a vehicle with autonomous capabilities.

[0064] 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.

[0065] 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.

[0066] 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 (such as analog-to-digital converters), data storage devices (such as RAM and / or non-volatile memory), software or firmware components and data processing components (such as application specific integrated circuits), microprocessors, and / or microcontrollers.

[0067] 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.

[0068] 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 is not formally defined as a thoroughfare by a municipality or other governmental or administrative agency.

[0069] 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).

[0070] “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.

[0071] It will also be understood that although in some cases, the terms "first," "second," etc. are used herein 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. Both the first contact and the second contact are contacts, but they are not the same contact.

[0072] The terms used in the specification of the various embodiments described herein are for the purpose of describing specific embodiments only and are not intended to be limiting. As used in the specification of the various embodiments described and the appended claims, the singular forms "a", "an", and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that "and / or" as used herein refers to and includes any and all possible combinations of one or more related list items. It will also be understood that when the terms "comprises", "comprising", "having" and / or "having" are used in this specification, the presence of the stated features, integers, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof is not excluded.

[0073] As used herein, the term "if" is alternatively understood to mean "when" or "at the time" or "in response to being determined as" or "in response to being detected," depending on the context. Similarly, the phrases "if it has been determined" or "if [stated condition or event] has been detected" are alternatively understood to mean "upon the determination" or "in response to being determined as" or "upon detecting [stated condition or event]" or "in response to detecting [stated condition or event]," depending on the context.

[0074] As used herein, an AV system refers to an AV and the array of hardware, software, stored data, and real-time generated data that supports AV operation. In an embodiment, the AV system is incorporated into the AV. In an embodiment, the AV system is distributed across several locations. For example, some software for the AV system is in a system similar to the following about Figure 2 The described cloud computing environment 200 is implemented on the cloud computing environment.

[0075] In general, this document describes technologies applicable to any vehicle having 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, respectively (see SAE International Standard J3016: Classification and Definitions of Terms Relating to Automated Driving Systems for Road-Based Motor Vehicles, which is incorporated by reference in its entirety into this document for more detailed information 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 of any level, ranging from fully autonomous vehicles to human-operated vehicles.

[0076] refer to Figure 1 , the AV system 120 causes the AV 100 to operate along a trajectory 198 through the 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 road rules (e.g., operating rules or driving preferences).

[0077] 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.

[0078] 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 velocity and acceleration, angular velocity and acceleration, and heading (e.g., the direction of the front end of the AV 100). Examples of sensors 121 are GNSS, an inertial measurement unit (IMU) that measures both linear acceleration and angular rate of the vehicle, wheel 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.

[0079] 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.

[0080] In an embodiment, the AV system 120 includes a data storage unit 142 and a memory 144 for storing machine instructions associated with the computer processor 146 or data collected by the sensor 121. In an embodiment, the data storage unit 142 is associated 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 from remote database 134 to AV 100 via a communication channel.

[0081] 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 an embodiment, 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.

[0082] 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 a computer 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 a remote database 134. In an embodiment, the communication interface 140 transmits information related to teleoperation to the AV 100. In an embodiment, the AV 100 communicates with other remote (e.g., "cloud") servers 136.

[0083] In an embodiment, the remote database 134 also stores and transmits digital data (e.g., data such as roads and street locations). 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.

[0084] In an embodiment, the remote database 134 stores and transmits historical information regarding driving attributes (e.g., speed and acceleration 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.

[0085] The computing device 146 located on the AV 100 algorithmically generates control actions based on both real-time sensor data and a priori information, allowing the AV system 120 to perform its autonomous driving capabilities.

[0086] In an embodiment, the AV system 120 includes a computer peripheral device 132 coupled to a computing device 146 for providing information and alerts 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 coupling may be wireless or wired. Any two or more of the interface devices may be integrated into a single device.

[0087] Sample cloud computing environment

[0088] Figure 2 is a block diagram illustrating an example "cloud" computing environment according to one or more embodiments. Cloud computing is a service delivery model for enabling 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 referring 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.

[0089] The cloud computing environment 200 includes one or more cloud data centers. Generally speaking, 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 arranged 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.

[0090] 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-206f. In embodiments, the network represents any combination of one or more local networks, wide area networks, or internetworks coupled via 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, a different network layer protocol is used on each underlying subnetwork. In embodiments, the network represents one or more interconnected internetworks, such as the public Internet.

[0091] Computing systems 206a-206f, or cloud computing service consumers, are connected to the cloud 202 via network links and network adapters. In embodiments, computing systems 206a-206f 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-206f are implemented in other systems or as part of other systems.

[0092] Computer system

[0093] Figure 3 is a block diagram illustrating a computer system 300 according to one or more embodiments. 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 digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs) that are 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. Such a special-purpose computing device may also combine customized hard-wired logic, ASICs or FPGAs with customized programming to accomplish 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.

[0094] 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.

[0095] In embodiments, computer system 300 also includes a read-only memory (ROM) 308 or other static storage device coupled 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 coupled to bus 302 to store information and instructions.

[0096] 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.

[0097] 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.

[0098] 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 particular 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 memory, such as storage device 310. Volatile media include dynamic memory, 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.

[0099] 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 wire, and optical fiber, 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.

[0100] In one embodiment, various forms of media are involved in carrying one or more sequences of one or more instructions to processor 304 for execution. For example, the instructions may initially be 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 modem local to 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.

[0101] Computer system 300 also includes a communication interface 318 coupled to bus 302. Communication interface 318 provides a two-way data communication coupled to a network link 320 that is 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 that carry digital data streams representing various types of information.

[0102] 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 through a local network 322. ISP 326, in turn, provides data communication services through the worldwide packet data communication network now commonly referred to as the "Internet" 328. Both local network 322 and Internet 328 use electrical, electromagnetic, or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 320 and through communication interface 318 are example forms of transmission media, where these signals carry digital data to and from computer system 300. In an embodiment, network 320 includes cloud 202 or a portion of cloud 202 as described above.

[0103] 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.

[0104] Autonomous Vehicle Architecture

[0105] Figure 4 is a diagram illustrating a method 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 an embodiment, 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).

[0106] 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.

[0107] 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.

[0108] 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 a global navigation satellite system (GNSS) unit and 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).

[0109] 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.

[0110] Autonomous Vehicle Input

[0111] Figure 5 is a diagram showing the perception module 402 ( Figure 4 ) used by the inputs 502a-502d (e.g., Figure 1 1) and outputs 504a-504d (e.g., sensor data). One input 502a is a LiDAR (Light Detection and Ranging) system (e.g., Figure 1 LiDAR 123 is shown. LiDAR is a technology that uses light (e.g., a beam of light such as infrared light) to obtain data about physical objects in its line of sight. The LiDAR system generates LiDAR data as output 504a. For example, LiDAR data is a collection of 3D or 2D points (also called a point cloud) used to construct a representation of the environment 190.

[0112] Another input 502b is a RADAR (radar) system. RADAR is a technology that uses radio waves to obtain data about nearby physical objects. RADAR can obtain data about objects that are not within the line of sight of the LiDAR system. RADAR system 502b generates RADAR data as output 504b. For example, RADAR data is one or more radio frequency electromagnetic signals used to construct a representation of environment 190.

[0113] Another input 502c is a camera system. The camera system uses one or more cameras (e.g., a digital camera using a light sensor such as a charge coupled device [CCD]) to acquire information about nearby physical objects. The camera system produces camera data as output 504c. The camera data is typically in the form of image data (e.g., data in an image data format such as RAW, JPEG, PNG, etc.). In some examples, the camera system has multiple independent cameras, such as for the purpose of stereo imaging (stereo vision), which enables the camera system to perceive depth. Although the objects perceived by the camera system are described here as "nearby", this is relative to the AV. In use, the camera system can be configured to "see" objects that are far away (e.g., up to 1 km or more in front of the AV). Therefore, the camera system can have features such as sensors and lenses that are optimized for perceiving distant objects.

[0114] Another input 502d is a traffic light detection (TLD) system. The TLD system uses one or more cameras to obtain information about traffic lights, street signs, and other physical objects that provide visual operational information. The TLD system generates TLD data as an output 504d. The TLD data often takes the form of image data (e.g., data in an image data format such as RAW, JPEG, PNG, etc.). The TLD system differs from a system that includes a camera in that the TLD system uses a camera with a wide field of view (e.g., using a wide-angle lens or a fisheye lens) to obtain information about as many physical objects that provide visual operational information as possible, allowing the AV 100 to access all relevant operational information provided by these objects. For example, the viewing angle of the TLD system can be approximately 120 degrees or greater.

[0115] In an embodiment, the outputs 504a-504d are combined using sensor fusion techniques. Thus, the individual outputs 504a-504d are provided to other systems of the AV 100 (e.g., to a Figure 4The combined output may be provided to other systems in the form of a single combined output or multiple combined outputs of the same type (e.g., using the same combining technique or combining the same outputs, or both) or a single combined output or multiple combined outputs of different types (e.g., using different individual combining techniques or combining different individual outputs, or both). In an embodiment, an early fusion technique is used. An early fusion technique is characterized in that the outputs are combined before one or more data processing steps are applied to the combined output. In an embodiment, a late fusion technique is used. A late fusion technique is characterized in that the outputs are combined after one or more data processing steps are applied to the individual outputs.

[0116] Figure 6 is an example of a LiDAR system 602 according to one or more embodiments (e.g., Figure 5 6a-6c). The LiDAR system 602 emits light 604a-604c from a light emitter 606 (e.g., a laser emitter). The light emitted by the LiDAR system is typically not in the visible spectrum; for example, infrared light is often used. Some of the emitted light 604b encounters a physical object 608 (e.g., a vehicle) and reflects back to the LiDAR system 602. (The light emitted from the LiDAR system typically does not penetrate a physical object, such as a solid form.) The LiDAR system 602 also has one or more light detectors 610 for detecting the reflected light. In an embodiment, one or more data processing systems associated with the LiDAR system generate an image 612 representing a field of view 614 of the LiDAR system. The image 612 includes information representing the boundaries 616 of the physical object 608. In this way, the image 612 is used to determine the boundaries 616 of one or more physical objects in the vicinity of the AV.

[0117] Figure 7 is a block diagram illustrating a LiDAR system 602 in operation according to one or more embodiments. In the scenario illustrated in this figure, the AV 100 receives both camera system output 504c in the form of an image 702 and LiDAR system output 504a in the form of LiDAR data points 704. In use, the data processing system of the AV 100 compares the image 702 with the LiDAR data points 704. In particular, physical objects 706 identified in the image 702 are also identified in the LiDAR data points 704. In this way, the AV 100 perceives the boundaries of the physical objects based on the contours and density of the data points 704.

[0118] Figure 8is a block diagram illustrating the operation of the LiDAR system 602 in more detail according to one or more embodiments. As described above, the AV 100 detects the boundaries of a physical object based on the characteristics of the data points detected by the LiDAR system 602. Figure 8 As shown, a flat object such as the ground 802 will reflect light 804a-804d emitted from the LiDAR system 602 in a consistent manner. In other words, because the LiDAR system 602 emits light using consistent intervals, the ground 802 will reflect light back to the LiDAR system 602 at the same consistent intervals. As the AV 100 travels over the ground 802, and nothing is blocking the road, the LiDAR system 602 will continue to detect light reflected by the next valid ground point 806. However, if an object 808 blocks the road, the light 804e-804f emitted by the LiDAR system 602 will reflect from points 810a-810b in a manner that is inconsistent with the expected consistent manner. Based on this information, the AV 100 can determine that the object 808 is present.

[0119] Path Planning

[0120] Figure 9 is a diagram illustrating a method according to one or more embodiments (e.g., Figure 4 900 shows a block diagram of the relationship between the inputs and outputs of the planning module 404 (shown in FIG. 1 ). Generally speaking, the output of the planning module 404 is a route 902 from a starting point 904 (e.g., a source location or initial location) to an end point 906 (e.g., a destination or final location). The route 902 is typically defined by one or more road segments. For example, a road segment refers to a distance to be traveled on at least a portion of a street, road, highway, lane, or other physical area suitable for automobile travel. In some examples, for example, if the AV 100 is an off-road capable vehicle such as a four-wheel drive (4WD) or all-wheel drive (AWD) car, SUV, or pickup truck, the route 902 includes "off-road" segments such as unpaved paths or open fields.

[0121] In addition to route 902, the planning module also outputs lane-level routing data 908. Lane-level routing data 908 is used to navigate the segments of route 902 at a specific time based on the conditions of those segments. For example, if route 902 comprises a multi-lane highway, lane-level routing data 908 includes trajectory planning data 910, which the AV 100 can use to select a lane from the multiple lanes based on, for example, whether an exit is imminent, whether other vehicles are available in one or more of the multiple lanes, or other factors that change over the course of a few minutes or less. Similarly, in some implementations, lane-level routing data 908 includes rate constraints 912 specific to a segment of route 902. For example, if the segment includes pedestrians or unexpected traffic, rate constraints 912 can limit the AV 100 to a slower travel speed than expected, such as a speed based on speed limit data for the segment.

[0122] In an embodiment, inputs to the planning module 404 include (e.g., Figure 4 ) database data 914, current location data 916 (e.g., Figure 4 AV position 418 shown), (e.g., for Figure 4 Destination data 918 and object data 920 (e.g., Figure 4 4 (see Figure 9). In one embodiment, database data 914 includes rules used during planning. Rules are specified using a formal language (e.g., using Boolean logic). In any given situation encountered by AV 100, at least some of these rules will apply to that situation. A rule applies to a given situation if it has conditions that are satisfied based on information available to AV 100 (e.g., information about the surrounding environment). Rules can have priorities. For example, a rule that says, "If the road is a freeway, move to the leftmost lane" may have a lower priority than a rule that says, "If an exit is within one mile, move to the rightmost lane."

[0123] Figure 10 4. In path planning (eg, by planning module 404 ( Figure 4 )) uses a directed graph 1000. Generally speaking, if Figure 10 A directed graph 1000, such as the one shown, is used to determine a path between any origin 1002 and destination 1004. In the real world, the distance separating the origin 1002 and destination 1004 may be relatively large (e.g., in two different metropolitan areas) or may be relatively small (e.g., two intersections adjacent to a city block or two lanes of a multi-lane road).

[0124] In one embodiment, directed graph 1000 includes nodes 1006a-1006d representing different locations that AV 100 may occupy between starting point 1002 and end point 1004. In some examples, for example, when starting point 1002 and end point 1004 represent different metropolitan areas, nodes 1006a-1006d represent sections of a road. In some examples, for example, when starting point 1002 and end point 1004 represent different locations on the same road, nodes 1006a-1006d represent different locations on that road. Thus, directed graph 1000 includes information at different levels of granularity. In one embodiment, a directed graph with high granularity is also a subgraph of another directed graph with a larger scale. For example, most of the information for a directed graph where the start point 1002 and the end point 1004 are far apart (e.g., many miles apart) is at a low granularity and is based on stored data, but the directed graph also includes some high granularity information for a portion of the directed graph that represents a physical location in the field of view of the AV 100.

[0125] Nodes 1006a-1006d are distinct from objects 1008a-1008b that cannot overlap with nodes. In an embodiment, at low granularity, objects 1008a-1008b represent areas that cannot be traversed by cars, such as areas without streets or roads. At high granularity, objects 1008a-1008b represent physical objects in the field of view of the AV 100, such as other cars, pedestrians, or other entities with which the AV 100 cannot share physical space. In an embodiment, some or all of objects 1008a-1008b are static objects (e.g., objects that do not change position, such as streetlights or utility poles) or dynamic objects (e.g., objects that can change position, such as pedestrians or other cars).

[0126] Nodes 1006a-1006d are connected by edges 1010a-1010c. If two nodes 1006a-1006b are connected by edge 1010a, the AV 100 can travel between one node 1006a and another node 1006b, for example, without having to travel to an intermediate node before reaching the other node 1006b. (When referring to the AV 100 traveling between nodes, it means that the AV 100 travels between two physical locations represented by the corresponding nodes.) Edges 1010a-1010c are typically bidirectional, in the sense that the AV 100 travels from a first node to a second node, or from a second node to a first node. In an embodiment, edges 1010a-1010c are unidirectional, in the sense that the AV 100 can travel from a first node to a second node, but the AV 100 cannot travel from a second node to the first node. Edges 1010a-1010c are unidirectional where they represent, for example, one-way streets, a single lane of a street, road, or highway, or other features that can only be traversed in one direction due to legal or physical constraints.

[0127] In an embodiment, the planning module 404 uses the directed graph 1000 to identify a path 1012 consisting of nodes and edges between the start point 1002 and the end point 1004 .

[0128] Edges 1010a-1010c have associated costs 1014a-1014b. Costs 1014a-1014b are values ​​representing the resources that would be expended if the AV 100 selected that edge. A typical resource is time. For example, if the physical distance represented by one edge 1010a is twice the physical distance represented by another edge 1010b, the cost 1014a associated with the first edge 1010a may be twice the cost 1014b associated with the second edge 1010b. Other factors that affect time include expected traffic, the number of intersections, speed limits, etc. Another typical resource is fuel economy. Two edges 1010a-1010b may represent the same physical distance, but one edge 1010a may require more fuel than the other edge 1010b, for example, due to road conditions, expected weather, etc.

[0129] When the planning module 404 identifies a path 1012 between the start point 1002 and the end point 1004 , the planning module 404 typically selects a path that is optimized for cost, eg, a path that has a minimum total cost when the individual costs of the edges are added together.

[0130] Autonomous vehicle control

[0131] Figure 11 is a diagram illustrating a method according to one or more embodiments (e.g., Figure 41 and 2. A block diagram 1100 of the inputs and outputs of the control module 406 (shown in FIG. 1 ) is provided. The control module operates according to a controller 1102, which includes, for example: one or more processors similar to the processor 304 (e.g., one or more computer processors such as a microprocessor or microcontroller or both); short-term and / or long-term data storage devices (e.g., memory, random access memory, or flash memory or both) similar to the main memory 306, ROM 308, and storage devices 310; and instructions stored in the memory that, when executed (e.g., by the one or more processors), perform the operations of the controller 1102.

[0132] In an embodiment, the controller 1102 receives data representing a desired output 1104. The desired output 1104 typically includes speed, such as velocity and heading. The desired output 1104 may be based on, for example, Figure 4 104 ). Based on the desired output 1104, the controller 1102 generates data that can be used as a throttle input 1106 and a steering input 1108. The throttle input 1106 indicates the amount by which the throttle of the AV 100 (e.g., an acceleration control) should be engaged, for example, by engaging a steering pedal or engaging another throttle control, to achieve the desired output 1104. In some examples, the throttle input 1106 also includes data that can be used to engage the brakes of the AV 100 (e.g., a deceleration control). The steering input 1108 indicates the steering angle, for example, the angle at which the steering control of the AV (e.g., a steering wheel, a steering angle actuator, or other function for controlling the steering angle) should be positioned to achieve the desired output 1104.

[0133] In an embodiment, the controller 1102 receives feedback that is used when adjusting inputs to the throttle and steering. For example, if the AV 100 encounters a disturbance 1110, such as a hill, the AV 100's measured velocity 1112 drops below a desired output rate. In an embodiment, any measured output 1114 is provided to the controller 1102 so that any necessary adjustments can be made, for example, based on the difference 1113 between the measured velocity and the desired output. The measured outputs 1114 include measured position 1116, measured velocity 1118 (including velocity and heading), measured acceleration 1120, and other outputs measurable by the AV 100's sensors.

[0134] In an embodiment, information about the disturbance 1110 is pre-detected, for example, by a sensor such as a camera or a LiDAR sensor, and provided to the predictive feedback module 1122. The predictive feedback module 1122 then provides information to the controller 1102 that the controller 1102 can use to adjust accordingly. For example, if the sensors of the AV 100 detect ("see") a hill, the controller 1102 can use this information to prepare to engage the throttle at an appropriate time to avoid significant deceleration.

[0135] Figure 12 1 is a block diagram 1200 illustrating inputs, outputs, and components of the controller 1102 according to one or more embodiments. The controller 1102 includes a rate analyzer 1206 that influences the operation of a throttle / brake controller 1204. For example, the rate analyzer 1206 instructs the throttle / brake controller 1204 to accelerate or decelerate using the throttle / brake 1206 based on, for example, feedback received by the controller 1102 and processed by the rate analyzer 1202.

[0136] Controller 1102 also has a lateral tracking controller 1208 that affects the operation of a steering wheel controller 1210. For example, lateral tracking controller 1208 instructs steering wheel controller 1210 to adjust the position of a steering angle actuator 1212 based on, for example, feedback received by controller 1102 and processed by lateral tracking controller 1208.

[0137] The controller 1102 receives several inputs used to determine how to control the throttle / brakes 1206 and the steering angle actuator 1212. The planning module 404 provides information used by the controller 1102, for example, to select a heading for the AV 100 to begin operation and to determine which road segment to traverse when the AV 100 reaches an intersection. The positioning module 408 provides information describing the current location of the AV 100 to the controller 1102, for example, so that the controller 1102 can determine whether the AV 100 is in the expected location based on how the throttle / brakes 1206 and the steering angle actuator 1212 are being controlled. In embodiments, the controller 1102 receives information from other inputs 1214, such as information received from a database, a computer network, or the like.

[0138] Adaptive point cloud generation for autonomous vehicles

[0139] Figure 13 is a diagram illustrating an example of adaptive point cloud generation for AV 100 according to one or more embodiments. Figure 1AV 100 is shown and described in more detail. AV 100 receives a plurality of LiDAR points 1304, 1308, 1312, 1316 from a LiDAR system of AV 100 using at least one processor. The processor and reference Figure 1 The processor 146 shown and described in more detail is the same or similar. For example, the processor 146 may be the same as the processor 146 described in more detail. Figure 4 The planning module 404 or a portion of the perception module 402 is shown and described in more detail. The LiDAR system 602 includes at least one LiDAR sensor 123. Figure 6 The LiDAR system 602 and the processing for receiving LiDAR points from the LiDAR sensor are shown and described in greater detail. Figure 1 The LiDAR sensor 123 is shown and described in greater detail.

[0140] The plurality of LiDAR points 1304, 1308, 1312, 1316 represent at least one object in the environment in which the AV 100 is traveling. Examples of such objects are reference Figure 1 The vehicle 193 is shown and described in greater detail. Figure 1 The environment 190 shown and described in more detail is the same or similar. The LiDAR sensor 123 plays an important role in object recognition, segmentation, and localization. However, the raw (unprocessed) LiDAR points acquired using the LiDAR sensor 123 may sometimes contain redundant information and a non-uniform density distribution. Therefore, the density of LiDAR points 1304, 1316 closer to the LiDAR system 602 may be greater than the density of LiDAR points 1308, 1312 farther away from the LiDAR system 602. The embodiments disclosed herein reduce the density variation of the LiDAR data acquired by the LiDAR system 602 while maintaining the accuracy of downstream systems (e.g., a planning module) during operation of the AV 100. Reference Figure 4 An example planning module 404 is shown and described in further detail.

[0141] In some embodiments, the processor determines a Euclidean distance d1 for each LiDAR point (e.g., LiDAR point 1304) in the plurality of LiDAR points 1304, 1308, 1312, 1316. The Euclidean distance d1 of the LiDAR point 1304 refers to the Euclidean distance between the LiDAR point 1304 and the LiDAR system 602. LiDAR points (e.g., LiDAR points 1308, 1312) located at a greater distance than other LiDAR points are more sparse. Therefore, the LiDAR points 1308, 1312 that are farther away carry more information. For example, the Euclidean distance d2 of the LiDAR point 1308 refers to the Euclidean distance between the LiDAR point 1308 and the LiDAR system 602. Figure 13 In the scan line shown, the distance between two consecutive LiDAR points 1304, 1316 (e.g., distance e1) is proportional to the distance d1 from the LiDAR system 602 to the object (e.g., vehicle 193). Figure 13 As shown, e1 = tanΘ × d1, where Θ represents the angle between the two scan lines corresponding to LiDAR points 1304 and 1316. Therefore, since tanΘ ≈ Θ, e1 ≈ Θ × d1. Similarly, e2 = tanΘ × d2, where Θ represents the angle between the two scan lines corresponding to LiDAR points 1308 and 1312. Therefore, since tanΘ ≈ Θ, e2 ≈ Θ × d2.

[0142] The processor compares the Euclidean distance d1 of each LiDAR point (e.g., LiDAR point 1304) to the corresponding sampled Euclidean distance d from the standard normal distribution. u In some embodiments, the corresponding sampled Euclidean distance d u It takes values ​​between 0 and d max In this paper, d max Refers to the range of the LiDAR system 602, sometimes referred to as the "maximum unambiguous measurement range." max Limited by the characteristics of the emitted light 604 from the LiDAR system 602. Figure 6 Emitted light 604 is shown and described in greater detail.

[0143] In some embodiments, the processor determines the measurement range d of the LiDAR system 602 based on the speed of light (c) and the pulse repetition frequency (PRF) of the LiDAR sensor 123. max LiDAR system 602 emits light 604 and receives an echo from a target object (e.g., vehicle 193) each time it sends a pulse of light 604. The higher the PRF, the more objects can be mapped. "Mapping" an object (e.g., vehicle 193) means generating a three-dimensional (3D) representation of the object based on the light 604 that bounces back from the object. The reflected light 604 is used to create a point cloud (3D representation) representing the object.

[0144] The emitted light 604 of the LiDAR sensor 123 travels at the speed of light c. As a result, the distance between the LiDAR sensor 123 and the target object (usually represented by d i ) by d i = c x t / 2, where t represents the time between transmitting the light 604 and receiving the echo. This time (t) is divided by 2 because the light 604 must travel a distance d in both directions. iWhen pulses of LiDAR light 604 repeat, to avoid ambiguity in the measurement of the light, each pulse of light 604 should return to the LiDAR sensor 123 before the next pulse is emitted. For a given PRF, this time limit can be determined as 1 / PRF. Therefore, using the speed of light (c), the maximum distance that light 604 can travel is determined as (c / PRF), and the maximum distance between the LiDAR sensor 123 and the target object (maximum unambiguous measurement range) is determined as d max =1 / 2×c / PRF.

[0145] In some embodiments, the Euclidean distance of the corresponding samples is a constant k. For example, as shown in FIG. Figure 13 As shown, the AV 100 receives LiDAR points 1304, 1308, 1312, 1316 from the LiDAR system 602. The processor determines the Euclidean distance d for each LiDAR point (e.g., LiDAR point 1304). i The processor may determine the likelihood of adding the LiDAR point 1304 to the output point cloud based on the density change of the plurality of LiDAR points 1304, 1308, 1312, 1316. Figure 14 An example output point cloud 1408 is shown and described in further detail. For example, a likelihood of retaining a LiDAR point is determined based on distribution characteristics of the plurality of LiDAR points 1304, 1308, 1312, 1316 using statistical processing.

[0146] For each LiDAR point, the processor calculates the distance d based on its Euclidean distance. i In some embodiments, the processor calculates the Euclidean distance d of each LiDAR point. i Compared with the constant k, the LiDAR points farther away are sparser and carry more information. Therefore, the probability of retaining a LiDAR point increases with its Euclidean distance d. i increases with the increase of i Until it is equal to the constant k. i When k is equal to or greater than the constant k, the probability of retaining the LiDAR point is 1. Figures 15 to 23 The experimental results shown are used to determine and adjust the value of the constant k. For example, the constant k can be set to (d max / 2)、(d max / 4) or some other value. The value of the constant k can also be adjusted based on the variation of computational runtime and the number of LiDAR points expected in the output point cloud. For example, the larger the value of the constant k, the fewer LiDAR points will appear in the output point cloud. As a result, the density of the output point cloud for AV operation and the complexity of processing the output point cloud are reduced. iIf k is less than the constant k, the processor does not include the LiDAR point in the output point cloud.

[0147] In other embodiments, as shown in FIG. Figure 15 As shown and described in more detail, the corresponding sampled Euclidean distance is a random variable between 0 and 1. In this embodiment, the corresponding sampled Euclidean distance is the ratio of the Euclidean distance R d The processor determines the Euclidean distance ratio R of each LiDAR point (eg, LiDAR point 1304). d . Euclidean distance ratio R d is the distance d (between the LiDAR system 602 and the LiDAR point 1304) i Compared with LiDAR range (d max ) ratio. The processor converts the Euclidean distance ratio (R d =d i / d max ) and the corresponding sampled Euclidean distance ratio R from the standard normal distribution u Compare. Euclidean distance R d is a measure of how far each LiDAR point 1304 is from the LiDAR sensor 123 that measured it. u is a random variable between 0 and 1 that reflects the Gaussian distribution of the distance ratio.

[0148] In response to the Euclidean distance (typically represented by d i represents) is less than the corresponding sampling Euclidean distance d u , the processor removes the LiDAR point 1304 from the plurality of LiDAR points 1304, 1308, 1312, 1316 to generate an output point cloud. Figure 14 An example output point cloud 1408 is shown and described in more detail. The described embodiment reduces the computational complexity of processing the plurality of LiDAR points 1304, 1308, 1312, 1316 by downsampling and filtering the plurality of LiDAR points 1304, 1308, 1312, 1316 as described. u Individual LiDAR points that are further away from the LiDAR sensor 123 are aggregated into an output point cloud. The processor operates the AV 100 based on the output point cloud. For example, the processor may be a reference Figure 4 A portion of the control module 406 is shown and described in more detail. The generated output point cloud is also a reduced density point cloud suitable for further processing.

[0149] Figure 141404, 1408 is a diagram illustrating example LiDAR point clouds 1404, 1408 for an AV according to one or more embodiments. Figure 1 、 Figure 13 The AV 100 is the same as or similar to the AV 100 shown and described in more detail. The AV receives an input set of LiDAR points (e.g., LiDAR points 1412, 1416) from the AV's LiDAR system. The LiDAR system is similar to the reference Figure 6 、 Figure 13 The input set of LiDAR points is the same as or similar to the LiDAR system 602 shown and described in more detail. Figure 14 Point cloud 1404 is shown. Point cloud 1404 is a raw point cloud from a multi-channel LiDAR scan. Point cloud 1404 acquired using a LiDAR system may have redundant information and a non-uniform density distribution. For example, LiDAR points 1412 farther from LiDAR system 602 are more sparsely populated than LiDAR points 1416 closer to LiDAR system 602. Consequently, LiDAR points 1416 closer to the LiDAR system are denser. Consequently, point cloud 1404 and LiDAR points 1412 and 1416 exhibit a first density variation. Figure 14 The symbol d shown max Refers to the reference Figure 13 The LiDAR range is described in more detail.

[0150] In response to a Euclidean distance d of a LiDAR point (eg, LiDAR point 1416 ) in the plurality of LiDAR points 1412 , 1416 , i is smaller than the corresponding sampled Euclidean distance from the standard normal distribution (d u ), the AV removes the LiDAR point 1416 from the plurality of LiDAR points 1412, 1416 to generate the output point cloud 1408. Figure 13 Describing the Euclidean distance d in more detail i and the corresponding sampled Euclidean distance d u .

[0151] In the point cloud 1408, the density of the LiDAR points 1420 that are farther away from the LiDAR system is closer to the density of the LiDAR points 1424 that are closer to the LiDAR system. Therefore, the plurality of LiDAR points 1412, 1416 (point cloud 1404) have a first density variation, and the point cloud 1408 has a second density variation that is smaller than the first density variation. In some embodiments, generating the point cloud 1408 includes downsampling the received LiDAR points 1412, 1416 by the AV to generate the second density variation. Because most of the LiDAR points (e.g., LiDAR point 1416) are closer to the LiDAR sensor of the LiDAR system, the closer LiDAR point 1416 has more redundant information. The LiDAR sensor is closer to the reference LiDAR system. Figure 1 The LiDAR sensor 123 is the same as or similar to the LiDAR sensor 123 shown and described in greater detail. The plurality of LiDAR points 1412, 1416 received from the LiDAR system has a first density distribution that has greater variation. This is because the plurality of LiDAR points 1412, 1416 includes more densely spaced LiDAR points 1416 located closer to the LiDAR system and more sparsely spaced LiDAR points 1412 located farther from the LiDAR system.

[0152] In some embodiments, the removal of LiDAR point 1416 from the plurality of LiDAR points 1412, 1416 is based on a first density variation. For example, most LiDAR points (e.g., LiDAR point 1416) are closer to the LiDAR sensor; therefore, the closer LiDAR points 1416 have more redundant information. Because the density of the LiDAR points has been smoothed by downsampling, the subset of the plurality of LiDAR points 1412, 1416 retained as the point cloud 1408 has a second density variation that is less than the first density variation.

[0153] In some embodiments, the AV segments the point cloud 1408 to identify an object based on the second density change. Figure 1 The vehicle 193 shown and described in more detail may be the same or similar. For example, the point cloud 1408 may be segmented into foreground and background. LiDAR points 1420, 1424 having similar characteristics may be segmented into homogeneous regions for localization and identification of objects, classification, and feature extraction. For example, the AV may construct a graph from the point cloud 1408 and cluster the graph to produce segmentations using smoothness or concavity along boundaries. The AV may further operate to avoid collisions with objects based on the segmented point cloud 1408. Object classification is performed by comparing the point cloud 1408 to the reference point cloud 1408. Figure 4 The same or similar perception module as shown and described in more detail is used for path planning (to avoid collisions) by the same or similar perception module as described in reference 402. Figure 4The same or similar planning modules as those shown and described in greater detail are performed by the planning module 404 .

[0154] In some embodiments, the AV reduces the amount of noise in the point cloud 1408 based on the second density variation. For example, statistical noise filtering (e.g., kernel clustering) can be used to smooth outliers from a noisy point cloud based on the second density variation. LiDAR points representing noise will have a lower density than non-noisy LiDAR points and can therefore be removed. In some embodiments, the AV smooths the point cloud 1408 based on the second density variation. For example, a projection operator can be used on the point cloud 1408 to project a subset of the point cloud 1408 onto a new point cloud to reduce noise. The second density variation is incorporated into the operator to produce a uniformly distributed new point cloud for operation of the AV using the planning module and the control module. The control module is connected to the reference Figure 4 The control module 406 is the same or similar to that shown and described in greater detail.

[0155] Figure 15 An example process for adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The AV 100 is the same as or similar to the AV 100 shown and described in more detail. in The original input point cloud P in With reference Figure 14 The point cloud 1404 shown and described in more detail is the same or similar. in The plurality of LiDAR points received from the LiDAR system of the AV are compared with the reference Figure 14 The LiDAR points 1412, 1416 shown and described in more detail are the same or similar. Figure 6 The same or similar LiDAR system 602 is shown and described in more detail. Figure 15 As shown, each of the multiple LiDAR points is represented by p i In some embodiments, the LiDAR range d max Too Figure 15 In other embodiments, using reference Figure 13 The method described above determines the LiDAR range d max . Figure 15 The output of the example process shown is produced by P out The filtered point cloud represented by . out With reference Figure 14 The output point cloud 1408 is the same or similar to that shown and described in greater detail.

[0156] For the original input point cloud P inEach LiDAR point p in i ,AV determines the Euclidean distance ratio R d . Euclidean distance ratio R d Yes (LiDAR system and LiDAR point p i The distance d between i With LiDAR range d max Therefore, if Figure 15 As shown, R d =d i / d max . Euclidean distance ratio R d is the LiDAR point p i A measure of how far away a LiDAR sensor is from the one that is measuring it. Figure 1 The same or similar LiDAR sensor 123 is shown and described in greater detail.

[0157] AV generates a random number R with a value between 0 and 1 u Random number R u The sampling ratio R represents the ratio of the Euclidean distances from the standard normal distribution. u is a random variable between 0 and 1 that reflects the Gaussian distribution of the distance ratio. d and R u The value of the LiDAR point p is compared by distance i Downsampling is performed so that LiDAR points closer to the LiDAR system are more likely to be removed than LiDAR points farther away. LiDAR points farther away are sparser and, therefore, carry more information.

[0158] In response to R d Greater than or equal to R u , the LiDAR point p i Added to the generated output point cloud P out Therefore, since all the raw input LiDAR points p are processed i The computational cost of P may be very high, so the input point cloud P in Downsampling and filtering are performed. u The LiDAR point p whose Euclidean distance is farther away from the LiDAR sensor is given by i are clustered into a subset of LiDAR points to generate the point cloud P out . The ratio is given by the random variable R u The Euclidean distance given is closer to the LiDAR point p of the LiDAR sensor i Remove. The generated point cloud P out For further processing and manipulation of the AV.

[0159] Figure 16 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an AV according to one or more embodiments is shown. In general, based on a single scan LiDAR point cloud, and thereafter as described herein Figure 15 Generates data with different settings (e.g., different LiDAR ranges, output point cloud sizes, or different runtimes) Figures 16 to 19 .AV and Reference Figure 1 The same or similar AV 100 shown and described in more detail. A single LiDAR scan can be used to trade off runtime and accuracy. Figure 16 The example point clouds generated in the experiment used a LiDAR range of 20 meters (m). max The number of downsampled LiDAR points (output point cloud) is 100,000, and the running time for the experiment is 5000ms (5 seconds). Output point cloud and reference Figure 14 The point cloud 1408 shown and described in greater detail is the same or similar.

[0160] Figure 17 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV100 as shown and described in more detail. Figure 17 The example point clouds generated in the experiment use a LiDAR range of 60m (d max The number of downsampled LiDAR points (output point cloud) is 30,000, and the running time for the experiment is 600ms. Figure 14 The point cloud 1408 shown and described in greater detail is the same or similar.

[0161] Figure 18 An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV 100 as shown and described in more detail. Figure 18 The example point clouds generated in the experiment use a LiDAR range of 200m (d max The number of downsampled LiDAR points (output point cloud) is 7,000, and the running time for the experiment is 165ms. Figure 14 The point cloud 1408 shown and described in greater detail is the same or similar.

[0162] Figure 19An example point cloud generated using a single LiDAR scan and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV 100 as shown and described in more detail. Figure 19 The example point clouds generated in the experiment use a LiDAR range of 500m (d max The number of downsampled LiDAR points (output point cloud) is 2,000, and the running time for the experiment is 60ms. Figure 14 The point cloud 1408 shown and described in more detail is the same or similar. Figures 16 to 19 As shown, an efficient trade-off between runtime and accuracy is achieved using the disclosed embodiments.

[0163] Figure 20 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figures 20 to 23 is based on using the accumulated LiDAR scans and Figure 15 Adaptive point cloud generation processing using different settings (e.g., different filter ranges, different downsampled LiDAR points, and different runtimes). Figure 1 The same or similar to the AV 100 shown and described in more detail. The accumulated LiDAR scans can be used to increase the resolution of the LiDAR sensor along its sparse axis. Using the accumulated LiDAR scans, the information in the output point cloud is preserved (accuracy) and greater efficiency (run time) is achieved. The output point cloud is compared to the reference Figure 14 The point cloud 1408 shown and described in more detail is the same or similar. Figure 20 The example point clouds generated in the experiment use a LiDAR range of 20m (d max ). The number of downsampled LiDAR points (output point cloud) is 100,000, and the running time for the experiment is 5000ms (5 seconds).

[0164] Figure 21 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV 100 as shown and described in more detail. Figure 21 The example point clouds generated in the experiment use a LiDAR range of 60m (d max The number of downsampled LiDAR points (output point cloud) is 30,000, and the running time for the experiment is 600ms. Figure 14The point cloud 1408 shown and described in greater detail is the same or similar.

[0165] Figure 22 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV 100 as shown and described in more detail. Figure 22 The example point clouds generated in the experiment use a LiDAR range of 200m (d max The number of downsampled LiDAR points (output point cloud) is 7,000, and the running time for the experiment is 165ms. Figure 14 The point cloud 1408 shown and described in greater detail is the same or similar.

[0166] Figure 23 An example point cloud generated using accumulated LiDAR scans and adaptive point cloud generation for an AV according to one or more embodiments is shown. Figure 1 The same or similar AV 100 as shown and described in more detail. Figure 23 The example point clouds generated in the experiment use a LiDAR range of 500m (d max The number of downsampled LiDAR points (output point cloud) is 2,000, and the running time for the experiment is 60ms. Figure 14 The point cloud 1408 shown and described in more detail is the same or similar. Figures 20 to 23 As shown, an efficient trade-off between runtime and accuracy is achieved using the disclosed embodiments. The embodiments disclosed herein provide probabilistic methods for improving the overall robustness of LiDAR point clouds without introducing many parameters. These methods are efficient and have a linear time complexity of O(n), which is suitable for real-time point cloud processing by autonomous vehicles. The disclosed methods are widely applicable to localization, perception, and prediction tasks based on LiDAR point clouds. These methods also provide effective and efficient pre-processing steps for applications such as point cloud segmentation, denoising, and smoothing.

[0167] Figure 24 is a flow chart illustrating a process 2400 for adaptive point cloud generation for an AV according to one or more embodiments. Figure 1 The AV 100 is the same as or similar to the AV 100 shown and described in more detail. Figure 24The processing is performed by the AV. In other embodiments, a separate entity (e.g., a perception module or a planning module) performs some or all of the steps of the processing. Likewise, embodiments may include different and / or additional steps, or perform the steps in a different order. The perception module and the planning module may be respectively associated with the reference Figure 4 The perception module 402 and planning module 404 shown and described in greater detail are the same or similar.

[0168] The AV receives (2404) a plurality of LiDAR points from the AV's LiDAR system using at least one processor. The processor and the reference Figure 1 The processor 146 is the same as or similar to the processor 146 shown and described in more detail. Figure 14 The LiDAR points 1404 shown and described in more detail are the same or similar. Figure 6 An example LiDAR system 602 and a process for receiving LiDAR points (LiDAR data) from the LiDAR system are shown and described in greater detail. The plurality of LiDAR points represent at least one object (e.g., a vehicle) in the environment in which the AV 100 is traveling. Figure 1 An example vehicle 193 and an example environment 190 are shown and described in greater detail. Thus, a LiDAR system plays an important role in localizing an object. In some embodiments, the plurality of LiDAR points have a first density variation. Consequently, the plurality of LiDAR points acquired using the LiDAR system may have redundant information and a non-uniform density distribution.

[0169] The AV uses a processor to determine (2408) the Euclidean distance d of each LiDAR point i . refer to Figure 13 An example Euclidean distance d1 of an example LiDAR point 1304 is shown and described in more detail. i is the distance from the LiDAR system to the LiDAR point. In some embodiments, the LiDAR system includes at least one LiDAR sensor. Figure 1 An example LiDAR sensor 123 of a LiDAR system is shown and described in greater detail. The processor determines a measurement range of the LiDAR system based on the speed of light and the pulse repetition frequency of the LiDAR sensor. The processor 146 compares the measurement range of the LiDAR system to the distance from the LiDAR system to the object (e.g., d i ) for comparison.

[0170] The AV 100 uses a processor to calculate the Euclidean distance d of each LiDAR point. i The corresponding sampled Euclidean distance d from the standard normal distribution u Compare (2412). In some embodiments, the corresponding sample Euclidean distance du is a Gaussian-distributed random variable reflecting the distance. The processor can also generate the corresponding sampled Euclidean distance d u As a random or pseudo-random number.

[0171] Euclidean distance d corresponding to the LiDAR point i Less than the corresponding sampling Euclidean distance d u , the AV uses a processor to remove the LiDAR point from the plurality of LiDAR points (2416) to generate an output point cloud. The output point cloud is compared with the reference Figure 14 The output point cloud may be the same as or similar to the example point cloud 1408 shown and described in greater detail. In some embodiments, the output point cloud has a second density variation that is less than the first density variation. Generating the output point cloud may include downsampling the plurality of LiDAR points to generate the second density variation. Removing the LiDAR point from the plurality of LiDAR points is based on the first density variation. The processor may determine a likelihood of adding the LiDAR point to the output point cloud based on the first density variation.

[0172] The AV operates (2420) the AV based on the output point cloud using a processor. The generated output point cloud is a point cloud with reduced density and is also suitable for further processing. The AV 100 is operated using a control module. Reference Figure 4 An example control module 406 is shown and described in greater detail. For example, as shown in FIG. Figure 13 and Figure 14 As shown and described in more detail, the processor segments the output point cloud based on the second density variation to identify the object. The AV is further operated based on the segmented point cloud to avoid collision with the object. The processor can reduce the amount of noise in the output point cloud based on the second density variation. The processor can smooth the point cloud based on the second density variation.

[0173] In the previous 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 only and exclusive indication of the scope of the invention, and what the applicant expects to be the scope of the invention, is the literal and equivalent scope of the claims issued from this application in the specific form of the claims of the authorization announcement, including any subsequent amendments. Any definition of terms explicitly 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 steps or entities previously described.

Claims

1. A method for a vehicle, comprising: receiving, by at least one processor of the vehicle, a plurality of LiDAR points from a LiDAR system of the vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determining, by the at least one processor, a Euclidean distance ratio between each of the plurality of LiDAR points and the LiDAR system, wherein the Euclidean distance ratio is a ratio of a distance between the LiDAR system and the LiDAR point to a LiDAR range; comparing, with the at least one processor, a Euclidean distance ratio of each LiDAR point in the plurality of LiDAR points to a corresponding sampled Euclidean distance ratio from a standard normal distribution, wherein the sampled Euclidean distance ratios cause LiDAR points closer to the LiDAR system to be more likely to be removed than LiDAR points farther from the LiDAR system; In response to a Euclidean distance ratio of each LiDAR point in the plurality of LiDAR points being less than the corresponding sampled Euclidean distance ratio, removing, by the at least one processor, the LiDAR point from the plurality of LiDAR points to generate a point cloud; and The vehicle is operated, via the at least one processor, based on the point cloud.

2. The method according to claim 1, wherein The plurality of LiDAR points have a first density variation, and the point cloud has a second density variation that is less than the first density variation.

3. The method according to claim 2, wherein: Generating the point cloud includes downsampling, by the at least one processor, the plurality of LiDAR points to provide the second density variation.

4. The method according to claim 2, wherein: Removing the LiDAR point from the plurality of LiDAR points is based on the first density change.

5. The method according to any one of claims 2 to 4, further comprising: Determining, by the at least one processor, a likelihood of adding the LiDAR point to the point cloud based on the first density change.

6. The method according to any one of claims 1 to 4, further comprising: A measurement range of the LiDAR system is compared, by the at least one processor, with a distance from the LiDAR system to the at least one object.

7. The method according to claim 6, wherein: The LiDAR system includes at least one LiDAR, and the method further includes: determining, by the at least one processor, a measurement range of the LiDAR system based on the speed of light and a pulse repetition frequency of the at least one LiDAR.

8. The method according to any one of claims 1 to 4, further comprising: The corresponding sampled Euclidean distance ratio is determined by the at least one processor as a random number.

9. The method according to any one of claims 2 to 4, further comprising: The point cloud is segmented, by the at least one processor, based on the second density variation to identify the at least one object.

10. The method according to claim 9, wherein: Operating the vehicle to avoid collision with the at least one object is also based on the segmented point cloud.

11. The method according to any one of claims 2 to 4, further comprising: An amount of noise in the point cloud is reduced, by the at least one processor, based on the second density variation.

12. The method according to any one of claims 2 to 4, further comprising: The point cloud is smoothed, by the at least one processor, based on the second density variation.

13. A vehicle comprising: at least one computer processor; as well as at least one non-transitory storage medium storing instructions that, when executed by the at least one computer processor, cause the at least one computer processor to: receiving a plurality of LiDAR points from a LiDAR system of the vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determining a Euclidean distance ratio between each of the plurality of LiDAR points and the LiDAR system, wherein the Euclidean distance ratio is a ratio of a distance between the LiDAR system and the LiDAR point to a LiDAR range; comparing a Euclidean distance ratio for each LiDAR point in the plurality of LiDAR points to a corresponding sampled Euclidean distance ratio from a standard normal distribution, wherein the sampled Euclidean distance ratios cause LiDAR points closer to the LiDAR system to be more likely to be removed than LiDAR points farther from the LiDAR system; In response to a Euclidean distance ratio of each LiDAR point in the plurality of LiDAR points being less than the corresponding sampled Euclidean distance ratio, removing the LiDAR point from the plurality of LiDAR points to generate a point cloud; and The vehicle is operated based on the point cloud.

14. The vehicle according to claim 13, wherein: The plurality of LiDAR points have a first density variation, and the point cloud has a second density variation that is less than the first density variation.

15. The vehicle according to claim 14, wherein: The instructions for generating the point cloud cause the at least one computer processor to downsample the plurality of LiDAR points to generate the second density variation.

16. The vehicle of claim 14, wherein: Causing the at least one computer processor to remove the LiDAR point from the plurality of LiDAR points is based on the first density change.

17. At least one non-transitory storage medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to: receiving a plurality of LiDAR points from a LiDAR system of a vehicle, the plurality of LiDAR points representing at least one object in an environment in which the vehicle is traveling; determining a Euclidean distance ratio between each of the plurality of LiDAR points and the LiDAR system, wherein the Euclidean distance ratio is a ratio of a distance between the LiDAR system and the LiDAR point to a LiDAR range; comparing a Euclidean distance ratio for each LiDAR point in the plurality of LiDAR points to a corresponding sampled Euclidean distance ratio from a standard normal distribution, wherein the sampled Euclidean distance ratios cause LiDAR points closer to the LiDAR system to be more likely to be removed than LiDAR points farther from the LiDAR system; In response to a Euclidean distance ratio of each LiDAR point in the plurality of LiDAR points being less than the corresponding sampled Euclidean distance ratio, removing the LiDAR point from the plurality of LiDAR points to generate a point cloud; and The vehicle is operated based on the point cloud.

18. The at least one non-transitory storage medium according to claim 17, wherein: The plurality of LiDAR points have a first density variation, and the point cloud has a second density variation that is less than the first density variation.

19. The at least one non-transitory storage medium of claim 18, wherein: The instructions for generating the point cloud cause the at least one computing device to downsample the plurality of LiDAR points to generate the second density variation.

20. The at least one non-transitory storage medium of claim 18, wherein: Causing the at least one computing device to remove the LiDAR point from the plurality of LiDAR points is based on the first density change.

21. A computer program product comprising a program for causing a computer to execute the method according to any one of claims 1 to 12.

Images