Method for a vehicle, autonomous vehicle and storage medium

Abstract

The present invention relates to methods for vehicles, autonomous vehicles, and storage media. Techniques for planning routes for autonomous vehicles are described, among other things. As an example, a set of candidate constraints for a section of a road that a vehicle is to traverse is obtained. A plurality of homotopies are determined, each homotopy comprising a different corresponding combination of the candidate constraints. For each homotopy, a first prediction of the movement of the vehicle is generated according to a first accuracy, and it is determined that the vehicle is able to traverse the section of the road according to a subset of the homotopy. In addition, a plurality of trajectories are determined according to the subset of the homotopy, including generating at least one second prediction of the movement of the vehicle according to a second accuracy greater than the first accuracy, and selecting one of the trajectories.

Description

Technical Field

[0001] This specification relates to route planning for autonomous vehicles. Background Art

[0002] A software stack for an autonomous vehicle (AV) may implement a planning module that generates a plurality of candidate trajectories along which the AV may traverse an environment (e.g., through a 4-way intersection). The trajectories may be generated based on a map, a current physical state of the AV (e.g., current location, speed, heading, etc.), and one or more objects detected by the AV. Summary of the invention

[0003] One aspect of the present invention relates to a method for a vehicle, comprising: using at least one processor to obtain a set of candidate constraints for a road segment that the vehicle is to traverse; using the at least one processor to determine a plurality of homologs, wherein each of the homologs includes a different corresponding combination of the candidate constraints for traversing the road segment; for each homology: using the at least one processor to generate a first prediction of the movement of the vehicle on the road segment according to a first accuracy; using the at least one processor and based on the first prediction, determining that the vehicle is able to traverse the road segment according to a subset of the homologs; using the at least one processor to determine a plurality of trajectories for the road segment according to the subset of the homologs, wherein determining the plurality of trajectories includes: generating at least one second prediction of the movement of the vehicle on the road segment according to a second accuracy, the second accuracy being greater than the first accuracy; using the at least one processor to select one of the trajectories; and using the at least one processor to send instructions to the control circuit of the vehicle to traverse the road segment according to the selected trajectory.

[0004] Another aspect of the present invention relates to an autonomous vehicle, comprising: one or more computer processors; one or more non-transitory storage media storing instructions, which, when executed by the one or more computer processors, enable the above method to be performed.

[0005] Yet another aspect of the present invention relates to one or more non-transitory storage media storing instructions that, when executed by one or more computing devices, cause the above-described method to be performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 An example of an AV with autonomous capabilities is shown.

[0007] Figure 2 An example "cloud" computing environment is shown.

[0008] Figure 3 A computer system is shown.

[0009] Figure 4A An example architecture of an AV is shown.

[0010] Figure 4B An example planning module is shown.

[0011] Figure 5 Shows examples of inputs and outputs that a perception module can use.

[0012] Figure 6 An example of a LiDAR system is shown.

[0013] Figure 7 The LiDAR system is shown in operation.

[0014] Figure 8 Additional details of the operation of the LiDAR system are shown.

[0015] Fig. 9 Block diagram showing the relationship between the inputs and outputs of the planning module.

[0016] Fig.10 Shows the directed graph used in path planning.

[0017] Fig.11 A block diagram showing the inputs and outputs of the control module.

[0018] Fig.12 A block diagram showing the inputs, outputs, and components of the controller.

[0019] Fig.13 An example process for generating trajectories using a homotopy-based approach is illustrated.

[0020] Fig.14 An example decision diagram is shown.

[0021] Figures 15A to 15F A practical example of using a decision diagram to assess the feasibility of a homotopy is shown.

[0022] Fig.16 A flow chart illustrating an example process for controlling the operation of an AV. DETAILED DESCRIPTION

[0023] In the following description, for the purpose of explanation, many 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 implemented 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.

[0024] In the accompanying drawings, for ease of description, a specific arrangement or order of schematic elements (such as those representing devices, modules, instruction blocks, and data elements) is shown. However, it should 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 schematic elements in the accompanying drawings is not intended to mean that such elements are required in all embodiments, nor is it intended to mean that the features represented by such elements cannot be included in some embodiments or cannot be combined with other elements in some embodiments.

[0025] 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 there is no such connecting element and 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 make the present disclosure vague. In addition, for the convenience of illustration, a single connecting element is used to represent multiple connections, relationships or associations between elements. For example, if the connecting element represents the communication of signal, data or instruction, it will be understood by those skilled in the art that this element represents one or more signal paths (for example, bus) that may be needed to affect the communication.

[0026] 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 implemented without these specific details. In other cases, well-known methods, procedures, components, circuits, and networks are not described in detail in order not to unnecessarily obscure aspects of the embodiments.

[0027] Several features described below can each be used independently of one another or in combination with 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 a title is provided, information related to a specific title but not found in the section with that title may also be found elsewhere in this specification. This article describes an embodiment according to the following summary:

[0028] 1. General Overview

[0029] 2. System Overview

[0030] 3.AV Architecture

[0031] 4.AV input

[0032] 5.AV Planning

[0033] 6.AV control

[0034] 7. Homotopy-based planner

[0035] General Overview

[0036] The disclosed embodiment of the AV planning module uses a "homotopy" based planning method to determine one or more trajectories of the AV. As an example, the planning module (e.g., Figure 4A and 4B ) can determine a route for the AV and determine several candidate constraints for traversing one or more road segments of the route. In addition, the planning module can determine feasible homotopies of these constraints (e.g., combinations of constraints that the AV can feasibly comply with when traversing the one or more road segments), generate trajectories for each of the feasible homotopies, and select one of the trajectories for the AV to execute. In some implementations, the techniques described herein can be performed with respect to a subset of the road segments that make up the route. In some implementations, the techniques described herein can be performed with respect to all road segments that make up the route.

[0037] Some advantages of these techniques include reducing the computational resources required to determine the trajectory of the AV. For example, in some implementations, the planning module can determine the trajectory in a brute force manner by the following process: (i) generating a large number of candidate trajectories (e.g., considering every possible trajectory that the AV may take along the route), (ii) evaluating each of the candidate trajectories, and (iii) selecting a particular candidate trajectory for execution. However, generating and evaluating trajectories across such a large search space (e.g., a search space that includes every possible trajectory) can be computationally expensive. In order to reduce the search space, the planning module can identify a subset of the search space that corresponds to feasible homology (e.g., a combination of constraints that the AV can safely comply with while traversing the route), and generate candidate trajectories only for that subset. Thus, the search space can be significantly reduced.

[0038] System Overview

[0039] Figure 1 An example of an AV 100 having autonomous capabilities is shown.

[0040] As used herein, the term “autonomous capability” refers to a function, feature, or facility that enables a vehicle to partially or fully operate without real-time human intervention, including but not limited to full AV, highly AV, and conditional AV.

[0041] As used herein, an AV is a vehicle with autonomous capabilities.

[0042] As used herein, "vehicle" includes a mode of transport of goods or people. For example, a car, bus, train, airplane, drone, truck, boat, ship, submersible, spacecraft, etc. An unmanned car is an example of a vehicle.

[0043] As used herein, a "track" refers to a path or route that navigates an AV 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 location, or target location. In some examples, a track consists of one or more road segments (e.g., several sections of a road), and each road segment consists of one or more blocks (e.g., a portion of a lane or intersection). In embodiments, a spatiotemporal location corresponds to a real-world location. For example, a spatiotemporal location is a pickup or drop-off location to get people or cargo on or off the vehicle.

[0044] As used herein, "sensor(s)" includes one or more hardware components for detecting information about the environment surrounding the sensor. Some hardware components may include sensing components (e.g., image sensors, biometric sensors), transmission and / or reception 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.

[0045] 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.

[0046] As used herein, a "road" is a physical area that can be traversed by a vehicle and may correspond to a named thoroughfare (e.g., a city street, an interstate highway, etc.) or may 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.) are able to traverse a variety of physical areas that are not particularly suitable for vehicle travel, a "road" may be any physical area that is not formally defined as a thoroughfare by a municipality or other governmental or administrative agency.

[0047] As used herein, a "lane" is a portion of a road that can be traversed by a vehicle. Lanes are sometimes identified based on lane markings. For example, a lane 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, so that one vehicle can pass another vehicle without crossing the lane markings, and thus may be interpreted as a lane that is narrower than the space between lane markings, or as having two lanes between 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 rural areas and trees along avenues, or natural obstacles that should be avoided, for example, in underdeveloped areas). Lanes may also be interpreted independently of lane markings or physical features. For example, a lane may be interpreted based on an arbitrary path without obstacles in an area that would otherwise lack features that would be interpreted as lane boundaries. In an example scenario, an AV may interpret a lane as an obstacle-free portion through a field or open space. In another example scenario, an AV may interpret a lane through a wide (e.g., wide enough for two or more lanes) road that does not have lane markings. In this scenario, the AV may communicate information about the lane to other AVs so that the other AVs may use the same lane information to coordinate path planning between AVs.

[0048] As used herein, "homotopy" refers to a subset of a set of constraints on an AV trajectory that an AV can obey while traversing a particular route.

[0049] As used herein, “feasible” refers to whether the AV can obey the constraints in the homotopy when traveling to the destination.

[0050] “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 above.

[0051] 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, without departing from the scope of the various described embodiments, a first contact may be referred to as a second contact, and similarly, a second contact may be referred to as a first contact. Both the first contact and the second contact are contacts, but they are not the same contact.

[0052] The terms used in the specification of the various embodiments described herein are only used for the purpose of describing specific embodiments 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 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 "include", "comprises", "have" and / or "have" are used in this specification, the stated features, integers, steps, operations, elements and / or components are specifically stated, but the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof are not excluded.

[0053] As used herein, the term "if" is alternatively understood to mean "when" or "at the time" or "in response to determining that" or "in response to detecting," depending on the context. Similarly, the phrases "if it has been determined" or "if [the stated condition or event] has been detected" are alternatively understood to mean "upon determination" or "in response to determining that" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]," depending on the context.

[0054] 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 the operation of the AV. 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 of the AV system is in a system similar to the following about Figure 3 The described cloud computing environment 300 is implemented on the cloud computing environment.

[0055] In general, this document describes technologies applicable to any vehicle with one or more autonomous capabilities, including full AV, highly AV, and conditional AV, such as so-called Level 5, Level 4, and Level 3 vehicles, respectively (see SAE International Standard J3016: Classification and Definition of Terms Relating to Automated Driving Systems for Road-Motor Vehicles, for more details on vehicle autonomy levels). The technologies described in this document are also applicable to partial AV and driver-assist vehicles, such as so-called Level 2 and Level 1 vehicles (see SAE International Standard J3016: Classification and Definition of Terms Relating to Automated Driving Systems for Road-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 use of maps) under certain operating conditions based on processing of sensor inputs. The technologies described in this document can benefit any level of vehicle ranging from fully AV to human-operated vehicles.

[0056] AVs have advantages over vehicles that require human drivers. One advantage is safety. For example, in 2016, the United States experienced 6 million automobile accidents, 2.4 million injuries, 40,000 deaths, and 13 million vehicle crashes, with an estimated social cost of more than $910 billion. From 1965 to 2015, the number of U.S. traffic fatalities has decreased from about 6 to about 1 per 100 million miles traveled, in part due to additional safety measures deployed in vehicles. For example, it is believed that an extra half-second of warning about an impending collision mitigates 60% of front-to-rear collisions. However, passive safety features (e.g., seat belts, airbags) may have reached their limits in improving this number. Therefore, active safety measures such as automatic control of vehicles are a possible next step to improve these statistics. Because human drivers are believed to be the cause of severe pre-crash events in 95% of crashes, automated driving systems have the potential to achieve better safety outcomes by, for example: reliably identifying and avoiding emergency situations better than humans; making better decisions than humans, obeying traffic laws better than humans, and predicting future events better than humans; and reliably controlling a vehicle better than humans.

[0057] refer to Figure 1 , the AV system 120 causes the AV 100 to operate along a trajectory 198, through an environment 190 to a destination 199 (sometimes referred to as a final location), while avoiding objects (e.g., natural obstacles 191, vehicles 193, pedestrians 192, cyclists, and other obstacles) and complying with road rules (e.g., operating rules or driving preferences).

[0058] In an embodiment, the AV system 120 includes a device 101 for receiving and operating commands from a computer processor 146. The term "operating command" is used to refer to an executable instruction (or set of instructions) that causes a vehicle to perform an action (e.g., a driving maneuver). The operating command may include, but is not limited to, instructions for causing the vehicle to start moving forward, stop moving forward, start moving backward, stop moving backward, speed up, slow down, make a left turn, and make a right turn. In an embodiment, the computing processor 146 and 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.

[0059] 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 position, linear and angular velocity and acceleration, and heading (e.g., the direction of the front end of the AV 100) of the AV. Examples of sensors 121 are GPS, an inertial measurement unit (IMU) that measures both linear acceleration and angular rate of the vehicle, wheel rate sensors for measuring or estimating wheel slip, wheel brake pressure or brake torque sensors, engine torque or wheel torque sensors, and steering angle and angular rate sensors.

[0060] In an embodiment, the sensors 121 also include sensors for sensing or measuring properties of the environment of the AV, such as monocular or stereo cameras 122 in the visible, infrared, or thermal (or both) spectrum, LiDAR 123, RADAR, ultrasonic sensors, time-of-flight (TOF) depth sensors, velocity sensors, temperature sensors, humidity sensors, and precipitation sensors.

[0061] In an embodiment, the AV system 120 includes a data storage unit 142 and a memory 144 for storing machine instructions associated with a computer processor 146 or data collected by the sensor 121. In an embodiment, the data storage unit 142 is associated with the following Figure 3 190 . In an embodiment, the memory 144 is similar to the main memory 306 described below. In an embodiment, the data storage unit 142 and the memory 144 store historical, real-time, and / or predictive information about the environment 190. In an embodiment, the stored information includes maps, driving performance, traffic congestion updates, or weather conditions. In an embodiment, data related to the environment 190 is transmitted from the remote database 134 to the AV 100 via a communication channel.

[0062] In an embodiment, the AV system 120 includes a communication device 140 for transmitting measured or inferred properties 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 and devices for wireless communication through point-to-point or ad hoc networks or both. In an embodiment, the communication device 140 communicates 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), vehicle-to-infrastructure (V2I) communications (and in some embodiments, one or more other types of communications) is sometimes referred to as vehicle-to-everything (V2X) communications. V2X communications generally comply with one or more communication standards for communication with and between AVs.

[0063] 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 Figure 2 The communication interface 140 transmits data collected from the sensor 121 or other data related to the operation of the AV 100 to the remote database 134. In an embodiment, the communication interface 140 transmits information related to teleoperation to the AV 100. In some embodiments, the AV 100 communicates with other remote (e.g., "cloud") servers 136.

[0064] In an embodiment, the remote database 134 also stores and transmits digital data (e.g., stores data such as roads and street locations). Such 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.

[0065] In an embodiment, the remote database 134 stores and transmits historical information (e.g., speed and acceleration profiles) related to driving attributes 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.

[0066] 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.

[0067] In an embodiment, the AV system 120 includes a computer peripheral device 132 coupled to the computing device 146 for providing information and reminders to a user of the AV 100 (e.g., an occupant or a remote user) and receiving input from the user. In an embodiment, the peripheral device 132 is similar to the one described below with reference to Figure 3 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.

[0068] In an embodiment, the AV system 120 receives and enforces the privacy level of the occupant, for example, specified by the occupant or stored in a profile associated with the occupant. The privacy level of the occupant determines how to permit the use of specific information associated with the occupant (e.g., occupant comfort data, biometric data, etc.) stored in the occupant profile and / or stored on the cloud server 136 and associated with the occupant profile. In an embodiment, the privacy level specifies specific information associated with the occupant that is deleted once the ride is completed. In an embodiment, the privacy level specifies specific information associated with the occupant and identifies one or more entities authorized to access the information. Examples of designated entities authorized to access information may include other AVs, third-party AV systems, or any entity that can potentially access the information.

[0069] The privacy level of an occupant may be specified at one or more levels of granularity. In an embodiment, the privacy level identifies specific information to be stored or shared. In an embodiment, the privacy level applies to all information associated with the occupant, such that the occupant may specify that her personal information is not to be stored or shared. The designation of entities permitted to access specific information may also be specified at various levels of granularity. The various sets of entities permitted to access specific information may include, for example, other AVs, cloud servers 136, specific third-party AV systems, etc.

[0070] In an embodiment, the AV system 120 or the cloud server 136 determines whether the AV 100 or another entity may access certain information associated with the occupant. For example, a third-party AV system attempting to access occupant input related to a particular spatiotemporal location must obtain authorization, such as from the AV system 120 or the cloud server 136, to access information associated with the occupant. For example, the AV system 120 uses the occupant's specified privacy level to determine whether the occupant input related to the spatiotemporal location can be presented to a third-party AV system, the AV 100, or another AV. This enables the occupant's privacy level to specify which other entities are allowed to receive data related to the occupant's actions or other data associated with the occupant.

[0071] Figure 2An example "cloud" computing environment is illustrated. 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 refer to Figure 2 , cloud computing environment 200 includes cloud data centers 204a, 204b, and 204c interconnected by cloud 202. Data centers 204a, 204b, and 204c provide cloud computing services for computer systems 206a, 206b, 206c, 206d, 206e, and 206f connected to cloud 202.

[0072] The cloud computing environment 200 includes one or more cloud data centers. Figure 2 The cloud data center 204a shown in FIG. 2 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. 202 or a specific portion of a cloud). 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, server nodes are similar to Figure 3 The data center 204a has many computing systems distributed across multiple racks.

[0073] Cloud 202 includes cloud data centers 204a, 204b, and 204c and 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 help facilitate access to cloud computing services by computing systems 206a-f. In an embodiment, the network represents any combination of one or more local networks, wide area networks, or internetworks coupled by wired or wireless links deployed using terrestrial or satellite connections. Data exchanged through the network is transmitted using a variety of network layer protocols (such as Internet Protocol (IP), Multi-Protocol Label Switching (MPLS), Asynchronous Transfer Mode (ATM), Frame Relay, etc.). In addition, in embodiments where the network represents a combination of multiple subnetworks, different network layer protocols are used on each underlying subnetwork. In some embodiments, the network represents one or more interconnected internetworks (such as the public Internet, etc.).

[0074] Computing systems 206a-f or cloud computing service consumers are connected to the cloud 202 through network links and network adapters. In an embodiment, computing systems 206a-f are implemented as various computing devices, such as servers, desktops, laptops, tablets, smartphones, Internet of Things (IoT) devices, AV (including cars, drones, shuttles, trains, buses, etc.) and consumer electronics. In an embodiment, computing systems 206a-f are implemented in other systems or as part of other systems.

[0075] Figure 3 Computer system 300 is illustrated. In implementation, computer system 300 is a special purpose computing device. The special purpose computing device is hardwired to perform these techniques, or includes a digital electronic device such as one or more application specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that 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 can also combine customized hardwired logic, ASICs or FPGAs with customized programming to complete 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 contains hardwired and / or program logic to implement these techniques.

[0076] 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 to process 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, which are executed 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 that is customized to perform the operations specified in the instructions.

[0077] In an embodiment, 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.

[0078] In an embodiment, the computer system 300 is coupled 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 via bus 302. An input device 314 including alphanumeric and other keys is coupled to bus 302 for communicating information and command selections to processor 304. Another type of user input device is a cursor controller 316, such as a mouse, a trackball, a touch display, or cursor direction keys, for communicating direction information and command selections to processor 304 and for controlling movement of a cursor on display 312. Such input devices typically have two degrees of freedom in two axes, a first axis (e.g., an x-axis) and a second axis (e.g., a y-axis) that allow the device to specify a position on a plane.

[0079] 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.

[0080] As used herein, the term "storage medium" refers to any non-temporary 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 memories such as storage device 310. Volatile media include dynamic memories such as main memory 306. Common forms of storage media include, for example, floppy disks, floppy disks, hard disks, solid-state drives, tapes or any other magnetic data storage media, CD-ROMs, any other optical data storage media, any physical media with a hole pattern, RAM, PROM and EPROM, FLASH-EPROM, NV-RAM, or any other memory chip or storage box.

[0081] Storage media are distinct from transmission media, but can be used in conjunction with transmission media. Transmission media participate in the transmission of information between storage media. For example, transmission media include coaxial cables, copper wires, and optical fibers, including wires that provide bus 302. Transmission media can also take the form of sound waves or light waves, such as those generated during radio wave and infrared data communications.

[0082] In an embodiment, various forms of media are involved in carrying one or more sequences of one or more instructions to the processor 304 for execution. For example, the instructions are initially executed on a disk or solid-state drive of a remote computer. The remote computer loads the instructions into its dynamic memory and sends the instructions over a telephone line using a modem. The local modem of the 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 the bus 302. The bus 302 carries the data to the main memory 306, from which the processor 304 retrieves and executes the instructions. The instructions received by the main memory 306 may optionally be stored on the storage device 310 before or after execution by the processor 304.

[0083] 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 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 an electrical, electromagnetic or optical signal carrying a digital data stream representing various types of information.

[0084] The network link 320 typically provides data communication to other data devices through one or more networks. For example, the network link 320 provides a connection to a host computer 324 or to a cloud data center or device operated by an Internet Service Provider (ISP) 326 through a local network 322. The ISP 326, in turn, provides data communication services through a worldwide packet data communication network now commonly referred to as the "Internet" 328. Both the local network 322 and the Internet 328 use electrical, electromagnetic, or optical signals that carry digital data streams. The signals through the various networks and the signals on the network link 320 and through the communication interface 318 are example forms of transmission media, where these signals carry digital data to and from the computer system 300. In an embodiment, the network 320 includes the cloud 202 described above or a portion of the cloud 202.

[0085] 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 as it is received, and / or stored in storage device 310, or other non-volatile storage for later execution.

[0086] AV Architecture

[0087] Figure 4A Shown for AV (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 1 404, 406, 408, and 410 are each sometimes referred to as a processing circuit (e.g., computer hardware, computer software, or a combination of the two). Any or all of the combinations of modules 402, 404, 406, 408, and 410 are also examples of processing circuits.

[0088] In use, planning module 404 receives data representing destination 412 and determines data representing a trajectory 414 (sometimes referred to as a route) that AV 100 may travel in order to reach (e.g., arrive at) destination 412. In order for planning module 404 to determine data representing trajectory 414, planning module 404 receives data from perception module 402, positioning module 408, and database module 410.

[0089] The perception module 402 uses, for example, Figure 1 One or more sensors 121 are shown to identify nearby physical objects. Objects are classified (e.g., grouped into types such as pedestrians, bicycles, cars, traffic signs, etc.), and a scene description including the classified objects 416 is provided to the planning module 404.

[0090] The planning module 404 also receives data representing the AV position 418 from the positioning module 408. The positioning module 408 determines the AV 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 GNSS (Global Navigation Satellite System) sensor 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 attributes, a map describing the road network connection attributes, a map describing the physical attributes of the lane (such as traffic speed, traffic volume, the number of vehicles and bicycle lanes, lane width, lane traffic direction, or lane marking type and location, or a combination thereof), and a map describing the spatial location of road features (such as intersections, traffic signs, or various types of other driving signals, etc.). In an embodiment, the high-precision map is constructed by adding data to the low-precision map via automatic or manual annotations.

[0091] The control module 406 receives data representing the trajectory 414 and data representing the AV position 418, and operates control functions 420a-420c (e.g., steering, throttle, brakes, ignition system) of the AV 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 420a-420c in the following manner: 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 making the turn.

[0092] Figure 4B 4 is a block diagram of a planning module 404 according to one or more embodiments. The planning module 404 includes a path planner 451, logical constraints 452, a homotopy extractor 453, a sample-based maneuver enabler 454, a trajectory score generator 455, a tracking controller 456, and an AV 457.

[0093] In an embodiment, the route planner 451: 1) receives the initial and final states; 2) plans the desired sequence of roadblocks / lanes using the lane route planner; 3) divides the route into segments based on lane changes so that the segments do not contain lane changes; 4) selects the segment that the AV is on based on the state of the AV projected on the roadblock (from the dynamic world model 458); 5) extracts the baseline path of the selected segment (which can be marked as the "desired" baseline path in the case of a desired lane change); and 6) trims the baseline path based on the maximum / minimum length. In the case where a lane change is not required, the adjacent baseline path is extracted and marked only as "optional", which means that the AV can use the lane (if necessary) to avoid a collision.

[0094] In an embodiment, the route planner 451 generates a graphical representation of the operating environment of the AV, the physical state of the AV (e.g., speed, position), and possible outcomes based on sensor data. In an embodiment, the graphical representation is a directed graph or decision graph (described below) comprising a plurality of nodes, wherein each node represents a sample of the decision space of the AV for a particular driving scenario, e.g., a plurality of maneuvers related to other vehicles and objects and environmental constraints (e.g., drivable area, lane markings). The edges of the directed graph represent different trajectories available to the AV for a particular driving scenario.

[0095] In an embodiment, the logical constraints 452 include "hard" constraints and "soft" constraints. Hard constraints are logical constraints that must not be violated because if violated, the AV will collide with other objects (such as pedestrians that may "stroll" across the road). Note that hard constraints do not mean "no collision". Instead, hard constraints can be, for example, a combination of space and rate constraints that may cause a collision. For example, a hard constraint can be expressed in words as: "If the AV advances at 30mph in lane A or accelerates at 2mph / s in lane B, it will collide with a pedestrian." Therefore, the formally expressed hard constraints are "do not advance at 30mph in lane A" and "do not exceed 25mph in lane A".

[0096] Soft constraints are constraints that the AV should follow but can be violated to, for example, complete the trip to the destination or avoid a collision. Some examples of "soft" constraints include, but are not limited to: passenger comfort constraints, and a minimum threshold for lateral clearance to pedestrians crossing the street (strolling) and AV passengers to provide comfort to the pedestrians. In an embodiment, soft constraints are embodied in one or more rulebooks. Soft constraints may include spatial constraints that change over time. Spatial constraints may be a drivable area.

[0097] In some embodiments, different constraints are sampled differently. For example, the homotopy extractor 453 may operate at 10 Hz, and the implementation search may be performed twice as fast at 20 Hz.

[0098] In an embodiment, the homotopy extractor 453 generates a set of potential maneuvers for the AV. Instead of assuming a goal and then selecting the goal that performs best, the homotopy extractor 453 assumes a set of active constraints (referred to as "homopy" (defined below)) and then selects the set of constraints that produces a lower cost. The homotopy extractor 453 receives a route plan from the route planner 451 that includes a baseline path. The baseline path is the best estimate of the lane in which the AV is located and is an optional path (potentially desired path) that can be used when the AV makes a lane change. In an embodiment, the route planner 451 also includes rate squares and spatial constraints calculated along the baseline path (e.g., calculated with a boundary generator). In some implementations, the route plan may include multiple baseline paths that the AV can traverse. One of the route plans may be designated as an "anchor path". By default, if the anchor path is not blocked (e.g., blocked by other vehicles, pedestrians, obstacles, etc.), the AV can traverse the anchor path. If the anchor path is blocked, the AV can traverse one of the other baseline paths.

[0099] Given the initial state of the AV, the final state of the AV, the map representation and predictions of other agents in the scene, the homotopy extractor 453 finds all "approximately" feasible maneuvers that the AV can perform. Note that in this context, the resulting maneuvers may not be dynamically feasible, but the homotopy extractor 453 guarantees that the resulting set of constraints describing the maneuvers is not an empty set (also considering the AV footprint). AV maneuvers are described by homotopies. As described above, a homotopy is a subset of the set of constraints of the AV trajectory that the AV can follow when traversing a specific route. In some implementations, a homotopy can be the only space in which any path starting at the starting position (AV state) and ending at the final state can be continuously deformed. In order to find these maneuvers, the homotopy extractor 453 iterates over all possible decisions that the AV can take relative to other agents (e.g., passing on the left / right, passing before or after, or just staying). In short, the output of the homotopy extractor 453 describes the spatiotemporal location of the AV to the agent. Although this may be a computationally expensive search, all infeasible combinations can be eliminated due to a set of simple checks.

[0100] In order to be able to describe constraints that represent where other agents are located and what a collision of the AV with these agents means, each agent is converted into a station-based and a space-based obstacle. The station-based constraints are parameterized over time, while the space-based constraints are parameterized over both station and time. Figures 13-16 Further details regarding the homotopy extractor 453 are described.

[0101] In an embodiment, the search 454a…454n is performed by a sample-based maneuver realizer 454 to generate a set of all extracted homologous trajectories 1…n. The sample-based maneuver realizer 454 is further described in detail in the co-pending application entitled “Sampling-Based Manuver Realizer” filed on December 7, 2021 (agent docket number 46154-0310001), the entire contents of which are incorporated herein by reference. Example techniques for generating maneuvers and / or trajectories are also further described in detail in the co-pending application entitled “Vehicle Operation Using Manuver Generation” filed on December 7, 2021 (agent docket number 46154-0316001), the entire contents of which are incorporated herein by reference.

[0102] In an embodiment, trajectory score generator 455 uses one or more rulebooks, one or more machine learning models 459, and / or one or more safe maneuver models 460 to score trajectories 1 ... N, and uses the scores to select the trajectory that best complies with the rules in the one or more rulebooks. In an embodiment, a predefined cost function is used to generate trajectory scores.

[0103] In an embodiment using a cost function, a total or partial order hierarchical cost function may be used to score trajectories. A cost function is applied to metrics (e.g., Boolean values) associated with violating and / or satisfying a hierarchy of rules in one or more rulebooks based on priority or relative importance. An example hierarchy of priority-based rules is as follows (from top to bottom): collision avoidance (Boolean), blocking (Boolean), final state in desired lane (Boolean), lane change (Boolean), and comfort (double floating point). In this example, each non-zero priority rule is defined as Boolean to avoid over-optimization of high priority costs. The most important or highest priority rule is collision avoidance, followed by blocking avoidance, followed by avoiding final state in desired lane, followed by lane change, followed by comfort rules (e.g., maximum acceleration or deceleration). These example rules are more fully described as follows:

[0104] Collision: Set to true if there is a state along the scoring trajectory where the AV vehicle's footprint collides with the footprint of any other agent / object (e.g., if their polygons intersect, they are considered to collide).

[0105] Blocked: A trajectory is considered blocked if the final homotopy does not contain the desired target state and the final velocity of the trajectory is below a specified threshold (e.g., 2 m / s). The target state can be, for example, a specific position of the AV (e.g., expressed in terms of a coordinate system, such as an (x, y) position, etc.).

[0106] Final state in desired lane: Set to true if the final state of the trajectory is found in the lane where the lane change is desired, and set to true if the AV’s footprint crosses a lane divider at any time during the trajectory.

[0107] Comfort: Maximum values ​​of acceleration / deceleration, braking distance, and lateral clearance can be considered.

[0108] For each trajectory, the rules are checked and a metric is determined. The metric is used to formulate a cost function, which is then minimized using, for example, a least squares formula or any other suitable solver. The trajectory with the lowest cost is the selected trajectory, i.e., the trajectory with the fewest rule violations or the most compliance. In an embodiment, minimizing the cost function can be used to score the trajectories, as described in further detail below. Note that the above rules are merely examples. One of ordinary skill in the art will recognize that any suitable cost function and rule book can be used for trajectory scoring, including rule books with more or fewer rules.

[0109] For machine learning embodiments, trajectory score generator 455 may implement one or more machine learning models 459 and / or safe maneuver models 460 to score trajectories. For example, a neural network may be used to predict the score of a trajectory.

[0110] Tracking controller 456 is used to improve the robustness of planning module 404 against unexpected spikes in computational demand. Tracking controller 456 is a fast executing tracking controller that provides stable and smooth control inputs and allows planning module 404 to react to disturbances more quickly. In an embodiment, tracking controller 456 runs at 40 Hz. The input to tracking controller 456 is the selected and time-parameterized trajectory provided by trajectory score generator 455, so that tracking controller 456 can query the exact desired position of the AV at a given time.

[0111] In an embodiment, the tracking controller 456 is formulated as a type of model predictive control (MPC) problem with constraints on control inputs and states. However, any suitable multivariable control algorithm may be used. The MPC-type formulation uses an internal dynamic model of the process, a cost function J on a receding horizon, and an optimization algorithm for minimizing the cost function J using the control input u. An example cost function for optimization is a quadratic cost function.

[0112] In an embodiment, the dynamic model is a kinematic vehicle model in Cartesian coordinates or any other suitable reference coordinate system. For example, the kinematic vehicle model may be a bicycle model that allows the sideslip angle to be defined geometrically to represent the yaw rate in terms of a variable expressed relative to the center of gravity of the AV. In an embodiment, the cost function J follows the profile error formula (orthogonal deviation from the anchor path), where the objective is to minimize the lateral and longitudinal errors.

[0113] AV Input

[0114] Figure 5 The perception module 402 ( Figure 4A ) 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 1 123). 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 produces 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.

[0115] Another input 502b is a RADAR (radar) system. RADAR is a technology that uses radio waves to obtain data related to nearby physical objects. RADAR can obtain data related to objects that are not within the line of sight of the LiDAR system. The RADAR system produces RADAR data as output 504b. For example, RADAR data is one or more radio frequency electromagnetic signals used to construct a representation of the environment 190.

[0116] 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 obtain information about nearby physical objects. The camera system generates 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 stereoscopic imaging (stereoscopic 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 some embodiments, the camera system is configured to "see" distant objects (e.g., as far as 1 km or more in front of the AV). Therefore, in some embodiments, the camera system has features such as sensors and lenses that are optimized for perceiving distant objects.

[0117] 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 navigation 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 navigation information as possible, so that the AV 100 can access all relevant navigation information provided by these objects. For example, the viewing angle of the TLD system is about 120 degrees or greater.

[0118] In some embodiments, sensor fusion techniques are used to combine the outputs 504a-504d. Thus, the individual outputs 504a-504d are provided to other systems of the AV 100 (e.g., to a Figure 4A and 4B The 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 some embodiments, 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 some embodiments, 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.

[0119] Figure 6 An example of a LiDAR system 602 is shown (eg, Figure 5502a shown). 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 physical object that is solid in 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 a boundary 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 near the AV.

[0120] Figure 7 6. The LiDAR system 602 is shown in operation. In the scenario shown in the figure, the AV 100 receives both the camera system output 504c in the form of an image 702 and the 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 to the data points 704. In particular, physical objects 706 identified in the image 702 are also identified in the 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.

[0121] Figure 8 6 shows additional details of the operation of the LiDAR system 602. As described above, the AV 100 detects the boundaries of the 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 drives over the ground 802, the LiDAR system 602 will continue to detect light reflected by the next valid ground point 806 if nothing is blocking the road. However, if an object 808 is blocking the road, the light 804e-804f emitted by the LiDAR system 602 will be reflected 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.

[0122] Path Planning

[0123] Fig. 9 Shown (for example, Figure 4A and 4B 900 of the relationship between the input and output of the planning module 404 (shown in FIG. 1 ). In general, 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" road segments such as unpaved paths or open fields.

[0124] In addition to the route 902, the planning module also outputs lane-level route planning data 908. The lane-level route planning data 908 is used to drive through the road segments of the route 902 at a specific time based on the conditions of the road segments. For example, if the route 902 includes a multi-lane highway, the lane-level route planning data 908 includes trajectory planning data 910, wherein the AV 100 can use the trajectory planning data 910 to select a lane from the multiple lanes based on, for example, whether an exit is approaching, whether there are other vehicles 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, the lane-level route planning data 908 includes a speed constraint 912 that is specific to a road segment of the route 902. For example, if the road segment includes pedestrians or unexpected traffic, the speed constraint 912 can limit the AV 100 to a travel speed that is slower than the expected speed, such as a speed based on the speed limit data of the road segment.

[0125] In an embodiment, inputs to the planning module 404 include (e.g., Figure 4A ) database data 914, current location data 916 (e.g., Figure 4A AV position 418 shown), (e.g., for Figure 4A4 ). In some embodiments, the database data 914 includes rules (also referred to as a "rulebook") used in planning. The rules are specified using a formal language (e.g., using Boolean logic or linear temporal logic (LTL)). In any given situation encountered by the AV 100, at least some of these rules will apply to the situation. A rule applies to a given situation if it has a condition that is satisfied based on information available to the AV 100 (e.g., information about the surrounding environment). Rules can have priorities. For example, a rule of "if the road is a highway, move to the leftmost lane" can have a lower priority than "if the exit is within one mile, move to the rightmost lane."

[0126] Fig.10 In path planning (eg, by planning module 404 ( Figure 4A and 4B )) uses a directed graph 1000. In general, if Fig.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).

[0127] In an embodiment, directed graph 1000 has 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 the road. In this way, directed graph 1000 includes information at different granularity levels. In an 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 the directed graph 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.

[0128] Nodes 1006a-1006d are different from objects 1008a-1008b that cannot overlap with nodes. In an embodiment, at low granularity, objects 1008a-1008b represent areas that cars cannot pass through, such as areas without streets or roads. At high granularity, objects 1008a-1008b represent physical objects in the field of view of AV 100, such as other cars, pedestrians, or other entities with which 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 street lights or telephone poles, etc.) or dynamic objects (e.g., objects that can change position, such as pedestrians or other cars, etc.).

[0129] Nodes 1006a-1006d are connected by edges 1010a-1010c. If two nodes 1006a-1006b are connected by edge 1010a, then 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. (That is, the AV 100 travels between two physical locations represented by the corresponding nodes.) Edges 1010a-1010c are generally 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, a one-way street, a single lane of a street, road, or highway, or other features that can only be traversed in one direction due to legal or map constraints.

[0130] 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 .

[0131] Edges 1010a-1010c have associated costs 1014a-1014b. Costs 1014a-1014b are values ​​representing resources that will be spent if the AV 100 selects 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 the other edge 1010b, the associated cost 1014a of the first edge 1010a may be twice the associated cost 1014b of 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, for example, due to road conditions, expected weather, etc., one edge 1010a requires more fuel than the other edge 1010b.

[0132] 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.

[0133] AV Control

[0134] Fig.11 Shown (for example, Figure 4A 1100 of the inputs and outputs of the control module 406 (shown in FIG. 110). 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 a microcontroller or both); short-term and / or long-term data storage devices similar to the main memory 306, ROM 308, and storage devices 310 (e.g., memory, random access memory, or flash memory or both); and instructions stored in the memory that, when executed (e.g., by the one or more processors), perform the operations of the controller 1102.

[0135] 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 4A and 4B104 . 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 represents the amount by which the throttle of the AV 100 (e.g., an acceleration control) should be engaged to achieve the desired output 1104, such as by engaging a steering pedal or engaging another throttle control. 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 represents a steering angle, such as 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.

[0136] In an embodiment, the controller 1102 receives feedback used in adjusting the inputs provided to the throttle and steering. For example, if the AV 100 encounters a disturbance 1110, such as a hill, the measured velocity 1112 of the AV 100 drops below the desired output rate. In an embodiment, any measured output 1114 is provided to the controller 1102 so that the required adjustments can be made, for example, based on the difference 1113 between the measured velocity and the desired output. The measured output 1114 includes measured position 1116, measured velocity 1118 (including velocity and heading), measured acceleration 1120, and other outputs that the sensors of the AV 100 can measure.

[0137] In an embodiment, information about the disturbance 1110 is detected in advance, for example, by a sensor such as a camera or 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.

[0138] Fig.12 A block diagram 1200 is shown of the inputs, outputs, and components of the controller 1102. The controller 1102 has a rate analyzer 1206 that affects the operation of a throttle / brake controller 1204. For example, the rate analyzer 1202 instructs the throttle / brake controller 1204 to use a throttle / brake 1206 to accelerate or decelerate based on, for example, feedback received by the controller 1102 and processed by the rate analyzer 1202.

[0139] Controller 1102 also has a lateral tracking controller 1208 that affects the operation of steering wheel controller 1210. For example, lateral tracking controller 1208 instructs steering wheel controller 1210 to adjust the position of steering angle actuator 1212 based on feedback received by controller 1102 and processed by lateral tracking controller 1208, for example.

[0140] The controller 1102 receives several inputs used to determine how to control the throttle / brake 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 cross 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 the way the throttle / brake 1206 and the steering angle actuator 1212 are being controlled. In an embodiment, the controller 1102 receives information from other inputs 1214, such as information received from a database, a computer network, etc.

[0141] Homotopy-based planner

[0142] As described herein (e.g., with respect to FIG. Fig. 9 and Fig.10 ), planning module 404 can receive data representing a destination. In addition, planning module 404 can receive data from one or more of the above modules (e.g., data from perception module 402, positioning module 408, database module 410, etc.). As an example, the data can represent nearby physical objects using one or more sensors, the location of the AV, geographic data, or any other data described herein. In addition, using this data, planning module 404 can determine (e.g., generate) data representing a trajectory that the AV can travel to reach the destination.

[0143] In some implementations, planning module 404 can determine the trajectory in a brute force manner by (i) generating a large number of candidate trajectories (e.g., to consider every possible trajectory that the AV may take along the route), (ii) evaluating each candidate trajectory, and (iii) selecting a particular candidate trajectory for execution. However, generating and evaluating each trajectory across such a large search space (e.g., a search space that includes every possible trajectory) can be computationally expensive.

[0144] To reduce the search space, in some implementations, the planning module 404 may determine a trajectory for the AV (e.g., the AV system 120) based on a "homopyrology"-based approach. As an example, the planning module 404 may determine a route for the AV and determine several candidate constraints for traversing the route. In addition, the planning module 404 may determine a feasible homology of these constraints (e.g., a combination of constraints that the AV can safely comply with when traversing the route, such as not violating any traffic regulations and not contacting any obstacles, vehicles, pedestrians, etc.). In addition, the planning module 404 may generate trajectories for each feasible homology (while abandoning the generation of trajectories for infeasible homology) and select one of the trajectories for the AV to execute. Thus, the trajectory may be selected more quickly and efficiently.

[0145] In some implementations, the techniques described herein may be performed for a subset of the segments that make up a route. In some implementations, the techniques described herein may be performed for all the segments that make up a route.

[0146] Fig.13 An example process 1300 is shown for determining a trajectory of an AV according to a “homotopy” based approach. In some implementations, the process 1300 may be performed at least in part using the homotopy extractor 453 of the planning module 404 of the AV 100 (e.g., as described with respect to Figure 4A and 4B described).

[0147] like Fig.13 As shown, homology extractor 453 can generate a set of candidate constraints 1302 associated with the AV traversing one or more segments of the route to the destination (e.g., constraints on the trajectory that the AV can follow when traversing the route). In some implementations, each candidate constraint in candidate constraints 1302 can include specific parameters and corresponding parameter values. For example, a candidate constraint can be a specific parameter C 1 Equal to a specific parameter value X 1 As another example, another candidate constraint could be the same parameter C 1 Equal to different parameter values ​​X 2 As another example, another candidate constraint could be a different parameter C 2 Equal to parameter value Y 1 .

[0148] In some implementations, at least some of the candidate constraints 1302 may be optional or "soft" (e.g., the AV does not necessarily need to comply with the candidate constraints when traversing to the destination). In some implementations, at least some of the candidate constraints 1302 may be required or "hard" (e.g., the AV must comply with the candidate constraints when traversing to the destination).

[0149] Candidate constraints 1302 may represent any aspect that may limit, control, or otherwise affect the operation of the AV as it traverses to a destination.

[0150] As an example, at least some of the candidate constraints 1302 may relate to the AV's ability to proceed. For example, one or more of the candidate constraints 1302 may specify that the AV is to comply with certain map constraints based on the AV's ability to proceed, including but not limited to: acceleration limits, braking limits, speed limits, turn rate limits, inertia limits, etc. As another example, one or more of the candidate constraints 1032 may specify the range of motion of the AV (e.g., the AV may travel forward or backward while maintaining a straight line or turning, but may not travel from one side to the other).

[0151] As another example, at least some of the candidate constraints 1302 may be map constraints related to the map geometry of one or more roads that the AV may use to traverse to a destination. For example, one or more of the candidate constraints 1302 may specify that the AV is to be restricted to certain lanes of a road and / or within certain boundaries of the road (e.g., between the left and right edges of a navigable portion of the road). As another example, one or more of the candidate constraints 1302 may specify the presence and location of obstacles on the road that the AV may not traverse.

[0152] As another example, at least some of the candidate constraints 1302 may relate to legal constraints regarding the operation of the AV. For example, one or more of the candidate constraints 1302 may specify that the AV is to comply with a particular speed limit for a road and / or a particular traffic flow (e.g., direction of travel) for a road. As another example, one or more of the candidate constraints may specify that the AV is to comply with traffic regulations or laws in a particular jurisdiction.

[0153] As another example, at least some of the candidate constraints 1302 may relate to the predicted comfort of one or more passengers of the AV. For example, one or more of the candidate constraints 1302 may specify that the AV adhere to certain acceleration limits, braking limits, speed limits, turn rate limits, etc. based on the impact of these constraints on the comfort of the passengers of the AV.

[0154] As another example, at least some of the candidate constraints 1302 may relate to the predicted safety of one or more passengers of the AV and / or the safety of the AV. For example, one or more of the candidate constraints 1302 may specify that the AV does not come into contact with certain objects (e.g., other vehicles, pedestrians, obstacles, etc.), stays within the boundaries of the road, travels in the direction of traffic on the road, does not accelerate or decelerate in a manner that will injure its passengers, etc. As another example, at least some of the candidate constraints 1302 may specify that the likelihood of the AV colliding with an obstacle, vehicle, pedestrian, or other object is less than a threshold. In some implementations, the likelihood may be calculated by the homotopy extractor 453 using one or more computer simulations or dynamic models.

[0155] As another example, at least some of the candidate constraints 1302 may specify that the AV perform certain operations or tasks. For example, a candidate constraint may specify that the AV perform a specific maneuver. As an example, a candidate constraint may specify that the AV change lanes on a road at a specific time and place. As another example, a candidate constraint may specify that the AV remain in its current location at a specific time and place. As another example, a candidate constraint may specify that the AV pass a specific vehicle at a specific time and place. As another example, a candidate constraint may specify that the AV remain behind a specific vehicle at a specific time and place. As another example, a candidate constraint may specify that the AV wait for a vehicle or pedestrian to leave the path before proceeding further along the AV's path. As another example, a candidate constraint may specify that the AV proceed along the path before a vehicle or pedestrian enters the path.

[0156] Although example candidate constraints 1302 are described herein, these are merely illustrative examples. In practice, candidate constraints 1302 may include additional constraints, either in place of or in addition to the constraints described herein.

[0157] Homotopy extractor 453 may generate one or more homotopies 1304a-1304n based on candidate constraints 1302. Each homotopy may include a different respective subset of candidate constraints 1302. For example, each homotopy may include a different one of candidate constraints 1302 and / or a different combination of two or more of candidate constraints 1302.

[0158] In some implementations, each homology may include one or more of the "optional" candidate constraints 1302. In addition, each homology may include each "required" candidate constraint 1302. In practice, whether a particular candidate constraint is "optional" or "required" may vary depending on the implementation. As an example, in some implementations, candidate constraints 1302 related to the AV's ability to proceed, map constraints on one or more roads that the AV can use to traverse to a destination, legal constraints regarding the operation of the AV, and / or the safety of one or more passengers of the AV may be considered "required." As another example, in some implementations, candidate constraints 1302 related to the comfort of one or more passengers of the AV and / or candidate constraints 1302 that specify that the AV perform certain operations or tasks may be considered "optional."

[0159] exist Fig.13 In the example shown, the first homotopy 1304a ("homotopy 1") includes: (i) parameters C 1 Equal to parameter value X 1 The "optional" candidate constraints, (ii) parameter C 2 Equal to parameter value Y 2 of the “optional” candidate constraints, and (iii) each of the “required” candidate constraints.

[0160] In addition, the second homotopy 1304b ("homotopy 2") includes: (i) parameters C 1 Equal to parameter value X 1 The "optional" candidate constraints (as in homology 1), (ii) the parameter C 2 Equal to parameter value Y 2 The "optional" candidate constraints (as in homology 1), (iii) the parameter C N Equal to parameter value Z 1 , and (iv) each "required" candidate constraint (as in homotopy 1). That is, although homotopy 2 shares some of the same candidate constraints as homotopy 2, it includes additional constraints that are not in homotopy 1.

[0161] In addition, the third homotopy 1304n ("homotopy N") includes: (i) parameters C 1 Equal to parameter value X 1 The "optional" candidate constraints (as in homotopies 1 and 2), (ii) the parameter C 2 Equal to parameter value Y 2 (iii) the parameter C N Equal to parameter value Z 2, and (iv) each “required” candidate constraint (as in homotopies 1 and 2). That is, although homotopy 3 shares some of the same candidate constraints as homotopies 1 and 2, it specifies a different parameter value for one of its candidate constraints.

[0162] although Fig.13 Three example homotopies are shown in , but this is merely an illustrative example. In practice, homotopy extractor 453 may generate any number of homotopies, each homotopy having a different corresponding subset of candidate constraints 1302 .

[0163] The homotopy extractor 453 determines whether each homotopy 1304a-1304n is "feasible". As an example, for each homotopy, the homotopy extractor 453 can determine whether the AV can traverse to the destination according to the candidate constraints of the homotopy without colliding with other objects on the road, without negatively affecting the safety of its passengers, without violating traffic regulations or laws of the jurisdiction, etc.

[0164] In some implementations, the homotopy extractor 453 can determine whether each of the homotopies 1304a-1304n is feasible by predicting the motion of the AV. For example, for each homotopy, the homotopy extractor 453 uses a computer simulation or a dynamic model to simulate the motion of the AV to predict how the AV will move when traversing the road segment while trying to comply with the various candidate constraints of the homotopy. If the homotopy extractor 453 determines that the AV cannot traverse the road segment while complying with the various candidate constraints of the homotopy, the homotopy extractor 453 determines that the homotopy is "infeasible". If the homotopy extractor 453 determines that the AV can traverse the road segment while complying with the various candidate constraints of the homotopy, the homotopy extractor 453 determines that the homotopy is "feasible".

[0165] As an example, a homology may include a subset of candidate constraints that specify: (i) the AV performs certain operations and tasks at certain times and places; (ii) the AV complies with all traffic rules and laws in the jurisdiction; (iii) the AV performs in a manner that does not exceed its ability to perform; and (iv) the AV does not collide with any objects or obstacles on the road. The homology extractor 453 can simulate the movement of the AV based on these candidate constraints. If the homology extractor 453 determines that the AV cannot perform the specified operations and tasks unless it violates certain traffic rules or laws, the homology extractor 453 determines that the homology is "infeasible". Similarly, if the homology extractor 453 determines that the AV cannot perform the specified operations and tasks without colliding with other objects, the homology extractor 453 also determines that the homology is "infeasible". Similarly, if the homology extractor 453 determines that performing the specified operations and tasks will require exceeding the ability of the AV to perform, the homology extractor 453 also determines that the homology is "infeasible". However, if the homotopy extractor 453 determines that the AV can perform the specified operations and tasks, and does not violate any other constraints, then the homotopy extractor 453 determines that the homotopy is "feasible".

[0166] For example, in Fig.13 In the example shown, the homotopy extractor 453 determines that homotopies 1 and N are “feasible”, and that homotopy 2 is “infeasible” (eg, due to violating one or more of the candidate constraints 1302 specified by homotopy 2).

[0167] Additionally, the homotopy extractor 453 may determine whether each of the homotopies 1304a - 1304n is “feasible” according to the first precision.

[0168] The planning module 404 generates one or more trajectories for each homology determined to be "feasible" and avoids generating trajectories for each homology determined to be "infeasible". For example, for each homology determined to be "feasible", the planning module 404 (e.g., using the sample-based maneuver implementer 454) can use computer simulation and one or more dynamic models, control laws and equivalents of the AV's motion to generate one or more trajectories for the AV that enable it to traverse the road segment while complying with each candidate constraint of the homology. In some implementations, the simulation and / or dynamic model can be implemented using one or more equivalents and / or control laws of the motion of one or more objects in a specified environment. Example techniques for generating one or more trajectories for the AV are described herein (e.g., reference to Figure 4A , 4B , 9 and 10).

[0169] For example, in Fig.13In the example shown, planning module 404 (e.g., using sample-based maneuver enabler 454) generates one or more trajectories 1306a corresponding to homotopy 1, and one or more trajectories 1306b corresponding to homotopy N (both of which are determined to be "feasible"). However, planning module 404 avoids generating any trajectories corresponding to homotopy 2 (which is determined to be "infeasible").

[0170] In some implementations, planning module 404 (eg, using sample-based maneuver enabler 454) can generate one or more trajectories of respective homotopies determined to be “feasible” according to a second precision. The second precision can be higher than the first precision.

[0171] In some implementations, the accuracy with which the motion of the AV is predicted and / or the trajectory of the AV is generated may refer to one or more of: (i) the spatial resolution with which the motion of the AV is predicted and / or the trajectory of the AV is generated, (ii) the temporal resolution with which the motion of the AV is predicted and / or the trajectory of the AV is generated, (iii) the complexity of the computer simulation or dynamic model generated for predicting the motion of the AV and / or the trajectory of the AV, (iv) the amount of computing resources allocated for predicting the motion of the AV and / or the trajectory of the AV, (v) the tolerance or error range associated with predicting the motion of the AV and / or the trajectory of the AV, and / or other such characteristics that may affect how the motion of the AV is predicted and / or how the trajectory of the AV is generated.

[0172] As an example, the homotopy extractor 453 may initially generate predictions for each homotopy according to a first spatial and / or temporal resolution. Subsequently, the planning module 404 (e.g., using the sample-based maneuver enabler 454) may generate one or more trajectories for each homotopy determined to be "feasible" according to a second, higher spatial and / or temporal resolution. For example, the homotopy extractor 453 may initially predict the motion of the AV for each homotopy according to a lower spatial resolution (e.g., in increments of 10 feet). Subsequently, the planning module 404 (e.g., using the sample-based maneuver enabler 454) may generate one or more trajectories for each homotopy determined to be "feasible" according to a higher spatial resolution (e.g., 1 foot increments). As an example, the homotopy extractor 453 may initially predict the motion of the AV for each homotopy according to a lower temporal resolution (e.g., in increments of 10 seconds). Subsequently, the sample-based maneuver enabler 454 may generate one or more trajectories for each homotopy determined to be "feasible" according to a higher spatial resolution (e.g., 1 second increments). Although example spatial and / or temporal resolutions are described above, these are merely illustrative examples. In practice, other spatial and / or temporal resolutions may be used to predict the motion of the AV and / or generate one or more trajectories of the AV.

[0173] As another example, the homotopy extractor 453 may initially generate predictions of each homotopy based on a first computer simulation or a first dynamic model. Subsequently, the sample-based maneuvering action implementer 454 may generate one or more trajectories of each homotopy determined to be "feasible" based on a second computer simulation or a second dynamic model that is more complex than the first computer simulation or the first dynamic model (e.g., more variables and / or parameters are modeled). For example, the first computer simulation or dynamic model may require fewer computing resources to generate predictions (but may be less accurate), while the first computer simulation or dynamic model may require more computing resources to generate trajectories (but may be more accurate). As another example, the first computer simulation or dynamic model may require fewer data inputs and / or less comprehensive data inputs to generate predictions (but may be less accurate), while the first computer simulation or dynamic model may require more data inputs and / or more comprehensive data inputs to generate trajectories (but may be more accurate). Example data inputs may include, for example, sensor data, traffic data, weather data, and / or other data about the characteristics of the environment of the AV.

[0174] Planning module 404 (e.g., using trajectory score generator 455) selects one of the generated trajectories 1306a and 1306b and instructs the AV to execute the selected trajectory, such as by providing the selected trajectory to tracking controller 456. Fig.13 In the example shown, track score generator 455 has selected track 1306a ("track 1") over track 1306b ("track N").

[0175] As mentioned above (for example, see Figure 4B ), the tracking controller 456 can generate stable and smooth control inputs for the AV based on the selected trajectory, and provide the inputs to the appropriate subsystems of the AV for execution. As an example, the tracking controller 456 can generate throttle inputs, steering inputs, and / or brake inputs based on the selected trajectory, and provide the respective inputs to the appropriate subsystems of the AV for execution.

[0176] In some implementations, one of the trajectories may be selected by calculating a quality score or other metric for each of the generated trajectories and selecting the trajectory based on the quality score or metric. For example, for each trajectory, the quality score or metric is based on various factors, such as the predicted safety of the passengers of the AV, the predicted comfort of the passengers of the AV, the predicted resources that the AV will consume (e.g., fuel, battery charge, etc.), the predicted amount of time it will take to traverse to the destination, and / or other factors. One of the trajectories (e.g., the trajectory with the highest quality score or metric) may be selected based on the quality score or metric.

[0177] In some implementations, various factors may have different corresponding weights, such that some factors may have a greater impact on the quality score or metric than other factors. For example, if passenger safety is more important than resource consumption, a greater weight may be assigned to passenger safety when calculating the quality score or metric. In some implementations, a quality score or metric may be calculated using a weighted sum as a scoring function. As an example, the quality score or metric Q of a trajectory T may be calculated using the following function:

[0178] Q T =w 1 x 1 +w 2 x 2 ,…+w n x n ,

[0179] where x i is a sub-score associated with a specific factor of trajectory T (e.g., safety, resource consumption, time required to traverse the trajectory, etc.), and w i is the weight assigned to that subscore. In some implementations, the higher the x i The value of w may indicate that a trajectory is more desirable with respect to a particular factor of the trajectory (e.g., safer, requires less resources to be consumed, requires less time to traverse, etc.). In some implementations, a higher w i A value indicates that its corresponding factor is given greater weight in calculating the quality score or metric.

[0180] In some implementations, the planning module 404 (e.g., using the maneuver implementer 454 based on the implementation sample) can also determine one or more emergency maneuvers 1308 that can override the trajectory generated based on the homology 1304a-1304n. For example, the emergency maneuver can correspond to an evasive action (e.g., a sudden turn, braking, acceleration, lane change, etc.) to avoid an unsafe or other undesirable outcome (e.g., a collision, running off the road, etc.). In some implementations, the planning module 404 can plan the emergency maneuver independently of the generated trajectory and selectively override the execution of the selected trajectory with the emergency maneuver based on one or more data inputs. Example data inputs can include, for example, sensor data indicating that the emergency maneuver can be authorized, a command from a passenger of the AV indicating that the emergency maneuver is to be performed, a command from a user remotely monitoring or controlling the AV indicating that the emergency maneuver is to be performed, an automatic command from a remote computer system indicating that the emergency maneuver is to be performed, etc.

[0181] In some implementations, homotopy extractor 453 may determine whether certain homotopies are "feasible" or "infeasible" based on a decision graph. As an illustrative example, Fig.14 A simplified decision diagram 1400 is shown in FIG.

[0182] Decision graph 1400 includes several interconnected nodes 1402, each of which corresponds to a different respective subset of candidate constraints. In some implementations, the nodes may be arranged hierarchically (e.g., according to different levels) and according to one or more branches, where a "child" node inherits the candidate constraints of its "parent" node and additionally includes one or more additional candidate constraints. In some implementations, decision graph 1400 may be similar to Fig.10 The directed graph 1000 shown in .

[0183] Homotopy extractor 453 may determine the feasibility of traversing to a destination according to the candidate constraints of various nodes, starting with the node with the highest level or layer, and proceeding through nodes of successively lower levels or layers. If homotopy extractor 453 determines that it is not feasible to comply with the candidate constraints of a particular node, homotopy extractor 453 may avoid evaluating the feasibility of the child nodes of that node.

[0184] For example, refer to Fig.14 , the homology extractor 453 determines that it is feasible to pass through to the destination according to the candidate constraints of the highest-level node 1402a. Based on this determination, the homology extractor 453 then evaluates the feasibility of each of the child nodes 1402b and 1402c, and determines that it is not feasible to pass through to the destination according to the candidate constraints of node 1402b, but it is feasible to pass through to the destination according to the candidate constraints in node 1402c. Based on this determination, the homology extractor 453 avoids evaluating the feasibility of any node that depends on node 1402b, and continues to evaluate the feasibility of nodes that depend on node 1402c. The above process can continue until each node in the decision diagram 1400 has been evaluated or omitted from the evaluation (due to an "infeasible" parent node).

[0185] In some implementations, planning module 404 (e.g., using maneuver implementer 454 based on implementation samples) can generate one or more candidate trajectories based on nodes determined to be “feasible”. Fig.14 , based on the implementation sample, the maneuver implementer 454 can generate one or more candidate trajectories for each of nodes 1402a, 1402d, 1402e, 1402f, and / or 1402g. In some implementations, the planning module 404 can generate one or more candidate trajectories based on nodes that are determined to be "feasible" and do not yet have any child nodes. For example, referring to Fig.14 , the maneuver implementer 454 based on the implementation sample can generate one or more candidate trajectories for each of nodes 1402e and 1402g. As described above, the homology extractor 453 can determine the feasibility of each node according to the first precision, and the maneuver implementer 454 based on the implementation sample can generate candidate trajectories according to the higher second precision.

[0186] exist Figures 15A to 15F A practical example of using decision diagrams to assess the feasibility of homotopy is shown in .

[0187] In this example (for example, Fig.15A 15), the AV 100 is located on a first road 1510a and faces an intersection between the first road 1510a and a second road 1510b perpendicular to the first road 1510a. Three vehicles 1512a-1512c are moving along the second road 1510b, and a pedestrian 1514 is moving along a sidewalk 1516 parallel to the second road 1510b. The movement of the vehicles 1512a-1512c and the pedestrian 1514 relative to the AV 100 is Fig. 15B This is shown in the graph 1502. For example, track 0 represents the position of the first vehicle 1512a over time, track 1 represents the position of the second vehicle 1512b over time, track 2 represents the position of the third vehicle 1512c over time, and track 3 represents the position of the pedestrian 1514 over time.

[0188] In this traffic scenario, the homotopy extractor 453 determines whether it is feasible for the AV 100 to turn onto the second road 1510b in the following situations: (i) before all three vehicles 1512a-1512c; (ii) between the second vehicle 1512b and the first vehicle 1512a; (iii) between the first vehicle 1512a and the third vehicle 1512c; and (iv) after all three vehicles 1512a-1512c. Fig. 15C As shown, the possibilities may be represented in the form of a decision graph 1504 having a plurality of nodes 1506, each node representing a different set of constraints (e.g., whether to turn onto the road ahead of the vehicles 1512a-1512c or wait for the vehicles 1512a-1512c to pass, and one or more "required" constraints, such as those related to safety, legal constraints, driving capabilities, map constraints, etc.). As an example, a "required constraint" may be a requirement that the AV 100 not contact any of the vehicles 1512a-1512c or pedestrians 1514, while obeying traffic laws, while staying on the road, and while maintaining the safety and comfort of its passengers.

[0189] As described above, the homotopy extractor 453 can assess the feasibility of each node, starting with the highest level node and proceeding through successively lower level nodes. Based on the positions and motions of the vehicles 1512a-1512c and the pedestrian 1514, the homotopy extractor 453 determines that the AV 100 can feasibly turn onto the second road 1510b if: (i) in front of all three vehicles 1512a-1512c (e.g., if Fig.15D (ii) between the second vehicle 1512b and the first vehicle 1512a (eg, Fig.15E ), corresponding to node 1506b; and (iii) after all three vehicles 1512a-1512c (e.g., as shown Fig.15F However, the homotopy extractor 453 determines that the AV 100 cannot feasibly turn onto the second road 1510b between the first vehicle 1512a and the third vehicle 1512c (due to the pedestrian 1514 entering the path of the AV 100 during this time).

[0190] Based on a determination that the AV 100 cannot feasibly turn onto the second road 1510 b, the planning module 404 (e.g., using the implementation sample-based maneuver implementer 454) may generate one or more candidate trajectories corresponding to each of the nodes 1506 a-1506 c (while avoiding generating trajectories for other nodes), and select one of the generated trajectories for control circuitry (e.g., of the AV 100) to execute. Fig.11 and 12 1102) is executed. In some implementations, one of the generated trajectories can be selected based on the quality scores or metrics of the respective trajectories. As described above, the homology extractor 453 can determine the feasibility of each node according to a first precision, and the maneuvering action implementer 454 based on the implementation sample can generate candidate trajectories according to a higher second precision. Therefore, the planning module 404 does not need to generate a higher precision trajectory corresponding to an infeasible operation or task for the AV, but can instead focus its processing resources on generating a higher precision trajectory corresponding to a feasible operation or task for the AV. Therefore, the planning module 404 can select the trajectory of the AV more quickly and efficiently.

[0191] Example Processing

[0192] Fig.16 An example process 1600 for controlling the operation of an AV is shown. Figures 1 to 12 One or more of the systems shown in (e.g., according to Fig.13 , 1415A-15E) to perform processing 1600. As an example, the processing 1600 can be performed at least in part using one or more processors using a planning module 404, which includes a homotopy extractor 453, a maneuver implementer 454 based on an implementation sample, a trajectory score generator 455, and / or a tracking controller 456 (e.g., as Figure 4A , 4B and 13).

[0193] According to process 1600, one or more processors obtain a set of candidate constraints for a road segment that a vehicle is to traverse (block 1602).

[0194] In some implementations, the candidate constraints can include a speed limit associated with at least a portion of the road segment and / or a physical boundary associated with at least a portion of the road segment.

[0195] In some implementations, the candidate constraints may include an acceleration limit associated with the vehicle, a speed limit associated with the vehicle, and / or a braking limit associated with the vehicle.

[0196] In some implementations, the candidate constraints may include an indication of at least one mobile object along the road segment. In addition, for each mobile object, the candidate constraints may include an indication of positioning the vehicle at a specific location relative to the mobile object. At least some of the mobile objects may be vehicles. At least some of the mobile objects may be pedestrians.

[0197] In some implementations, the candidate constraints may include instructions for performing a maneuver with the vehicle, such as changing lanes, turning, accelerating, decelerating, or any other maneuver while traversing a road segment.

[0198] The one or more processors determine a plurality of homotopies (block 1604). Each homotopy includes a different respective combination of candidate constraints for traversing the road segment.

[0199] For each homotopy, the one or more processors generate a first prediction of the movement of the vehicle on the road segment according to a first accuracy (block 1606).

[0200] Based on the first prediction, the one or more processors determine that the vehicle can traverse the road segment according to the subset of homotopies (block 1608). Determining that the vehicle can traverse the road segment according to the subset of homotopies may include: based on the first prediction, determining that the vehicle can traverse the road segment according to the subset of homotopies without colliding with an object.

[0201] The one or more processors determine a plurality of trajectories for the road segment based on the subset of homotopies (block 1610). Determining the plurality of trajectories includes generating at least one second prediction of movement of the vehicle on the road segment based on a second precision. The second precision is greater than the first precision.

[0202] The one or more processors select one of the trajectories (block 1612). In some implementations, selecting one of the trajectories may include determining, for each trajectory, a quality metric for the trajectory, and selecting one of the trajectories based on the quality metric. In some implementations, at least some of the quality metrics may be determined based on a predicted time to traverse the road segment according to the respective trajectory, a predicted safety of a passenger of the autonomous vehicle when traversing the road segment according to the respective trajectory, and / or a predicted comfort of a passenger of the vehicle when traversing the road segment according to the respective trajectory.

[0203] In some implementations, a first trajectory among the plurality of trajectories may include an emergency maneuver for the vehicle. Additionally, selecting one of the trajectories may include receiving data including an indication of a predicted collision between the vehicle and the object and an indication of an emergency maneuver for avoiding the predicted collision. In response to receiving the data, the first trajectory may be selected.

[0204] The one or more processors send instructions to the control circuit of the vehicle to traverse the road segment according to the selected trajectory (1614). As an example, the instructions can be sent to the control module 406 (e.g., Figure 4A ) and / or controller 1102 (e.g., Fig.11 shown).

[0205] In some implementations, determining that a vehicle can traverse a road segment according to a subset of homotopies may include generating a decision graph based on the homotopies. The graph may include a plurality of nodes. Each node may correspond to a different type of action to be performed by the vehicle when traversing the road segment. An example decision graph is shown in Fig.14 and 15C Shown in.

[0206] Additionally, determining that a vehicle is able to traverse a road segment based on homologous subsets may include: (i) determining, for a first subset of nodes, whether the vehicle can safely perform a corresponding type of action, and (ii) avoiding determining, for a second subset of nodes, whether the vehicle can safely perform a corresponding type of action.

[0207] In some implementations, at least some of the nodes may correspond to making a lane change when crossing a road section. In some implementations, at least some of the nodes may correspond to positioning a vehicle in front of a moving object when the vehicle crosses a road section. In some implementations, at least some of the nodes may correspond to positioning a vehicle behind a moving object when the vehicle crosses a road section. In some implementations, at least some of the nodes may correspond to positioning a vehicle between two moving objects when the vehicle crosses a road section. In some implementations, at least some of the nodes may correspond to changing the speed of the vehicle when the vehicle crosses a road section.

[0208] In some implementations, a plurality of trajectories can be determined based on a decision graph.

[0209] In the previous description, multiple embodiments have been described with reference to many specific details, which may be different due to implementation. Therefore, the description and the drawings should be regarded as illustrative, not restrictive. The only and exclusive indication of the scope of the invention, and the applicant's expectation that the content of the scope of the invention is the literal and equivalent scope of the claims issued from this application in the specific form of issuing the claims, including any subsequent amendments. Any definition of the terms used to be included in such claims clearly set forth herein 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 attached claims, the following of the phrase can be an additional step or entity, or a sub-step / sub-entity of the previously described step or entity.

[0210] Additional Examples

[0211] Example implementations of the features described herein are provided below.

[0212] Example 1: A method, comprising: using at least one processor to obtain a set of candidate constraints for a road segment that a vehicle is to traverse; using the at least one processor to determine a plurality of homologs, wherein each of the homologs includes a different corresponding combination of the candidate constraints for traversing the road segment; for each homology: using the at least one processor to generate a first prediction of the movement of the vehicle on the road segment according to a first accuracy; using the at least one processor and based on the first prediction, determining that the vehicle is able to traverse the road segment according to a subset of the homologs; using the at least one processor to determine a plurality of trajectories for the road segment according to the subset of the homologs, wherein determining the plurality of trajectories includes: generating at least one second prediction of the movement of the vehicle on the road segment according to a second accuracy, the second accuracy being greater than the first accuracy; using the at least one processor to select one of the trajectories; and using the at least one processor to send instructions to a control circuit of the vehicle to traverse the road segment according to the selected trajectory.

[0213] Example 2: A method according to Example 1, wherein determining that the vehicle can traverse the road segment according to the subset of the homology includes: based on the first prediction, determining that the vehicle can traverse the road segment according to the subset of the homology without colliding with an object.

[0214] Example 3: A method according to any of the preceding examples, wherein the candidate constraints include at least one of: a speed limit associated with at least a portion of the road segment, and a physical boundary associated with at least a portion of the road segment.

[0215] Example 4: A method according to any of the preceding examples, wherein the candidate constraints include at least one of: an acceleration limit associated with the vehicle, a speed limit associated with the vehicle, and a braking limit associated with the vehicle.

[0216] Example 5: A method according to any of the preceding examples, wherein the candidate constraint includes an indication of at least one moving object along the road segment.

[0217] Example 6: A method according to any of the preceding examples, wherein, for each of the at least one mobile object, the candidate constraint includes an indication to position the vehicle at a specific location relative to the mobile object.

[0218] Example 7: A method according to any of the preceding examples, wherein the at least one moving object includes at least one of the following: a vehicle, and a pedestrian.

[0219] Example 8: A method according to any of the preceding examples, wherein the candidate constraint includes an indication to make a lane change when crossing the road segment.

[0220] Example 9: A method according to any of the preceding examples, wherein selecting one of the trajectories comprises: for each of the trajectories, determining a quality metric for the trajectory, and selecting one of the trajectories based on the quality metric.

[0221] Example 10: A method according to any of the preceding examples, wherein each of the quality metrics is determined based on at least one of: a predicted time to cross the road segment according to a corresponding trajectory, a predicted safety of passengers of the autonomous vehicle when crossing the road segment according to the corresponding trajectory, and a predicted comfort of passengers of the vehicle when crossing the road segment according to the corresponding trajectory.

[0222] Example 11: A method according to any of the preceding examples, wherein a first trajectory of the plurality of trajectories includes an emergency maneuver of the vehicle.

[0223] Example 12: A method according to any of the preceding examples, wherein selecting one of the trajectories comprises: receiving data using the at least one processor, the data comprising: an indication of a predicted collision between the vehicle and an object, and an indication of the emergency maneuver to avoid the predicted collision; and selecting the first trajectory in response to receiving the data.

[0224] Example 13: A method according to any of the preceding examples, wherein determining that the vehicle is capable of traversing the road segment according to the subset of the homology includes: generating a decision graph based on the homology, wherein the decision graph includes a plurality of nodes, and each node corresponds to a different type of action to be performed when the vehicle traverses the road segment.

[0225] Example 14: A method according to any of the preceding examples, wherein determining whether the vehicle is able to traverse the road segment based on the subset of the homology includes: determining whether the vehicle is able to safely perform a corresponding type of action for a first subset of the nodes, and avoiding determining whether the vehicle is able to safely perform a corresponding type of action for a second subset of the nodes.

[0226] Example 15: A method according to any of the preceding examples, wherein at least one of the nodes corresponds to a lane change when crossing the road segment.

[0227] Example 16: A method according to any of the preceding examples, wherein at least one of the nodes corresponds to positioning the vehicle in front of a moving object when traversing the road segment.

[0228] Example 17: A method according to any of the preceding examples, wherein at least one of the nodes corresponds to positioning the vehicle behind a moving object when traversing the road segment.

[0229] Example 18: A method according to any of the preceding examples, wherein at least one of the nodes corresponds to positioning the vehicle between two moving objects when traversing the road segment.

[0230] Example 19: A method according to any of the preceding examples, wherein at least one of the nodes corresponds to changing the speed of the vehicle when traversing the road segment.

[0231] Example 20: A method according to any of the preceding examples, wherein the plurality of trajectories are determined based on the decision graph.

[0232] Example 21: An autonomous vehicle comprising: one or more computer processors; one or more non-transitory storage media storing instructions that, when executed by the one or more computer processors, cause the method described in any one of Examples 1-20 to be performed.

[0233] Example 22: One or more non-transitory storage media storing instructions that, when executed by one or more computing devices, cause the method of any of Examples 1-20 to be performed.

[0234] Related Applications

[0235] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 142,878, filed on January 28, 2021, the entire contents of which are incorporated herein by reference.

Claims

1. A method for a vehicle, comprising: Using at least one processor, obtaining a set of candidate constraints for a road segment to be traversed by a vehicle; determining, using the at least one processor, a plurality of homotopies, wherein respective ones of the homotopies include a different respective combination of the candidate constraints for traversing the road segment; For each homology: generating, using the at least one processor, a first prediction of movement of the vehicle on the road segment according to a first accuracy; determining, using the at least one processor and based on the first prediction, that the vehicle is capable of traversing the road segment according to a subset of the homotopies; Determine, using the at least one processor, a plurality of trajectories for the road segment based on the subset of the homotopies, wherein determining the plurality of trajectories comprises: generating at least one second prediction of movement of the vehicle on the road segment according to a second accuracy, the second accuracy being greater than the first accuracy; selecting one of the trajectories using the at least one processor; and Instructions are sent using the at least one processor to control circuitry of the vehicle to traverse the road segment according to the selected trajectory.

2. The method according to claim 1, wherein: Determining that the vehicle can traverse the road segment according to the subset of the homotopy includes: Based on the first prediction, it is determined that the vehicle can traverse the road segment without colliding with an object according to the subset of the homotopies.

3. The method according to claim 1, wherein: The candidate constraints include at least one of the following: a speed limit associated with at least a portion of the road segment, and A physical boundary associated with at least a portion of the road segment.

4. The method according to claim 1, wherein: The candidate constraints include at least one of the following: acceleration limits associated with the vehicle, the speed limit associated with the vehicle, and A braking limit associated with the vehicle.

5. The method according to claim 1, wherein: The candidate constraint includes an indication of at least one moving object along the road segment.

6. The method according to claim 5, wherein: For each of the at least one mobile object, the candidate constraint includes an indication to position the vehicle at a particular location relative to the mobile object.

7. The method according to claim 5, wherein: The at least one moving object includes at least one of the following: Vehicles, and pedestrian.

8. The method according to claim 1, wherein: The candidate constraint includes an indication to make a lane change when traversing the road segment.

9. The method according to claim 1, wherein: Selecting one of the trajectories includes: For each of the trajectories, determining a quality metric for the trajectory, and One of the trajectories is selected based on the quality metric.

10. The method according to claim 9, wherein: Each of the quality metrics is determined based on at least one of the following: According to the predicted time of the corresponding trajectory passing through the road segment, the predicted safety of passengers of the vehicle when traversing the road segment according to the corresponding trajectory, and A predicted level of comfort for passengers of the vehicle while traversing the route segment according to a corresponding trajectory.

11. The method according to claim 1, wherein: A first trajectory of the plurality of trajectories includes an emergency maneuver of the vehicle.

12. The method according to claim 11, wherein: Selecting one of the trajectories includes: receiving, using the at least one processor, data comprising: an indication of a predicted collision between the vehicle and the object, and an indication of the emergency maneuver to avoid the predicted collision; and In response to receiving the data, the first trajectory is selected.

13. The method according to claim 1, wherein: Determining that the vehicle can traverse the road segment according to the subset of the homotopy includes: A decision graph is generated based on the homotopy, wherein the decision graph includes a plurality of nodes, and each node corresponds to a different type of action to be performed when the vehicle passes through the road segment.

14. The method according to claim 13, wherein: Determining that the vehicle can traverse the road segment according to the subset of the homotopy includes: determining, for a first subset of the nodes, whether the vehicle can safely perform a corresponding type of action, and For a second subset of the nodes, determining whether the vehicle can safely perform a corresponding type of action is avoided.

15. The method according to claim 13, wherein: At least one of the nodes corresponds to making a lane change when traversing the road segment.

16. The method according to claim 13, wherein: At least one of the nodes corresponds to positioning the vehicle in front of a moving object when traversing the road segment.

17. The method according to claim 13, wherein: At least one of the nodes corresponds to positioning the vehicle behind a moving object when traversing the road segment.

18. The method according to claim 13, wherein: At least one of the nodes corresponds to positioning the vehicle between two moving objects when traversing the road segment.

19. The method according to claim 13, wherein: At least one of the nodes corresponds to changing a velocity of the vehicle while traversing the road segment.

20. The method according to claim 13, wherein: The plurality of trajectories are determined based on the decision graph.

21. An autonomous vehicle, comprising: one or more computer processors; One or more non-transitory storage media storing instructions which, when executed by the one or more computer processors, cause the method of claim 1 to be performed.

22. One or more non-transitory storage media storing instructions that, when executed by one or more computing devices, cause the method of claim 1 to be performed.

Images