RU2790105C2 - Method and electronic device for control of self-driving car - Google Patents

Abstract

FIELD: car industry.

SUBSTANCE: invention relates to self-driving cars (hereinafter – SDC), in particular to an electronic device and a method for control of SDC. The method for control of SDC includes generation of a path including a sequence of potential positions, generation of indications of planned speeds for SDC, when following the sequence of potential positions, and inducement of control of SDC along the path in accordance with planned speeds. Generation of planned speeds includes generation of a speed graph having nodes and ribs, generation of time assessment for the node, indicating amount of time, which the device has before launch of an emergency maneuver for prevention of collision with a moving object, if SDC is in a potential state, and the moving object performs an unexpected maneuver in a potential future moment of time, generation of cost for this rib, using time assessment, determination of a sequence of ribs, using cost, and generation of indications of planned speeds, using the sequence of ribs.

EFFECT: safety in operation of a self-driving car is increased.

24 cl, 9 dwg

Description

Technical field

[0001] The present technology mainly relates to unmanned vehicles (SDC); and, in particular, to the electronic device and method of controlling the SDC.

State of the art

[0002] Self-driving vehicles (SDCs) are vehicles that can autonomously navigate terrain through private and/or public spaces. Using a system of sensors that determine the location and/or surroundings of the SDC, logic within or associated with the SDC controls the speed, movement, braking, and steering of the SDC based on the sensor's detected location and surroundings of the SDC. For example, the computer system may use sensor data to generate future trajectories for the SDC on a road segment and may direct the operation of the SDC to follow a selected path on that road segment.

[0003] Typically, the SDC has a variety of sensors that allow the SDC to capture and "understand" its surroundings. The SDC may use various sensor systems such as, but not limited to, camera systems, radar systems, and lidar systems. Different sensor systems may be used to collect different information and/or in a different format about the location and environment of the SDC. For example, camera systems may be used to capture image data of the SDC environment. In another example, lidar systems can be used to collect point cloud data to build 3D mapping representations of the environment and other potential features in the vicinity of the SDC. The SDC may process the captured sensor data to generate predictions using machine learning algorithms, for example, regarding the presence and/or behavior of objects in the vicinity of the SDC. Such predictions can then be used by the SDC to plan the SDC's offline move.

[0004] Motion planning for autonomous driving is the task of planning the desired motion of the SDC in a dynamic environment. For example, the plan may be saved as a trajectory and includes spatial and temporal information about the future movement of the SDC (as planned). Generating collision-free and low-bump trajectories for various urban traffic scenarios is a difficult task.

[0005] US Patent Publication No. 2020/0086855 discloses a vehicle computing system that controls the vehicle to avoid collisions between the vehicle and agents in the environment.

The essence of the invention

[0006] There is a need for systems and methods that avoid, reduce, or overcome the limitations of the prior art.

[0007] It should be noted that an unmanned vehicle (SDC) must cope with complex traffic scenarios. For example, dynamic factors must be taken into account, as well as traffic rules. The trajectory, consisting of information about time and space, indicates the desired movement of the SDC in a dynamic environment. Traffic planning is responsible for finding a trajectory that is possible for the SDC, comfortable for passengers, and/or avoids collisions with other traffic participants.

[0008] The developers of the present technology have realized that SDC motion planning can be divided into two steps. The path for the SDC can be planned in the first step, and in a sense represents "where" the SDC will move through the terrain. In this first step, for example, the geometry of the road and stationary obstacles can be taken into account. In the second step, the SDC can, in a sense, determine "when" the SDC will be located at appropriate points along the path. For example, such information may be represented by a timestamp associated with each point along the path, and hence the speed at which the SDC must move to reach that point at a given time. Developers of the present technology have developed methods and electronics for performing temporal rate planning for a given SDC path.

[0009] It should be noted that the electronic device may include a number of different modules for performing motion planning for the SDC. For example, the electronic device may include a first module for performing high-level route planning that selects a preferred route through a road network organized as a map. A route can be said to define a "global plan" for the SDC as a sequence of roads to arrive at a destination. Since route planning does not take into account the local environment, then lower level planning is carried out. Thus, the second module may be responsible for making decisions about the maneuvers that the SDC should perform in a given situation. For example, the electronic device may decide whether the SDC should keep its lane or change lanes. To perform this maneuver, you can use the third module to determine the trajectory on the road section. The trajectory is then converted into vehicle commands by the fourth module to control the operation of the SDC according to the trajectory to perform the maneuver.

[00010] In at least some embodiments of the present technology, the developers of the present technology have developed methods and electronic devices in which the third module uses a two-stage process to determine a trajectory on the ground and/or on a road section. It can also be said that the third module performs “decoupled planning” of trajectories, where the path is determined in the first stage, and the velocity profile is determined in the second stage. In at least some embodiments of the present technology, the electronic device can perform independent path planning in an iterative manner. In other words, within each scheduling cycle, the electronic device repeats path and velocity scheduling to take into account the latest information about the SDC dynamic environment.

[00011] The developers of the present technology have developed methods and systems for optimizing the process of building a velocity profile for a given path. In some embodiments, the speed profile generated for a given path, as disclosed herein, can ensure that the SDC does not end up in a future state in which a collision with a moving object is imminent. For example, a speed profile can be generated such that when an SDC follows a path according to that speed profile, the SDC will not find itself at a future time at a given position and speed, which would put the SDC at risk of colliding with a moving object and making it unable to respond. to an unexpected maneuver of a moving object.

[00012] In the context of the present technology, during a given traffic scheduling cycle, an electronic device is configured to generate a "graph structure" having nodes and edges, where the nodes represent the respective potential SDC states on a road section, and where the edges represent transitions between potential node states, connected by them. The given potential states of a node may represent the position, time, and speed at which the SDC could potentially be on the path in the future. For each node, the electronic device is configured to determine a "time estimate" indicating the amount of time that the electronic device could have before initiating an emergency maneuver to avoid collision with a moving object if the SDC is in the appropriate potential state and the moving object performs an unexpected maneuver at the time the time of the corresponding potential state.

[00013] The developers of the present technology have realized that the subsequent (potential) rate of the SDC associated with a given node is important in determining this amount of time, sometimes referred to as Time-To-React (TTR). For example, for the same position-time pair, the SDC has a lower TTR at a comparatively higher speed than at a comparatively lower speed. As a result, the electronic device is configured to take into account not only the positional and timing data when determining the time estimate for a given node, but also the associated potential SDC speed associated with that node.

[00014] Once a time estimate is determined for a given node in the graph structure, the electronic device may use the time estimate to assign a cost to an edge connecting that node to a previous node in the graph structure. We can say that this cost represents the security of transition from the potential state associated with the previous node to the potential state associated with this node. One or more algorithms can then be used to determine the sequence of edges in the graph structure based on the corresponding costs. One or more of the sequences may be used to build the corresponding speed profiles for the SDC while following the route.

[00015] The developers of the present technology realized that such a choice of a sequence of edges for constructing a velocity profile allows you to take into account the "unpredictability" of the behavior of a moving object. As will become apparent from the description below, although a number of predicted trajectories can be calculated for a moving object, such predictions may not be correct in the near future if the moving object changes its behavior abruptly. For example, although the current behavior of the moving object indicates that the moving object is moving steadily ahead of the SDC at a constant speed, there is always a risk that the moving object will change its current behavior and perform an unexpected maneuver, such as a sudden braking maneuver.

[00016] In some embodiments of the present technology, developers have developed methods and electronic devices that can be used to generate a velocity profile that ensures that a collision cannot occur if the moving object changes its current behavior (no longer follows the best predicted trajectory) and , rather, performs a different, predetermined, unexpected trajectory. In some embodiments, a speed profile may be built during a given scheduling cycle such that if the SDC follows the path according to that speed profile, no collision is possible until at least the next scheduling cycle. A new velocity profile may be generated in the next scheduling cycle and may be different from the velocity profile generated during this scheduling cycle, however it will still ensure that a "collision free solution" exists in the subsequent scheduling cycle.

[00017] In some embodiments of the present technology, it is contemplated that the electronic device can build a speed profile, portions of which are adapted to provide anti-collision maneuver capability for the SDC. For example, the graph structure may include a number of nodes representing potential states having the same position but different times and/or speeds. As such, depending on their respective potential states, these nodes may be assigned different time estimates, and hence different costs may be assigned to the respective edges. Thus, the edge selection algorithm can determine the sequence of edges that will result in the SDC being at the "best" of a number of nodes associated with the same location. In other words, building a velocity profile in this way can allow the SDC to be at a given position along the path at the "correct" time, and also at the "correct" speed to ensure the existence of a collision-free solution.

[00018] In a first broad aspect of the present technology, a method for controlling an unmanned vehicle (SDC) on the ground is provided. The moving object is in the SDC environment. The SDC is controlled by an electronic device. Said method may be executed by an electronic device. The method includes, at a given time during operation of the SDC, electronically generating a path for the SDC on the ground, where the path includes a sequence of potential positions on the ground to be followed by the SDC. The method includes, at a predetermined point in time during operation of the SDC, electronically generating indications of planned speeds for the SDC while following a sequence of potential positions. The generation of indications includes the generation by an electronic device of a graph structure having nodes and edges. This node represents the first potential state of the SDC on the ground, and the first potential state indicates the first potential position and the first potential speed of the SDC at the first potential future time. This edge connects this node to the previous node in the graph structure and represents the corresponding potential transition from the previous potential state to the first potential state. The generation of indications includes generating by the electronic device a time estimate for a given node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid collision with a moving object if the SDC is in a first potential state and the object performs a predetermined unexpected maneuver in the first potential future point in time. The generation of indications includes electronically generating a cost for a given edge using a given node's time estimate, where the cost indicates the safety of the corresponding potential transition. The generation of indications includes determining, by means of the electronic device, a sequence of ribs using the cost of a given rib, a sequence of ribs having a valid total rib cost. The generation of indications includes the generation by the electronic device of indications of planned speeds using potential states of nodes connected by a series of edges. The method includes, at a given point in time during operation of the SDC, driving the SDC electronically along the track in accordance with the planned speeds.

[00019] In some embodiments of the method, generating a time estimate includes: electronically generating an SDC emergency trajectory if the SDC performs an emergency maneuver while the SDC is in a first potential state; generating, by means of the electronic device, an unexpected trajectory of the object if the object performs a predetermined unexpected maneuver when the object is in a third potential state at a first potential future time; projecting by the electronic device a time point and an end position of the unexpected object trajectory to the time point and end position of the SDC emergency trajectory to determine the distance between the SDC and the object after completion of the emergency maneuver and the predetermined unexpected maneuver; and generating, by the electronic device, a time estimate based on the distance estimate and the first potential speed of the first potential SDC state.

[00020] In some embodiments of the method, the method further includes: electronically generating a plurality of predicted trajectories for an object on the ground; determining by the electronic device the most likely predicted trajectory among the plurality of predicted trajectories; and selecting by the electronic device the third potential state of the object as the potential state of the object at the first potential future point in time in accordance with the most likely predicted trajectory.

[00021] In some embodiments of the method, the moving object comprises the first moving object, and the second moving object is in the SDC environment, and the time estimate is the first time estimate associated with the first object. Generating the indications further includes generating, by the electronic device, a second time estimate for a given node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid collision with the second object if the SDC is in the first potential state and the second moving object is performing in advance a certain unexpected maneuver at the first potential future point in time. Cost generation includes electronically generating a cost for a given edge using a first time estimate and a second time estimate of a given node.

[00022] In some method embodiments, generating a cost for a given edge using a first time estimate and a second time estimate includes electronically calculating a weighted sum of the first time estimate and the second time estimate.

[00023] In some embodiments of the method, a cost is generated in response to a time estimate being below a predetermined threshold.

[00024] In some embodiments of the method, the cost is proportional to the square of the difference between the predetermined threshold and the time estimate.

[00025] In some embodiments of the method, the corresponding potential transition is a transition from a previous potential state to a first potential state at constant acceleration.

[00026] In some embodiments of the method, generating the path includes electronically generating another graph structure for the terrain based on the geometry of the terrain. Another graph structure has other nodes and other edges, where this other node represents the corresponding potential location of the SDC on the ground, and this other edge represents the corresponding potential transition between the corresponding pair of potential positions. Path generation involves electronically determining a sequence of potential positions from another graph structure.

[00027] In some embodiments of the method, the method further includes, at another predetermined point in time during operation of the SDC after the predetermined point in time: electronically generating a different path for the SDC on the ground, wherein the path includes a different sequence of potential positions on the ground, which the SDC must follow; generating by the electronic device a different graph structure having different nodes and different edges, generating by the electronic device a different time estimate for that other node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid a collision with a moving object if the SDC is in the corresponding potential state of a given other node, and the object performs a predetermined unexpected maneuver at the corresponding potential time; selecting by the electronic device a different sequence of edges in the graph structure based on a different time estimate of another given node; electronically generating indications of other planned speeds for the SDC while following a different sequence of potential positions based on a different sequence of fins; and prompting by the electronic control device SDC along the path in accordance with other planned speeds.

[00028] In some embodiments of the method, the terrain is a section of road with a lane, and the SDC follows the moving object in the lane, and the predetermined unexpected maneuver of the moving object is a quick braking maneuver, and the emergency SDC maneuver is a quick braking maneuver.

[00029] In some embodiments of the method, the terrain is a section of road having a first lane and a second lane. SDC is moving in the first lane. The object is moving in the second lane. The predetermined unexpected maneuver of the moving object is a lane change maneuver to the first lane, and the emergency SDC maneuver is a quick braking maneuver.

[00030] In a second broad aspect of the present technology, an electronic device is provided for controlling an unmanned vehicle (SDC) on the ground. The moving object is in the SDC environment. The electronic device is configured to, at a given point in time during operation of the SDC, generate a path for the SDC on the ground, where the path includes a sequence of potential positions on the ground to be followed by the SDC. The electronic device is configured to generate indications of planned speeds for the SDC at a given point in time during operation of the SDC while following the sequence of potential positions. To generate indications, the electronic device is configured to generate a graph structure having nodes and edges. This node represents the first potential state of the SDC on the ground, and the first potential state indicates the first potential position and the first potential speed of the SDC at the first potential future time. This edge connects this node to the previous node in the graph structure and represents the corresponding potential transition from the previous potential state to the first potential state. To generate indications, the electronic device is configured to generate a time estimate for a given node indicating the amount of time that the electronic device has before initiating an emergency maneuver to avoid a collision with a moving object if the SDC is in the first potential state and the object performs a predetermined unexpected maneuver in the first potential future point in time. To generate indications, the electronic device is configured to generate a cost for a given edge using a given node's time estimate, where the cost indicates the safety of the corresponding potential transition. To generate indications, the electronic device is configured to determine a sequence of ribs using the cost of a given rib, where the sequence of ribs has a valid total cost of ribs. To generate indications, the electronic device is configured to generate indications of planned speeds using potential states of nodes connected by a sequence of edges. The electronic device is configured to, at a given time during SDC operation, instruct the SDC to operate along the path in accordance with the planned speeds.

[00031] In some embodiments of an electronic device for generating a time estimate, the electronic device is configured to: generate an emergency SDC trajectory if the SDC performs an emergency maneuver when the SDC is in a first potential state; generate an unexpected trajectory of the object if the object performs a predetermined unexpected maneuver when the object is in the third potential state at the first potential future time; projecting a point in time and an end position of the unexpected object trajectory to a point in time and an end position of the SDC emergency trajectory to determine the distance between the SDC and the object after completing the emergency maneuver and the predetermined unexpected maneuver; and generate a time estimate based on the distance estimate and the first potential velocity of the first SDC potential state.

[00032] In some embodiments of the electronic device, the electronic device is further configured to: generate a plurality of predicted trajectories for an object on the ground; determine the most likely predicted trajectory among the plurality of predicted trajectories; and selecting the third potential state of the object as the potential state of the object at the first potential future point in time according to the most likely predicted trajectory.

[00033] In some embodiments of the electronic device, the moving object comprises a first moving object, and the second moving object is in an SDC environment, where the time estimate is the first time estimate associated with the first object, and in order to generate indications, the electronic device is further configured to: generate a second time estimate for a given node indicating the amount of time the electronic device has before triggering an emergency maneuver to avoid collision with the second object if the SDC is in the first potential state and the second moving object performs a predetermined unexpected maneuver at the first potential future time. To generate the cost, the electronic device is configured to generate a cost for a given edge using the first time estimate and the second time estimate of the given node.

[00034] In some embodiments of the electronic device, in order to generate a cost for a given edge using the first time estimate and the second time estimate, the electronic device is configured to calculate a weighted sum of the first time estimate and the second time estimate.

[00035] In some embodiments of an electronic device, a cost is generated in response to a time estimate being below a predetermined threshold.

[00036] In some embodiments of an electronic device, the cost is proportional to the square of the difference between a predetermined threshold and a time estimate.

[00037] In some embodiments of the electronic device, the corresponding potential transition is a transition from a previous potential state to a first potential state at constant acceleration.

[00038] In some embodiments of the path generating electronic device, the electronic device is configured to: generate a different graph structure for the terrain based on the geometry of the terrain. Another graph structure has other nodes and other edges, and this other node represents the corresponding potential location of the SDC on the ground, and this other edge represents the corresponding potential transition between the corresponding pair of potential positions. To generate the path, the electronic device is configured to determine a sequence of potential positions from another graph structure.

[00039] In some embodiments of the electronic device, the electronic device is further configured to, at a different predetermined point in time during SDC operation after a predetermined point in time: generate a different path for the SDC on the ground, wherein the path includes a different sequence of potential ground positions , which the SDC should follow; generate a different graph structure having different nodes and different edges, generate a different time estimate for this other node, indicating the amount of time the electronic device has before triggering an emergency maneuver to avoid a collision with a moving object, if the SDC is in the corresponding potential state of this other node and the object performs a predetermined unexpected maneuver at the appropriate potential time; select a different sequence of edges in the graph structure based on a different time estimate of another given node; generate indications of other planned speeds for the SDC while following a different sequence of potential positions based on a different sequence of edges; and instruct the SDC to operate along the path in accordance with other planned speeds.

[00040] In some embodiments of the electronic device, the terrain is a section of road having a lane, and the SDC follows a moving object in a lane where the predetermined unexpected maneuver of the moving object is a quick braking maneuver and the emergency SDC maneuver is a quick braking maneuver .

[00041] In some embodiments of the electronic device, the terrain is a section of road having a first lane and a second lane, and the SDC is moving in the first lane and the object is moving in the second lane, and the predetermined unexpected maneuver of the moving object is the maneuver with a lane change to the first lane, and the SDC emergency maneuver is a quick braking maneuver.

[00042] In the context of the present description, the term "environment" of a given vehicle refers to the area or volume around a given vehicle, including part of its current environment, available for scanning using one or more sensors installed on a given vehicle, for example, for generating a three-dimensional map of such an environment or detecting objects in it.

[00043] As used herein, a "region of interest" may broadly include a portion of the observed environment of a lidar system in which one or more objects may be detected. It should be noted that the area of interest of the lidar system can be affected by various conditions such as, but not limited to: the orientation of the lidar system (eg, the direction of the optical axis of the lidar system); position of the lidar system in relation to the environment (for example, distance above the ground and adjacent terrain and obstacles); operating parameters of the lidar system (for example, radiation power, computational settings, specified operating angles), etc. The ROI of a lidar system can be defined, for example, as a planar angle or a solid angle. In one example, the ROI may also be determined within a certain range of distances (eg, up to 200 m or so).

[00044] As used herein, a "server" is a computer program that runs on appropriate hardware and is capable of receiving requests (eg, from client devices) over a network and fulfilling or causing those requests to be executed. The hardware may be implemented as one physical computer or one physical computer system, but neither is required with respect to the present technology. In this context, the use of the term "server" is not intended to imply that every task (e.g. received instructions or requests) or any particular task was accepted, executed or called to be executed by the same server (i.e. the same software and/or or hardware) this means that any number of software elements or hardware devices may be involved in receiving/sending, executing or facilitating any task or request or the consequences of any task or request; and all such software and hardware may be a single server or multiple servers, both of which are included in the expression "at least one server".

[00045] As used herein, an "electronic device" is any computer hardware that is capable of running software appropriate for the task at hand. In the context of the present description, the term "electronic device" implies that the device can function as a server for other electronic devices and client devices, however, this is not necessary in relation to the present technology. Thus, some (non-limiting) examples of electronic devices include personal computers (desktops, laptops, netbooks, etc.), smartphones and tablets, and network equipment such as routers, switches, and gateways. It should be understood that in this context, the fact that a device functions as an electronic device does not mean that it cannot function as a server for other electronic devices. The use of the term "electronic device" does not preclude the use of multiple client devices to receive/send, perform or enable any task or request, or the consequences of any task or request, or the steps of any method described herein.

[00046] As used herein, a "client device" is any computer hardware that is capable of running software appropriate for the task at hand. In the context of the present description, the term "client device" is usually associated with the user of the client device. Thus, some (non-limiting) examples of client devices include personal computers (desktops, laptops, netbooks, etc.), smartphones and tablets, and network equipment such as routers, switches, and gateways. It should be noted that a device acting as a client device in this context is not prohibited from acting as a server for other client devices. The use of the term "client device" does not preclude the use of multiple client devices to receive/send, perform, or enable any task or request, or the consequences of any task or request, or the steps of any method described herein.

[00047] In the context of the present description, the expression "information" includes information of any nature or kind that can be stored in a database. Thus, information includes, but is not limited to, audiovisual works (images, films, sound recordings, presentations, etc.), data (location data, numerical data, etc.), text (opinions, comments , questions, messages, etc.), documents, spreadsheets, etc.

[00048] In the context of the present description, the expression "software component" means the inclusion of software (suitable for a particular hardware context) that is both necessary and sufficient to perform the particular function(s) referred to.

[00049] As used herein, the term "computer storage medium" (also referred to as "media") is intended to include media of any kind and type, including, without limitation, RAM, ROM, disks (CD-ROMs), DVDs, floppy disks, hard drives, etc.), USB keys, solid state drives, tape drives, etc. A plurality of components may be combined to form computer storage media, including two or more media components of the same type and/or two or more media components of different types.

[00050] As used herein, a "database" is any structured set of data, regardless of its specific structure, database management software, or computer hardware on which the data is stored, implemented, or otherwise made available for use. The database may reside on the same hardware as the process that stores or uses the information stored in the database, or it may reside on separate hardware such as a dedicated server or multiple servers.

[00051] In the context of the present description, the words "first", "second", "third", etc. were used as adjectives only for the purpose of providing a distinction between the nouns they modify relative to one another, and not for the purpose of describing any specific relationship between those nouns. Thus, for example, it should be understood that the use of the terms "first database" and "third server" is not intended to imply any particular order, type, chronology, hierarchy or ranking (for example) of/between servers and their use (itself by itself) does not imply that any "second server" must necessarily exist in any given situation. Also, as discussed here in other contexts, referring to a "first" element and a "second" element does not prevent the two elements from being the same actual real world element. Thus, for example, in some cases the "first" server and the "second" server may be the same software and/or hardware components, in other cases they may be different software and/or hardware components.

[00052] Each of the implementations of the present technology has at least one of the above objects and/or aspects, but does not necessarily have all of them. It should be understood that some aspects of the present technology that have arisen in an attempt to achieve the aforementioned goal may not satisfy this goal and/or satisfy other goals that are not explicitly described in this document.

[00053] Additional and/or alternative features, aspects, and advantages of implementations of the present technology will become apparent from the following description, the accompanying drawings, and the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

[00054] These and other features, aspects, and advantages of the present technology will become more apparent from the following description, the appended claims, and the accompanying drawings, in which:

[00055] Figure 1 depicts a schematic diagram of an exemplary computer system configured to implement some non-limiting embodiments of the present technology.

[00056] FIG. 2 is a schematic diagram of a networked computing environment suitable for use with certain non-limiting embodiments of the present technology.

[00057] FIG. 3 depicts a representation of a vehicle and an object moving on a stretch of road, in accordance with some embodiments of the present technology.

[00058] FIG. 4 depicts a representation of the road and path graph structure generated for the road segment of FIG. 3, in accordance with some embodiments of the present technology.

[00059] FIG. 5 is a representation of the speed graph structure generated for the vehicle of FIG. 3 in accordance with some embodiments of the present technology.

[00060] FIG. 6 depicts a representation of edge sequences determined from the rate graph structure of FIG. 5, in accordance with some embodiments of the present technology.

[00061] FIG. 7 depicts a representation of potential future states of the vehicle and object of FIG. 3, in accordance with some embodiments of the present technology.

[00062] FIG. 8 depicts a representation of potential future states of a vehicle and an object in another scenario, in accordance with some embodiments of the present technology.

[00063] FIG. 9 is a schematic flow diagram of a method performed by an electronic device in accordance with at least some non-limiting embodiments of the present technology.

Detailed description

[00064] The examples and conventions provided herein are intended primarily to help the reader understand the principles of the present technology, and not to limit its scope to such specific examples and terms. It should be understood that those skilled in the art will be able to develop various mechanisms that, although not explicitly described in this document, nevertheless embody the principles of the present technology and are included in its essence and scope.

[00065] In addition, the following description may describe implementations of the present technology in a relatively simplified manner for purposes of ease of understanding. Those skilled in the art will appreciate that various implementations of the present technology may be more complex.

[00066] In some cases, examples of modifications to the present technology that are considered useful may also be set forth. This is only to promote understanding and, again, not to rigorously define the scope or delineate the boundaries of the present technology. These modifications are not an exhaustive list, and other modifications may be made by one skilled in the art while still remaining within the scope of the present technology. In addition, cases where examples of modifications are not given should not be interpreted to mean that no modifications can be made and/or that what is described is the only way to implement such an element of the present technology.

[00067] Moreover, all statements in this document that set forth the principles, aspects, and implementations of technology, as well as their specific examples, are intended to cover both their structural and functional equivalents, whether they are currently known or are being developed in the future. Thus, for example, those skilled in the art will appreciate that any block diagrams herein represent conceptual views of an illustrative circuit embodying the principles of the present technology. Likewise, it will be understood that any and all flowcharts, flow charts, state transition diagrams, pseudo-codes, and the like represent various processes that can be as such represented on computer-readable media and executed by a computer or processor, whether or not shown. such a computer or processor explicitly or not.

[00068] The functions of the various elements shown in the figures, including any functional unit labeled "processor", can be provided through the use of specialized hardware, as well as hardware capable of executing software in combination with appropriate software. When provided by a processor, the functions may be provided by one dedicated processor, one shared processor, or multiple individual processors, some of which may be shared. In addition, explicit use of the term "processor" or "controller" should not be construed as referring solely to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), read-only memory (ROM) for software storage, random access memory (RAM), and non-volatile storage. Other hardware, traditional and/or specialized, may also be included.

[00069] Software modules, or simply modules, which may be referred to as software, may be represented herein as any combination of flowchart elements or other elements indicating the execution of process steps and/or textual description. Such modules may be executed by hardware that is explicitly or implicitly shown.

[00070] With these fundamentals in mind, consider some non-limiting examples to illustrate various implementations of aspects of the present technology.

computer system

[00071] Referring first to Figure 1, there is shown a schematic diagram of a computer system 100 suitable for use with some implementations of the present technology. Computer system 100 includes various hardware components including one or more single or multi-core processors collectively represented by processor 110, solid state drive 120, and memory 130, which may be RAM or any other type of memory.

[00072] Communication between various components of computer system 100 may be provided by one or more internal and/or external buses (not shown) (e.g., PCI bus, Universal Serial Bus, Firewire IEEE 1394 bus, SCSI bus, Serial-ATA bus, etc. .d.) with which various hardware components are electronically coupled. In accordance with embodiments of the present technology, the solid state drive 120 stores program instructions suitable for loading into memory 130 and execution by processor 110 to determine the presence of an object. For example, the program instructions may be part of a vehicle control application executed by processor 110. It should be noted that computer system 100 may have additional and/or optional components (not shown), such as network communication modules, localization modules, and the like.

Networked Computing Environment

[00073] With reference to FIG. 2, a networked computing environment 200 is depicted suitable for use with certain non-limiting embodiments of the present technology. Networked computing environment 200 includes an electronic device 210 associated with vehicle 220 and/or associated with a user (not shown) who is associated with vehicle 220 (eg, as an operator of vehicle 220). The environment 200 also includes a server 235 communicating with the electronic device 210 via a communications network 240 (eg, the Internet, etc., as will be described in more detail below).

[00074] In at least some non-limiting embodiments of the present technology, the electronic device 210 is associated with the ability to communicate with the control systems of the vehicle 220. The electronic device 210 can be configured to control various operating systems of the vehicle 220, including, but not limited to: ECU (engine control unit), steering systems, braking systems, and signaling and lighting systems (i.e. headlights, brake lights, and/or direction indicators). In such an embodiment, vehicle 220 may be an unmanned vehicle 220.

[00075] In some non-limiting embodiments of the present technology, network computing environment 200 may include a GPS satellite (not shown) transmitting and/or receiving a GPS signal to/from electronic device 210. It should be understood that the present technology is not limited to GPS and may use a location technology other than GPS. It should be noted that the GPS satellite may not be used at all.

[00076] The vehicle 220 with which the electronic device 210 is associated can be any vehicle, recreational or otherwise, such as a private or commercial car, truck, motorcycle, or the like. Although vehicle 220 is depicted as a ground vehicle, this may not be the case in all non-limiting embodiments of the present technology. For example, in some non-limiting embodiments of the present technology, vehicle 220 may be a waterborne vehicle, such as a boat, or an aircraft, such as a flying drone.

[00077] Vehicle 220 may be user driven or may be a driverless vehicle. In some non-limiting embodiments of the present technology, it is contemplated that vehicle 220 may be implemented as an unmanned vehicle (SDC). It should be noted that the specific parameters of the vehicle 220 are not limiting, these specific parameters include, for example: vehicle manufacturer, vehicle model, vehicle year, vehicle weight, vehicle dimensions, vehicle weight distribution, surface area vehicle, vehicle height, transmission type (eg 2x or 4x), tire type, brake system, fuel system, mileage, vehicle identification number and engine size.

[00078] According to the present technology, the implementation of the electronic device 210 is not particularly limited. For example, electronic device 210 may be implemented as a vehicle engine control unit, a vehicle central processing unit, a vehicle navigation device (eg, TomTom™, Garmin™), a tablet, a personal computer built into vehicle 220, and the like. Thus, it should be noted that electronic device 210 may or may not be permanently associated with vehicle 220. Additionally or alternatively, electronic device 210 may be implemented in a wireless communication device such as a mobile phone (eg, smartphone or cordless phone). In certain embodiments, the electronic device 210 has a display 270.

[00079] Electronic device 210 may include some or all of the components of computer system 100 depicted in FIG. 1, depending on the particular embodiment. In some embodiments, electronic device 210 is an on-board computing device and includes a processor 110, a solid state drive 120, and memory 130. In other words, electronic device 210 includes hardware and/or software and/or firmware, or a combination thereof for data processing, as will be described in more detail below.

[00080] In some non-limiting embodiments of the present technology, communication network 240 is the Internet. In alternative non-limiting embodiments of the present technology, communications network 240 may be implemented as any suitable local area network (LAN), wide area network (WAN), private communications network, and the like. It should be clearly understood that the implementations for the communications network 240 are provided for purposes of illustration only. A communication link (not individually numbered) is provided between electronic device 210 and communication network 240, the implementation of which will depend on, among other things, how electronic device 210 is implemented. By way of example only, and not limitation, in those non-limiting embodiments of the present technology where the electronic device 210 is implemented as a wireless communication device such as a smartphone or navigation device, the communication link may be implemented as a wireless communication link. Examples of wireless links may include, without limitation, a 3G network link, a 4G link, and the like. Communication network 240 may also use a wireless connection to server 235.

[00081] In some embodiments of the present technology, server 235 is implemented as a computer server and may include some or all of the components of computer system 100 in FIG. In one non-limiting example, server 235 is implemented as a Dell™ PowerEdge™ server running the Microsoft™ Windows Server™ operating system, but may also be implemented in any other suitable hardware, software and/or firmware, or combinations thereof. In the illustrated non-limiting embodiment of the present technology, server 235 is the only server. In alternative non-limiting embodiments of the present technology, the functionality of the server 235 may be distributed and may be implemented by multiple servers (not shown).

[00082] In some non-limiting embodiments of the present technology, the processor 110 of the electronic device 210 may communicate with the server 235 to receive one or more updates. Such updates may include, but are not limited to, software updates, map updates, route updates, weather updates, and the like. In some non-limiting embodiments of the present technology, the processor 110 may also be configured to transmit to the server 235 some operational data, such as routes traveled, traffic data, performance data, and the like. Some or all of such data transmitted between a vehicle 220 and server 235 may be encrypted and/or anonymized.

[00083] It should be noted that electronic device 210 may use a variety of sensors and systems to collect information about the environment 250 of vehicle 220. As seen in FIG. 2, vehicle 220 may be equipped with multiple sensor systems 280. It should be noted that different sensor systems from the plurality of sensor systems 280 may be used to collect different types of data regarding the environment 250 of the vehicle 220.

[00084] In one example, the plurality of sensor systems 280 may include various optical systems, including but not limited to one or more camera-type sensor systems that are mounted on vehicle 220 and are in communication with the processor 110 of the electronic device 210. Generally speaking, one or more camera-type sensor systems may be configured to collect image data about various parts of the environment 250 of vehicle 220. In some cases, image data provided by one or more camera-type sensor systems may be used by electronic device 210 to perform procedures. object detection. For example, the electronic device 210 may be configured to feed image data provided by one or more camera type sensor systems to an Object Detection Neural Network (ODNN) that is trained to locate and classify potential objects in the environment 250 of the vehicle 220 .

[00085] In another example, the plurality of sensor systems 280 may include one or more radar-type sensor systems that are mounted on vehicle 220 and in communication with processor 110. Generally speaking, one or more radar-type sensor systems may be configured to use radio waves to collect data about various parts of the environment 250 of the vehicle 220. For example, one or more radar-type sensor systems can be configured to collect radar data about potential objects in the environment 250 of the vehicle 220, such data potentially representing the distance of the objects from a system of radar-type sensors, the orientation of objects, the speed and / or speed of objects, etc.

[00086] In a further example, the plurality of sensor systems 280 may include one or more optical detection and ranging (LIDAR) systems that are mounted on vehicle 220 and are in communication with processor 110. Generally speaking, a lidar system configured to collect data about the environment 250 of the vehicle 220, used, for example, to build a multidimensional map of objects in the environment 250 of the vehicle 220. The lidar system can be installed or modified on the vehicle 220 at various locations and/or in various configurations to collect information about the environment 250 of the vehicle 220.

[00087] For example, depending on the implementation of the vehicle 220 and the lidar system, the lidar system may be mounted on the inside, top of the windshield of the vehicle 220. However, other mounting locations for the lidar system are within the scope of this disclosure, including on the rear window, side windows, front hood, roof, front grille, front bumper, or side of the vehicle 220.

[00088] In the context of the present technology, electronic device 210 is configured to detect one or more objects in environment 250 of vehicle 220 based on data received from one or more camera systems and one or more lidar systems. For example, an electronic device 210 configured to detect a given object in the environment 250 of vehicle 220 may be configured to identify lidar data and camera data associated with a given object, generate a "embedding" representing features associated with a given object, and detect an object by creating a bounding box for the object.

Scenario 1

[00089] Referring to Figure 3, there is an illustrative example 300 of a vehicle 220 in an environment 250. Assume that the vehicle 220 is moving along a section 350 of the road. The electronic device 210 may receive from the sensor system 280 information about the surroundings 250 of the vehicle 220 and, in particular, about the section 350 of the road and about one or more "actors" (also sometimes called "agents") on the section 350 of the road, for example, neighboring objects in the environment of the vehicle 220. For example, the electronic device 210 may receive information collected about the object 310 on the section 350 of the road. You can say that the object 310 "dynamic" or moving on the section 350 of the road.

[00090] It should be noted that vehicle 220 operating on road section 350 and in the vicinity of object 310 is only one non-limiting example of the present technology. In another example, vehicle 220 may be operating in a different area and near moving object 310. In this other example, vehicle 220 and moving object 310 may be moving in respective lanes that are about to converge. In some embodiments of the present technology, the vehicle 220 may operate on terrain other than a road section, such as, for example, a sidewalk section and/or an off-road section. In the context of the present technology, the electronic device 210 is configured to perform traffic planning for the vehicle 220 on the road section 350 . As will become apparent from the description below, vehicle 220 motion planning may be performed through a two-step process, ie, a path planning step and a speed planning step.

[00091] The electronic device 210 is configured to generate at a given time a "road graph" for the section 350 of the road to control the vehicle 220. To better illustrate this, we now turn to Fig.4, where at a given time the electronic device 210 is made with the ability to generate a road graph 420 for a section 350 of the road. The road graph 420 has a plurality of nodes (not numbered) and a plurality of edges (not numbered) connecting respective nodes from the plurality of nodes. For example, an edge 450 of the road graph 420 connects the first node 451 and the second node 452. This node is associated with the respective potential position of the vehicle 220 on the section 350 of the road. This edge represents the transition of the vehicle 220 between the potential positions of the corresponding pair of nodes. For example, edge 450 represents the transition of vehicle 220 between its potential positions of first node 451 and second node 452. It should be noted that the size and shape of the road graph 420 may depend on, among other things, the size and shape of the road section 350, as well as other geometries. characteristics of road section 350 and/or environment 250.

[00092] It should be noted that electronic device 210 may be configured to store information in association with a corresponding node and/or corresponding edge of road graph 420. For example, electronic device 210 may be configured to store positional data in association with a given node. In another example, the electronic device 210 may be configured to store, in association with a given edge, the positional data of a respective pair of nodes.

[00093] It is contemplated that additional data to data not exhaustively mentioned above may be stored in association with a corresponding node and/or edge of road graph 420. For example, during road graph 420 generation, electronic device 210 may be configured to generate attributes for corresponding nodes and/or edges of the road graph 420 and store these attributes along with the corresponding nodes and/or edges. The type of attributes that can be stored in associated with the respective nodes and/or edges is not particularly limited. It should be noted that electronic device 210 may use these attributes when evaluating sequences of nodes and/or edges in road graph 420.

[00094] The purpose of the road schedule 420 (and the analysis of the data contained therein) is to create a "path" that the vehicle 220 must follow on the section 350 of the road. Generally speaking, a given path for a given road section is represented by a corresponding sequence of nodes/edges of the corresponding road graph and contains information about a sequence of positions, sometimes referred to as "stations", on a given road section that the vehicle 220 could potentially follow during operation.

[00095] In some embodiments, the electronic device 210 may be configured to generate a plurality of potential paths based on the road graph 420 and perform a path evaluation process to select a target path (among the plurality of potential paths) that the vehicle 220 should follow. In one In a non-limiting example, during the path estimation process, electronic device 210 may be configured to apply "cost criteria" to attributes of nodes and/or edges. The electronic device 210 may also determine the "total cost" for the various sequences of edges corresponding to the respective candidate paths. The electronic device 210 may also rank the respective candidate paths based on how much the respective edge sequences cost.

[00096] Returning to the description of FIG. 4, suppose that the electronic device 210 generates a path 480 that the vehicle 220 is to follow on the road section 350. Path 480 corresponds to a corresponding sequence of nodes/edges from road graph 420. Thus, path 480 can be said to include a sequence of potential positions on road segment 350 that vehicle 220 is to follow. For example, a sequence of potential positions includes potential positions associated with the first node 451, the second node 452, and other nodes (not numbered) of the path 480.

[00097] As mentioned above, the sequence of potential positions corresponding to the path 480 is sometimes referred to as the stations where the vehicle 220 should move on the section 350 of the road. Electronic device 210 is configured to use path 480 to steer vehicle 220 on road section 350 at a given time. More specifically, the electronic device 210 is configured to generate trajectory data for the vehicle 220 to actually follow the positions (stations) on the road section 350 corresponding to the path 480.

[00098] As part of the trajectory data, electronic device 210 is configured to construct a "speed profile" for vehicle 220 as it follows path 480 on road section 350. Generally speaking, a speed profile contains indications of the planned speeds for vehicle 220 as it follows the sequence of potential positions corresponding to path 480. The purpose of building a speed profile is to plan, at a given time, the future speeds at which vehicle 220 should operate following the sequence of potential positions. track 480 (station on section 350 of the road).

[00099] In some embodiments of the present technology, electronic device 210 may be configured to currently perform an appropriate scheduling iteration during which electronic device 210 uses predetermined path information to generate trajectory data, including a speed profile, for vehicle 220 The electronic device 210 is configured to use the trajectory data thus generated to plan the autonomous operation of the vehicle 220 on the road section 350 along this path until the next point in time (corresponding to the next scheduling cycle). A subsequent scheduling iteration may be performed by electronic device 210 at the next point in time in a manner similar to how electronic device 210 is configured to perform a corresponding scheduling iteration at a given point in time, taking into account new and/or updated information about the environment 250 of vehicle 220. Note, that once vehicle 220 is actually operating as planned using trajectory data, additional safety control can be provided by vehicle 220's auxiliary safety systems. For example, once vehicle 220 is actually being controlled by electronic device 210 on track as planned , using the trajectory data, one or more collision detection and avoidance systems can be used to further reduce the risk of collisions on road section 350. The type of collision detection and avoidance systems that can be used is not particularly limited.

[000100] In some embodiments of the present technology, developers have developed methods and electronics for generating speed profiles for a given vehicle in order to reduce the risk of collision with a moving object. In particular, the developers of the present technology have developed methods and electronic devices for planning speeds for the operation of the vehicle 220 so that if the vehicle 220 operates in accordance with the planned speeds, the vehicle 220 would have enough "reaction time" to an unexpected maneuver of a moving object. 310, that is, the vehicle 220 operating at the planned speeds will have time to start and perform an emergency maneuver in response to the unexpected maneuver of the moving object 310.

[000101] The developers of the present technology have realized that scheduling vehicle 220 speeds as disclosed herein can reduce the risk of vehicle 220 being in a future state on road section 250 resulting in an unavoidable collision. Unlike collision detection and avoidance systems, which are capable of "detecting" and "responding" to the risk of a collision, the ability to "plan" future speeds for vehicle 220, as disclosed herein for autonomous operation of vehicle 220, can prevent, so that the vehicle 220 generally finds itself in hopeless situations.

[000102] The developers of the present technology have realized that scheduling vehicle 220 so that vehicle 220 maintains a predetermined safety distance (at different speeds) from vehicle 220 is not sufficient to prevent vehicle 220 from getting into deadlock. This is because the braking distance of the vehicle 220 changes depending on the current speed of the vehicle 220 when the vehicle 220 initiates an emergency maneuver, such as a quick braking maneuver. Without wishing to be bound by any particular theory, developers have devised an electronic device that plans the speed of vehicle 220 in a way that allows longer safety distances to be maintained at relatively higher speeds than at relatively slower speeds.

[000103] In the context of the present technology, the electronic device 210 is configured to generate a "rate graph" (sometimes referred to as a "rate graph structure"). This speed graph can be used to generate indications of the planned speeds of the speed profile that vehicle 220 should operate on road section 350 following route 480.

[000104] To better illustrate this, referring now to FIG. 5, where at a given time the electronic device 210 is configured to generate a velocity graph 500 for path 480. The velocity graph 500 comprises nodes and edges. This node represents the corresponding potential state of the vehicle 220 at the road section 350, and where the corresponding potential state indicates the first potential position and the first potential speed of the vehicle 220 at the corresponding potential future time. This edge connects the given node to the previous node in the velocity graph 500 and represents the corresponding potential transition from the previous node's previous potential state to the given node's potential state.

[000105] For example, node 501 represents a corresponding potential state and indicates (i) a corresponding potential position, (ii) a corresponding time point, and (iii) a corresponding potential speed. In some embodiments, the node 501 may represent the current state of the vehicle 220 on the section 250 of the road. For example, the state associated with node 501 may indicate the current position of vehicle 220 (e.g., the first station on track 480), the current time, and the current speed of vehicle 220.

[000106] Node 501 is connected to node 502 via edge 512. It is contemplated that node 502 may represent a second potential state of vehicle 220. This second potential state may indicate a second potential position, a second time, and a second potential speed. Also, by way of example, the second potential state associated with node 502 may indicate the next position/station on path 480 after the current position of vehicle 220 at the corresponding future time after the current time, and the corresponding potential speed. In this example, edge 512 may indicate a transition between the current state of vehicle 220 and the second potential state of vehicle 220. For example, the transition of edge 512 may indicate a constant acceleration transition between the current state and the second potential state. In other words, edge 512 may represent a transition that allows vehicle 220 to move from a current state (e.g., current position/station, current time, current speed) to another potential state (e.g., next position/station along path 480, corresponding future time after the current time and the corresponding potential speed) with constant acceleration.

[000107] Node 501 is also connected to node 503 via edge 513. It is contemplated that node 503 may represent a third potential state of vehicle 220. This third potential state may indicate a third potential position, a third time, and a third potential speed. Also, by way of example, the third potential state associated with node 503 may indicate a different next position/station on path 480 after the current position of vehicle 220 at a corresponding future time after the current time, and a corresponding potential speed. In this example, edge 513 may indicate a transition between the current vehicle state 220 and a third potential vehicle state 220.

[000108] It is contemplated that although the two nodes represent two different potential states of the vehicle 220, the two different potential states may share at least some of the state parameters. This means that the second candidate state of node 502 and the third candidate state of node 503 can share at least some state parameters. For example, the second potential state of node 502 and the third potential state of node 503 may share the same next position/station of track 480, but may have different future times and different potential speeds. In another example, the second potential state of node 502 and the third potential state of node 503 may share the same next position/station of track 480 and the same future point in time, but have different potential speeds. In an additional example, the second potential state of node 502 and the third potential state of node 503 may share the same next position/station of track 480 and the same potential speed, but may have different future times.

[000109] In at least some embodiments, nodes 502, 503, and 504 may represent potential vehicle states 220 that share the next position/station along path 480, but have different times and/or different potential speeds. Therefore, respective edges 512, 513, and 514 indicate respective transitions at respective constant accelerations, which, if performed by vehicle 220, may allow vehicle 220 to reach the next position/station on path 480 at certain future times and/or at various potential speeds. In other words:

- if the vehicle 220 moves from the current position/station to the next position/station at the first constant acceleration (rib transition 512), the vehicle 220 will be in the next position/station at the corresponding future time and at the corresponding potential speed corresponding to the second potential state node 502;

- if the vehicle 220 moves from the current position/station to the next position/station at the second constant acceleration (transition of the rib 513), the vehicle 220 will be in the next position/station at the appropriate time in the future and at the corresponding potential speed corresponding to the third potential node state 503; And

- if the vehicle 220 moves from the current position/station to the next position/station with a third constant acceleration (rib transition 514), the vehicle 220 will be in the next position/station at the corresponding future time and at the corresponding potential speed corresponding to the fourth potential state node 504.

[000110] As will become apparent from the description below, generating a speed graph 500 in which potential states indicate positions/stations, future times, and potential speeds may allow the electronic device 210 to choose not only "when" the vehicle 220 should be in a given position/station along track 480, but also choose "at what speed" vehicle 220 should be located at a given position/station along track 480.

[000111] The electronic device 210 is configured to evaluate the edge sequences on the velocity graph 500. For example, the electronic device 210 may be configured to determine the "cost" for the respective edges of the rate graph 500, and then determine the total cost of the respective sequences to select the sequence with the lowest total cost and/or the acceptable total cost.

[000112] FIG. 6 shows the first sequence 601, the second sequence 602, and the third sequence 603 of edges on a velocity graph 600. The electronic device 210 may determine the costs for the respective edges and determine the total costs for the first sequence 601, the second sequence 602, and the third sequence 603. The electronic device 210 may be configured to distinguish between the first sequence 601, the second sequence 602, and the third sequence 603 based on their respective total costs. In one example, electronic device 210 may be configured to select second sequence 602 as the target sequence on rate graph 500 if second sequence 602 has the lowest total cost among the combined costs of first sequence 601, second sequence 602, and third sequence 603. In another example, the electronic device 210 may be configured to select the second sequence 602 as the target sequence on the rate graph 500 if the second sequence 602 has a total cost that is below a predetermined allowable cost threshold. Such a threshold may be predetermined by the operator of the electronic device 210 and may vary depending on specific implementations of the present technology.

[000113] It should be noted that the target sequence on the rate graph 500 contains information for constructing a rate profile for a given point in time. For example, the target sequence contains information indicating the sequence of transitions at appropriate constant accelerations to be performed by the vehicle 220 while following the path 480. In addition, the target sequence contains information indicating the sequence of planned states in which the vehicle 220 should be in section 350 road following route 480. More specifically, the nodes connected by the target edge sequence indicate (i) respective times and (ii) respective planned vehicle 220 speeds when vehicle 220 is at respective positions/stations along path 480.

[000114] Therefore, it is contemplated that electronic device 210 may be configured to perform target sequence processing on speed graph 500 to generate indications of planned speeds and/or accelerations at appropriate times for vehicle 220 to follow the positions/stations of track 480 .

[000115] The developers of the present technology have developed methods and electronic devices that allow the creation of planned/target speed profiles that contribute to the safety of passengers in the vehicle 220. More specifically, the planned speed profile can be built by the electronic device 210, taking into account unexpected maneuvers performed by dynamic objects surrounded by a vehicle 220.

[000116] As will become apparent from the description below, the developers of the present technology have developed methods and electronic devices that allow you to plan speeds for the vehicle 220 so that the electronic device 210 has enough time to perform an emergency maneuver to avoid a collision with a moving object, if the vehicle 220 follows the path 480 in accordance with these planned speeds.

[000117] In the context of the present technology, a method has been developed to generate costs for the respective edges of the speed graph 500 such that a target sequence of edges selected based on these costs indicates planned speeds that will provide enough time for the electronic device 210 to perform an emergency maneuver if the traffic means 220 follows route 480 in accordance with these planned speeds.

[000118] How the cost of fin 516 is determined will now be described in more detail (see FIG. 5). Edge 516 connects node 503 (previous node) to node 506 (next node). It is contemplated that the cost of rib 516 can be generated based on at least information associated with the potential state of vehicle 220 and node 506. More specifically, electronic device 210 is configured to generate a "time estimate" for the potential state of vehicle 220 and node 506. The electronic device 210 is then configured to use node 506's time estimate to generate a cost for edge 516. In those embodiments where more than one edge has node 506 as the next node, node 506's time estimate may be used to generate the appropriate cost for each of more than one edge connecting the corresponding previous nodes to node 506.

Time Estimate Generation

[000119] Referring to FIG. 7, a representation 700 of potential future states of vehicle 220 and moving object 310 is depicted. The current state 710 of vehicle 220 is illustrated and can be associated with node 501 (see FIG. 5) and indicate the triple "p0, t0, v0", where p0 represents the current position of the vehicle 220, t0 represents the current time, and v0 represents the current speed of the vehicle 220. Also illustrated is the current state 730 of the moving object 310, which may indicate the triple "pA, t0, vA", where pA represents the current position of the moving object 310 and vB represents the current speed of the moving object. 310.

[000120] On the one hand, the electronic device 210 may be configured to generate one or more predictive trajectories for a moving object 310 moving along the section 350 of the road. How the electronic device 210 is configured to generate one or more predictive trajectories for the moving object 310 is not particularly limited. In one example, the electronic device 210 may be configured to use the current state of the moving object 310 and previous states of the moving object 310 to predict one or more future states of the moving object 310. Information about the current and/or one or more previous states of the moving object 310 may be provided to the electronic device 210 of the sensor system 280. It is contemplated that the electronic device 210 may be configured to perform a kinematic analysis of the current and/or one or more previous states of the moving object 310 for a predicted one or more future states of the moving object 310.

[000121] Regardless of how the electronic device 210 is configured to generate a predicted trajectory for the moving object 310, the electronic device 210 may use the predicted trajectory of the moving object 310 to determine a time estimate for a given node of the velocity graph 550. In those embodiments where the electronic device 210 generates a plurality of predictive paths for the moving object 310, the electronic device 210 may select one of the plurality of predictive paths for further processing. For example, electronic device 210 may select the "most likely" predicted trajectory from among the plurality of predicted trajectories and use it for further processing. In the non-limiting example of FIG. 7 depicts a representation of the predicted trajectory 750 that the electronic device 210 is configured to generate for a moving object 310 at a given time.

[000122] On the other hand, the electronic device 210 may be configured to identify the potential state of the vehicle 220 associated with the corresponding node on the graph 500 speed. For example, suppose node 506 is associated with potential state 720. Potential state 720 indicates the triple “p1, t1, v1”, where p1 represents the position of vehicle 220 associated with potential state 720 of node 506, t1 represents the time associated with potential state 720 of node 506, and v1 represents the vehicle speed 220 associated with potential state 720 of node 506.

[000123] Electronic device 210 is configured to use potential state information 720 and predicted trajectory information 750 to identify potential state 740 of moving object 310. For example, electronic device 210 can identify time t1 of potential state 720 of vehicle 220 associated with the node 506 and can access predicted trajectory information 750 to determine the future position (and future speed) of the moving object 310 at time t1. In this example, assume that the potential state 740 of the moving object 310 points to the triple "pB, t1, vB", where pB represents the predicted position of the moving object 310 at time t1 according to the predicted trajectory 750, and vB represents the predicted speed of the moving object 310 at time t1 in accordance with the predicted trajectory 750.

[000124] Electronic device 210 is configured to use information about potential state 720 of vehicle 220 and potential state 740 of moving object 310 to determine a time estimate for node 506 associated with potential state 720 of vehicle 220. Electronic device 210 may be configured with the ability to generate (simulate) a first trajectory for the moving object 310 if the moving object 310 performs an unexpected maneuver when in potential state 740, and generate (simulate) a second trajectory for the vehicle 220 if the vehicle 220 performs an emergency maneuver when in potential state 720.

[000125] In at least some embodiments, it is assumed that the unexpected maneuver that the moving object 310 may perform is a quick braking maneuver. In these embodiments, the electronic device 210 may be configured to generate (simulate) a deceleration path for the moving object 310 if the moving object 310 unexpectedly begins to perform a quick braking maneuver while in potential state 740.

[000126] In at least some embodiments, it is contemplated that the emergency maneuver that vehicle 220 can perform is also a quick braking maneuver. In these embodiments, electronic device 210 may be configured to generate (simulate) a braking path for vehicle 220 if vehicle 220 initiates a quick braking maneuver in potential state 720 as an emergency measure to avoid collision.

[000127] We can say that the electronic device 210 is configured to in some sense "simulate" a future situation where the vehicle 220 may need to initiate an emergency maneuver in response to an unexpected maneuver of a moving object 310, if the moving object 310 is in a potential state 740, and vehicle 220 is in potential state 720. In other words, electronic device 210 may be configured to generate a simulated emergency trajectory for vehicle 220 if vehicle 220 is in potential state 720, and a simulated unexpected trajectory for moving object 310 if moving object 310 is in potential state 740.

[000128] It should be noted that the emergency trajectory of the vehicle 220 may vary depending on, among other things, the weight of the vehicle 220 and the speed at which the emergency maneuver is initiated. In at least some embodiments of the present technology, the electronic device 210 may access pre-stored data regarding emergency trajectories of the vehicle 220 for its various weights and/or initial speeds, and retrieve data corresponding to an emergency trajectory related to weight and/or initial speed that best match their current weight and potential speed v1 of potential state 720. It is contemplated that in those embodiments where the emergency maneuver is a quick braking maneuver, the electronic device 210 is configured to generate and/or reconstruct a deceleration path that may be performed by vehicle 220 if vehicle 220 initiates a quick braking maneuver while in potential state 720.

[000129] It should be noted that the unexpected trajectory of the moving object 310 may also vary depending on a variety of factors, including the speed at which the unexpected maneuver begins. In at least some embodiments of the present technology, electronic device 210 may have access to pre-stored data regarding unexpected trajectories for multiple objects (cars, trucks, cyclists, etc.) and various initial speeds. In other embodiments, electronic device 210 may also use potential state information 740 to generate an unexpected trajectory for moving object 310. It is contemplated that in those embodiments where the unexpected maneuver is a quick braking maneuver, electronic device 210 is configured to generate and/ or restore a deceleration path that the moving object 310 can perform if the moving object 310 initiates a quick deceleration maneuver when in potential state 740.

[000130] The electronic device 210 is then configured to project the braking path of the moving object 310, which is the path of the moving object 310 resulting from the unexpected maneuver of the moving object 310 when it is in potential state 740, onto the braking path of the vehicle 220, which represents is the trajectory of vehicle 220 resulting from the emergency maneuver of vehicle 220 when it is in potential state 720.

[000131] In some embodiments, the implementation of the electronic device 210 may be configured to determine the distance between the vehicle 220 and the moving object 310 after the completion of an emergency maneuver and an unexpected maneuver. In one embodiment, the electronic device 210 may be configured to compare the final position of the braking path of the vehicle 220 and the final position of the braking path of the moving object 310.

[000132] The electronic device 210 is configured to use the distance between the vehicle 220 and the moving object 310 after completing their respective simulated deceleration paths and the speed of the vehicle 220 associated with the potential state 720 (associated with node 506) to determine a time estimate. In this case, the electronic device 210 may be configured to determine the time estimate as the ratio of distance to speed v1.

[000133] The developers of the present technology have realized that calculating the time estimate for node 506 in this way results in the potential state 720 being associated with a time estimate that indicates the amount of time the electronic device 210 will have before initiating an emergency maneuver to avoid a collision with a moving vehicle. object 310 if vehicle 220 is in potential state 720 and moving object 310 performs an unexpected maneuver while in potential state 740. For example, suppose the time estimate for node 506 is 2 seconds. This means that if vehicle 220 is in potential state 720 and moving object 310 initiates an unexpected maneuver while in potential state 740, electronic device 210 has 2 seconds at speed v1 of potential state 720 before initiating an emergency maneuver to avoid collision with moving object 310.

[000134] If the time estimate is below a predetermined threshold, electronic device 210 may be configured to assign a cost to edge 516. For example, electronic device 210 may be configured to determine the cost of edge 516 as the weighted square of the difference between node 506's time estimate and a predetermined threshold. Needless to say, the cost of the rib 516 may be determined based on the time estimate in different ways, depending on, among other things, different implementations of the present technology. In addition to timing, other features or attributes may also be taken into account in determining the cost of a given edge in velocity graph 600 without departing from the scope of the present technology.

[000135] It should be noted that in those embodiments where more than one object is present in the environment 250 of the vehicle 220, the electronic device 210 may be configured to generate a given time estimate for a corresponding one of the more than one object. Thus, the electronic device 210 may be configured to compare respective time estimates against a predetermined threshold. The electronic device 210 may also calculate the cost of the edge 516 as the sum of the costs for the respective time estimates of the corresponding more than one object.

[000136] It should be noted that the scenario depicted in FIG. 3 and 7, where vehicle 220 follows a moving object 350 is just one non-limiting example of how the present technology can be used to construct a speed profile for vehicle 220. In another non-limiting example, vehicle 220 and moving object 350 can be located on a section of road other than section 350 of the road.

[000137] To better illustrate this, reference will now be made to FIG. 8 illustrating another scenario in which a vehicle 220 may be on a stretch of road 850 with a moving object 310 in its vicinity. As can be seen, the vehicle 220 is moving in a lane 801 that merges with the lane 802 of the road section on which the moving object 310 is located. 480 is generated for section 350 of the road. Electronic device 210 may also be configured to generate a speed graph (not shown) for planning vehicle 220 on road section 850 along path 880 in a manner similar to how electronic device 210 is configured to generate a speed graph 600 for planning vehicle 220. speeds on the section 350 of the road along the path 480. Also shown is the current state 810 of the vehicle 220 and the current state 830 of the moving object 310.

[000138] Assume that the potential state 820 of the vehicle 220 corresponds to a given node from the speed graph generated by the electronic device 210. The electronic device 210 may be configured to determine a predicted trajectory 850 for a moving object 310 in a road section 850 in a manner similar to how the electronic device 210 is configured to determine a predicted trajectory 750 along road section 350. Assume that the moving object 310 will be in the potential state 840 (according to the predicted trajectory 850) at a time that coincides with the time of the potential state 820 of the vehicle 220 (similar to how the potential state 740 has a time that corresponds to the potential state 720 in the non-limiting example described above).

[000139] Electronic device 210 may be configured to generate a first braking path (not shown) for vehicle 220 and a second braking path (not shown) for moving object 310 in a manner similar to that described above.

[000140] It should be noted that the electronic device 210 may be configured to project the time and end position of the second deceleration path of the moving object 310 onto the first deceleration path of the vehicle 220. It may also be said that the electronic device 210 may be configured to project the moment time and end position of the second deceleration path of the moving object 310 at the time and end position of the first deceleration path of the vehicle 220 to determine the distance between the vehicle 220 and the moving object 310 after the completion of the first and second deceleration paths. It is also contemplated that at least one time associated with a corresponding position from the second deceleration path of the moving object 310 can be projected onto at least one time associated with a corresponding position from the first deceleration path of the vehicle 220 to determine the distance between vehicles means 220 and a moving object 310.

[000141] It should be noted that the deceleration paths of vehicle 220 and moving object 310 in the scenario shown in FIG. 8 are not aligned, but rather at an "angle" to each other. Therefore, it can also be said that the projection of the end time and end position of the second trajectory onto the first trajectory can be used to determine the distance between the vehicle 220 and the object 310 when the first and second deceleration paths are completed in a scenario where these deceleration paths are at an angle to each other. to friend.

[000142] As shown in FIG. 9, electronic device 210 may be configured to perform method 900 implemented on a computer. It should be noted that electronic device 210 may be configured to perform method 900 during a given scheduling cycle of vehicle 220. In other words, electronic device 210 may be configured to iteratively execute method 900 at various times during vehicle 220 operation and which correspond to the respective scheduling cycles of the vehicle 220. The various steps of the method 900 will now be discussed in more detail.

STEP 902: generating a path for the SDC on the ground, where the path includes a sequence of potential positions on the ground to be followed by the SDC.

[000143] Method 900 begins at 902 with an electronic device configured to generate a predetermined path for the SDC on the ground, and where the path includes a sequence of potential positions on the ground that the SDC should follow.

[000144] In at least some embodiments of the present technology, the electronic device 210 may be configured to perform a two-step process to determine a predetermined trajectory on the ground and/or on a road segment. In other words, the electronic device 210 may perform "independent planning" of trajectories, where the target path is determined in the first step (step 902) and the velocity profile is determined in the second step (step 904 below). In at least some embodiments of the present technology, the electronic device 210 can perform independent path planning in an iterative manner. In other words, within each scheduling cycle, the path and speed planning is repeated by the electronic device 210 so that the electronic device 210 takes into account the latest information about the dynamic environment of the vehicle 220.

[000145] In some embodiments of the present technology, the terrain on which the SDC operates may be a predetermined section of the road. For example, vehicle 220 associated with electronic device 210 may operate on road section 350 and/or road section 850. In a scenario where vehicle 220 is moving on road section 350, electronic device 210 may be configured to generate path 480. In a scenario where vehicle 220 is moving on road section 850, electronic device 210 may be configured to generate path 880.

[000146] In some embodiments, to determine a given path, the electronic device 210 may be configured to generate a terrain graph for the terrain based on terrain geometry. For example, electronic device 210 may be configured to generate a road graph 420 for road section 350 based, among other things, on the geometry of road section 350. It should be noted that road graph 420 contains nodes and edges, where a given node represents a corresponding potential position of vehicle 220 on road section 350, and a given edge represents a corresponding potential transition between a corresponding pair of potential positions.

[000147] Electronic device 210 may be configured to determine a sequence of potential locations from road graph 420 as path 480. As described in more detail above, nodes/edges of road graph 420 may be associated with appropriate attributes and may be used in conjunction with cost criteria for determining the cost of the corresponding edges in the road graph 420. In one non-limiting example, the shortest path algorithm can then be applied to the cost of the corresponding edges in the road graph 420 to determine the shortest path in terms of its total cost in the road graph 420.

STEP 904: generating indications of planned speeds for the SDC while following the sequence of potential positions

[000148] Method 900 continues at 904, where the electronic device is configured to generate planned speed indications for the SDC as it follows the sequence of potential positions out of the way. It can be said that this step may correspond to the second step of the independent path planning technique described above, during which the electronic device 210 is in some sense configured to determine, among other things, how the speed of the vehicle 220 should change over time while moving along the path generated on the previous stage.

[000149] Electronic device 210 is configured to generate a speed graph at step 904. For example, electronic device 210 can be configured to generate a speed graph 600 for path 480 on road section 350. The speed graph 600 has nodes and edges.

[000150] This node in the speed graph 600 represents the first potential state of the vehicle 220 on the road section 350, and the first potential state indicates the first potential position and the first potential speed of the vehicle 220 at the first potential future time. In some embodiments, a given potential state of the vehicle 220 associated with the corresponding node in the speed graph 600 can be represented by at least the triple "station, time and speed" at which the vehicle 220 could potentially be on the section of road 350 along the highway 480.

[000151] A given edge of rate graph 600 connects a given node to a previous node in rate graph 600 and represents a corresponding potential transition from a previous potential state to a given potential state. In some embodiments of the present technology, a potential transition may be a transition from a previous potential state to a first potential state at constant acceleration.

[000152] The electronic device 210 is also configured to generate a time estimate for a given node in a speed column 600 indicating the amount of time that the electronic device 210 has before initiating an emergency maneuver to avoid a collision with a moving object if the vehicle 220 is in the appropriate potential state and the moving object 310 performs a predetermined unexpected maneuver at an appropriate potential future time.

[000153] It should be noted that during the determination of the time estimate, the electronic device 210 does not actually initiate an emergency maneuver, and the moving object 310 does not actually perform a predetermined unexpected maneuver. In at least some embodiments, it can be said that in determining the time estimate for a given node on the velocity graph 600, the electronic device 210 in some sense "simulates" the situation when, at the corresponding potential future time of the potential state of this node, the moving object 310 performs a predetermined unexpected maneuver, and the vehicle performs an emergency maneuver.

[000154] In at least some embodiments of the present technology, when generating a time estimate for a given node, electronic device 210 may be configured to generate an emergency trajectory for vehicle 220 if vehicle 220 performs an emergency maneuver while vehicle 220 is in the first potential state (then potential position, the then potential moment of time and the then potential velocity). In addition, when generating a time estimate for a given node, the electronic device 210 may be configured to generate an unexpected trajectory of the moving object 310 if the object performs a predetermined unexpected maneuver when the moving object is in a predicted potential state at the first potential future time.

[000155] In some embodiments, in order to generate an unexpected trajectory of the moving object 310, the electronic device 210 may first be configured to determine a predicted potential state of the moving object 310 that corresponds to the potential future time of a given node/potential state of the vehicle 220.

[000156] It is contemplated that the electronic device 210 may be configured to generate a plurality of predicted trajectories for the moving object 310 based on one or more previous states of the moving object 310. The electronic device 210 may also determine the most likely predicted trajectory among the plurality of predicted trajectories and/or choose one of the many predictable trajectories. The electronic device 210 may then select the predicted potential state of the moving object 310 (which should be used as the initial state to initiate the simulation of the unexpected trajectory of the moving object 310) as the potential state of the moving object 310 at a time that corresponds to the time associated with the given node, and which corresponds to the most likely/selected predicted trajectory of the moving object 310.

[000157] The electronic device 210 may be configured to project the time and end position of the unexpected trajectory of the moving object 310 to the time and end position of the emergency trajectory of the vehicle 220. The purpose of such a projection of the time and corresponding position from the unexpected trajectory onto the emergency trajectory is to is to determine the distance between the vehicle 220 and the moving object 310 after the completion of an emergency maneuver and a predetermined unexpected maneuver (during simulation).

[000158] The electronic device 210 can also be configured to generate a time estimate based on the distance and potential speed of a potential state associated with a given node (then potential speed of vehicle 220).

[000159] The electronic device 210 may be configured to generate the cost of an edge leading to a given node in the rate graph 600 using a given node's time estimate. The cost of an edge indicates the safety of the corresponding potential transition. In some embodiments, a cost may be generated in response to a time estimate being below a predetermined threshold. In one implementation of the present technology, the predetermined threshold may be about 1.5 seconds, while in other implementations, the predetermined threshold may be 1 second, 2 seconds, 1.2 seconds, 1.7 seconds, or the like. It is also contemplated that the cost may be proportional to the square of the difference between the predetermined threshold and the time estimate.

[000160] In cases where more than one moving object is in the vicinity of the vehicle 220, the electronic device 210 may be configured to calculate appropriate time estimates for each of the more than one moving object and determine the corresponding costs for each of the more than one moving object. object. These respective costs can be weighted and summed to determine the cost of an edge leading to a given node. It is contemplated that cost reduction for a given edge of the rate graph 600 can be performed for the corresponding edges of the rate graph 600 .

[000161] The electronic device 210 is configured to determine the sequence of edges in the velocity graph 600 using the cost of that edge, such that the sequence of edges has a valid total cost of the edges. For example, the total cost of the candidate rib sequence may be compared to a threshold cost, and if the total cost of the candidate sequence is below the threshold cost, the electronic device 210 may be configured to select the candidate sequence as a target sequence for planning vehicle speeds 220. In another example, the electronic device device 210 may select the edge sequence in rate graph 600 that is associated with the lowest total edge cost among the possible edge sequences.

[000162] Electronic device 210 is configured to generate indications of planned speeds (representing a speed profile) using potential states of nodes connected by a selected sequence of edges in speed graph 600.

STEP 906: induce SDC control along the path in accordance with the planned speeds

[000163] The method 900 proceeds to step 906 with the electronic device 210 configured to ensure that the vehicle 220 operates along the path in accordance with the planned speeds. In at least one embodiment of the present technology, the electronic device 210 may be configured to generate one or more commands intended for the vehicle control system 220 so that the vehicle 220 reaches the respective track stations at the respective planned speeds. For example, electronic device 210 may be configured to process indications of planned speeds and generate commands to the vehicle control system indicative of synchronized accelerations/decelerations that will allow vehicle 220 to actually travel along the route at the planned speeds.

[000164] Modifications and improvements to the above implementations of the present technology may become apparent to those skilled in the art. The preceding description is intended to be exemplary and not limiting. Therefore, it is intended that the scope of the present technology be limited only by the scope of the appended claims.

[000165] While the implementations described above have been described and shown with reference to specific steps performed in a particular order, it should be understood that some of these steps may be combined, subdivided, or reordered without deviating from the principles of the present technology. Accordingly, the order and grouping of said steps is not a limitation of the present technology.

Claims (86)

1. A method for controlling an unmanned vehicle (SDC) on the ground, wherein there is a moving object in the environment of the SDC, the SDC is controlled by an electronic device, the method is performed by the electronic device, and the method includes the steps of: at a given time during SDC operation: electronically generating a path for the SDC on the ground, the path including a sequence of potential positions on the ground to be followed by the SDC; electronically generating indications of planned speeds for the SDC following the sequence of potential positions, the generation of indications including the steps of: generate by means of an electronic device a graph structure having nodes and edges, moreover, this node represents the first potential state of the SDC on the ground, the first potential state indicates the first potential position and the first potential speed of the SDC at the first potential future time, this edge connects this node to the previous node in the graph structure and represents the corresponding potential transition from the previous potential state to the first potential state; generating by the electronic device a time estimate for the given node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid collision with a moving object if the SDC is in the first potential state and the moving object performs a predetermined unexpected maneuver at the first potential future time ; electronically generating a cost for the given edge using the time estimate of the given node, the cost indicating the security of the corresponding potential transition; determining by means of an electronic device a sequence of ribs using the cost of this rib, and the sequence of ribs has a valid total cost of the ribs; And generating, by means of an electronic device, indications of planned speeds using potential states of nodes connected by a sequence of edges; And causing the SDC to be controlled by the electronic device along the track in accordance with the planned speeds. 2. The method of claim 1, wherein generating the time estimate includes the steps of: generating by the electronic device an emergency trajectory of the SDC if the SDC performs an emergency maneuver when the SDC is in the first potential state; electronically generating an unexpected trajectory of the moving object if the moving object performs a predetermined unexpected maneuver when the moving object is in a third potential state at a first potential future time; electronically projecting a point in time and an end position of the unexpected trajectory of the moving object to the point in time and an end position of the emergency trajectory SDC to determine the distance between the SDC and the moving object after completing the emergency maneuver and the predetermined unexpected maneuver; And generating, by means of the electronic device, a time estimate based on the distance estimate and the first potential speed of the first potential SDC state. 3. The method of claim 2, wherein the method further comprises the steps of: generating by means of an electronic device a plurality of predicted trajectories for a moving object on the ground; determining by means of the electronic device the most likely predicted trajectory among the plurality of predicted trajectories; And by means of an electronic device, the third potential state of the moving object is selected as the potential state of the moving object at the first potential future point in time in accordance with the most likely predicted trajectory. 4. The method of claim. 1, in which the moving object contains the first moving object, and in which the second moving object is in the SDC environment, and the time estimate is the first time estimate associated with the first moving object, and generating indications further includes the steps , where: generating by the electronic device a second time estimate for the given node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid collision with the second moving object if the SDC is in the first potential state and the second moving object performs a predetermined unexpected maneuver in the first potential future point in time; and wherein the cost generation includes electronically generating a cost for a given edge using the first time estimate and the second time estimate of the given node. 5. The method of claim 4, wherein generating a cost for a given edge using the first time estimate and the second time estimate includes electronically calculating a weighted sum of the first time estimate and the second time estimate. 6. The method of claim 1, wherein the cost is generated in response to the time estimate being below a predetermined threshold. 7. The method of claim 6 wherein the cost is proportional to the square of the difference between the predetermined threshold and the time estimate. 8. The method of claim. 1, in which the corresponding potential transition is a transition from the previous potential state to the first potential state at constant acceleration. 9. The method of claim 1, wherein generating the path includes the steps of: generating by means of an electronic device another graph structure for the terrain based on the geometry of the terrain, while the other graph structure has other nodes and other edges, wherein this other node represents the corresponding potential position of the SDC on the ground, this other edge represents the corresponding potential transition between the corresponding pair of potential positions; And determining by means of an electronic device a sequence of potential positions from another graph structure. 10. The method of claim 1, wherein the method further comprises the steps of: at another given point in time while the SDC is running after this point in time: electronically generating a different path for the SDC on the ground, the path including a different sequence of potential positions on the ground to be followed by the SDC; generate by means of an electronic device another graph structure having other nodes and other edges, generating by the electronic device another time estimate for the given other node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid collision with the moving object if the SDC is in the corresponding potential state of the given other node and the moving object performs a predetermined unexpected maneuver in corresponding potential point in time; electronically select a different sequence of edges in the graph structure based on a different time estimate of another given node; electronically generating indications of other planned speeds for the SDC while following a different sequence of potential positions based on a different sequence of fins; And the electronic device is induced to operate the SDC along the track in accordance with the other planned speeds. 11. The method of claim 1, wherein the terrain is a road section having a traffic lane and the SDC follows a moving object in the traffic lane, the predetermined unexpected maneuver of the moving object being a quick braking maneuver, the SDC emergency maneuver being a quick braking maneuver. 12. The method of claim 1, wherein the terrain is a road section having a first lane and a second lane, the SDC is moving in the first lane, the object is moving in the second lane, and the predetermined unexpected maneuver of the moving object is a maneuver with lane change to the first lane, the SDC emergency maneuver is a quick braking maneuver. 13. An electronic device for controlling an unmanned vehicle (SDC) on the ground, and the moving object is surrounded by SDC, and the electronic device is configured to: at a given time during SDC operation: generate a path for the SDC on the ground, and the path includes a sequence of potential positions on the ground, which should be followed by the SDC; generate indications of planned speeds for the SDC while following the sequence of potential positions, and in order to generate indications, the electronic device is configured to: generate a graph structure with nodes and edges, moreover, this node represents the first potential state of the SDC on the ground, the first potential state indicates the first potential position and the first potential speed of the SDC at the first potential future time, a given edge connecting the given node to the previous node in the graph structure and representing the corresponding potential transition from the previous potential state to the first potential state; generate a time estimate for a given node indicating the amount of time the electronic device has before triggering an emergency maneuver to avoid collision with a moving object if the SDC is in the first potential state and the moving object performs a predetermined unexpected maneuver at the first potential future time; generate a cost for a given edge using the given node's time estimate, the cost indicating the security of the corresponding potential transition; determine the sequence of edges using the cost of the given edge, and the sequence of edges has a valid total edge cost; And generate indications of planned speeds using potential states of nodes connected by a sequence of edges; And order the SDC to operate along the track in accordance with the planned speeds. 14. The electronic device of claim 13, wherein, in order to generate the time estimate, the electronic device is configured to: generate an emergency SDC trajectory if the SDC performs an emergency maneuver when the SDC is in the first potential state; generate an unexpected trajectory of the moving object if the moving object performs a predetermined unexpected maneuver when the moving object is in a third potential state at a first potential future time; projecting a point in time and an end position of the unexpected trajectory of the moving object to a point in time and an end position of the SDC emergency trajectory to determine the distance between the SDC and the moving object after completing the emergency maneuver and the predetermined unexpected maneuver; And generate a time estimate based on the distance estimate and the first potential velocity of the first potential SDC state. 15. An electronic device according to claim 14, wherein the electronic device is additionally configured to: generate a set of predicted trajectories for a moving object on the ground; determine the most likely predicted trajectory among the plurality of predicted trajectories; And select the third potential state of the moving object as the potential state of the moving object at the first potential future time in accordance with the most likely predicted trajectory. 16. The electronic device of claim. 13, in which the moving object contains the first moving object, and while the second moving object is in the environment of the SDC, while the time estimate is the first time estimate associated with the first moving object, to generate indications, the electronic device further made with the ability to: generate a second time estimate for a given node indicating the amount of time the electronic device has before initiating an emergency maneuver to avoid a collision with a second moving object if the SDC is in the first potential state and the second moving object performs a predetermined unexpected maneuver at the first potential future instant time; and wherein, to generate the cost, the electronic device is configured to generate a cost for a given edge using the first time estimate and the second time estimate of the given node. 17. The electronic device of claim 16, wherein in order to generate a cost for a given edge using the first time estimate and the second time estimate, the electronic device is configured to compute a weighted sum of the first time estimate and the second time estimate. 18. The electronic device of claim 13, wherein the cost is generated in response to the time estimate being below a predetermined threshold. 19. The electronic device of claim 18, wherein the cost is proportional to the square of the difference between a predetermined threshold and a time scale. 20. The electronic device of claim 13, wherein the corresponding potential transition is a transition from a previous potential state to a first potential state at constant acceleration. 21. The electronic device of claim 13, wherein, in order to generate the path, the electronic device is configured to: generate a different graph structure for the terrain based on the geometry of the terrain, while the different graph structure has different nodes and different edges, wherein this other node represents the corresponding potential position of the SDC on the ground, this other edge represents the corresponding potential transition between the corresponding pair of potential positions; And determine the sequence of potential positions from another graph structure. 22. An electronic device according to claim 13, wherein the electronic device is additionally configured to: at another given point in time while the SDC is running after this point in time: generate a different path for the SDC on the ground, and the path includes a different sequence of potential positions on the ground, which should be followed by the SDC; generate a different graph structure having different nodes and different edges, generate a different time estimate for this other node indicating the amount of time the electronic device has before triggering an emergency maneuver to avoid collision with a moving object if the SDC is in the corresponding potential state of this other node and the moving object performs a predetermined unexpected maneuver at the appropriate potential instant time; select a different sequence of edges in the graph structure based on a different time estimate of another given node; generate indications of other planned speeds for the SDC while following a different sequence of potential positions based on a different sequence of edges; And direct the SDC to operate along the track in accordance with other planned speeds. 23. The electronic device of claim 13, wherein the terrain is a road section having a traffic lane and the SDC follows a moving object in the traffic lane, the object's predetermined unexpected maneuver being a quick braking maneuver and the SDC's emergency maneuver being a quick braking maneuver. 24. The electronic device of claim 13, wherein the terrain is a road section having a first lane and a second lane, the SDC is moving in the first lane, the object is moving in the second lane, and the predetermined unexpected maneuver of the moving object is the maneuver with a lane change to the first lane, the emergency SDC maneuver is a quick braking maneuver.

Images