CN113587950B - Static path planning method, device and storage medium for autonomous driving vehicle - Google Patents

Abstract

The present disclosure provides a method, device and storage medium for static path planning of an autonomous vehicle, including: selecting multiple groups of feature points according to the road topology of an intersection and the expected number of exits of the driving route in the intersection, the number of groups of feature points being consistent with the expected number of exits, and each group of feature points comprising a number of internal feature points of the intersection and external feature points of the intersection; inputting the multiple groups of feature points into a path calculation function to obtain corresponding different candidate static continuous paths; setting an expected passing rate and an expected stopping rate for each candidate static continuous path, assigning a driving rate to the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the signal light, obtaining multiple candidate paths containing the rate information of the autonomous vehicle, discretizing them, and outputting the static discrete path of the final plan. The present disclosure provides multiple candidate paths for decision-making and control tasks such as path tracking of an autonomous vehicle, and ensures high computing efficiency in online applications.

Description

Static path planning method, device and storage medium for autonomous driving vehicle

Technical Field

The present invention relates to the technical field of decision-making and planning for autonomous driving vehicles, and in particular to a method, device and storage medium for static path planning for autonomous driving vehicles.

Background technique

Automotive intelligence and driver assistance systems have great potential in improving safety, reducing fuel consumption, and improving traffic efficiency. High-level intelligent driving relies on high real-time decision-making and control.

The existing vehicle decision-making method mainly uses motion prediction, behavior selection, path planning and other sub-modules in series, and finally obtains a feasible path after calculation. However, this process decomposition method cannot guarantee real-time performance when dealing with large-scale dynamic obstacle avoidance tasks, and the method has poor versatility, and different solutions need to be designed for different scenarios.

Summary of the invention

The present disclosure aims to solve one of the above-mentioned problems.

To this end, the first aspect of the present disclosure provides a static path planning method for an autonomous driving vehicle suitable for intersections, which can provide multiple candidate paths for decision-making control tasks such as path tracking of an autonomous driving vehicle and ensure high computational efficiency during online application, including:

According to the road topology of the intersection and the expected number of exits of the driving route in the intersection, multiple groups of feature points are selected, the number of groups of feature points is consistent with the expected number of exits, and each group of feature points includes a number of internal feature points of the intersection and a number of external feature points of the intersection;

Inputting multiple groups of the feature points into a path calculation function to obtain corresponding different candidate static continuous paths;

For each of the candidate static continuous paths, an expected travel rate and an expected stop rate are set, and a travel rate is assigned to the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the traffic light, so as to obtain multiple candidate paths containing the rate information of the autonomous vehicle, discretize them, and output the final planned static discrete path.

The static path planning method for an autonomous driving vehicle provided by the first embodiment of the present disclosure has the following characteristics and beneficial effects:

The present invention only considers static traffic information such as road topology and traffic rules when planning the path of an autonomous vehicle, and plans multiple candidate paths and corresponding expected speeds through road topology in intersection scenarios.

Static path planning only considers static traffic information and does not consider dynamic obstacles. It can generate static paths and expected speeds in advance, and directly obtain candidate path information during driving for subsequent tracking control and other purposes. Therefore, the present invention has the characteristics of efficient online computing and strong scalability.

In some embodiments, the external feature points of the intersection are selected according to the following steps:

Set the expected number of exits of the driving route in the intersection as the number N of candidate static continuous paths, mark the midpoint coordinates of the lane start lines of the N expected exits as _X1,4 , _X2,4 , ..., _Xi,4 , ..., _XN,4 , i∈{1,2,3, ..., N}; mark the midpoint coordinate of the lane stop line at the entrance where the autonomous driving vehicle is located as _X1 , and replicate it N times to become _X1,1 , _X2,1 , ..., Xi _,1 , ..., _XN,1 ; start from Xi _,1 and move a distance _l1 in the driving direction opposite to the entrance lane where the autonomous driving vehicle is located to obtain _X1,0 , _X2,0 , ..., Xi _,0 , ..., XN _,0 ; start from Xi _,4 and move a distance _l2 in the driving direction of the parallel exit lane to obtain _X1,5 , _{X2,5, ..., Xi,5} , ..., _XN,5 ; select Xi _,0 , _Xi,1 , XN,5 ...1, XN,1, _{XN,1, XN,1} , XN The feature points corresponding to _Xi,4 and Xi _,5 are used as the external feature points of the intersection of the i-th candidate static continuous path.

In some embodiments, the internal feature points of the intersection are selected according to the following steps:

Assume that the coordinates of the internal feature points of the intersection of the i-th candidate static continuous path are _Xi,2 and Xi _,3 respectively, and select the internal feature points of the intersection according to the following formula:

Among them, _θ1 is the angle between the driving direction of the entrance lane and the horizontal axis of the intersection coordinate axis, and θi _,2 is the angle between the driving direction of the i-th candidate exit lane and the horizontal axis of the intersection coordinate axis.

In some embodiments, the internal feature points of each intersection and the external feature points of the intersection are classified according to N expected exits to obtain feature point groups of N candidate paths.

In some embodiments, for the i-th candidate static continuous path, the path between Xi _,0 and _Xi,1 , the path between Xi _,1 and Xi _,4 , and the path between Xi _,4 and Xi _,5 are respectively recorded as and/> The path calculation functions used are as follows:

Among them, t ₁ , t ₂ and t ₃ are respectively and/> Corresponding parameters;

Will and/> Connect them end to end to form a static continuous path at the i-th intersection

In some embodiments, the allocation of a driving speed for the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the traffic light is specifically:

3-1-1) The autonomous vehicle starts from Xi _{, 0.} If, before the autonomous vehicle reaches Xi _{, 1} , the traffic light is always green, or the traffic light is always yellow and the autonomous vehicle can drive past the stop line within the remaining yellow light time, the autonomous vehicle is set to drive to Xi _{, 1} at the expected passing speed, and step 3-1-2) is executed; if, before the autonomous vehicle reaches Xi _{, 1} , the traffic light is always red, or the traffic light is always yellow and the autonomous vehicle cannot drive past the stop line within the remaining yellow light time, the autonomous vehicle is set to drive to Xi _{, 1} at the expected stopping speed, and step 3-1-2) is executed; if, before the autonomous vehicle reaches Xi _{, 1} , the phase of the traffic light changes, the driving speed of the autonomous vehicle is jumped to the expected stopping speed or the expected passing speed when the phase of the traffic light changes, until the autonomous vehicle reaches Xi _{, 1} , and step 3-1-2) is executed;

3-1-2) The autonomous vehicle is located at Xi _,1 . If the traffic light is yellow or green, the autonomous vehicle is set to travel at the expected speed to Xi _,5 . If the traffic light is red, the autonomous vehicle is set to travel at the expected stop speed until the traffic light turns green, and the autonomous vehicle is set to travel at the expected speed to Xi _,5 .

In some embodiments, the multiple candidate paths containing the autonomous driving vehicle speed information are discretized using equal time distance or equal space distance.

The second aspect of the present disclosure provides a static path planning device for an autonomous driving vehicle, comprising:

A feature point selection module is used to select multiple groups of feature points according to the intersection road topology and the expected number of exits of the driving route in the intersection, the number of groups of feature points is consistent with the expected number of exits, and each group of feature points includes a number of intersection internal feature points and a number of intersection external feature points;

A path calculation module, used for inputting multiple groups of feature points into a path calculation function to obtain corresponding different candidate static continuous paths; and

The discrete processing module is used to set an expected passing speed and an expected stopping speed for each of the candidate static continuous paths, assign a driving speed to the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the traffic light, obtain multiple candidate paths containing the speed information of the autonomous vehicle, discretize them, and output the final planned static discrete path.

The storage medium provided by the embodiment of the third aspect of the present disclosure is characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned static path planning method for the autonomous driving vehicle.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is an overall flow chart of a static path planning method for an autonomous driving vehicle provided by an embodiment of the first aspect of the present disclosure;

FIG2 is a schematic diagram of static path planning according to an embodiment of the first aspect of the present disclosure;

In FIG. 3 , (a), (b), and (c) are respectively the static continuous path planning results corresponding to left turn, straight going, and right turn in the first aspect of the present disclosure;

FIG4 is a diagram of two types of expected rate curves selected from an embodiment of the first aspect of the present disclosure;

FIG5 is a schematic diagram of an expected rate jump state machine used in an embodiment of the first aspect of the present disclosure;

FIG6 (a) and (b) are schematic diagrams of two continuous path discretization methods used in the embodiment of the first aspect of the present disclosure;

7 is a schematic diagram of the structure of a static path planning device for an autonomous driving vehicle provided by an embodiment of the second aspect of the present disclosure;

FIG8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the third aspect of the present disclosure.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

On the contrary, the present application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present application as defined by the claims. Further, in order to make the public have a better understanding of the present application, some specific details are described in detail in the detailed description of the present invention below. For those skilled in the art, the present application can be fully understood without the description of these details.

Referring to FIG1 , the static path planning method for an autonomous driving vehicle provided in an embodiment of the present disclosure includes the following steps:

According to the intersection road topology and the expected number of exits of the driving route in the intersection, multiple groups of feature points are selected, the number of groups of feature points is consistent with the expected number of exits, and each group of feature points includes a number of intersection internal feature points and a number of intersection external feature points;

Input the obtained multiple sets of feature points into the path calculation function to obtain corresponding different candidate static continuous paths;

For each candidate static continuous path obtained, the expected travel rate and expected stop rate are set, and the driving rate is assigned to the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the traffic light. Multiple candidate paths containing the speed information of the autonomous vehicle are obtained, which are discretized and the final planned static discrete path is output.

The static path planning method for an autonomous driving vehicle provided in an embodiment of the present disclosure is suitable for an intersection scenario, see FIG2 . In the embodiment, according to the intersection road topology and the expected number of exits of the driving route, a corresponding number of groups of feature points are calculated, specifically including the following steps:

1-1) Selection of external feature points at intersections: The expected number of exits in the driving route at the intersection (i.e., the number of feasible exits in the planned direction of the intersection scenario) N is set as the number of candidate static continuous paths, and the midpoint coordinates of the lane start lines of the N expected exits are marked as _X1,4 , _X2,4 , ..., _Xi,4 , ..., _XN,4 , i∈{1,2,3, ..., N}. The midpoint coordinates of the lane stop line at the entrance where the autonomous vehicle is located are marked as _X1 , and replicated N times to become _X1,1 , _X2,1 , ..., Xi _,1 , ..., _XN,1 . Starting from Xi _,1 , move a distance l ₁ (the distance is determined by the length of the straight road, usually 10-30m) in the direction opposite to the entrance lane where the autonomous driving car is located, and obtain X _1,0 , X _2,0 , ... , _Xi,0 , ... , X _N,0 ; starting from Xi _,4, move a certain distance l ₂ (the value range is the same as l ₁ ) in the direction of the parallel exit lane, and obtain X _1,5 , X _2,5 , ... , _Xi,5 , ... , X _N,5 .

1-2) Selection of internal feature points at intersections: According to the intersection road topology, calculate the feature points of each feature point group inside the intersection. The internal feature points are selected according to the following rules: Draw perpendicular lines from the points P and Q to Xi _{,0, Xi,1} and _Xi , ₄ Xi _,s to obtain the internal characteristic points of the intersection. Their coordinates are recorded as Xi _,2 and Xi _,3 respectively. The specific calculation formula is as follows:

Among them, _θ1 is the angle between the driving direction of the entrance lane and the horizontal axis of the intersection coordinate axis, and θi _,2 is the angle between the driving direction of the i-th candidate exit lane and the horizontal axis of the intersection coordinate axis.

1-3) Classify the internal feature points of each intersection and the external feature points of each intersection according to N expected exits to obtain feature point groups of N candidate paths As shown in Figure 2. In the above text, Xi _,j is a two-dimensional vector, that is,/> represents the jth feature point of the i-th candidate path, and the superscript (k) represents the kth component of the vector. The value range of i is {1, 2..., N}, where N is the expected number of exits of the vehicle's route; the value range of j is {0, 1, 2..., 5}.

In some embodiments, the obtained multiple groups of feature points are input into a Bezier curve path calculation function to obtain corresponding different candidate static continuous paths, which specifically includes the following steps:

2-1) Calculation of internal paths at intersections: For each set of feature points, the static continuous path inside the intersection is calculated as follows:

in, represents the internal path segment of the intersection of the i-th candidate static continuous path, i∈{1, 2, 3, ..., N}; t ₂ is the internal path segment parameter of the intersection.

2-2) Intersection external path splicing: The straight lane segments outside the intersection are directly connected to obtain the straight segment path:

in, is the first intersection external path segment of the i-th candidate static continuous path, /> is the second intersection external path segment of the i-th candidate static continuous path, i∈{1, 2, 3, ..., N}; _t1 and _t3 are the first intersection external path segment parameter and the second intersection external path segment parameter, respectively.

The three continuous smooth paths are divided into The order of the ends is connected to obtain N continuous smooth intersection static continuous paths/> In some embodiments, the static continuous paths corresponding to the planned left turn, straight going, and right turn are shown in (a), (b), and (c) of FIG. 3 , respectively.

In some embodiments, step 3) comprises the following steps:

3-1) Path rate curve setting: The rate at which the autonomous vehicle travels to Xi _,0 is recorded as the initial rate, and the expected rate of the autonomous vehicle is set for the static continuous path planned in step 2). As shown in Figure 4, there are two rate curves to choose from, including the expected passing rate for the autonomous vehicle to continue driving and the expected stopping rate for the autonomous vehicle to stop. After each discrete time step _t0 (common values are 0.1s and 0.05s), the driving rate of the autonomous vehicle is selected according to the jump relationship of the finite state machine in Figure 5. The state jump judgment rules include A-signal phase and B-if A is in yellow light, whether it can drive beyond the stop line within the remaining yellow light time. Among them, rule A includes the current signal light being red, the current signal light being green, and the current signal light being yellow, which are recorded as A-red, A-green, and A-yellow respectively; rule B includes that the autonomous vehicle can drive beyond the stop line within the remaining yellow light time and the autonomous vehicle cannot drive beyond the stop line within the remaining yellow light time, which are recorded as B-yes and B-no respectively. The method for judging whether the vehicle can cross the stop line often uses a uniform recursive model: if t _yellow ×v _current ≥d _stop , then it is judged that the vehicle can cross the stop line, otherwise it is not, where t _yellow is the remaining yellow light time, v _current is the current vehicle speed, and d _stop is the distance from the autonomous vehicle to the stop line.

The self-driving car drives to Xi _,0 and selects and jumps to the desired rate according to the rules shown in Figure 4:

3-1-1) The autonomous driving car starts from Xi _{, 0.} If before the autonomous driving car travels to Xi _{, 1} , the state is always A-green, or (the "||" in Figure 5 indicates "or") A-yellow and (the "&&" in Figure 5 indicates "and") B-yes, then the autonomous driving car is set to travel to Xi _{, 1} at the expected passing speed, and step 3-1-2) is executed; if before the autonomous driving car travels to Xi _{, 1} , the state is always A-red, or A-yellow and B-no, then the autonomous driving car is set to travel to Xi _{, 1} at the expected stopping speed, and step 3-1-2) is executed; if before the autonomous driving car travels to Xi _{, 1} , the state changes, then when the state changes, the driving speed of the autonomous driving car is jumped to the expected stopping speed or the expected passing speed until the autonomous driving car travels to Xi _{, 1} , and step 3-1-2 is executed.

3-1-2) If the current state is A-yellow or A-green, the autonomous driving car is set to travel at the expected passing speed to Xi _{, 5} ; if the current state is A-red, the autonomous driving car is set to travel at the expected stopping speed until the current state is A-green, and the autonomous driving car is set to travel at the expected passing speed to Xi _{, 5} .

3-2) Path discretization output: After obtaining the static continuous path and the corresponding rate according to the above steps, in order to save the calculation time and space consumption of the path, the continuous path needs to be discretized. Common path discretization methods include equal time distance discretization and equal space distance discretization, which are described below:

a) See (a) in Figure 6, the equal time distance discretization method: This method expects that the time taken by the vehicle to pass any two adjacent path points is the same, and this time is defined as Δt (a common value is 0.01s). According to the expected rate curve, the expected rate v ^ref at different spatial positions can be obtained. The starting point _Xi,0 of the path is taken as the first discretized path point Check the expected rate curve to get/> Then the next path point /> The spacing of According to/> The expected velocity curve is obtained at the position of / > Then get/> Set the next waypoint /> This process is repeated until a discrete path point sequence is obtained. Based on the starting point, the next point with a spacing of Δ on the continuous path can be found by using numerical solution and other methods to obtain an approximate numerical solution.

b) See Figure 6 (b), the equispatial distance discretization method: take the starting point _Xi,0 of the path as the first discrete path point Directly solve the next discrete point with a curve distance of Δτ on the continuous path by numerical calculation method/> Recalculate the distance/> is the next discrete point of Δτ/> Repeat the recursion until a discrete path point sequence is obtained/>

In the above text, is the pth discrete point on the i-th path,/> For waypoints/> The corresponding expected rate is

According to the static discrete path obtained by the discretization method, the expected rate of each path point is obtained from the expected rate curve Calculate the path points according to the following formula/> The desired vehicle heading angle at/>

According to the order of path points, the path output by this static path planning method is There are N candidate static discrete paths and the expected speed and vehicle orientation angle of the corresponding discrete points, and each path contains M discrete points.

The present disclosure provides a static path planning device for an autonomous driving vehicle, the structure of which is shown in FIG7 , and includes:

A feature point selection module is used to select multiple groups of feature points according to the intersection road topology and the expected number of exits of the driving route in the intersection. The number of groups of feature points is consistent with the expected number of exits, and each group of feature points includes a number of internal feature points of the intersection and a number of external feature points of the intersection;

A path calculation module, used for inputting the obtained multiple sets of feature points into a path calculation function to obtain corresponding different candidate static continuous paths; and

The discrete processing module is used to set the expected travel speed and the expected stop speed for each candidate static continuous path obtained, assign a travel speed to the autonomous vehicle according to the current state of the autonomous vehicle and the phase of the traffic light, obtain multiple candidate paths containing the speed information of the autonomous vehicle, discretize them, and output the final planned static discrete path.

In order to implement the above-mentioned embodiments, the embodiments of the present disclosure also propose a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to execute the static path planning method for an autonomous driving vehicle of the above-mentioned embodiments.

Reference is made to FIG8 , which shows a schematic diagram of the structure of an electronic device 100 suitable for implementing an embodiment of the present disclosure. It should be noted that the electronic device 100 includes a static path planning system for an autonomous driving vehicle, wherein the electronic device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, servers, etc. The electronic device shown in FIG8 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG8 , the electronic device 100 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. In the RAM 103, various programs and data required for the operation of the electronic device 100 are also stored. The processing device 101, the ROM 102, and the RAM 103 are connected to each other via a bus 104. An input/output (I/O) interface 105 is also connected to the bus 104.

Typically, the following devices may be connected to the I/O interface 105: an input device 106 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, etc.; an output device 107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 109. The communication device 109 may allow the electronic device 100 to communicate wirelessly or wired with other devices to exchange data. Although FIG. 5 shows an electronic device 100 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present embodiment includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 109, or installed from the storage device 108, or installed from the ROM 102. When the computer program is executed by the processing device 101, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: selects multiple groups of feature points according to the road topology of the intersection and the expected number of exits of the driving route in the intersection, the number of groups of feature points is consistent with the expected number of exits, and each group of feature points includes a number of internal feature points of the intersection and a number of external feature points of the intersection; inputs the obtained multiple groups of feature points into the path calculation function to obtain corresponding different candidate static continuous paths; sets an expected passing rate and an expected stopping rate for each obtained candidate static continuous path, assigns a driving rate to the autonomous driving vehicle according to the current state of the autonomous driving vehicle and the phase of the traffic light, obtains multiple candidate paths containing the rate information of the autonomous driving vehicle, discretizes them, and outputs the final planned static discrete path.

Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, python, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

A person of ordinary skill in the art may understand that all or part of the steps carried out in the above-mentioned embodiment method may be implemented by instructing the relevant hardware through a program, and the developed program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims (5)

1. A method for planning a static path of an automatic driving automobile, comprising:

selecting a plurality of groups of characteristic points according to road topology of an intersection and the expected number of exits of a running route in the intersection, wherein the number of the groups of the characteristic points is consistent with the expected number of exits, and each group of the characteristic points comprises a plurality of intersection internal characteristic points and a plurality of intersection external characteristic points;

inputting a plurality of groups of characteristic points into a path calculation function to obtain corresponding different candidate static continuous paths;

setting expected traffic rate and expected stop rate for each candidate static continuous path, distributing running rate for the automatic driving automobile according to the current state of the automatic driving automobile and signal lamp phase, obtaining a plurality of candidate paths containing speed information of the automatic driving automobile, discretizing the candidate paths, and outputting a final planned static discrete path;

the external feature points of the intersection are selected according to the following steps:

setting the expected exit number of the running routes in the intersection as the number N of candidate static continuous paths, and marking the midpoint of the lane starting lines of the N expected exitsIs X _1,4 ,X _2,4 ,…,X _i,4 ,…,X _N,4 I e {1,2,3, …, N }; marking the midpoint of a lane stop line of an entrance where an automatic driving automobile is located as X ₁ Copy N times to X _1,1 ,X _2,1 ,…,X _i,1 ,…,X _N,1 The method comprises the steps of carrying out a first treatment on the surface of the From X _i,1 Moving distance l along opposite driving direction of entrance lane of automatic driving automobile ₁ Obtaining X _1,0 ,X _2,0 ,…,X _i,0 ,…,X _N,0 The method comprises the steps of carrying out a first treatment on the surface of the From X _i,4 Distance l of departure along running direction of parallel exit lane ₂ Obtaining X _1,5 ,X _2,5 ,…,X _i,5 ,…,X _N,5 The method comprises the steps of carrying out a first treatment on the surface of the Selecting X _i,0 、X _i,1 、X _i,4 And X _i,5 The corresponding feature points are used as the intersection external feature points of the ith candidate static continuous path;

the intersection internal feature points are selected according to the following steps:

let the coordinates of the feature points inside the intersection of the ith candidate static continuous path be X _i,2 And X _i,3 Selecting the characteristic points in the intersection according to the following steps:

wherein θ ₁ For the included angle theta between the driving direction of the entrance lane and the transverse axis of the intersection coordinate axis _i,2 An included angle between the driving direction of the ith candidate exit lane and the transverse axis of the intersection coordinate axis is formed;

for the ith candidate static continuous path, it will be located at X _i,0 And X _i,1 The path between them is located at X _i,1 And X _i,4 The path between them and is located at X _i,4 And X _i,5 The paths between are respectively marked asAnd->The path computation functions employed are as follows:

wherein t is ₁ 、t ₂ And t ₃ Respectively is withAnd->Corresponding parameters;

will beAnd->Sequentially connected end to form a static continuous path +.>

The driving speed is distributed for the automatic driving automobile according to the current state of the automatic driving automobile and the phase of the signal lamp, and the driving speed is specifically as follows:

3-1-1) automatic driving automobile Slave X _i,0 If the automobile is driven to X in the automatic driving _i,1 Before, the signal lamp is always green, or the signal lamp is always yellow and the automatic driving automobile can be driven by the residual yellowIf the inter-vehicle travel exceeds the stop line, the automatic driving vehicle is set to travel to X at a desired traveling rate _i,1 Executing the step 3-1-2); if the automobile is driven to X in automatic driving _i,1 Before, the signal lamp is always red, or the signal lamp is always yellow, and the automatic driving automobile cannot travel in the remaining yellow time to exceed the stop line, the automatic driving automobile is set to travel to X at the expected stop speed _i,1 Executing the step 3-1-2); if the automobile is driven to X in automatic driving _i,1 Before, when the phase of the signal lamp changes, the driving speed of the automatic driving automobile is jumped to be the expected stop speed or the expected traffic speed until the automatic driving automobile is driven to X _i,1 Executing the step 3-1-2);

3-1-2) autopilot automobile is located at X _i,1 If the signal lamp is a yellow lamp or a green lamp, the automatic driving automobile is set to drive to X at the expected passing rate _i,5 The method comprises the steps of carrying out a first treatment on the surface of the If the signal lamp is red, the automatic driving automobile is set to drive at the expected stop speed until the signal lamp turns to be green, and the automatic driving automobile is set to drive at the expected passing speed to X _i,5 。

2. The method for planning static path of automatic driving vehicle according to claim 1, wherein the feature points inside and outside each intersection are classified according to N expected exits to obtain feature point groups of N candidate paths

3. The method for planning a static path of an automatic driving automobile according to claim 1, wherein the plurality of candidate paths containing speed information of the automatic driving automobile are discretized by means of equal time distances or equal space distances.

4. An automatic driving car static path planning device based on the automatic driving car static path planning method according to any one of claims 1 to 3, characterized by comprising:

the characteristic point selection module is used for selecting a plurality of groups of characteristic points according to the road topology of the intersection and the expected number of exits of the running route in the intersection, wherein the number of the groups of the characteristic points is consistent with the expected number of the exits, and each group of the characteristic points comprises a plurality of intersection internal characteristic points and a plurality of intersection external characteristic points;

the path calculation module is used for inputting a plurality of groups of characteristic points into the path calculation function to obtain corresponding different candidate static continuous paths; and

and the discrete processing module is used for setting expected traffic rate and expected stop rate for each candidate static continuous path, distributing running rate for the automatic driving automobile according to the current state and signal lamp phase of the automatic driving automobile, obtaining a plurality of candidate paths containing speed information of the automatic driving automobile, discretizing the candidate paths and outputting a final planned static discrete path.

5. A storage medium storing computer instructions for causing a computer to perform the method of static path planning for an autonomous vehicle according to any one of claims 1 to 3.