CN113264038A

CN113264038A - Unmanned vehicle parking method and device based on temporary event and electronic equipment

Info

Publication number: CN113264038A
Application number: CN202110810680.3A
Authority: CN
Inventors: 张弛
Original assignee: Neolix Technologies Co Ltd
Current assignee: Neolix Technologies Co Ltd
Priority date: 2021-07-19
Filing date: 2021-07-19
Publication date: 2021-08-17
Anticipated expiration: 2041-07-19
Also published as: CN113264038B

Abstract

The disclosure relates to the technical field of unmanned driving, and provides an unmanned vehicle parking method and device based on a temporary event and electronic equipment. The method is applied to an automatic driving vehicle or an unmanned vehicle, and comprises the following steps: acquiring a parking instruction generated by a temporary event; judging whether a parking instruction is responded according to a first decision rule, and determining whether the parking instruction contains a target parking position after the parking instruction is responded; when the target parking position is included, judging whether the vehicle is parked at the target parking position according to a second decision rule; when the parking is judged not to be carried out at the target parking position, the target parking position is adjusted; and when the target parking position is not included or the driving position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks along the side according to a third decision rule. The method and the device can realize triggering of the parking function of the unmanned vehicle based on the temporary event, dynamically adjust the parking position of the unmanned vehicle, and improve the interaction capacity and the environment coping capacity between the unmanned vehicle and external users.

Description

Unmanned vehicle parking method and device based on temporary event and electronic equipment

Technical Field

The present disclosure relates to the field of unmanned driving technologies, and in particular, to an unmanned vehicle parking method and apparatus based on a temporary event, and an electronic device.

Background

The unmanned vehicle is a comprehensive system integrating functions of environmental perception, planning decision, multi-level auxiliary driving and the like, and is also called as an automatic driving vehicle and an unmanned vehicle. During the driving process of the unmanned vehicle, the unmanned vehicle may need to cope with temporary events in a task scene, for example, taking an automatic taxi as an example, the automatic taxi needs to handle a task of bringing a passenger to take a bus at the roadside, and after receiving a passenger bringing signal, the unmanned vehicle realizes temporary parking beside the passenger according to needs.

At present, the existing unmanned vehicle parking mode mainly aims at station parking, namely parking is realized by planning a path to a parking point according to a preset parking point, the parking point theoretically belongs to a position where parking can be performed, and the parking position of temporary event trigger type parking is possibly limited by constraint conditions such as road environment, traffic rules, obstacles and the like. Therefore, the existing parking mode based on the station cannot realize triggering of parking of the unmanned vehicle based on the temporary event, and further cannot realize dynamic adjustment of the parking position of the unmanned vehicle.

Based on prior art, need provide one kind and can trigger unmanned car parking function based on interim event, the parking position of dynamic adjustment unmanned car promotes unmanned car and the external user between the interactive ability's unmanned car parking scheme.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide a method and an apparatus for parking an unmanned vehicle based on a temporary event, and an electronic device, so as to solve the problems that triggering the unmanned vehicle to park based on the temporary event cannot be implemented, and dynamic adjustment of a parking position of the unmanned vehicle cannot be implemented in the prior art.

In a first aspect of the disclosed embodiments, a method for parking an unmanned vehicle based on a temporary event is provided, including: acquiring a parking instruction generated by a temporary event, wherein the temporary event comprises an event capable of triggering the unmanned vehicle to park; judging whether the unmanned vehicle responds to a parking instruction according to a first decision rule, and determining whether the parking instruction contains a target parking position after responding to the parking instruction; when the parking instruction is determined to contain the target parking position, judging whether the unmanned vehicle parks at the target parking position according to a second decision rule, and executing a parking task when the unmanned vehicle parks at the target parking position is judged; when judging that the unmanned vehicle does not park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position; when the parking instruction does not contain the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks in the side direction or not according to a third decision rule, and executing a parking task when the judgment result shows that the unmanned vehicle parks in the side direction; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task; and in the process of executing the parking task, judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule.

In a second aspect of the disclosed embodiments, there is provided an unmanned vehicle parking apparatus based on a temporary event, including: the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is configured to acquire a parking instruction generated by a temporary event, and the temporary event comprises an event which can trigger the unmanned vehicle to park; the first judgment module is configured to judge whether the unmanned vehicle responds to a parking instruction according to a first decision rule, and after the unmanned vehicle responds to the parking instruction, whether the parking instruction contains a target parking position is determined; the second judgment module is configured to judge whether the unmanned vehicle parks at the target parking position according to a second decision rule when the parking instruction is determined to contain the target parking position, and execute a parking task when the unmanned vehicle is judged to park at the target parking position; when judging that the unmanned vehicle does not park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position; the third judgment module is configured to judge whether the unmanned vehicle parks in the side according to a third decision rule when the parking instruction does not contain the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, and execute a parking task when the judgment result shows that the unmanned vehicle parks in the side; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task; and the fourth judgment module is used for judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule in the process of executing the parking task.

In a third aspect of the embodiments of the present disclosure, an electronic device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method when executing the program.

The embodiment of the present disclosure adopts at least one technical scheme that can achieve the following beneficial effects:

the method comprises the steps of obtaining a parking instruction generated by a temporary event, wherein the temporary event comprises an event capable of triggering the unmanned vehicle to park; judging whether the unmanned vehicle responds to a parking instruction according to a first decision rule, and determining whether the parking instruction contains a target parking position after responding to the parking instruction; when the parking instruction is determined to contain the target parking position, judging whether the unmanned vehicle parks at the target parking position according to a second decision rule, and executing a parking task when the unmanned vehicle parks at the target parking position is judged; when judging that the unmanned vehicle does not park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position; when the parking instruction does not contain the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks in the side direction or not according to a third decision rule, and executing a parking task when the judgment result shows that the unmanned vehicle parks in the side direction; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task; and in the process of executing the parking task, judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule. The system can trigger the parking function of the unmanned vehicle based on the temporary event, dynamically adjust the parking position of the unmanned vehicle, improve the interaction capacity between the unmanned vehicle and external users, and improve the environment coping capacity of the unmanned vehicle.

Drawings

To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a schematic diagram of an autopilot system provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a temporary event triggered parking decision maker provided by an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart diagram of a method for parking an unmanned vehicle based on a temporary event according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating a process for determining parking decisions based on temporary events according to an embodiment of the present disclosure;

fig. 5 is a schematic view illustrating a process of determining parking position adjustment according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an unmanned vehicle parking device based on a temporary event according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

During driving, an unmanned vehicle (hereinafter also referred to as an autonomous vehicle) may need to cope with temporary emergencies in a scene according to different task scene attributes, for example: the method comprises the following steps that a scene that a roadside passenger takes a taxi is required to be processed when a taxi is automatically driven, and after a passenger hand-taking signal is received, the taxi is temporarily parked in front of the passenger by the side according to requirements; for another example, in the cruising and retail process of the automatic driving retail vehicle, if the vehicle body is provided with the retail touch screen, when passengers click the touch screen to need to hold on for purchase, the vehicle needs to be temporarily stopped; for example, in the driving process of the automatic driving vehicle, the remote cloud terminal issues an immediate parking instruction, and the vehicle needs to be temporarily forced to park or temporarily close to the side to park according to the cloud terminal instruction.

Compared with the existing parking mode based on a fixed stop, the parking space of the trigger type parking based on the temporary event is influenced by the constraint conditions such as road environment, traffic rules, obstacles and the like, for example, the passenger recruitment position belongs to a position where the traffic rules do not allow parking, and the vehicle needs to dynamically adjust the parking position, even give up responding to the parking signal. At present, a stop parking mode based on a known parking point is focused on how to plan a reasonable path from a vehicle to the parking point by using a path planning module according to the known parking point, and a decision on how to make a parking decision specifically, such as whether to respond to parking, how to select the parking point, how to maintain a state in the parking process and the like, after a parking instruction triggered by a temporary event is received in the automatic driving process is not disclosed. Therefore, the existing station parking mode cannot realize dynamic adjustment of the parking position of the unmanned vehicle, the interaction capacity of the automatic driving vehicle and external clients is reduced, and meanwhile, the environment coping capacity of the unmanned vehicle is reduced.

Based on the above prior art solution, the embodiments of the present disclosure mainly focus on and solve the following two technical problems, specifically:

on the first hand, after receiving a temporary parking instruction in the driving process of an automatic driving vehicle, the automatic driving vehicle integrates road environment information, and how to judge whether to make a final parking decision and how to select a parking position;

in a second aspect, during a responsive stop, an autonomous vehicle may have traveled past a stop position but failed to complete a stop procedure for any number of reasons (e.g., traveled on a multi-lane, failed to change lane to side lane stop, but the longitudinal distance has passed the stop position), and determine whether to readjust the stop position to continue responding to a stop command.

The following describes functional modules of an improved automatic driving system according to an embodiment of the present disclosure with reference to the drawings. Fig. 1 is a schematic structural diagram of an automatic driving system provided in an embodiment of the present disclosure. As shown in fig. 1, the automatic driving system mainly includes the following:

the automatic driving system comprises a sensing module, a positioning module (including a map module), a decision planning module, a control module and a bottom layer module, wherein the decision planning module is divided into a decision module and a motion planning module, the decision module is used for making a decision on the current driving state of the unmanned vehicle, and the motion planning module plans a specific driving track based on a driving reference line by considering constraint conditions such as barriers, road environments and the like and is executed by the control module. In the embodiment of the present disclosure, the temporary event triggered parking function may be implemented by a temporary event triggered parking decider in the decision planning module, and the decision module may further include other function modules, such as a cruise function, a lane change function, a reverse driving function, a lane crossing turning function, and the like, in addition to the temporary event triggered parking function module.

Further, in the embodiment of the present disclosure, the temporary event triggered parking function in the decision module is mainly used for making a parking decision, and specifically, is mainly used for determining whether the temporary parking function can be triggered, and maintaining a parking state. The operation principle of the temporary event triggered parking decision maker in the embodiment of the present disclosure is described below with reference to the accompanying drawings. Fig. 2 is a schematic diagram of a temporary event triggered parking decision maker provided by an embodiment of the present disclosure. As shown in fig. 2, the temporary event triggered parking decision maker mainly includes the following components:

the internal state of the temporary event triggered parking decision maker comprises an initialization state (namely an Init state), a parking state (namely a Doing state) is executed, and a parking state (namely a Finish state) is completed, wherein the decision maker judges whether the final parking decision can be triggered currently or not in the Init state; in the Doing state, the decision maker judges whether to finish parking, whether to finish parking and whether to give up parking in real time; and in the Finish state, the decision maker judges that the parking task is finished and returns to the Init state again.

It should be noted that, in the embodiment of the present disclosure, the parking decision maker triggered by a temporary event mainly implements a parking decision based on a temporary event by performing the following four aspects of determination and calculation, where the four aspects of determination include: (1) whether the parking instruction (2) can be responded currently, whether the current parking task has the target parking position (3) and whether the current parking task needs to be parked by the roadside (4) or not, whether the parking task can be ended currently, and whether the parking task can be continued or not are described in the following embodiments of the present disclosure by taking the four judgments as main decision judgments, and detailed descriptions are provided for the embodiments of the present disclosure.

Fig. 3 is a schematic flow chart of a method for parking an unmanned vehicle based on a temporary event according to an embodiment of the present disclosure. The temporary event based unmanned vehicle parking method of fig. 3 may be performed by an electronic device in an autonomous driving system. As shown in fig. 3, the method for parking an unmanned vehicle based on a temporary event may specifically include:

s301, a parking instruction generated by a temporary event is acquired, wherein the temporary event comprises an event capable of triggering the unmanned vehicle to park;

s302, judging whether the unmanned vehicle responds to a parking instruction according to a first decision rule, and determining whether the parking instruction contains a target parking position after responding to the parking instruction;

s303, when the parking instruction is determined to contain the target parking position, judging whether the unmanned vehicle parks at the target parking position according to a second decision rule, and executing a parking task when the unmanned vehicle parks at the target parking position is judged; when judging that the unmanned vehicle does not park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position;

s304, when the parking instruction does not contain the target parking position or the running position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks in the side direction according to a third decision rule, and executing a parking task when the judgment result shows that the unmanned vehicle parks in the side direction; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task;

and S305, judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule in the process of executing the parking task.

Specifically, the temporary event (also referred to as a temporary parking event) may be regarded as an event that the unmanned vehicle can generate a temporary parking instruction during the road driving process, and in practical applications, the following behaviors may be taken as the temporary parking event, for example: the parking is controlled by the cloud; the parking instruction or the parking signal generated by the temporary parking event may include a target parking position (e.g., a hand-in position) and a forced parking instruction.

Further, in practical application, environmental data around the vehicle can be sensed in real time through a sensing module (such as a sensor installed on an unmanned vehicle), whether a temporary parking event occurs or not is judged according to the environmental data, for example, when a camera collects an image of a user waving hand, a user area in the image is extracted, and whether the user is waving is judged according to the extracted user area image, so that whether the waving parking event occurs or not is judged; in addition, the system can also receive an instruction sent by the cloud end in real time according to a communication module in the automatic driving system, and judge whether a temporary parking event occurs according to the instruction, for example, a remote driving platform sends a parking instruction to the unmanned vehicle through the cloud end.

Further, in the embodiment of the present disclosure, the parking instruction may include a target parking position and/or a forced parking instruction, and therefore, according to the target parking position and/or the forced parking instruction in the parking instruction, the parking decision of the embodiment of the present disclosure may be divided into different situations, which is described in detail below with reference to specific embodiments, which may specifically include the following:

whether the parking position comprises a target parking position or not is distinguished, if the parking position comprises a preset parking position, a specific parking position and a transverse offset with a road need to be calculated, and the parking position sent by a trigger event may not be parked or the lane change is required to be carried out to a side lane of the road at present (according to the current environmental constraint, the lane change distance needs to be dynamically adjusted in real time); if the vehicle does not contain the preset parking position, the vehicle is decelerated and parked close to the side (or not close to the side) under the safe state (whether the lane is changed to a side lane of a road or not needs to be considered);

distinguishing from the point of whether the forced parking command is included, if the forced parking command is included in the parking command, directly responding to the parking command (generally used for responding to a command sent by a cloud) without considering road traffic rules; if the parking instruction does not contain forced parking, the preset parking space needs to be readjusted according to the calculation of the traffic rules of the road, and if the parking space cannot be adjusted successfully within a certain threshold range, the parking task is given up, and the vehicle end is controlled to feed back the parking task to an external user.

According to the technical scheme provided by the embodiment of the disclosure, a parking instruction generated by a temporary event is acquired, wherein the temporary event comprises an event which can trigger the unmanned vehicle to park; judging whether a parking instruction is responded according to a preset first decision rule, and determining whether the parking instruction contains a target parking position after the parking instruction is responded; when the target parking position is included, judging whether parking is carried out at the target parking position according to a preset second decision rule, and executing a parking task when the parking is judged at the target parking position; when the parking is judged not to be performed at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position; when the target parking position is not included or the driving position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks near according to a preset third decision rule, and executing a parking task when the judgment result shows that the unmanned vehicle parks near; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task; and in the process of executing the parking task, judging whether to finish the parking task according to a preset fourth decision rule. The system can trigger the parking function of the unmanned vehicle based on the temporary event, dynamically adjust the parking position of the unmanned vehicle, improve the interaction capacity between the unmanned vehicle and external users, and improve the environment coping capacity of the unmanned vehicle.

In some embodiments, determining whether the unmanned vehicle responds to the parking instruction according to a first decision rule includes: and responding to a parking instruction for the unmanned vehicle, and judging whether parking is allowed under the current road scene according to the road environment information, the traffic identification information, the traffic regulation information and the high-precision map information after the parking instruction is acquired so as to judge whether the parking instruction is responded.

Specifically, the road environment information may include pedestrian information, vehicle information, obstacle information, road surface information, and the like on the road, the traffic identification information may include traffic signs (such as a parking prohibition sign, an emergency lane sign, and the like) on both sides of the road, the traffic regulation information may include traffic regulations (such as a parking prohibition area, a lane change prohibition, and the like) corresponding to the current travel section, the high-precision map information includes a high-precision map that is preloaded into the automatic driving system, and the high-precision map information includes lane information, exit information, obstacle information on both sides of the road, traffic signs, speed limit information, and the like.

Further, in the embodiment of the present disclosure, taking the traffic rule information as an example, a process of determining the first decision rule is described, for example: when the road area corresponding to the target parking position is a parking prohibition area (such as a parking area or an exit position area of an emergency ambulance), it is determined that the current target parking position does not permit parking, and the parking instruction is not responded. For another example, by acquiring road environment information around the target parking position, and determining that a road segment ahead of the target parking position belongs to the main highway road (an emergency lane of the highway belongs to the emergency parking-permitted road segment) based on the road environment information, it is determined that the current target parking position is not permitted to be parked.

In some embodiments, determining whether the unmanned vehicle is parked at the target parking position according to a second decision rule includes: the method comprises the steps of obtaining road environment information, traffic identification information, traffic regulation information and high-precision map information corresponding to a road section within a preset threshold range of a target parking position, and judging whether the target parking position has a parking condition or not according to the road environment information, the traffic identification information, the traffic regulation information, the high-precision map information and the distance between an unmanned vehicle and the target parking position.

Specifically, the first decision rule is used for determining whether the target parking position is in a parking available area, that is, whether the target parking position has the basic parking condition, and the second decision rule further determines whether to park in the target parking position, thereby further verifying whether the target parking position has the parking condition.

Further, in the embodiment of the present disclosure, by increasing distance information between the unmanned vehicle and the target parking position, whether to park the vehicle is further determined according to the distance information, taking a user hiring a parking scene as an example, when a distance between the user hiring a parking position and the automatically driven taxi exceeds a certain threshold, the parking decision maker of the automatically driven taxi determines that the vehicle needs to move a longer distance, and at this time, determines that the vehicle is not parked at the target parking position, and readjusts the target parking position or refuses to respond to a parking instruction.

In some embodiments, when it is determined that the unmanned vehicle parks at the target parking position, the parking task is performed, including: and when the parking condition of the target parking position is judged, generating a driving reference line corresponding to the unmanned vehicle according to the target parking position so that the unmanned vehicle executes a parking task along the driving reference line.

Specifically, after the determination of the first decision rule and the second decision rule, it is determined that the target parking position has the parking condition, and in this case, a driving reference line capable of driving the unmanned vehicle to the target parking position may be generated according to the target parking position, and the driving reference line may be specifically generated by the decision module. It should be noted that the driving reference line is different from the planned trajectory of the path planning module, and the driving reference line is used to indicate what driving trajectory the unmanned vehicle can move to the target parking position, and the specific path and speed in the moving process still need to be processed by the motion planning module.

In some embodiments, when it is determined that the unmanned vehicle is not parked at the target parking position, adjusting the target parking position includes: and when the target parking position is judged not to have the parking condition, readjusting the target parking position according to the road environment information, the traffic identification information, the traffic rule information and the high-precision map information corresponding to the road section within the preset threshold range of the target parking position.

Specifically, after the judgment of the first decision rule and the second decision rule, it is determined that the target parking position does not have the parking condition, at this time, the target parking position is adjusted, specifically, a new target parking position is determined again by acquiring road environment information, traffic identification information, traffic regulation information and high-precision map information corresponding to a road section within a certain preset threshold range around the target parking position and calculating the road environment information, the traffic identification information, the traffic regulation information and the high-precision map information, for example, the new target parking position can meet the requirement that a vehicle head is parked before a temporary event trigger point.

In some embodiments, determining whether the unmanned vehicle parks alongside according to a third decision rule comprises: determining the transverse offset between the unmanned vehicle and the roadside, and determining the number of lane changing times and the longitudinal distance of the lane changing when the unmanned vehicle changes from the current lane to the roadside; determining whether the roadside has an edge-approaching parking condition or not according to the transverse offset, the lane changing times, the longitudinal distance and road environment information within a preset roadside range; and when the roadside is determined to have the side parking condition, determining the side parking position, acquiring barrier information before and after the side parking position, and judging whether to execute the side parking task according to the barrier information.

Specifically, the third decision rule is mainly used for determining whether to park by side, and in practical application, whether to park by side may be determined according to the attribute of the temporary event, for example: passengers get on or off the vehicle, cargo handling and the like need to park the vehicle by the roadside, and other vehicles on the road can be parked by the roadside without influencing the driving of the other vehicles; when the automatic driving retail vehicle temporarily parks, whether obstacles interfere with the front and the back of the parking position in the lane can be calculated according to the parking position, and if the obstacles do not interfere with the front and the back of the parking position, the automatic driving retail vehicle can be judged to park by side; if the obstacle interferes, the parking near the edge is not triggered; the obstacle at the roadside parking position is judged in advance, so that the driving capacity of the vehicle after the temporary parking event is finished can be improved.

Further, in the embodiment of the present disclosure, when determining whether there is an edge parking condition, it is necessary to determine whether to park an edge parking and a position of the edge parking according to the number of lane changes, the longitudinal distance of the lane changes, and an obstacle of the lane change parking position, for example: and if the current vehicle runs on a non-side lane of the multi-lane and needs to change the lane to a side lane for parking, calculating the longitudinal distance required by lane change according to the number of lane change times. The following detailed description is given to the decision process of lane change and side parking with reference to a specific embodiment, which may specifically include the following contents:

the lane changing module is used for providing a lane changing function from lane changing to a side lane, and if the current vehicle runs in a non-side lane, the temporary event triggered parking decision-making calls the lane changing module to calculate whether the lane changing can be successful or not and provides a lane changing reference line for follow-up; after receiving an edge parking instruction issued by the temporary event trigger type parking decision module, the path planning module synthesizes road information and plans a specific parking transverse track; after receiving an edge-approaching parking instruction sent by a temporary event trigger type parking decision module, the offset driving module integrates road information and calculates a specific distance capable of approaching the edge; the speed protection module provides the maximum speed limit of the speed in the parking stage, and the transverse and longitudinal precision of parking is improved; the speed planning module integrates the road information and the transverse track of the path planning, the speed limit provided by the speed protection module plans the specific longitudinal speed, and the transverse and longitudinal precision of parking is improved.

In some embodiments, determining whether the unmanned vehicle finishes the parking task according to a fourth decision rule comprises: determining the parking position of the unmanned vehicle after the parking task is executed, and judging whether the unmanned vehicle can continue to execute the current routing task after the parking task is executed according to the road environment information in the preset range corresponding to the parking position of the unmanned vehicle; and when judging that the unmanned vehicle cannot continuously execute the current routing task, ending the parking task, or dynamically adjusting the parking position of the unmanned vehicle in the parking process of the unmanned vehicle.

Specifically, in order to avoid that the unmanned vehicle cannot continue to execute the current routing task at the parking position where the unmanned vehicle is located and the surrounding road environment after the unmanned vehicle executes the temporary parking task, a fourth decision rule is required to be used for judging the situation. That is to say, the fourth decision rule is used for judging whether the global routing planning from the parking position of the unmanned vehicle to the current task is feasible after the temporary parking instruction is supposed to be completed, so that the situation that the unmanned vehicle falls into a dead zone and cannot continue to run due to the fact that the temporary parking task is responded is prevented.

In some embodiments, the parking instruction further includes a forced parking instruction, and the executing of the forced parking task according to the forced parking instruction includes: responding to a forced parking instruction for the unmanned vehicle, acquiring road environment information, traffic identification information, traffic regulation information and high-precision map information within a preset range around the unmanned vehicle, and judging whether to execute a forced parking task according to the road environment information, the traffic identification information, the traffic regulation information and the high-precision map information; and when the forced parking task is judged to be executed, controlling the unmanned vehicle to immediately park.

Specifically, when the parking instruction comprises a forced parking instruction, information such as road traffic rules, road environment, high-precision maps and the like is comprehensively considered, and whether the vehicle immediately parks in response to the instruction is judged; if the parking instruction does not contain a forced parking instruction, the preset target parking position needs to be adjusted again according to the calculation of the traffic rules of the road, and if the parking space cannot be adjusted successfully within a certain threshold range, the parking task is given up, and the vehicle end is controlled to feed back the parking task to an external user.

Further, specific triggered signs and state feedback are different for each temporary parking event, and a basic decision flow for triggering parking by a temporary event in the embodiment of the present disclosure is described below with reference to the accompanying drawings. Fig. 4 is a schematic view of a determination process of parking decision based on a temporary event according to an embodiment of the present disclosure. As shown in fig. 4, the parking decision determining process mainly includes the following steps:

the current parking state indicates that the temporary parking instruction needing to be responded is calculated, and the current parking state is in a state of continuously responding to the temporary parking instruction;

vehicle state control, parking timer maintenance; when the current vehicle finishes parking, vehicle state control is carried out, such as parking, door opening and other states (vehicle response is different according to trigger events), meanwhile, a parking timer starts to time, when the parking time reaches a set time or a trigger mark for finishing the event is received, the parking task is tried to finish, and the task is continuously executed or a new task after the event is triggered is executed;

when judging whether starting is possible, judging whether starting is possible or not according to the vehicle state (such as judgment of vehicle door closing information and the like, and judgment difference according to a trigger event);

when judging whether the front road section is allowed to stop within the threshold value, whether the road section within the front threshold value range contains a stop prohibition identification or not, or whether the front road section is completely positioned at an intersection or a stop prohibition area (for example, a 119 vehicle exit or a 120 vehicle exit), or whether the front road section belongs to a stop prohibition road section such as a main highway road (an emergency lane of a highway belongs to a stop permission road section), and whether the parking position is positioned within the range to prohibit the parking;

judging whether the parking position is adjusted again, entering a temporary parking state, but driving the parking position for various reasons but failing to complete the parking step (for example, driving in a multi-lane, failing to change lane to a side lane for parking, but the longitudinal distance passes through the parking position), and judging whether to adjust the parking position again and continue to respond to the parking instruction;

when the parking position is adjusted, calculating whether the parking position is in the range of the intersection and the forbidden parking area, and if so, adjusting the parking position to avoid parking in the range; otherwise, calculating a new parking position to meet the condition that the vehicle head parks before the event trigger point;

when the parking is carried out by the side, judging according to the event attribute; for example, passengers get on or off the vehicle, cargo handling and the like need to park the vehicle by the roadside, and other vehicles on the road are not influenced; the temporary retail parking calculates whether obstacles interfere with the front and the rear of the parking position in the lane according to the parking position, and if the obstacles do not interfere with the parking position, the parking is carried out by the side; if the obstacle interferes, the vehicle is not triggered to stop at the side, and the driving capacity of the vehicle after the parking event is finished is improved.

Further, the following describes a flow of adjusting the parking position in the embodiment of the present disclosure with reference to the drawings. Fig. 5 is a schematic view of a determination process of parking position adjustment according to an embodiment of the present disclosure. As shown in fig. 5, the flow of determining the parking position adjustment mainly includes the following contents:

calculating the times of changing lanes from a lane where the unmanned vehicle is located to a side lane, and calculating the longitudinal required distance dis1, wherein if the current vehicle runs on a non-side lane of a multi-lane, the lane needs to be changed to the side lane for parking, and the longitudinal distance required for changing lanes needs to be calculated according to the times of changing lanes; the step and the subsequent steps mainly calculate whether the initial parking position needs to be moved backwards under the consideration of lane change constraint; whether the global routing planning from the parking position to the current task is feasible or not is judged, and whether the current routing task can be continuously executed by the self-vehicle or not is judged after the response of assuming the temporary parking is finished; the problem that the vehicle runs continuously due to the fact that the vehicle falls into a dead zone in response to the temporary parking task is avoided.

According to the technical scheme provided by the embodiment of the disclosure, the unmanned vehicle needs to be frequently interacted with the outside in the driving process, and when an external interaction parking instruction is responded, whether parking conditions are met or not needs to be judged according to the current road environment. The disclosed embodiment provides a series of decision rules, which are used for realizing the judgment of whether an unmanned vehicle responds to a parking instruction, whether the unmanned vehicle parks at a target parking position, whether the unmanned vehicle parks at the side and whether the temporary parking task is finished or not by integrating information such as the parking instruction, road environment, traffic rules, traffic identification and the like aiming at different temporary events. The parking decision logic based on the temporary event can realize the maintenance of the parking process state, realize the real-time updating of the parking position, dynamically adjust the parking position of the unmanned vehicle, improve the interaction capacity between the unmanned vehicle and external users and the environment coping capacity of the unmanned vehicle, prevent the problems of traffic violation, road congestion and the like caused by direct response parking, improve the running efficiency of the unmanned vehicle and reduce the intervention frequency of a remote cloud.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

Fig. 6 is a schematic structural diagram of an unmanned vehicle parking device based on a temporary event according to an embodiment of the present disclosure. As shown in fig. 6, the unmanned vehicle parking apparatus based on the temporary event includes:

an obtaining module 601 configured to obtain a parking instruction generated by a temporary event, wherein the temporary event includes an event that can trigger the unmanned vehicle to park;

the first judging module 602 is configured to judge whether the unmanned vehicle responds to a parking instruction according to a first decision rule, and after responding to the parking instruction, determine whether the parking instruction includes a target parking position;

a second judging module 603 configured to, when it is determined that the parking instruction includes the target parking position, judge whether the unmanned vehicle parks at the target parking position according to a second decision rule, and execute a parking task when it is judged that the unmanned vehicle parks at the target parking position; when judging that the unmanned vehicle does not park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position;

a third determining module 604, configured to determine whether the unmanned vehicle parks near according to a third decision rule when it is determined that the parking instruction does not include the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, and execute a parking task when the determination result is that the unmanned vehicle parks near; when the judgment result is that the unmanned vehicle is parked without being leaned on the side, determining a parking position for the unmanned vehicle and executing a parking task;

the fourth determining module 605 determines whether the unmanned vehicle finishes the parking task according to a fourth decision rule in the process of executing the parking task.

In some embodiments, the first determining module 602 in fig. 6 determines, in response to a parking instruction for an unmanned vehicle, whether to allow parking in a current road scene according to the road environment information, the traffic identification information, the traffic regulation information, and the high-precision map information after the parking instruction is acquired, so as to determine whether to respond to the parking instruction.

In some embodiments, the second determining module 603 in fig. 6 obtains road environment information, traffic identification information, traffic regulation information, and high-precision map information corresponding to a road segment within a preset threshold range of the target parking position, and determines whether the target parking position has a parking condition according to the road environment information, the traffic identification information, the traffic regulation information, the high-precision map information, and a distance between the unmanned vehicle and the target parking position.

In some embodiments, after determining that the parking at the target parking position has the parking condition, the second determining module 603 in fig. 6 generates a driving reference line corresponding to the unmanned vehicle according to the target parking position, so that the unmanned vehicle performs the parking task along the driving reference line.

In some embodiments, after determining that the target parking position does not have the parking condition, the second determining module 603 in fig. 6 readjusts the target parking position according to the road environment information, the traffic identification information, the traffic regulation information, and the high-precision map information corresponding to the road segment within the preset threshold range of the target parking position.

In some embodiments, the third determining module 604 of fig. 6 determines a lateral offset between the unmanned vehicle and the roadside, and determines a lane change number and a lane change longitudinal distance when the unmanned vehicle changes from the current lane to the roadside; determining whether the roadside has an edge-approaching parking condition or not according to the transverse offset, the lane changing times, the longitudinal distance and road environment information within a preset roadside range; and when the roadside is determined to have the side parking condition, determining the side parking position, acquiring barrier information before and after the side parking position, and judging whether to execute the side parking task according to the barrier information.

In some embodiments, the fourth determining module 605 of fig. 6 determines the parking position of the unmanned vehicle after the parking task is executed, and determines whether the unmanned vehicle can continue to execute the current routing task after the parking task is executed according to the road environment information within the preset range corresponding to the parking position of the unmanned vehicle; and when judging that the unmanned vehicle cannot continuously execute the current routing task, ending the parking task, or dynamically adjusting the parking position of the unmanned vehicle in the parking process of the unmanned vehicle.

In some embodiments, the parking instruction further includes a forced parking instruction, and the forced parking module 606 in fig. 6, in response to the forced parking instruction for the unmanned vehicle, acquires road environment information, traffic identification information, traffic regulation information, and high-precision map information within a preset range around the unmanned vehicle, and determines whether to execute a forced parking task according to the road environment information, the traffic identification information, the traffic regulation information, and the high-precision map information; and when the forced parking task is judged to be executed, controlling the unmanned vehicle to immediately park.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

Fig. 7 is a schematic structural diagram of the electronic device 7 provided in the embodiment of the present disclosure. As shown in fig. 7, the electronic apparatus 7 of this embodiment includes: a processor 701, a memory 702, and a computer program 703 stored in the memory 702 and executable on the processor 701. The steps in the various method embodiments described above are implemented when the computer program 703 is executed by the processor 701. Alternatively, the processor 701 implements the functions of each module/unit in each device embodiment described above when executing the computer program 703.

Illustratively, the computer program 703 may be partitioned into one or more modules/units, which are stored in the memory 702 and executed by the processor 701 to accomplish the present disclosure. One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 703 in the electronic device 7.

The electronic device 7 may be a desktop computer, a notebook, a palm computer, a cloud server, or other electronic devices. The electronic device 7 may include, but is not limited to, a processor 701 and a memory 702. Those skilled in the art will appreciate that fig. 7 is merely an example of the electronic device 7, does not constitute a limitation of the electronic device 7, and may include more or less components than those shown, or combine certain components, or different components, e.g., the electronic device may also include input-output devices, network access devices, buses, etc.

The Processor 701 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage 702 may be an internal storage unit of the electronic device 7, for example, a hard disk or a memory of the electronic device 7. The memory 702 may also be an external storage device of the electronic device 7, such as a plug-in hard disk provided on the electronic device 7, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 702 may also include both an internal storage unit of the electronic device 7 and an external storage device. The memory 702 is used to store computer programs and other programs and data required by the electronic device. The memory 702 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/computer device and method may be implemented in other ways. For example, the above-described apparatus/computer device embodiments are merely illustrative, and for example, a division of modules or units, a division of logical functions only, an additional division may be made in actual implementation, multiple units or components may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method in the above embodiments, and may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the above methods and embodiments. The computer program may comprise computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain suitable additions or additions that may be required in accordance with legislative and patent practices within the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals or telecommunications signals in accordance with legislative and patent practices.

The above examples are only intended to illustrate the technical solutions of the present disclosure, not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present disclosure, and are intended to be included within the scope of the present disclosure.

Claims

1. An unmanned vehicle parking method based on temporary events is characterized by comprising the following steps:

acquiring a parking instruction generated by a temporary event, wherein the temporary event comprises an event capable of triggering the unmanned vehicle to park;

judging whether the unmanned vehicle responds to the parking instruction according to a first decision rule, and determining whether the parking instruction contains a target parking position after responding to the parking instruction;

when the parking instruction is determined to contain the target parking position, judging whether the unmanned vehicle parks at the target parking position according to a second decision rule, and executing a parking task when the unmanned vehicle parks at the target parking position is judged; when the unmanned vehicle is judged not to park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position;

when the parking instruction is determined not to contain the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, judging whether the unmanned vehicle parks in the way of leaning to the side according to a third decision rule, and executing a parking task when the judgment result shows that the unmanned vehicle parks in the way of leaning to the side; when the judgment result is that the unmanned vehicle is parked without being close to the side, determining a parking position for the unmanned vehicle and executing a parking task;

and in the process of executing the parking task, judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule.

2. The method of claim 1, wherein said determining whether the unmanned vehicle responds to the parking instruction according to a first decision rule comprises:

and responding to a parking instruction aiming at the unmanned vehicle, and judging whether parking is allowed under the current road scene according to the road environment information, the traffic identification information, the traffic regulation information and the high-precision map information after the parking instruction is acquired so as to judge whether the parking instruction is responded.

3. The method of claim 1, wherein the determining whether the unmanned vehicle is parked at the target parking location according to a second decision rule comprises:

acquiring road environment information, traffic identification information, traffic regulation information and high-precision map information corresponding to a road section within a preset threshold range of the target parking position, and judging whether the target parking position has a parking condition or not according to the road environment information, the traffic identification information, the traffic regulation information, the high-precision map information and the distance between the unmanned vehicle and the target parking position.

4. The method of claim 3, wherein performing a parking task when it is determined that the unmanned vehicle is parked at the target parking location comprises:

and when the target parking position is judged to have parking conditions, generating a driving reference line corresponding to the unmanned vehicle according to the target parking position so that the unmanned vehicle executes a parking task along the driving reference line.

5. The method of claim 3, wherein the adjusting the target parking position when it is determined that the unmanned vehicle is not parking at the target parking position comprises:

and when the target parking position is judged not to have the parking condition, readjusting the target parking position according to the road environment information, the traffic identification information, the traffic rule information and the high-precision map information corresponding to the road section within the preset threshold range of the target parking position.

6. The method of claim 1, wherein the determining whether the unmanned vehicle parks alongside according to a third decision rule comprises:

determining the transverse offset between the unmanned vehicle and the roadside, and determining the number of lane changing times and the longitudinal distance of the lane changing when the unmanned vehicle changes from the current lane to the roadside;

determining whether the roadside has an edge-approaching parking condition according to the transverse offset, the lane changing times, the longitudinal distance and road environment information within a preset roadside range;

when the roadside is determined to have the side parking condition, the side parking position is determined, the barrier information before and after the side parking position is obtained, and whether the side parking task is executed or not is judged according to the barrier information.

7. The method of claim 1, wherein the determining whether the unmanned vehicle ends the parking task according to a fourth decision rule comprises:

determining the parking position of the unmanned vehicle after the parking task is executed, and judging whether the unmanned vehicle can continuously execute the current routing task after the parking task is executed according to the road environment information in the preset range corresponding to the parking position of the unmanned vehicle;

and when the unmanned vehicle is judged to be incapable of continuously executing the current routing task, ending the parking task, or dynamically adjusting the parking position of the unmanned vehicle in the parking process of the unmanned vehicle.

8. The method of claim 1, wherein the parking instruction further comprises a forced parking instruction, and the executing of the forced parking task according to the forced parking instruction comprises:

responding to a forced parking instruction aiming at the unmanned vehicle, acquiring road environment information, traffic identification information, traffic regulation information and high-precision map information within a preset range around the unmanned vehicle, and judging whether to execute the forced parking task according to the road environment information, the traffic identification information, the traffic regulation information and the high-precision map information; and when the forced parking task is judged to be executed, controlling the unmanned vehicle to immediately park.

9. An unmanned vehicle parking apparatus based on a temporary event, comprising:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is configured to acquire a parking instruction generated by a temporary event, and the temporary event comprises an event which can trigger the unmanned vehicle to park;

the first judgment module is configured to judge whether the unmanned vehicle responds to the parking instruction according to a first decision rule, and after the parking instruction is responded, whether a target parking position is included in the parking instruction is determined;

the second judging module is configured to judge whether the unmanned vehicle parks at the target parking position according to a second decision rule when the parking instruction is determined to contain the target parking position, and execute a parking task when the unmanned vehicle is judged to park at the target parking position; when the unmanned vehicle is judged not to park at the target parking position, adjusting the target parking position, and executing a parking task based on the adjusted target parking position;

the third judging module is configured to judge whether the unmanned vehicle parks in the side according to a third decision rule when the parking instruction is determined not to contain the target parking position or the driving position of the unmanned vehicle exceeds the target parking position, and execute a parking task when the judgment result is that the unmanned vehicle parks in the side; when the judgment result is that the unmanned vehicle is parked without being close to the side, determining a parking position for the unmanned vehicle and executing a parking task;

and the fourth judgment module is used for judging whether the unmanned vehicle finishes the parking task according to a fourth decision rule in the process of executing the parking task.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 8 when executing the program.