CN113628471A

CN113628471A - Scheduling method, device, equipment and medium for unmanned vehicle

Info

Publication number: CN113628471A
Application number: CN202110909208.5A
Authority: CN
Inventors: 黄超; 韩旭
Original assignee: Guangzhou Weride Technology Co Ltd
Current assignee: Guangzhou Weride Technology Co Ltd
Priority date: 2021-08-09
Filing date: 2021-08-09
Publication date: 2021-11-09

Abstract

The invention discloses a method, a device, equipment and a medium for scheduling unmanned vehicles, which are applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the method comprises the following steps: when an online car booking order sent by any online car booking platform is received, extracting a vehicle identification and a planning route point; carrying out accessibility verification on the planned route points based on a preset semantic map, and carrying out position conversion on the planned route points according to verification results to generate vehicle control instructions; encrypting the vehicle control command, and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identification; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order. Therefore, the dispatching cloud platform is in butt joint with the network car booking platforms, the network car booking orders are analyzed, the car control instructions are generated, the unmanned vehicles are controlled, the unmanned vehicles can be rapidly connected into the car booking platforms, and the operation cost is greatly reduced.

Description

Scheduling method, device, equipment and medium for unmanned vehicle

Technical Field

The invention relates to the technical field of unmanned dispatching, in particular to a dispatching method, a device, equipment and a medium for an unmanned vehicle.

Background

With the continuous development of science and technology, the related technologies such as automatic driving, driving assistance and the like are optimized in the aspects of the driving experience and safety of the automobile, and the method has wide application prospects in the fields of national defense and national economy.

In the practical unmanned application, the net appointment is a common mode. However, the current unmanned vehicle open operation to the public generally comprises two modes: the unmanned vehicle is in butt joint with the network car booking operation platform, the order is forwarded to the unmanned vehicle through the network car booking operation platform to carry out passenger receiving and sending, or the operation of the unmanned network car booking is carried out in a mode of self-research and development of the network car booking platform.

However, in the operation process of the unmanned network car booking, the whole order uploading and issuing control flow needs to be researched and developed by the self-research and development network car booking platform, so that the research and development period is long, the investment cost is high, and the applicability is poor; the mode of accessing the taxi appointment operation platform is to analyze orders through the unmanned vehicles to complete the pickup of passengers, so that more computing resources are required for the unmanned vehicles, and the dispatching cost of the unmanned vehicles is increased.

Disclosure of Invention

The invention provides a scheduling method, a device, equipment and a medium for an unmanned vehicle, and solves the technical problems that the existing network appointment scheduling method requires more computing resources or the initial research and development period is long, so that the scheduling cost is high.

The invention provides a method for scheduling unmanned vehicles, which is applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the method comprises the following steps:

when an online car booking order sent by any one online car booking platform is received, extracting a vehicle identification and a planning route point;

carrying out accessibility verification on the planned route point, and carrying out position conversion on the planned route point according to a verification result to generate a vehicle control instruction;

encrypting the vehicle control command, and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identification; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order.

Optionally, the step of extracting a vehicle identifier and a planned route point when receiving a network car booking order sent by any one of the network car booking platforms includes:

if the network appointment order has the passing point, extracting the passing point;

if the route point does not exist in the network taxi appointment order, inquiring a preset semantic map, and determining a planned path from the starting point to the destination point;

and extracting the passing point to update the planned path according to the real-time road condition information corresponding to the planned path.

Optionally, the step of extracting the route point to update the planned path according to the real-time traffic information corresponding to the planned path includes:

judging whether the planned path has a congested road section according to the real-time road condition information corresponding to the planned path;

if the congested road section does not exist, or the congested road section exists and the planning path does not have a steerable intersection, judging that the passing point is not extracted;

and if the congested road section exists and the planned path has a steerable intersection, updating the planned path by using the steerable intersection as a passing point, and skipping to execute the step of judging whether the planned path has the congested road section according to the real-time road condition information corresponding to the planned path until the skipping times are equal to a preset skipping threshold value.

Optionally, the congested road segment includes at least one congested sub-road segment, the steerable intersection includes a first steerable intersection and a second steerable intersection, if the congested road segment exists and the planned path has the steerable intersection, the steerable intersection is used as a passing point to update the planned path, and the step of judging whether the planned path has the congested road segment according to real-time road condition information corresponding to the planned path is executed by skipping until the number of skips is equal to a preset skipping threshold value includes:

sequentially searching whether a first steerable intersection exists behind each congestion sub-road section in the semantic map according to a target reverse direction;

if the first steerable road junction exists, sequentially searching whether a second steerable road junction exists in front of each section of the congested sub-road section in the semantic map according to the forward direction of the destination;

inserting the first steerable intersection and the second steerable intersection into the planned path as passing points to generate a new planned path;

and skipping to execute the step of judging whether the planned path has a congested road section according to the real-time road condition information corresponding to the planned path until the skipping times are equal to a preset skipping threshold value.

Optionally, the reachability verification includes a viable license plate region verification and a viable region verification; the step of performing reachability verification on the planned route point includes:

performing feasible license plate area verification on the destination point and the starting point based on a plurality of longitude and latitude points extracted from a preset network map, and judging whether the destination point and the starting point are in a feasible license plate area;

searching a preset semantic map, performing feasible region verification on the destination point and the starting point, and judging whether the destination point and the starting point are in feasible regions;

and if the destination point and the starting point are both in the feasible license plate area and the feasible area, judging that the verification is passed, otherwise, judging that the verification is not passed.

Optionally, the step of performing feasible license plate area verification on the destination point and the starting point based on a plurality of longitude and latitude points extracted from a preset network map, and determining whether the destination point and the starting point are in a feasible license plate area includes:

retrieving a preset network map, extracting a plurality of longitude and latitude points corresponding to a feasible license plate area, and constructing a polygon marking frame along each longitude and latitude point;

if the number of first intersection points of the first ray constructed by taking the destination point as the starting point and the polygon marking frame is an odd number, the verification is passed, and the destination point is judged to be in the feasible license plate area;

if the number of second intersection points between the second ray constructed by taking the starting point as the starting point and the polygon marking frame is an odd number, the verification is passed, and the starting point is judged to be in the feasible license plate area;

and if the first intersection point number or the second intersection point number is an even number, the verification is not passed.

Optionally, the step of retrieving a preset semantic map, performing feasible region verification on the destination point and the starting point, and determining whether the destination point and the starting point are in a feasible region includes:

retrieving the semantic map, and verifying whether the destination point and the starting point are in the semantic map;

if so, acquiring the destination position coordinate of the destination point in the semantic map and the initial position coordinate of the starting point in the semantic map;

if the target position coordinate is in a road area in the semantic map, or a first distance between the target position coordinate and a vertical line intersection point of the road area is smaller than or equal to a preset distance threshold value, the verification is passed, and the target point is judged to be in a feasible area;

if the initial position coordinate is in the road area, or a second distance between the initial position coordinate and a perpendicular intersection of the road area is smaller than or equal to the distance threshold, passing the verification, and determining that the initial point is in a feasible area;

and if the destination position coordinate or the starting position coordinate is not in the road area in the semantic map, and the first distance or the second distance is greater than the distance threshold, the verification is failed.

Optionally, the step of performing location conversion on the planned route point according to the verification result to generate a vehicle control instruction includes:

if the target unmanned vehicle passes the verification, respectively converting the target point and the starting point into position coordinates of a coordinate system where the target unmanned vehicle is located, and generating a first vehicle control instruction and a second vehicle control instruction;

respectively setting the overtime time of the first vehicle control instruction and the second vehicle control instruction, and writing the overtime time into a preset instruction cache region;

wherein the first vehicle control instruction is used for controlling the target unmanned vehicle to move from the current position coordinate to the position coordinate of the starting point; the second vehicle control instruction is used for controlling the target unmanned vehicle to move from the position coordinate of the starting point to the position coordinate of the destination point along the planned route mark at the current moment.

Optionally, the method further comprises:

and if any verification fails or a planned path from the current position of the target unmanned vehicle to the destination point cannot be constructed, sending a vehicle replacement notice to the network appointment platform.

Optionally, the target unmanned vehicle includes a vehicle client and an unmanned system, and the target unmanned vehicle is specifically configured to:

receiving and decrypting the vehicle control command through the vehicle client

Acquiring a current vehicle identifier corresponding to the unmanned system through the vehicle client; the vehicle control command carries a command timestamp and the vehicle identification;

verifying, by the vehicle client, whether the vehicle identification is the same as the current vehicle identification;

verifying whether the instruction timestamp is less than a preset timeout time through the vehicle client;

if the vehicle identification is the same as the current vehicle identification and the instruction timestamp is less than the overtime, issuing the vehicle control instruction to the unmanned system through the vehicle client;

and executing the vehicle control command through the unmanned system to complete the network car appointment order.

The invention provides a scheduling device of an unmanned vehicle, which is applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the device comprises:

the data extraction module is used for extracting vehicle identification and planning route points when receiving a network car booking order sent by any one of the network car booking platforms;

the vehicle control instruction generating module is used for carrying out accessibility verification on the planned route point, carrying out position conversion on the planned route point according to a verification result and generating a vehicle control instruction;

the command encryption and issuing module is used for encrypting the vehicle control command and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identification; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order.

A third aspect of the present invention provides an electronic device comprising a memory and a processor, the memory having stored therein a computer program, the computer program, when executed by the processor, causing the processor to perform the method of scheduling an unmanned vehicle according to any one of the first aspect of the present invention.

A fourth aspect of the invention provides a computer readable storage medium having stored thereon a computer program which, when executed, implements a method of scheduling an unmanned vehicle according to any one of the first aspects of the invention.

According to the technical scheme, the invention has the following advantages:

the dispatching cloud platform is in communication connection with the plurality of network car booking platforms, when a network car booking order sent by any one network car booking platform is received, the vehicle identification and the planned route point are extracted from the network car booking order, accessibility verification is conducted on the planned route point according to a pre-marked semantic map so as to judge whether the unmanned vehicle can reasonably and legally arrive, if the unmanned vehicle can reasonably and legally arrive, the planned route point can be subjected to position conversion, a vehicle control command under a coordinate system where the unmanned vehicle is located is generated, the vehicle control command is encrypted and then issued to the target unmanned vehicle according to the vehicle identification, the target unmanned vehicle can be verified, the vehicle control command is executed to receive and send passengers, and the network car booking order is completed. The method solves the technical problems that the existing network car booking dispatching method requires more computing resources or the dispatching cost is high due to long initial research and development period, the unmanned vehicle is controlled by generating the vehicle control command in a mode that the dispatching cloud platform is in butt joint with the network car booking platforms and analyzing the sent network car booking orders, the network car booking orders do not need to be analyzed on the unmanned vehicle, the unmanned vehicle can be rapidly accessed to the network car booking platforms, and the operation cost is greatly reduced

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a flowchart illustrating steps of a scheduling method for an unmanned vehicle according to an embodiment of the present invention;

fig. 2 is a flowchart illustrating steps of a scheduling method for an unmanned vehicle according to a second embodiment of the present invention;

FIG. 3 is a flowchart of a vehicle identification and planned route point extraction process according to a second embodiment of the present invention;

fig. 4 is a flowchart of a route point generation process in the second embodiment of the present invention;

fig. 5 is a flowchart of a feasible license plate region verification process in the second embodiment of the present invention;

fig. 6 is a block diagram of a scheduling apparatus of an unmanned vehicle according to a third embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a scheduling method, a scheduling device and a scheduling medium for an unmanned vehicle, which are used for solving the technical problems of higher scheduling cost caused by more computing resources required by the conventional network appointment scheduling method or long initial research and development period.

In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a flowchart illustrating a method for scheduling an unmanned vehicle according to an embodiment of the present invention. The method for dispatching the unmanned vehicle can be executed by dispatching the unmanned vehicle, and the dispatching device of the unmanned vehicle can be realized by software and/or hardware and can be configured in electronic equipment, such as a computer, a server, an electronic terminal and the like.

step 101, when an online car booking order sent by any online car booking platform is received, extracting a vehicle identification and a planning route point;

the online taxi booking order in the embodiment of the invention refers to a taxi operation service booked by the network, a service platform is built by relying on the internet technology, vehicles and drivers meeting conditions are accessed, and the order provided by the operation activities of the taxi booking service of non-tour is provided by integrating supply and demand information. It should be noted that, in the embodiment of the present invention, the number of the network car booking platforms connected to the network car booking order and the scheduling cloud platform is not limited.

The dispatching cloud platform in the embodiment of the invention is a cloud computing platform which is used for establishing communication connection with a plurality of network car-booking cloud platforms according to a specific communication protocol such as https and the like, analyzing network car-booking orders sent by the network car-booking cloud platforms, generating vehicle control instructions, encrypting the vehicle control instructions and issuing the vehicle control instructions to at least one unmanned vehicle, and providing computing, network and storage capabilities based on hardware resources and software resources.

In the embodiment of the invention, the scheduling cloud platform can be in communication connection with a plurality of network car booking platforms, and when a network car booking order sent by any one of the network car booking platforms is received, the network car booking order is analyzed to extract the vehicle identification and the planned route point, so that a data basis is provided for the subsequent generation of the vehicle control instruction.

102, performing reachability verification on the planned route points;

the reachability verification in the embodiment of the invention refers to a process that the scheduling cloud platform verifies whether the unmanned vehicle can reasonably and safely complete the reachability of the network car booking order by combining data such as a target point, a starting point, a vehicle identifier of the scheduling vehicle and the like in the network car booking order with a semantic map before the unmanned vehicle is scheduled. It should be noted that the reachability verification may also include processes such as congestion route avoidance during subsequent traveling of the unmanned vehicle.

After the planned route points and the vehicle identifications are extracted from the network appointment orders, the accessibility verification can be carried out on the planned route points on the basis of the semantic map prestored on the scheduling cloud platform, so that the feasibility of the target points, the starting points and the planned paths in the planned route points can be verified to different degrees.

103, performing position conversion on the planned route points according to the verification result to generate a vehicle control instruction;

because the coordinates used by the semantic map are not in the same coordinate system as the target unmanned vehicle, in order to realize subsequent control of the target unmanned vehicle, after the accessibility verification, if the verification results are all verified, the position conversion can be carried out on the extracted planned route points based on the verification results, the coordinate system where the semantic map is located is converted into the coordinate system where the target unmanned vehicle is located, and the vehicle control command is generated by adopting the converted data such as the starting point, the current position of the target unmanned vehicle, the target point, the planned path and the like.

Step 104, encrypting the vehicle control command, and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identification; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order.

In the specific implementation, in order to ensure the communication security between the dispatching cloud platform and the target unmanned vehicle, a preset encryption algorithm may be adopted to encrypt the vehicle control command, and the vehicle identification is issued to the target unmanned vehicle corresponding to the vehicle identification as a target, so that after the target unmanned vehicle can decrypt the vehicle control command, the movement control of the target unmanned vehicle is realized through the vehicle control command, the target unmanned vehicle receives a passenger from a current position to an initial position, and the passenger is sent to a network car booking flow of a target point along a planned path at the current time.

In the embodiment of the invention, the dispatching cloud platform is in communication connection with a plurality of network car booking platforms, when a network car booking order sent by any one of the network car booking platforms is received, the vehicle identification and the planned route point are extracted from the network car booking platforms, accessibility verification is carried out on the planned route point according to a pre-marked semantic map so as to judge whether the unmanned vehicle can reasonably and legally arrive, if the unmanned vehicle can reasonably and legally arrive, position conversion can be carried out on the planned route point, a vehicle control instruction under a coordinate system where the unmanned vehicle is located is generated, the vehicle control instruction is encrypted and then issued to the target unmanned vehicle according to the vehicle identification, so that the target unmanned vehicle can verify and execute the vehicle control instruction to receive and send passengers, and the network car booking order is completed. The method and the system solve the technical problems that the existing network car booking scheduling method is high in required computing resources or high in scheduling cost caused by long initial research and development period, the unmanned vehicle is controlled by generating the vehicle control command in a mode that the scheduling cloud platform is in butt joint with the network car booking platforms and analyzing the sent network car booking orders, the network car booking orders do not need to be analyzed on the unmanned vehicle, the unmanned vehicle can be rapidly accessed to the network car booking platforms, and the operation cost is greatly reduced.

Referring to fig. 2, fig. 2 is a flowchart illustrating a method for scheduling an unmanned vehicle according to a second embodiment of the present invention. The second embodiment of the invention performs further feature refinement and content supplement on the basis of the first embodiment, and further performs reachability verification on the planned route point and practical application description on position conversion of the planned route point.

step 201, when an online car booking order sent by any online car booking platform is received, extracting a vehicle identifier and a planning route point;

Alternatively, the planned route points include a start point, a destination point and/or a route point, and referring to fig. 3, step 201 may include the following sub-steps S11-S14:

s11, when a network car booking order sent by any one network car booking platform is received, extracting a vehicle identification, a starting point and a destination point from the network car booking order;

after the user finishes the order placing operation of vehicle scheduling on the network car booking platform, the network car booking platform generates a network car booking order according to the starting point and the destination point selected by the user and the vehicle identification to be called. And after the dispatching cloud platform receives the online car booking order, the online car booking order can be analyzed, and based on corresponding keywords such as a destination, a user position, a vehicle type and the like, vehicle identification, a starting point and a destination point are extracted from the online car booking order.

It should be noted that the starting point may be a current location of the user or a location selected by the user, and the destination point may be a specific address or a map fix.

S12, if the network appointment order has the route point, extracting the route point;

s13, if no passing point exists in the network car booking order, inquiring a preset semantic map, and determining a planned path from a starting point to a destination point;

in one example of the invention, if it is determined that no passing point exists in the network appointment order, in order to guarantee riding experience of a user and effectively avoid congested road sections, the scheduling cloud platform can query a semantic map, determine the current position of a target driving vehicle through a vehicle identifier, and determine a planned path from the current position to the starting point and then to the destination point by adopting a path planning algorithm by combining map coordinates of the starting point and the destination point in the semantic map.

It should be noted that the path planning algorithm may be a graph search method, an RRT algorithm, an artificial potential field method, a BUG algorithm, or the like, and the specific type of the algorithm is not limited in the embodiment of the present invention.

And S14, extracting the passing point to update the planned path according to the real-time road condition information corresponding to the planned path.

The passing point in the embodiment of the present invention refers to a point position corresponding to each marker passing through from a starting point to a destination point or a point position marked according to a preset interval, where the markers may include, but are not limited to, intersections, traffic lights, zebra crossings, and the like, and the embodiment of the present invention does not limit the type of the specific markers.

In the embodiment of the invention, due to the difference of the network car booking platforms, part of the network car booking platforms can generate the route points which need to be passed through in the network car booking orders at the same time of generating the network car booking orders. The scheduling cloud platform searches the network car booking order, and if the passing point exists in the network car booking order, the passing point can be directly extracted for subsequent use.

For the online taxi appointment orders without the passing points, the scheduling cloud platform can adopt the extracted starting points and the extracted destination points and perform path retrieval by combining the semantic map so as to obtain the required passing points.

Further, referring to fig. 4, step S14 may include the following sub-steps S141-S143:

s141, judging whether a planned path has a congested road section according to real-time road condition information corresponding to the planned path;

the real-time road condition information in the embodiment of the invention can be obtained from third-party road condition software and is used for reflecting the congestion condition of the planned path in real time.

After determining a planned path from the current position to a destination point of the target unmanned vehicle, the scheduling cloud platform can judge the congested road section of the planned path by acquiring real-time road condition information.

In the concrete implementation, the congestion condition of the third-party road condition software on the path is generally identified to be smooth by adopting green marks, the third-party road condition software runs slowly by adopting yellow marks, and the congestion degree is identified by red with different degrees. In an example of the present invention, after the real-time traffic information is acquired, the scheduling cloud platform may determine whether a congested road segment exists according to a color of an identifier of the real-time traffic information corresponding to a planned path by retrieving the real-time traffic information, and determine that the congested road segment exists if the identifier is red, and determine that the congested road segment does not exist if the identifier is red.

S142, if no congested road section exists, or if a congested road section exists and the planned path does not have a steerable intersection, judging that no passing point is extracted;

in the embodiment of the invention, if the congested road section is judged to be absent, the target unmanned vehicle can smoothly pick up the passenger at the moment, and the passing point does not need to be extracted to detour the congested road section.

In addition, if it is determined that a congested road segment exists, but the planned path does not have a steerable intersection before the congested road segment, it may be determined that the planned path at the current time is the only path to the destination point, and at this time, since the congested road segment cannot be bypassed, it is determined that no passing point is extracted in order to reduce consumption of computing resources.

S143, if a congested road section exists and the planned path has a steerable road section, updating the planned path by using the steerable road section as a passing point, and skipping to execute the step of judging whether the planned path has the congested road section according to real-time road condition information corresponding to the planned path until the skipping times are equal to a preset skipping threshold value;

in the embodiment of the invention, if the congested road sections exist, the semantic map can be further searched based on the congested road sections, and the road sections with fewer congested road sections are searched on the basis of the planned path, so that the planned path is updated, and whether the congested road sections exist in the updated planned path is judged again according to the real-time road condition information corresponding to the updated planned path.

Optionally, the congestion road segment includes at least one congestion sub-segment, the steerable intersection includes a first steerable intersection and a second steerable intersection, and the step S143 may include the following sub-steps:

sequentially searching whether a first steerable intersection exists behind each congested sub-road section in a semantic map according to a target reverse direction;

if the first steerable road junction exists, sequentially searching whether a second steerable road junction exists in front of each congestion sub-road section in a semantic map according to the forward direction of the destination;

inserting the first steerable intersection and the second steerable intersection into a planned path as passing points to generate a new planned path;

and the step of judging whether the planned path has a congested road section or not according to the real-time road condition information corresponding to the planned path until the jumping times are equal to a preset jumping threshold value is executed.

The target reverse direction in the embodiment of the present invention refers to a direction of a flow of traffic in a process in which the target unmanned vehicle is driven toward the target point; the target forward direction refers to the forward direction of the vehicle in the process that the target unmanned vehicle drives to the target point.

It should be noted that the first steerable intersection in the embodiment of the present invention is located before the second steerable intersection, and the first steerable intersection and the second steerable intersection are opposite in direction.

In an example of the present invention, the congested road segment may include at least one congested sub-road segment, and if the scheduling cloud platform determines that the current planned road segment has the at least one congested sub-road segment, each congested sub-road segment may be sequentially searched in a semantic map according to a target reverse direction, and whether a first steerable intersection exists after each congested sub-road segment is determined, so as to determine whether the target unmanned vehicle can turn right at the first steerable intersection before encountering the congested sub-road segment. If a first steerable intersection exists behind any congested sub-road section, whether a second steerable intersection exists in front of each congested sub-road section is further sequentially searched in a semantic map according to the forward direction of the target, and if yes, the first steerable intersection and the second steerable intersection can be sequentially inserted into a planned path as passing points so as to generate a new planned path through a path planning algorithm. And judging whether the current planned path has a congested road section or not according to the real-time road condition information corresponding to the new planned path.

For example, after a planned path R1 from the current position to the destination point of the target unmanned vehicle is obtained, the real-time traffic information of R1 may be combined by querying the semantic map semap, and if the R1 has no congested road section, the route point is directly extracted; if the congested road segment exists on the R1, determining a position set S1 where the congested road segment exists on the R1, where S1 may include multiple congested sub-segments D1, D2, and D3. Searching whether a first steerable intersection C1 exists before D1 by the R1 in the opposite direction of purpose, further searching whether the first steerable intersection C1 exists before D2 and before D3 if the first steerable intersection C1 does not exist, and ending the current process if the first steerable intersection C1 does not exist, and extracting a path point from R1; if the C1 exists, R1 is further searched along the forward direction of the purposes of D3, D2 and D1, and if the second steerable intersection C2 is searched, C1 and C2 can be sequentially inserted into R1, the planned path R2 is regenerated, and the steps are repeated until the number of times is equal to the preset jump threshold value.

In order to save resource consumption, the jump threshold may be set to 3 times, 4 times, and the like, and the specific times are not limited in the embodiment of the present invention.

Optionally, in order to further reduce resource consumption and cost, markers such as each intersection, a traffic light, a zebra crossing and the like can be used as route points for extraction, and on the basis of ensuring smooth receiving and delivering processes, the number of the route points extracted by the scheduling cloud platform is reduced, so that control instructions required to be executed by the subsequent target unmanned vehicle are reduced, and the operation cost is reduced.

Step 202, performing feasible license plate area verification on a target point and a starting point based on a plurality of longitude and latitude points extracted from a preset network map, and judging whether the target point and the starting point are in the feasible license plate area;

the feasible region in the embodiment of the invention refers to a feasible license plate region and a passable region, wherein the feasible license plate region refers to a region where a license plate of an unmanned vehicle can normally run, and the passable region refers to a region which is not limited by a limiting condition of height limitation and width limitation in the actual running process of the unmanned vehicle with different vehicle types due to different structural designs, namely a region where the vehicle can normally pass.

In the embodiment of the invention, because the operation range of the unmanned vehicle is possibly limited, different license plates are required for vehicle operation in different areas, the types of the unmanned vehicle are different, and the model of the unmanned vehicle is different, after the target point and the starting point are obtained, the dispatching cloud platform can search the semantic map, determine the positions of the target point and the starting point, and determine that the vehicle can normally pass and run by combining the positions with the semantic map, thereby verifying whether the target point and the starting point are in a feasible area, and ensuring the performability of the network appointment vehicle order.

Alternatively, referring to FIG. 5, step 202 may include the following sub-steps S21-S24:

s21, retrieving a preset network map, extracting a plurality of longitude and latitude points corresponding to the feasible license plate area, and constructing a polygon marking frame along each longitude and latitude point;

s22, if the number of first intersection points of the first ray constructed by taking the destination point as the starting point and the polygon marking frame is an odd number, the verification is passed, and the destination point is judged to be in the feasible license plate area;

s23, if the number of second intersection points of the second rays constructed by taking the starting point as the starting point and the polygon marking frame is an odd number, the verification is passed, and the starting point is judged to be in the feasible license plate area;

and S24, if the number of the first intersection points or the number of the second intersection points is even, the verification is not passed.

In one example of the invention, the semantic map can be retrieved through the scheduling cloud platform, and whether the positions of the destination point and the starting point are located in a feasible license plate area is determined, so that whether the unmanned vehicle can provide the delivery service is verified.

In this embodiment, the scheduling cloud platform may determine the feasible license plate region of the target unmanned vehicle based on information such as vehicle identification by retrieving various network maps, for example, an open source map carrying longitude and latitude points such as a Baidu map and a Gaudi map. Extracting a plurality of longitude and latitude points from the planned outermost circle region of the feasible license plate region, connecting the longitude and latitude points along each longitude and latitude point of the feasible license plate region, and labeling the feasible license plate region in a polygon labeling frame mode; if the number of the first intersection points of the first ray taking the destination point as the starting point and the polygon marking frame is an odd number, the destination point is positioned in the polygon marking frame at the moment, and the target point is judged to be in the feasible license plate area after passing the verification; if the number of the second intersection points of the second ray pair polygon marking frame taking the starting point as the starting point is odd, the starting point is also in the feasible license plate area.

If the first or second number of intersections is an even number, the verification is determined not to be passed. For example, if the number of the first intersection points is even, no matter how the number of the second intersection points is, the target point is not in a feasible license plate area, and the target unmanned vehicle cannot complete the network taxi appointment order; if the second intersection point number is an even number, it is also determined that the target unmanned vehicle cannot complete the network reservation order regardless of the first intersection point number.

Step 203, retrieving a preset semantic map, performing feasible region verification on the destination point and the starting point, and judging whether the destination point and the starting point are in feasible regions;

the semantic map in the embodiment of the invention refers to a geographic information database which is prestored on a scheduling cloud platform and is marked and checked based on position coordinates, actual environment identifications and other data acquired by each unmanned vehicle in the historical operation process, wherein the geographic information database is marked with areas, routes and the like which can be driven by the unmanned vehicle corresponding to each vehicle identification in the actual operation process, and the semantic map can also include marking information such as whether the actual environment is a lane line, a road, whether turning can be performed and the like.

In the embodiment of the application, after the destination point and the starting point are determined to be in the feasible license plate area, it is indicated that the unmanned vehicle can run in the feasible license plate area at the moment, but a limited area may exist between the destination point and the starting point due to road planning, and at the moment, the destination point and the starting point can be further verified in the feasible area through searching of the preset semantic map, so as to determine whether a running route between the destination point and the starting point meets the requirement of the feasible area.

In one example of the present application, step 203 may include the following sub-steps S31-S35:

s31, retrieving the semantic map, and verifying whether the destination point and the starting point are in the semantic map;

s32, if yes, acquiring the destination position coordinate of the destination point in the semantic map and the initial position coordinate of the initial point in the semantic map;

the feasible region in the embodiment of the present application refers to a region where the unmanned vehicle can travel normally, not restricted, from the current position of the unmanned vehicle to the starting point and from the starting point to the destination point, and the passable region refers to a region where the unmanned vehicle can travel safely with the current vehicle specifications.

In the embodiment of the application, the semantic map can be obtained by continuously optimizing and labeling the unmanned vehicle for multiple times, and is used for identifying the drivable road of the unmanned vehicle. In order to determine whether the unmanned vehicle can drive between a starting point and a destination point, whether the destination point and the starting point are in an area or a line marked by a semantic map can be determined from the semantic map by retrieving the semantic map, if the destination point and the starting point are retrieved from the semantic map, the fact that the two points are both in the semantic map is indicated, and at the moment, in order to enable the unmanned vehicle to accurately and safely deliver passengers, the corresponding destination position coordinate and the corresponding starting position coordinate can be obtained, so that a data basis for verifying whether the unmanned vehicle can normally pass through a road is provided.

S33, if the destination position coordinate is in a road area in the semantic map, or the first distance between the intersection point of the target position coordinate and the perpendicular line of the road area is smaller than or equal to a preset distance threshold value, the verification is passed, and the destination point is judged to be in a feasible area;

s34, if the initial position coordinate is in the road area, or the second distance between the initial position coordinate and the intersection point of the perpendicular lines of the road area is smaller than or equal to the distance threshold value, the verification is passed, and the initial point is judged to be in the feasible area;

and S35, if the destination position coordinate or the starting position coordinate is not in the road area in the semantic map, and the first distance or the second distance is greater than the distance threshold, the verification is not passed.

It should be noted that the road area refers to a feasible road for a motor vehicle in the semantic map, and the vertical intersection refers to a closest intersection of a vertical line from the destination position coordinate or the start position coordinate and any boundary of the road area.

In this embodiment, in order to further screen a passable network appointment order of the unmanned vehicle, after obtaining a destination position coordinate of a destination point in a semantic map and an initial position coordinate corresponding to an initial point, further comparing whether the destination position coordinate is in a road area in the semantic map, or whether a first distance between the destination position coordinate and a perpendicular intersection of the road area is less than or equal to a preset distance threshold, which indicates that the destination position coordinate is in an area reachable by the target unmanned vehicle, and at this time, it may be determined that the verification is passed; similarly, the verification is passed if the start position coordinate is in the road area, or a second distance between the start position coordinate and a perpendicular intersection of the road area is less than or equal to a distance threshold.

If the destination position coordinate or the starting position coordinate is not in the road area in the semantic map, the starting point or the destination point is in a position where a certain motor lane cannot reach, at this time, whether the first distance or the second distance is larger than a distance threshold value or not can be further compared, if any one of the first distance or the second distance is larger than the distance threshold value, the target unmanned vehicle is indicated to be one position point where the target unmanned vehicle cannot reach, and the current network appointment order cannot be completed.

It is worth mentioning that when the destination point and the starting point are judged to be in the passing area, the network appointment order belongs to orders which can be executed by the target unmanned vehicle, and at this time, a vehicle control command can be further generated to call the subsequent target unmanned vehicle.

Step 204, if the destination point and the starting point are both in the feasible license plate area and the feasible area, judging that the verification is passed, otherwise, judging that the verification is not passed;

in one example of the present application, after the destination point and the starting point are subjected to the above-mentioned viable license plate region verification and viable region verification, two verification results, i.e., verification pass or verification fail, may occur. When the verification is passed, the destination point and the starting point at the moment are both in a feasible license plate area and a feasible area, the unmanned vehicle can complete the current network car booking order, and the planned route point can be further subjected to position conversion to generate a vehicle control instruction.

If any one of the destination point or the starting point is not in the feasible license plate area or the feasible area, the fact that the network car booking order issued by the network car booking platform cannot be completed is indicated, the verification can be judged to be failed at the moment, and the vehicle replacement pass is sent to the network car booking platform through the dispatching cloud platform to replace the unmanned vehicle.

Step 205, performing position conversion on the planned route points according to the verification result to generate a vehicle control instruction;

optionally, step 205 may comprise the following sub-steps:

respectively setting the overtime time of a first vehicle control instruction and the overtime time of a second vehicle control instruction, and writing the overtime time into a preset instruction cache region;

the first vehicle control instruction is used for controlling the target unmanned vehicle to move from the current position coordinate to the position coordinate of the starting point; the second vehicle control command is used for controlling the position coordinates of the target unmanned vehicle to move from the starting point to the destination point along the planned path at the current moment

In an example of the present invention, after determining that the destination point and the start point are all in the feasible region, since the current destination point, the current start point and the current passing point are coordinates belonging to a coordinate system in which the semantic map is located, in order to enable the target unmanned vehicle to recognize coordinates of the point, the destination point and the start point may be converted into position coordinates of the coordinate system in which the target unmanned vehicle is located, respectively. On the basis, the planning path is constructed by adopting the starting point and the destination point in the steps, and the planning path with the path point can be updated in real time. Therefore, after the latest planned path is acquired, the position coordinates of the target point and the position coordinates of the start point may be connected along the planned path at the current time, so as to generate a second vehicle control instruction for controlling the target unmanned vehicle to move from the start point to the target point, and for the first vehicle control instruction, the second vehicle control instruction may be generated by the scheduling cloud platform based on the current position coordinates of the target unmanned vehicle and the position coordinates of the start point, so that the target unmanned vehicle can move from the current position coordinates to the start point coordinates.

In the embodiment of the invention, the scheduling cloud platform is also provided with the instruction cache region, and as the same scheduling cloud platform not only corresponds to the control of the unique unmanned vehicle, the vehicle control instruction can be cached through the instruction cache region and is distinguished and issued by the vehicle identification.

Meanwhile, in order to avoid the overtime of the instruction execution of the unmanned vehicle, overtime time can be set for the first vehicle control instruction and the second vehicle control instruction respectively, and then the overtime time is written into the instruction cache region.

Optionally, the present invention further comprises the steps of:

and if any verification fails or a planned path from the current position of the target unmanned vehicle to the destination point cannot be constructed, sending a vehicle replacement notice to the network car booking platform.

In another example of the present invention, if the feasible region verification or other verification process for the destination point or the start point determines that the verification fails or the planned path from the current position of the target unmanned vehicle to the destination point cannot be constructed, which indicates that the target unmanned vehicle corresponding to the vehicle identifier is not suitable for the network car-booking order, the scheduling cloud platform sends a vehicle change notification to the network car-booking platform to notify the user of order data changes such as the vehicle identifier, the destination point, the start point, and the like.

Step 206, encrypting the vehicle control command, and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identifier; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order.

In this embodiment, after the dispatching cloud platform generates the vehicle control command, to ensure communication security and avoid vehicle control errors caused by unexpected situations, an encryption algorithm associated with the target unmanned vehicle, such as an algorithm of the national secret SM2, an algorithm of the SM4, and the like, may be used to encrypt the vehicle control command, and then the encrypted vehicle control command is issued to the corresponding target unmanned vehicle according to the vehicle identifier.

After the target unmanned vehicle receives the vehicle control command, the target unmanned vehicle can be decrypted to obtain a first vehicle control command and a second vehicle control command, the target unmanned vehicle is controlled to move from the current position to the starting point to receive a passenger through the analysis command, and after the passenger gets on the vehicle, the target unmanned vehicle is moved from the starting point to the destination point in response to the second vehicle control command to complete a network car booking order, so that the network car booking application flexibility of the unmanned vehicle is further increased, and the problem that the current unmanned vehicle operation can only fix the getting on/off point is solved.

Further, the target unmanned vehicle comprises a vehicle client and an unmanned system, and the target unmanned vehicle is specifically configured to:

receiving and decrypting vehicle control instructions through vehicle client

Acquiring a current vehicle identifier corresponding to the unmanned system through a vehicle client; the vehicle control command carries a command timestamp and a vehicle identifier;

verifying whether the vehicle identification is the same as the current vehicle identification through the vehicle client;

if the vehicle identification is the same as the current vehicle identification and the instruction timestamp is less than the overtime, issuing a vehicle control instruction to the unmanned system through the vehicle client;

and executing the vehicle control command through the unmanned system to complete the network car booking order.

In one example of the present invention, a vehicle control instruction execution process for a target unmanned vehicle is further set forth, wherein the target unmanned vehicle comprises a vehicle client and an unmanned system.

The vehicle client in the embodiment of the invention refers to a terminal, such as a vehicle-mounted computer and the like, which is arranged in a target unmanned vehicle and used for establishing communication with the scheduling cloud platform and receiving and decrypting a vehicle control command of the scheduling cloud platform by using a predetermined decryption algorithm. The unmanned system is a central control system which can respond to a vehicle control command issued by a vehicle client and control a power driving system, a steering system, a braking system and the like of a target unmanned vehicle.

In the embodiment of the invention, after a vehicle control command issued by a scheduling cloud platform is received by a vehicle client, a current vehicle identifier corresponding to an unmanned system is obtained, whether the vehicle identifier carried by the vehicle control command is the same as the current vehicle identifier is compared, and whether the time recorded by a command timestamp carried by the vehicle control command exceeds the overtime time is compared, so that the vehicle command is verified.

If the time recorded by the instruction timestamp does not exceed the timeout time and the vehicle identifier is the same as the current vehicle identifier, the position coordinates of the passing point, the starting point and the destination point corresponding to the vehicle control instruction can be issued to the unmanned system, the unmanned system moves from the current position to the starting point to receive the passenger, and after the passenger gets on the vehicle, the passenger moves to the destination point along the planned path at the current moment to complete the network appointment order.

Optionally, after the vehicle client establishes communication connection with the scheduling cloud platform, the vehicle identifier may be used to periodically retrieve whether the instruction cache region has the vehicle control instruction cached therein, and if so, the vehicle control instruction may be directly obtained.

Referring to fig. 6, fig. 6 is a block diagram of a scheduling apparatus of an unmanned vehicle according to a third embodiment of the present invention.

The embodiment of the invention provides a scheduling device of an unmanned vehicle, which is applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the device comprises:

the data extraction module 601 is used for extracting a vehicle identifier and a planned route point when a vehicle booking order sent by any one vehicle booking platform is received;

a vehicle reachability verification module 602, configured to perform reachability verification on the planned route point;

the vehicle control instruction generating module 603 is configured to perform position conversion on the planned route point according to the verification result, and generate a vehicle control instruction;

the command encryption and issuing module 603 is used for encrypting the vehicle control command and issuing the vehicle control command to the target unmanned vehicle according to the vehicle identifier; and the target unmanned vehicle is used for verifying and executing the vehicle control command to complete the network car booking order.

Optionally, the planned route point includes a start point, a destination point and/or a route point, and the data extraction module 601 includes:

the identification and route point extraction submodule is used for extracting a vehicle identification, a starting point and a destination point from the network car booking order when the network car booking order sent by any one network car booking platform is received;

the route point extraction submodule is used for extracting a route point if the route point exists in the network appointment order;

the planning path construction sub-module is used for inquiring a preset semantic map and determining a planning path from a starting point to a destination point if no passing point exists in the network taxi appointment order;

and the passing point extracting and updating submodule is used for extracting a passing point to update the planned path according to the real-time road condition information corresponding to the planned path.

Optionally, the route point extracting and updating sub-module includes:

the congestion road section judging unit is used for judging whether a congestion road section exists in the planned path according to the real-time road condition information corresponding to the planned path;

the first extraction judging unit is used for judging that no passing point is extracted if no congested road section exists or a congested road section exists and no steerable intersection exists in the planned path;

and the second extraction and judgment unit is used for updating the planned path by adopting the steerable road junction as a passing point if the congested road section exists and the planned path has the steerable road junction, and skipping to execute the step of judging whether the congested road section exists in the planned path according to the real-time road condition information corresponding to the planned path until the skipping times are equal to a preset skipping threshold value.

Optionally, the congested road segment includes at least one congested sub-road segment, the steerable intersection includes a first steerable intersection and a second steerable intersection, and the second extraction determination unit is specifically configured to:

Optionally, the reachability validation includes a viable license plate region validation and a viable region validation; the vehicle reachability verification module 602 includes:

a feasible license plate region verification submodule for performing feasible license plate region verification on the destination point and the starting point based on the plurality of longitude and latitude points extracted from the preset network map and judging whether the destination point and the starting point are in the feasible license plate region

The feasible region verification submodule is used for retrieving a preset semantic map, performing feasible region verification on the target point and the starting point and judging whether the target point and the starting point are in a feasible region;

and the verification result generation submodule is used for judging that the verification is passed if the destination point and the starting point are both in the feasible license plate area and the feasible area, and otherwise, judging that the verification is not passed.

Optionally, the viable license plate region validation sub-module includes:

the marking frame construction unit is used for retrieving a preset network map, extracting a plurality of longitude and latitude points corresponding to the feasible license plate area, and constructing a polygon marking frame along each longitude and latitude point;

the first judging unit is used for judging that the target point is in the feasible license plate area if the number of first intersection points of the first ray constructed by taking the target point as the starting point and the polygon marking frame is an odd number;

the second judging unit is used for judging that the starting point is in the feasible license plate area if the number of second intersection points of the second ray constructed by taking the starting point as the starting point and the polygon marking frame is an odd number;

and the third judging unit is used for failing to verify if the first intersection point number or the second intersection point number is an even number.

Optionally, the feasible region comprises a passable region and a travelable region; the feasible region verification submodule comprises:

the semantic map retrieval unit is used for retrieving a semantic map and verifying whether a destination point and a starting point are in the semantic map;

the passable area verification unit is used for passing verification and judging that the destination point is in a feasible area if the destination position coordinate is in a road area in the semantic map or a first distance between the destination position coordinate and a vertical line intersection point of the road area is smaller than or equal to a preset distance threshold value if the destination position coordinate is in the road area in the semantic map or the first distance between the destination position coordinate and the vertical line intersection point of the road area is smaller than or equal to the preset distance threshold value;

a fourth determination unit, configured to, if the initial position coordinate is in the road area, or a second distance between the initial position coordinate and a perpendicular intersection of the road area is less than or equal to the distance threshold, pass the verification, and determine that the initial point is in the feasible area;

and the fifth judging unit is used for judging that the verification is not passed if the destination position coordinate or the starting position coordinate is not in the road area in the semantic map and the first distance or the second distance is greater than the distance threshold.

Optionally, the vehicle control instruction generating module 603 includes:

the vehicle control instruction generation sub-module is used for converting the destination point and the starting point into position coordinates of a coordinate system where the target unmanned vehicle is located respectively and generating a first vehicle control instruction and a second vehicle control instruction if the destination point and the starting point are both located in a feasible area;

the timeout setting and caching submodule is used for respectively setting the timeout time of the first vehicle control instruction and the timeout time of the second vehicle control instruction and writing the timeout time into a preset instruction caching area;

the first vehicle control instruction is used for controlling the target unmanned vehicle to move from the current position coordinate to the position coordinate of the starting point; the second vehicle control command is used for controlling the target unmanned vehicle to move from the position coordinate of the starting point to the position coordinate of the destination point along the position coordinate of the planned path at the current moment.

Optionally, the apparatus further comprises:

and the vehicle replacement judging module is used for sending a vehicle replacement notice to the network car-reserving platform if any verification fails or a planned path from the current position of the target unmanned vehicle to the destination point cannot be constructed.

Optionally, the target unmanned vehicle comprises a vehicle client and an unmanned system, and the target unmanned vehicle is specifically configured to: receiving and decrypting vehicle control instructions through vehicle client

An embodiment of the present invention further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to execute the method for scheduling an unmanned vehicle according to any embodiment of the present invention.

Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed to implement the scheduling method of the unmanned vehicle according to any of the embodiments of the present invention.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, modules and sub-modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. 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.

The 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 invention 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 unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. The method for scheduling the unmanned vehicle is applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the method comprises the following steps:

performing reachability verification on the planned route points;

performing position conversion on the planned route points according to the verification result to generate a vehicle control instruction;

2. The method according to claim 1, wherein the planned route points comprise a starting point, a destination point and/or a passing point, and the step of extracting the vehicle identifier and the planned route point when receiving a network car booking order sent by any one of the network car booking platforms comprises:

when a network car booking order sent by any one network car booking platform is received, extracting a vehicle identification, a starting point and a destination point from the network car booking order;

3. The method according to claim 2, wherein the step of extracting the route point to update the planned path according to the real-time traffic information corresponding to the planned path comprises:

4. The method according to claim 3, wherein the congested road segment includes at least one congested sub-road segment, the steerable intersection includes a first steerable intersection and a second steerable intersection, if the congested road segment exists and the planned path has the steerable intersection, the steerable intersection is used as a passing point to update the planned path, and the step of performing the jump to determine whether the planned path has the congested road segment according to the real-time road condition information corresponding to the planned path until the number of jumps is equal to a preset jump threshold value includes:

5. The method of claim 2, wherein the reachability validation comprises a viable license plate area validation and a viable area validation; the step of performing reachability verification on the planned route point includes:

6. The method of claim 5, wherein the step of performing feasible license plate area verification on the destination point and the starting point based on a plurality of longitude and latitude points extracted from a preset network map and determining whether the destination point and the starting point are in a feasible license plate area comprises:

7. The method according to claim 5, wherein the step of retrieving a preset semantic map, performing feasible region verification on the destination point and the starting point, and determining whether the destination point and the starting point are in feasible regions comprises:

8. The method according to claim 5, 6 or 7, wherein the step of performing position conversion on the planned route point according to the verification result to generate the vehicle control command comprises:

wherein the first vehicle control instruction is used for controlling the target unmanned vehicle to move from the current position coordinate to the position coordinate of the starting point; the second vehicle control instruction is used for controlling the target unmanned vehicle to move from the position coordinate of the starting point to the position coordinate of the destination point along the planned path at the current moment.

9. The method of any one of claims 3-7, further comprising:

10. The method according to claim 1, wherein the target unmanned vehicle comprises a vehicle client and an unmanned system, the target unmanned vehicle being specifically configured to:

receiving and decrypting the vehicle control command through the vehicle client

11. The scheduling device of the unmanned vehicle is applied to a scheduling cloud platform, wherein the scheduling cloud platform is in communication connection with a plurality of network appointment platforms, and the scheduling device comprises:

the vehicle reachability verification module is used for performing reachability verification on the planned route points;

the vehicle control instruction generating module is used for carrying out position conversion on the planned route points according to the verification result to generate vehicle control instructions;

12. An electronic device, comprising a memory and a processor, wherein the memory has stored thereon a computer program that, when executed by the processor, causes the processor to perform the method of scheduling an unmanned vehicle according to any of claims 1-10.

13. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed, implements the method of scheduling an unmanned vehicle of any of claims 1-10.