Path planning method and system and vehicle-mounted equipment

Abstract

The invention provides a path planning method and system and vehicle-mounted equipment, and the method comprises the steps: obtaining a real-time position, a final position and a driving path of a vehicle, and first road condition information in front of the real-time position monitored during the planning of the driving path; monitoring second road condition information in front of the real-time position on the driving path; if the first road condition information is superior to the second road condition information, a candidate path is searched, third road condition information of the candidate path is monitored, and the first road condition information, the second road condition information and the third road condition information all comprise traffic information, road information and path risk information; and according to the advantages and disadvantages of the third road condition information and the second road condition information, determining a target path from the real-time position to the final position from the remaining paths of the candidate path and the driving path. According to the method, traffic information, road information and path risk information are comprehensively considered, local path optimization is carried out by self-adaption to real-time changing road conditions in complex traffic data, the reliability of path planning is ensured, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of navigation, and in particular, to a path planning method, system, and vehicle-mounted device. Background Art

[0002] With the remarkable acceleration of the urbanization process, the traffic network has not only expanded rapidly in scale but also become increasingly complex, resulting in an extremely complex path planning problem, which poses higher requirements for the data processing ability, path calculation intelligence, and accuracy of the navigation system. When facing a complex traffic network and large-scale data, ensuring the timeliness and accuracy of path planning is the key to improving the user experience.

[0003] In the related art, the navigation system mainly relies on classical computing technologies for path planning to determine the optimal path between two points. For simple road conditions, it can meet the requirements of path planning timeliness and accuracy to a certain extent. However, when facing complex traffic data, there are still certain limitations in path optimization, resulting in a low reliability of the path planning result and affecting the user experience. Summary of the Invention

[0004] In view of the above disadvantages, the present application discloses a path planning method, system, and vehicle-mounted device for solving the technical problem of low reliability of path planning results.

[0005] In a first aspect, the present application provides a path planning method, which includes: obtaining the driving information of the vehicle, where the driving information includes the real-time position, the end position, and the driving path, and obtaining the first road condition information in front of the real-time position when planning the driving path; monitoring the second road condition information in front of the real-time position on the driving path; if the second road condition information is worse than the first road condition information, searching for candidate paths from the real-time position to the end position and monitoring the third road condition information of the candidate paths, where the first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information; and determining the target path from the real-time position to the end position from the candidate paths and the remaining paths of the driving path according to the superiority and inferiority of the third road condition information and the second road condition information.

[0006] In an embodiment of the present application, after monitoring the second road condition information in front of the real-time position on the driving path, it further includes: if at least one of the traffic information, road information, and path risk information in the first road condition information is superior to the traffic information, road information, and path risk information in the second road condition information, it is determined that the first road condition information is superior to the second road condition information; if the traffic information, road information, and path risk information in the second road condition information are all superior to the traffic information, road information, and path risk information in the first road condition information, it is determined that the second road condition information is superior to the first road condition information.

[0007] In an embodiment of the present application, the method for determining the target path includes: evaluating a first score of the remaining path according to the traffic information, road information, and path risk information in the second road condition information, and evaluating a second score of the candidate path according to the traffic information, road information, and path risk information in the third road condition information, where the candidate path is at least one; determining the path corresponding to the larger value of the scores as the target path according to the first score and each of the second scores.

[0008] In an embodiment of the present application, the method for determining the target path further includes: if the first score and each of the second scores are equal, evaluating the immediate rewards of each candidate path and the remaining path according to a preset path selection criterion, where the indicators in the path selection criterion include path time consumption, path fuel consumption, road type, and facilities along the path; calculating the path values of each candidate path and the remaining path according to a preset path value function and the immediate rewards; determining the path corresponding to the larger value of the path values as the target path according to each of the path values.

[0009] In an embodiment of the present application, the method for determining the target path further includes: evaluating a third score of the remaining path according to a preset path selection criterion and the traffic information, road information, and path risk information in the second road condition information, and evaluating a fourth score of the candidate path according to the path selection criterion and the traffic information, road information, and path risk information in the third road condition information, where the candidate path is at least one; determining the path corresponding to the larger value of the scores as the target path according to the third score and each of the fourth scores.

[0010] In an embodiment of the present application, the method for planning the driving route includes: constructing a traffic road network, which is composed of multiple nodes, road segments connecting the multiple nodes, and the segment attributes of each road segment. The segment attributes include segment length, traffic time, and fourth road condition information, and the fourth road condition information includes traffic information, road information, and path risk information; constructing a path cost function according to the segment attributes of each road segment, and constructing a Hamiltonian according to the cost function; in the traffic road network, searching for a feasible path from the starting position of the vehicle to the ending position, where the driving information also includes the starting position, and encoding each feasible path into a qubit state to form a quantum superposition state; performing annealing evolution on the quantum superposition state according to the Hamiltonian, and decoding the qubit state evolved to the ground state to obtain the driving route.

[0011] In an embodiment of the present application, the constructing a path cost function according to the segment attributes of each road segment includes: constructing the segment weight of each road segment according to the traffic information, road information, and path risk information in the fourth road condition information; constructing a single-segment cost function according to the segment length, the traffic time, and the segment weight; and superimposing the single-segment cost functions of each road segment to obtain the path cost function.

[0012] In an embodiment of the present application, after determining the target path from the real-time position to the ending position, it further includes: pushing each of the candidate paths and the remaining paths of the driving route for path selection; collecting feedback information on path selection, where the feedback information includes the path selection result, and adjusting the path selection criteria according to the feedback information.

[0013] In a second aspect, the present application provides a path planning system, which includes: an acquisition module for acquiring the driving information of the vehicle, where the driving information includes the real-time position, the ending position, and the driving route, and acquiring the first road condition information in front of the real-time position when planning the driving route; a monitoring module for monitoring the second road condition information in front of the real-time position on the driving route; a search module for searching for candidate paths from the real-time position to the ending position if the second road condition information is worse than the first road condition information, and monitoring the third road condition information of the candidate paths, where the first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information; and a screening module for determining the target path from the real-time position to the ending position from the candidate paths and the remaining paths of the driving route according to the superiority and inferiority of the third road condition information and the second road condition information.

[0014] In a third aspect, the present application provides a vehicle-mounted device, including: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, enable the vehicle-mounted device to implement the path planning method described in the first aspect.

[0015] As described above, a path planning method, system, and vehicle-mounted device provided by the embodiments of the present application have the following beneficial effects:

[0016] First, obtain the driving information of the vehicle, where the driving information includes the real-time position, the end position, and the driving path, and obtain the first road condition information in front of the real-time position monitored during the driving path planning. Then, monitor the second road condition information in front of the real-time position on the driving path. If the first road condition information is better than the second road condition information, search for candidate paths from the real-time position to the end position, and monitor the third road condition information of the candidate paths. Among them, the first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information. Finally, according to the advantages and disadvantages of the third road condition information and the second road condition information, determine the target path from the real-time position to the end position from the candidate paths and the remaining paths of the driving path, comprehensively consider the traffic information, road information, and path risk information of the path, adaptively optimize the local path according to the real-time changing road conditions in complex traffic data, can flexibly respond to road condition changes, realize dynamic and precise optimization of the path, ensure that the path is always optimal, thereby improving the reliability of path planning, ensuring driving efficiency and driving safety, and enhancing the user experience.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:

[0019] Figure 1 is a schematic diagram of the implementation environment of a path planning system shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a flowchart of a path planning method shown in an exemplary embodiment of the present application;

[0021] Figure 3 is a flowchart of planning a driving path shown in an exemplary embodiment of the present application;

[0022] Figure 4 It is a flowchart of an optimized driving route shown in an exemplary embodiment of the present application;

[0023] Figure 5 It is another flowchart of an optimized driving route shown in an exemplary embodiment of the present application;

[0024] Figure 6 It is a flowchart of a specific path planning method shown in an exemplary embodiment of the present application;

[0025] Figure 7 It is a block diagram of a path planning system shown in an exemplary embodiment of the present application;

[0026] Figure 8 It is a schematic structural diagram of an in-vehicle device provided by an embodiment of the present application. Detailed implementation manners

[0027] The following will describe the implementation manners of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application, rather than for limiting the protection scope of the present application.

[0028] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The form, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the layout form of its components may also be more complex.

[0029] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0030] When facing a complex traffic network and large-scale data, ensuring the timeliness and accuracy of path planning is the key to enhancing the user experience. Navigation systems have achieved path planning through various classical computing technologies. However, the inventors of this application have found that these technologies can, to a certain extent, meet the requirements of timeliness and accuracy of path planning for simple road conditions. But when facing complex traffic data, if the road conditions change, such as sudden traffic accidents, temporary road closures, or severe road congestion, they cannot respond to the changes in road conditions in a timely manner, resulting in the planned path not being the optimal one. Therefore, in path planning, there are still certain limitations in the optimization of paths, leading to a low reliability of path planning results and affecting the user experience.

[0031] Accordingly, please refer to Figure 1 , Figure 1 which is a schematic diagram of the implementation environment of a path planning system shown in an exemplary embodiment of this application. As Figure 1 shown, this implementation environment includes a vehicle 110 and a path planning system 120. Among them, the path planning system 120 is embedded in the vehicle 110 and is used to implement the path planning of the vehicle 110. The path planning system 120 includes, but is not limited to, a car machine system, an in-vehicle computer, etc. It comprehensively considers the traffic information, road information, and path risk information of the path, adaptively optimizes the local path according to the real-time changing road conditions in complex traffic data, can flexibly respond to the changes in road conditions, realizes the dynamic and accurate optimization of the path, so as to ensure that the path is always the optimal one, thereby enhancing the reliability of path planning, ensuring the driving efficiency and driving safety, and enhancing the user experience.

[0032] Please refer to Figure 2 , Figure 2 which is a flowchart of a path planning method shown in an exemplary embodiment of this application. This method can be applied to the Figure 1 shown implementation environment and is specifically executed by the path planning system 120 in this implementation environment. It should be understood that this method can also be applicable to other exemplary implementation environments and be specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment applicable to this method.

[0033] As Figure 2 shown, in an exemplary embodiment, the path planning method at least includes steps S210 to S240, which are introduced in detail as follows:

[0034] Step S210, obtain the driving information of the vehicle. The driving information includes the real-time position, the end position, and the driving path, and obtain the first road condition information in front of the real-time position monitored when planning the driving path.

[0035] Step S220, monitor the second road condition information in front of the real-time position on the driving path.

[0036] In step S230, if the first road condition information is better than the second road condition information, search for candidate paths from the real-time position to the end position, and monitor the third road condition information of the candidate paths. The first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information.

[0037] In step S240, determine the target path from the real-time position to the end position from the remaining paths of the candidate paths and the driving path according to the superiority and inferiority of the third road condition information and the second road condition information.

[0038] Among them, the real-time position of the vehicle can be collected in real time based on the in-vehicle sensor GPS (Global Positioning System); the end position and the driving path of the vehicle can be obtained from the navigation system.

[0039] In addition, the first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information. Among them, the traffic information includes traffic flow, traffic light status (the status of the traffic light when the vehicle passes a certain traffic light), traffic congestion status, and average driving speed, etc. The road information includes road type (such as highway, urban expressway, etc.), road surface quality (considering whether the road surface is damaged, whether there is water accumulation, whether it is slippery, etc.), and accident, construction, and control situations, etc. The path risk information includes a path risk coefficient, which is determined according to multiple factors such as whether there are high-incidence accident sections, whether there are special areas (such as schools, hospitals, residential areas) in the path, and weather conditions. The traffic information, road information, and path risk information can be obtained through various methods such as V2X (Vehicle to Everything) communication technology, traffic monitoring platforms, and third-party service platforms.

[0040] In step S220, through various methods such as V2X communication technology, traffic monitoring platforms, and third-party service platforms, realize the real-time monitoring of the road condition information in front of the real-time position on the vehicle driving path, so as to monitor the road condition changes in front of the real-time position on the driving path in real time.

[0041] In step S230, if the first road condition information is better than the second road condition information, that is, the road condition in front of the real-time position on the driving path deteriorates, trigger the path replanning mechanism, search for all candidate paths from the real-time position to the end position. After searching for the candidate paths, also monitor the road condition information of the candidate paths through various methods such as V2X communication technology, traffic monitoring platforms, and third-party service platforms for subsequent path screening.

[0042] In step S240, the third road condition information of the candidate path is compared with the second road condition information of the remaining path in the driving path, so as to accurately select the path with better road conditions from the candidate path and the remaining path. Based on the traffic information and road information, the selected path can ensure the driving efficiency, and based on the path risk information, the selected path can ensure driving safety.

[0043] In this embodiment, the traffic information, road information and path risk information of the path are comprehensively considered, and the local path is optimized adaptively to the real-time changing road conditions in the complex traffic data, which can flexibly respond to the road condition changes, realize the dynamic and accurate optimization of the path, ensure that the path is always optimal, thus improving the reliability of the path planning, ensuring the driving efficiency and driving safety, and enhancing the user experience.

[0044] In a possible embodiment, the road condition information obtained through various methods such as V2X communication technology, traffic monitoring platform, third-party service platform, etc. is cleaned, denoised, synchronized and standardized to ensure the data quality.

[0045] In a possible embodiment, the data from different sources (such as in-vehicle sensors, vehicle networking data, traffic monitoring data, third-party data) are fused to form a unified format for facilitating subsequent path planning processing.

[0046] In a possible embodiment, the historical road condition information is combined with the real-time road condition information obtained through various methods such as V2X communication technology, traffic monitoring platform, third-party service platform, etc. to predict the future road condition information, and the monitoring of the second road condition information in front of the real-time position on the driving path and the third road condition information of the candidate path is realized.

[0047] In an embodiment, the planning method of the driving path includes: constructing a traffic road network, which is composed of multiple nodes, sections connecting multiple nodes, and the section attributes of each section. The section attributes include section length, traffic time and the fourth road condition information, and the fourth road condition information includes traffic information, road information and path risk information; constructing a path cost function according to the section attributes of each section, and constructing a Hamiltonian according to the cost function; in the traffic road network, searching for the feasible path from the starting position to the ending position of the vehicle, and the driving information also includes the starting position, and encoding each feasible path into a qubit state to form a quantum superposition state; performing annealing evolution on the quantum superposition state according to the Hamiltonian, and decoding the qubit state evolved to the ground state to obtain the driving path.

[0048] Among them, the fourth road condition information includes traffic information, road information, and path risk information. The traffic information includes traffic flow, traffic light status (the status of the traffic light when a vehicle passes through a certain traffic light), traffic congestion status, average driving speed, etc. The road information includes road type (such as highway, urban expressway, etc.), road surface quality (considering whether the road surface is damaged, flooded, slippery, etc.), as well as accident, construction, and control situations, etc. The path risk information includes a path risk coefficient, which is determined by multiple factors such as whether there are high-incidence accident sections, whether there are special areas (such as schools, hospitals, residential areas) in the path, and weather conditions. The traffic information, road information, and path risk information can be obtained through various methods such as V2X communication technology, traffic monitoring platforms, and third-party service platforms.

[0049] In this embodiment, the quantum superposition state represents the combination of all feasible paths, that is, all feasible paths are taken into consideration without giving up any possibility; performing annealing evolution on the quantum superposition state according to the Hamiltonian means that through the coupling and interaction between qubits, the state of the qubits evolves on the energy function. During the quantum annealing process, the evolution process of the energy function can be represented by the Hamiltonian. The goal is to minimize the path cost function, and by continuously iteratively adjusting the state of the qubits, the path cost is reduced. After a certain number of quantum iterations, the energy state of the system tends to be stable and finally converges to the global optimal path, thereby obtaining the final driving path.

[0050] In this embodiment, considering the problem that when facing complex traffic data, the path calculation complexity increases sharply, resulting in low path calculation efficiency, which affects the immediacy and accuracy of path planning. Therefore, the path planning problem is transformed into an optimization problem of quantum computing, so as to utilize the parallelism of quantum algorithms and the superposition characteristics of quantum states to consider the advantages and disadvantages of all paths at once, rather than comparing them one by one slowly. It can efficiently consider complex factors (such as traffic information, road information, path risk information, etc.), perform parallel calculations under a large-scale traffic road network, quickly find the global optimal path, improve the path search efficiency, and thus ensure the reliability of path planning.

[0051] Exemplarily, the expression of the Hamiltonian is:

[0052] H(P) = C(P)·path(P) Formula (1)

[0053] Among them, H(P) represents the Hamiltonian; C(P) represents the path cost function; patg(P) represents the selection state of the path, taking values of 0 or 1. 0 means the path is not selected, and 1 means the path is selected.

[0054] Exemplarily, the expression of the quantum superposition state is:

[0055]

[0056] Among them, |Ψ init > represents the quantum superposition state of all feasible paths, and N represents the number of feasible paths; |P i > represents the qubit state of the feasible path i.

[0057] In one embodiment, a path cost function is constructed according to the road section attributes of each road section, including: constructing the road section weight of each road section according to the traffic information, road information and path risk information in the fourth road condition information; constructing a single road section cost function according to the road section length, traffic time and road section weight; superimposing the single road section cost functions of each road section to obtain the path cost function.

[0058] In this embodiment, considering the complexity of traffic data, various situations will be encountered during driving. Therefore, the path cost is not limited to short distance or less time, but also comprehensively considers the traffic information, road information and path risk information of each road section in the path, so as to more accurately reflect various situations that may be encountered during actual driving, provide a comprehensive and accurate reference for path planning, and improve the reliability of path planning.

[0059] Exemplarily, the expression of the path cost function is:

[0060]

[0061] Among them, C(P) represents the path cost from the starting position to the ending position; n represents the number of road sections; d i represents the road section length of road section i; w i represents the road section weight of road section i, and t i represents the traffic time of road section i.

[0062] In a possible embodiment, the method for determining the road section weight includes: determining the traffic information weight of the road section according to the traffic information in the fourth road condition information and a preset traffic information weight table; determining the road information weight of the road section according to the road information in the fourth road condition information and a preset road information weight table; determining the path risk information weight of the road section according to the path risk information in the fourth road condition information and a path risk information weight table; calculating the sum of the traffic information weight, road information weight and path risk information weight of the road section to obtain the road section weight.

[0063] Among them, the traffic information weight table includes a traffic flow weight table, a traffic light status weight table, a traffic congestion status weight table, and an average driving speed weight table. The traffic flow weight table is a correspondence table between different traffic flows and different weights. The traffic light status weight table is a correspondence table between different traffic light statuses and different weights. The traffic congestion status weight table is a correspondence table between different traffic congestion statuses and different weights. The average driving speed weight table is a correspondence table between different average driving speeds and different weights. The road information weight table includes a road type weight table, a road surface quality weight table, and an accident, construction, and control situation weight table. The road type weight table is a correspondence table between different road types and different weights. The road surface quality weight table is a correspondence table between different road surface qualities and different weights. The accident, construction, and control situation weight table is a correspondence table between different accident, construction, and control situations and different weights. The path risk information weight table includes a path risk coefficient weight table, and the path risk coefficient weight table is a correspondence table between different path risk coefficients and different weights.

[0064] Exemplarily, the method for determining the traffic information weight includes: determining the traffic flow weight according to the traffic flow and the traffic flow weight table; determining the traffic light status weight according to the traffic light status and the traffic light status weight table; determining the traffic congestion status weight according to the traffic congestion status and the traffic congestion status weight table; determining the average driving speed weight according to the average driving speed and the average driving speed weight table; calculating the sum of the traffic flow weight, the traffic light status weight, the traffic congestion status weight, and the average driving speed weight to obtain the traffic information weight.

[0065] Exemplarily, the method for determining the road information weight includes: determining the road type weight according to the road type and the road type weight table; determining the road surface quality weight according to the road surface quality and the road surface quality weight table; determining the accident, construction, and control situation weight according to the accident, construction, and control situation and the accident, construction, and control situation weight table; calculating the sum of the road type weight, the road surface quality weight, and the accident, construction, and control situation weight to obtain the road information weight.

[0066] Exemplarily, the method for determining the path risk information weight includes: determining the path risk information weight according to the path risk information and the path risk information weight table.

[0067] In this possible embodiment, the greater the traffic flow, the traffic light status is red, the more congested the traffic congestion status, and the smaller the average driving speed, the greater the corresponding weight, that is, the greater the traffic information weight; the worse the road type, the worse the road surface quality, and the more accidents, construction, and control situations, the greater the corresponding weight, that is, the greater the road information weight; the greater the path risk coefficient, that is, the greater the path risk information weight.

[0068] Please refer to Figure 3 , Figure 3 which is a flowchart showing a method for planning a driving route according to an exemplary embodiment of the present application. As Figure 3 shown, the steps of planning the driving route at least include steps S310 to S380, which are described in detail as follows:

[0069] Step S310: Construct a traffic road network and a path cost function;

[0070] Step S320: Construct a Hamiltonian according to the path cost function;

[0071] Step S330: Obtain the starting position and the ending position of the vehicle;

[0072] Step S340: Search for a feasible path from the starting position to the ending position in the traffic road network;

[0073] Step S350: Encode each feasible path into a qubit state to form a quantum superposition state;

[0074] Step S360: Perform annealing evolution on the quantum superposition state according to the Hamiltonian;

[0075] Step S370: Decode the qubit state evolved to the ground state;

[0076] Step S380: Output the driving route.

[0077] Exemplarily, it is assumed that the constructed traffic network includes 10 nodes and 15 edges, and there are two feasible paths from the starting position A to the ending position B, which are: Path 1: A - B, Path 2: A - C - D - B. The process of determining the driving route from Path 1 and Path 2 is as follows:

[0078] (1) Path cost calculation:

[0079] Path 1: If the length of section A - B is d1 = 10 km, the traffic time is t1 = 1 h, and the section weight is w1 = 2, then the path cost C(P1) = d1 × w1 + t1 = 10 × 2 + 1 = 21;

[0080] Path 2: If the length of section A - C is d2 = 5 km, the traffic time is t2 = 0.5 h, and the section weight is w2 = 1.5, the length of section C - D is d3 = 4 km, the traffic time is t3 = 0.6 h, and the section weight is w3 = 1.2, the length of section D - B is d4 = 6 km, the traffic time is t4 = 0.7 h, and the section weight is w4 = 1.1, then the path cost: C(P2) = d2 × w2 + t2 + d3 × w3 + t3 + d4 × w4 + t4 = 5 × 1.5 + 0.5 + 4 × 1.2 + 0.6 + 6 × 1.1 + 0.7 = 20.7;

[0081] (2) Determine the quantum superposition state

[0082] Map path 1 and path 2 to qubit states, which are ∣P1> and ∣P2> respectively, and form a quantum superposition state, indicating that the probability amplitudes of the two paths are the same:

[0083] (3) Quantum annealing evolution

[0084] During the quantum annealing process, for path 1 and path 2, the Hamiltonian can be expressed as: H(P1) = C(P1) × 1 = 21 × 1 = 21, H(P2) = C(P2) × 1 = 20.7 × 1 = 20.7, and attempt to find the path with the lowest energy. Therefore, H(P2) = 20.7 is the optimal solution;

[0085] (4) Path output

[0086] H(P2) corresponds to path 2, and decoding obtains the optimal path as A - C - D - B.

[0087] In one embodiment, after monitoring the second road condition information in front of the real-time position on the driving path, it further includes: if at least one of the traffic information, road information, and path risk information in the first road condition information is better than the traffic information, road information, and path risk information in the second road condition information, it is determined that the first road condition information is better than the second road condition information; if the traffic information, road information, and path risk information in the second road condition information are all better than the traffic information, road information, and path risk information in the first road condition information, it is determined that the second road condition information is better than the first road condition information.

[0088] Among them, at least one of the traffic information, road information, and path risk information in the first road condition information being better than the traffic information, road information, and path risk information in the second road condition information includes: the traffic information in the first road condition information is better than the traffic information in the second road condition information; the road information in the first road condition information is better than the road information in the second road condition information; the path risk information in the first road condition information is better than the path risk information in the second road condition information (that is, the path risk in the second road condition information is higher than the path risk in the first road condition information); the traffic information and road information in the first road condition information are respectively better than the traffic information and road information in the second road condition information; the road information and path risk information in the first road condition information are respectively better than the road information and path risk information in the second road condition information; the traffic information and path risk information in the first road condition information are respectively better than the traffic information and path risk information in the second road condition information; the traffic information, road information, and path risk information in the first road condition information are respectively better than the traffic information, road information, and path risk information in the second road condition information.

[0089] In addition, if at least one of the traffic flow, traffic light status, traffic congestion status, and average driving speed in the traffic information of the first road condition information is better than that in the traffic information of the second road condition information, it indicates that the traffic information in the first road condition information is better than that in the second road condition information. The same applies to road information and path risk information, which will not be elaborated here.

[0090] For example, when planning a route, there is no congestion on a certain section of the driving route. Subsequently, it is monitored that congestion occurs on this section and the vehicle has not yet passed through this section, indicating that the first road condition information is better than the second road condition information, that is, the current road condition has deteriorated, and then route optimization is triggered.

[0091] In this embodiment, by comprehensively considering traffic information, road information, and path risk information, comparing the road condition information before the remaining routes with the current road condition information, the changes in the road condition are evaluated in real time and comprehensively, which can improve the accuracy of monitoring road condition changes under complex traffic data, thereby ensuring the reliability of route optimization.

[0092] In a possible embodiment, the local A algorithm is used for route optimization, which is applied to locally adjust the planned route when the road condition deteriorates.

[0093] In an embodiment, the method for determining the target route includes: evaluating the first score of the remaining routes according to the traffic information, road information, and path risk information in the second road condition information, and evaluating the second score of the candidate routes according to the traffic information, road information, and path risk information in the third road condition information, where the candidate routes are at least one; determining the route corresponding to the larger value of the scores as the target route according to the first score and each second score.

[0094] In this embodiment, considering that when facing complex traffic data, there are many factors affecting the road condition and the accuracy of route optimization is insufficient, which affects the reliability of route planning. Therefore, the traffic information, road information, and path risk information of each route are comprehensively considered for route scoring, providing a comprehensive and accurate reference for route optimization, being able to bypass congested, accident-prone, high-risk and other sections, thereby improving the accuracy of route optimization and ensuring the reliability of route planning.

[0095] In a possible embodiment, a weighted model is used to score the routes.

[0096] In a possible embodiment, the calculation method of the first score includes: converting the traffic information, road information, and path risk information in the second road condition information into traffic information scores, road information scores, and path risk information scores; calculating the first score according to a preset weight distribution table, traffic information scores, road information scores, and path risk information scores, and the weight distribution table includes the weight ratios of traffic information, road information, and path risk information.

[0097] As a possible embodiment, the traffic information score, road information score, and path risk information score are subdivided into traffic flow score, traffic light status score, traffic congestion status score, average driving speed score, road type score, road surface quality score, accident, construction, and control situation score, path risk score; the weight ratios of traffic information, road information, and path risk information are subdivided into traffic flow weight ratio, traffic light status weight ratio, traffic congestion status weight ratio, average driving speed weight ratio, road type weight ratio, road surface quality weight ratio, accident, construction, and control situation weight ratio, path risk weight ratio, and the sum of each weight ratio is 1.

[0098] In a possible embodiment, the calculation method of the second score includes: converting the traffic information, road information, and path risk information in the third road condition information into traffic information scores, road information scores, and path risk information scores; calculating the second score according to a preset weight distribution table, traffic information scores, road information scores, and path risk information scores, and the weight distribution table includes the weight ratios of traffic information, road information, and path risk information.

[0099] As a possible embodiment, the traffic information score, road information score, and path risk information score are subdivided into traffic flow score, traffic light status score, traffic congestion status score, average driving speed score, road type score, road surface quality score, accident, construction, and control situation score, path risk score; the weight ratios of traffic information, road information, and path risk information are subdivided into traffic flow weight ratio, traffic light status weight ratio, traffic congestion status weight ratio, average driving speed weight ratio, road type weight ratio, road surface quality weight ratio, accident, construction, and control situation weight ratio, path risk weight ratio, and the sum of each weight ratio is 1. Additionally, this weight distribution table is the same as the above-mentioned weight distribution table.

[0100] Exemplarily, the expression of the weighted model is:

[0101]

[0102] where F represents the path score, n represents the number of factors, w i represents the weight ratio of factor i, and f iIndicates the score of factor i. The factors include traffic flow, traffic light status, traffic congestion status, average driving speed, road type, road surface quality, accidents, construction and control conditions, and path risk coefficient.

[0103] In one embodiment, the method for determining the target path further includes: if the first score is equal to each second score, then according to the preset path selection criteria, evaluate the immediate rewards of each candidate path and the remaining paths. The indicators in the path selection criteria include path time consumption, path fuel consumption, road type, and facilities along the path; calculate the path values of each candidate path and the remaining paths according to the preset path value function and the immediate rewards; according to each path value, determine the path corresponding to the larger path value as the target path.

[0104] Among them, the indicators in the path selection criteria include path time consumption, path fuel consumption, road type, and facilities along the path. Each indicator can be set according to the user's personalization. For example, the standard for path time consumption is that the shorter the time, the better; the standard for path fuel consumption is that the less the fuel consumption, the better; the standard for road type is to avoid toll roads; the standard for facilities along the path is that the scenery along the path is better, or there are service facilities such as rest stops, gas stations, restaurants, and hospitals on the way.

[0105] In this embodiment, considering the situation where the scores of each path are the same, the path optimization is restricted to a certain extent. Therefore, on the basis of scoring and selecting based on traffic information, road information, and path risk information, the user's personal preferences are introduced, and the path corresponding to the larger path value is selected as the target path. In this way, the limitation of only relying on road condition information can be broken through, making the path optimization more in line with the user's preferences and ensuring the reliability of path planning.

[0106] Exemplarily, the expression of the path value function is:

[0107] Q(s,a)=Q(s,a)+α[r+γmax a′ Q(s′,a′)-Q(s,a)] Formula (5)

[0108] Among them, Q(s,a) represents the value estimation of taking action a in state s, α represents the learning rate, r represents the immediate reward of taking action a in state s, γ represents the discount factor, which is the degree of emphasis on future rewards, and max a′ Q(s′,a′) represents the value corresponding to the action that maximizes Q(s′,a′) in the next state s′.

[0109] In the embodiment of the present application, Q(s,a) represents the path value of selecting path a when the road condition information of path a is s. The immediate reward r is determined according to path time consumption, path fuel consumption, road type, and facilities along the path, and max a′Q(s′, a′) represents the value corresponding to the path that maximizes Q(s′, a′) when the road condition information of path a′ is s′.

[0110] Please refer to Figure 4 , Figure 4 which is a flowchart for optimizing a driving path shown in an exemplary embodiment of the present application. As Figure 4 shown, the steps for optimizing the driving path at least include steps S410 to S470, which are detailed as follows:

[0111] Step S410: Obtain the first road condition information at a historical moment in front of the driving path, and monitor the second road condition information at the current moment in front of the driving path;

[0112] Step S420: Determine whether the road condition deteriorates. If it deteriorates, go to step S430; if not, return to step S410;

[0113] Step S430: Search for candidate paths from the real-time position to the end position, and monitor the third road condition information of the candidate paths;

[0114] Step S440: Evaluate the first score of the remaining paths according to the second road condition information, and evaluate the second score of the candidate paths according to the third road condition information;

[0115] Step S450: Determine whether the first score is equal to the second score. If they are equal, go to step S452-1; if not, go to step S451;

[0116] Step S451: Determine the path corresponding to the larger score value as the target path;

[0117] Step S452-1: Calculate the path values of the remaining paths and the candidate paths according to the preset path value function and path selection criteria;

[0118] Step S452-2: Determine the path corresponding to the larger path value as the target path;

[0119] Step S460: Continue driving according to the target path;

[0120] Step S470: Determine whether the end position is reached. If it is reached, end; if not, return to step S410.

[0121] Suppose a vehicle is traveling on Highway A and an accident is detected ahead, causing severe congestion. Based on the real-time position, candidate path B is searched. Here, only two factors (traffic flow and path risk information) are taken as examples for illustrative purposes. If the traffic flow weight w1 = 0.6, the path risk information weight w2 = 0.4, the traffic flow score of the remaining path of Highway A is f1 = 0.7 (the larger the score, the less congested), the path risk information score is f2 = 0.2 (the larger the score, the lower the risk), the traffic flow score of candidate path B is f3 = 0.3, and the path risk information score is f4 = 0.8, then the score of the remaining path of Highway A is: F(A) = 0.6×0.7 + 0.4×0.2 = 0.42 + 0.08 = 0.5, and the score of candidate path B is: F(B) = 0.6×0.3 + 0.4×0.8 = 0.18 + 0.32 = 0.5.

[0122] Therefore, under the scoring of the weighted model, the scores of the remaining path of Highway A and candidate path B are the same. The system will not immediately select candidate path B but will make a further judgment based on path preferences.

[0123] Suppose α is 0.1 and γ is 0.9. First, set the states and actions: state s (road condition information), s1 is the road condition information of Highway A, s2 is the road condition information of the candidate path, action a (selected path), a1 is to select the remaining path of Highway A, a2 is to select candidate path B; for each path, determine the immediate reward r. The immediate reward is determined based on path travel time, path fuel consumption, road type, and facilities along the path. Suppose the immediate reward of Highway A is r1 = -10 (negative reward), and the immediate reward of candidate path B is r2 = 5 (positive reward); for choosing a1 in state s1 (assuming the initial Q value is 0): Q(s1,a1) = 0 + 0.1(-10 + 0.9×max(Q(s2,a1),Q(s2,a2)) - 0). Suppose Q(s2,a1) = 0 and Q(s2,a2) = 0, then Q(s1,a1) = 0 + 0.1(-10 + 0.9×0 - 0) = -1. For choosing a2 in state s1 (assuming the initial Q value is 0): Q(s1,a2) = 0 + 0.1(5 + 0.9×max(Q(s2,a1),Q(s2,a2)) - 0). Suppose Q(s2,a1) = 0 and Q(s2,a2) = 0, then Q(s1,a2) = 0 + 0.1(5 + 0.9×0 - 0) = 0.5. Therefore, the Q value of candidate path B is greater than that of the remaining path of Highway A, and candidate path B is the target path.

[0124] In one embodiment, the method for determining the target path further includes: evaluating a third score of the remaining paths according to a preset path selection criterion and the traffic information, road information, and path risk information in the second road condition information; evaluating a fourth score of the candidate paths according to the path selection criterion and the traffic information, road information, and path risk information in the third road condition information, where the candidate paths are at least one; and determining the path corresponding to the larger value of the scores as the target path according to the third score and each fourth score.

[0125] In this embodiment, considering that in path optimization, the user's personalized preferences are not fully considered, which limits the accuracy of path optimization to a certain extent. Therefore, when performing path optimization, the user's personalized preferences are introduced, and the path is directly scored by combining the road condition information and the path selection criterion, and the path corresponding to the larger value of the scores is selected as the target path. In this way, the limitation of relying only on the road condition information can be broken through, making the path optimization more in line with the user's preferences and ensuring the reliability of path planning.

[0126] Please refer to Figure 5 , Figure 5 which is a flowchart of another optimized driving path shown in an exemplary embodiment of the present application. As Figure 5 shown, the steps of this another optimized driving path at least include step S510 to step S580, which are described in detail as follows:

[0127] Step S510: Obtain the first road condition information at a historical moment in front of the driving path, and monitor the second road condition information at the current moment in front of the driving path.

[0128] Step S520: Determine whether the road condition deteriorates. If it deteriorates, go to step S530; if not, return to step S510.

[0129] Step S530: Search for candidate paths from the current position to the end position, and monitor the third road condition information of the candidate paths.

[0130] Step S540: Evaluate the third score of the remaining paths according to the preset path selection criterion and the second road condition information, and evaluate the fourth score of the candidate paths according to the path selection criterion and the third road condition information.

[0131] Step S550: Determine whether the third score is equal to the fourth score. If they are equal, go to step S570 to continue driving according to the original path; if not, go to step S560.

[0132] Step S560: Determine the path corresponding to the larger value of the scores as the target path, and go to step S570 to continue driving according to the target path.

[0133] Step S570, continue driving according to the original path or the target path;

[0134] Step S580, determine whether the end position is reached. If it is reached, end. If not, return to Step S510.

[0135] In a possible embodiment, in the path cost function, in addition to considering the segment length, traffic time, and segment weight of each segment, the preference score of each segment is also considered, so that the path planning is more in line with the user's preferences and the reliability of the path planning is ensured.

[0136] Exemplarily, the new path cost function is:

[0137]

[0138] where C(P′) represents the path cost from the starting position to the ending position; n represents the number of segments; d i represents the segment length of segment i; w i represents the segment weight of segment i; t i represents the traffic time of segment i; q i represents the preference score of segment i.

[0139] In a possible embodiment, after determining the target path from the real-time position to the end position, the vehicle is automatically controlled to drive based on the target path through autonomous driving.

[0140] In an embodiment, after determining the target path from the real-time position to the end position, it further includes: pushing each candidate path and the remaining paths for path selection; collecting feedback information on the path selection, where the feedback information includes the path selection result, and adjusting the path selection criteria according to the feedback information.

[0141] In this embodiment, each candidate path and the remaining paths are pushed to the user in real time through the in-vehicle display screen or voice prompt, etc., for the user to independently select a path, and based on the path selected by the user, the path selection criteria are adjusted, that is, the path recommendation strategy is adjusted, so as to improve the reliability of the path planning and enhance the user experience.

[0142] In a possible embodiment, during the vehicle driving process, the user's behavior (such as whether to change the route) is monitored in real time to optimize the path selection criteria, thereby improving the reliability of the path planning and enhancing the personalized experience.

[0143] The above path planning method first obtains the driving information of the vehicle, which includes the real-time position, the end position, and the driving path, and obtains the first road condition information in front of the real-time position monitored during the driving path planning. Then, it monitors the second road condition information in front of the real-time position on the driving path. If the first road condition information is better than the second road condition information, it searches for candidate paths from the real-time position to the end position and monitors the third road condition information of the candidate paths. Among them, the first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information. Finally, according to the advantages and disadvantages of the third road condition information and the second road condition information, it determines the target path from the real-time position to the end position from the candidate paths and the remaining paths of the driving path. By comprehensively considering the traffic information, road information, and path risk information of the path, and adapting to the real-time changing road conditions in complex traffic data for local path optimization, it can flexibly respond to road condition changes, achieve dynamic and precise optimization of the path, ensure that the path is always optimal, thus improving the reliability of path planning, ensuring driving efficiency and driving safety, and enhancing the user experience.

[0144] Please refer to Figure 6 , Figure 6 which is a flowchart of a specific path planning method shown in an exemplary embodiment of the present application. As Figure 6 shown, the specific path planning method at least includes steps S610 to S670, which are described in detail as follows:

[0145] Step S610, obtain the starting position and the end position;

[0146] Step S620, construct a traffic road network;

[0147] Step S630, in the traffic road network, perform path planning based on quantum computing to obtain the driving path from the starting position to the end position;

[0148] Step S640, adaptively perform local path optimization according to road condition changes to determine the target path from the real-time position to the end position;

[0149] Step S650, continue driving according to the target path;

[0150] Step S660, determine whether the end position is reached. If it is reached, end. If not, return to step S610.

[0151] In this way, in the face of complex traffic networks and large-scale data, path planning is performed based on quantum computing. At the same time, the adaptive local optimization technology can respond to road condition changes in real time for local path adjustment. Combining the high-speed parallel computing ability of quantum computing and the flexibility of adaptive local optimization, it can provide efficient, precise, and dynamic path planning and optimization in complex traffic environments, improving the reliability of path planning.

[0152] Please refer to Figure 7 , Figure 7 which is a block diagram of a path planning system shown in an exemplary embodiment of the present application. This system can be applied to Figure 1 the implementation environment shown. It should be understood that this system can also be applicable to other exemplary implementation environments, and the implementation environment applicable to this system is not limited in this embodiment.

[0153] As Figure 7 shown, in an exemplary embodiment, the path planning system 700 at least includes an acquisition module 710, a monitoring module 720, a search module 730, and a screening module 740, which are introduced in detail as follows:

[0154] The acquisition module 710 is configured to acquire the driving information of the vehicle. The driving information includes the real-time position, the end position, and the driving path, and to acquire the first road condition information in front of the real-time position monitored during the driving path planning;

[0155] The monitoring module 720 is configured to monitor the second road condition information in front of the real-time position on the driving path;

[0156] The search module 730 is configured to, if the first road condition information is better than the second road condition information, search for a candidate path from the real-time position to the end position, and monitor the third road condition information of the candidate path. The first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information;

[0157] The screening module 740 is configured to determine the target path from the real-time position to the end position from the candidate path and the remaining paths of the driving path according to the superiority and inferiority of the third road condition information and the second road condition information.

[0158] It should be noted that the path planning system provided in the above embodiment and the path planning method provided in the above embodiment belong to the same concept. The content of the operations performed by each module has been described in detail in the method embodiment, and will not be repeated here.

[0159] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of an in-vehicle device provided in an embodiment of the present application. Figure 8 Shows a schematic structural diagram of a computer system of an in-vehicle device suitable for implementing the embodiments of the present application. It should be noted that Figure 8 the computer system 800 of the in-vehicle device shown is only an example, and should not bring any limitation to the functions and usage scope of the embodiments of the present application.

[0160] As Figure 8As shown, computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 802 or the program loaded from the storage section 808 into the Random Access Memory (RAM) 803, such as executing the methods in the above embodiments. In the RAM 803, various programs and data required for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0161] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc. and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed so that the computer program read from it can be installed into the storage section 808 as needed.

[0162] Specifically, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a computer program for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 809, and / or installed from the removable medium 811. When the computer program is executed by the Central Processing Unit (CPU) 801, various functions defined in the system of the present application are executed.

[0163] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and the above-mentioned module, segment of a program, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0164] The units described in the embodiments of the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the units themselves.

[0165] The above embodiments are only used to exemplarily illustrate the principles and effects of the present application, rather than to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application should still be covered by the claims of the present application.

Claims

1. A path planning method, characterized in that, The method includes: Obtaining the driving information of the vehicle, where the driving information includes the real-time position, the end position, and the driving route, and obtaining the first road condition information in front of the real-time position monitored when planning the driving route; Monitoring the second road condition information in front of the real-time position on the driving route; If the first road condition information is better than the second road condition information, search for candidate routes from the real-time position to the end position, and monitor the third road condition information of the candidate routes. The first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information; Determine the target route from the real-time position to the end position from the candidate routes and the remaining routes of the driving route according to the advantages and disadvantages of the third road condition information and the second road condition information.

2. The path planning method according to claim 1, wherein After monitoring the second road condition information in front of the real-time position on the driving route, it further includes: If at least one of the traffic information, road information, and path risk information in the first road condition information is better than the traffic information, road information, and path risk information in the second road condition information, determine that the first road condition information is better than the second road condition information; If the traffic information, road information, and path risk information in the second road condition information are all better than the traffic information, road information, and path risk information in the first road condition information, determine that the second road condition information is better than the first road condition information.

3. The path planning method according to claim 1, characterized in that, The determination method of the target route includes: Evaluating the first score of the remaining route according to the traffic information, road information, and path risk information in the second road condition information, and evaluating the second score of the candidate route according to the traffic information, road information, and path risk information in the third road condition information. The candidate route is at least one; Determine the route corresponding to the larger score value as the target route according to the first score and each second score.

4. The path planning method according to claim 3, wherein The determination method of the target route further includes: If the first score and each second score are equal, evaluate the immediate reward of each candidate route and the remaining route according to the preset route selection criteria. The indicators in the route selection criteria include route time consumption, route fuel consumption, road type, and facilities along the route; Calculate the route value of each candidate route and the remaining route according to the preset route value function and the immediate reward; Determine the route corresponding to the larger route value as the target route according to each route value.

5. The path planning method according to claim 1, wherein The determination method of the target route further includes: Evaluating the third score of the remaining route according to the preset route selection criteria and the traffic information, road information, and path risk information in the second road condition information, and evaluating the fourth score of the candidate route according to the route selection criteria and the traffic information, road information, and path risk information in the third road condition information. The candidate route is at least one; Determine the route corresponding to the larger score value as the target route according to the third score and each fourth score.

6. The path planning method according to claim 1, wherein The planning method of the driving route includes: Construct a transportation road network, which consists of multiple nodes, road segments connecting the multiple nodes, and road segment attributes of each road segment. The road segment attributes include road segment length, traffic time, and fourth road condition information. The fourth road condition information includes traffic information, road information, and path risk information; Construct a path cost function based on the road segment attributes of each road segment, and construct a Hamiltonian based on the cost function; In the transportation road network, search for a feasible path from the starting position of the vehicle to the ending position. The driving information also includes the starting position, and encode each feasible path into a quantum bit state to form a quantum superposition state; Perform annealing evolution on the quantum superposition state according to the Hamiltonian, and decode the quantum bit state evolved to the ground state to obtain the driving path.

7. The path planning method according to claim 6, wherein, The constructing a path cost function based on the road segment attributes of each road segment includes: Construct the road segment weights of each road segment according to the traffic information, road information, and path risk information in the fourth road condition information; Construct a single road segment cost function according to the road segment length, the traffic time, and the road segment weights; Superimpose the single road segment cost functions of each road segment to obtain the path cost function.

8. The path planning method according to claim 4 or 5, characterized in that, After determining the target path from the real-time position to the ending position, it further includes: Push each of the candidate paths and the remaining paths for path selection; Collect feedback information on path selection. The feedback information includes the path selection result, and adjust the path selection criteria according to the feedback information.

9. A path planning system, characterized in that, The system includes: An acquisition module for acquiring the driving information of the vehicle. The driving information includes the real-time position, the ending position, and the driving path, and acquiring the first road condition information in front of the real-time position detected during the driving path planning; A monitoring module for monitoring the second road condition information in front of the real-time position on the driving path; A search module for searching for candidate paths from the real-time position to the ending position if the first road condition information is better than the second road condition information, and monitoring the third road condition information of the candidate paths. The first road condition information, the second road condition information, and the third road condition information all include traffic information, road information, and path risk information; A screening module for determining the target path from the real-time position to the ending position from the candidate paths and the remaining paths of the driving path according to the superiority and inferiority of the third road condition information and the second road condition information.

10. A vehicle-mounted device, characterized in that, It includes: One or more processors; A storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the in-vehicle device is enabled to implement the path planning method according to any one of claims 1 to 8.

Images