WO2021035759A1

WO2021035759A1 - Route planning method and apparatus

Info

Publication number: WO2021035759A1
Application number: PCT/CN2019/103898
Authority: WO
Inventors: 朱国峰; 贝学威; 许红
Original assignee: 华为技术有限公司
Priority date: 2019-08-31
Filing date: 2019-08-31
Publication date: 2021-03-04
Also published as: CN114450556A

Abstract

Provided is a route planning method, which meets the multi-policy user requirement, and can be applied in an intelligent driving system comprising autonomous driving and assistant driving. The route planning method comprises: obtaining route planning reference information, the route planning reference information comprising at least one of the traffic condition, the road condition, the weather condition or the vehicle condition (201); obtaining a plurality of user policies input by one or more users (202); and performing route planning according to the route planning reference information and the plurality of user policies (203). Also provided are a route planning apparatus, a computer storage medium, a computer program product, and an intelligent vehicle.

Description

Path planning method and device

Technical field

This application relates to intelligent driving technology, and in particular to a path planning method and device.

Background technique

In the current intelligent driving scenario, for example, when a vehicle starts, a destination needs to be selected in the path planning software, and then the path planning software plans the driving path of the vehicle. In this way, the vehicle can follow the planned path while driving, and finally reach the destination.

Current path planning software uses path planning methods: shortest distance path planning, shortest time path planning, optimal comfort path planning, most economical path planning, etc. Existing path planning methods, based on a single strategy to pursue the only best path, collectively referred to as single strategy path planning, can solve the uncertainty caused by incomplete information to a certain extent, and can also plan a relatively optimal path , But there are many problems, including: the existing path planning method does not take user needs as the core, does not consider the needs of multiple strategies, it is difficult to meet the needs of application scenarios where multiple path planning strategies coexist, and the user experience is poor; due to environmental changes such as road conditions It’s not appropriate to allow users to fix a certain strategy in advance; because road conditions, vehicle information, weather, and traffic conditions change dynamically in real time, no single path planning strategy can be applied to actual scenarios alone, for example, based on The shortest distance path planning strategy. When a certain section of the path planned in advance is temporarily constructed, if the strategy is not changed, it may cause the path planning software to instruct the vehicle to die on the road section, etc.; the path is not supported when the user's strategic needs change Autonomous dynamic switching requires manual intervention to adjust and update the planned path; it is difficult to tap more potential path opportunities.

In short, there is an urgent need for a path planning solution that is more adaptable to actual scenarios and improves user experience.

Summary of the invention

In order to overcome the above-mentioned problems in the prior art, embodiments of the present invention provide a path planning method and device.

In a first aspect, a path planning method is provided, including: obtaining path planning reference information, where the path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions; and obtaining one or more user input Multiple user strategies; path planning is performed according to the path planning reference information and the multiple user strategies. The user strategy reflects the user’s preference for the path planning strategy. The multiple user strategies may be multiple user strategies of a user. For example, a user wants the path to take time priority and distance priority into consideration; the multiple user strategies may also be Multiple user strategies for multiple users. For example, when multiple users ride in a car, user A wants time first, user B wants distance first, and user C wants cost first, so we try our best by considering time priority, distance priority and cost priority. Take into account the different needs of multiple users. By using multi-strategy as a decision reference for path planning, user-centric intelligent path planning can be realized, and when the driving environment information changes in real time, the multi-strategy path planning mechanism is convenient to adjust the path more flexibly and dig out better ones. Potential path, the path obtained by planning is more suitable for the actual scene.

According to the first aspect, in the first possible implementation manner of the path planning method, the user strategy includes distance priority, time priority, safety priority, comfort priority, or expense priority. Distance priority is aimed at short driving distances without detours; time priority is aimed at short travel times, such as trying to meet high speeds, short distances, avoiding congestion and avoiding waiting for traffic lights; safety priority is aimed at avoiding driving accidents, such as avoiding frequent accidents Road sections, avoid frequent lane changes, and avoid road sections with imperfect traffic facilities; comfort priority aims to improve user experience, such as driving as evenly as possible, driving roads as flat as possible, and avoiding sharp turns; cost priority aims to reduce travel costs, as stated Travel expenses include tolls and fuel costs.

According to the first aspect or the first possible implementation manner of the first aspect, in a second possible implementation manner of the path planning method, the method further includes: updating the path planning reference information; acquiring one or Updating the multiple user policies by multiple users; re-executing the path planning according to the updated path planning reference information or at least one of the updated multiple user policies. The updating the path planning reference information includes using a sensor to continue to collect the path planning reference information, or using a receiver to receive the updated path planning reference information. The update of the one or more users to the plurality of user policies includes deleting one or more user policies of the plurality of user policies, or adding a new one or more user policies, and the new one or Multiple user policies are obtained from one or more original users, or one or more newly added users. When the real-time change of the path planning reference information makes the current path not the optimal path, or the user needs to adjust the selected user strategy, it is necessary to use the updated path planning reference information or the updated path Multiple user strategies re-execute the path planning, so that the planned path meets the real-time changes of the driving scene and the adjustment of user preferences.

According to the first aspect, or any one of the implementation manners of the first aspect above, in a third possible implementation manner of the path planning method, the method further includes: determining a recommendation to the user according to the path planning reference information One or more user policies of the user; sending a suggestion message containing the one or more user policies suggested to the user to the user; the obtaining multiple user policies of one or more user inputs includes: obtaining the one or more user policies One or more user policies selected by a user from the one or more user policies suggested to the user. Because it is difficult for users to understand the complete path planning reference information and the limitations of subjective judgment, the user strategy that the user hopes to adopt may not be suitable for the current driving scene. By suggesting the user strategy to the user, the user strategy selected by the user can be matched with The actual driving environment is more suitable.

According to the first aspect, or any one of the implementation manners of the first aspect above, in a fourth possible implementation manner of the path planning method, the path planning reference information further includes a map, and the map includes a plurality of connections. For path fragments of two adjacent intersections, the performing path planning according to the path planning reference information and the multiple user strategies includes: determining, according to the path planning reference information, that each path fragment corresponds to the multiple user strategies The weight of each user policy in the user policy, the weight is used to identify the traffic cost of a path segment under a user policy; according to the multiple user policies and each path segment corresponds to each of the multiple user policies The weight of each user policy determines one or more reachable paths between the source location and the destination location, and the reachable path includes multiple path segments that are continuous on the map; from the one or more reachable paths Determine the current path in. The user strategies adopted by the multiple consecutive path segments may be different. By spatially distributing the multiple user strategies, path planning based on the multiple user strategies is realized.

According to the first aspect, or any one of the implementations of the first aspect above, in a fifth possible implementation of the path planning method, the multiple path segments corresponding to each of the multiple path segments The weight of at least one user policy in the user policies meets the threshold limit of the corresponding user policy. Identifying and excluding path segments that do not meet the requirements of any one of the multiple user policies by means of threshold limitation can make the planned path meet the requirements of the multiple user policies at the same time.

According to the first aspect, or any one of the foregoing implementation manners of the first aspect, in a sixth possible implementation manner of the path planning method, determining the current path from the multiple reachable paths includes: One of the multiple reachable paths is randomly selected as the current path; or, according to the weight of the multiple path segments included in each reachable path corresponding to each user policy in the multiple user policies, One of the multiple reachable paths is selected as the current path; or, according to the number of the multiple path segments included in each reachable path, one of the multiple reachable paths is selected The path is used as the current path.

According to the first aspect, or any one of the implementation manners of the first aspect above, in a seventh possible implementation manner of the path planning method, the process is performed according to the path planning reference information and the multiple user strategies The path planning includes: sequentially selecting a user policy from the multiple user policies as the current user policy, until a reachable path from the source location to the destination location that satisfies a preset condition is successfully planned based on the current user policy. In addition to the spatial distribution of the multiple user strategies mentioned above, it is also possible to implement path planning based on multiple user strategies by distributing the multiple user strategies in time.

According to the first aspect, or any one of the foregoing implementation manners of the first aspect, in an eighth possible implementation manner of the path planning method, the step of selecting one user strategy from the plurality of user strategies as the current The user strategy includes: sorting the plurality of user strategies by priority, and selecting one user strategy from the plurality of user strategies as the current user strategy in the order of the priority from high to low, or in turn Select one user policy from the multiple user policies in sequence as the current user policy.

In a second aspect, a path planning device is provided, including: a path planning reference information acquisition module for acquiring path planning reference information, where the path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions The user strategy acquisition module is used to acquire multiple user strategies input by one or more users; the path planning module is used to perform path planning according to the path planning reference information and the multiple user strategies. The user strategy reflects the user’s preference for the path planning strategy. The multiple user strategies may be multiple user strategies of a user. For example, a user wants the path to take time priority and distance priority into consideration; the multiple user strategies may also be Multiple user strategies for multiple users. For example, when multiple users ride in a car, user A wants time first, user B wants distance first, and user C wants cost first, so we try our best by considering time priority, distance priority and cost priority. Take into account the different needs of multiple users. By using multi-strategy as a decision reference for path planning, user-centric intelligent path planning can be realized, and when the driving environment information changes in real time, the multi-strategy path planning mechanism is convenient to adjust the path more flexibly and dig out better ones. Potential path, the path obtained by planning is more suitable for the actual scene.

According to the second aspect, in the first possible implementation manner of the path planning device, the user strategy includes distance priority, time priority, safety priority, comfort priority or expense priority. Distance priority is aimed at short driving distances without detours; time priority is aimed at short travel times, such as trying to meet high speeds, short distances, avoiding congestion and avoiding waiting for traffic lights; safety priority is aimed at avoiding driving accidents, such as avoiding frequent accidents Road sections, avoid frequent lane changes, and avoid road sections with imperfect traffic facilities; comfort priority aims to improve user experience, such as driving as evenly as possible, driving roads as flat as possible, and avoiding sharp turns; cost priority aims to reduce travel costs, as stated Travel expenses include tolls and fuel costs.

According to the second aspect or the first possible implementation manner of the second aspect, in a second possible implementation manner of the path planning apparatus: the path planning reference information acquisition module is further configured to update the path planning Reference information; the user policy acquisition module is also used to acquire one or more users' updates to the multiple user policies; the path planning module is also used to update or update the path planning reference information according to the updated At least one of the subsequent multiple user policies performs the path planning again. The updating the path planning reference information includes using a sensor to continue to collect the path planning reference information, or using a receiver to receive the updated path planning reference information. The update of the one or more users to the plurality of user policies includes deleting one or more user policies of the plurality of user policies, or adding a new one or more user policies, and the new one or Multiple user policies are obtained from one or more original users, or one or more newly added users. When the real-time change of the path planning reference information makes the current path not the optimal path, or the user needs to adjust the selected user strategy, it is necessary to use the updated path planning reference information or the updated path Multiple user strategies re-execute the path planning, so that the planned path meets the real-time changes of the driving scene and the adjustment of user preferences.

According to the second aspect, or any one of the foregoing implementation manners of the second aspect, in a third possible implementation manner of the path planning device, the device further includes: a user policy suggestion module, configured to follow the path The planning reference information determines one or more user strategies suggested to the user; the sending module is used to send the user a suggestion message containing the one or more user strategies suggested to the user; the user strategy obtaining module obtains one or more user strategies. The multiple user policies input by a user include: obtaining one or more user policies selected by the one or more users from the one or more user policies suggested to the user. Because it is difficult for users to understand the complete path planning reference information and the limitations of subjective judgment, the user strategy that the user hopes to adopt may not be suitable for the current driving scene. By suggesting the user strategy to the user, the user strategy selected by the user can be matched with The actual driving environment is more suitable.

According to the second aspect, or any one of the implementation manners of the second aspect above, in a fourth possible implementation manner of the path planning device, the path planning reference information further includes a map, and the map includes a plurality of connections For path segments of two adjacent intersections, the path planning module includes: a weight determination module, configured to determine, according to the path planning reference information, the weight of each path segment corresponding to each user strategy in the plurality of user strategies, The weight is used to identify the traffic cost of a path segment under a user policy; the reachable path determination module is used to determine each of the multiple user policies according to the multiple user policies and each path segment. The weight of each user strategy determines one or more reachable paths between the source location and the destination location, and the reachable path includes multiple path segments that are continuous on the map; the current path determination module is used to determine the path from the Determine the current path from one or more reachable paths. The user strategies adopted by the multiple consecutive path segments may be different. By spatially distributing the multiple user strategies, path planning based on the multiple user strategies is realized.

According to the second aspect, or any one of the implementation manners of the second aspect above, in a fifth possible implementation manner of the path planning device, the multiple path segments corresponding to each of the multiple path segments The weight of at least one user policy in the user policies meets the threshold limit of the corresponding user policy. Identifying and excluding path segments that do not meet the requirements of any one of the multiple user policies by means of threshold limitation can make the planned path meet the requirements of the multiple user policies at the same time.

According to the second aspect, or any one of the implementation manners of the above second aspect, in a sixth possible implementation manner of the path planning device, the current path determination module selects from the one or more reachable paths Determining the current path includes: randomly selecting a reachable path from the multiple reachable paths as the current path; or, according to the multiple path segments included in each reachable path corresponding to the multiple user policies For the weight of each user policy, select a reachable path from the multiple reachable paths as the current path; or, according to the number of the multiple path segments included in each reachable path, select from the multiple Select a reachable path from the reachable path as the current path.

According to the second aspect, or any one of the implementation manners of the second aspect above, in a seventh possible implementation manner of the path planning device, the path planning module is based on the path planning reference information and the multiple The path planning of the user strategy includes: sequentially selecting a user strategy from the plurality of user strategies as the current user strategy, until a reachable path from the source location to the destination location that satisfies a preset condition is successfully planned based on the current user strategy . In addition to the spatial distribution of the multiple user strategies mentioned above, it is also possible to implement path planning based on multiple user strategies by distributing the multiple user strategies in time.

According to the second aspect, or any one of the implementation manners of the second aspect above, in an eighth possible implementation manner of the path planning apparatus, the step of selecting one user strategy from the plurality of user strategies as the current The user strategy includes: sorting the plurality of user strategies by priority, and selecting one user strategy from the plurality of user strategies as the current user strategy in the order of the priority from high to low, or in turn Select one user policy from the multiple user policies in sequence as the current user policy.

In a third aspect, a path planning device is provided, including a memory and a processor, the memory stores computer program instructions, and the processor runs the computer program instructions to execute the first aspect or any implementation of the first aspect above The path planning method mentioned in the method.

According to the third aspect, in the first possible implementation manner of the path planning device, the device further includes: a user interface for acquiring multiple user policies input by one or more users and Update of user policy.

According to the third aspect or the first possible implementation manner of the third aspect, in the second possible implementation manner of the path planning apparatus, the user interface acquires multiple user policies input by one or more users, and The updating of the multiple user policies includes: obtaining one or more user policies selected by the one or more users from the one or more user policies suggested to the user.

According to the third aspect, or any one of the foregoing implementation manners of the third aspect, in a third possible implementation manner of the path planning apparatus, the memory is further configured to store the multiple user policies and the path Planning reference information.

According to the third aspect, or any one of the foregoing implementation manners of the third aspect, in a fourth possible implementation manner of the path planning device, the device further includes a sensor or a receiver for acquiring the path planning Reference Information. The sensor collects the path planning reference information. The receiver receives the path planning reference information.

In a fourth aspect, a computer storage medium is provided, including computer instructions, which when the computer instructions are executed by a processor, cause the path planning apparatus to execute as described in the first aspect or any one of the implementation manners of the first aspect above. The mentioned path planning method.

In a fifth aspect, a computer program product is provided. When the computer program product runs on a processor, the path planning device executes the path planning device as mentioned in the first aspect or any one of the implementations of the first aspect above. Path planning method.

In a sixth aspect, a smart car is provided, including the path planning device mentioned in the second aspect, any one of the implementations of the second aspect above, the third aspect or any one of the implementations of the third aspect above.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic diagram of a reference source on which a path planning decision is made in Embodiment 1 of the present invention.

Fig. 2 is a flowchart of a path planning method provided by Embodiment 1 of the present invention.

Fig. 3 is a flow chart of the path planning method provided by the second embodiment of the present invention.

FIG. 4 is a flowchart of a path planning method provided by Embodiment 3 of the present invention.

FIG. 5 is a schematic diagram of weights under multiple strategies of path segments determined during path planning in Embodiment 3 of the present invention.

FIG. 6 is a schematic diagram of multiple reachable paths generated during path planning in Embodiment 3 of the present invention.

FIG. 7 is a flowchart of a path planning method provided by Embodiment 4 of the present invention.

FIG. 8 is a structural block diagram of a path planning device provided by Embodiment 5 of the present invention.

FIG. 9 is a structural block diagram of a path planning device provided by Embodiment 6 of the present invention.

FIG. 10 is a structural block diagram of a path planning device provided by Embodiment 7 of the present invention.

FIG. 11 is a structural block diagram of a path planning device provided by Embodiment 8 of the present invention.

detailed description

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Different from using a single user strategy for path planning in the prior art, the path planning in the embodiments of the present invention is based on multiple user strategies, which can be applied to an in-vehicle navigation system implemented by hardware, software, or a combination of software and hardware, and can also be applied to Electronic devices such as navigators, mobile phones, portable computers, tablets or wearable devices with navigation functions.

The first embodiment of the present invention provides a path planning method, wherein the reference source on which the path planning decision is made is as shown in FIG. 1, and includes user strategy and path planning reference information. There is more than one user strategy, and one or more users can choose multiple from cost priority, safety priority, comfort priority, time priority, distance priority, or other path planning strategies that reflect user preferences. The path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions, each of which further includes a variety of path planning reference elements: for example, inherent information such as vehicle height and vehicle width can be derived from local sources. Storage; For example, historical information such as historical traffic flow and historical transit time can be sourced from local storage or received by the receiver; for example, real-time information such as lane division and current congestion can be collected by sensors in real time or received by the receiver.

2 is a flowchart of a path planning method provided by Embodiment 1 of the present invention. It can be seen that the path planning method includes: step 201, obtaining path planning reference information, where the path planning reference information includes traffic conditions, road conditions, At least one of weather conditions or vehicle conditions; step 202, obtain multiple user strategies input by one or more users; step 203, perform path planning according to the path planning reference information and the multiple user strategies.

The user strategy reflects the user’s preference for path planning strategies. One or more users can choose from the cost priority, safety priority, comfort priority, time priority, distance priority or other path planning strategies that reflect user preferences as shown in Figure 1. A. The multiple user policies may be multiple user policies of a user. For example, a user wants a path to be time- and distance-prioritized; the multiple user policies may also be multiple user policies of multiple users, for example, multiple user policies. When a user rides in a car, user A wants time first, user B wants distance first, and user C wants cost first, so the different needs of multiple users are taken into consideration by comprehensively considering time priority, distance priority and cost priority.

By using multi-strategy as a decision-making reference for route planning, user-centric intelligent route planning can be realized. When the driving environment information changes dynamically in real time, the multi-strategy route planning mechanism facilitates more flexible route adjustment and excavation of better potential. Path, the path obtained by planning is more suitable for the actual scenario, and it is also convenient to realize autonomous and dynamic switching of paths when the user's strategy changes.

Fig. 3 is a flowchart of the path planning method provided in the second embodiment of the present invention.

Steps

301 and 305 in Fig. 3 are the same as

steps

201 and 203 in Fig. 2 respectively. It can be seen that the second embodiment is relative to the implementation Example 1 has two improvements:

The first improvement is the addition of a strategy suggestion mechanism, that is, before the step of obtaining multiple user strategies input by one or more users, step 302 is further included, and one or more suggestions to the user are determined according to the path planning reference information. User strategy, and step 303, sending a suggestion message containing the one or more user strategies suggested to the user to the user, and step 304 obtaining one or more user strategies input by the user includes: obtaining the one or more user strategies. One or more user policies selected by a user from the one or more user policies suggested to the user.

Since it is difficult for users to understand the complete path planning reference information and subjective judgments are limited, the user strategy that the user wants to adopt may not be suitable for the current driving scene. By suggesting the user strategy to the user, the user strategy selected by the user can be consistent with The actual driving environment is more suitable.

The second improvement is the addition of a dynamic update mechanism, that is, after the path planning is performed according to the path planning reference information and the multiple user strategies, step 306 is further included to update the path planning reference information and monitor one or more When the user updates the multiple user policies, when the update of the path planning reference information satisfies a preset condition or the multiple user policies are updated, step 307 is executed, according to the updated path planning reference information Or at least one of the updated multiple user policies re-plans the path.

The updating the path planning reference information includes using a sensor to collect the path planning reference information, or using a receiver to receive the updated path planning reference information. The update of the one or more users to the plurality of user policies includes deleting one or more user policies of the plurality of user policies, or adding a new one or more user policies, and the new one or Multiple user policies come from one or more original users, or from one or more newly added users. When the real-time change of the path planning reference information satisfies the preset condition, for example, the current path is not the optimal path after the real-time change of the path planning reference information, or the user needs to adjust the selected user strategy, according to the updated all The path planning reference information or the updated multiple user strategies are re-executed for the path planning, so that the planned path can meet the real-time changes of the driving scene and the adjustment of the user's preferences.

The third embodiment provides a path planning method, as shown in FIG. 4, in which step 401 and step 402 are the same as step 201 and step 202 in FIG. "The path planning reference information and the multiple user strategies for path planning" are refined, including: step 403, according to the path planning reference information, it is determined that each path segment corresponds to each user in the multiple user strategies. The weight of the policy, where the weight is used to identify the traffic cost of a path segment under a user policy. For example, when the travel time of a path segment is (0,1min), (1min,2min), (2min,3min), (3min,5min) and (5min,8min) respectively, the corresponding time priority (Time The weight (Time Cost, abbreviated as TC) under the First, abbreviated as TF) strategy is 1, 2, 3, 4, and 5 respectively; the length of a path segment is (0,200m), (200m,400m), (400m) ,600m], (600m,800m], and (800m,1000m), the corresponding weights (Distance Cost, abbreviated as DC) under the Distance First (Distance First, abbreviated as DF) strategy are 1, 2, respectively 3, 4, and 5. The path planning reference information also includes a map, and the map includes multiple path segments connecting two adjacent intersections. From Figure 5, you can see the weight of the path segments under multiple strategies. Figure 5 The circles with letters in the middle represent the intersections on the map. The letters indicate the number of the intersection. "S" is the intersection closest to the source location, "D" is the intersection closest to the destination location, "A", "B", " C", "E", "F", "G", "H", "I", "J" and "K" are the intersections involved in the topology of the directed path from the source location to the destination location on the map , The arrow connection between two adjacent intersections represents the path segment, the number in parentheses on each arrow is the number of the path segment, and the equation after the colon is used to indicate that the path segment corresponds to each user in the multiple user policy The weight of the strategy. Take Figure 5, which uses two user strategies of Distance First (DF) and Time First (TF) as an example. In the figure, the distance between “S” and “A” is The text "(1):DC=6,TC=4" on the arrow line indicates that the path segment between "S" and "A" is path segment (1), which corresponds to the weight of the distance priority user strategy (Distance Cost, abbreviated as DC) is 6, and the weight corresponding to the time-first user policy (Time Cost, abbreviated as TC) is 4.

Step 404: Determine one or more reachable paths between the source location and the destination location according to the multiple user policies and the weight of each path segment corresponding to each user policy in the multiple user policies, so The reachable path includes a plurality of continuous path segments on the map, and the weight of at least one of the plurality of user policies corresponding to each path segment of the plurality of path segments satisfies the corresponding user policy. Threshold limit.

In order to take into account multiple user strategies, during path planning, by judging the weight of each path segment under each user strategy, identify and avoid path segments whose traffic cost is too high relative to the user's expectations. For example, when using the directional path topology in Figure 5 for path planning, it is assumed that the thresholds of the two user strategies, time priority and distance priority, are both 3. That is, only path segments whose weight DC does not exceed 3 or weight TC does not exceed 3. The reachable path can be composed. It can be seen that since the DC and TC of the path fragments (1) and (6) both exceed 3, they are not regarded as the constituent path fragments of the reachable path. The path fragments (8), (9) ), (14) and (15) all have only one weight (DC or TC) that meets the threshold requirement and can be used as a path segment of the reachable path. The reachable paths obtained based on this method can be seen in Fig. 6, a total of 5 reachable paths are obtained, namely S-B-E-J-K-D, S-B-E-I-D, S-B-G-I-D, S-C-G-I-D and S-C-H-D.

In addition to the above methods, the reachable path can also be determined in other ways. For example, the thresholds of DC and TC are not equal, or only path segments with a weight DC not exceeding 3 and a weight TC not exceeding 3 can form a reachable path (at this time The reachable paths in Figure 6 are only SBEID and SBGID), or the path fragments included in the limited reachable path do not exceed the threshold limit (for example, no more than 4, at this time, the reachable paths in Figure 6 are only SBEID, SBGID, SCGID, and SCHD) .

Step 405: Determine the current path from the one or more reachable paths. There are many methods for determining the current path. For example, a reachable path may be randomly selected from the multiple reachable paths as the current path, or the multiple path segments included in each reachable path may correspond to For the weight of each user policy in the plurality of user policies, a reachable path is selected from the plurality of reachable paths as the current path, or according to the number of path fragments included in each reachable path, from the Select one of the multiple reachable paths as the current route. For example, select the path with the least number of path fragments from the 5 reachable paths shown in FIG. 6, that is, path S-C-H-D as the current path. For another example, a path with the smallest sum of TC is selected from the five reachable paths shown in FIG. 6 (the reachable path including path segments whose TC does not meet the threshold requirement is not considered), that is, the path S-B-E-I-D is taken as the current path.

It can be seen that the user strategies adopted by multiple consecutive path segments on the reachable path may be different. By spatially balancing the multiple user strategies, path planning based on multiple user strategies is realized. In addition to balancing the multiple user strategies in space, it is also possible to balance the multiple user strategies in time to achieve path planning based on multiple user strategies. The fourth embodiment shown in FIG. ", the path planning methods described include:

Step 701: Obtain path planning reference information, where the path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions;

Step 702: Obtain multiple user policies input by one or more users;

Step 703: Select one user policy from the multiple user policies as the current user policy in sequence, until a reachable path from the source location to the destination location that satisfies a preset condition is successfully planned based on the current user policy.

The step of sequentially selecting a user policy from the plurality of user policies as the current user policy includes: sorting the plurality of user policies in order of priority, and sequentially descending from the plurality of user policies according to the order of priority from high to low. Select one user policy as the current user policy among the user policies, or select one user policy from the multiple user policies as the current user policy in turn. For example, a car is shared by three users. The three users have different preferences. The selected user strategies are time priority, cost priority, and distance priority, and each of the three users has three options for time, cost, and distance. All parameters have acceptable limits; or there may be another situation where the car is taken by a user who chooses the three user strategies of time priority, cost priority, and distance priority, and for time, cost, and distance All three parameters have acceptable limits. In short, for the executor of the fourth embodiment, the multiple user policies obtained include time priority, cost priority, and distance priority, and the one or more users’ policies for each of the multiple user policies are obtained. The acceptable range is limited, and the priority of the multiple user policies is determined in descending order of time priority, cost priority, and distance priority for the scenarios described in the above example. First, the path planning is based on the time priority strategy, but the cost or distance of the path planned based on the time priority strategy exceeds the acceptable range limit preset by at least one user, that is, the time priority strategy cannot plan a path that meets the preset conditions. Reachable path, and then plan the path based on the cost priority strategy. If the planned path meets the acceptable range limits for the three parameters of time, cost, and distance for each of the one or more users, then The route planned based on the cost priority strategy is taken as the current route. It can be seen that when a user strategy cannot plan a reachable path that satisfies the preset conditions, the method described in the fourth embodiment can switch strategies autonomously and quickly, and select other user strategies from the multiple user strategies to re-plan the path to avoid In addition to the "dead waiting" state, manual switching operations are also avoided. While taking into account the needs of multi-user strategies, it has better dynamic adaptability.

The fifth embodiment of the present invention provides a path planning device, as shown in FIG. 8, including: a path planning reference information acquisition module 801, configured to acquire path planning reference information, the path planning reference information includes traffic conditions, road conditions, At least one of weather conditions or vehicle conditions; a user strategy acquisition module 802, configured to acquire multiple user strategies input by one or more users; a path planning module 803, configured based on the path planning reference information and the multiple User strategy for path planning.

By using multi-strategy as a decision reference for path planning, user-centric intelligent path planning can be realized, and when the driving environment information changes in real time, the multi-strategy path planning mechanism is convenient to adjust the path more flexibly and dig out better ones. Potential path, the path obtained by planning is more suitable for the actual scene.

Fig. 9 is a structural block diagram of a path planning device provided in the sixth embodiment of the present invention. It can be seen that, compared with the fifth embodiment, the path planning device shown in the sixth embodiment further includes: a user strategy suggestion module 904 for The path planning reference information determines one or more user strategies suggested to the user; the sending module 905 is configured to send to the user a suggestion message containing the one or more user strategies suggested to the user; the user strategy acquisition module acquires The multiple user policies input by one or more users include: obtaining one or more user policies selected by the one or more users from the one or more user policies suggested to the user. Because it is difficult for users to understand the complete path planning reference information and the limitations of subjective judgment, the user strategy that the user hopes to adopt may not be suitable for the current driving scene. By suggesting the user strategy to the user, the user strategy selected by the user can be matched with The actual driving environment is more suitable.

In addition, the path planning module 903 in FIG. 9 may adopt the aforementioned method of balancing the multiple user strategies in time to implement path planning based on multiple user strategies. Specifically, the path planning module 903 sequentially starts from the multiple user strategies. A user strategy is selected from the user strategy as the current user strategy, until a reachable path from the source location to the destination location that satisfies the preset condition is successfully planned based on the current user strategy. The step of sequentially selecting a user policy from the plurality of user policies as the current user policy includes: sorting the plurality of user policies in order of priority, and sequentially descending from the plurality of user policies according to the order of priority from high to low. One user policy is selected as the current user policy among the user policies; or, one user policy is selected from the plurality of user policies as the current user policy in turn according to the order of turns.

FIG. 10 is a structural block diagram of a path planning device provided by Embodiment 7 of the present invention. It can be seen that, with respect to the sixth embodiment, the path planning device 1003 shown in the seventh embodiment achieves path planning based on multiple user strategies by spatially balancing the multiple user strategies, and the path planning module 1003 further includes: weight The determining module 1006 is configured to determine, according to the path planning reference information, the weight of each path segment corresponding to each user policy in the plurality of user policies, and the weight is used to identify the passage of a path segment under a user policy cost. The reachable path determination module 1007 is configured to determine one or more values between the source location and the destination location according to the multiple user policies and the weight of each path segment corresponding to each user policy in the multiple user policies. A reachable path, the reachable path includes a plurality of continuous path fragments on the map, and each path fragment in the plurality of path fragments corresponds to at least one of the plurality of user policies The weight meets the threshold limit of the corresponding user policy. The current path determination module 1008 is configured to determine the current path from the one or more reachable paths. There are multiple ways to determine the current path, for example: randomly selecting a reachable path from the multiple reachable paths as the current path; or, corresponding to the multiple path segments included in each reachable path Based on the weight of each user policy in the plurality of user policies, a reachable path is selected from the plurality of reachable paths as the current path; or, according to the plurality of path segments included in each reachable path And select a reachable path from the plurality of reachable paths as the current path.

Only one or more of the modules in Figures 8-10 can be implemented in software, hardware, firmware, or a combination thereof. The software or firmware includes but is not limited to computer program instructions or codes, and can be executed by a hardware processor. The hardware includes, but is not limited to, various integrated circuits, such as a central processing unit (CPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

Figure 11 is a structural block diagram of a path planning device provided by Embodiment 8 of the present invention. The path planning device can be a component of an in-car navigation system, or a navigator, mobile phone, portable computer, or tablet with navigation functions. Electronic devices such as wearable devices. As shown in FIG. 11, the path planning device includes:

A memory 1102, where the memory 1102 stores computer program instructions, the multiple user strategies, and the path planning reference information. The path planning reference information stored in the memory 1102 includes inherent information such as vehicle height and vehicle width, and historical information such as historical traffic volume and historical transit time.

The processor 1101 is configured to run the computer program instructions to perform the operations described in any one of the first to the fourth embodiments. The processor 1101 includes, but is not limited to, various types of CPUs, DSPs, microcontrollers, microprocessors, or artificial intelligence processors.

The user interface 1103 is used to obtain multiple user policies input by one or more users and to update the multiple user policies. The user interface acquiring multiple user policies input by one or more users and updating the multiple user policies includes: acquiring the one or more users from the one or more user policies suggested to the user One or more user policies selected. The user interface 1103 includes a display, a touch screen, a mouse, a keyboard, a voice input device, or a somatosensory input device.

The sensor 1104 is used to collect the path planning reference information, for example, to collect lane divisions and current congestion conditions. The sensor 1104 includes, but is not limited to, a temperature sensor, a humidity sensor, a height sensor, a pressure sensor, a light sensor, a speed sensor, a gravity sensor, an acceleration sensor, a camera, a lidar, an ultrasonic radar, or a millimeter wave radar.

The receiver 1105 is configured to receive the path planning reference information. The path planning reference information received by the receiver 1105 includes historical information such as historical traffic volume and historical transit time, and real-time information such as lane division and current congestion. The manner in which the receiver 1105 receives the path planning reference information includes but is not limited to 2G (second-generation mobile communication technology), 3G (third-generation mobile communication technology), 4G (fourth-generation mobile communication technology), and 5G ( Fifth-generation mobile communication technology), Wifi (wireless local area network), Wimax (Worldwide Interoperability for Microwave Access), Bluetooth (Bluetooth communication technology), ZigBee (Zigbee communication technology), optical transmission, optical fiber transmission, cable Wired or wireless transmission methods such as transmission, satellite communication or infrared transmission.

The above-mentioned embodiments of the present invention can be used in both vehicles and devices with path planning functions such as portable electronic devices, communication devices, navigation devices, etc. The application scenarios include but are not limited to assisted driving and unmanned driving.

Those skilled in the art can clearly understand that the descriptions of the various embodiments provided in the present application can be referred to each other for convenience and conciseness of the description. For example, the functions of the various devices and equipment provided in the embodiments of the present application and the steps performed can be With reference to the related description of the method embodiments of this application, each method embodiment and each device embodiment may also refer to each other.

Those skilled in the art can understand that all or part of the steps in the foregoing method embodiments can be implemented by a program instructing relevant hardware. The aforementioned program can be stored in a computer readable storage medium. When the program is executed, the execution includes all or part of the steps of the foregoing method embodiments; and the foregoing storage medium includes: ROM, RAM, magnetic disk, or optical disk and other media that can store program codes.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center. Transmission to another website site, computer, server or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media. The usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

In the several embodiments provided in this application, it should be understood that the disclosed device and method can be implemented in other ways within the scope of this application. For example, the above-described embodiments are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not implemented. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. . Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.

In addition, the described devices and methods and schematic diagrams of different embodiments can be combined or integrated with other systems, modules, technologies, or methods without departing from the scope of the present application. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electronic, mechanical or other forms.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application. Should be covered within the scope of protection of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A path planning method is characterized in that it includes:

Acquiring path planning reference information, where the path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions;

Obtain multiple user policies entered by one or more users;

Perform path planning according to the path planning reference information and the multiple user strategies.
The method according to claim 1, wherein the user strategy includes distance priority, time priority, safety priority, comfort priority or expense priority.
The method according to claim 1 or 2, wherein the method further comprises:

Update the path planning reference information;

Obtaining updates of one or more users to the multiple user policies;

Perform the path planning again according to the updated path planning reference information or at least one of the updated multiple user policies.
The method according to any one of claims 1-3, wherein the method further comprises:

Determining one or more user strategies suggested to the user according to the path planning reference information;

Sending to the user a suggestion message containing the one or more user policies suggested to the user;

The obtaining multiple user policies input by one or more users includes: obtaining one or more user policies selected by the one or more users from the one or more user policies suggested to the user.
The method according to any one of claims 1 to 4, wherein the path planning reference information further includes a map, the map includes a plurality of path fragments connecting two adjacent intersections, and the path according to the path The planning reference information and the multiple user strategies for path planning include:

Determining, according to the path planning reference information, the weight of each path segment corresponding to each of the multiple user policies, where the weight is used to identify the traffic cost of a path segment under one user policy;

Determine one or more reachable paths between the source location and the destination location according to the multiple user policies and the weight of each path segment corresponding to each user policy in the multiple user policies. The path includes multiple path segments that are continuous on the map;

Determine the current path from the one or more reachable paths.
The method according to claim 5, wherein the weight of at least one user policy of the plurality of user policies corresponding to each path segment of the plurality of path segments meets the threshold limit of the corresponding user policy.
The method according to claim 5, wherein determining the current path from the plurality of reachable paths comprises:

Randomly selecting a reachable path from the plurality of reachable paths as the current path;

Or, according to the weight of the multiple path segments included in each reachable path corresponding to each user policy in the multiple user policies, one of the multiple reachable paths is selected as the current path ；

Or, according to the number of the multiple path segments included in each reachable path, one of the multiple reachable paths is selected as the current path.
The method according to any one of claims 1 to 4, wherein the path planning according to the path planning reference information and the multiple user strategies comprises:

One user policy is selected from the plurality of user policies in turn as the current user policy, until a reachable path from the source location to the destination location that satisfies a preset condition is successfully planned based on the current user policy.
The method according to claim 8, wherein the step of sequentially selecting a user policy from the plurality of user policies as the current user policy comprises:

Sorting the plurality of user policies by priority, and sequentially selecting one user policy from the plurality of user policies as the current user policy in the order of the priority from high to low,

Alternatively, one user policy is selected from the plurality of user policies in turn as the current user policy.
A path planning device is characterized in that it comprises:

A path planning reference information acquisition module, configured to acquire path planning reference information, where the path planning reference information includes at least one of traffic conditions, road conditions, weather conditions, or vehicle conditions;

The user strategy acquisition module is used to acquire multiple user strategies entered by one or more users;

The path planning module is configured to perform path planning according to the path planning reference information and the multiple user strategies.
The device according to claim 10, wherein the user strategy includes distance priority, time priority, safety priority, comfort priority or expense priority.
The device according to claim 10 or 11, characterized in that:

The path planning reference information acquisition module is also used to update the path planning reference information;

The user policy obtaining module is further configured to obtain updates of one or more users to the multiple user policies;

The path planning module is further configured to perform the path planning again according to at least one of the updated path planning reference information or the updated multiple user policies.
The device according to any one of claims 10-12, wherein the device further comprises:

A user strategy suggestion module, configured to determine one or more user strategies suggested to the user according to the path planning reference information;

A sending module, configured to send a suggestion message containing the one or more user policies suggested to the user to the user;

The user policy acquiring module acquiring multiple user policies input by one or more users includes: acquiring one or more user policies selected by the one or more users from the one or more user policies suggested to the user .
The device according to any one of claims 10-13, wherein the path planning reference information further includes a map, the map includes a plurality of path segments connecting two adjacent intersections, and the path planning module includes :

The weight determination module is configured to determine, according to the path planning reference information, the weight of each path segment corresponding to each user policy in the plurality of user policies, and the weight is used to identify the passage of a path segment under a user policy cost;

The reachable path determination module is configured to determine one or more paths between the source location and the destination location according to the multiple user policies and the weight of each path segment corresponding to each user policy in the multiple user policies A reachable path, where the reachable path includes multiple path segments that are continuous on the map;

The current path determination module is used to determine the current path from the one or more reachable paths.
The method according to claim 14, wherein the weight of at least one user policy of the plurality of user policies corresponding to each path segment of the plurality of path segments meets the threshold limit of the corresponding user policy.
The device according to claim 14, wherein the current path determination module determining the current path from the one or more reachable paths comprises:

Randomly selecting a reachable path from the plurality of reachable paths as the current path;

Or, according to the weight of the multiple path segments included in each reachable path corresponding to each user policy in the multiple user policies, one of the multiple reachable paths is selected as the current path ；

Or, according to the number of the multiple path segments included in each reachable path, one of the multiple reachable paths is selected as the current path.
The device according to any one of claims 10-13, wherein the path planning module performing path planning according to the path planning reference information and the multiple user strategies comprises:

One user policy is selected from the plurality of user policies in turn as the current user policy, until a reachable path from the source location to the destination location that satisfies a preset condition is successfully planned based on the current user policy.
The apparatus according to claim 17, wherein the sequentially selecting a user policy from the plurality of user policies as the current user policy comprises:

Sorting the plurality of user policies by priority, and sequentially selecting one user policy from the plurality of user policies as the current user policy in the order of the priority from high to low,

Alternatively, one user policy is selected from the plurality of user policies in turn as the current user policy.
A path planning device, characterized by comprising a memory and a processor, the memory storing computer program instructions, and the processor running the computer program instructions to perform the operation of any one of claims 1-9.
The device according to claim 19, wherein the device further comprises:

The user interface is used to obtain multiple user policies input by one or more users and to update the multiple user policies.
The device according to claim 20, wherein the user interface acquiring multiple user policies input by one or more users and updating the multiple user policies comprises: acquiring the one or more users from One or more user policies selected from the one or more user policies suggested to the user.
The device according to any one of claims 19-21, wherein the memory is further configured to store the multiple user policies and the path planning reference information.
The device according to any one of claims 19-22, wherein the device further comprises a sensor or a receiver for obtaining the path planning reference information.
A computer storage medium, characterized by comprising computer instructions, when the computer instructions are executed by a processor, cause the path planning device to execute the method according to any one of claims 1-9.
A computer program product, characterized in that, when the computer program product runs on a processor, the path planning device is caused to execute the method according to any one of claims 1-9.
A smart car, characterized by comprising the path planning device according to any one of claims 10-23.