CN115727862A - Control method of unmanned vehicle and its control system, unmanned vehicle and readable storage medium - Google Patents

Abstract

This application discloses a control method for an unmanned vehicle. The method includes: acquiring the user's ride request, the user's current location and road information; determining at least one alternative boarding point according to the user's ride request and the user's current location; performing route planning according to the road information and the alternative boarding point to obtain at least one Alternative routes: Determine the estimated passing time of each alternative route to determine the target boarding point. In the control method of the unmanned vehicle of the present application, the user can select a target route from the alternative routes to control the unmanned vehicle to drive to the target boarding point, and the way of meeting people and vehicles is flexible, which improves the efficiency of meeting people and vehicles . The application also discloses a control system of the unmanned vehicle, the unmanned vehicle and a readable storage medium.

Description

Control method of unmanned vehicle and its control system, unmanned vehicle and readable storage medium

technical field

The present application relates to the technical field of smart cars, and in particular to a control method of an unmanned vehicle and its control system, an unmanned vehicle and a readable storage medium.

Background technique

At present, after calling an unmanned taxi, the user can only get on the bus from a fixed station, and it often takes a long time to reach the boarding point of the unmanned taxi. Therefore, in the process of actually taking the unmanned taxi, how do people It is an urgent problem to be solved to improve the efficiency of people-vehicle meeting by making the way of car meeting more flexible.

Contents of the invention

In view of this, the present invention aims to solve one of the problems in the related art at least to a certain extent. Therefore, the purpose of the present application is to provide a control method of an unmanned vehicle and its control system, an unmanned vehicle and a readable storage medium.

An embodiment of the present application provides a control method for an unmanned vehicle. The control method of the unmanned vehicle includes: obtaining the user's ride request, the user's current location and road information; determining at least one alternative boarding point according to the user's ride request and the user's current location; according to the road information Performing route planning with the candidate boarding points to obtain at least one candidate route; determining the estimated passing time of each candidate route to determine the target boarding point.

In some embodiments, the determining at least one candidate boarding point according to the user's ride request and the user's current location includes: determining the original boarding point according to the user's ride request; When the boarding point is located behind the U-turn driving section and/or the congested road section, select a replacement point on the non-turning driving section and/or the non-congested road section; calculate the user's current location or the original boarding point to the replacement point The first walking duration, and the first driving duration of the unmanned vehicle through the U-turn driving section and/or the congested road section; when the first walking duration is less than the first driving duration, the The replacement point is added as the alternative boarding point.

In some implementations, the determining at least one candidate boarding point according to the user's ride request and the user's current location includes: determining the original boarding point and the target point according to the user's ride request; When the U-turn driving section and/or the congested road section are located behind the original boarding point, select a replacement point on the non-turning driving section and/or the non-congested road section; calculate the second walk from the user's current position to the replacement point duration, the second travel duration of the unmanned vehicle from the replacement point to the target point, and the third travel duration of the unmanned vehicle from the original boarding point to the target point; If the second walking time plus the second driving time is less than the third driving time, the replacement point is added as the candidate boarding point.

In some implementations, the determining at least one candidate boarding point according to the user's ride request and the user's current location includes: acquiring historical boarding point data of the user in the area corresponding to the user's current location; performing density analysis on the historical boarding point data to obtain commonly used boarding points; determining the candidate boarding points according to the commonly used boarding points.

In some embodiments, the performing density analysis on the historical boarding point data to obtain commonly used boarding points includes: determining the latitude and longitude of the historical boarding point data to draw a corresponding coordinate map; Aggregating the historical boarding point data according to a preset range to obtain a boarding point cluster; determining the common boarding point according to the boarding point cluster.

In some embodiments, the determining the common boarding point according to the boarding point cluster includes: using a cluster analysis algorithm to iteratively aggregate the historical boarding point data corresponding to the boarding point cluster The position of the center of mass is obtained; the position of the center of mass is used as the common boarding point.

In some embodiments, the iterative aggregation of the historical boarding point data corresponding to the boarding point cluster by using a clustering analysis algorithm to obtain the centroid position includes: obtaining data corresponding to the historical boarding point data Creation time; determine the weighted value of the corresponding historical boarding point data according to the data creation time; use the cluster analysis algorithm to analyze the historical boarding point corresponding to the boarding point cluster according to the weighted value The data is iteratively aggregated to obtain the centroid position.

In some implementations, the control method includes: automatically calculating the optimal solution to determine the target route when no user operation on the alternative route is received; sending a route confirmation message to notify the user and Give directions.

In some implementations, after the acquisition of the user's ride request, the user's current location and road information, the control method includes: acquiring the user's route preference; Determining at least one candidate boarding point includes: determining at least one candidate boarding point according to the user's route preference, the user's ride request, and the user's current location.

In some implementations, the acquiring the user's route preference includes: sending preference selection information to the user's mobile terminal; receiving the user's operation on the preference selection information to determine the user's route preference.

In some implementations, the acquiring user route preferences includes: acquiring user historical travel information, the historical travel information including preset user tags; analyzing the historical travel information according to a word frequency calculation algorithm to obtain the user route preference.

In some implementations, the preset user tags are learned according to a neural network.

In some embodiments, the control method includes: when the unmanned vehicle travels to the target boarding point within a first preset distance, acquiring the surrounding environment information of the target boarding point; If the surrounding environment information of the target boarding point is not suitable for the vehicle to stop, the target boarding point will be re-determined and the user will be notified.

In some embodiments, after the unmanned vehicle reaches the target boarding point, the control method includes: when the distance between the user and the target boarding point is greater than a second preset distance or the waiting time is longer than In the case of a preset time, the unmanned vehicle is controlled to select a parking space near the target boarding point to stop.

The present application also provides a control system for an unmanned vehicle. The control system of the unmanned vehicle includes: an acquisition module, a boarding point determination module, a route planning module, a duration determination module, a route determination module and a control module. The acquiring module is used to acquire the user's ride request, the user's current location and road information; the boarding point determination module is used to determine at least one alternative boarding point according to the user's ride request and the user's current location; The route planning module is configured to perform route planning according to the road information and the alternative boarding points to obtain at least one alternative route; the determination module is configured to determine the estimated passing time of each alternative route to determine the The above target boarding point.

The present application also provides an unmanned vehicle. The unmanned vehicle includes a processor and a memory, the memory is used to store a computer program, and the processor implements the control method described in any one of the above embodiments when executing the computer program.

The present application also provides a non-volatile computer-readable storage medium of the computer program. When the computer program is executed by one or more processors, the control method described in any one of the above embodiments is realized.

In the control method of the unmanned vehicle of the present application, the user can select a target route from the alternative routes to control the unmanned vehicle to drive to the target boarding point, and the way of meeting people and vehicles is flexible, which improves the efficiency of meeting people and vehicles .

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

FIG. 1 is a schematic flow diagram of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 2 is a schematic structural diagram of a control system of an unmanned vehicle in some embodiments of the present application;

FIG. 3 is a schematic diagram of a scene of a control method for an unmanned vehicle in some embodiments of the present application;

FIG. 4 is a schematic diagram of a scene of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 5 is a schematic diagram of the scene of the control method of the unmanned vehicle in some embodiments of the present application;

Fig. 6 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

7 is a schematic structural diagram of a boarding point determination module in the control system of an unmanned vehicle according to some embodiments of the present application;

Fig. 8 is a schematic diagram of the scene of the control method of the unmanned vehicle in some embodiments of the present application;

FIG. 9 is a schematic flow diagram of a control method for an unmanned vehicle in some embodiments of the present application;

FIG. 10 is a schematic diagram of a scene of a control method for an unmanned vehicle in some embodiments of the present application;

FIG. 11 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 12 is a schematic structural diagram of the determination unit in the boarding point determination module in some embodiments of the present application;

FIG. 13 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 14 is a schematic structural diagram of the analysis unit in the determination unit in some embodiments of the present application;

FIG. 15 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

FIG. 16 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 17 is a schematic structural diagram of a boarding point determination unit commonly used in the analysis unit of some embodiments of the present application;

FIG. 18 is a schematic flowchart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 19 is a schematic structural diagram of a control system of an unmanned vehicle according to some embodiments of the present application;

FIG. 20 is a schematic flowchart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 21 is a schematic flowchart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 22 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

Figure 23 is a schematic diagram of the formula of the TF-IDF algorithm in some embodiments of the present application;

Fig. 24 is a schematic flowchart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 25 is a schematic structural diagram of the control module in the control system of the unmanned vehicle in some embodiments of the present application;

Fig. 26 is a schematic flow chart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 27 is a schematic structural diagram of the control system of the unmanned vehicle in some embodiments of the present application;

Fig. 28 is a schematic flowchart of a control method for an unmanned vehicle in some embodiments of the present application;

Fig. 29 is a schematic structural diagram of a control system of an unmanned vehicle in some embodiments of the present application;

Figure 30 is a schematic structural view of an unmanned vehicle in some embodiments of the present application;

Fig. 31 is a schematic structural diagram of a computer-readable storage medium in some embodiments of the present application.

Detailed ways

Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, are only for explaining the present application, and should not be construed as limiting the present application.

In the description of the present application, it should be understood that the terms "first" and "second" are used for description purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of said features. In the description of the present application, "plurality" means two or more, unless otherwise clearly and specifically defined.

In the description of this application, it should be noted that unless otherwise specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection. Connected, or integrally connected; may be mechanically connected, may be electrically connected or may communicate with each other; may be directly connected, or indirectly connected through an intermediary, may be internal communication between two components or interaction between two components relation. Those of ordinary skill in the art can understand the specific meanings of the above terms in this application according to specific situations.

The following disclosure provides many different implementations or examples for implementing different structures of the present application. To simplify the disclosure of the present application, components and arrangements of specific examples are described below. Of course, they are examples only and are not intended to limit the application. Furthermore, the present application may repeat reference numerals and/or reference letters in various instances, such repetition is for simplicity and clarity and does not in itself indicate a relationship between the various embodiments and/or arrangements discussed.

Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, are only for explaining the present application, and should not be construed as limiting the present application.

At present, after calling an unmanned taxi, the user can only get on the bus from a fixed station, and it often takes a long time to reach the boarding point of the unmanned taxi. Therefore, in the process of actually taking the unmanned taxi, how do people It is an urgent problem to be solved to improve the efficiency of people-vehicle meeting by making the way of car meeting more flexible.

In view of this, please refer to FIG. 1 , the present application provides a control method for an unmanned vehicle. The control methods of unmanned vehicles include:

01: Get the user's ride request, user's current location and road information;

02: Determine at least one alternative boarding point according to the user's ride request and the user's current location;

03: Perform route planning based on road information and alternative boarding points to obtain at least one alternative route;

04: Determine the estimated passing time of each alternative route to determine the target boarding point.

Please refer to FIG. 2 , the present application also provides a control system 10 for an unmanned vehicle. The control system 10 of the unmanned vehicle includes: an acquisition module 11 , a boarding point determination module 12 , a route planning module 13 and a determination module 14 . The control system 10 of the unmanned vehicle can be internally connected to the unmanned vehicle, or it can be a control device externally connected to the unmanned vehicle. In this application, the control system 10 of the unmanned vehicle is internally connected to the unmanned vehicle as an example for illustration. The control system 10 of the unmanned vehicle can also be a part of the online booking platform of the unmanned vehicle.

Step 01 can be realized by the acquisition module 11 , step 02 can be realized by the boarding point determination module 12 , step 03 can be realized by the route planning module 13 , and step 04 can be realized by the determination module 14 . That is, the acquisition module 11 is used to acquire the user's ride request, the user's current location and road information. The boarding point determination module 12 is used to determine at least one alternative boarding point according to the user's ride request and the user's current location. The route planning module 13 is used for performing route planning according to road information and alternative boarding points to obtain at least one alternative route. The determination module 14 is used to determine the estimated passing time of each alternative route to determine the target boarding point.

Specifically, firstly, the control system 10 of the unmanned vehicle can obtain the user's ride request, and can determine the user's current location (such as point O in Figure 3 or Figure 4 and Figure 5) according to the user's ride request, and can The current location and the location of the unmanned vehicle itself can determine the road information near the boarding point of the unmanned vehicle. For example, if the user’s ride request is to take an unmanned vehicle from point A to point B, then the area near point A is the boarding point of the unmanned vehicle, and the road information between the area near point A and point O can be obtained, and the road information Including vehicle congestion on the roads near point A, and road information such as whether it is necessary to make a U-turn, turn, and pass through in the past.

Then, at least one candidate boarding point is determined according to the user's ride request and the user's current location. At least one alternative boarding point means that there may be one alternative boarding point A1 or multiple alternative boarding points A2, A3, A4... near the area of point A.

When there is only one alternative boarding point A1, multiple alternative routes can be obtained through route planning based on the road information and the target boarding point, as shown in Figure 3, three alternative routes A1O1, A1O2, A1O3.

When there are multiple alternative boarding points, for example, there are 4 alternative boarding points A2, A3, A4, and A5, the control system of the unmanned vehicle can perform route planning according to multiple target boarding points to obtain the One or more alternative routes corresponding to the target boarding point, so that multiple alternative routes can be obtained.

In one example, each candidate boarding point corresponds to planning only one candidate route, that is, the number of candidate boarding points is the same as the number of candidate routes. For example, as shown in Figure 4, the alternative route corresponding to the alternative boarding point A2 can be one, which is the alternative route A201, and the alternative route corresponding to the alternative boarding point A3 can be one, which is the alternative route A3O1, there may be one alternative route corresponding to the alternative boarding point A4, which is the alternative route A4O1, and there may be one alternative route corresponding to the target boarding point A5, which is the alternative route A5O1. At this time, four target boarding points A2, A3, A4 and A5 are route-planned to obtain four alternative routes A2O1, A3O1, A4O1 and A5O1.

In another example, each alternative boarding point can be correspondingly planned to obtain multiple alternative routes. As shown in Figure 5, for example, there may be three alternative routes corresponding to the alternative boarding point A2, which are respectively the alternative routes A2O2, A2O3 and A2O4, and there may also be three alternative routes corresponding to the alternative boarding point A3 The alternative routes are alternative routes A3O2, A3O3 and A3O4 respectively, and there may be three alternative routes corresponding to the alternative boarding point A4, which are respectively the alternative routes A4O2, A4O3 and A4O4, and the alternative boarding point A4 There may also be three alternative routes corresponding to A5, which are alternative routes A5O2, A5O3, and A5O4.

In other embodiments of the present application, when there are multiple candidate boarding points, one candidate route can be obtained by planning the alternative target boarding points, and multiple candidate routes can be obtained by planning the remaining candidate boarding points. The planning of the selected route is determined according to the actual road conditions.

Then, determine the estimated passing time of each alternative route to determine the target boarding point. Specifically, determining the estimated passing time of each alternative route to determine the target boarding point may first determine the estimated passing time of each alternative route to send the alternative route and the estimated passing time to the user's mobile terminal, and then receive the user's information about the alternative route. The operation of the route determines the target route to determine the target pick-up point. Finally, the unmanned vehicle can be controlled to drive along the target route to the corresponding target boarding point.

In detail, the estimated passing time of each alternative route can be calculated and determined according to the distance of each alternative route and the real-time congestion situation of the vehicle combined with the driving speed of the unmanned vehicle. For example, as shown in FIG. 3 , the estimated passage times of the three alternative routes A1O1, A1O2, and A1O3 are 4 minutes, 5 minutes, and 6 minutes, respectively. Among them, the alternative route A1O3 is the main traffic road, and the traffic flow is heavy and congested. Therefore, the estimated passing time of the alternative route A1O3 is the longest, with a duration of 6 minutes, including the expected congestion time of 2 minutes. Alternative route A1O2 may require the unmanned vehicle to turn around or the unmanned vehicle is far away from the user's location, so the estimated passing time of the alternative route A1O2 is longer; the alternative route A1O1 may not require the unmanned vehicle to turn around to be a straight section or the unmanned vehicle The distance to the user's location is relatively short, so the estimated passing time of the alternative route A1O1 is the shortest.

Next, the control system 10 of the unmanned vehicle may receive the user's operation on the alternative route to determine the target route. For example, the alternative route A1O1 with the shortest expected passing time in FIG. 3 is selected as the target route, so that the target boarding point is determined to be point A1. The user's operation on the alternate route may refer to that the user touches a certain alternate route with a finger after viewing the alternate route and the corresponding estimated passing time on the user's mobile terminal (such as mobile phone, smart bracelet, computer and other mobile devices). Select a route as the target route, or use the language function to select an alternative route as the target route.

Finally, the control system 10 of the unmanned vehicle can control the unmanned vehicle to travel along the target route to the corresponding target boarding point. For example, the control system 10 of the unmanned vehicle may control the unmanned vehicle to travel along the target route A1O1 to the corresponding target boarding point A1.

The control method of the unmanned vehicle of the present application can determine at least one alternative boarding point according to the user's ride request and the user's current position, and then carry out route planning according to the road information and the alternative boarding point to at least one alternative route, and determine The estimated passing time of each alternative route is used to determine the target boarding point, which can make the meeting between the user and the unmanned vehicle more flexible and improve the efficiency of the meeting between people and vehicles.

Referring to FIG. 6, in some embodiments, step 02 includes:

021: Determine the original boarding point according to the user's ride request;

022: When the original boarding point is located behind the U-turn road section and/or the congested road section, select a replacement point on the non-turn-driving section and/or the non-congested road section;

023: Calculate the first walking time from the user's current location or the original boarding point to the replacement point, and the first driving time of the unmanned vehicle through the U-turn section and/or the congested section;

024: When the first walking time is shorter than the first driving time, add the replacement point as an alternative boarding point.

Please refer to FIG. 7 , in some embodiments, the boarding point determination module 12 includes a determination unit 121 , a replacement point selection unit 122 , a duration calculation unit 123 and a boarding point addition unit 124 .

Step 021 can be implemented by the determination unit 121 , step 022 can be implemented by the replacement point selection unit 122 , step 023 can be implemented by the duration calculation unit 123 , and step 024 can be implemented by the boarding point addition unit 124 . That is to say, the determination unit 121 is used to determine the original boarding point according to the user's ride request; the replacement point selection unit 122 is used to replace the original boarding point when the original boarding point is located on the U-turn road section and/or behind the congested road section, and then the original boarding point is not turned around. Road section and/or non-congested road section select replacement point; Duration calculation unit 123 is used to calculate the user's current position or the first walking time from the original boarding point to the replacement point, and the first walking time of the unmanned vehicle through the U-turn driving section and/or the congested road section. - Duration of travel; boarding point addition unit 124 is used to add a replacement point as an alternative boarding point when the first walking duration is shorter than the first driving duration.

Specifically, for example, as shown in Figure 8, the user's ride request is to take an unmanned vehicle from point A to point B. If the original boarding point determination unit determines that point A1 near point A is the original boarding point, then the original boarding point When the point A1 is located behind the U-turn road section and/or the congested road section, that is, when the unmanned vehicle needs to go through the U-turn section and/or the congested road section to reach the original boarding point A1, correspondingly, it can be Select replacement points for driving and/or non-congested road segments. Among them, there are three situations in which the unmanned vehicle needs to go through the U-turn road section and/or the congested road section to reach the original boarding point A1: the unmanned vehicle only needs to go through the U-turn section to reach the original boarding point A1; To reach the original boarding point A1, it only needs to go through the congested road section; to reach the original boarding point A1, the unmanned vehicle needs to go through the U-turn driving section and the congested road section.

In this application, an unmanned vehicle needs to go through a U-turn driving section and a congested road section to reach the original boarding point A1 as an example, that is, as shown in FIG. Therefore, the new alternative boarding point C1 point that can be selected is a road section position close to the unmanned vehicle outside the U-turn driving section (ab section) or the congested road section (cd section). In addition, by calculating whether the first walking time of the user from the user's current location to point C1 is less than the first driving time of the unmanned vehicle turning around and passing through the congested road section, if the first walking time is less than the first driving time, then The new candidate boarding point C1 can be selected as the replacement point. Or, when the user has arrived at the original boarding point A1, but the unmanned vehicle has not yet arrived at the original boarding point A1, the first walking time of the user from the original boarding point to the new alternative boarding point C1 is calculated to be less than none When people and vehicles complete a U-turn and pass the first driving time of the congested road section, the new alternative boarding point C1 can be temporarily selected as the replacement point.

To reach the original boarding point A1, the unmanned vehicle only needs to go through the U-turn driving section and the congested road section to select a replacement point for boarding, and the unmanned vehicle needs to go through the U-turn driving section and the congested road section to reach the original boarding point A1 The principle of the plan to select a replacement point for boarding is the same, but the calculated first driving time is different. Specifically, if the unmanned vehicle arrives at the original boarding point A1 and only passes through the U-turn section, it only needs to calculate the first driving time after the unmanned vehicle completes the U-turn; Calculate the first driving time after the unmanned vehicle passes through the congested road section. Correspondingly, compare the first driving time with the first walking time from the user's current location to the selected new boarding point, if the first walking time is shorter than the first driving time, then the selected new boarding point can be used as the replacement point.

In one example, the control system 10 of the unmanned vehicle calculates the first walking time from the user's current position O to the replacement point C1 through the duration calculation unit 123 as 2.5 minutes, or the first walking time from the original boarding point A1 to the replacement point C1 A walk is 2 minutes long. In addition, the control system 10 of the unmanned vehicle can also calculate the first driving duration of the unmanned vehicle through the U-turn section and/or the congested section through the duration calculation unit 123, for example, in FIG. The first travel time of the road section is 6 minutes. At this time, the first walking time (2 minutes or 2.5 minutes) is less than the first driving time (6 minutes), so the replacement point C1 can be added as an alternative boarding point, that is, the user can choose from the user's current Position O or walk from the original boarding point A1 to the replacement point C1 to get on the bus, the unmanned vehicle does not need to go through the U-turn section or the congested road section to reach the boarding point, which shortens the time for people and vehicles to meet, and the way of people and vehicles to meet is flexible , improving the efficiency of people and vehicles meeting.

Referring to Figure 9, in some embodiments, step 02 includes:

025: Determine the original boarding point and target point according to the user's ride request;

026: When the U-turn driving section and/or the congested road section is located behind the original boarding point, select a replacement point on the non-turning driving section and/or the non-congested road section;

027: Calculate the second walking time from the user's current location to the replacement point, the second driving time of the unmanned vehicle from the replacement point to the target point, and the third driving time of the unmanned vehicle from the original boarding point to the target point;

028: When the second walking time plus the second driving time is less than the third driving time, add the replacement point as an alternative boarding point.

Please refer to FIG. 7 , step 025 can be implemented by the determination unit 121 , step 026 can be implemented by the replacement point selection unit 122 , step 027 can be implemented by the duration calculation unit 123 , and step 028 can be implemented by the boarding point addition unit 124 . That is to say, the determination unit 121 is used to determine the original boarding point and the target point according to the user's request; U-turn driving road section and/or non-congested road section selects the replacement point; The duration calculation unit 123 is used to calculate the second walking duration from the user's current position to the replacement point, the second driving duration of the unmanned vehicle from the replacement point to the target point, and the unmanned The third driving duration of the car from the original boarding point to the target point; the boarding point adding unit 124 is used to add the replacement point as a backup when the second walking duration plus the second driving duration is less than the third driving duration. Pick a pick-up point.

Specifically, referring to FIG. 10 , if the user's ride request is from point A (supermarket location or community location) to point B, then it can be determined that the original boarding point is point A1, and the target point is point B. In the case where the U-turn driving section (ab section) and/or the congested road section (cd section) is located behind the original boarding point A1, it means that the unmanned vehicle will pass through the U-turn driving section after meeting the user at the original boarding point A1 (ab section) and/or congested section (cd section). After the unmanned vehicle meets the user at the original boarding point A1, it will go through the U-turn section (ab section) and/or the congested road section (cd section), including three situations: the unmanned vehicle meets the user at the original boarding point A1 Only go through the U-turn section (section ab); the unmanned vehicle only passes through the congested section (cd section) after meeting the user at the original boarding point A1; the unmanned vehicle will also go through the U-turn after meeting the user at the original boarding point A1 segment (ab segment) and congested road segment (cd segment).

This application takes the unmanned vehicle shown in FIG. 10 as an example to go through the U-turn driving section (ab section) and the congested road section (cd section) after meeting the user at the original boarding point A1. As shown in Figure 10, the time for the unmanned vehicle to reach the target point B from the original boarding point A1 will take a lot of time due to the need to turn around and traffic jams. Therefore, when selecting the boarding point, you can drive without turning around Select a replacement point for road sections and non-congested road sections. For example, you can choose to select a replacement point D1 point on another alternative route 2 of a non-congested road section without a U-turn road section and no traffic jam situation. The user walks to the replacement point D1 point to get on the bus, thereby It avoids the situation that it takes a lot of time for the unmanned vehicle to reach the target point B from the original boarding point A1 due to the need to turn around and traffic jams.

Further, the duration calculation unit 123 can be used to calculate the second walking duration from the user's current position to the replacement point, the second driving duration of the unmanned vehicle from the replacement point to the target point, and the travel time of the unmanned vehicle from the original boarding point to the target point. For the third driving duration, when the second walking duration plus the second driving duration is less than the third driving duration, the replacement point is added as the target boarding point. For example, the user's current location is O1, and the replacement point is D1. The user's second walking time from the user's current location O1 to the replacement point D1 is 2 minutes. ) to the target point B is 4 minutes long. At this time, since the unmanned vehicle will pass through a U-turn section or a congested road section after being loaded to the user at the original boarding point A1, the unmanned vehicle will go from the original boarding point A1 to the target The third driving time at point B is longer and may be 10 minutes, that is, the second walking time is 2 minutes plus the second driving time is 4 minutes, which is 6 minutes and less than the third driving time. It is 10 minutes. At this time, the replacement Point D1 is added as the boarding point, which shortens the total time required for the unmanned vehicle to meet the user's vehicle and carry the user to the target point after receiving the user's ride request, and improves the driving performance of the unmanned vehicle efficiency.

After the unmanned vehicle meets the user at the original boarding point A1, it only needs to go through the U-turn road section and the congested road section to select the replacement point D1. The third travel time from the boarding point A1 to the target point B is different because it only needs to make a U-turn or only needs to pass through the congested road section, so it will not be repeated here.

Please refer to Fig. 11, step 021 comprises:

0211: Obtain the historical boarding point data of the user in the area corresponding to the user's current location;

0212: Perform density analysis on historical boarding point data to obtain commonly used boarding points;

0213: Determine alternative boarding points based on common boarding points.

Please refer to FIG. 12 , the determination unit 121 may include an acquisition unit 1211 , an analysis unit 1212 and a boarding point determination unit 1213 .

Step 0211 can be implemented by the acquisition unit 1211 , step 0212 can be implemented by the analysis unit 1212 , and step 0213 can be implemented by the boarding point determination unit 1213 . That is to say, the acquisition unit 1211 is used to obtain the historical boarding point data of the user in the area corresponding to the user's current location; the analysis unit 1212 is used to perform density analysis on the historical boarding point data to obtain common boarding points; the boarding point determination unit 1213 is used to determine the target boarding point according to the common boarding point.

Specifically, when selecting a boarding point, you can obtain the data of multiple taxi boarding points within a certain period of time to obtain the historical boarding point data in the area corresponding to the user's current location, and perform density analysis on the historical boarding point data to collect Then the user's current location corresponds to the most frequently used boarding point of the user, and the coordinate map can be drawn with latitude and longitude as the horizontal and vertical coordinates to indicate the user's common boarding point, and then the alternative boarding point is determined according to the common boarding point. For example, common boarding points can be used as alternative boarding points.

Referring to Figure 13, step 0212 includes:

02121: Determine the latitude and longitude of the vehicle point data in history to draw the corresponding coordinate map;

02122: On the coordinate map, aggregate the historical boarding point data according to the preset range to obtain the boarding point cluster;

02123: Determine common boarding points according to boarding point clusters.

Please refer to FIG. 14 , the analysis unit 1212 includes a map drawing unit 12121 , a boarding point cluster acquisition unit 12122 and a commonly used boarding point determination unit 12123 .

Step 02121 can be realized by the map drawing unit 12121, step 02122 can be realized by the boarding point cluster acquisition unit 12122, and step 02123 can be realized by the commonly used boarding point determination unit 12123. That is to say, the map drawing unit 12121 is used to determine the latitude and longitude of the historical vehicle point data to draw the corresponding coordinate map; the boarding point cluster acquisition unit 12122 is used to aggregate the historical vehicle point data according to the preset range in the coordinate map Obtain the boarding point cluster; the commonly used boarding point determination unit 12123 is used to determine the frequently used boarding point according to the boarding point cluster.

Specifically, the historical pick-up point data includes the most frequently used pick-up points collected by nearby users, and then the coordinate map is drawn with latitude and longitude as horizontal and vertical coordinates. The historical bus point data can be determined based on the selection of other taxi boarding points within a certain period of time.

Then, based on the DBSCAN algorithm, the boarding point data set can be aggregated into several clusters according to a certain radius of activity (for example, 10 meters as the radius of activity), so as to distinguish data clusters of different orientations, such as different clusters on the east or west side of the gate of the community. The data cluster can prevent the results of different data clusters with different boarding location preferences from interfering. Finally, the data set of each cluster can be used as new input data to obtain several boarding point clusters, so as to determine common boarding points according to the boarding point clusters.

Referring to Figure 15, step 02123 includes:

021231: Use the cluster analysis algorithm to iteratively aggregate the historical boarding point data corresponding to the boarding point cluster to obtain the centroid position;

021232: Use the centroid location as a common pick-up point.

Please refer to FIG. 14 , step 021231 and step 021232 can be realized by the common boarding point determination unit 12123 . That is, the commonly used boarding point determination unit 12123 is used to iteratively aggregate the historical boarding point data corresponding to the boarding point cluster by using a cluster analysis algorithm to obtain the centroid position; the centroid position is used as the common boarding point.

Specifically, the clustering analysis algorithm includes the Kmeans algorithm, that is, using the iterative aggregation function of the Kmeans algorithm, the position of the centroid can be obtained as a common boarding point according to several boarding point clusters.

Referring to Figure 16, step 021231 includes:

0212311: Obtain the data creation time corresponding to the historical vehicle point data;

0212312: Determine the weighted value of the corresponding historical vehicle point data according to the data creation time;

0212313: According to the weighted value, use the cluster analysis algorithm to iteratively aggregate the historical boarding point data corresponding to the boarding point cluster to obtain the centroid position.

Please refer to FIG. 17 , the common boarding point determination unit 12123 also includes a centroid determination unit 121231 .

Steps 0212311, 0212312 and 0212313 can all be implemented by the centroid determination unit 121231. That is, the centroid determination unit 121231 is used to obtain the data creation time corresponding to the historical vehicle point data; determine the weighted value of the corresponding historical vehicle point data according to the data creation time; use the cluster analysis algorithm to classify the vehicle point according to the weighted value The location of the centroid is obtained by iterative aggregation of the historical vehicle point data corresponding to the cluster.

Understandably, based on the analysis of the selection of other taxi boarding points within a certain period of time, it is possible to avoid unmanned taxis from choosing to park at boarding points that are prohibited from parking according to other rules, such as the main entrance of the community, which is inconvenient for users and unmanned taxis. People and vehicles meet.

Specifically, because the parking prohibition rules of a boarding point may change over time, that is, it is possible to prohibit parking at this location within a certain period of time, and this location can be used again after this period of time. Stopped, so time correlation needs to be considered. Therefore, when using the Kmeans algorithm, you can add time tags, determine the weighted value of the corresponding historical boarding point data according to the data creation time, and then use the cluster analysis algorithm to classify the historical boarding point corresponding to the boarding point cluster according to the weighted value. The data is iteratively aggregated to obtain the centroid position.

Wherein, determining the weighted value of the corresponding historical vehicle point data according to the data creation time refers to, for example, the weight of the data within 1 hour is 1, and the weight of the data of 1 week ago is 0.1.

The control method of the present application can implement cluster analysis of short-term data by weighting the data in a data cluster with respect to time. In other embodiments of the present application, for example, the weight of the same time period in history can also be set to 1, and the weight of other time periods can be set to 0.1, etc., so as to avoid the influence of other historically same factors on the boarding point.

Referring to Figure 18, the control method also includes:

07: Automatically calculate the optimal solution to determine the target route without receiving the user's operation on the alternative route;

08: Send a route confirmation message to notify the user and give route guidance.

Please refer to FIG. 19 , the control system 10 of the unmanned vehicle also includes an automatic optimization module 17 and a route confirmation and guidance module 18 .

Step 07 can be realized by the automatic optimization module 17 , and step 08 can be realized by the route confirmation and guidance module 18 . That is, the automatic optimization module 17 is used to automatically calculate the optimal solution to determine the target route without receiving the user's operation on the alternative route; the route confirmation and guidance module 18 is used to send a route confirmation message to notify the user And give path guidance.

Specifically, if the user who placed the order fails to respond to the selection of the alternatives in real time, that is, the unmanned vehicle can automatically select and calculate the optimal solution without receiving the user's operation on the alternative route. Before arriving, the user will be notified by phone or message sent by the unmanned vehicle online booking platform, and the route guidance will be given.

Please refer to Fig. 20, after step 01, the control method includes:

011: Obtain user route preferences;

Step 02 includes:

021: Determine at least one alternative boarding point according to the user's route preference, the user's ride request, and the user's current location.

Please refer to FIG. 1 , step 011 can be realized by the acquisition module 11 , and step 021 can be realized by the boarding point determination module 12 . That is, the acquisition module 11 is used to acquire the user's route preference; the boarding point determination module 12 is used to determine at least one alternative boarding point according to the user's route preference, the user's ride request and the user's current location.

It can be understood that each user has different preferences and prefers to choose different boarding points. Determining at least one target boarding point in combination with the user's route preference can better adapt to the user's preferences and improve user experience.

Specifically, when the user places an order on the unmanned car online booking platform for the first time, the user's preference in terms of rides can be collected through a question and answer method. For example, you can ask the user whether they would like to spend an extra 5 minutes, avoid walking as much as possible for a 10-minute drive, or give priority to efficiency.

Please refer to Figure 21, further, step 011 includes:

0111: Send preference selection information to the user's mobile terminal;

0112: Receive the user's operation on the above preference selection information to determine the user's route preference.

Referring to FIG. 1 , both step 0111 and step 0112 can be implemented by the acquisition module 11 . That is to say, the acquisition module 11 can be specifically configured to send preference selection information to the user's mobile terminal; receive the user's operation on the preference selection information to determine the user's route preference.

Specifically, the preference information can be sent to the user's mobile terminal in the form of a question and answer on the order platform of the unmanned vehicle network, and the preference information can also be sent to the user's mobile terminal in the form of a questionnaire or other forms. Then, the unmanned vehicle can receive the preference selection information selected by the user to determine the user's route preference.

Please refer to Figure 22, step 011 includes:

0113: Obtain the user's historical travel information, which includes preset user tags;

0114: According to the word frequency calculation algorithm, analyze the historical travel information to obtain the user's route preference.

Referring to FIG. 1 , both step 0113 and step 0114 can be implemented by the acquisition module 11 . That is to say, the acquisition module 11 can be specifically used to acquire the user's historical travel information, which includes preset user tags; analyze the historical travel information according to the word frequency calculation algorithm to obtain the user's route preference.

Specifically, for users who have taken multiple rides, it can be analyzed in combination with previous travel records, such as judging in which time period the user prefers to save travel time, which pick-up point is more desirable to reduce walking distance, etc. Help users generate more appropriate travel plans.

For example, when analyzing user preferences, the TF-IDF algorithm can be used to analyze and obtain the user's travel preferences (algorithm formula shown in Figure 23, where p is the user identifier, which is used to distinguish different users, and Ti includes the identifier P user all preset user tags). The control method of the unmanned vehicle of the present application can mark a user's preference one by one with the user's preset user label through the preset user label, and can analyze the travel preference of the user.

Wherein, the preset user label can be a yellow triangle logo or other color or shape representation, for example, a yellow triangle logo indicates that the user does not like to walk, and a red triangle logo indicates that the user likes to save travel time between 8 o'clock and 9 o'clock.

Specifically, the user's label can also be continuously learned through the neural network.

Referring to Figure 24, in some embodiments, step 04 includes:

041: When the unmanned vehicle travels to the target boarding point within the first preset distance, obtain the surrounding environment information of the target boarding point;

042: When the surrounding environment information of the target boarding point is not suitable for the vehicle to park, re-determine the target boarding point and notify the user.

Please refer to FIG. 25 , the determining module 14 includes an environment information obtaining unit 141 and a re-determining unit 142 .

Step 041 can be implemented by the environment information acquiring unit 141 , and step 042 can be implemented by the re-determining unit 142 . That is, the environmental information acquisition unit 141 is used to acquire the surrounding environment information of the target boarding point when the unmanned vehicle travels to the target boarding point within the first preset distance; the re-determining unit 142 is used to If the surrounding environment information of the point is not suitable for the vehicle to park, re-determine the target boarding point and notify the user.

Specifically, when the unmanned vehicle is driving near the target boarding point, if the user has a certain distance, and through image analysis, it is found that there are certain obstacles near the target boarding point, such as shared bicycles parked, other vehicles parked, temporary building maintenance If it is not suitable for unmanned vehicles to park for a long time, the unmanned vehicle will start to drive slowly around while sending the situation to the online car-hailing platform. After eliminating the target boarding point, the online car-hailing platform will re- Plan pick-up points and notify users.

Re-plan the pick-up point and notify the user that it can collect the road conditions near the pick-up point for the online car-hailing cloud platform, including vehicle congestion, whether it is necessary to make a U-turn, turn, and the time of passing through in the past, etc., and analyze the time when the user arrives at the pick-up point And the waiting time of the unmanned vehicle, so as to give other alternatives and the corresponding passing time and send them to the user's mobile terminal.

Please refer to Figure 26. After the unmanned vehicle reaches the target boarding point, the control method includes:

051: Obtain user identity information for identity matching;

052: After the identity matching is successful, allow the user to get on the car to complete the car boarding task.

Please refer to FIG. 27 , the control system 10 of the unmanned vehicle also includes an identity matching module 151 .

Both step 051 and step 052 can be implemented by the identity matching module 151 . That is, the identity matching module 151 is used to obtain user identity information for identity matching; after the identity matching is successful, the user is allowed to get on the car to complete the task of getting on the car.

Specifically, the online car-hailing platform can analyze the distance between the user and the unmanned workshop in real time. When the unmanned vehicle drives near the boarding point, if the user is also located near the boarding point, the unmanned vehicle stops at the selected boarding point, and then the user scans the QR code for identity matching and completes the boarding process. car. The way of identity matching is not limited to the way of scanning the two-dimensional code, but also other forms, which are not limited here.

Please refer to Figure 28. After the unmanned vehicle reaches the target boarding point, the control method includes:

053: When the distance between the user and the target boarding point is greater than the second preset distance or the waiting time is longer than the preset time, control the unmanned vehicle to select a parking space near the target boarding point to park.

Please refer to FIG. 29 , the control system 10 of the unmanned vehicle further includes a parking module 153 .

Step 053 can be implemented by the docking module 153, that is, the docking module 153 is used to control the unmanned vehicle to select the target when the distance between the user and the target boarding point is greater than the second preset distance or the waiting time is greater than the preset time. Stop at a parking space near the pick-up point.

Specifically, if the user is far away from the boarding point or is delayed for a long time due to other things, the unmanned vehicle chooses the parking lot near the boarding point or the fixed parking space of the unmanned vehicle to stop, and waits for the user to go out or walk to the boarding point Resume driving when nearby.

Please refer to FIG. 30 , the present application also provides an unmanned vehicle 100 . The unmanned vehicle 100 includes a processor 110 and a memory 120. The memory 120 is used to store a computer program 121. When the processor 110 executes the computer program 121, the control method of the unmanned vehicle described in any one of the above embodiments is implemented.

The unmanned vehicle of the present application can determine at least one alternative boarding point according to the user's ride request and the user's current location, and then plan at least one alternative route according to the road information and the alternative boarding point, and determine each alternative route. The estimated passing time of the route is sent to the user's mobile terminal. The user can select a target route from the alternative routes to control the unmanned vehicle to drive to the target boarding point according to the target route, which can make the meeting between the user and the unmanned vehicle more flexible and improve the efficiency of the meeting between people and vehicles.

Referring to FIG. 31 , the present application also provides a non-volatile computer-readable storage medium 200 of a computer program. When the computer program 210 is executed by one or more processors 220, the control method of the unmanned vehicle described in any one of the above embodiments is realized.

The control method of the unmanned vehicle of the present application and its control system, the unmanned vehicle and the readable storage medium determine at least one alternative boarding point according to the user's ride request and the user's current location, and then according to the road information and the alternative boarding point Carry out route planning to find at least one alternative route, and determine the estimated passing time of each alternative route and send it to the user's mobile terminal. The user can select a target route from the alternative routes to control the unmanned vehicle to drive to the target boarding point according to the target route, which can make the meeting between the user and the unmanned vehicle more flexible and improve the efficiency of the meeting between people and vehicles.

The above examples only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Claims (17)

1. A control method of an unmanned vehicle, comprising:

acquiring a user riding request, a user current position and road information;

determining at least one alternative boarding point according to the user riding request and the current position of the user;

carrying out route planning according to the road information and the alternative boarding points to obtain at least one alternative route;

and determining the predicted passing time of each alternative route to determine a target boarding point.

2. The control method according to claim 1, wherein the determining at least one alternative boarding point according to the user boarding request and the user current position comprises:

determining an original boarding point according to the user riding request;

under the condition that the original vehicle getting-on point is positioned behind the U-turn driving road section and/or the congested road section, selecting a replacement point on the non-U-turn driving road section and/or the uncongested road section;

calculating the first step time length from the current position of the user or the original vehicle-loading point to the replacement point and the first running time length of the unmanned vehicle passing through the U-turn running road section and/or the congested road section;

and under the condition that the first step traveling time length is smaller than the first traveling time length, newly adding the replacement point as the alternative boarding point.

3. The control method according to claim 1, wherein the determining at least one alternative boarding point according to the user boarding request and the user current position comprises:

determining an original boarding point and a target point according to the user riding request;

under the condition that the turning-around driving section and/or the congested section are/is positioned behind the original vehicle-entering point, selecting a replacement point on the non-turning-around driving section and/or the uncongested section;

calculating a second step driving time length from the current position of the user to the replacement point, a second driving time length from the replacement point to the target point of the unmanned vehicle, and a third driving time length from the original driving point to the target point of the unmanned vehicle;

and under the condition that the sum of the second step driving time length and the second driving time length is smaller than the third driving time length, adding the replacement point as the alternative getting-on point.

4. The control method of claim 1, wherein the determining at least one alternative pick-up point based on the user ride request and the user current location comprises:

obtaining historical vehicle-boarding point data of the user in an area corresponding to the current position of the user;

performing density analysis on the historical boarding point data to obtain a common boarding point;

and determining the alternative boarding points according to the common boarding points.

5. The control method according to claim 4, wherein the performing density analysis on the historical boarding point data to obtain frequent boarding points comprises:

determining the longitude and latitude of the historical vehicle point data to draw a corresponding coordinate map;

aggregating the historical boarding point data according to a preset range on the coordinate map to obtain a boarding point cluster;

and determining the common boarding points according to the boarding point clusters.

6. The control method according to claim 5, wherein the determining the common pick-up point according to the pick-up point cluster includes:

performing iterative aggregation on the historical boarding point data corresponding to the boarding point cluster by using a cluster analysis algorithm to obtain a centroid position;

and taking the position of the center of mass as the common boarding point.

7. The control method according to claim 6, wherein the iteratively aggregating the historical boarding point data corresponding to the boarding point cluster by using a cluster analysis algorithm to obtain a centroid position comprises:

acquiring data creating time corresponding to the historical vehicle point data;

determining a weighted value of the corresponding historical vehicle point data according to the data creation time;

and performing iterative aggregation on the historical vehicle-entering point data corresponding to the vehicle-entering point cluster by utilizing the cluster analysis algorithm according to the weighted value to obtain the centroid position.

8. The control method according to claim 1, characterized by comprising:

automatically calculating an optimal scheme to determine the target route without receiving user operation on the alternative route;

a route confirmation message is sent to notify the user and give the route guidance.

9. The control method according to claim 1, wherein after the obtaining of the user riding request, the user current position, and the road information, the control method comprises:

obtaining a user route preference;

the determining at least one target boarding point according to the user riding request and the current position of the user comprises the following steps:

and determining at least one alternative boarding point according to the user route preference, the user boarding request and the current position of the user.

10. The control method of claim 9, wherein the obtaining the user route preference comprises:

sending preference selection information to the user mobile terminal;

and receiving the operation of the user on the preference selection information to determine the route preference of the user.

11. The control method of claim 9, wherein the obtaining the user route preference comprises:

acquiring historical trip information of a user, wherein the historical trip information comprises a preset user label;

and analyzing the historical travel information according to a word frequency calculation algorithm to obtain the route preference of the user.

12. The control method of claim 11, wherein the predetermined user label is learned from a neural network.

13. The control method according to claim 1, characterized by comprising:

under the condition that the unmanned vehicle runs to the first preset distance of the target boarding point, acquiring the environmental information around the target boarding point;

and under the condition that the environmental information around the target boarding point is not suitable for the parking of the vehicle, re-determining the target boarding point and informing the user.

14. The control method according to claim 1, characterized in that after the unmanned vehicle travels to the target boarding point, the control method includes:

and under the condition that the distance between the user and the target boarding point is greater than a second preset distance or the waiting time is greater than preset time, controlling the unmanned vehicle to select a parking space near the target boarding point to park.

15. A control system for an unmanned vehicle, comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a riding request of a user, the current position of the user and road information;

the boarding point determining module is used for determining at least one alternative boarding point according to the riding request of the user and the current position of the user;

the route planning module is used for carrying out route planning according to the road information and the alternative vehicle-loading points to obtain at least one alternative route;

a determination module for determining an expected transit time for each of the alternative routes to determine the target pick-up point.

16. An unmanned vehicle comprising a processor and a memory, the memory for storing a computer program, the processor implementing the control method of any one of claims 1 to 14 when executing the computer program.

17. A non-transitory computer-readable storage medium of a computer program, characterized in that, when the computer program is executed by one or more processors, the control method of any one of claims 1 to 14 is implemented.

Images