Unmanned vehicle control method, unmanned vehicle and storage medium

Abstract

The application discloses an unmanned vehicle control method, an unmanned vehicle and a computer readable storage medium, and is applied to the unmanned vehicle. The unmanned vehicle control method comprises the following steps: acquiring personnel distribution in a current detection range; when the personnel distribution meets path correction conditions, determining personnel positions corresponding to the current detection range, and determining a personnel obstacle area according to the personnel positions; updating a driving path based on the personnel obstacle area; and controlling the unmanned vehicle to drive around the personnel obstacle area according to the updated driving path. Based on the above method, when the unmanned vehicle encounters a situation with many pedestrians during driving, the unmanned vehicle can reasonably plan a driving path, avoid personnel or crowds and perform a distribution task, so that the distribution efficiency of the unmanned vehicle is improved.

Description

Unmanned vehicle control methods, unmanned vehicles and storage media Technical Field

[0001] This invention relates to the field of unmanned delivery, and more particularly to unmanned vehicle control methods, unmanned vehicles, and computer-readable storage media. Background Technology

[0002] In outdoor settings such as industrial parks, plazas, or communities, autonomous vehicles are sometimes used for delivery. These settings share common characteristics such as large area, high pedestrian traffic, and diverse and ever-changing demographics. Therefore, when autonomous vehicles follow their original delivery routes, they are easily disturbed by pedestrians and other factors. In particular, when there are crowds gathering in the route, the autonomous vehicles often cannot rationally plan new routes to avoid the crowds, which leads to low delivery efficiency.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide an unmanned vehicle control method, which aims to solve the technical problem that unmanned vehicles often cannot reasonably plan new driving routes to avoid crowds when there are crowds in the driving section, resulting in low delivery efficiency of unmanned vehicles.

[0005] To achieve the above objectives, the present invention provides an unmanned vehicle control method, the unmanned vehicle control method comprising:

[0006] Obtain the distribution of people within the current detection range;

[0007] When the personnel distribution meets the path correction conditions, the personnel positions within the current detection range are determined, and the personnel obstacle area is determined based on the personnel positions.

[0008] Update the driving path based on the personnel obstacle area;

[0009] The driverless vehicle is controlled to avoid the area containing the people and obstacles according to the updated driving path.

[0010] Optionally, after the step of obtaining the distribution of people within the current detection range, the method further includes:

[0011] Based on the personnel distribution, determine the number of personnel and the distance between them within the current detection range;

[0012] Select any person within the current detection range as the first target person, and create a team based on the first target person;

[0013] When the distance between other personnel and any member of the team is less than a preset distance, the other personnel are merged into the team;

[0014] When the number of people in the team is greater than or equal to the preset number, and the team's location occupies the path that the unmanned vehicle is to travel, it is determined that the distribution of people within the current detection range meets the path correction condition.

[0015] Optionally, the step of determining the location of the person within the current detection range and determining the obstacle area based on the person's location includes:

[0016] Teams that meet the path correction conditions will be designated as target teams;

[0017] Determine the location of all personnel within the target team;

[0018] Based on the positions of all personnel within the target team, a corresponding personnel obstacle area is determined, wherein the personnel obstacle area includes the positions of all personnel within the target team.

[0019] Optionally, the step of updating the driving path based on the personnel obstacle area includes:

[0020] Obtain the environmental map corresponding to the current detection range;

[0021] The corresponding obstacle area is determined based on the environmental map and the personnel obstacle area;

[0022] The environment map is updated based on the obstacle area;

[0023] Based on the updated environment map, the driving path used to bypass the obstacle area is replanned.

[0024] Optionally, after the step of controlling the unmanned vehicle to avoid the area of ​​pedestrian obstacles according to the updated driving path, the method further includes:

[0025] Obtain the location information of the second target person in the current delivery task;

[0026] Based on the location information of the second target personnel, determine the target docking point that meets the docking conditions;

[0027] When the unmanned vehicle arrives at the target docking point, it sends a first notification message to the second target person.

[0028] When the unmanned vehicle is unable to reach the target stop due to path obstruction, a second prompt message is sent to the second target personnel and / or management personnel.

[0029] Optionally, the step of determining a target stopping point that meets the stopping conditions based on the location information of the second target person includes:

[0030] The current position of the unmanned vehicle and the position of the second target person are obtained and used as the first position and the second position, respectively.

[0031] Based on the first location and the second location, plan a first path and determine the distance of the first path;

[0032] Calculate the straight-line distance between the first position and the second position;

[0033] When the ratio of the distance traveled to the straight-line distance is less than a preset value, the location of the second target person is taken as the target stopping point;

[0034] When the ratio of the distance traveled to the straight-line distance is greater than or equal to a preset value, a location point that meets the stopping conditions is selected as the target stopping point within a preset range of distance from the second target person.

[0035] Optionally, the unmanned vehicle control method further includes:

[0036] When the unmanned vehicle malfunctions and is unable to perform its delivery task, it sends a request for help to the management personnel.

[0037] The administrator is prompted to verify their identity, and their identity information is verified.

[0038] Once the identity information of the manager is successfully verified, the manager's management instructions are received and executed.

[0039] Optionally, the unmanned vehicle control method further includes:

[0040] When the unmanned vehicle receives a new instruction while executing other instructions, or when the unmanned vehicle receives multiple instructions simultaneously;

[0041] Determine the identity of the person who initiated the command;

[0042] When the initiator of the instruction includes an administrator, the instruction initiated by the administrator shall be executed first.

[0043] In addition, to achieve the above objectives, the present invention also provides an unmanned vehicle, the unmanned vehicle comprising: a memory, a processor, and an unmanned vehicle control program stored in the memory and executable on the processor, wherein when the processor executes the unmanned vehicle control program, it implements the steps of the unmanned vehicle control method as described above.

[0044] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing an unmanned vehicle control program, which, when executed by a processor, implements the steps of the unmanned vehicle control method described above.

[0045] This invention provides an unmanned vehicle control method, an unmanned vehicle, and a computer-readable storage medium. During delivery, the system continuously monitors the number of people along the route. Based on the distribution of people, it determines whether pre-set path correction conditions are met. When the conditions are met, the system identifies the location of each person within the current detection range. Based on this location, it identifies corresponding obstacle areas and updates the environmental map of the current route. A new route is then planned based on the updated map. Finally, the unmanned vehicle follows the updated route to avoid crowds and continue its delivery mission. This method enables the unmanned vehicle to rationally plan its route and avoid crowds when encountering situations with many pedestrians, thus improving delivery efficiency. Attached Figure Description

[0046] Figure 1 is a flowchart illustrating the first embodiment of the unmanned vehicle control method of the present invention;

[0047] Figure 2 is a detailed flowchart of step S20 in Figure 1;

[0048] Figure 3 is a detailed flowchart of step S30 in Figure 1;

[0049] Figure 4 is a flowchart illustrating another embodiment of the unmanned vehicle control method of the present invention;

[0050] Figure 5 is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention.

[0051] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0053] Currently, autonomous vehicles are used in many scenarios, such as industrial parks, communities, and plazas. These scenarios share common characteristics: large area, high pedestrian traffic, and diverse and ever-changing personnel. Therefore, when autonomous vehicles perform delivery tasks according to their original delivery routes, they are easily interfered with by pedestrians and other factors. Especially when there are crowds gathering in the driving section, autonomous vehicles often cannot reasonably plan new driving routes to avoid the crowds, which leads to low delivery efficiency.

[0054] To address the aforementioned problems, this invention provides an unmanned vehicle control method. When the unmanned vehicle performs a delivery task, it continuously detects the personnel situation on the current road. Based on the personnel situation, it determines whether the path correction conditions are met. Specifically, any person within the current detection range is selected as the first target person, and a team is created. When the distance between other people and any person in the team is less than a preset distance, the other person is added to the team. When the number of people in the team is greater than or equal to the preset number, and the team's location occupies the path to be traveled by the unmanned vehicle, the personnel distribution is determined to meet the path correction conditions. To plan a path that avoids crowds, the positions of people within the current detection range need to be determined first. Then, based on the personnel positions, the corresponding obstacle areas are set as obstacle areas. Based on the determined obstacle areas, the environmental map of the current detection range is updated. Based on the updated environmental map, a new driving path is planned and updated to the unmanned vehicle's control unit. The unmanned vehicle is then controlled to follow this driving path to avoid crowds and continue performing the delivery task.

[0055] The following explanation, through specific exemplary solutions, clarifies the scope of protection claimed in the claims of this invention, so that those skilled in the art can better understand the scope of protection of the claims. It is understood that the following exemplary solutions do not limit the scope of protection of this invention, but are only used to explain this invention.

[0056] This invention provides an unmanned vehicle control method. Referring to Figure 1, Figure 1 is a flowchart illustrating a first embodiment of the unmanned vehicle control method of this invention. In this embodiment, the unmanned vehicle control method includes:

[0057] Step S10: Obtain the distribution of personnel within the current detection range.

[0058] In this embodiment, the unmanned vehicle control method is applied to an unmanned vehicle, which can execute delivery tasks as needed after receiving them. The unmanned vehicle is equipped with a detection unit and a camera unit, which can detect the distribution of people on the current road segment, including the number of people and the distance between them.

[0059] In addition, before executing the current step S10, the unmanned vehicle can also plan an initial delivery route based on the location information of the target personnel in this delivery task and execute the delivery task according to the delivery route.

[0060] Optionally, the camera unit of the unmanned vehicle may be, but is not limited to, a depth camera, other camera devices or equipment, and the detection unit may be, but is not limited to, lidar, other detection devices or equipment.

[0061] Step S20: When the personnel distribution meets the path correction conditions, determine the personnel position corresponding to the current detection range, and determine the personnel obstacle area based on the personnel position.

[0062] It should be noted that in this embodiment, after obtaining the distribution of people, the autonomous vehicle also needs to determine whether the distribution of people within the current detection range meets the path correction conditions, thereby determining whether to plan a detour route. That is, the autonomous vehicle determines the distribution of people within the current detection range based on at least one of three images: optical image, depth image, and laser point cloud image. It then determines the distance and number of people between them, selects any person within the current detection range as the first target person, and creates a team around this first target person. When the distance between another person and any person in this team is less than a preset distance, that other person is added to the team.

[0063] A team led by a target individual is considered within the detection range if the number of members in the team is greater than or equal to a preset number (5) and the team's location occupies the path that the autonomous vehicle is to travel.

[0064] If the number of people in the team is less than the preset number, and / or the path that the autonomous vehicle is to travel does not pass through the area where the team is located, then the distribution of people within the current detection range is determined not to meet the path correction conditions.

[0065] Understandably, the preset distance and preset number of people can be set by staff based on the actual situation.

[0066] Alternatively, in other embodiments, the distribution of people within the current detection range can be clustered using a clustering algorithm to determine the clustered teams and identify the target teams that meet the path correction conditions.

[0067] After determining that the distribution of personnel within the current detection range meets the path correction conditions, it is necessary to determine the corresponding personnel positions and, based on these positions, identify the obstacle areas. Referring to Figure 2, step 5S20, which involves determining the corresponding personnel positions within the current detection range and, based on these positions, identifying the personnel obstacle areas, includes:

[0068] Step S21: Select the teams that meet the path correction conditions as the target teams.

[0069] Step S22: Determine the location of all personnel within the target team.

[0070] Step S23: Based on the positions of all personnel within the target team, determine the corresponding personnel obstacle area, wherein the personnel obstacle area includes all personnel within the target team.

[0071] The personnel positions.

[0072] After confirming that the personnel distribution within the current detection range meets the path correction criteria, the teams meeting the path correction criteria are designated as target teams. Subsequently, all personnel within these target teams are identified.

[0073] Based on the determined personnel locations, the corresponding obstacle area is further determined. This obstacle area contains the locations of all personnel within the target team.

[0074] Optionally, the unmanned vehicle can obtain optical images, depth images or laser point cloud images within the current detection range by working together with the detection unit and the camera unit. The detection unit can be, but is not limited to, lidar, other detection devices or equipment, and the camera unit can be, but is not limited to, a depth camera, other camera devices or equipment.

[0075] For example, the autonomous vehicle selects a person within its current detection range as the first target person. Preset parameters: a preset distance of 1.5m and a preset number of people of 3. Therefore, when the autonomous vehicle detects another person whose distance to the first target person is less than 1.5m, it adds that person to the team. Furthermore, when any other person's distance to any member of this updated team is less than 1m, that other person is added to the team. When the number of people in the team exceeds 3, and the team's location is within the autonomous vehicle's driving path, the autonomous vehicle determines that the current personnel team meets the path correction conditions. Finally, the autonomous vehicle designates the team that meets the path correction conditions as the target team, determines the location of all personnel within that target team, and uses this to further confirm the corresponding personnel obstacle areas.

[0076] Step S30: Update the driving path based on the personnel obstacle area.

[0077] In this embodiment, after determining the obstacle area, the driving path needs to be updated based on the obstacle area. Referring to Figure 3, specifically, step S30, the step of updating the driving path based on the obstacle area, includes:

[0078] Step S31: Obtain the environmental map corresponding to the current detection range.

[0079] Step S32: Determine the corresponding obstacle area based on the environmental map and the personnel obstacle area.

[0080] Step S33: Update the environment map based on the obstacle area.

[0081] Step S34: Based on the updated environment map, replan the driving path to bypass the obstacle area.

[0082] In this embodiment, the unmanned vehicle first retrieves the environmental map corresponding to the current detection range, determines the location of the personnel obstacle area in the environmental map as the obstacle area, updates the environmental map accordingly, and plans a driving path to bypass the obstacle area based on the updated environmental map.

[0083] Optionally, the autonomous vehicle can determine the corresponding obstacle areas by establishing an equivalent obstacle model to further update the environmental map. That is, all personnel within the target team are treated as a single obstacle, and the location of the personnel obstacle area on the environmental map corresponds to the location of the obstacle. Since the number and distribution of personnel in different target teams vary, the area they occupy also differs. Therefore, the corresponding equivalent obstacle model can be determined based on the center coordinates of the personnel obstacle area for each target team and the obstacle's volume. Here, feature point detection algorithms can first be used to collect feature points from the team members. Then, these feature points are clustered, grouping the team members' feature points into the same personnel obstacle area category. Similarly, this step can also be implemented using clustering algorithms. Finally, the location of the actual obstacle is represented by extracting feature points of the same category, forming an equivalent model around the outermost feature points of the obstacle. The purpose is to demonstrate the position and size relationships of different obstacles in space, preparing for the autonomous vehicle's obstacle avoidance path planning. To facilitate the autonomous vehicle's handling of obstacles, the shape of the equivalent model is usually set to a cuboid that most closely approximates the size of the personnel obstacle itself. It should be noted that the calculation of the model size not only needs to consider the obstacle itself, but also the speed of the autonomous vehicle and the safe braking distance. Subsequently, it is also necessary to calculate the area covered by the equivalent model of the obstacle, determine the corresponding obstacle area, update the environmental map corresponding to the current detection range of the autonomous vehicle based on the obtained obstacle area, and based on the updated environmental map, the autonomous vehicle can determine which areas in the current detection range are drivable areas and which areas are not drivable areas, plan a path to avoid pedestrians, and also adaptively adjust its own driving speed.

[0084] In this embodiment, by constructing an obstacle equivalent model of the crowd and updating the environmental map in the current detection range after determining the obstacle area, a new driving path is planned based on the environmental map. This enables the unmanned vehicle to rationally plan its driving path when encountering crowds, avoid pedestrians and continue to perform delivery tasks, thereby improving the working efficiency of the unmanned vehicle.

[0085] Step S40: Control the unmanned vehicle to drive around the area of ​​people and obstacles according to the updated driving path.

[0086] In this embodiment, after planning a new driving route, the autonomous vehicle will update the planned new route to its own control unit, which will then control the autonomous vehicle to run based on the updated driving route, avoid crowds, and continue to perform the delivery task.

[0087] In this embodiment, when the unmanned vehicle is performing a delivery task, it may encounter a scene with a large number of people during the journey. In this scene, there may be a crowd gathering. In order to avoid collisions with the unmanned vehicle or the execution of the delivery task being affected by the crowd, the area where the crowd is located is divided into an obstacle area. Based on the obstacle area, the corresponding driving path is reasonably planned and updated to avoid the crowd and continue to perform the delivery task, thereby improving the working efficiency of the unmanned vehicle.

[0088] Referring to Figure 4, after step S40, the following steps are also included:

[0089] Step S50: Obtain the location information of the second target person in the current delivery task.

[0090] Step S60: Based on the location information of the second target personnel, determine the target docking point that meets the docking conditions.

[0091] Step S70: When the unmanned vehicle arrives at the target parking point, a first prompt message is sent to the second target person.

[0092] Step S80: When the unmanned vehicle is unable to reach the target stop due to path obstruction, a second prompt message is sent to the second target personnel and / or management personnel.

[0093] In this embodiment, before the autonomous vehicle performs a delivery task, the manager issues the task to it. This task includes a second target person and their location information. The autonomous vehicle's task is to transport the item to the location of the second target person and deliver it successfully. However, since the location of the second target person is not a fixed location, it may exist anywhere in the autonomous vehicle's operating environment. Some locations may be inaccessible to the vehicle. Therefore, the autonomous vehicle also needs to determine the corresponding target stopping point based on the location information of the second target person in this delivery task. The second target person is the recipient of the service provided by the autonomous vehicle.

[0094] In this embodiment, the current location of the unmanned vehicle and the location of the second target person corresponding to the delivery task are obtained and designated as the first location and the second location, respectively. Based on the first and second locations, a first path for the unmanned vehicle to perform the delivery task from the first location to the second location is planned, and the distance corresponding to the first path is determined. In addition, the straight-line distance between the first location and the second location needs to be calculated. When the ratio of the distance to the straight-line distance is greater than or equal to a preset ratio (for example, the preset ratio is 1.2), it indicates that the delivery route may involve a detour. Therefore, to avoid the unmanned vehicle making a detour, a location point that meets the parking conditions is selected within a preset range (for example, within 20m of the second target person) as the target parking point, allowing the user to pick up the package at the target parking point. When the ratio of the distance to the straight-line distance is less than the preset ratio, it indicates that the delivery route is within a reasonable range and there is no detour. Therefore, the location of the target person is used as the target parking point.

[0095] Optionally, the preset ratio and preset range can be determined by the staff according to the actual situation.

[0096] Optionally, when selecting a location that meets the parking conditions as the target parking point, the autonomous vehicle can also obtain the corresponding real-scene map based on the location information of the second target person. The real-scene map is a 3D map. For example, when the user enters the destination, the navigation program can obtain the real-scene map of the destination based on positioning systems such as GPS or Beidou and send it to the user terminal. After the user opens the real-scene map, they can see the road features of the destination, which makes it easier for people to determine whether they can reach the destination. In this invention, the unmanned vehicle also utilizes a positioning system to retrieve a real-world map corresponding to the location of the second target person. This map is then used to analyze the environmental information of the target person's location. Based on an analysis algorithm, the environmental information is analyzed and evaluated to select a suitable area as the target stopping point. The stopping conditions include flat terrain, free from any dynamic or static obstacles such as trash cans, steps, or small animals. The area of ​​the stopping area must be greater than twice the area of ​​the road covered by the unmanned vehicle to facilitate U-turns or reversing. Furthermore, the distance from the stopping point to the second target person is within a preset range, for example, no more than 5 meters. In other words, the target stopping point should be selected as close as possible to the target person, minimizing the distance the second target person needs to travel to retrieve goods. Optionally, the stopping conditions can be further specified by the developers to facilitate the selection of a more reasonable target stopping point for the unmanned vehicle. After determining the target stopping point, the unmanned vehicle is controlled to move towards it.

[0097] Furthermore, when the autonomous vehicle arrives at the target stop, it can send a first notification message to the second target person. This first notification message reminds the target person to pick up the goods. In addition to the pickup notification, the first notification message also includes a randomly generated pickup code for verifying the pickup person's identity. The pickup code can be a four- or six-character string consisting of numbers and / or letters. Moreover, even though the autonomous vehicle has selected the target stop, it may still encounter some objective obstacles during the delivery process that obstruct its path, such as stairs or fences. In this case, the autonomous vehicle can send a second notification message in advance to the target person and / or management personnel. The second notification message differs from the first notification message indicating normal arrival. In addition to the pickup code, the second notification message includes the reason why the unmanned vehicle could not reach the target stop, such as a blocked path or being obstructed by other people, as well as the current location of the unmanned vehicle. Based on this information, the second target personnel and / or managers can know the current working status and specific location of the unmanned vehicle, making it convenient for the second target personnel to go to the location of the unmanned vehicle to pick up the goods. Managers can also rely on the second notification message to determine whether it is necessary to intervene manually to help the unmanned vehicle complete the remaining delivery work.

[0098] Optionally, after the unmanned vehicle arrives at the target stop, the location of the second target person may change. In order to complete the delivery task, the unmanned vehicle can also receive the new target location sent by the second target person and replan the driving route and target stop based on the new target location.

[0099] Optionally, during delivery missions, unmanned vehicles may encounter malfunctions such as map loading failure, location failure, target person authentication failure, or inability to locate the target person. When these malfunctions occur, the unmanned vehicle sends a request for assistance to the management personnel. Upon receiving this request, the management personnel will go to the location of the unmanned vehicle to investigate the cause of the malfunction. Meanwhile, to ensure the safety of the unmanned vehicle in a malfunctioning state, the malfunction status can only be viewed by management personnel. Therefore, the unmanned vehicle will prompt the management personnel to verify their identity. The management personnel's identity verification information is fixed, such as fingerprint information, facial information, user password, or iris information. This identity authentication information is pre-collected and set, and can be stored locally on the unmanned vehicle or in the cloud. When the management personnel enter the corresponding identity verification information, the unmanned vehicle can verify whether the current person's identity is that of a management personnel based on the stored identity information. Only after successful verification can the unmanned vehicle receive auxiliary instructions from the management personnel and execute the corresponding operations. It's important to note that auxiliary commands and regular commands are not the same. Auxiliary commands involve managing the internal permissions of the autonomous vehicle, such as viewing information about the secondary target person in a delivery task or the delivery task's execution status. Regular commands, such as asking a pedestrian for directions, do not require identity verification and can be executed directly. Furthermore, the autonomous vehicle can also respond to auxiliary commands by following management personnel or moving according to their instructions.

[0100] Optionally, the autonomous vehicle can also categorize people in outdoor scenarios into multiple types, including: management personnel, secondary target personnel corresponding to the delivery task, and the general public. When the autonomous vehicle receives multiple instructions simultaneously during task execution, or receives new instructions while executing other instructions, it prioritizes responding to instructions given by management personnel, and then executes instructions from secondary target personnel. That is, when receiving multiple instructions or receiving new instructions while executing other instructions, the autonomous vehicle must first determine the identity of the instruction initiator. If the initiator's identity includes management personnel, it prioritizes responding to task instructions entered by management personnel midway, then completes the delivery task instructions, and finally avoids pedestrians or does not respond to operations by the general public.

[0101] It should be noted that the terms "first target personnel," "second target personnel," "first prompting information," and "second prompting information" in this invention are merely for distinguishing terms and do not limit the order of the two.

[0102] Optionally, the division of personnel in outdoor scenarios can also be adjusted according to the working scenario of the unmanned vehicle. For example, when the working scenario of the unmanned vehicle is a factory, the personnel's job title level can be determined according to the color of their clothing or safety helmet. During the delivery task, the personnel can be stopped by staff with a fixed job title level or above, and the execution status of the delivery task can be viewed.

[0103] In this embodiment, the unmanned vehicle is equipped with countermeasures for potential problems in the delivery task and the execution of the delivery process, so that the unmanned vehicle can ensure the safety and privacy of the machine itself and the delivery task when performing the delivery task. This not only improves the working efficiency of the unmanned vehicle, but also makes the unmanned vehicle more intelligent.

[0104] Referring to Figure 5, which is a schematic diagram of the unmanned vehicle structure of the hardware operating environment involved in the embodiment of the present invention.

[0105] As shown in Figure 5, the unmanned vehicle may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0106] Those skilled in the art will understand that the structure shown in Figure 5 does not constitute a limitation on the autonomous vehicle, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0107] As shown in Figure 5, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and an unmanned vehicle control program.

[0108] In the unmanned vehicle shown in Figure 5, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the unmanned vehicle of the present invention can be set in the unmanned vehicle, and the unmanned vehicle calls the unmanned vehicle control program stored in the memory 1005 through the processor 1001 and performs the following operations:

[0109] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005 and also perform the following operations:

[0110] Obtain the distribution of people within the current detection range;

[0111] When the personnel distribution meets the path correction conditions, the personnel positions within the current detection range are determined, and the personnel obstacle area is determined based on the personnel positions.

[0112] Update the driving path based on the personnel obstacle area;

[0113] The driverless vehicle is controlled to avoid the area containing the people and obstacles according to the updated driving path.

[0114] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005 and also perform the following operations:

[0115] Based on the personnel distribution, determine the number of personnel and the distance between them within the current detection range;

[0116] Select any person within the current detection range as the first target person, and create a team based on the first target person;

[0117] When the distance between other personnel and any member of the team is less than a preset distance, the other personnel are merged into the team;

[0118] When the number of people in the team is greater than or equal to the preset number, and the team's position occupies...

[0119] When determining the path to be traveled by the unmanned vehicle, the distribution of personnel within the current detection range is determined to meet the path correction conditions.

[0120] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005 and also perform the following operations:

[0121] Teams that meet the path correction conditions will be designated as target teams;

[0122] Determine the location of all personnel within the target team;

[0123] 0. Based on the positions of all personnel within the target team, determine the corresponding personnel obstacles.

[0124] The area, wherein the personnel obstacle area includes the personnel locations of all personnel within the target team.

[0125] Furthermore, the processor 1001 can call the unmanned vehicle control program stored in the memory 1005 and also perform the following operations: 5. Obtain the environmental map corresponding to the current detection range;

[0126] The corresponding obstacle area is determined based on the environmental map and the personnel obstacle area;

[0127] The environment map is updated based on the obstacle area;

[0128] Based on the updated environment map, the driving path used to bypass the obstacle area is replanned.

[0129] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005.

[0130] Also perform the following operations:

[0131] Obtain the location information of the second target person in the current delivery task;

[0132] Based on the location information of the second target personnel, determine the target docking point that meets the docking conditions;

[0133] When the unmanned vehicle arrives at the target docking point, it sends a first prompt message to the second target person.

[0134] When the unmanned vehicle is unable to reach the target stop due to path obstruction, a second prompt message is sent to the second target personnel and / or management personnel.

[0135] Furthermore, the processor 1001 can call the unmanned vehicle control program stored in the memory 1005 and also perform the following operations: 0. Obtain the current position of the unmanned vehicle and the position of the second target person, and use them as the first position and the second position respectively;

[0136] Based on the first location and the second location, plan a first path and determine the distance of the first path;

[0137] Calculate the straight-line distance between the first position and the second position;

[0138] When the ratio of the distance traveled to the straight-line distance is less than a preset value, the location of the second target person is taken as the target stopping point;

[0139] When the ratio of the distance traveled to the straight-line distance is greater than or equal to a preset value, a location point that meets the stopping conditions is selected as the target stopping point within a preset range of distance from the second target person.

[0140] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005 and also perform the following operations:

[0141] When the unmanned vehicle malfunctions and is unable to perform its delivery task, it sends a request for help to the management personnel.

[0142] The administrator is prompted to verify their identity, and their identity information is verified.

[0143] Once the identity information of the manager is successfully verified, the manager's management instructions are received and executed.

[0144] Furthermore, the processor 1001 can call the driverless vehicle control program stored in the memory 1005 and also perform the following operations:

[0145] When the unmanned vehicle receives a new instruction while executing other instructions, or when the unmanned vehicle receives multiple instructions simultaneously;

[0146] Determine the identity of the person who initiated the command;

[0147] When the initiator of the instruction includes an administrator, the instruction initiated by the administrator shall be executed first.

[0148] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0149] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0150] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of the present invention.

[0151] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for controlling an unmanned vehicle, characterized in that, An autonomous vehicle control method, applied to unmanned vehicles, includes: acquiring the distribution of personnel within a current detection range; determining the number of personnel and the distance between them based on the personnel distribution; selecting any person within the current detection range as a first target person and creating a team based on the first target person; merging other personnel into the team when the distance between other personnel and any person in the team is less than a preset distance; determining that the personnel distribution within the current detection range meets a path correction condition when the number of personnel in the team is greater than or equal to a preset number, and the team's position occupies the path to be traveled by the unmanned vehicle; determining the corresponding personnel position within the current detection range when the personnel distribution meets the path correction condition, and determining a personnel obstacle area based on the personnel position; updating the driving path based on the personnel obstacle area; and controlling the unmanned vehicle to avoid the personnel obstacle area according to the updated driving path.

2. The unmanned vehicle control method as described in claim 1, characterized in that, The step of determining the personnel positions within the current detection range and determining the personnel obstacle area based on the personnel positions includes: designating the team that meets the path correction conditions as the target team; determining the personnel positions of all personnel within the target team; and determining the corresponding personnel obstacle area based on the personnel positions of all personnel within the target team, wherein the personnel obstacle area includes the personnel positions of all personnel within the target team.

3. The unmanned vehicle control method as described in claim 1, characterized in that, The step of updating the driving path based on the personnel obstacle area includes: obtaining an environmental map corresponding to the current detection range; determining the corresponding obstacle area based on the environmental map and the personnel obstacle area; updating the environmental map based on the obstacle area; and replanning the driving path to bypass the obstacle area based on the updated environmental map.

4. The unmanned vehicle control method according to any one of claims 1 to 3, characterized in that, After the step of controlling the unmanned vehicle to avoid the area of ​​obstacles caused by people according to the updated driving path, the method further includes: obtaining the location information of the second target person in the current delivery task; determining a target stopping point that meets the stopping conditions based on the location information of the second target person; sending a first prompt message to the second target person when the unmanned vehicle arrives at the target stopping point; and sending a second prompt message to the second target person and / or the management personnel when the unmanned vehicle cannot reach the target stopping point due to path obstruction.

5. The unmanned vehicle control method as described in claim 4, characterized in that, The step of determining a target stopping point that meets the stopping conditions based on the location information of the second target person includes: obtaining the current position of the unmanned vehicle and the position of the second target person, and respectively designating them as a first position and a second position; planning a first path and determining the distance of the first path based on the first position and the second position; calculating the straight-line distance between the first position and the second position; when the ratio of the distance to the straight-line distance is less than a preset value, designating the position of the second target person as the target stopping point; when the ratio of the distance to the straight-line distance is greater than or equal to the preset value, selecting a location point that meets the stopping conditions within a preset range from the second target person as the target stopping point.

6. The unmanned vehicle control method according to any one of claims 1 to 3, characterized in that, The unmanned vehicle control method further includes: when the unmanned vehicle malfunctions and cannot perform the delivery task normally, sending a request for help to the manager; prompting the manager to verify identity and verifying the manager's identity information; and receiving and executing the manager's management instructions after the manager's identity information is successfully verified.

7. The unmanned vehicle control method according to any one of claims 1 to 3, characterized in that, The unmanned vehicle control method further includes: when the unmanned vehicle receives a new instruction while executing other instructions, or when the unmanned vehicle receives multiple instructions simultaneously; determining the identity of the instruction initiator; and when the instruction initiator includes a manager, prioritizing the execution of instructions initiated by the manager.

8. An unmanned vehicle, characterized in that, The unmanned vehicle includes: a memory, a processor, and an unmanned vehicle control program stored in the memory and executable on the processor, the unmanned vehicle control program being configured to implement the steps of the unmanned vehicle control method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an unmanned vehicle control program, which, when executed by a processor, implements the steps of the unmanned vehicle control method as described in any one of claims 1 to 7.

Images