Unmanned logistics vehicle interaction control method and system

Abstract

The invention provides an unmanned logistics vehicle interaction control method and system, and the method comprises the steps: determining the driving direction of a vehicle in a target region road section when determining that the vehicle enters the target region road section; based on the driving direction of the vehicle in the target area road section, whether other target vehicles exist or not is judged through driving area point cloud data obtained in real time, and the vehicle is controlled to execute different driving strategies; when the vehicle passes through the target area road section based on different driving strategies, the dynamic obstacle is predicted in real time, the motion trend of the dynamic obstacle is obtained, whether interaction exists between the vehicle and the dynamic obstacle is judged, and the vehicle is controlled to execute different interaction strategies. The problem that in the prior art, an unmanned logistics vehicle does not have a flexible executable passing strategy at a fork road in a complex environment, so that the passing safety of the unmanned logistics vehicle is poor is solved. The unmanned logistics vehicle can sense complex road conditions and environments and flexibly execute passing strategies, and the passing safety of the unmanned logistics vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of interactive control of unmanned logistics vehicles, and in particular to an interactive control method and system for unmanned logistics vehicles. Background Art

[0002] In closed industrial parks, unmanned logistics vehicles are increasingly used, especially in complex scenarios such as when the factory door is close to the main road, vehicles drive directly from indoors to the main road, and there are serious visual obstructions. The safety and efficiency game of two-vehicle interaction at the fork in the road is becoming increasingly prominent, so a more flexible end-to-end strategy needs to be formulated to solve the vehicle interaction problem.

[0003] At present, the existing technology mainly adopts the left-turn protection strategy, that is, the turning vehicle first stops to confirm whether there are vehicles passing in the straight area of ​​the main road, and then starts the vehicle to pass after confirming that the area is safe. The problem is that it will seriously affect the traffic efficiency of the turning vehicle lane. In addition, during the time of entering the main road after restarting again, collisions with vehicles on the main road often occur. Due to the lack of flexible and executable traffic strategies, there is a problem of poor traffic safety for unmanned logistics vehicles. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an interactive control method and system for an unmanned logistics vehicle, which enables the unmanned logistics vehicle to perceive complex road conditions and environments and flexibly execute traffic strategies, thereby improving the traffic safety of the unmanned logistics vehicle.

[0005] To achieve the above objectives, an embodiment of the present invention provides an interactive control method for an unmanned logistics vehicle, comprising:

[0006] When it is determined that the vehicle has entered a target area section, determining the driving direction of the vehicle in the target area section;

[0007] Based on the driving direction of the vehicle on the target area section, determine whether there are other target vehicles through the point cloud data of the driving area obtained in real time, and control the vehicle to execute different driving strategies;

[0008] When passing through the target area based on different driving strategies, dynamic obstacles are predicted in real time to obtain the movement trend of dynamic obstacles;

[0009] Based on the movement trend of the dynamic obstacle, it is determined whether there is interaction between the vehicle and the dynamic obstacle, and the vehicle is controlled to execute different interaction strategies.

[0010] Furthermore, when determining that the vehicle enters the target area section, determining the driving direction of the vehicle in the target area section includes:

[0011] Determine the driving direction of the vehicle based on preset map data;

[0012] Based on the driving direction of the vehicle, when it is determined that the vehicle enters a target area section, the driving direction of the vehicle in the target area section is obtained.

[0013] Furthermore, based on the driving direction of the vehicle in the target area section, judging whether there are other target vehicles through the point cloud data of the driving area acquired in real time, and controlling the vehicle to execute different driving strategies include:

[0014] Acquire environmental information of the driving area in real time, and perform three-dimensional coordinate calculation on the environmental information of the driving area to obtain point cloud data of the driving area;

[0015] Based on the point cloud data of the driving area, obtaining point cloud information of other target vehicles;

[0016] Based on the driving direction of the ego vehicle on the road section in the target area and the point cloud information of other target vehicles, the ego vehicle is controlled to execute different driving strategies.

[0017] Furthermore, based on the driving direction of the vehicle on the target area section and the point cloud information of other target vehicles, controlling the vehicle to execute different driving strategies includes:

[0018] The driving direction of the vehicle in the target area section includes: the vehicle goes straight;

[0019] When the vehicle is traveling straight and there are other target vehicles, the vehicle is controlled to reduce the maximum cruising speed to a preset safe speed.

[0020] Furthermore, based on the driving direction of the vehicle on the target area section and the point cloud information of other target vehicles, controlling the vehicle to execute different driving strategies includes:

[0021] The driving direction of the vehicle in the target area section includes: turning of the vehicle;

[0022] If the vehicle turns, when there are other target vehicles, the vehicle is controlled to travel to the stop line and stop, waiting for the other target vehicles to pass.

[0023] Furthermore, when passing through the target area section based on different driving strategies, dynamic obstacles are predicted in real time to obtain the movement trend of the dynamic obstacles, including:

[0024] Based on the point cloud data of the driving area, obtaining dynamic obstacle position point cloud data;

[0025] Based on a preset algorithm, the dynamic obstacle posture point cloud data is clustered and divided to predict the movement trend of the dynamic obstacle.

[0026] Furthermore, based on the movement trend of the dynamic obstacle, it is determined whether there is interaction between the vehicle and the dynamic obstacle, and the vehicle is controlled to execute different interaction strategies, including:

[0027] Based on the movement trend of the dynamic obstacle, determine whether there is interaction between the dynamic obstacle and the vehicle, and obtain a dynamic obstacle interaction prediction result;

[0028] Based on the dynamic obstacle interaction prediction results, the vehicle is controlled to execute different interaction strategies.

[0029] Furthermore, based on the dynamic obstacle interaction prediction result, the vehicle is controlled to execute different interaction strategies, including:

[0030] The dynamic obstacle interaction prediction result includes: existence of interaction;

[0031] If the vehicle interacts with the dynamic obstacle, the current cruising speed of the vehicle is controlled to decrease;

[0032] When the current cruising speed of the vehicle decreases, if there is a risk of collision with the dynamic obstacle, the vehicle is controlled to brake and stop, and the dynamic obstacle prediction result is updated in real time until there is no risk of collision between the vehicle and the dynamic obstacle.

[0033] Furthermore, based on the dynamic obstacle interaction prediction result, the vehicle is controlled to execute different interaction strategies, including:

[0034] The dynamic obstacle interaction prediction results include: no interaction;

[0035] If there is no interaction between the vehicle and the dynamic obstacle, control the vehicle to travel at the current cruising speed;

[0036] updating the interaction judgment result between the vehicle and the dynamic obstacle in real time until the vehicle interacts with the dynamic obstacle;

[0037] The dynamic obstacle prediction result is updated in real time until there is a risk of collision between the vehicle and the dynamic obstacle.

[0038] The embodiment of the present invention further provides an interactive control system for an unmanned logistics vehicle, comprising: a driving direction determination module, a first control module, an obstacle prediction module, and a second control module;

[0039] The driving direction determination module is used to determine the driving direction of the vehicle in the target area section when the vehicle enters the target area section;

[0040] The first control module is used to determine whether there are other target vehicles based on the driving direction of the vehicle on the target area section through the point cloud data of the driving area acquired in real time, and control the vehicle to execute different driving strategies;

[0041] The obstacle prediction module is used to predict dynamic obstacles in real time when passing through the target area section based on different driving strategies to obtain the movement trend of the dynamic obstacles;

[0042] The second control module is used to determine whether there is interaction between the ego vehicle and the dynamic obstacle based on the movement trend of the dynamic obstacle, and control the ego vehicle to execute different interaction strategies.

[0043] Beneficial effects:

[0044] It does not rely on additional cloud-side or road-side equipment, but only relies on the vehicle itself to judge the driving direction in the target area section, and then determines whether there are other target vehicles by obtaining point cloud data in the driving area. It combines the driving direction of the vehicle and the judgment of the target vehicle to execute different driving strategies. In addition, it also predicts dynamic obstacles in real time, identifies possible driving risks in advance, and executes corresponding end-to-end interaction strategies. It has good real-time and reliability, effectively reduces interaction risks, and improves vehicle safety. Through end-to-end flexible and executable control strategies, it can realize the demand of stopping when visible, ensure driving safety in situations such as being blocked, and further improve the safety of unmanned logistics vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic flow chart of the steps of an interactive control method for an unmanned logistics vehicle provided in one embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a judgment logic flow of an interactive control method for an unmanned logistics vehicle provided in an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of an application example of an interactive control method for an unmanned logistics vehicle provided by a certain embodiment of the present invention;

[0048] Figure 4 A schematic diagram of the module structure of an unmanned logistics vehicle interactive control system provided in accordance with a certain embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] See also Figure 1, Figure 1 A schematic flow chart of the steps of an interactive control method for an unmanned logistics vehicle provided by an embodiment of the present invention. Figure 1 As shown, the embodiment of the present invention proposes an interactive control method for an unmanned logistics vehicle, including steps 101 to 104, each of which is specifically as follows:

[0052] Step 101, when it is determined that the vehicle enters a target area section, the driving direction of the vehicle in the target area section is determined;

[0053] As an example of this embodiment, the driving direction of the vehicle is determined based on preset map data; based on the driving direction of the vehicle, when the vehicle enters the target area section, the driving direction of the vehicle in the target area section is obtained. A specific implementation method is to obtain map data based on the prior experience of high-precision maps and construct a road model, wherein the map data should include key information such as road geometry, intersection layout, traffic signs and signals, and according to the road model, use RTK (Real-time kinematic, real-time dynamic carrier phase difference technology) and other high-precision positioning technologies to match the driving direction of the vehicle in real time to determine the position of the vehicle in the current road, wherein the map matching algorithm can use the nearest neighbor algorithm and hidden Markov model, etc., which can accurately determine the driving direction of the vehicle in the target area section by analyzing the relationship between the position of the vehicle and the road direction in the map and the connection relationship between adjacent sections.

[0054] Step 102, based on the driving direction of the vehicle on the target area section, judging whether there are other target vehicles through the point cloud data of the driving area acquired in real time, and controlling the vehicle to execute different driving strategies;

[0055] As an example of this embodiment, environmental information of the driving area is acquired in real time, and the three-dimensional coordinates of the environmental information of the driving area are calculated to obtain point cloud data of the driving area; based on the point cloud data of the driving area, point cloud information of other target vehicles is acquired; based on the driving direction of the vehicle on the road section of the target area and the point cloud information of other target vehicles, the vehicle is controlled to execute different driving strategies. A specific implementation method is to use laser radar (LiDAR), camera and millimeter wave radar to obtain environmental information of different ranges and different precisions, such as obtaining three-dimensional point cloud data of the environment through laser radar scanning, capturing images through cameras, extracting feature information in the environment, such as lane lines and traffic signs, etc., using millimeter wave radar to detect surrounding obstacles and vehicles, obtain their distance and speed information, perform pre-processing such as denoising and filtering on the three-dimensional point cloud data of the environment, calculate the three-dimensional coordinates of the processed three-dimensional point cloud data, construct a three-dimensional point cloud map, and then identify other target vehicles through a clustering algorithm. For the identified target vehicles, extract their three-dimensional coordinates and motion trajectory in the point cloud data, predict their possible driving path according to their driving direction and speed, and control the vehicle to execute different driving strategies; in this embodiment, the vehicle uses the advantage of the longitudinal recognition distance of the sensor, and the main road vehicle actively reduces the cruising speed of the vehicle before identifying the risk of interaction with the auxiliary road vehicle, thereby improving the vehicle traffic efficiency while ensuring safety.

[0056] As another example of this embodiment, see Figure 2 , Figure 2 A schematic diagram of a judgment logic flow of an unmanned logistics vehicle interactive control method provided by a certain embodiment of the present invention; it is worth mentioning that in this embodiment, the logic judgment process adopts the following Figure 2 The judgment logic flow diagram of an interactive control method for an unmanned logistics vehicle is explained in detail below and will not be repeated in detail. Figure 2 As shown, the driving direction of the vehicle in the target area section includes: the vehicle goes straight; when the vehicle goes straight and there are other target vehicles, the vehicle is controlled to reduce the maximum cruising speed to a preset safe speed. Figure 3 , Figure 3 A schematic diagram of an application example of an interactive control method for an unmanned logistics vehicle provided by a certain embodiment of the present invention; Figure 3As shown, in this embodiment, an L-shaped fork is used as an example for explanation, which will not be described in detail below. When the vehicle is driving straight at the intersection, it is determined whether there are other vehicles in the L-shaped area. If there are other vehicles, the speed of the vehicle is actively reduced from the maximum cruising speed to the safe speed; if there are no other vehicles, the vehicle is driven at the maximum cruising speed; for example, Car_1 is taken as the vehicle, and Car_1 passes the stop line (blue line segment) in a straight line. If there are other vehicles, the vehicle's maximum cruising speed is reduced to the safe speed; Car_1 passes the stop line (blue line segment) in a straight line. If there are no other vehicles, the vehicle is driven at the maximum cruising speed;

[0057] As another example of this embodiment, the driving direction of the self-vehicle in the target area section includes: the self-vehicle turns; if the self-vehicle turns, when there are other target vehicles, the self-vehicle is controlled to drive to the stop line and stop, waiting for the other target vehicles to pass. A specific implementation method is that when the self-vehicle turns at the interactive intersection, it is determined whether there are other vehicles in the L-shaped area. If there are other vehicles, the self-vehicle drives to the stop line and stops to wait for straight vehicles to pass; if there are no other vehicles, the self-vehicle drives through the stop line at a normal turning speed; for example: take Car_2 as the self-vehicle, Car_2 turns and passes the stop line (blue line segment), if there are other vehicles, it stops and yields; Car_2 turns and passes the stop line (blue line segment), if there are no other vehicles, it passes at a normal speed.

[0058] Step 103, when passing through the target area section based on different driving strategies, dynamic obstacles are predicted in real time to obtain the movement trend of the dynamic obstacles;

[0059] As an example of this embodiment, based on the point cloud data of the driving area, the dynamic obstacle posture point cloud data is obtained; based on the preset algorithm, the dynamic obstacle posture point cloud data is clustered and divided to predict the movement trend of the dynamic obstacle. A specific implementation method is to use the spatial distribution characteristics of the point cloud data of the driving area, combined with the timestamp information, to identify the dynamic obstacles that change relative to the static environment, and then process the precise posture data of the dynamic obstacles by fitting, segmenting and registering the point cloud data, input the dynamic obstacle posture point cloud data into the clustering algorithm, perform clustering division, divide similar points into the same cluster, and obtain the clustering division result. Specifically, according to the characteristics of the dynamic obstacles, the clustering algorithms that can be selected include: K-means and hierarchical clustering, etc.; then, according to the clustering division results, a motion model is established for each dynamic obstacle, and motion features such as speed change, acceleration change and trajectory direction are extracted from the posture point cloud data of the dynamic obstacle. Finally, according to the motion model and motion features of each dynamic obstacle, a deep learning algorithm is used to predict the motion trend of the dynamic obstacle, wherein the deep learning algorithm can use: time series analysis and neural network, etc.

[0060] Step 104: based on the movement trend of the dynamic obstacle, determine whether there is interaction between the ego vehicle and the dynamic obstacle, and control the ego vehicle to execute different interaction strategies.

[0061] As an example of this embodiment, based on the movement trend of the dynamic obstacle, it is determined whether there is interaction between the dynamic obstacle and the vehicle, and a dynamic obstacle interaction prediction result is obtained; based on the dynamic obstacle interaction prediction result, the vehicle is controlled to execute different interaction strategies. A specific implementation method is as follows:

[0062] As another example of this embodiment, the dynamic obstacle interaction prediction result includes: there is interaction; if there is interaction between the vehicle and the dynamic obstacle, control the current cruising speed of the vehicle to reduce; when the current cruising speed of the vehicle is reduced, if there is a risk of collision with the dynamic obstacle, control the vehicle to brake and stop, and update the dynamic obstacle prediction result in real time until there is no risk of collision between the vehicle and the dynamic obstacle. A specific implementation method is that the vehicle needs to perform real-time dynamic obstacle prediction when driving in the L-shaped area. According to the dynamic obstacle interaction prediction result, it is predicted whether the driving trajectory of the target vehicle interacts with the vehicle within a certain period of time. If there is, it will slow down first, and stop and give way immediately when there is a risk of collision. If there is no risk, it will drive normally; after the vehicle stops and gives way, it is also necessary to predict and judge the dynamic obstacle. If there is an interaction risk, the vehicle will continue to stop and give way. If there is no risk, it will drive normally through the courtesy area; specifically, Car_1 and Car_2 vehicles need to perform dynamic obstacle prediction and give way when entering the L-shaped intersection area. In this embodiment, the dynamic obstacle detection algorithm used by vehicles at interactive intersections can effectively reduce the interaction risk and improve the safe passage of vehicles.

[0063] As another example of this embodiment, the dynamic obstacle interaction prediction result includes: no interaction; if there is no interaction between the self-vehicle and the dynamic obstacle, control the self-vehicle to travel at the current cruising speed; update the interaction judgment result between the self-vehicle and the dynamic obstacle in real time until there is interaction between the self-vehicle and the dynamic obstacle; update the dynamic obstacle prediction result in real time until there is a risk of collision between the self-vehicle and the dynamic obstacle. A specific implementation method is to predict whether the target vehicle's driving trajectory interacts with the self-vehicle within a certain period of time based on the dynamic obstacle interaction prediction result. If there is no interaction, the dynamic obstacle interaction prediction result is updated in real time until there is interaction, and the self-vehicle is controlled to change the interaction strategy; in this embodiment, the road right determination in the L-shaped area outside the interactive intersection solves the need for safe passage of vehicles on the main road of unmanned logistics vehicles when there are multiple ramps and ramps are blocked.

[0064] An interactive control method for an unmanned logistics vehicle proposed in an embodiment of the present invention does not rely on additional cloud-side or road-side equipment, but only relies on the vehicle itself to judge the driving direction in the target area section, and then determines whether there are other target vehicles by obtaining point cloud data of the driving area. Different driving strategies are executed in combination with the driving direction of the vehicle itself and the judgment of the target vehicle. In addition, real-time prediction of dynamic obstacles is performed to identify possible driving risks in advance, and corresponding end-to-end interactive strategies are executed. The method has good real-time performance and reliability, effectively reduces interactive risks, and improves the safe passage of vehicles. Through flexible and executable end-to-end control strategies, the demand for stopping as soon as it is visible is realized, and driving safety can be guaranteed under conditions of obstruction, etc., further improving the passage safety of unmanned logistics vehicles.

[0065] Example 2

[0066] See also Figure 4 , Figure 4 The following is a schematic diagram of the module structure of an unmanned logistics vehicle interactive control system provided by an embodiment of the present invention. Figure 4 As shown, the embodiment of the present invention proposes an interactive control system for an unmanned logistics vehicle, including: a driving direction judgment module 401, a first control module 402, an obstacle prediction module 403 and a second control module 404;

[0067] The driving direction determination module 401 is used to determine the driving direction of the vehicle in the target area section when the vehicle enters the target area section;

[0068] The first control module 402 is used to determine whether there are other target vehicles based on the driving direction of the vehicle on the target area section through the point cloud data of the driving area obtained in real time, and control the vehicle to execute different driving strategies;

[0069] The obstacle prediction module 403 is used to predict dynamic obstacles in real time when passing through the target area section based on different driving strategies to obtain the movement trend of the dynamic obstacles;

[0070] The second control module 404 is used to determine whether there is interaction between the ego vehicle and the dynamic obstacle based on the movement trend of the dynamic obstacle, and control the ego vehicle to execute different interaction strategies.

[0071] An interactive control system for an unmanned logistics vehicle proposed in an embodiment of the present invention does not rely on additional cloud-side or road-side equipment, but only relies on the driving direction judgment module of the vehicle itself to judge the driving direction in the target area section, and then judges whether there are other target vehicles by obtaining the point cloud data of the driving area. In combination with the driving direction of the vehicle itself and the judgment of the target vehicle, the first control module executes different driving strategies. In addition, the obstacle prediction module performs real-time prediction of dynamic obstacles, identifies possible driving risks in advance, and executes the corresponding end-to-end interactive strategy through the second control module. It has good real-time performance and reliability, effectively reduces interactive risks, and improves the safe passage of vehicles. Through the flexible and executable end-to-end control strategy, the demand for stopping when visible is realized, and the driving safety can be guaranteed under conditions of obstruction, etc., further improving the passage safety of unmanned logistics vehicles.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0074] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

Claims

1. An interactive control method for an unmanned logistics vehicle, characterized in that: include: When it is determined that the vehicle has entered a target area section, determining the driving direction of the vehicle in the target area section; Based on the driving direction of the vehicle on the target area section, determine whether there are other target vehicles through the point cloud data of the driving area obtained in real time, and control the vehicle to execute different driving strategies; When passing through the target area based on different driving strategies, dynamic obstacles are predicted in real time to obtain the movement trend of dynamic obstacles; Based on the movement trend of the dynamic obstacle, it is determined whether there is interaction between the vehicle and the dynamic obstacle, and the vehicle is controlled to execute different interaction strategies.

2. The interactive control method of an unmanned logistics vehicle according to claim 1, characterized in that: When determining that the vehicle enters the target area section, determining the driving direction of the vehicle in the target area section includes: Determine the driving direction of the vehicle based on preset map data; Based on the driving position of the vehicle, when it is determined that the vehicle enters a target area section, the driving direction of the vehicle in the target area section is obtained.

3. The interactive control method of an unmanned logistics vehicle according to claim 2, characterized in that: Based on the driving direction of the vehicle in the target area section, judging whether there are other target vehicles through the point cloud data of the driving area acquired in real time, and controlling the vehicle to execute different driving strategies, including: Acquire environmental information of the driving area in real time, and perform three-dimensional coordinate calculation on the environmental information of the driving area to obtain point cloud data of the driving area; Based on the point cloud data of the driving area, obtaining point cloud information of other target vehicles; Based on the driving direction of the ego vehicle on the road section in the target area and the point cloud information of other target vehicles, the ego vehicle is controlled to execute different driving strategies.

4. The interactive control method of an unmanned logistics vehicle according to claim 3, characterized in that: The method of controlling the vehicle to execute different driving strategies based on the driving direction of the vehicle on the target area section and the point cloud information of other target vehicles includes: The driving direction of the vehicle in the target area section includes: the vehicle goes straight; When the vehicle is traveling straight and there are other target vehicles, the vehicle is controlled to reduce the maximum cruising speed to a preset safe speed.

5. The interactive control method of an unmanned logistics vehicle according to claim 3, characterized in that: The method of controlling the vehicle to execute different driving strategies based on the driving direction of the vehicle on the target area section and the point cloud information of other target vehicles includes: The driving direction of the vehicle in the target area section includes: turning of the vehicle; If the vehicle turns, when there are other target vehicles, the vehicle is controlled to travel to the stop line and stop, waiting for the other target vehicles to pass.

6. The interactive control method of an unmanned logistics vehicle according to claim 3, characterized in that: When passing through the target area section based on different driving strategies, dynamic obstacles are predicted in real time to obtain the movement trend of the dynamic obstacles, including: Based on the point cloud data of the driving area, obtaining dynamic obstacle position point cloud data; Based on a preset algorithm, the dynamic obstacle posture point cloud data is clustered and divided to predict the movement trend of the dynamic obstacle.

7. The interactive control method of an unmanned logistics vehicle according to claim 1, characterized in that: Based on the movement trend of the dynamic obstacle, it is determined whether the vehicle interacts with the dynamic obstacle, and the vehicle is controlled to execute different interaction strategies, including: Based on the movement trend of the dynamic obstacle, determine whether there is interaction between the dynamic obstacle and the vehicle, and obtain a dynamic obstacle interaction prediction result; Based on the dynamic obstacle interaction prediction results, the vehicle is controlled to execute different interaction strategies.

8. The interactive control method of an unmanned logistics vehicle according to claim 7, characterized in that: Based on the dynamic obstacle interaction prediction results, the vehicle is controlled to execute different interaction strategies, including: The dynamic obstacle interaction prediction result includes: existence of interaction; If the vehicle interacts with the dynamic obstacle, the current cruising speed of the vehicle is controlled to decrease; When the current cruising speed of the vehicle decreases, if there is a risk of collision with the dynamic obstacle, the vehicle is controlled to brake and stop, and the dynamic obstacle prediction result is updated in real time until there is no risk of collision between the vehicle and the dynamic obstacle.

9. The interactive control method of an unmanned logistics vehicle according to claim 7, characterized in that: Based on the dynamic obstacle interaction prediction results, the vehicle is controlled to execute different interaction strategies, including: The dynamic obstacle interaction prediction results include: no interaction; If there is no interaction between the vehicle and the dynamic obstacle, control the vehicle to travel at the current cruising speed; updating the interaction judgment result between the vehicle and the dynamic obstacle in real time until the vehicle interacts with the dynamic obstacle; The dynamic obstacle prediction result is updated in real time until there is a risk of collision between the vehicle and the dynamic obstacle.

10. An interactive control system for an unmanned logistics vehicle, characterized in that: Executing an interactive control method for an unmanned logistics vehicle as claimed in any one of claims 1 to 9, comprising: A driving direction determination module, a first control module, an obstacle prediction module, and a second control module; The driving direction determination module is used to determine the driving direction of the vehicle in the target area section when the vehicle enters the target area section; The first control module is used to determine whether there are other target vehicles based on the driving direction of the vehicle on the target area section through the point cloud data of the driving area acquired in real time, and control the vehicle to execute different driving strategies; The obstacle prediction module is used to predict dynamic obstacles in real time when passing through the target area section based on different driving strategies to obtain the movement trend of the dynamic obstacles; The second control module is used to determine whether there is interaction between the ego vehicle and the dynamic obstacle based on the movement trend of the dynamic obstacle, and control the ego vehicle to execute different interaction strategies.

Images