Unmanned logistics vehicle steering control method and device, computer equipment and storage medium

Abstract

The invention relates to an unmanned logistics vehicle steering control method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring state information and environment information of a vehicle; respective steering cost of various preset steering modes is calculated according to the state information and the environment information, wherein the various preset steering modes comprise Ackerman steering, front and back double-steering and bidirectional driving; the steering mode of the current vehicle is obtained, if the steering mode with the minimum steering cost is different from the current steering mode and the cost difference between the steering mode with the minimum steering cost and the current steering mode is larger than a preset switching threshold value, the steering mode is determined as a target steering mode, and otherwise, the current steering mode is maintained; and controlling the vehicle to run in the target steering mode. By the adoption of the method, the unmanned logistics vehicle can autonomously select the optimal steering mode, frequent mode switching is avoided, and the driving efficiency and smoothness in different scenes are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a steering control method, device, computer equipment, and storage medium suitable for unmanned logistics vehicles. Background Technology

[0002] With the rapid development of autonomous driving technology, unmanned logistics vehicles are increasingly being used in scenarios such as express delivery and industrial park logistics. In order to adapt to different operating environments, unmanned logistics vehicles usually need to have multiple steering modes, such as Ackerman steering suitable for high-speed urban roads, and front-to-back dual-turn or bidirectional driving suitable for narrow industrial park roads.

[0003] However, existing steering control solutions for unmanned logistics vehicles have the following shortcomings: most solutions only support a single steering mode, or require manual intervention when switching modes, and cannot autonomously and flexibly select the optimal steering method based on real-time road conditions, vehicle status, and planned routes. This results in low driving efficiency and poor smoothness in complex road conditions with varying speeds and widths, making it difficult to complete logistics tasks efficiently and autonomously. Therefore, there is an urgent need for a control method that can adapt to changes in the scene and smoothly switch steering modes. Summary of the Invention

[0004] Therefore, it is necessary to provide a steering control method, device, computer equipment, and storage medium for unmanned logistics vehicles to address the aforementioned technical problems.

[0005] A steering control method for an unmanned logistics vehicle, the method comprising:

[0006] Acquire vehicle status information and information about the surrounding environment; Based on the state information and environmental information, the steering costs of various preset steering methods are calculated; wherein, the various preset steering methods include Ackerman steering, front and rear dual-turn steering, and bidirectional driving; Obtain the current vehicle's steering mode, and select a target steering method based on the steering cost and the current steering mode; wherein, if the steering method with the lowest steering cost is different from the current steering mode and the difference between their steering costs is greater than a preset switching threshold, then the steering method with the lowest steering cost is determined as the target steering method; otherwise, the current steering mode is maintained as the target steering method. Control the vehicle to travel in the target steering manner.

[0007] In one embodiment, the method further includes: calculating the steering cost of each steering mode based on the state information and environmental information using a preset cost function; the cost function is expressed as: Cost = a v + b r + c k + d l Where Cost is the turning cost, v is the vehicle speed, r is the road type information, k is the road curvature, l is the planned path length, and a, b, c, and d are preset weight coefficients.

[0008] In one embodiment, the method further includes: dynamically adjusting the weighting coefficients a, b, c, and d based on the vehicle's current speed range and / or current road type.

[0009] In one embodiment, dynamically adjusting the weight coefficients a, b, c, and d includes: increasing the weight coefficient a corresponding to the vehicle speed v when the current vehicle speed is higher than a first speed threshold; and / or increasing the weight coefficient c corresponding to the road curvature k when the current road curvature is greater than a first curvature threshold.

[0010] In one embodiment, the method further includes: predicting the vehicle's predicted state information within a future preset time window based on the vehicle's historical state information, current state information, and planned path; calculating the steering cost of each of the multiple preset steering modes includes: calculating the cumulative steering cost of each preset steering mode within the future preset time window based on the predicted state information.

[0011] In one embodiment, the state information is obtained through a high-precision positioning module and a chassis module, and the environmental information is obtained through a perception fusion module and a vector map module; wherein, the high-precision positioning module is used to obtain the vehicle's pose information in the map from GPS and IMU sensors; the perception fusion module is used to obtain environmental and obstacle information around the vehicle from LiDAR and camera sensors; the vector map module is used to provide road information; and the chassis module is used to provide vehicle speed information.

[0012] In one embodiment, when the target steering mode is Ackerman steering, the vehicle is controlled to drive in Ackerman steering mode; when the target steering mode is front and rear dual steering, the vehicle is controlled to drive in front and rear dual steering mode; when the target steering mode is bidirectional driving, the vehicle is controlled to drive in bidirectional driving mode.

[0013] An unmanned logistics vehicle steering control device, the device comprising: The information acquisition module is used to acquire vehicle status information and environmental information around the vehicle; The cost calculation module is used to calculate the steering cost of various preset steering modes based on the state information and environmental information; wherein, the various preset steering modes include Ackerman steering, front and rear dual-turn steering, and bidirectional driving; The steering control module is used to obtain the current vehicle's steering mode, select a target steering method based on the steering cost and the current steering mode, and control the vehicle to drive in the target steering method; wherein, if the steering method with the lowest steering cost is different from the current steering mode and the difference in steering cost between the two is greater than a preset switching threshold, the steering control module determines the steering method with the lowest steering cost as the target steering method; otherwise, it maintains the current steering mode as the target steering method.

[0014] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the methods described above.

[0015] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0016] The aforementioned unmanned logistics vehicle steering control method, device, computer equipment, and storage medium acquire information about the vehicle's own state and surrounding environment, calculate the cost of different steering modes based on this information, and introduce a hysteresis comparison mechanism based on the current steering mode to select the final steering mode. This method enables the unmanned logistics vehicle to autonomously and flexibly switch to the optimal steering mode in different scenarios such as high speed and low speed, wide and narrow spaces, while effectively avoiding frequent mode switching caused by parameter fluctuations, significantly improving the vehicle's driving efficiency, smoothness, and fluidity in complex road conditions. Attached Figure Description

[0017] Figure 1 This is an application scenario diagram of the steering control method for an unmanned logistics vehicle in one embodiment; Figure 2 This is a flowchart illustrating the steering control method for an unmanned logistics vehicle in one embodiment; Figure 3 This is a structural block diagram of the steering control device for an unmanned logistics vehicle in one embodiment. Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The unmanned logistics vehicle steering control method provided in this application can be applied to, for example... Figure 1In the application environment shown, the unmanned logistics vehicle 102 communicates with the cloud server 104 via a network. The unmanned logistics vehicle itself is equipped with various sensors and computing units, including a high-precision positioning module, a perception fusion module, a vector mapping module, a chassis module, and a planning module, used to perceive the environment, plan paths, and control vehicle movement. The cloud server can provide high-precision map data, remote monitoring, and scheduling commands. The terminal can be a tablet or smartphone for manual monitoring or intervention.

[0020] A steering control method for an unmanned logistics vehicle is provided, which can be applied to... Figure 1 Taking unmanned logistics vehicles as an example, the following steps are included: Step 202: Obtain the vehicle's status information and the environmental information surrounding the vehicle.

[0021] Specifically, vehicle status information may include current speed and vehicle pose (position and attitude angle). Environmental information may include road type (such as urban roads, park roads, U-turn sections, dead-end roads, etc.), road curvature, the position and speed of surrounding obstacles, and the planned path length given by the planning module. This information is obtained in real time through onboard sensors and a positioning module.

[0022] Step 204: Calculate the steering cost of various preset steering modes based on the status and environmental information. These preset steering modes include Ackermann steering, dual-direction steering (front and rear turns), and bidirectional driving.

[0023] Ackerman steering is suitable for regular urban roads, characterized by a large turning radius and stable driving. Dual-turn steering is suitable for narrow U-turn sections in industrial parks, enabling small-radius turns and even U-turns on the spot. Two-way steering is suitable for dead-end roads and other scenarios requiring a return trip, allowing vehicles to travel directly in the opposite direction without turning around. For each steering method, the system calculates a cost based on the current environment and vehicle status; this cost reflects the overall cost of using that steering method in that scenario.

[0024] Step 206: Obtain the current vehicle's steering mode and select the target steering method based on the steering cost and the current steering mode.

[0025] If the steering method with the lowest steering cost is different from the current steering mode and the difference in steering cost between the two is greater than a preset switching threshold, then the steering method with the lowest steering cost is determined as the target steering method; otherwise, the current steering mode is maintained as the target steering method.

[0026] This step introduces a hysteresis comparison mechanism. The preset switching threshold is a positive number, such as 0.15. If the newly calculated optimal steering method differs from the currently used steering method, but their cost differences are small, it indicates that the advantages and disadvantages of the two methods are not significant in the current scenario. In this case, switching immediately could easily lead to repeated mode switching due to minor parameter fluctuations, i.e., mode oscillation. By setting a threshold, switching is only performed when the cost of the new method is significantly better than the current method; otherwise, the current method continues to be used. This ensures the smoothness and stability of steering mode switching.

[0027] Step 208: Control the vehicle to drive in the target steering manner.

[0028] This means sending the corresponding steering command to the vehicle's chassis control unit, so that the vehicle performs steering operations according to the determined target steering method.

[0029] In the aforementioned unmanned logistics vehicle steering control method, the cost of different steering methods in a specific scenario is evaluated in real time, and the optimal method is selected based on the hysteresis comparison of the current mode. This enables the unmanned logistics vehicle to flexibly adapt to various working conditions, from high-speed urban roads to narrow park roads, while avoiding unnecessary mode jitter and achieving efficient, smooth, and fluid autonomous driving.

[0030] In one embodiment, the steering cost for each steering mode is calculated based on state information and environmental information using a preset cost function; the cost function is expressed as: Cost = a v + b r + c k + d l In this system, Cost represents the turning cost, v represents the vehicle speed, r represents the road type information, k represents the road curvature, l represents the planned path length, and a, b, c, and d are preset weighting coefficients. Specifically, these can be numerical values ​​assigned to different road types, such as 1 for urban roads, 2 for park roads, 3 for U-turn sections, and 4 for dead-end roads; k represents the road curvature in meters; l represents the planned path length in meters; and a, b, c, and d are preset weighting coefficients used to balance the impact of different factors on the cost. For example, in high-speed scenarios, the weight 'a' for vehicle speed v should be larger to ensure safety; in narrow scenarios, the weights for curvature k and path length l should be larger to ensure passability and efficiency.

[0031] Taking real-world scenarios as examples: In urban roads with high speeds, wide roads, and large turning radii, the cost of Ackerman steering is usually the lowest; in U-turns in parks with large curvatures, the cost of double turns is the lowest; in dead-end roads, the planned path for two-way traffic is the shortest and has the lowest cost.

[0032] In one embodiment, the system further includes dynamically adjusting weighting coefficients a, b, c, and d based on the vehicle's current speed range and / or current road type. Since static weighting coefficients cannot adapt to all scenarios, this embodiment introduces an adaptive mechanism. For example, when the vehicle enters a high-speed driving state, the system automatically increases the weighting coefficient a corresponding to the vehicle speed v, making safety factors dominant; when the vehicle enters a high-curvature road section, it automatically increases the weighting coefficient c corresponding to the curvature k, making turning flexibility dominant. Dynamic adjustment can be implemented based on a preset rule table or fuzzy logic.

[0033] In one embodiment, the specific method for dynamically adjusting the weight coefficients a, b, c, and d includes: when the current vehicle speed is higher than a first speed threshold, increasing the weight coefficient a corresponding to the vehicle speed v. The first speed threshold can be set to 15 kilometers per hour. When the current road curvature is greater than a first curvature threshold, increasing the weight coefficient c corresponding to the road curvature k. The first curvature threshold can be set to 0.2 per meter. In this way, the cost function can adaptively highlight the main contradictions according to real-time operating conditions, thereby making more reasonable steering decisions.

[0034] In one embodiment, a prediction step is included: based on the vehicle's historical state information, current state information, and planned path, predictive state information of the vehicle within a future preset time window is generated. Historical state information may include vehicle speed, position, heading angle, etc., from the past few seconds; by using Kalman filtering or kinematic model extrapolation, the state within the next 1 or 2 seconds can be predicted. Then, when calculating the steering costs of various preset steering modes, the cumulative steering cost of each preset steering mode within the future preset time window is calculated based on the predicted state information. For example, an instantaneous cost can be calculated every 0.1 seconds, and then all instantaneous costs within the window are summed or averaged. This prediction-based decision-making method allows the vehicle to prepare in advance for upcoming road condition changes, such as switching to dual-turn mode before entering a curve, avoiding decision lag caused by perception delays.

[0035] In one embodiment, state information is acquired through a high-precision positioning module and a chassis module, while environmental information is acquired through a perception fusion module and a vector map module. The high-precision positioning module obtains the vehicle's pose information on a map from sensors such as GPS and IMU, achieving centimeter-level accuracy. The perception fusion module obtains environmental and obstacle information surrounding the vehicle from sensors such as LiDAR and cameras, including obstacle location, speed, and size. The vector map module provides road information, such as lane lines, intersections, curvature, and slope. The chassis module provides vehicle dynamic information such as vehicle speed, wheel speed, and steering wheel angle. The planning module then integrates the above information to provide the navigation path the autonomous vehicle needs to take, including a sequence of path points and the corresponding desired speed.

[0036] In one embodiment, the specific operation of controlling vehicle driving according to the target steering mode is as follows: when the target steering mode is Ackerman steering, the vehicle is controlled to drive in Ackerman steering mode, that is, the front wheels steer and the rear wheels follow; when the target steering mode is dual-steering, the vehicle is controlled to drive in both front and rear steering mode, that is, both front and rear wheels can steer, achieving small-radius turns; when the target steering mode is bidirectional driving, the vehicle is controlled to drive in bidirectional driving mode, that is, the vehicle can drive in either direction without turning around. The underlying control algorithms for these steering modes are existing technologies, and the core of this application lies in the autonomous selection and switching based on the scenario.

[0037] It should be understood that, although Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0038] In one embodiment, such as Figure 3 As shown, an unmanned logistics vehicle steering control device is provided, including: an information acquisition module 302, a cost calculation module 304, and a steering control module 306, wherein: Information acquisition module 302 is used to acquire vehicle status information and environmental information around the vehicle; The cost calculation module 304 is used to calculate the steering cost of various preset steering modes based on the status information and environmental information; among which, the various preset steering modes include Ackerman steering, front and rear dual steering, and bidirectional driving; The steering control module 306 is used to obtain the current steering mode of the vehicle, select a target steering method based on the steering cost and the current steering mode, and control the vehicle to drive in the target steering method. If the steering method with the lowest steering cost is different from the current steering mode and the difference in steering cost between the two is greater than a preset switching threshold, the steering control module determines the steering method with the lowest steering cost as the target steering method; otherwise, the current steering mode is maintained as the target steering method.

[0039] The specific limitations of this device can be found in the above description of the steering control method for unmanned logistics vehicles, and will not be repeated here. Each module in the aforementioned device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0040] In one embodiment, a computer device is provided, which may be an in-vehicle computer or a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores high-precision map data, vehicle parameters, historical trajectories, etc. The network interface is used for communication with external terminals, such as cloud servers, via a network connection. When the computer program is executed by the processor, it implements a steering control method for an unmanned logistics vehicle.

[0041] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0042] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0043] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0044] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0045] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0046] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A steering control method for an unmanned logistics vehicle, characterized in that, The method includes: Acquire vehicle status information and information about the surrounding environment; Based on the state information and environmental information, the steering costs of various preset steering methods are calculated; wherein, the various preset steering methods include Ackerman steering, front and rear dual-turn steering, and bidirectional driving; Obtain the current vehicle's steering mode, and select a target steering method based on the steering cost and the current steering mode; wherein, if the steering method with the lowest steering cost is different from the current steering mode and the difference between their steering costs is greater than a preset switching threshold, then the steering method with the lowest steering cost is determined as the target steering method; otherwise, the current steering mode is maintained as the target steering method. Control the vehicle to travel in the target steering manner.

2. The method according to claim 1, characterized in that, Calculate the steering costs for various preset steering modes, including: Based on the state information and environmental information, the steering cost for each steering mode is calculated using a preset cost function; the cost function is expressed as: Cost = a v + b r + c k + d l Where Cost is the turning cost, v is the vehicle speed, r is the road type information, k is the road curvature, l is the planned path length, and a, b, c, and d are preset weight coefficients.

3. The method according to claim 1, characterized in that, The method also includes: The weighting coefficients a, b, c, and d are dynamically adjusted based on the vehicle's current speed range and / or the current road type.

4. The method according to claim 3, characterized in that, Dynamically adjusting the weight coefficients a, b, c, and d includes: When the current vehicle speed is higher than the first speed threshold, the weighting coefficient a corresponding to the vehicle speed v is increased; and / or, When the current road curvature is greater than the first curvature threshold, the weighting coefficient c corresponding to the road curvature k is increased.

5. The method according to claim 1, characterized in that, The method further includes: Based on the vehicle's historical status information, current status information, and planned path, predict the vehicle's predicted status information within a future preset time window. The calculation of the steering cost of each of the various preset steering modes includes: Based on the predicted state information, the cumulative turning cost for each preset turning mode is calculated within the preset future time window.

6. The method according to claim 1, characterized in that, The status information is obtained through a high-precision positioning module and a chassis module, and the environmental information is obtained through a perception fusion module and a vector map module. The high-precision positioning module obtains the vehicle's pose information on the map from GPS and IMU sensors. The perception fusion module obtains environmental and obstacle information around the vehicle from LiDAR and camera sensors. The vector map module provides road information, and the chassis module provides vehicle speed information.

7. The method according to claim 1, characterized in that, When the target steering mode is Ackerman steering, the vehicle is controlled to drive in Ackerman steering mode; when the target steering mode is front and rear dual steering, the vehicle is controlled to drive in front and rear dual steering mode; when the target steering mode is bidirectional driving, the vehicle is controlled to drive in bidirectional driving mode.

8. A steering control device for an unmanned logistics vehicle, characterized in that, The device includes: The information acquisition module is used to acquire vehicle status information and environmental information around the vehicle; The cost calculation module is used to calculate the steering cost of various preset steering modes based on the state information and environmental information; wherein, the various preset steering modes include Ackerman steering, front and rear dual-turn steering, and bidirectional driving; The steering control module is used to obtain the current vehicle's steering mode, select a target steering method based on the steering cost and the current steering mode, and control the vehicle to drive in the target steering method; wherein, if the steering method with the lowest steering cost is different from the current steering mode and the difference in steering cost between the two is greater than a preset switching threshold, the steering control module determines the steering method with the lowest steering cost as the target steering method; otherwise, it maintains the current steering mode as the target steering method.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images