Method and equipment for guiding vehicle to enter platform trailer

Abstract

The invention discloses a method and equipment for guiding a vehicle to enter a platform trailer, belongs to the field of data processing, and aims to solve the problems of low efficiency and low safety when the vehicle enters the platform trailer, and the method comprises the steps: obtaining images of a trailer platform and a loading and unloading ramp; extracting the network model through physical parameters to obtain physical parameter information of the trailer flat plate and the loading and unloading ramp; constructing a trailer space coordinate model according to the physical parameter information of the trailer flat plate and the loading and unloading ramp; according to the vehicle operation parameters of the towed vehicle and the trailer space coordinate model, theoretical driving information of the towed vehicle on the trailer flat plate is generated; extracting the theoretical driving track, and generating a theoretical position matrix of the dragged vehicle; and according to the theoretical driving speed interval, the theoretical position matrix and the trailer space coordinate model, determining guiding information of the towed vehicle driving into the platform trailer. Through a visual system, deep learning and man-machine interaction, the efficiency of driving the vehicle into the platform trailer is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for guiding a vehicle into a flatbed trailer. Background Art

[0002] Flatbed carpooling refers to transporting multiple small vehicles by splicing them onto a large flatbed trailer, thereby effectively utilizing space, reducing transportation costs, and improving transportation efficiency. This mode of transportation has obvious advantages in the automobile towing industry, especially in the context of urban traffic congestion and increasing environmental protection requirements.

[0003] Currently, drivers must maneuver the towed vehicle to a designated location on a large flatbed trailer, and the journey time on the flatbed is lengthy. This is because the trailer flatbeds are relatively long and have two or more decks. The higher the number of decks, the higher the driver requirements and the greater the risk. During this process, the large flatbed trailer pre-deploys the loading ramp. Once deployed, the trailer flatbed closest to the ramp (for example, on the first or second deck) is tilted, lowering its rear end and raising its front end. This reduces the angle between the trailer flatbed and the ramp, facilitating the towed vehicle's transfer to the trailer flatbed. The towed vehicle then continues driving on the level trailer flatbed to its designated location, completing the task of loading the flatbed onto the trailer.

[0004] However, the process of loading a vehicle onto a flatbed trailer relies heavily on manual guidance, which can easily lead to vehicle collisions. For example, drivers typically rely on their experience to control the towed vehicle by visually observing the relative position of the trailer flatbed and the towed vehicle. This results in low efficiency and poor safety during the loading process. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for guiding a vehicle onto a flatbed trailer, which are used to solve the problems of low efficiency and poor safety during the vehicle loading process.

[0006] The embodiments of this application adopt the following technical solutions: On the one hand, an embodiment of the present application provides a method for guiding a vehicle to enter a flatbed trailer, the method comprising: upon receiving a request for guiding the trailer flatbed to enter, obtaining an image of the trailer flatbed and a loading and unloading ramp; recognizing the image through a pre-trained physical parameter extraction network model to obtain physical parameter information of the trailer flatbed and the loading and unloading ramp; the physical parameter information includes length, width, inclination angle and safety edge distance; constructing a trailer space coordinate model based on the physical parameter information of the trailer flatbed and the loading and unloading ramp; generating theoretical driving information of the towed vehicle on the trailer flatbed based on the vehicle operating parameters of the towed vehicle and the trailer space coordinate model; the theoretical driving information includes a theoretical driving trajectory and a theoretical driving speed range; converting the theoretical driving trajectory to generate a theoretical position matrix of the towed vehicle; determining the guidance information for the towed vehicle to enter the flatbed trailer based on the theoretical driving speed range, the theoretical position matrix and the trailer space coordinate model.

[0007] In one example, the spatial coordinate model of the trailer flatbed is constructed based on the physical parameter information of the trailer flatbed, specifically including: determining the geometric center of the horizontal trailer flatbed as the origin of the global coordinate system, and determining the length direction, width direction and height direction of the horizontal trailer flatbed as the coordinate axis direction; determining the spatial coordinates of the horizontal trailer flatbed based on the physical parameter information of the horizontal trailer flatbed; determining the coordinates of the hinge point between the inclined trailer flatbed and the horizontal trailer flatbed; calculating the spatial coordinates of the inclined trailer flatbed based on the physical parameter information of the inclined trailer flatbed and the hinge point coordinates; determining the coordinates of the connection point between the loading and unloading ramp and the inclined trailer flatbed; determining the spatial coordinates of the loading and unloading ramp based on the physical parameter information of the loading and unloading ramp and the connection point coordinates; performing three-dimensional grid representation on the spatial coordinates of the horizontal trailer flatbed, the spatial coordinates of the inclined trailer flatbed and the spatial coordinates of the loading and unloading ramp to obtain the spatial coordinate model of the trailer flatbed.

[0008] In one example, the theoretical driving information of the towed vehicle on the trailer flatbed is generated based on the vehicle operating parameters of the towed vehicle and the trailer spatial coordinate model, specifically including: determining the similarity between the right triangle formed by the inclined trailer flatbed and the right triangle formed by the loading and unloading ramp; mapping the similarity to obtain the smoothness of the transition between the inclined trailer flatbed and the loading and unloading ramp; the smoothness is used to represent the flatness of the transition angle at the connection between the loading and unloading ramp and the inclined trailer flatbed; obtaining the driving speed constraint of the towed vehicle based on the smoothness and the vehicle operating parameters; determining the effective driving area of ​​the trailer flatbed based on the trailer spatial coordinate model and the safety edge distance; generating the theoretical driving speed range and theoretical driving trajectory of the towed vehicle based on the trailer trajectory equation, the driving speed constraint and the effective driving area.

[0009] In one example, determining the similarity between the right triangle formed by the tilted trailer flatbed and the right triangle formed by the loading and unloading ramp specifically includes: calculating the angle difference between the tilt angle of the tilted trailer flatbed and the tilt angle of the loading and unloading ramp, the length ratio between the length of the tilted trailer flatbed and the length of the loading and unloading ramp, and the height ratio between the front end height of the tilted trailer flatbed and the front end height of the loading and unloading ramp; and performing a weighted summation of the angle difference, length ratio, and height ratio according to a similarity scoring function to obtain the similarity between the right triangle formed by the tilted trailer flatbed and the right triangle formed by the loading and unloading ramp.

[0010] In one example, the driving speed constraint of the towed vehicle is obtained based on the smoothness and the vehicle operating parameters, specifically including: calculating the average angle of the inclination angle of the tilted trailer flatbed and the inclination angle of the loading and unloading ramp; according to a preset maximum driving speed constraint function, the braking coefficient of the towed vehicle, the length and the average angle of the tilted trailer flatbed are calculated to obtain a first maximum driving speed; the maximum driving speed constraint function meets the braking safety requirement; according to a preset minimum driving speed constraint function, the minimum stable power and the average angle of the engine of the towed vehicle are calculated to obtain a first minimum driving speed; the minimum driving speed constraint function meets the power requirement for overcoming slope resistance; the driving speed constraint of the towed vehicle is obtained based on the smoothness, the first maximum driving speed and the first minimum driving speed.

[0011] In one example, the method of obtaining a speed constraint of the towed vehicle based on the smoothness, a first maximum speed, and a first minimum speed specifically includes: determining the speed constraint of the towed vehicle based on the first maximum speed and the first minimum speed when the smoothness is a smooth transition; determining a safety factor of the towed vehicle based on the angular difference between the inclination angle of the tilted trailer platform and the inclination angle of the loading and unloading ramp when the smoothness is substantially smooth; a larger ratio indicates a smaller safety factor; calculating the product of the first maximum speed and the safety factor to obtain a second maximum speed; determining the speed constraint of the towed vehicle based on the second maximum speed and the first minimum speed; and determining the target inclination angle based on the maximum of the inclination angle of the tilted trailer platform and the inclination angle of the loading and unloading ramp when the smoothness is a non-smooth transition. Determining a second minimum speed based on the preset minimum speed constraint function and the target inclination speed; and determining the speed constraint of the towed vehicle based on the second maximum speed and the second minimum speed.

[0012] In one example, a theoretical driving speed range and a theoretical driving trajectory of the towed vehicle are generated based on the trailer trajectory equation, the driving speed constraint and the effective driving area, specifically including: converting the driving speed constraint value into a theoretical driving speed range; obtaining a driving distance sequence of the towed vehicle according to a preset time window and the average speed of the theoretical driving speed range; the driving distance sequence is used to quantify the position progress of the vehicle at different times; substituting the driving distance sequence into the trailer trajectory equation to obtain a trajectory sequence of the towed vehicle; and determining the lateral boundary of the effective driving area as a constraint condition of the trajectory sequence to obtain the theoretical driving trajectory of the towed vehicle.

[0013] In one example, the theoretical driving trajectory is extracted to generate a theoretical position matrix of the towed vehicle, specifically including: extracting position coordinate data of each time point in the trajectory sequence corresponding to the theoretical driving trajectory; converting each time point and the position coordinate data of each time point into an initial theoretical position matrix; and when the parking tilt angle of the trailer is greater than a parking angle threshold, adjusting the position coordinates of the initial theoretical position matrix according to the parking tilt angle of the trailer to obtain the theoretical position matrix.

[0014] In one example, the guidance information for the towed vehicle to enter the flatbed trailer is determined based on the theoretical driving speed range, the theoretical position matrix and the trailer space coordinate model, specifically including: constructing a virtual model of the trailer space coordinate model; connecting the discrete points of the theoretical position matrix as target points of the virtual model to construct a virtual guide line; calculating the difference between the driving position of the towed vehicle at the current time point and the matrix target position, and predicting the vehicle driving speed based on the difference when the difference is greater than a preset difference threshold; rendering the guide line as a highlighted line with an arrow to display the corresponding line color according to the vehicle driving speed; wherein the arrow direction indicates the driving direction, and the line color changes dynamically according to the speed constraint of the theoretical driving speed range; when the towed vehicle approaches the edge of the effective driving area, the edge area is flashed and highlighted in the virtual model.

[0015] On the other hand, an embodiment of the present application provides a guiding device for a vehicle to enter a flatbed trailer, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-described methods for guiding a vehicle to enter a flatbed trailer.

[0016] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: Through a logical chain of visual systems, deep learning, spatial modeling, trajectory generation, matrix conversion, driving position recognition, and human-computer interaction guidance, precise control of the vehicle's entry into the Daban carpooling process is achieved.

[0017] By building a physical parameter extraction network model combined with an image recognition vision solution, there is no need for manual and precise pre-measurement of trailer parameters or on-site input. The vision system automatically adapts to the on-site environment and can accurately perceive even in adverse weather (night, rain).

[0018] A trailer spatial coordinate model is constructed based on the physical parameters of the trailer flatbed and loading ramp. This quantifies the trailer's spatial boundaries and safety constraints, preventing risks such as slippage and collisions caused by vehicle overstepping or angular deviation. The modular design of physical parameters allows for adaptability to different trailer flatbed sizes (e.g., trailers with varying load capacities and tilt angles), providing strong scenario adaptability.

[0019] Based on the spatial coordinate model, the theoretical driving trajectory and speed range are generated in combination with the operating parameters of the towed vehicle, which can guide the vehicle to drive smoothly along the optimal path and speed, reducing errors in manual operation (such as understeering or oversteering, and collisions caused by sudden speed changes).

[0020] The theoretical position matrix, as quantifiable coordinate points, enables the construction of virtual guide lines, providing guidance for drivers entering a flatbed. This is particularly helpful for new drivers unfamiliar with flatbed trailering. This improves efficiency while ensuring the towed vehicle is safely and accurately driven to the designated location within the flatbed trailer. Furthermore, the theoretical position matrix facilitates real-time verification of deviations between the actual position and the theoretical trajectory, enabling dynamic deviation correction.

[0021] By generating AR guidance information, the guidance information is made more intuitive, easy to understand and execute, reducing the driver's operating burden and achieving intuitive human-computer interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which: Figure 1 A schematic flow chart of a method for guiding a vehicle onto a flatbed trailer provided in an embodiment of the present application; Figure 2 A schematic structural diagram of a guiding device for a vehicle entering a flatbed trailer provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a flow chart of a method for guiding a vehicle onto a flatbed trailer provided by an embodiment of the present application. Certain input parameters or intermediate results in the process allow for manual intervention and adjustment to help improve accuracy.

[0026] The analysis method involved in the embodiments of the present application can be implemented as a guiding server. For the convenience of understanding and description, the following embodiments are described in detail using the server as an example.

[0027] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make any specific restrictions on this.

[0028] Figure 1 The process in includes the following steps: S101: upon receiving a trailer flatbed driving guidance request, acquiring images of the trailer flatbed and the loading and unloading ramp.

[0029] It should be noted that visual images are collected by visual cameras deployed on the trailer flatbed, and users can also upload the captured images.

[0030] S102: Recognize the image using a pre-trained physical parameter extraction network model to obtain physical parameter information of the trailer flatbed and the loading and unloading ramp; the physical parameter information includes length, width, tilt angle, and safety edge distance.

[0031] In some embodiments of the present application, it is necessary to pre-train a physical parameter extraction network model, and a deep learning model (such as CNN, Transformer) can learn the mapping relationship from raw pixels to physical parameters through end-to-end training.

[0032] For example, feature extraction: Convolutional layers automatically learn to identify key structures in an image (e.g., trailer edges, ramp outlines, tire positions). Geometric reasoning: Deep layers of the network incorporate spatial constraints (e.g., perspective geometry, dimensional correlation) to regress physical quantities. Multi-task output: Identify multiple parameters (width, angle, distance, etc.).

[0033] It should be noted that the network architecture can be image input, ResNet backbone, global average pooling, fully connected layers, and parameter output. The training data includes a large number of annotated images and annotated physical parameter values ​​(for example, manually measured trailer width, length, angle, and set edge distance).

[0034] Furthermore, data enhancement strategies can be adopted during the training process to simulate rain, fog, or nighttime conditions (e.g., adjusting brightness, adding noise) for training.

[0035] It should be noted that a multimodal fusion solution can also be adopted. When the lidar is deployed on the trailer, the image and point cloud data can be input into the network model at the same time. At this time, the network model is a dual-branch network, which can process the image and 3D point cloud separately, and output parameters after feature fusion.

[0036] In some embodiments of the present application, another training method can be used. The trained physical parameter extraction network model can be used to identify different image regions (e.g., the trailer flatbed and loading ramp on each floor) and output depth information. The system then combines this depth information with the LiDAR point cloud data to construct a three-dimensional spatial model. The physical parameters of the trailer flatbed and loading ramp are then extracted from the three-dimensional spatial model.

[0037] S103: Constructing a trailer space coordinate model based on the physical parameter information of the trailer flatbed and the loading and unloading ramp.

[0038] It should be noted that the guidance request information can also upload some physical parameter information of the trailer flatbed and the loading and unloading ramp. When the trailer flatbed's entry guidance request is received, it means that the trailer has been deployed and is waiting for the towed vehicle to enter.

[0039] In some embodiments of the present application, the process of constructing the trailer space coordinate model is as follows: First, determine the origin and coordinate axis directions of the global coordinate system.

[0040] The geometric center of the horizontal trailer flatbed is used as the coordinate origin, the X-axis is set along the length of the flatbed, the Y-axis is set along the width of the flatbed, and the Z-axis is set perpendicular to the flatbed surface.

[0041] Then, the spatial coordinates of the horizontal trailer flatbed are determined according to the physical parameter information of the horizontal trailer flatbed.

[0042] Based on this, the length of the horizontal trailer flatbed is , width is , the height is When the X-axis range of the horizontal trailer flatbed belongs to ( ), the Y-axis range belongs to ( ), the Z axis is .

[0043] Then, the coordinates of the hinge point between the tilted trailer bed and the horizontal trailer bed are determined.

[0044] For example, the coordinates of the hinge point are ( ).

[0045] It should be noted that the tilting direction is that the front end is lifted and the rear end is connected to the ramp.

[0046] Then, the spatial coordinates of the tilted trailer flatbed are calculated according to the physical parameter information of the tilted trailer flatbed and the coordinates of the hinge points.

[0047] The hinge point can be considered as the rotation center, and the tilt trailer flatbed rotates around the Y axis of the hinge point by the tilt angle.

[0048] For example, suppose the length of the tilt trailer flatbed is , width is , the front end height from the ground is , the tilt angle is , then the rear end height from the ground is . Based on this, the X-axis range of the tilt trailer flatbed belongs to ( ), the Y-axis range belongs to ( ), the Z-axis range belongs to ( ).

[0049] Then, determine the coordinates of the connection point between the loading ramp and the tilt trailer bed.

[0050] For example, the coordinates of the connection point are ( 0 ).

[0051] Then, the spatial coordinates of the loading and unloading ramp are determined according to the physical parameter information of the loading and unloading ramp and the coordinates of the connection points.

[0052] Assume the length of the loading ramp is , width is , the tilt angle is .

[0053] It should be noted that the rear end of the loading and unloading ramp usually contacts the ground, so the height of the rear end from the ground is 0.

[0054] Based on this, the X-axis range of the loading and unloading ramp belongs to ( ), the Y-axis range belongs to ( ), the Z-axis range belongs to (0, ).

[0055] Finally, the spatial coordinates of the horizontal trailer flatbed, the inclined trailer flatbed, and the loading and unloading ramp are represented by three-dimensional grids to obtain the spatial coordinate model of the trailer flatbed.

[0056] S104: Generate theoretical driving information of the towed vehicle on the trailer flatbed according to the vehicle operating parameters of the towed vehicle and the trailer space coordinate model; the theoretical driving information includes a theoretical driving trajectory and a theoretical driving speed range.

[0057] In some embodiments of the present application, the slope of the tilted trailer bed and the slope of the loading ramp may be the same or different. Therefore, the greater the difference in slope between the two, the more sudden the transition angle between the tilted trailer bed and the loading ramp. A more sudden angle transition is more likely to cause bumps, tire slippage, or track deviation.

[0058] Among them, by combining the geometric characteristics of similar triangles, complex segmented inclined structures can be converted into proportional correlation relationships, providing high-precision trajectory guidance, safety boundary verification and dynamic control basis for vehicle driving, which is especially suitable for intelligent loading scenarios with multiple models and multi-layer structure inclinations in large-plate carpooling.

[0059] It should be noted that if the similarity between the right triangle formed by the tilted trailer flatbed and the right triangle formed by the loading and unloading ramp is very high, it means that the slope of the loading and unloading ramp is almost the same as that of the tilted trailer flatbed. When the towed vehicle transitions from the loading and unloading ramp to the tilted trailer flatbed, the vertical ascent or descent rate is uniform, and the gravity distribution of the towed vehicle on the loading and unloading ramp and the tilted trailer flatbed is the same, which reduces the frequency of control strategy switching, and the driving trajectory can be smoothly connected, simplifying path planning.

[0060] It should be noted that in uphill scenarios, the vehicle can be considered to need to overcome constant resistance, and the upper speed limit is limited by the engine power, and the lower speed limit is constrained by the braking performance to avoid loss of control.

[0061] Based on this, the process of generating the theoretical driving information of the towed vehicle on the trailer flatbed is as follows: First, determine the similarity between the right triangle formed by the tilted trailer bed and the right triangle formed by the loading ramp.

[0062] The similarities are then mapped to obtain the smoothness of the transition between the tilted trailer platform and the loading ramp. The smoothness represents the gentleness of the transition angle between the loading ramp and the tilted trailer platform.

[0063] That is, the smoothness here describes whether the transition angle between the ramp and the trailer is gentle. The larger the angle difference at the connection, the lower the speed required to enter.

[0064] It should be noted that the degree of smoothness can include smooth transition, basically smooth transition, and non-smooth transition. Smooth transition means that the connection can be made directly without special processing, basically smooth transition means that a slight speed adjustment is required, and non-smooth transition means that a significant speed adjustment is required.

[0065] Then, the speed constraint of the towed vehicle is obtained according to the smoothness and vehicle operating parameters.

[0066] For example, when driving uphill, if the connection between the loading ramp and the tilted trailer bed suddenly becomes steeper, the car is at risk of being bumped and slipping.

[0067] Then, the effective driving area of ​​the trailer flatbed is determined based on the distance between the trailer space coordinate model and the safety edge.

[0068] Among them, when the safety distance is d, the Y-axis range of the effective driving area of ​​the horizontal trailer flatbed belongs to [ )], the Y-axis range of the effective driving area of ​​the tilt trailer flatbed belongs to [ )].

[0069] Finally, according to the trailer trajectory equation, driving speed constraints and effective driving area, the theoretical driving speed range and theoretical driving trajectory of the towed vehicle are generated.

[0070] In some embodiments of the present application, the process of calculating similarity is as follows: Calculate the angular difference between the tilt angle of the tilted trailer bed and the tilt angle of the loading ramp, calculate the length ratio between the length of the tilted trailer bed and the length of the loading ramp, and calculate the height ratio between the front end height of the tilted trailer bed and the front end height of the loading ramp.

[0071] According to the similarity scoring function, the angle difference, length ratio and height ratio are weightedly summed to obtain the similarity between the right triangle formed by the tilted trailer flatbed and the right triangle formed by the loading and unloading ramp.

[0072] Among them, the similarity scoring function can be as follows:

[0073] in, is the weight coefficient of the angle term, which is used to control the contribution ratio of the angle difference to the similarity score. is the sensitivity coefficient of the angle difference, The larger the , the greater the inhibitory effect of the angle difference on the score.

[0074] in, hour, =1, indicating that the contribution is greatest when the angles are exactly the same.

[0075] also, is the length proportional term, is the height proportional term, is the weight coefficient of the length-to-height ratio term, which is used to control the contribution of the ratio term to the similarity score. is the sensitivity coefficient of the proportional difference.

[0076] in, The bigger it is, ) is smaller, indicating a greater difference in proportions and a lower similarity.

[0077] It should be noted that the larger the angle difference, the more severe the slope change (such as a sudden change from a gentle slope to a steep slope), which can easily cause vehicle bumps or trajectory deviation, so the similarity should decrease exponentially.

[0078] In some embodiments of the present application, the process of obtaining the driving speed constraint condition of the towed vehicle is as follows: First, calculate the average angle of the tilt angle of the tilted trailer bed and the tilt angle of the loading ramp.

[0079] It's important to note that the average angle reflects the impact of the combined slope on braking and climbing, adapting to the specificities of large-scale flatbed carpooling. In this scenario, trailer flatbeds with two or more decks typically have larger inclination angles and longer slopes (for example, the upper ramp is steeper in double-decker transport). Taking the average angle in this situation is essentially a conservative design. Even if the loading and unloading ramp angle is smaller, the average angle still needs to meet the stringent conditions of the trailer flatbed, ensuring that braking safety and power requirements are met under the most unfavorable conditions (such as upper-deck transport).

[0080] Then, according to the preset maximum driving speed constraint function, the braking coefficient of the towed vehicle, the length and average angle of the tilted trailer flatbed are calculated to obtain the first maximum driving speed; the maximum driving speed constraint function meets the braking safety requirements.

[0081] It should be noted that in the scenario of large-plate carpooling, the inclination angle of the second floor and above is usually larger, the slope length is longer, and the braking safety requirements need to be met more. Therefore, the length of the inclined trailer flatbed is used for calculation at this time.

[0082] In addition, according to a preset minimum driving speed constraint function, the minimum stable power and average angle of the towed vehicle's engine are calculated to obtain a first minimum driving speed; the minimum driving speed constraint function meets the power requirement for overcoming slope resistance.

[0083] Finally, the driving speed constraint condition of the towed vehicle is obtained according to the smoothness, the first maximum driving speed and the first minimum driving speed.

[0084] It should be noted that for the same vehicle model, the aforementioned vehicle operating parameters (e.g., braking coefficient, minimum stable engine power) are the same. Large-plate carpooling is often also used in the transportation of new vehicles to 4S stores. Therefore, the speed constraints for vehicles of the same model are the same, and repeated calculations are not required when the inclination angle remains unchanged. For example, multiple vehicles of the same model need to enter the same floor.

[0085] The process of obtaining the driving speed constraint condition of the towed vehicle based on the smoothness, the first maximum driving speed, and the first minimum driving speed is as follows: When the smoothness level is smooth transition, the driving speed constraint condition of the towed vehicle is determined according to the first maximum driving speed and the first minimum driving speed.

[0086] When the smoothing level is basic smoothing, the calculation process is as follows: The safety factor of the towed vehicle is determined based on the ratio between the angle difference and a preset angle difference threshold. The larger the ratio, the smaller the safety factor.

[0087] The product of the first maximum travel speed and the safety factor is calculated to obtain the second maximum travel speed.

[0088] A driving speed constraint condition of the towed vehicle is determined according to the second maximum driving speed and the first minimum driving speed.

[0089] When the smoothness is non-smooth transition, the calculation process is as follows: The maximum of the tilt angle of the tilted trailer bed and the tilt angle of the loading ramp is determined as the target tilt angle.

[0090] A second minimum driving speed is obtained according to the preset minimum driving speed constraint function and the target tilt angle.

[0091] A driving speed constraint condition of the towed vehicle is determined according to the second maximum driving speed and the second minimum driving speed.

[0092] It should be noted that the maximum driving speed is required to be able to brake in time on an inclined trailer flatbed (for example, when climbing a slope above the second floor of a large flatbed carpool, there is a risk of the vehicle sliding backward), and the minimum driving speed is required to overcome the slope resistance.

[0093] For example, when the smoothness level is smooth transition, the driving speed constraint can be as follows:

[0094] in, is the braking coefficient of the towed vehicle, The length of the tilted trailer flatbed and the inclination angle of the loading ramp are , the tilt angle of the tilt trailer flatbed is , is the minimum stable power of the engine, is the mass of the towed vehicle, is the acceleration due to gravity. The braking coefficient plays a key role in precise parking control. The engine's minimum stable power determines the vehicle's low-speed maneuverability.

[0095] It should be noted that It is a safety redundant design. During the large-scale carpooling process, sufficient power margin is reserved to cope with multiple layers of different slope changes and environmental interference.

[0096] In addition, when the smoothness is basically smooth and the transition is non-smooth, a safety factor is introduced to reduce the maximum speed when the vehicle is approximately similar. This is to address the risk of extended braking distance or impact caused by slight angle differences. The upper speed limit is limited by the gravity component of the slope. The steeper the slope, the lower the allowed speed. The safety factor generation process is as follows: First, the function of the safety factor is as follows: p

[0097] in, is the angular difference between the tilt angle of the tilted trailer bed and the tilt angle of the loading ramp, is the maximum angle difference threshold allowed.

[0098] It should be noted that the safety factor decreases as the angle difference increases, which can reflect that the larger the angle difference, the lower the safety redundancy.

[0099] When the smoothness is basic, the driving speed constraint can be as follows:

[0100] in, is the safety factor for basic smoothness.

[0101] When the smooth speed is a non-smooth transition, the driving speed constraint can be as follows:

[0102] in, is the safety factor for non-smooth transition.

[0103] It should be noted that the angle difference during the above-mentioned non-smooth transition may lead to a significant increase in actual resistance, so a larger single slope angle is used to replace the average slope to avoid insufficient power.

[0104] In some embodiments of the present application, the theoretical driving speed range and theoretical driving trajectory of the towed vehicle are generated as follows: Among them, the trajectory equation can be as follows:

[0105] It should be noted that E refers to the inclination angle of the flatbed or the inclination angle of the loading and unloading ramp. For example, E on a horizontal trailer flatbed is 0, and E on an inclined trailer flatbed is 0. , E of the loading and unloading ramp is , is the driving distance, .

[0106] Based on this, the driving speed constraint condition value is converted into a theoretical driving speed range.

[0107] In addition, the generation process of the theoretical driving trajectory is as follows: First, the distance series of the towed vehicle is obtained based on the average speed within the preset time window and the theoretical driving speed range. The driving area corresponding to the distance series includes the horizontal trailer platform, the inclined trailer platform, and the loading and unloading ramp.

[0108] It's important to note that the distance traveled series represents the total distance traveled by the towed vehicle at different moments in time, arranged in chronological order. In other words, the distance traveled series discretizes the continuous driving process using a time window and average speed, quantifying the vehicle's positional progress at different moments.

[0109] Then, the travel distance sequence is substituted into the trailer trajectory equation to obtain the trajectory sequence of the towed vehicle.

[0110] It should be noted that the trajectory sequence is a set of discrete position coordinate data points.

[0111] Finally, the lateral boundaries of the effective driving area are determined as the constraints of the trajectory sequence, and the theoretical driving trajectory of the towed vehicle is obtained.

[0112] It should be noted that the theoretical driving trajectory refers to the path of the towed vehicle when it is driving, which is composed of a set of discrete position coordinate points, and different towed vehicles will be placed in different positions of the trailer, so the trajectory on the flatbed is also different.

[0113] It should be noted that the theoretical driving trajectory and theoretical driving speed range can also be adjusted in combination with the influence of meteorological information.

[0114] Based on this, the environmental impact factor value of the trailer is determined according to the weather information at the time of towing. Among them, the environmental impact factors include light, rain and snow.

[0115] According to the environmental impact factor value, the driving speed constraint conditions and the effective driving area are compensated.

[0116] For example, the darker the light or the heavier the rain and snow, the lower the driving speed and the smaller the effective driving area (equivalent to increasing the safety margin distance).

[0117] The theoretical driving speed range of the trailer flatbed is adjusted according to the compensated driving speed constraint condition, and the theoretical driving trajectory of the trailer flatbed is adjusted according to the compensated effective driving area.

[0118] It should be noted that, without incorporating meteorological information, the system can also use the trailer's visual camera to capture road images. Using a road condition neural network model, the system can identify special road condition patterns, such as reflections from accumulated water, to assess the degree of slipperiness. This is then converted into a compensation coefficient. The higher the degree of slipperiness, the smaller the compensation coefficient, resulting in lower driving speeds and a smaller effective driving area.

[0119] S105: Extracting the theoretical driving trajectory to generate a theoretical position matrix of the towed vehicle.

[0120] In some embodiments of the present application, the theoretical position matrix can be A two-dimensional array, where each row corresponds to a moment in time. However, when the carpool arrives at the destination to pick up the vehicle, it may not be able to find a suitable pickup location. That is, the trailer parking location may not be on a flat surface. In this case, the driving trajectory is adjusted to take into account the impact of the trailer parking location.

[0121] Based on this, the process of generating the theoretical position matrix of the towed vehicle is as follows: First, the position coordinate data of each time point is extracted from the trajectory sequence corresponding to the theoretical driving trajectory.

[0122] Then, each time point and the position coordinate data of each time point are converted into an initial theoretical position matrix.

[0123] Then, when the parking tilt angle of the trailer is greater than the parking angle threshold, the position coordinates of the initial theoretical position matrix are adjusted according to the parking tilt angle of the trailer to obtain the theoretical position matrix.

[0124] It should be noted that the visual system can identify the horizontal line on the ground or the parking space markings to calculate the angle between the trailer and the horizontal plane. Alternatively, the trailer's onboard IMU can directly output the pitch angle (the angle at which the front end of the trailer tilts up and down).

[0125] Among them, since the trailer usually has a slope along the slope when the tilt angle is large, the adjustment expression can be as follows:

[0126] in, To adjust the Z-axis coordinate, is the original Z-axis coordinate, is the driving distance, The tilt angle of the trailer.

[0127] S106: Determine guidance information for the towed vehicle to enter the flatbed trailer based on the theoretical driving speed range, the theoretical position matrix, and the trailer space coordinate model.

[0128] In some embodiments of the present application, the process of determining the guidance information for the towed vehicle to enter the flatbed trailer is as follows: First, a virtual model of the trailer's spatial coordinate model is constructed.

[0129] Then, the discrete points of the theoretical position matrix are connected as the target points of the virtual model to construct the virtual guide line.

[0130] It should be noted that virtual guide lines can refer to two guide lines located at the edge of the effective driving area and parallel to the flat surface or ramp. For example, the distance between the guide lines and the edge of the effective driving area is less than the guidance distance threshold. Furthermore, virtual guide lines can also dynamically change based on the geometric parameters of different vehicles.

[0131] The virtual guide line generation process can be as follows: spline interpolation is performed on discrete points in the theoretical position matrix to generate a continuous and differentiable curve to avoid sudden changes in steering angle. For example, cubic spline interpolation is used to calculate the intermediate trajectory points between adjacent points to ensure curvature continuity.

[0132] It should be noted that in the flatbed trailer scenario, the vehicle's speed cannot be obtained when the towed vehicle is not connected to the guidance software. Therefore, this application can predict the vehicle's speed through the theoretical position matrix.

[0133] Based on this, the difference between the towed vehicle's current driving position and the matrix target position is calculated, that is, the vehicle's real-time driving position at the current time and the matrix target position at the current time.

[0134] When the difference is greater than a preset difference threshold, the vehicle's speed is predicted based on the difference. For example, if the speed of the theoretical position matrix is ​​the average speed of the theoretical speed interval, the ratio of the difference to the travel time is calculated, and the vehicle's speed is calculated by summing or subtracting the ratio from the average speed.

[0135] Therefore, the towed vehicle can be given a speed reminder, for example, if the speed is too fast, it needs to slow down.

[0136] It should be noted that the towed vehicle is assumed to be traveling at a near-constant speed when entering the trailer. Considering the multi-layer special scenario of large-scale carpooling, in actual operation, when a towed vehicle enters a large-scale carpool, the driver usually drives at a relatively stable speed for safety reasons.

[0137] Furthermore, the guide line is rendered as a highlighted line with an arrow. The direction of the arrow indicates the driving direction, and the line color changes dynamically according to the speed constraint.

[0138] For example, if the speed is within the theoretical driving speed range, it will be one color; if it is close to the upper or lower speed limit, it will be another color; if it exceeds the speed limit, it will be immediately adjusted to another color.

[0139] It should be noted that when the vehicle speed can be obtained, the actual vehicle speed priority is higher than the predicted speed priority.

[0140] In addition, when the towed vehicle approaches the edge of the effective driving area, the edge area will flash and highlight in the virtual model. For example, the distance between the tire position of the towed vehicle and the edge of the effective driving area is less than a preset distance threshold.

[0141] Wherein, when the distance between the towed vehicle and the boundary of the effective driving area is less than a preset distance threshold, it can be determined that the towed vehicle is approaching the edge of the effective driving area.

[0142] It should be noted that the vehicle's driving position can be acquired based on the visual system of this application, using a pattern recognition technology solution to accurately monitor the vehicle's actual position relative to the trailer edge, as follows: Tire-edge relationship analysis (pattern recognition): Using image processing techniques (such as Hough transform to detect tire edges) and machine learning classifiers (such as Support Vector Machines), the system analyzes the relative position of the vehicle tires and the visual edges of the trailer flatbed in real time. The system determines whether the tires are in a safe, critical, or dangerous (overrunning or crossing a line) state.

[0143] In addition, when sensors are installed on the trailer, the tire position information of the towed vehicle can also be obtained through the sensors installed on the trailer.

[0144] It should be noted that when the towed vehicle is connected to the trailer control system via wireless communication, the vehicle's real-time posture data (position, speed, acceleration, heading angle) can be transmitted to the trailer control system.

[0145] It should be noted that icons may be displayed in advance on the virtual model at the slope change points in the theoretical position matrix.

[0146] In some embodiments of the present application, a steering angle guidance instruction may also be generated based on the theoretical position matrix, which is particularly suitable for unmanned driving scenarios of towed vehicles.

[0147] Firstly, continuous target discrete points are selected from the theoretical position matrix, and the coordinates of the adjacent discrete points of the target discrete points are extracted to calculate the instantaneous curvature.

[0148] Then, the instantaneous curvature of the target discrete point is obtained according to the instantaneous curvature formula and the position information of the three discrete points.

[0149] Finally, the front wheel steering angle at the target discrete point corresponding to the time point is calculated according to the wheelbase and instantaneous curvature of the towed vehicle.

[0150] It should be noted that in an unmanned driving scenario, based on the description above, the speed of the towed vehicle can also be corrected in a timely manner based on the theoretical position matrix.

[0151] It should be noted that although the embodiments of this application are based on Figure 1 To introduce and explain step S101 to step S106 in sequence, but this does not mean that step S101 to step S106 must be executed in a strict order. Figure 1 The order shown in FIG1 is to introduce and explain steps S101 to S106 in order to facilitate those skilled in the art to understand the technical solutions of the embodiments of the present application. In other words, in the embodiments of the present application, the order of steps S101 to S106 can be adjusted appropriately according to actual needs.

[0152] pass Figure 1 The method realizes precise control of the vehicle entering the carpooling process in Daban through a logical chain of vision system, space modeling, trajectory generation, matrix transformation, pattern recognition, and human-computer interaction guidance.

[0153] By building a physical parameter extraction network model combined with an image recognition vision solution, there's no need for manual, pre-measurement of trailer parameters or on-site input. The vision system automatically adapts to the on-site environment, enabling accurate perception even in inclement weather (nighttime, rain).

[0154] A trailer spatial coordinate model is constructed based on the physical parameters of the trailer flatbed and loading ramp. This quantifies the trailer's spatial boundaries and safety constraints, preventing risks such as slippage and collisions caused by vehicle overstepping or angular deviation. The modular design of physical parameters allows for adaptability to different trailer and flatbed sizes (e.g., trailers with varying loads and tilt angles), providing strong scenario adaptability.

[0155] Based on the spatial coordinate model, the theoretical driving trajectory and speed range are generated in combination with the operating parameters of the towed vehicle, which can guide the vehicle to drive smoothly along the optimal path and speed, reducing errors in manual operation (such as understeering or oversteering, and impact caused by sudden speed changes).

[0156] The theoretical position matrix, as quantifiable coordinate points, enables the construction of virtual guide lines, providing guidance for drivers entering a flatbed. This is particularly helpful for new drivers unfamiliar with flatbed trailering. This improves efficiency while ensuring the towed vehicle is safely and accurately driven to the designated location within the flatbed trailer. Furthermore, the theoretical position matrix facilitates real-time verification of deviations between the actual position and the theoretical trajectory, enabling dynamic deviation correction.

[0157] The visual system can also be used to identify images of the vehicle as it enters the vehicle, thereby accurately identifying the vehicle's driving position.

[0158] By generating AR guidance information, the guidance information is made more intuitive, easy to understand and execute, reducing the driver's operating burden and achieving intuitive human-computer interaction.

[0159] Furthermore, the above method can be adapted to autonomous driving scenarios. The theoretical driving trajectory can be directly used as a reference path for autonomous vehicles, and the theoretical speed range can be converted into speed control commands. For example, the theoretical position matrix can be converted into the state-space model input of the autonomous driving system and integrated with on-board positioning data (such as GPS and inertial navigation) to achieve real-time pose verification (for example, calculating the difference between the vehicle's real-time driving position and the matrix target position at the current time). Furthermore, the theoretical position matrix can be combined to generate steering angle guidance. Furthermore, the safety margin distance can be directly mapped into obstacle avoidance constraints for autonomous driving, preventing the vehicle from driving off the edge of the flatbed or colliding with the trailer structure.

[0160] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above methods.

[0161] Figure 2 A schematic structural diagram of a vehicle guiding device for entering a flatbed trailer provided in an embodiment of the present application includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the above-mentioned methods for guiding a vehicle to enter a flatbed trailer.

[0162] Some embodiments of the present application provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions can execute any one of the above-mentioned methods.

[0163] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0164] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0165] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0170] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0171] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0173] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the technical principles of the present application should fall within the scope of protection of the present application.

Claims

1. A method for guiding a vehicle into a flatbed trailer, characterized in that: The method comprises: Upon receiving a trailer flatbed entry guidance request, acquiring images of the trailer flatbed and the loading and unloading ramp; The image is recognized using a pre-trained physical parameter extraction network model to obtain physical parameter information of the trailer flatbed and the loading and unloading ramp; the physical parameter information includes length, width, tilt angle, and safety edge distance; Construct a trailer space coordinate model based on the physical parameter information of the trailer flatbed and loading and unloading ramp; generating theoretical driving information of the towed vehicle on the trailer flatbed based on the vehicle operating parameters of the towed vehicle and the trailer space coordinate model; the theoretical driving information includes a theoretical driving trajectory and a theoretical driving speed range; Extracting the theoretical driving trajectory to generate a theoretical position matrix of the towed vehicle; Guidance information for the towed vehicle to enter the flatbed trailer is determined based on the theoretical driving speed range, the theoretical position matrix, and the trailer space coordinate model.

2. The method according to claim 1, characterized in that The step of constructing a spatial coordinate model of the trailer flatbed according to the physical parameter information of the trailer flatbed specifically includes: The geometric center of the horizontal trailer flatbed is determined as the origin of the global coordinate system, and the length, width and height directions of the horizontal trailer flatbed are determined as the coordinate axis directions; Determine the spatial coordinates of the horizontal trailer flatbed according to the physical parameter information of the horizontal trailer flatbed; determining the coordinates of the hinge point between the tilted trailer flatbed and the horizontal trailer flatbed; Calculating the spatial coordinates of the tilted trailer flatbed according to the physical parameter information of the tilted trailer flatbed and the coordinates of the hinge points; determining the coordinates of the connection point between the loading ramp and the tilted trailer platform; Determining the spatial coordinates of the loading and unloading ramp based on the physical parameter information of the loading and unloading ramp and the coordinates of the connection points; The spatial coordinates of the horizontal trailer flatbed, the spatial coordinates of the inclined trailer flatbed, and the spatial coordinates of the loading and unloading ramp are represented by a three-dimensional grid to obtain a spatial coordinate model of the trailer flatbed.

3. The method according to claim 1, characterized in that Generating theoretical driving information of the towed vehicle on the trailer flatbed based on the vehicle operating parameters of the towed vehicle and the trailer space coordinate model specifically includes: Determine the similarity between the right triangle formed by the tilted trailer bed and the right triangle formed by the loading ramp; Mapping the similarities to obtain a smoothness of the transition between the tilted trailer platform and the loading and unloading ramp; the smoothness is used to represent the smoothness of the transition angle at the connection between the loading and unloading ramp and the tilted trailer platform; Obtaining a driving speed constraint condition of the towed vehicle according to the smoothness and the vehicle operating parameters; determining an effective driving area of ​​the trailer flatbed according to the distance between the trailer space coordinate model and the safety edge; A theoretical driving speed range and a theoretical driving trajectory of the towed vehicle are generated according to the trailer trajectory equation, the driving speed constraint condition and the effective driving area.

4. The method according to claim 3, characterized in that Determining the similarity between the right triangle formed by the tilted trailer platform and the right triangle formed by the loading and unloading ramp specifically includes: Calculate the angle difference between the tilt angle of the tilted trailer bed and the tilt angle of the loading ramp, the length ratio between the length of the tilted trailer bed and the length of the loading ramp, and the height ratio between the front end height of the tilted trailer bed and the front end height of the loading ramp; According to the similarity scoring function, the angle difference, length ratio and height ratio are weightedly summed to obtain the similarity between the right triangle formed by the tilted trailer flatbed and the right triangle formed by the loading and unloading ramp.

5. The method according to claim 3, characterized in that Obtaining the driving speed constraint condition of the towed vehicle based on the smoothness and the vehicle operating parameters specifically includes: Calculate the average angle of the tilt of the trailer bed and the tilt of the loading ramp; The first maximum driving speed is obtained by calculating the braking coefficient of the towed vehicle, the length and average angle of the tilted trailer flatbed according to a preset maximum driving speed constraint function; the maximum driving speed constraint function satisfies the braking safety requirement; The minimum stable engine power and average angle of the towed vehicle are calculated according to a preset minimum speed constraint function to obtain a first minimum speed; the minimum speed constraint function satisfies the power requirement for overcoming slope resistance; A driving speed constraint condition of the towed vehicle is obtained according to the smoothness, the first maximum driving speed, and the first minimum driving speed.

6. The method according to claim 5, characterized in that Obtaining the driving speed constraint condition of the towed vehicle according to the smoothness, the first maximum driving speed, and the first minimum driving speed specifically includes: When the smoothness level is smooth transition, determining a driving speed constraint condition of the towed vehicle according to the first maximum driving speed and the first minimum driving speed; When the smoothness is basically smooth, the safety factor of the towed vehicle is determined based on the ratio of the angle difference between the inclination angle of the tilted trailer platform and the inclination angle of the loading and unloading ramp to a preset angle difference threshold; the larger the ratio, the smaller the safety factor; calculating a product of the first maximum travel speed and the safety factor to obtain a second maximum travel speed; determining a driving speed constraint condition of the towed vehicle according to the second maximum driving speed and the first minimum driving speed; When the smoothness level is non-smooth transition, the maximum of the tilt angle of the tilted trailer bed and the tilt angle of the loading and unloading ramp is determined as the target tilt angle; Obtaining a second minimum driving speed according to a preset minimum driving speed constraint function and the target tilt angle; A driving speed constraint condition of the towed vehicle is determined according to the second maximum driving speed and the second minimum driving speed.

7. The method according to claim 3, characterized in that Generating a theoretical driving speed range and a theoretical driving trajectory of the towed vehicle according to the trailer trajectory equation, the driving speed constraint condition, and the effective driving area specifically includes: Convert the driving speed constraint condition value into a theoretical driving speed range; The distance series of the towed vehicle is obtained according to the average speed of the preset time window and the theoretical driving speed range. The distance series is used to quantify the position progress of the vehicle at different times. Substitute the travel distance sequence into the trailer trajectory equation to obtain the trajectory sequence of the towed vehicle; The lateral boundaries of the effective driving area are determined as the constraints of the trajectory sequence, and the theoretical driving trajectory of the towed vehicle is obtained.

8. The method according to claim 1, characterized in that Extracting the theoretical driving trajectory to generate a theoretical position matrix of the towed vehicle specifically includes: Extract the position coordinate data of each time point in the trajectory sequence corresponding to the theoretical driving trajectory; Convert each time point and the position coordinate data of each time point into an initial theoretical position matrix; When the parking tilt angle of the trailer is greater than the parking angle threshold, the position coordinates of the initial theoretical position matrix are adjusted according to the parking tilt angle of the trailer to obtain a theoretical position matrix.

9. The method according to claim 1, characterized in that The determining, based on the theoretical driving speed range, the theoretical position matrix, and the trailer space coordinate model, of guidance information for the towed vehicle to enter the flatbed trailer specifically includes: Constructing a virtual model of the trailer's spatial coordinate model; The discrete points of the theoretical position matrix are connected as the target points of the virtual model to construct a virtual guide line; Calculating the difference between the driving position of the towed vehicle at the current time point and the matrix target position, and predicting the vehicle driving speed based on the difference when the difference is greater than a preset difference threshold; Render guide lines as highlighted lines with arrows, displaying the corresponding line color according to the vehicle's speed; the arrow direction indicates the driving direction, and the line color changes dynamically according to the speed constraint of the theoretical driving speed range; When the towed vehicle approaches the edge of the effective driving area, the edge area will flash and highlight in the virtual model.

10. A device for guiding a vehicle into a flatbed trailer, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for guiding a vehicle to enter a flatbed trailer as described in any one of claims 1 to 9.

Images