Method and device for controlling vehicle driving

Abstract

The invention provides a method for controlling vehicle driving, and the method comprises the following steps: S1, detecting a cleaning vehicle in the surrounding environment of a vehicle, and obtaining the operation state information of the cleaning vehicle; s2, detecting road surface state information of a road on which the vehicle runs; s3, on the basis of the operation state information and the road surface state information, the safety distance between the vehicle and the cleaning vehicle is obtained; and S4, according to the safety distance, the running operation of the vehicle relative to the cleaning vehicle is controlled. The invention further provides a device for controlling the driving of the vehicle and a computer program product. By comprehensively considering the road surface state information and the real-time operation state of the cleaning vehicle, the safety distance between the vehicle and the cleaning vehicle can be more accurately determined, the risk that the vehicle is polluted by water columns or splashes in the operation process of the cleaning vehicle is effectively reduced, and the neat appearance and normal running of the vehicle are guaranteed.

Description

Technical Field

[0001] The present application relates to a method for controlling vehicle driving, and also relates to a device for controlling vehicle driving and a computer program product. Background Art

[0002] With the continuous evolution of autonomous driving technology, its advantages in improving road safety and traffic efficiency are becoming increasingly significant. However, existing autonomous driving systems have obvious shortcomings when interacting with special operation vehicles (such as road sweepers and sprinkler trucks). Specifically, in urban road scenarios, when a cleaning vehicle is in operation, if the distance between the cleaning vehicle and the vehicle is not properly controlled, the fluid spray (such as water jets, aerosols, etc.) generated by the cleaning vehicle operation may cause liquid splashing or pollutant adhesion to surrounding vehicles, seriously affecting the driving experience.

[0003] Currently, existing technical solutions primarily focus on a single factor: the water jet from a sprinkler truck, and control the distance accordingly. However, the actual operating environment is often more complex. For example, when there are deposited pollutants on the road surface (such as silt, industrial dust, etc.), the high-pressure water jet will interact with these pollutants secondary to the water jet, potentially significantly expanding the pollutant's spread and exacerbating the degree of contamination on the vehicle's exterior surface.

[0004] In summary, the existing technology still has deficiencies in controlling the interaction between vehicles and cleaning vehicles. Summary of the Invention

[0005] The purpose of this application is to provide a method for controlling vehicle driving, the method comprising the following steps:

[0006] Step S1, detecting a cleaning vehicle in the surrounding environment of the vehicle and obtaining operation status information of the cleaning vehicle;

[0007] Step S2, detecting road surface condition information of the road on which the vehicle is traveling;

[0008] Step S3, calculating a safe distance between the vehicle and the cleaning vehicle based on the operation status information and the road surface status information; and

[0009] Step S4: controlling the driving operation of the vehicle relative to the cleaning vehicle according to the safety distance.

[0010] This application specifically encompasses the following technical concepts: By comprehensively considering road surface status information and the real-time operating status of cleaning vehicles, this application can more accurately determine the safe distance between vehicles and cleaning vehicles, effectively reducing the risk of vehicles being contaminated by water jets or splashes during cleaning vehicle operations, ensuring a clean appearance and normal operation. Compared to existing technologies, this application not only focuses on the operating characteristics of the cleaning vehicle itself, but also fully considers the impact of factors such as road surface sediment and dust on the water jet splash range and contamination risk, thereby significantly improving the safety and reliability of autonomous vehicles interacting with cleaning vehicles in urban environments.

[0011] In an exemplary embodiment, the pavement status information includes: pavement cover type information and / or pavement contamination level information, the pavement cover type information includes: mud, coal ash, industrial dust, humic residues, tire particles, water, snow or a mixture thereof, and the pavement contamination level information includes a classification result of a pavement contamination level or a splash risk level; the method includes: pre-storing corresponding buffer spacing and / or spacing adjustment coefficients for different pavement cover type information and / or pavement contamination level information, and in step S3, retrieving the pre-stored buffer spacing and / or spacing adjustment coefficient according to the detected pavement cover type information and / or pavement contamination level information, and determining the safety spacing based on the retrieved buffer spacing and / or spacing adjustment coefficient.

[0012] In an exemplary embodiment, step S3 includes: when the operating state of the cleaning vehicle is a watering state, obtaining the spray range of the watering column of the cleaning vehicle; determining the buffer distance and / or the distance adjustment coefficient based on the road surface state information; and setting the safety distance between the vehicle and the cleaning vehicle to be greater than or equal to the sum of the spray range of the watering column and the buffer distance, or setting the safety distance to the spray range of the watering column multiplied by the distance adjustment coefficient, and the distance adjustment coefficient is set to be at least greater than 1.

[0013] In an exemplary embodiment, step S3 includes: determining a buffer distance according to road surface status information; when the operation state of the cleaning vehicle is a cleaning state, setting a safety distance between the vehicle and the cleaning vehicle to be greater than or equal to the buffer distance.

[0014] In an exemplary embodiment, step S3 includes: when the operating state of the cleaning vehicle is the cleaning state, identifying that the cleaning mechanism of the cleaning vehicle exceeds the physical extension length L of the vehicle body; and setting the safety distance to be greater than or equal to the sum of the buffer distance and the physical extension length L.

[0015] In an exemplary embodiment, the method further includes: determining an expected driving strategy of the vehicle, the expected driving strategy including following driving of a cleaning vehicle and overtaking driving of overtaking the cleaning vehicle from the side, and in step S3, additionally determining a safety distance based on the expected driving strategy, wherein the safety distance is determined in different manners for different expected driving strategies of the vehicle; and / or, step S4 includes: controlling the vehicle to perform following driving of following the cleaning vehicle or controlling the vehicle to perform overtaking driving of overtaking the cleaning vehicle from the side, and during the period of controlling the vehicle to perform following driving or overtaking driving, controlling the relative distance between the vehicle and the cleaning vehicle not to exceed the determined safety distance.

[0016] In an exemplary embodiment, in step S2, road surface condition information is obtained in the following manner: road surface visual information is obtained through an image sensor, and road surface covering type information and / or dirtiness information is determined based on characteristic parameters of the road surface visual information; and / or, splash trajectory characteristics of raised pollutants are detected through a motion sensor, and road surface covering type information and / or dirtiness information is determined based on the splash trajectory characteristics.

[0017] In an exemplary embodiment, the method further includes: acquiring the driving speed of the cleaning vehicle in real time; and, additionally determining the safety distance based on the driving speed of the cleaning vehicle, wherein as the driving speed of the cleaning vehicle increases, the safety distance is increased accordingly, and / or, as the driving speed of the cleaning vehicle increases, the weight of the road surface condition information in determining the safety distance is increased.

[0018] According to a second aspect of the present application, a device for controlling vehicle driving is provided, the device comprising a memory and a processor, the memory storing computer program instructions, and when the computer program instructions are executed by the processor, the processor is capable of executing the method described in the first aspect of the present application.

[0019] According to a third aspect of the present application, a computer program product is provided, comprising computer program instructions, wherein when the computer program instructions are executed by one or more processors, the one or more processors are enabled to perform the method according to the first aspect of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention will be described in more detail below with reference to the accompanying drawings, so that the principles, features and advantages of the present invention can be better understood. The accompanying drawings include:

[0021] Figure 1 A block diagram of a vehicle according to an exemplary embodiment of the present application is shown, the vehicle including an apparatus for controlling vehicle travel;

[0022] Figure 2A flow chart of a method for controlling vehicle driving according to an exemplary embodiment of the present application is shown;

[0023] Figure 3 Shown Figure 2 A flowchart of the steps of the method is shown;

[0024] Figure 4 A schematic diagram showing the application of the method according to the present application in an exemplary scenario is shown;

[0025] Figure 5 A schematic diagram showing application of the method according to the present application in another exemplary scenario; and

[0026] Figure 6 A schematic diagram showing the application of the method according to the present application in another exemplary scenario is shown. DETAILED DESCRIPTION

[0027] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by this application more clearly understood, this application will be further described in detail below with reference to the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit the scope of protection of this application.

[0028] Figure 1 A block diagram of a vehicle 1 according to an exemplary embodiment of the present application is shown. The vehicle 1 includes an apparatus 10 for controlling the travel of the vehicle 1 .

[0029] The vehicle 1 can support both partial automatic driving and fully automatic driving, and can also have a manual driving mode. The device 10 for controlling the driving of the vehicle 1 can be, for example, a submodule of the driving assistance device / automatic driving device of the vehicle 1, and includes a processor 12 and a memory 11. The memory 11 stores computer program instructions, which can be stored in a computer-readable storage medium such as a hard disk, memory, or flash memory card. The processor 12 can be a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), or other general-purpose processor. When the processor 12 executes the computer program instructions in the memory 11, it can implement a method for determining the driving control of the vehicle 1, which will be further explained in conjunction with the following text and will not be described in detail here.

[0030] The device 10 can be connected to a plurality of sensors and actuators 13 , 14 , 15 , 20 , 22 of the vehicle 1 in a wired or wireless manner via an in-vehicle network (such as CAN bus, FlexRay, MOST, etc.).

[0031] The device 10 can be connected to the environmental sensors 13 of the vehicle 1 to detect in real time the presence of cleaning vehicles in the vehicle's surroundings and the road conditions of the road on which it is traveling. For example, the environmental sensors 13 may include a camera to capture image data of the vehicle's surroundings. The device 10 may have built-in or network-accessible trained object classifiers or machine learning models that can identify typical visual features of cleaning vehicles (such as specific dimensions, rotating brushes, warning lights, etc.) and determine whether they are in operation. Regarding road surface condition detection, the device 10 can use the camera to analyze road surface texture, color, and reflectivity to identify and classify the type of road surface covering, such as mud, dust, accumulated water, or snow. Furthermore, to further improve detection accuracy, the device 10 can be connected to other environmental sensors, such as lidar, millimeter-wave radar, and ultrasonic radar. These sensors can provide the cleaning vehicle's three-dimensional profile, distance information, driving speed information, and the reflectivity characteristics of road objects, thereby achieving multi-dimensional perception of the cleaning vehicle's operating status and road conditions.

[0032] The device 10 can also be connected to the vehicle 1's state sensors 14, such as motion sensors (e.g., wheel speed sensors, accelerometers) and position sensors (e.g., GPS). Through these sensors, the device 10 can obtain the vehicle 1's motion state (e.g., speed, acceleration, direction of travel) and geographic location in real time. Based on this information, the device 10 can accurately calculate the relative position and relative motion relationship between the vehicle 1 and the cleaning vehicle, providing a reliable basis for inter-vehicle distance control and improving the safety and stability of the autonomous driving system in complex scenarios.

[0033] The device 10 can also be connected to the communication interface 15 to receive auxiliary information from the outside with the help of the communication network, such as weather conditions and cleaning vehicle operating area information released by the road supervision platform. This information can be used to further improve the accuracy and robustness of the recognition of the cleaning vehicle's operating status and road surface status. For example, when the device 10 receives a notification that a cleaning operation is underway in a certain area, the working mode and detection sensitivity of the environmental sensor 13 can be adjusted in advance to improve the efficiency of identifying the cleaning vehicle and its operating status. In addition, combined with weather information (such as rain, snow or sandstorms), the device 10 can also dynamically optimize the judgment logic of the road surface status, so as to more accurately assess the potential pollution risk and adjust the safety distance determination strategy accordingly.

[0034] Device 10 can also be connected to a driving actuator 20 of vehicle 1 to enable lateral and longitudinal control of vehicle 1. The actuator 20 includes key components such as the powertrain, transmission, steering, and braking systems. In response to the safe distance information transmitted by device 10, driving actuator 20 can execute corresponding vehicle control operations to ensure a safe distance between vehicle 1 and the cleaning vehicle.

[0035] The device 10 can also be connected to an output device 22 of the vehicle 1. The output device 22 may include, for example, a display unit, a speaker, an indicator light, or a tactile feedback device. Using the output device 22, the device 10 can provide the driver with real-time information about the currently recommended safe distance in the vehicle 1 for reference. For example, the display unit can visually present the safe distance in graphical or numerical form, the speaker can provide voice prompts to remind the driver to maintain an appropriate distance, and the indicator light or tactile feedback device can provide warnings when approaching or exceeding the safe distance.

[0036] It should be understood that Figure 1 The number and types of various sensors or actuators connected to the device 10 shown in FIG are merely examples and are not intended to be limiting. In actual applications, other types or numbers of sensors and actuators may be used in the vehicle 1 to meet specific needs and conditions.

[0037] It should also be understood that without departing from the core concept of this application, the connection relationship and functional division of each module can be appropriately adjusted according to actual needs, and these adjustments are within the scope of protection of this application.

[0038] Figure 2 A flow chart of a method for controlling vehicle driving according to an exemplary embodiment of the present application is shown. The method exemplarily includes steps S1, S2, S3 and S4, and can be used, for example, in a vehicle. Figure 1 The device 10 is shown as implemented in the context of FIG.

[0039] In step S1 , a cleaning vehicle in the surrounding environment of the vehicle is detected, and operation status information of the cleaning vehicle is obtained.

[0040] Cleaning vehicles may include a variety of models with different appearances, sizes and structural forms. They may have only a watering function, only a sweeping function, or both watering and sweeping functions, and may even further include other types of cleaning functions.

[0041] The operation status information of the cleaning vehicle includes, for example, a watering state and a cleaning state, and may also include a non-operation state.

[0042] As previously mentioned Figure 1As described above, through the multi-sensor data fusion algorithm, it is possible to accurately identify whether there is a cleaning vehicle in the environment surrounding the vehicle. Specifically, the vehicle's front environmental sensors (such as millimeter-wave radar, camera and lidar) can monitor the road environment ahead in real time. The camera is used to capture high-resolution visual images, combined with trained artificial neural networks or object recognition algorithms, and the identity of the cleaning vehicle can be confirmed by analyzing key features of the vehicle's appearance (such as rotating brush plates, water tanks, warning lights, etc.). Millimeter-wave radar can be used to detect the size, speed and contour features of surrounding vehicles. LiDAR uses three-dimensional point cloud data to accurately depict the appearance structure of surrounding vehicles, thereby achieving accurate identification of cleaning vehicles.

[0043] Furthermore, multi-sensor data fusion algorithms can be used to determine the specific operating status of a cleaning vehicle. For example, if image recognition technology detects a water jet from the rear or side of the vehicle, the spraying device is deployed, or there is a clear mist pattern around the vehicle, the vehicle can be determined to be spraying water. Furthermore, for example, by analyzing image data and / or LiDAR point cloud data, the mechanical motion characteristics of the cleaning mechanism (such as the spray arm deployment angle, swing frequency, and the rotation state of the bottom brush) can be analyzed to more accurately determine the operating status of the cleaning vehicle.

[0044] In step S2, road surface condition information of the road on which the vehicle is traveling is detected.

[0045] Road surface condition information includes, for example, road surface cover type information and / or road surface dirtiness information. Road surface cover type information includes, but is not limited to, mud, coal ash, industrial dust, humic residues, tire particles, water, snow, or mixtures thereof. Road surface dirtiness information includes, for example, classification results of road surface dirtiness level or splash risk level. Road surface dirtiness level can be divided according to factors such as the type, quantity, distribution density, and degree of adhesion of road surface pollutants, for example, it can be divided into light, medium, and heavy pollution levels. The splash risk level can be evaluated based on the physical properties of road surface pollutants (such as particle size, humidity, viscosity, etc.) and the degree of influence of vehicle speed on the splash of pollutants, for example, it can be divided into low risk, medium risk, and high risk levels.

[0046] In one embodiment, the road surface condition information can be detected in a variety of ways with the help of environmental sensors carried by the vehicle. Specifically, the visual information of the road surface can be obtained through an image sensor (such as a camera), and the type of road surface cover and / or the degree of dirtiness of the road surface can be identified based on image feature parameters (such as color, texture, reflectivity, etc.). For example, a camera can capture an image of the road surface and analyze the color changes, texture features, and reflectivity in the image through an image processing algorithm to determine whether there is mud, dust, accumulated water, snow, or other pollutants on the road surface. In addition, a machine learning model can be combined to conduct in-depth analysis of the image to improve the accuracy and robustness of recognition.

[0047] In another embodiment, the vehicle's onboard environmental sensors can also be used to detect the splash trajectory characteristics of pollutants raised by the cleaning vehicle during cleaning operations or water jets. Specifically, when the cleaning vehicle is traveling at a certain speed, particulate matter on the road (such as mud, dust, and snow) will be splashed due to the agitation of the cleaning mechanism or the disturbance of the water flow. Therefore, sensors such as cameras, lidar, or millimeter-wave radar can be used to capture and analyze parameters such as the splash height, splash angle, diffusion range, and movement trajectory of the pollutants in real time.

[0048] In step S3, a safe distance between the vehicle and the cleaning vehicle is calculated based on the operation status information and the road surface status information.

[0049] In one embodiment, corresponding buffer spacing and / or spacing adjustment coefficients can be pre-set and stored for different types of road coverings and / or road surface dirtiness. These preset parameters can be obtained through pre-calibration or experimental testing and stored in a local vehicle or remote server for real-time call-up. For example, for mud and sand coverings, since their particles are large and their structure is loose, they are easily lifted by water or air flow, the splashing distance is long, and the pollution risk is high, so a larger buffer spacing and a higher spacing adjustment coefficient can be set. For dry and clean roads, since there is almost no splashing risk, the buffer spacing and spacing adjustment coefficient can be set to smaller values. During the actual driving of the vehicle, the corresponding preset parameters can be called according to the road covering type and / or dirtiness detected in real time, and the safe distance between the vehicle and the cleaning vehicle can be dynamically calculated in combination with the current operating status of the cleaning vehicle.

[0050] In one embodiment, a corresponding method for determining the safety distance can be selected based on the obtained operating status information of the cleaning vehicle. Specifically, different safety distance calculation methods can be used for different operating states of the cleaning vehicle (such as water sprinkling state and non-water sprinkling state). When the cleaning vehicle is in the water sprinkling state, the determination of the safety distance can comprehensively consider the spray range of the water sprinkling column and the buffer distance and / or distance adjustment coefficient corresponding to the road surface state information. When the cleaning vehicle is in the non-water sprinkling state, there is no need to consider the spray range of the water sprinkling column, and the safety distance can be determined only based on the buffer distance corresponding to the road surface state information (such as the type of road surface cover and the degree of dirtiness). By adopting differentiated safety distance determination methods for different operating states, it can more accurately reflect the actual operating environment's requirements for vehicle safety distances, and improve the safety and reliability of the interaction between the autonomous driving vehicle and the cleaning vehicle. This will be combined with the following Figure 3 Further elaborate.

[0051] In another embodiment, the vehicle's intended driving strategy can also be determined. This includes, for example, following a cleaning vehicle and overtaking a cleaning vehicle from the side. A safety distance is then additionally determined based on the intended driving strategy. For example, the safety distance can be determined differently for different intended driving strategies. Specifically, the cleaning vehicle's water jet may have different spray angles and ranges in the longitudinal and lateral directions. For example, a cleaning vehicle may primarily spray water forward and to the sides, with different spray distances. Furthermore, splash patterns may vary in different directions. Therefore, the buffer distance and distance adjustment coefficient corresponding to the road surface condition information can be calibrated differently for different driving strategies. Furthermore, when the vehicle selects the following driving strategy, the safety distance determination must not only consider the spray range of the water jet and the splash characteristics of the road surface covering, but also the road surface slipperiness and the vehicle's braking performance. In this case, the longitudinal safety distance should ensure that it is greater than the vehicle's minimum braking distance under the current road conditions to avoid the risk of insufficient braking due to slippery roads.

[0052] In another embodiment, the driving speed of the cleaning vehicle can also be obtained in real time, and additionally, the safety distance can be determined according to the driving speed of the cleaning vehicle. For example, when the driving speed of the cleaning vehicle increases, the splashing situation may be more serious. Therefore, as the driving speed of the cleaning vehicle increases, the safety distance can be set larger to more effectively reduce the risk of the vehicle being contaminated. In addition, as the driving speed of the cleaning vehicle increases, the weight of the road surface state information in determining the safety distance can be dynamically increased. Exemplarily, when jointly calculating the safety distance with the spraying range of the sprinkler column of the cleaning vehicle, when the cleaning vehicle is in a low-speed driving state (for example, v ≤ 20 km / h), the weight of the road surface state information can be set to 1, when the cleaning vehicle is in a medium-speed driving state (for example, 20 km / h < v ≤ 50 km / h), the weight of the road surface state information can be increased to 1.2, and when the cleaning vehicle is in a high-speed driving state (for example, v > 50 km / h), the weight of the road surface state information can be increased to 1.5.

[0053] In step S4, according to the safety distance, control the driving operation of the vehicle relative to the cleaning vehicle.

[0054] In one embodiment, when the vehicle is driving adjacent to the cleaning vehicle, it should be ensured that the actual vehicle distance is not less than the set minimum safety distance. Specifically, if the vehicle executes a driving strategy of following the cleaning vehicle, during the following process, the longitudinal distance between the vehicle and the cleaning vehicle should always be maintained within the determined longitudinal safety distance range. If the vehicle executes an overtaking strategy of overtaking the cleaning vehicle from the side, during the overtaking process, the lateral distance between the vehicle and the cleaning vehicle should always be maintained within the determined lateral safety distance range.

[0055] In another embodiment, the current safety distance requirement can also be prompted to the driver through a suitable output device (such as a display screen, voice prompt or warning light, etc.) equipped on the vehicle. Further, the system can compare the actual distance between the vehicle and the cleaning vehicle with the determined safety distance in real time, and when the actual distance is less than the safety distance, issue a warning or prompt message to the driver, such as reminding the driver that "the current distance is too small, there is a risk of the vehicle body being contaminated by the cleaning vehicle", so that the driver can take corresponding measures in time to ensure driving safety.

[0056] It should be noted that in the process described in combination with Figure 2 Although steps S1 and S2 are shown as being executed sequentially, this application is not limited to this. According to actual application requirements, steps S1 and S2 can also be executed in reverse order, or in a parallel or alternating manner.

[0057] Figure 3 shows Figure 2 a flowchart of a method step shown. In this embodiment, Figure 2Step S3 of the illustrated method is shown to include sub-steps S31 , S32 , S33 and S34 .

[0058] In sub-step S31, based on the detected road surface cover type and / or road contamination level, pre-stored buffer spacing and / or spacing adjustment coefficients are retrieved. As previously mentioned, these preset parameters can be determined based on experimental data or big data analysis and stored in a local vehicle database or remote server for real-time system access.

[0059] In addition, optionally, with the help of a trained machine learning model, the buffer spacing and / or spacing adjustment coefficient that matches the current road surface state can be directly output according to the currently detected road surface cover type and / or degree of dirtiness, thereby further improving the accuracy and real-time performance of parameter acquisition.

[0060] For example, the spacing adjustment coefficient K can be dynamically set based on the degree of ground dirtiness. For example, for light dirtiness, K = 1.2; for moderate dirtiness, K = 1.5; and for heavy dirtiness, K = 2.0. Furthermore, specific buffer spacing can be set for different types of road coverings. For example, a buffer spacing of 0.2 meters can be set for roads covered with mud and sand, and 0.3 meters for roads exposed to industrial dust.

[0061] In sub-step S32, based on the pre-acquired operating status information of the cleaning vehicle, it is determined whether the cleaning vehicle is currently in the watering operating state. If it is determined to be in the watering state, the process proceeds to sub-step S33.

[0062] In sub-step S33, the spray range of the water column of the cleaning vehicle is further obtained, and the buffer distance and / or distance adjustment coefficient determined based on the road surface status information in sub-step S31 are combined to jointly calculate the safe distance between the vehicle and the cleaning vehicle.

[0063] It should be noted that the "sprinkler" referred to here is not limited to plain water but can also include a variety of operating media, such as cleaning fluids, pesticides, de-icing agents, and aerosols. The term "spray range" refers to the horizontal projection distance from the nozzle outlet to the point where the jet lands, also known as the "range." In actual operation, this range may vary or remain consistent in the longitudinal and lateral directions due to the aerodynamic effects of the vehicle's movement, depending on the nozzle's structural design, installation angle, and the cleaning vehicle's operating mode.

[0064] In one embodiment, the safe distance between the vehicle and the cleaning vehicle can be set to be greater than or equal to the sum of the spray range of the sprinkler column and the buffer distance determined by the road surface condition information, that is, satisfying the following formula:

[0065] d≥d_w+d_s

[0066] Where d represents the safety distance, d_w represents the spray range of the water column of the cleaning vehicle, and d_s represents the buffer distance determined according to the road condition information.

[0067] In another embodiment, the safety distance can also be set as the spray range of the watering column multiplied by the distance adjustment coefficient K determined by the road surface condition information. Here, the distance adjustment coefficient is set to at least greater than 1, for example, to reflect the amplification effect of road surface contamination on the risk of splashing. For example, assume that the spray range of the watering column of the cleaning vehicle during watering operation is 3 meters, and the distance adjustment coefficient K is determined to be 1.2 based on the current road surface condition (e.g., slightly dirty). Then the safety distance d can be calculated as follows:

[0068] d≥d_w×K=3 meters×1.2=3.6 meters

[0069] That is, a safe distance of at least 3.6 meters should be maintained between the vehicle and the cleaning vehicle.

[0070] If the cleaning vehicle's current operating state is determined to be non-sprinkling in sub-step S32, the process proceeds to sub-step S34. Here, "non-sprinkling" includes, for example, the cleaning state, but may also encompass situations where the cleaning vehicle is in a non-operating state (i.e., neither the cleaning mechanism nor the sprinkler mechanism is operating). The following describes how to determine the safety distance, primarily using the "cleaning state" as an example.

[0071] In sub-step S34, since the water jet does not affect the vehicle in the non-sprinkling state, the range of the water jet is no longer a factor in determining the safety distance. Instead, the road surface conditions can be used to determine the safety distance. For example, the safety distance d between the vehicle and the cleaning vehicle can be set to be greater than or equal to the buffer distance determined by the road surface conditions, i.e., d ≥ d_s.

[0072] In one embodiment, considering that the cleaning mechanism of a cleaning vehicle (such as a rotating brush disc and snow pusher) may extend beyond the physical boundaries of the cleaning vehicle during operation, the structural dimensions of the cleaning mechanism should also be taken into consideration when determining the safe distance. Specifically, image recognition or LiDAR point cloud analysis can be used to identify the maximum physical extension length L of the cleaning mechanism beyond the vehicle body. Based on this, the safe distance can be further adjusted, for example, as follows: d ≥ d_s + L.

[0073] By comprehensively considering the road surface conditions and the structural characteristics of the cleaning mechanism, the minimum safe distance between the vehicle and the cleaning vehicle can be set more accurately, thereby effectively avoiding interference or contamination of the vehicle with the cleaning vehicle during overtaking or following.

[0074] Figure 4 A schematic diagram showing the application of the method according to the present application in an exemplary scenario is shown.

[0075] In this scenario, vehicle 1 uses its front-mounted environmental sensors (such as a camera, millimeter-wave radar, and lidar) to identify a cleaning vehicle 3 operating ahead and further confirm that it is currently spraying water. Because cleaning vehicle 3 is traveling slowly, vehicle 1 plans to overtake it by changing lanes.

[0076] In this case, the spray range of water column 31 of cleaning vehicle 3 is first detected and determined as d_w. Simultaneously, the environmental sensor identifies that the road surface is currently covered with a moderate amount of industrial dust, and accordingly determines the corresponding buffer distance d_s. Based on these parameters and the safety distance calculation formula proposed in this application, the minimum safety distance d to be maintained between vehicle 1 and cleaning vehicle 3 satisfies the following: d ≥ d_w + d_s.

[0077] During the overtaking process, when the vehicle 1 overtakes the cleaning vehicle 3 from the adjacent lane, it strictly follows the above-mentioned safety distance requirements to ensure that a sufficient distance is maintained in the lateral direction to avoid contamination by the sprinkler column or road splashes.

[0078] Figure 5 A schematic diagram showing the application of the method according to the present application in another exemplary scenario is shown.

[0079] In this scenario, the expected driving strategy of the vehicle 1 is to follow the vehicle, that is, the vehicle 1 will stay in the same lane behind the cleaning vehicle 3. In this case, the main consideration is the longitudinal safety distance.

[0080] Similar to the above-mentioned overtaking scenario, the longitudinal spray range of the water column 31 of the cleaning vehicle 3 is first detected and determined as d_w. At the same time, the current road surface state is identified in conjunction with the environmental sensor, and the corresponding buffer distance d_s is determined based on the longitudinal dust splash characteristics. It is worth noting that since the spray angle and dust splash characteristics of the water column 31 in the longitudinal direction are different from those in the transverse direction, the values ​​of d_w and d_s may be different. Figure 4 The overtaking scenario shown is different.

[0081] Based on the above parameters, it can be determined that the minimum safe distance that should be maintained between the host vehicle 1 and the cleaning vehicle 3 is: d≥d_w+d_s.

[0082] Furthermore, in the following driving scenario, in addition to considering the spray range of the water jet 31 and the impact of road dust splash, the braking safety of vehicle 1 must also be fully considered. Since cleaning vehicle 3 may slow down or stop at any time, vehicle 1 must maintain sufficient longitudinal distance to ensure safe braking. Therefore, the actual safe distance should also be greater than the minimum safe braking distance d_brake of vehicle 1 under the current road conditions.

[0083] Figure 6A schematic diagram showing the application of the method according to the present application in another exemplary scenario is shown.

[0084] In this scenario, the cleaning vehicle 3 is in a cleaning state and is not in a watering operation. However, the cleaning mechanism 32 (such as a rotating brush disc) of the cleaning vehicle 3 extends outward during operation, exceeding the maximum physical limit of the cleaning vehicle 3 body.

[0085] In this case, the maximum physical extension length of the cleaning mechanism 32 beyond the vehicle body is first identified and determined to be L. At the same time, the current road surface state is identified in conjunction with the environmental sensor of the vehicle 1, and the corresponding buffer distance d_s is determined.

[0086] Taking into account that the protruding part of the cleaning mechanism 32 may cause interference or pollution risk to the vehicle 1, in this case, for example, the safety distance d between the vehicle 1 and the cleaning vehicle 3 is set to be greater than or equal to the sum of the buffer distance d_s determined by the road surface conditions and the extension length L of the cleaning mechanism, that is, d≥d_s+L is satisfied.

[0087] By controlling the vehicle 1 to strictly follow the above-mentioned safety distance requirements when following or overtaking the cleaning vehicle 3, it is possible to ensure that sufficient safety space is maintained in both the lateral and longitudinal directions, thereby effectively avoiding interference with the cleaning mechanism of the cleaning vehicle and reducing the risk of vehicle contamination.

[0088] Although specific embodiments of the present application are described in detail herein, they are provided for illustrative purposes only and should not be considered to limit the scope of the present application. Various replacements, changes, and modifications may be conceived without departing from the spirit and scope of the present application.

Claims

1. A method for controlling the movement of a vehicle (1), the method comprising the following steps: Step S1, detecting a cleaning vehicle (3) in the surrounding environment of the vehicle (1), and obtaining operating status information of the cleaning vehicle (3); Step S2, detecting road surface condition information of the road on which the vehicle (1) is traveling; Step S3, based on the operation status information and the road surface status information, calculating a safety distance d between the vehicle (1) and the cleaning vehicle (3); as well as Step S4, controlling the driving operation of the vehicle (1) relative to the cleaning vehicle (3) according to the safety distance d.

2. The method according to claim 1, wherein The road surface condition information includes: road surface cover type information and / or road surface contamination level information, wherein the road surface cover type information includes: mud, coal ash, industrial dust, humic residue, tire particles, water, snow, or a mixture thereof; and the road surface contamination level information includes a classification result of a road surface contamination level or a splash risk level. The method includes: pre-storing corresponding buffer spacing d_s and / or spacing adjustment coefficient K for different road surface cover type information and / or road surface dirtiness information; in step S3, based on the detected road surface cover type information and / or road surface dirtiness information, retrieving the pre-stored buffer spacing d_s and / or spacing adjustment coefficient K, and determining the safety spacing d based on the retrieved buffer spacing d_s and / or spacing adjustment coefficient K.

3. The method according to claim 1 or 2, wherein: Step S3 includes: When the operation state of the cleaning vehicle (3) is the watering state, the spray range d_w of the watering column (31) of the cleaning vehicle (3) is obtained; Determining a buffer distance d_s and / or a distance adjustment coefficient K according to road surface condition information; and The safety distance d between the vehicle (1) and the cleaning vehicle (3) is set to be greater than or equal to the sum of the spray range d_w of the watering column (31) and the buffer distance d_s, or the safety distance d is set to be the spray range d_w of the watering column (31) multiplied by the distance adjustment coefficient K, and the distance adjustment coefficient K is set to be at least greater than 1.

4. The method according to any one of claims 1 to 3, wherein Step S3 includes: Determine the buffer distance d_s according to the road surface status information; When the operation state of the cleaning vehicle (3) is a cleaning state, the safety distance d between the vehicle (1) and the cleaning vehicle (3) is set to be greater than or equal to the buffer distance d_s.

5. The method according to claim 4, wherein Step S3 includes: When the operation state of the cleaning vehicle (3) is a cleaning state, identifying that the cleaning mechanism (32) of the cleaning vehicle (3) exceeds the physical extension length L of the vehicle body; and The safety distance d is set to be greater than or equal to the sum of the buffer distance d_s and the physical extension length L.

6. The method according to any one of claims 1 to 5, wherein The method further comprises: determining an expected driving strategy of the vehicle (1), the expected driving strategy comprising following the cleaning vehicle (3) and overtaking the cleaning vehicle (3) from the side, and in step S3, additionally determining a safety distance d according to the expected driving strategy, wherein the safety distance d is determined in different ways for different expected driving strategies of the vehicle (1); and / or Step S4 includes: controlling the vehicle (1) to execute following driving of the cleaning vehicle (3) or controlling the vehicle (1) to execute overtaking driving of the cleaning vehicle (3) from the side, and controlling the relative distance between the vehicle (1) and the cleaning vehicle (3) to not exceed a determined safety distance d during the period when the vehicle (1) executes following driving or overtaking driving.

7. The method according to any one of claims 1 to 6, wherein in step S2, the road surface condition information is obtained by: Acquiring road surface visual information through an image sensor, and determining road surface covering type information and / or dirtiness information based on characteristic parameters of the road surface visual information; and / or The splash trajectory characteristics of the raised pollutants are detected by a motion sensor, and the road surface covering type information and / or dirtiness information are determined according to the splash trajectory characteristics.

8. The method according to any one of claims 1 to 7, wherein The method further comprises: Acquire the running speed of the cleaning vehicle (3) in real time; and The safety distance d is additionally determined based on the driving speed of the cleaning vehicle (3), wherein as the driving speed of the cleaning vehicle (3) increases, the safety distance d is correspondingly increased, and / or, as the driving speed of the cleaning vehicle (3) increases, the weight of the road surface condition information in determining the safety distance d is increased.

9. A device for controlling the travel of a vehicle (1), the device comprising a memory (11) and a processor (12), the memory (11) storing computer program instructions, and when the computer program instructions are executed by the processor (12), the processor (12) is capable of executing the method according to any one of claims 1 to 8.

10. A computer program product comprising computer program instructions, wherein: The computer program instructions, when executed by one or more processors, enable the one or more processors to perform the method according to any one of claims 1 to 8.

Images