CN112140991A

CN112140991A - Load shedding prediction method and device, and driving assistance method and system

Info

Publication number: CN112140991A
Application number: CN201910567847.0A
Authority: CN
Inventors: 孙铎; 唐帅
Original assignee: Audi AG
Current assignee: Audi AG
Priority date: 2019-06-27
Filing date: 2019-06-27
Publication date: 2020-12-29

Abstract

The present application relates to a load shedding prediction method, device, driving assistance method, system, computer device, and storage medium, wherein a driving risk level is obtained by performing driving risk evaluation based on road information of a target position in a driving direction of a vehicle, that is, a factor causing a load of the vehicle to shed due to driving of the vehicle is considered, and a loading risk level is obtained by performing loading risk evaluation based on loading information of the vehicle, that is, a factor causing a load of the vehicle to shed due to loading is considered, and then the two evaluation results are integrated to predict whether the load of the vehicle shed. The method comprehensively considers two important factors (vehicle running and loading) causing the vehicle loading to fall off, and can accurately predict whether the vehicle loading falls off or not.

Description

Load shedding prediction method and device, and driving assistance method and system

Technical Field

The present application relates to the field of vehicle engineering technologies, and in particular, to a load shedding prediction method, device, driving assistance method, system, computer device, and storage medium.

Background

During the transportation of the loaded goods, the loaded goods may fall off due to road conditions, goods types or goods packages.

Under the condition, the safety of rear vehicles which are not avoided in time can be influenced, property loss can be caused, and the load transportation time is influenced.

Disclosure of Invention

In view of the above, it is desirable to provide a load shedding prediction method, device, driving assistance method, system, computer device, and storage medium capable of predicting whether a vehicle load is shed.

A method of load shedding prediction, the method comprising:

acquiring road surface information of a target position, carrying out driving risk assessment according to the road surface information of the target position, and acquiring a driving risk grade;

acquiring loading information of a vehicle, carrying out loading risk assessment according to the loading information, and acquiring a loading risk grade;

and predicting whether the load of the vehicle falls off or not according to the driving risk level and the loading risk level.

In one embodiment, the performing driving risk assessment according to the road information of the target position to obtain a driving risk level includes:

obtaining the road surface evenness of the target position according to the road surface information of the target position;

and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

In one embodiment, obtaining road surface information of a target location includes:

and acquiring the road surface information of the target position from a map database and/or a road surface information database according to the geographical position of the target position, wherein the road surface information database comprises the road surface information of a plurality of geographical positions.

In one embodiment, acquiring loading information of a vehicle, performing loading risk assessment according to the loading information, and acquiring a loading risk level includes:

acquiring the height and/or weight of the load by a sensor;

and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

acquiring an image containing a rear suspension and a load of the vehicle;

inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

In one embodiment, the neural network model is further configured to obtain binding information of the load according to the load in the image, perform loading risk assessment by using the binding information of the load as loading information, and obtain a loading risk level.

In one embodiment, predicting whether the load of the vehicle is dropped according to the driving risk level and the loading risk level includes:

carrying out weighted calculation on the driving risk grade and the loading risk grade to obtain a falling risk grade of the loaded object;

and predicting whether the load of the vehicle is fallen according to the falling risk grade of the load.

A driving assist method characterized by comprising:

according to the load shedding prediction method, whether the load of the vehicle is shed or not is predicted, and a prediction result is obtained;

if the prediction result is that the load of the vehicle falls off, performing auxiliary driving on the target vehicle;

further preferably, the driving assistance for the target vehicle includes: when the prediction result is that the load of the vehicle is fallen off, warning is sent to the target vehicle; alternatively, the target vehicle is braked.

A load shedding prediction device, the device comprising:

the driving risk evaluation module is used for acquiring the road surface information of the target position, carrying out driving risk evaluation according to the road surface information of the target position and acquiring a driving risk grade;

the loading risk evaluation module is used for acquiring loading information of the vehicle, carrying out loading risk evaluation according to the loading information and acquiring a loading risk grade;

and the prediction module is used for predicting whether the loaded object of the vehicle falls off or not according to the driving risk level and the loading risk level.

In one embodiment, the driving risk assessment module is specifically configured to obtain the road flatness of the target position according to the road information of the target position; and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

In one embodiment, the load risk assessment module is specifically configured to acquire the height and/or weight of the load via a sensor; and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

In one embodiment, the load risk assessment module is specifically configured to acquire an image containing a rear suspension and loads of a vehicle; inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

A driving assistance system characterized by comprising:

the load shedding prediction device is used for predicting whether the load of the vehicle is shed or not according to the load shedding prediction method of the embodiment of the application to obtain a prediction result;

an auxiliary driving device for performing auxiliary driving on the target vehicle if the prediction result is that the load of the vehicle falls off;

further preferably, the driving assistance device is specifically configured to issue a warning to the target vehicle when the prediction result is that the load of the vehicle is dropped; alternatively, the target vehicle is braked.

A computer device comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor to, when executed, perform the steps of a method as described in embodiments of the present application.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to an embodiment of the application.

The load shedding prediction method, the load shedding prediction device, the driving assisting method, the driving assisting system, the computer equipment and the storage medium can be used for obtaining the driving risk grade by carrying out driving risk evaluation according to the road surface information of the target position in the driving direction of the vehicle, namely, the factor of the vehicle caused by the vehicle driving to shed the load is considered, meanwhile, carrying out load risk evaluation according to the load information of the vehicle, obtaining the load risk grade by considering the factor of the vehicle caused by the load shedding, and then comprehensively considering the two evaluation results to predict whether the load of the vehicle is shed or not. The method comprehensively considers two important factors (vehicle running and loading) causing the vehicle loading to fall off, and can accurately predict whether the vehicle loading falls off or not.

Drawings

FIG. 1 is a diagram of an embodiment of a load shedding prediction method;

FIG. 2 is a flow diagram of a load shed prediction method in one embodiment;

FIG. 3 is a flow chart of the refinement step of step S210 in one embodiment;

FIG. 4 is a schematic flow chart of a refinement step of step S210 in another embodiment;

FIG. 5 is a flow chart of the refinement step of step S220 in one embodiment;

FIG. 6 is a schematic flow chart showing a refinement step of step S220 in another embodiment;

FIG. 7 is a schematic flow chart illustrating a refinement step of step S230 in one embodiment;

FIG. 8 is a flow chart of a driving assistance method in one embodiment;

FIG. 9 is a block diagram of the structure of load shedding prediction in one embodiment;

FIG. 10 is a block diagram showing the construction of a driving assistance system in one embodiment;

FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The method for predicting the falling of the loads can be applied to the application environment shown in figure 1. The load drop prediction apparatus 100 predicts whether a load on the vehicle 200 drops or not based on the traveling information and the loading information of the vehicle 200. Alternatively, the load shedding prediction apparatus 100 may be, but is not limited to, various vehicle-mounted computers, personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.

In one embodiment, as shown in fig. 2, a method for load shedding prediction is provided, which is illustrated by way of example as applied to the load shedding prediction device 100 of fig. 1, comprising the steps of:

step 210, obtaining road surface information of a target position, performing driving risk assessment according to the road surface information of the target position, and obtaining a driving risk level.

Wherein the target position is a position within a preset distance from the vehicle 200 in the traveling direction of the vehicle 200. Alternatively, the preset distance may be 0-10 meters. Specifically, the load drop prediction apparatus 100 acquires road surface information of a target position, performs travel risk assessment based on the road surface information of the target position, and acquires a travel risk level. Optionally, a corresponding relationship between the road information and the driving risk level may be preset, and then the driving risk evaluation may be performed according to the corresponding relationship and the road information of the target position to obtain the driving risk level. Alternatively, the load drop prediction apparatus 100 may also consider the traveling speed of the vehicle 200 when performing the traveling risk assessment on the vehicle 200. Alternatively, the higher the estimated travel risk level, the higher the likelihood of the vehicle's contents being dislodged as a result of the vehicle traveling. Alternatively, the traveling risk classification of the vehicle may be preset to 5 classes.

And step 220, acquiring loading information of the vehicle, carrying out loading risk assessment according to the loading information, and acquiring a loading risk grade.

Specifically, the load drop prediction apparatus 100 obtains loading information of the vehicle, performs loading risk assessment on the vehicle 200 based on the loading information, and obtains a loading risk level. Optionally, the loading information may include one or more of weight, volume, height, and banding information of the load. Alternatively, the corresponding relationship between the loading information and the loading risk level may be preset, and then the loading risk assessment may be performed on the vehicle 200 according to the corresponding relationship and the loading information of the vehicle 200 to obtain the loading risk level. Optionally, the higher the assessed loading risk level, the higher the likelihood of the load of the vehicle falling due to loading. Alternatively, the loading risk classification of the vehicle may be preset to 5.

And step 230, predicting whether the loaded object of the vehicle falls off according to the driving risk level and the loading risk level.

Specifically, the load drop prediction apparatus 100 predicts whether the load of the vehicle drops according to the travel risk level and the loading risk level. Alternatively, the driving risk level and the loading risk level may be first weighted, and then whether the load of the vehicle is removed may be predicted according to the weighted calculation result.

In the method for predicting the falling of the loaded objects, the driving risk evaluation is carried out according to the road information of the target position in the driving direction of the vehicle, the driving risk grade is obtained, namely the factor of the vehicle for causing the loaded objects to fall off when the vehicle is driven is considered, meanwhile, the loading risk evaluation is carried out according to the loading information of the vehicle, the loading risk grade is obtained, namely the factor of the vehicle for causing the loaded objects to fall off when the loading is considered, and then the two evaluation results are integrated to predict whether the loaded objects of the vehicle fall off or not. The method comprehensively considers two important factors (vehicle running and loading) causing the vehicle loading to fall off, and can accurately predict whether the vehicle loading falls off or not.

In one embodiment, as shown in fig. 3, step S210 includes:

and S211, obtaining the road surface flatness of the target position according to the road surface information of the target position.

The road surface flatness information may reflect the flatness (degree of unevenness) of the road surface. Specifically, the load drop prediction apparatus 100 obtains the road flatness of the target position from the road information of the target position. Alternatively, the load drop prediction apparatus 100 acquires road surface information of the target position from the geographical position of the target position.

And S212, carrying out running risk assessment according to the road flatness of the target position and the running speed of the vehicle, and acquiring a running risk grade.

Specifically, the load drop prediction apparatus 100 performs driving risk evaluation based on the road flatness of the target position and the driving speed of the vehicle, and obtains a driving risk level. Alternatively, the load drop prediction apparatus 100 may acquire the traveling speed of the vehicle from data of the driving system of the vehicle 200. Alternatively, the load drop prediction apparatus 100 may also acquire the running speed of the vehicle 200 through a vehicle speed test apparatus.

In the embodiment, when the driving risk assessment is performed, the road flatness of the target position and the driving speed of the vehicle are considered, and the obtained assessment result is reliable.

In one embodiment, as shown in fig. 4, step S210 further includes:

s213, according to the geographical position of the target position, the road surface information of the target position is obtained from a map (such as a high definition map (HD map)) database and/or a road surface information database.

Wherein the road surface information database contains road surface information for a plurality of geographical locations. Alternatively, the map may be a highrise map, a Baidu map, or the like. It should be understood that the map database contains road surface information for a plurality of geographic locations. Specifically, the load drop prediction apparatus 100 obtains the road surface information of the target position from a map database and/or a road surface information database according to the geographical position of the target position. Alternatively, the load drop prediction apparatus 100 may first locate the geographical position of the vehicle 200 using the GPS, and then determine the geographical position of the target position according to the geographical position of the vehicle 200, the preset distance, and the traveling direction of the vehicle 200.

In the embodiment, the road surface flatness information can be obtained through the road surface information in the existing database, a vehicle is not required to be provided with a road surface information acquisition device, the scheme is simple to implement, and the requirement on the configuration of the vehicle is low.

In one embodiment, as shown in fig. 5, step S220 includes:

step S221, the height and/or weight of the load is acquired through a sensor.

Specifically, the load drop prediction apparatus 100 acquires loading information of the load through a sensor.

And step S222, taking the height and/or weight of the loaded object as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

Specifically, the load drop prediction apparatus 100 performs a loading risk assessment using the height and/or weight of the load as loading information, and obtains a loading risk grade. Alternatively, the corresponding relationship between the height and/or weight of the loaded object and the loading risk level may be preset, and then the loading risk assessment may be performed on the vehicle 200 according to the corresponding relationship and the loading information of the vehicle 200 to obtain the loading risk level.

The method in the embodiment extracts two important factors which influence the falling height and weight of the loaded object in the loading transportation process, evaluates the loading risk of the vehicle and has accurate and reliable evaluation results.

In one embodiment, as shown in fig. 6, step S220 may also include:

step S223, an image containing the rear suspension and the load of the vehicle is acquired.

And S224, inputting the image containing the rear suspension and the loaded object of the vehicle into a neural network model, and acquiring a loading risk grade.

The neural network model is used for acquiring the weight of the loads according to the rear suspension in the image, acquiring the height of the loads according to the loads in the image, and performing loading risk assessment by using the height and/or the weight of the loads as loading information to acquire a loading risk grade. Optionally, the neural network model comprises a correspondence of the state of the rear suspension to the weight of the load.

Optionally, before using the neural network model, a neural network of the neural network model needs to be constructed first, and then the neural network is trained to obtain a neural network with converged neural network layer. The neural network layer converged neural network may be used to perform step S224.

In one embodiment, the neural network model is further configured to obtain binding information of the load according to the load in the image, perform loading risk assessment by using the binding information of the load as loading information, and obtain a loading risk level. Since the binding information is also an important factor influencing the falling of the loaded object, the evaluation result of the embodiment is more accurate.

The present embodiment processes the image containing the rear suspension and load of the vehicle through the neural network model to directly obtain the load risk level. The scheme is simple to implement and high in data processing efficiency.

In one embodiment, as shown in fig. 7, step S230 may also include:

and S231, performing weighted calculation on the driving risk level and the loading risk level to obtain a falling risk level of the loaded object.

Specifically, the load drop prediction apparatus 100 performs weighted calculation on the driving risk level and the loading risk level to obtain a drop risk level of the load.

And step S232, predicting whether the load of the vehicle falls off or not according to the falling risk level of the load.

Specifically, the load shedding prediction apparatus 100 predicts whether the load of the vehicle is shed or not according to the shedding risk level of the load. Alternatively, a corresponding relationship between the falling risk level and whether the load falls off may be preset, and then whether the load of the vehicle 200 falls off may be predicted according to the corresponding relationship. Optionally, when the falling risk level is larger and the possibility of the load falling is higher, it can be preset that the load of the vehicle is predicted to possibly fall when the falling risk level is larger than a preset threshold value.

The above-described load shedding prediction method may be applied to the driving assistance of a vehicle, and how the above-described load shedding prediction method is applied to the driving assistance system of a vehicle will be specifically described below as an example in which the load shedding prediction method in the above-described embodiment is applied to the driving assistance of a vehicle.

In one alternative embodiment, as shown in fig. 8, a driving assistance method is proposed, which is described by taking the application environment of fig. 1 as an example, and includes the following steps:

and S310, predicting whether the loaded object of the vehicle falls off or not to obtain a prediction result.

Specifically, the driving assistance system predicts whether the load of the vehicle is removed using the load removal prediction method in the above embodiment, and obtains a prediction result. For a specific way of using the method for predicting load shedding in the above embodiment to predict whether a load is shed or not, reference may be made to the method for predicting load shedding in the above embodiment of the present application, which is not described in detail herein.

And step S320, if the prediction result is that the load of the vehicle is fallen off, performing auxiliary driving on the target vehicle.

Specifically, the driving assistance system assists driving of the target vehicle when the prediction result is that the load of the vehicle falls. Optionally, the driving assistance of the target vehicle includes: when the prediction result is that the load of the vehicle is fallen off, warning is sent to the target vehicle; alternatively, the target vehicle is braked.

The driving assistance method in this embodiment comprehensively considers the driving information and the loading information of the vehicle, predicts whether the loaded object falls off, and when the obtained prediction result is that the loaded object of the vehicle falls off, adopts a driving assistance mode of warning or braking the vehicle by the vehicle, so that the related vehicle can avoid damage caused by the falling of the loaded object, and simultaneously, loss caused by the falling of the loaded object in the process of transporting the loaded object by the vehicle can be reduced.

It should be understood that although the various steps in the flowcharts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, a load shedding prediction device is provided, which is shown in fig. 9 and includes:

a driving risk evaluation module 110, configured to obtain road surface information of a target position, perform driving risk evaluation according to the road surface information of the target position, and obtain a driving risk level;

a loading risk evaluation module 120, configured to obtain loading information of a vehicle, perform loading risk evaluation according to the loading information, and obtain a loading risk level;

a prediction module 130, configured to predict whether the load of the vehicle will drop according to the driving risk level and the loading risk level.

In one embodiment, the driving risk assessment module 110 is specifically configured to obtain the road flatness of the target position according to the road information of the target position; and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

In one embodiment, the driving risk assessment module 110 is further specifically configured to obtain the road surface information of the target location from a map database and/or a road surface information database according to the geographic location of the target location, wherein the road surface information database includes road surface information of a plurality of geographic locations.

In one embodiment, the loading risk assessment module 120 is specifically configured to obtain the height and/or weight of the load via sensors; and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

In one embodiment, the load risk assessment module 120 is specifically configured to acquire an image containing the rear suspension and loads of the vehicle; inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

In one embodiment, the prediction module 130 is specifically configured to perform weighted calculation on the driving risk level and the loading risk level to obtain a dropping risk level of the loaded article; and predicting whether the load of the vehicle is fallen according to the falling risk grade of the load.

In one embodiment, there is provided a driving assistance system, a block diagram of which is shown in fig. 10, including:

the load shedding prediction apparatus 100 is configured to predict whether the load of the vehicle is shed according to the load shedding prediction method in the above embodiment, and obtain a prediction result.

And a driving assistance device 300 configured to perform driving assistance with respect to the target vehicle if the load of the vehicle is dropped as a result of the prediction.

In one embodiment, the driving assistance device 300 is specifically configured to issue a warning to the target vehicle when the predicted result is that the load of the vehicle is dropped; alternatively, the target vehicle is braked.

For the specific limitations of the load shedding prediction device and the driving assistance system, reference may be made to the above limitations of the load shedding prediction method and the driving assistance method, which are not described herein again. The above-mentioned load shedding prediction device and the respective modules of the driving assistance system may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a load shedding prediction method or a driving assistance method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, the processor implementing the following steps when executing the computer program: acquiring road surface information of a target position, carrying out driving risk assessment according to the road surface information of the target position, and acquiring a driving risk grade; acquiring loading information of a vehicle, carrying out loading risk assessment according to the loading information, and acquiring a loading risk grade; and predicting whether the load of the vehicle falls off or not according to the driving risk level and the loading risk level.

In one embodiment, the processor when executing the computer program embodies the following steps: obtaining the road surface evenness of the target position according to the road surface information of the target position; and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

In one embodiment, the processor when executing the computer program embodies the following steps: and acquiring the road surface information of the target position from a map database and/or a road surface information database according to the geographical position of the target position, wherein the road surface information database comprises the road surface information of a plurality of geographical positions.

In one embodiment, the processor when executing the computer program embodies the following steps: acquiring the height and/or weight of the load by a sensor; and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

In one embodiment, the processor when executing the computer program embodies the following steps: acquiring an image containing a rear suspension and a load of the vehicle; inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

In one embodiment, the processor when executing the computer program embodies the following steps: carrying out weighted calculation on the driving risk grade and the loading risk grade to obtain a falling risk grade of the loaded object; and predicting whether the load of the vehicle is fallen according to the falling risk grade of the load.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring road surface information of a target position, carrying out driving risk assessment according to the road surface information of the target position, and acquiring a driving risk grade; acquiring loading information of a vehicle, carrying out loading risk assessment according to the loading information, and acquiring a loading risk grade; and predicting whether the load of the vehicle falls off or not according to the driving risk level and the loading risk level.

In one embodiment, the computer program when executed by the processor embodies the steps of: obtaining the road surface evenness of the target position according to the road surface information of the target position; and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

In one embodiment, the computer program when executed by the processor embodies the steps of: and acquiring the road surface information of the target position from a map database and/or a road surface information database according to the geographical position of the target position, wherein the road surface information database comprises the road surface information of a plurality of geographical positions.

In one embodiment, the computer program when executed by the processor embodies the steps of: acquiring the height and/or weight of the load by a sensor; and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

In one embodiment, the computer program when executed by the processor embodies the steps of: acquiring an image containing a rear suspension and a load of the vehicle; inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

In one embodiment, the computer program when executed by the processor embodies the steps of: carrying out weighted calculation on the driving risk grade and the loading risk grade to obtain a falling risk grade of the loaded object; and predicting whether the load of the vehicle is fallen according to the falling risk grade of the load.

In one embodiment, another computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: according to the load shedding prediction method in the embodiment of the application, whether the load of the vehicle is shed or not is predicted, and a prediction result is obtained; and if the prediction result is that the load of the vehicle falls off, performing auxiliary driving on the target vehicle.

In one embodiment, the processor when executing the computer program embodies the following steps: when the prediction result is that the load of the vehicle is fallen off, warning is sent to the target vehicle; alternatively, the target vehicle is braked.

In one embodiment, another computer-readable storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of: according to the load shedding prediction method in the embodiment of the application, whether the load of the vehicle is shed or not is predicted, and a prediction result is obtained; and if the prediction result is that the load of the vehicle falls off, performing auxiliary driving on the target vehicle.

In one embodiment, the computer program when executed by the processor embodies the steps of: when the prediction result is that the load of the vehicle is fallen off, warning is sent to the target vehicle; alternatively, the target vehicle is braked.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method for load shedding prediction, the method comprising:

2. The method of claim 1, wherein performing a driving risk assessment based on the road surface information of the target location, and obtaining a driving risk level comprises:

3. The method of claim 2, wherein obtaining the road surface information at the target location comprises:

4. The method according to any one of claims 1-3, wherein obtaining loading information of a vehicle, performing a loading risk assessment based on the loading information, and obtaining a loading risk rating comprises:

acquiring the height and/or weight of the load by a sensor;

5. The method according to any one of claims 1-3, wherein obtaining loading information of a vehicle, performing a loading risk assessment based on the loading information, and obtaining a loading risk rating comprises:

acquiring an image containing a rear suspension and a load of the vehicle;

6. The method of claim 5, wherein the neural network model is further used for obtaining the banding information of the loads according to the loads in the images, performing loading risk assessment by using the banding information of the loads as the loading information, and obtaining the loading risk level.

7. The method of claim 1, wherein predicting whether the load of the vehicle is shed based on the travel risk level and the loading risk level comprises:

8. A driving assist method characterized by comprising:

the method for predicting load shedding according to any one of claims 1 to 7, wherein whether the load of the vehicle is shed or not is predicted, and a prediction result is obtained;

9. A load shedding prediction device, the device comprising:

10. The device according to claim 9, wherein the driving risk assessment module is specifically configured to obtain the road flatness of the target position according to the road information of the target position; and evaluating the running risk according to the road surface evenness of the target position and the running speed of the vehicle to obtain a running risk grade.

11. The device according to claim 9 or 10, characterized in that the loading risk assessment module is particularly adapted to acquire the height and/or weight of the load by means of sensors; and taking the height and/or weight of the load as loading information to carry out loading risk assessment, and acquiring a loading risk grade.

12. The apparatus according to claim 9 or 10, wherein the loading risk assessment module is particularly adapted to acquire an image containing a rear suspension and a load of the vehicle; inputting the image containing the rear suspension and the load of the vehicle into a neural network model, and acquiring a loading risk grade, wherein the neural network model is used for acquiring the weight of the load according to the rear suspension in the image, acquiring the height of the load according to the load in the image, and performing loading risk evaluation by taking the height and the weight of the load as loading information to acquire the loading risk grade.

13. A driving assistance system characterized by comprising:

load shedding prediction means for predicting whether the load of the vehicle is shed according to the load shedding prediction method of any one of claims 1 to 7, and obtaining a prediction result;

14. A computer device comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of any of claims 1 to 8.

15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.