Driving method and device, electronic equipment and storage medium

Abstract

The application discloses a driving method and device, electronic equipment and storage medium, wherein the method comprises: obtaining environmental data of a first vehicle in an environment, wherein the first vehicle adopts a first driving strategy to travel; if a second vehicle exists in the environment, predicting first reference information of the second vehicle according to the environmental data of the first vehicle; determining a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environmental data of the first vehicle, so that the first vehicle adopts the second driving strategy to travel in the environment; wherein the driving safety of the first vehicle in the environment adopting the second driving strategy is better than the driving safety of the first vehicle in the environment adopting the first driving strategy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent transportation, and in particular to a driving method and device, an electronic device, and a storage medium. BACKGROUND

[0002] In intelligent driving and intelligent assisted driving technologies, most solutions are to formulate or optimize a driving strategy for a vehicle according to a driving environment in which the vehicle is located. Alternatively, a driving strategy for a vehicle is formulated or optimized according to a driving environment and a driving strategy of another vehicle close to the vehicle. There is an urgent need for a new solution for formulating or optimizing a driving strategy. SUMMARY

[0003] The present application provides a driving method and device, an electronic device, and a storage medium to at least solve the above technical problems in the prior art.

[0004] According to a first aspect of the present application, a driving method is provided, comprising:

[0005] obtaining environment data of a first vehicle in a driving environment, the first vehicle driving in the driving environment according to a first driving strategy;

[0006] if a second vehicle exists in the driving environment, predicting first reference information of the second vehicle according to the environment data of the first vehicle;

[0007] determining a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle, so that the first vehicle drives in the driving environment according to the second driving strategy; wherein the driving safety of the first vehicle in the driving environment according to the second driving strategy is better than the driving safety of the first vehicle in the driving environment according to the first driving strategy.

[0008] According to a second aspect of the present application, a driving device is provided, comprising:

[0009] an obtaining unit configured to obtain environment data of a first vehicle in a driving environment, the first vehicle driving in the driving environment according to a first driving strategy;

[0010] a first predicting unit configured to, if a second vehicle exists in the driving environment, predict first reference information of the second vehicle according to the environment data of the first vehicle;

[0011] a first determining unit configured to determine a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle, so that the first vehicle drives in the driving environment according to the second driving strategy; wherein the driving safety of the first vehicle in the driving environment according to the second driving strategy is better than the driving safety of the first vehicle in the driving environment according to the first driving strategy.

[0012] According to a third aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein

[0013] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present application.

[0014] According to a fourth aspect of the present application, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to cause the computer to perform the method described in the present application.

[0015] The traveling method, device, electronic device and storage medium of the present application, wherein the method comprises: obtaining environmental data of a first vehicle traveling in a first traveling strategy in an environment; if a second vehicle exists in the environment, predicting first reference information of the second vehicle according to the environmental data of the first vehicle; determining a second traveling strategy of the first vehicle according to the first reference information of the second vehicle and the environmental data of the first vehicle, so that the first vehicle travels in the environment in the second traveling strategy; wherein the safety of the first vehicle traveling in the environment in the second traveling strategy is better than the safety of the first vehicle traveling in the environment in the first traveling strategy.

[0016] In the technical solution of the present application, the first reference information of the second vehicle is predicted according to the environmental data of the first vehicle. This way of obtaining the first reference information is a new way, and the present application provides a new technical support for the formulation or optimization of the traveling strategy. And the new solution can ensure the safe traveling of the vehicle.

[0017] It should be understood that the contents described in this part are not intended to identify the key or important features of the embodiments of the present application, nor are they used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other objects, features and advantages of the exemplary embodiments of the present application will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0019] In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0020] Figure 1 The implementation flowchart of the traveling method in the embodiments of the present application is shown Figure 1 ;

[0021] Figure 2An implementation flow of the driving method in the embodiment of the present application is shown Figure 2 ;

[0022] Figure 3 An implementation flow of the driving method in the embodiment of the present application is shown Figure 3 ;

[0023] Figure 4 An implementation flow of the driving method in the embodiment of the present application is shown Figure 4 ;

[0024] Figure 5 An implementation flow of the driving method in the embodiment of the present application is shown Figure 5 ;

[0025] Figure 6 A driving scene in the embodiment of the present application is shown.

[0026] Figure 7 A composition structure of the driving device in the embodiment of the present application is shown.

[0027] Figure 8 A composition structure of the electronic device in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0028] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0029] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail in conjunction with the drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0030] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict.

[0031] In the following description, the terms "first\second" are merely used to distinguish similar objects, and do not represent a specific order of the objects. It can be understood that the "first\second" can be interchanged in a specific order or sequence as allowed, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only, and is not intended to be limiting of this application.

[0033] It should be understood that the size of the serial number of each implementation process in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0034] The driving method provided by the present application can be applied to a vehicle to formulate a driving strategy for the vehicle or adjust the formulated driving strategy (i.e. optimize the driving strategy), thereby providing a guarantee for the safe driving of the vehicle. In the following description, the first vehicle can be regarded as the subject vehicle, and the second vehicle can be regarded as other vehicles close to the subject vehicle in driving distance. In actual application, the other vehicles close to the subject vehicle in driving distance include but are not limited to the front vehicle, rear vehicle, left vehicle, right vehicle, etc. of the subject vehicle.

[0035] The driving method provided by the present application can be applied to the subject vehicle to provide a new scheme for formulating or optimizing the driving strategy of the vehicle, thereby providing a new technical support for formulating or optimizing the driving strategy. Moreover, the new scheme can guarantee the safe driving of the subject vehicle.

[0036] The first embodiment of the driving method provided by the present application, as shown in Figure 1 The method comprises:

[0037] S101: obtaining environmental data of a first vehicle driving in a first driving strategy in an environment;

[0038] In this step, the environmental data refers to the environmental data of the first vehicle during driving, which can be regarded as the driving environment or external environment of the vehicle. It can be understood that the environmental data usually includes natural environment such as weather, road conditions, etc., and external interference information such as noise, electromagnetic interference, etc.

[0039] In the present application, if the weather, road conditions, noise, electromagnetic interference, etc. are regarded as different types of environmental data, the first vehicle can obtain the environmental data through the sensors or sensors installed in the vehicle for collecting each type of external environmental data.

[0040] The camera as a sensor can be used to collect the traveling image. The image clarity in normal weather is usually lower than that in abnormal weather, such as rain. The microphone as a sensor can collect audio information in the traveling environment. The audio noise collected in normal weather is usually lower than that in abnormal weather, such as rain. The greater the rain, the greater the audio noise. The friction coefficient sensor can sense the ground friction coefficient, or the friction coefficient supported by the tire can be obtained in the traveling environment. The friction coefficient can reflect the normal or abnormal road surface, such as wet and slippery. The more slippery the ground, the smaller the friction coefficient. The electromagnetic wave sensor or inductor can also sense the electromagnetic interference existing in the traveling environment. The greater the electromagnetic interference, the more serious the electromagnetic interference in the traveling environment.

[0041] It can be understood that by analyzing the above collected various types of information, including traveling image, audio information, friction coefficient, electromagnetic interference, etc., the first driving strategy of the vehicle can be determined.

[0042] The first driving strategy can be a strategy adopted by the first vehicle in the driving environment in terms of driving speed, brake distance, etc. Illustratively, the driving speed needs to be controlled at 80-100 km / h, and the brake distance is greater than or equal to 90 meters. It can be understood that the first driving strategy is based on the environmental data of the first vehicle in the environment. Illustratively, the environmental data can be input into a pre-trained artificial intelligence (AI) model to determine the first driving strategy using the AI model.

[0043] S102: If the second vehicle exists in the environment, the first reference information of the second vehicle is predicted according to the environmental data of the first vehicle;

[0044] In this step, if other vehicles such as the second vehicle exist in the environment where the vehicle is located, it means that the vehicle and other vehicles are in the same environment. For the weather (such as light, rain), road conditions, noise, electromagnetic interference, etc. environment suffered by the vehicle, other vehicles will also suffer such environment.

[0045] In simple terms, for the external environment suffered by the vehicle at a certain position, other vehicles are also subjected to the same or similar external environment by analogy or speculation. Based on the external environment suffered by the vehicle, the first reference information of other vehicles is predicted or speculated.

[0046] The first reference information can be the driving strategy of the second vehicle used in the same or similar environment as the first vehicle. The scheme for predicting the driving strategy of the second vehicle based on the environmental data of the first vehicle is described in the related description.

[0047] Preferably, the first reference information can be predicted second vehicle in the environment with the first vehicle, such as image clarity, audio situation, ground friction, electromagnetic interference information, etc.

[0048] In implementation, considering that the second vehicle exists in the environment of the first vehicle, the image clarity, audio situation, ground friction, electromagnetic interference information, etc. of the first vehicle in the environment can be taken as the first reference information of the second vehicle predicted by the first vehicle according to the traveling environment of the first vehicle. This scheme is the first prediction mode of the first reference information of the second vehicle by the first vehicle.

[0049] Alternatively, considering that the number and / or type of the camera, microphone, friction coefficient sensor, and electromagnetic wave sensor of the first vehicle and the second vehicle are different, there can be a certain conversion relationship between the information collected by the above sensors or sensors of the second vehicle and the information collected by the same sensors of the first vehicle. In the case of using the above multiple sensors of the first vehicle to collect the above multiple information, the first vehicle uses this conversion relationship to convert the first reference information of the second vehicle in the driving environment of the first vehicle, thereby realizing the prediction of the first reference information of the second vehicle. This scheme is the second prediction mode of the first reference information of the second vehicle by the first vehicle.

[0050] In the second prediction mode, the types and / or numbers of the above various types of sensors of the second vehicle in the same driving environment can be taken as public information in the network for the first vehicle to query. The first vehicle can determine the conversion relationship by comparing at least one of the types and numbers of the various types of sensors of the first vehicle and the various types of sensors of the first vehicle.

[0051] In implementation, the environmental data of the first vehicle can be taken as the input of a pre-trained artificial intelligence (AI) model such as a prediction model, and the prediction model can be used to predict the first reference information of the second vehicle.

[0052] The scheme of predicting the first reference information of the second vehicle based on the external environment suffered by the vehicle provides a new technical scheme for the adjustment of the driving strategy of the vehicle, and is easy to implement in engineering and has high feasibility.

[0053] The number of the second vehicle can be one or multiple. For convenience of description, it is assumed that the number of the second vehicle in the environment where the first vehicle is located is one.

[0054] In the present application, the reference information of the second vehicle is not obtained from the second vehicle side, but is predicted or inferred according to the environmental data of the first vehicle. The obtaining method of the reference information of the second vehicle is a new method, which lays a foundation for a new vehicle driving adjustment scheme.

[0055] S103: determining a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environmental data of the first vehicle, so that the first vehicle travels in the environment by using the second driving strategy; wherein the driving safety of the first vehicle in the environment by using the second driving strategy is better than the driving safety of the first vehicle in the environment by using the first driving strategy.

[0056] In this step, the second driving strategy can refer to the description of the first driving strategy. The second driving strategy is different from the first driving strategy, and the difference can be reflected in any aspect that can change the driving strategy, such as vehicle driving speed, safety distance, etc. Compared with the driving strategy of the first vehicle obtained based on the environmental data of the first vehicle, the second driving strategy of the first vehicle takes into account the influence of the first reference information of the second vehicle and the environmental data of the first vehicle on the driving strategy. The second driving strategy obtained based on the two factors is more secure than the first driving strategy, and the driving safety is improved.

[0057] In S101-S103, the more secure driving strategy (second driving strategy) adopted by the first vehicle takes into account the influence of the first reference information of the second vehicle on the driving strategy when the second vehicle is subjected to the same environment as the first vehicle. The first reference information of the second vehicle is predicted or inferred based on the environmental data of the first vehicle, and is not obtained from the second vehicle side. Compared with the related art, the present application is a new scheme for formulating or optimizing the driving strategy of the vehicle, and provides a new technical support for formulating or optimizing the driving strategy.

[0058] It can be understood that, in the present application, for the second vehicle existing in the environment where the first vehicle is located, the first vehicle can predict or speculate the first reference information of the second vehicle according to the environment, and determine the second driving strategy of the first vehicle which is safer than the first driving strategy according to the first reference information of the second vehicle and the environmental data of the first vehicle. In a popular way, for the environment suffered by the first vehicle, it is analogous to that other vehicles such as the second vehicle also suffer from the environment, and at the same time, based on the first reference information of the second vehicle suffered from the environment which is predicted or speculated and the environment suffered by the first vehicle, the determination of the safer driving strategy (the second driving strategy) is carried out, which can ensure the accuracy of the driving strategy and improve the driving safety.

[0059] In a popular way, the technical solution of the present application adjusts the driving strategy of the vehicle based on the comprehensive influence of the vehicle and other vehicles on the external environment, realizes the timely adjustment of the driving strategy, and ensures the driving safety.

[0060] In some embodiments, the technical solution of determining the second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environmental data of the first vehicle can be realized by the scheme as shown in Figure 2

[0061] S201: determining a first target influence factor based on the first reference information of the second vehicle and the environmental data of the first vehicle, the first target influence factor representing the influence degree of the first reference information of the second vehicle and the environmental data of the first vehicle on the first driving strategy;

[0062] In this step, the influence degree value of the first reference information of the second vehicle on the first driving strategy can be calculated based on the first reference information of the second vehicle, and the influence degree value of the environmental data of the first vehicle on the first driving strategy can be calculated based on the environmental data of the first vehicle. Then, the comprehensive influence degree value of the first reference information and the environmental data of the second vehicle on the first driving strategy is calculated as the first target influence factor. Wherein, the influence degree values of the first reference information and the environmental data on the first driving strategy can be calculated by using an artificial intelligence (AI) model such as a machine learning model.

[0063] ​It can be understood that in actual application, because the first driving strategy is formulated according to the environment data of the first vehicle, the influence degree of the environment data of the first vehicle on the first driving strategy is small or the influence degree value is 0 (no influence). The corresponding weight is pre-assigned to the environment data of the first vehicle and the first reference information of the second vehicle. The weight assigned to the environment data of the first vehicle is multiplied by the influence degree value of the environment data of the first vehicle on the first driving strategy, and then added to the multiplication result of the weight assigned to the first reference information of the second vehicle and the influence degree value of the first reference information of the second vehicle on the first driving strategy, to obtain a weighted average calculation result, and the weighted average calculation result is taken as a comprehensive influence degree value. Alternatively, the influence degree value of the first reference information of the second vehicle on the first driving strategy and the influence degree value of the environment data of the first vehicle on the first driving strategy are arithmetically averaged to obtain a comprehensive influence degree value (comprehensive influence factor).

[0064] S202: adjusting the first driving strategy based on the first target influence factor to obtain the second driving strategy.

[0065] Exemplarily, taking the environment in which the first vehicle is located as a normal light environment, and the clarity of the predicted travel image collected by the second vehicle as the normal clarity of the second vehicle as examples, the second vehicle can appropriately increase the driving speed under the condition of ensuring safe driving. As the first vehicle close to the second vehicle, such as the second vehicle being the rear vehicle of the first vehicle, the driving speed of the second vehicle is increased, and the first vehicle also needs to increase the driving speed on the basis of the first driving strategy to maintain the distance between the two vehicles as a safe distance.

[0066] Based on the AI model, the influence degree value of the first reference information of the second vehicle on the first driving strategy is calculated under the condition that the travel image of the second vehicle is of normal clarity. Assuming that the comprehensive influence factor obtained according to the weighted average calculation result is 1.2, the driving speed in the first driving strategy can be adjusted by 1.2 times, and the driving speed of 1.2 times is taken as the driving speed in the second driving strategy.

[0067] In a popular way, the adjustment or optimization of the first driving strategy of the first vehicle in S201-S202 is realized based on the comprehensive influence degree of the first reference information of the second vehicle and the environment data of the first vehicle on the first driving strategy, which provides a new technical solution for the adjustment of the driving strategy of the vehicle, is easy to implement in engineering, and has high feasibility. The first reference information of the second vehicle is obtained based on the environment data of the first vehicle, which provides technical support for the new technical solution of the driving strategy adjustment of the present application. The driving strategy adjustment based on the comprehensive influence degree value can ensure the accuracy of the adjustment and ensure safe driving.

[0068] In the foregoing scheme, the first reference information of the second vehicle is predicted or inferred according to the environmental data of the first vehicle. In addition, the first driving strategy of the first vehicle can also be considered, and the prediction or inference of the first reference information of the second vehicle is performed. That is, the first reference information of the second vehicle is predicted according to the environmental data of the first vehicle and the first driving strategy of the first vehicle.

[0069] It can be understood that the first driving strategy in the present application is obtained by inputting the environmental data of the first vehicle into an AI model and using the calculation of the AI model. In intelligent assisted driving or automatic driving, in order to achieve safe driving, the driving speed of the vehicle is related to the external environment. Taking the weather in the external environment as an example, in order to achieve safe driving, the driving speed of the vehicle in normal weather such as sunny day is higher than that in abnormal weather such as rainy day. The driving speed of the vehicle in strong light weather is lower than that in normal light weather. Therefore, the external environment can be inferred according to the driving speed. In the present application, the external environment data that the first vehicle may exist when the first driving strategy is adopted can be inferred based on this relationship. In the case where the inferred external environment data and the actual environment obtained by the first vehicle through various types of sensors or sensors are very small, it is proved that the actual environment obtained by the sensor or the sensor is accurate, and the collected actual environment is used as the input of the prediction model, to realize the prediction or inference of the first reference information of the second vehicle. The problem of inaccurate calculation of the first reference information caused by inaccurate actual environment (such as broken camera or scratched image blur) can be avoided.

[0070] In the foregoing scheme, the inference or prediction of the first reference information is performed according to the environmental data of the first vehicle and the first driving strategy, which can greatly ensure the accuracy of the environmental data of the first vehicle, thereby ensuring the accuracy of the prediction or inference of the first reference information, and further realizing the precise adjustment of the driving strategy of the first vehicle and improving the driving safety.

[0071] In the foregoing scheme, the scheme of optimizing the driving strategy of the first vehicle is realized under the condition that the environment of the first vehicle remains relatively stable, such as the first vehicle always being in the same or similar sunny day or always being in the stable rainy day during the driving time of the first vehicle, or the noise or electromagnetic wave interference on the driving route of the first vehicle being not much different. The first reference information of the second vehicle is predicted or inferred based on the environmental data of the first vehicle, which is a new scheme for formulating or optimizing the driving strategy of the vehicle.

[0072] In practical applications, the vehicle's driving environment may change. For example, it may change from normal weather to abnormal weather, from normal road conditions to slippery road conditions, from a region with normal audio frequencies to a region with abnormal audio frequencies, or from a region with normal electromagnetic interference to a region with abnormal electromagnetic interference. Specifically, changing from sunny weather to rainy weather, or from normal lighting to abnormal lighting, can be considered forms of changing from normal weather to abnormal weather. Similarly, moving from an area with low external noise to an area with high external noise can be considered a form of moving from a region with normal audio frequencies to a region with abnormal audio frequencies. Likewise, moving from an area with low electromagnetic interference to an area with high electromagnetic interference can be considered a form of moving from a region with normal electromagnetic interference to a region with abnormal electromagnetic interference.

[0073] If we predefine normal weather, normal road conditions, normal audio, and normal electromagnetic interference as standard environmental data for a vehicle, and abnormal weather, abnormal road conditions, abnormal audio, and abnormal electromagnetic interference as non-standard environmental data, then the aforementioned scheme can be considered as a scheme that, while maintaining the vehicle's environment at either standard or abnormal levels, predicts the first reference information for a second vehicle based on the environmental data of the first vehicle, and optimizes the vehicle's driving strategy based on the first reference information of the second vehicle and the environmental data of the first vehicle. However, in practical applications, the first vehicle may encounter changes in the external environment during its operation, such as a change from standard environmental data to a non-standard data environment, or vice versa.

[0074] Taking the environmental data of the first vehicle as an example, which is the environmental data after changes relative to the standard environmental data, such as... Figure 3 As shown, the method further includes:

[0075] S301: Based on the environmental data of the first vehicle, predict the second reference information of the second vehicle;

[0076] In this step, the meaning of the second reference information is similar to that of the first reference information mentioned above. By inputting the environmental data of the first vehicle after changes relative to the standard environmental data into the prediction model, the image clarity, audio conditions, ground friction conditions, electromagnetic interference conditions, etc. of the second vehicle in the changed external environment can be obtained, and at least one of these information is used as the second reference information of the second vehicle.

[0077] For example, in a standard environment such as under normal lighting, the first reference information of the second vehicle, such as image sharpness, is mostly at normal sharpness, such as 100% sharpness. In a changing environment, such as in an environment with strong lighting, the second reference information of the second vehicle, such as image sharpness, will decrease due to the strong lighting environment, such as a decrease of 20%, and the sharpness in the strong lighting environment will be 80% of the normal sharpness.

[0078] During implementation, the changed environmental data of the first vehicle can be input into the prediction model, and the prediction model can be used to obtain the second reference information of the second vehicle.

[0079] S302: Based on the second reference information of the second vehicle and the environmental data of the first vehicle, a third driving strategy for the first vehicle is determined so that the first vehicle can travel in the changed environment using the third driving strategy; wherein the driving safety of the first vehicle using the third driving strategy in the changed environment is better than the driving safety of the first vehicle using the second driving strategy in the changed environment.

[0080] In this step, the third driving strategy can be found in the explanations of the first and second driving strategies. The third driving strategy is different from the first and second driving strategies, and this difference can be reflected in any aspect that can change the driving strategy, such as vehicle speed and safe distance.

[0081] In the schemes shown in S301-S302, when the environmental data of the first vehicle changes relative to the standard environmental data, the reference information of the second vehicle is re-predicted based on the changed environmental data of the first vehicle. Then, based on the re-predicted reference information of the second vehicle and the changed environmental data of the first vehicle, the driving strategy of the first vehicle is adjusted in a timely manner. This scheme, which optimizes the driving strategy in a timely manner according to the changed environment, improves driving safety and demonstrates the advantages of better autonomous driving or intelligent assisted driving.

[0082] The aforementioned scheme predicts the second reference information of the second vehicle based on the environmental data of the first vehicle. Alternatively, the second reference information of the second vehicle can be predicted based on the environmental data of the first vehicle and the first reference information of the second vehicle.

[0083] It can be understood that the first reference information is the image clarity, audio conditions, ground friction conditions, electromagnetic interference conditions, etc., predicted by the first vehicle for the second vehicle in the first vehicle's standard environment. In implementation, the second reference information can be obtained by adjusting the first reference information of the second vehicle based on the changes in the first vehicle's environmental data relative to the standard environmental data.

[0084] Exemplarily, taking the image definition as an example of the reference information, in the standard environment data, the image definition is 100%. Relative to the light intensity in the standard environment, the light intensity in the environment where the first vehicle is located is enhanced by 10%. Since the stronger the light intensity is, the worse the definition of the traveling image is. By utilizing the change value of 10%, the image definition of 100% is adjusted to obtain the second reference information that the image definition is decreased by 10%. That is, in the second reference information, the image definition is 90%.

[0085] Based on the environment data of the first vehicle and the first reference information of the second vehicle, the second reference information of the second vehicle is predicted, which can simply and easily obtain the second reference information of the second vehicle, is easy to popularize, and has good reliability.

[0086] In some embodiments, according to the second reference information of the second vehicle and the environment data of the first vehicle, the scheme of determining the third driving strategy of the first vehicle can be implemented by the scheme shown in the following. Figure 4 In the scheme shown in the following, the method further includes: Figure 4

[0087] S401: obtaining a second target influence factor according to the second reference information of the second vehicle and the environment data of the first vehicle, the second target influence factor representing an influence degree of the second reference information and the changed environment data on the second driving strategy;

[0088] In this step, the influence degree value of the second reference information of the second vehicle on the second driving strategy can be calculated based on the second reference information of the second vehicle, and the influence degree value of the changed environment data of the first vehicle on the second driving strategy can be calculated based on the changed environment data of the first vehicle relative to the standard environment. Then, the comprehensive influence degree value of the second reference information of the second vehicle and the changed environment data on the second driving strategy is calculated as the second target influence factor. Wherein, the AI model can be used to calculate the influence degree values of the second reference information and the changed environment data on the second driving strategy.

[0089] ​It can be understood that in actual application, the corresponding weight is pre-assigned for the changed environment data of the first vehicle and the second reference information of the second vehicle. The weight assigned for the changed environment data of the first vehicle is multiplied by the influence degree value of the changed environment data of the first vehicle on the second driving strategy, and then added to the multiplication result of the weight assigned for the second reference information of the second vehicle and the influence degree value of the second reference information of the second vehicle on the second driving strategy, to obtain a weighted average calculation result, and the weighted average calculation result is taken as the comprehensive influence degree value. Alternatively, the influence degree value of the second reference information of the second vehicle on the second driving strategy and the influence degree value of the changed environment data of the first vehicle on the second driving strategy are arithmetically averaged to obtain the comprehensive influence degree value (comprehensive influence factor).

[0090] S402: Adjusting the second driving strategy of the first vehicle according to the second target influence factor to obtain a third driving strategy of the first vehicle.

[0091] Exemplarily, taking the light intensity in the changed environment of the first vehicle being enhanced and the second reference information being the clarity of the second vehicle traveling image being 80% as an example, assuming that the comprehensive influence factor obtained by the weighted average calculation of S401 is 0.8, then the driving speed in the second driving strategy can be adjusted by 0.8 times, and the driving speed in the second driving strategy is reduced to 0.8 times as the driving speed in the third driving strategy.

[0092] In S401-S402, the adjustment or optimization of the driving strategy of the first vehicle in the changed environment is realized based on the comprehensive influence degree of the second reference information of the second vehicle and the changed environment data of the first vehicle on the second driving strategy, which provides a technical support for the timely adjustment of the driving strategy of the first vehicle according to the changed environment. And the driving strategy adjustment based on the comprehensive influence degree value can ensure the accuracy of the adjustment and ensure safe driving.

[0093] It can be understood that the second vehicle is a vehicle that will be in the same environment as the first vehicle, and in the changed environment, the second reference information of the second vehicle predicted according to the changed environment will necessarily be more accurate than the first reference information predicted in the environment before the change. Thus, for the second vehicle, it can input the second reference information to the AI model to determine the driving strategy of the second vehicle in the changed environment. In the changed environment, the driving safety of the second vehicle driving by using the determined driving strategy in the changed environment is better than the driving safety of the second vehicle driving by using the driving strategy in the environment before the change. Wherein, the driving strategy in the environment before the change can be obtained by inputting the first reference information to the AI model and processing by the AI model. That is, in this application, the driving safety of the second vehicle based on the second reference information in the changed environment is better than the driving safety of the second vehicle based on the first reference information in the changed environment. It can be seen that the first vehicle and the second vehicle of the present disclosure can greatly guarantee the safety of vehicle driving by adjusting or optimizing the driving strategy with the change of the environment.

[0094] The following will be described in combination with Figure 5 and Figure 6 further illustrate the present solution.

[0095] In Figure 6 the scenario shown, vehicle A can be regarded as the first vehicle, and vehicle B can be regarded as the second vehicle. In the process of vehicle travel, vehicle A can travel from position 2 to position 1, and vehicle B, which is the rear vehicle of vehicle A, can also travel from position 2 to position 1 following the travel trajectory of vehicle A.

[0096] In the process of vehicle A travel, various types of sensors or inductors arranged or installed on vehicle A collect respective data. For example, a camera is used to collect travel images, a microphone is used to collect audio, and an electromagnetic wave sensor or inductor is used to collect electromagnetic wave interference.

[0097] It is assumed that when vehicle A is at position 2, vehicle B does not appear in the travel environment of vehicle A. The various types of sensors on vehicle A collect external environment data when vehicle A is at position 2 and input to the AI model to obtain the driving speed and / or brake distance that vehicle A can adopt at position 2, and at least one of these parameters is used as the first driving strategy in this application.

[0098] Assuming that vehicle A drives away from position 2 but does not reach position 1, vehicle A is at position 3 between position 2 and position 1, and vehicle B appears at position 2, it is considered that other vehicles appear in the environment in which vehicle A is located. When vehicle A reaches position 1, vehicle B also exists in the environment in which vehicle A is located. At this time, vehicle A can detect whether other vehicles appear behind it based on the distance collected by the distance sensor.

[0099] In the case where it is detected that other vehicles appear behind vehicle A, and assuming that the external environment from position 2 to position 1 is a relatively stable environment, vehicle A predicts the first reference information of the second vehicle based on the relatively stable external environment, and adjusts the originally adopted first driving strategy based on the first reference information of the second vehicle and the relatively stable external environment to obtain a new driving strategy, i.e., the second driving strategy, to adapt to the appearance of other vehicles.

[0100] In the foregoing scheme, when other vehicles appear in the external environment of vehicle A, the driving strategy of vehicle A is adjusted in time, thereby ensuring driving safety. The first reference information of vehicle B used in the adjustment process of the driving strategy is adjusted based on the external environment in which vehicle A is located. A new technical support is provided for the adjustment of the driving strategy, which has strong implementability and high feasibility.

[0101] The foregoing relatively stable environment can refer to standard environment data. Generally, for the data collected by each type of sensor provided on vehicle A, it is determined whether the data is within the standard range set for the data. If it is within the standard range, it is considered that the collected data is standard environment data. If it is not, it is considered that the environment in which vehicle A is located has changed relative to the standard environment data. If the external environment of vehicle A changes relative to the standard environment data, the change and the impact of the change on vehicle A are recorded.

[0102] Taking normal or standard light as an example of standard environment data, the camera in vehicle A is set with an acceptable standard light range when it is factory-set. Within this light range, the camera can present an image with 100% clarity.

[0103] If the light at position 1 changes, for example, compared with the relatively gentle sunlight at position 2 and position 3, the sunlight at position 1 is dazzling, so that the light intensity sensed by the camera at position 1 becomes strong. The strong light intensity will affect the imaging quality of the traveling image for the camera, and the imaging clarity decreases. For example, if the light intensity at position 1 increases by 20% compared with the previous position, the clarity of the traveling image decreases from the original 100% to 80%.

[0104] If vehicle A is affected by strong sunlight at position 1, the clarity of the travel image is reduced to 80%. Vehicle A is affected by such strong sunlight at position 1, when vehicle B travels to position 1, it will also be affected by the strong sunlight. Then, vehicle A refers to the influence of the strong sunlight at position 1 on the clarity of its own travel image to predict or speculate that vehicle B will also be affected by the strong sunlight at position 1 on the clarity of its own travel image.

[0105] For example, vehicle A takes the influence of the clarity of its own travel image reduced to 80% at position 1 as the predicted or speculated influence of the strong sunlight at position 1 on the clarity of its own travel image of vehicle B. Alternatively, considering that the camera of vehicle B can be different from the camera of vehicle A in number and / or type, the influence of the imaging clarity that vehicle B can be affected at position 1 is predicted based on the difference and the degree of influence that vehicle A is affected, that is, the second prediction scheme of the first reference information of the second vehicle is adopted.

[0106] Next, the degree of influence of the clarity of the travel image of vehicle A reduced to 80% is taken as the degree of influence of the second travel strategy of vehicle A under strong light at position 1. The predicted influence of the imaging clarity that vehicle B can be affected at position 1 is taken as the degree of influence of the second travel strategy of vehicle B. The two degrees of influence are weighted and averaged or arithmetically averaged to obtain a comprehensive influence degree value. For example, if the comprehensive influence factor obtained is 0.8, the travel speed in the second travel strategy can be adjusted by 0.8 times, and the travel speed in the second travel strategy is reduced to 0.8 times as the travel speed in the third travel strategy.

[0107] Here, the influence of the external environment on the host vehicle at a certain position, such as position 1, is analogous or speculated to the influence of other vehicles traveling to the position. It can be understood that if other vehicles travel to the position, the travel speed and / or brake distance of the other vehicles will change at the position. For example, if the light at the position becomes strong, the other vehicles will slow down to ensure safe driving. Considering safety, the host vehicle can slow down appropriately as the other vehicles slow down to maintain a safe distance between the host vehicle and the other vehicles.

[0108] In the optimization or adjustment scheme of the travel strategy of the host vehicle, the influence of the other vehicles is obtained by speculation or prediction of the host vehicle, and the method of obtaining the influence of the other vehicles is simple in engineering and easy to implement. Thus, the implementability of the travel strategy optimization or adjustment of the present application is ensured.

[0109] The adjustment scheme of the driving strategy analogizes or infers that other vehicles will also be affected similarly when they travel to the position where the vehicle A is affected by the external environment. Based on the influence, the driving strategy of the vehicle A is adjusted in time, so as to realize safer automatic driving or intelligent auxiliary driving.

[0110] In actual application, each type of sensor or sensor on the vehicle A is set with a corresponding standard range of data collected by the sensor or sensor when it leaves the factory. For example, when the light intensity of the external environment is within the range A (the standard range of light intensity), the imaging clarity of the camera can reach 100%. In a popular way, the present scheme can be:

[0111] S501: record the standard range of each sensor or sensor;

[0112] S502: each sensor or sensor collects its own data, and when the data collected by a certain sensor exceeds the standard range, the data is recorded and the influence is calculated; for example, when the light intensity of the external environment exceeds the range A, such as the light intensity at the position 1 exceeds the range A, the light intensity is recorded and the influence on the vehicle A under the light intensity is calculated; analogize or infer that other vehicles will also be affected similarly under the external environment.

[0113] Among them, the influence on the vehicle A can be used as the influence program value of the second driving strategy of the vehicle A in the strong light intensity environment. The influence on other vehicles under the external environment can be used as the influence degree value of the second driving strategy of the second reference information of the vehicle B.

[0114] S503: according to the influence on the vehicle A and other vehicles such as vehicle B under the strong light intensity, calculate the comprehensive influence degree value, wherein the comprehensive influence degree value is used as the second target influence factor.

[0115] S504: according to the comprehensive influence degree value, adjust the second driving strategy, and obtain the driving strategy of the vehicle A under the strong light intensity environment- the third driving strategy.

[0116] It can be understood that when vehicle A reaches position 1, which is an environment with strong light, vehicle A needs to slow down to ensure safe driving. Vehicle A assumes that the following vehicle B will also be affected by the strong light when it reaches position 1, and vehicle B will also slow down appropriately to ensure its safe driving. Vehicle A adjusts its driving strategy based on the direct and indirect effects of the strong light on vehicle B when it reaches position 1, as well as the effects of the strong light on itself when it reaches position 1, to ensure safe driving and avoid problems such as scratching or rear-end collisions between adjacent vehicles, such as vehicle A and vehicle B. For example, vehicle A slows down at position 1, while vehicle B does not slow down at position 1 and still drives at a faster speed, which may cause vehicle B to rear-end vehicle A during subsequent driving.

[0117] In the above scheme, the first, second and third driving strategies are driving strategies obtained by vehicle A using automatic driving technology.

[0118] If automatic driving is not used, and a person is driving, the driving strategy that he or she may use under the current strong light can be predicted or identified based on a driving style model, such as opening the sun visor, choosing a place with more shade, driving more cautiously (such as reducing driving speed and increasing braking distance), etc. Thus, safe driving is achieved. The driving style model can be an AI model that predicts or identifies the driving style of the driver.

[0119] In the foregoing scheme, the change in light and the change in other dimensions (see subsequent related description) are used as examples for explanation, which is equivalent to assuming that the other dimensions remain unchanged and only the light dimension changes. It can be understood that in actual application, in addition to light, at least one of the road conditions such as wet road conditions, environmental noise and electromagnetic wave interference may change during vehicle travel. In this application, changes in each of the above dimensions can be used to predict or classify similar changes in other vehicles in the corresponding dimension. The overall impact of each dimension on the driving strategy adjustment is obtained, and the driving strategy of the vehicle is adjusted based on the overall impact.

[0120] For example, taking the changes in light, wet road, and electromagnetic wave interference as examples, it is assumed that the influence degree of light is 60%, the influence degree of wet road is 20%, and the influence degree of electromagnetic wave interference is 50%. The influence degree values of the above dimensions are multiplied by the weights assigned to each dimension and then added to obtain the final comprehensive influence factor under multiple dimensions, and the driving strategy is adjusted in a timely manner according to the final comprehensive influence factor.

[0121] In addition, it needs to be explained that, taking the scenario shown by the strong light exposure suffered by vehicle A at position 1 as an example, the influence of the external environment suffered by vehicle A can include both direct and indirect influences of the change in the external environment on vehicle A. Among them, the direct influence can be regarded as the change in the collection accuracy of each sensor of the ego vehicle, such as vehicle A, caused by the change in the external environment, which means that the accuracy of the collected information changes. For example, the clarity of the travel image collected by the camera under strong light decreases, for example, by 20%. Compared with the case where the external environment does not change, the change in the external environment can bring more calculation amount and / or greater calculation difficulty to vehicle A. This influence can be used as one of the indirect influences. More calculation amount or greater calculation difficulty will increase the reaction time of the travel strategy adjustment. For example, in the case where the environment does not change, the reaction time of adjusting the travel strategy is 0.1s, i.e., the adjustment of the travel strategy can be completed within 0.1s to determine the new travel strategy. In the case where the environment changes, the reaction time of adjusting the travel strategy increases, such as to 0.3s, i.e., the adjustment of the travel strategy can be completed within 0.3s to determine the new travel strategy. The reaction time is significantly longer.

[0122] It can be understood that, in the case where the adjustment of the travel strategy is realized by the AI model, in the case where the external environment of the ego vehicle changes, the change in the accuracy of the data collected by the sensor and the change in the calculation amount and calculation difficulty can cause the adjustment accuracy of the AI model (referred to as model accuracy) to change. For example, in the case where the environment does not change, the AI model has a 99% probability of definitely increasing the travel strategy from 80 kilometers / hour to 90 kilometers / hour. In the case where the environment changes, this probability decreases, for example, the AI model has a 90% probability of definitely increasing the travel strategy from 80 kilometers / hour to 90 kilometers / hour, and the definitely correct rate of the model decreases from 99% to 90%. It can be seen that, for the ego vehicle, the change in the external environment in which it is located not only brings changes in the collection accuracy of the sensors of the ego vehicle and the reaction time of the travel strategy adjustment, but also brings changes in the model accuracy of the ego vehicle. The change in the model accuracy can be used as another indirect influence.

[0123] It can be understood that the foregoing scheme is to adjust the driving strategy by taking the direct influence as an influence factor. In implementation, in addition to taking the direct influence as an influence factor, at least one of the reaction time and / or the model accuracy can also be taken as an influence factor for guiding the vehicle A to adjust the driving strategy. That is, in the present application, the direct influence and the indirect influence brought by the change of the external environment to the vehicle can be taken as influence factors for adjusting the driving strategy. That is, the first and second reference information not only includes at least one of the image definition, the audio condition, the ground friction condition, the electromagnetic interference information, etc., but also includes at least one of the reaction time and the model accuracy. In this way, the adjustment accuracy can be ensured.

[0124] In the present application, the change of the external environment brings changes in the collection accuracy of the sensor of the host vehicle, the reaction time of the driving strategy adjustment, and the model accuracy of the host vehicle, etc. According to the analogy of the present application, other vehicles such as vehicle B will also suffer similar changes. It can be considered that the sensor collection accuracy of the other vehicle, the reaction time, and the adjustment accuracy of the AI model of the other vehicle will also change in the changed external environment. These changes of the other vehicle can be inferred based on the changes of the host vehicle in the changed external environment.

[0125] The collection accuracy of the sensor, the reaction time, and the model accuracy of the host vehicle and other vehicles can all be taken as influence factors brought by the change of the external environment for the driving strategy adjustment of the host vehicle. In this way, the present application is equivalent to considering the influence of the collection accuracy of the sensor, the reaction time, and the model accuracy of the host vehicle and other vehicles in all aspects, adjusting the driving strategy of the host vehicle based on the influence in all aspects, which can greatly improve the adjustment accuracy of the driving strategy, thereby ensuring the safe driving of the vehicle.

[0126] In a popular way, in the present application, it is considered that in the actual driving process, the driving strategy of the vehicle can be affected by various external environments. For example, the influence of light (the imaging clarity of the camera is poor under strong light), the influence of ambient noise (the more the ambient noise, the more the noise collected by the microphone), the influence of sand or water on the ground on the driving controllability and braking distance, the large interference of electromagnetic waves brought by high-power equipment in the surrounding, and the complex external environment (such as many disturbances and bumpy terrain) which can affect the adjustment speed of the driving strategy. In the present application, considering the above factors, according to the influence of the external environment on the vehicle, it is analogized or speculated that other vehicles are also affected in a similar way. Then, the driving strategy of the vehicle is adjusted in time by comprehensively considering the influence on the vehicle and the similar influence on other vehicles. A new technical solution is provided for the optimization of the driving strategy of the vehicle. A new technical support is provided for the formulation or adjustment of the driving strategy of the vehicle. In a popular way, according to the influence of the external environment on the vehicle, the present application speculates that other vehicles are affected by the external environment, and adjusts the driving strategy of the vehicle based on the comprehensive influence of the vehicle and other vehicles on the external environment, so as to realize the timely adjustment of the driving strategy and ensure the driving safety.

[0127] The present application provides a driving device, as shown in Figure 7 The device comprises:

[0128] The obtaining unit 701 is configured to obtain environment data of a first vehicle traveling in a first driving strategy in an environment;

[0129] The first prediction unit 702 is configured to, if a second vehicle exists in the environment, predict first reference information of the second vehicle according to the environment data of the first vehicle;

[0130] The first determination unit 703 is configured to determine a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle, so that the first vehicle travels in the second driving strategy in the environment;

[0131] The driving safety of the first vehicle in the second driving strategy in the environment is better than the driving safety of the first vehicle in the first driving strategy in the environment.

[0132] In some embodiments, the first driving strategy is obtained based on the environment data of the first vehicle;

[0133] The first determination unit 703 is configured to determine a first target influence factor based on the first reference information of the second vehicle, the first target influence factor representing the influence degree of the first reference information of the second vehicle on the first driving strategy;

[0134] adjust the first driving strategy based on the first target influence factor to obtain the second driving strategy.

[0135] In some embodiments, the first prediction unit 702 is configured to predict the first reference information of the second vehicle according to the environmental data of the first vehicle and the first driving strategy of the first vehicle.

[0136] In some embodiments, the device further comprises:

[0137] The second prediction unit is configured to predict the second reference information of the second vehicle based on the environmental data of the first vehicle if the environmental data of the first vehicle is changed data relative to the standard environmental data.

[0138] The second determination unit is configured to determine a third driving strategy of the first vehicle according to the second reference information of the second vehicle and the environmental data of the first vehicle, so that the first vehicle travels in the changed environment by using the third driving strategy; and the driving safety of the first vehicle in the changed environment by using the third driving strategy is better than the driving safety of the first vehicle in the changed environment by using the second driving strategy.

[0139] In some embodiments, the second prediction unit is configured to predict the second reference information of the second vehicle based on the environmental data of the first vehicle and the first reference information of the second vehicle.

[0140] In some embodiments, the second determination unit is configured to obtain a second target influence factor according to the second reference information of the second vehicle and the environmental data of the first vehicle, the second target influence factor representing the influence degree of the second reference information and the changed environmental data on the second driving strategy; and adjust the second driving strategy of the first vehicle based on the second target influence factor to obtain the third driving strategy of the first vehicle.

[0141] In some embodiments, the driving safety of the second vehicle in the changed environment based on the second reference information is better than the driving safety of the second vehicle in the changed environment based on the first reference information.

[0142] It should be noted that the driving device of the embodiments of the present application has similar principles to the driving method described above, and therefore the implementation process and implementation principles of the driving device can be described with reference to the implementation process and implementation principles of the above method, and the repeated parts will not be described again. The driving device in the present application can be located in a vehicle.

[0143] According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium. The electronic device comprises at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the aforementioned driving method.

[0144] The readable storage medium stores a non-transient computer readable storage medium of computer instructions for enabling a computer to perform the aforementioned driving method. For the description of the computer readable storage medium, please refer to the relevant description in Figure 8 .

[0145] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document. The electronic device 800 can be used as a device that can be installed or set in a vehicle to ensure the safe driving of the vehicle.

[0146] As shown in Figure 8 , the device 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0147] Various components in the device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, a speaker, etc.; the storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0148] The computing unit 801 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs various methods and processes described above, such as the driving method. For example, in some embodiments, the driving method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded onto the RAM 803 and executed by the computing unit 801, one or more steps of the driving method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the driving method by any other suitable means, such as by means of firmware.

[0149] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0150] Program code for carrying out methods of the present application can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0151] In the context of this application, a machine-readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include but are not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0152] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0153] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0154] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0155] In the technical solutions of the present application, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0156] The above merely describes a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be encompassed in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of driving a vehicle, characterized by, The method comprises: obtaining environment data of a first vehicle in an environment in which the first vehicle travels according to a first driving strategy; if a second vehicle exists in the environment, predicting first reference information of the second vehicle according to the environment data of the first vehicle and the first driving strategy of the first vehicle; determining a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle, so that the first vehicle travels in the environment according to the second driving strategy; wherein the safety of the first vehicle traveling in the environment according to the second driving strategy is better than the safety of the first vehicle traveling in the environment according to the first driving strategy; wherein the predicting of the first reference information of the second vehicle according to the environment data of the first vehicle and the first driving strategy of the first vehicle comprises: based on the first driving strategy of the first vehicle, back-propagating the external environment data in which the first vehicle is located; when the difference between the back-propagated external environment data in which the first vehicle is located and the obtained environment data of the first vehicle in the environment is small, inputting the obtained environment data of the first vehicle in the environment into a prediction model to obtain the first reference information of the second vehicle output by the prediction model; if the environment data of the first vehicle is data changed from standard environment data, the method further comprises: based on the environment data of the first vehicle, predicting second reference information of the second vehicle; calculating an influence degree value of the second reference information of the second vehicle on the second driving strategy; based on the changed environment data of the first vehicle relative to the standard environment, calculating an influence degree value of the changed environment data of the first vehicle on the second driving strategy; calculating a comprehensive influence degree value of the second reference information of the second vehicle and the changed environment data on the second driving strategy; adjusting the second driving strategy of the first vehicle according to the comprehensive influence degree value to obtain a third driving strategy of the first vehicle; wherein the safety of the first vehicle traveling in the changed environment according to the third driving strategy is better than the safety of the first vehicle traveling in the changed environment according to the second driving strategy.

2. The method of claim 1, wherein, The first driving strategy is obtained based on the environment data of the first vehicle; wherein the determining of the second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle comprises: based on the first reference information of the second vehicle and the environment data of the first vehicle, determining a first target influence factor, the first target influence factor representing the influence degree of the first reference information of the second vehicle and the environment data of the first vehicle on the first driving strategy; based on the first target influence factor, adjusting the first driving strategy to obtain the second driving strategy.

3. The method of claim 1, wherein, The predicting of the second reference information of the second vehicle based on the environment data of the first vehicle comprises: based on the environment data of the first vehicle and the first reference information of the second vehicle, predicting the second reference information of the second vehicle.

4. The method of claim 1, wherein, The driving safety of the second vehicle in the changed environment based on the second reference information is better than the driving safety of the second vehicle in the changed environment based on the first reference information.

5. A driving apparatus characterized by comprising: The device comprises: an obtaining unit configured to obtain environment data of a first vehicle in an environment in which the first vehicle travels in a first driving strategy; a first prediction unit configured to, if there is a second vehicle in the environment, predict first reference information of the second vehicle according to the environment data of the first vehicle and the first driving strategy of the first vehicle; a first determination unit configured to determine a second driving strategy of the first vehicle according to the first reference information of the second vehicle and the environment data of the first vehicle, so that the first vehicle travels in the environment in the second driving strategy; wherein the driving safety of the first vehicle in the environment in the second driving strategy is better than the driving safety of the first vehicle in the environment in the first driving strategy; wherein the first prediction unit is further configured to, based on the first driving strategy of the first vehicle, back-propagate external environment data in which the first vehicle is located; when a difference between the back-propagated external environment data in which the first vehicle is located and the obtained environment data of the first vehicle in the environment is small, input the obtained environment data of the first vehicle in the environment to a prediction model to obtain the first reference information of the second vehicle output by the prediction model; The device further comprises: a second prediction unit configured to, if the environment data of the first vehicle is changed data relative to standard environment data, predict second reference information of the second vehicle based on the environment data of the first vehicle; a second determination unit configured to calculate an influence degree value of the second reference information of the second vehicle on the second driving strategy, calculate an influence degree value of the changed environment data of the first vehicle on the second driving strategy based on the changed environment data of the first vehicle relative to the standard environment, calculate a comprehensive influence degree value of the second reference information of the second vehicle and the changed environment data on the second driving strategy, and adjust the second driving strategy of the first vehicle according to the comprehensive influence degree value to obtain a third driving strategy of the first vehicle; wherein the driving safety of the first vehicle in the changed environment in the third driving strategy is better than the driving safety of the first vehicle in the changed environment in the second driving strategy.

6. An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-4.

Images