Automatic driving vehicle obstacle encountering processing method and device, medium and equipment

Abstract

The invention discloses an obstacle encountering processing method and device for an automatic driving vehicle, a medium and equipment. The method comprises the steps of reporting blocking information to a cloud end when the time length of parking of the autonomous vehicle due to barrier blocking reaches a first preset time length; after a release instruction issued by the cloud is received, entering a release mode; in the release mode, determining a target obstacle meeting a preset ignoring condition; when driving planning is carried out in a release mode, the target obstacle is ignored, whether driving is recovered or not is determined according to a driving planning scheme, and the release mode is exited when the automatic driving vehicle meets a preset exit condition. Potential safety hazards when the automatic driving vehicle encounters obstacles are reduced through various means, and safe driving is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and device, medium, and equipment for handling obstacles encountered by an autonomous driving vehicle. Background Art

[0002] During field operations, autonomous vehicles may encounter problems such as being blocked by obstacles ahead and unable to resume driving. Obstacles such as leaves, plastic bags, and sensor noise can be ignored without affecting the driving safety of autonomous vehicles. However, when faced with a variety of obstacles, it is difficult for the autonomous driving system to accurately determine whether the obstacles pose a safety hazard to the vehicle, affecting normal driving or causing safety hazards. Summary of the invention

[0003] In order to solve at least one of the above technical problems, the present invention provides a method and device, medium, and equipment for handling obstacles of an autonomous driving vehicle.

[0004] According to the first aspect, the method for handling an obstacle of an autonomous driving vehicle provided by an embodiment of the present invention includes:

[0005] When the autonomous driving vehicle is stopped due to an obstacle and the parking time reaches a first preset time, reporting the blocking information to the cloud; wherein the blocking information includes the current environment information of the autonomous driving vehicle;

[0006] After receiving the release command issued by the cloud, entering the release mode; wherein, after receiving the blocking information, if the cloud determines according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle, then issuing the release command;

[0007] In the release mode, determine the target obstacles that meet the preset ignore conditions;

[0008] When performing driving planning in the release mode, the target obstacle is ignored, and the release mode is exited when the autonomous driving vehicle meets a preset exit condition.

[0009] In one embodiment, the method further includes: in the release mode, after resuming driving, controlling the driving speed of the autonomous driving vehicle to be less than a preset speed.

[0010] In one embodiment, before determining the target obstacles that meet the preset ignoring conditions, the method further includes: in the release mode, determining whether each obstacle meets the preset non-ignorable conditions; correspondingly, determining the target obstacles that meet the preset ignoring conditions includes: among the obstacles that do not meet the preset non-ignorable conditions, screening the target obstacles that meet the preset ignoring conditions.

[0011] In one embodiment, the preset non-negligible conditions include at least one of the following: the type of obstacle belongs to the non-negligible obstacle type recorded in the preset obstacle blacklist; the size of the minimum circumscribed rectangular frame of the obstacle is greater than or equal to the non-negligible obstacle size lower limit; the obstacle is located directly in front of the autonomous driving vehicle.

[0012] In one embodiment, before determining the target obstacle that meets the preset ignoring condition, the method further includes:

[0013] Determining a security level of the release instruction; wherein the security levels of the release instructions issued by cloud operation and maintenance personnel of different levels are different;

[0014] Determining the value of the security parameter according to the security level of the release instruction;

[0015] The preset ignore condition and / or the preset exit condition is determined according to the value of the security parameter.

[0016] In one embodiment, the preset ignoring condition includes: the distance between the obstacle and the autonomous driving vehicle is less than a preset distance upper limit and greater than a preset distance lower limit; and the moving speed of the obstacle is less than a preset moving speed.

[0017] In one embodiment, the preset exit condition includes at least one of the following: the driving distance of the autonomous driving vehicle after resuming driving reaches a preset longitudinal release distance, a new obstacle is identified entering the longitudinal path of the autonomous driving vehicle, the time when the autonomous driving vehicle enters the release mode reaches a second preset time, and the autonomous driving vehicle receives a cancel release instruction issued by the cloud.

[0018] According to the second aspect, the automatic driving vehicle obstacle handling device provided by the embodiment of the present invention includes:

[0019] An information reporting module, configured to report blocking information to the cloud when the autonomous driving vehicle is stopped due to an obstacle for a first preset time period; wherein the blocking information includes current environment information of the autonomous driving vehicle;

[0020] A mode setting module, configured to enter a release mode after receiving a release instruction issued by the cloud; wherein, after receiving the blocking information, the cloud issues the release instruction if it is determined according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle;

[0021] A first determination module is used to determine a target obstacle that meets a preset ignore condition in a release mode;

[0022] The recovery driving module is used to ignore the target obstacle when performing driving planning in the release mode, and exit the release mode when the automatic driving vehicle meets the preset exit conditions.

[0023] In one embodiment, the apparatus further comprises:

[0024] The speed control module is used to control the driving speed of the autonomous driving vehicle to be less than a preset speed after resuming driving in the release mode.

[0025] In one embodiment, the apparatus further comprises:

[0026] A second determination module, used for determining whether each obstacle meets a preset non-ignorable condition in a release mode before the first determination module determines the target obstacle that meets the preset ignorable condition;

[0027] Correspondingly, the first determination module is specifically used to: select target obstacles that meet the preset ignorable conditions from obstacles that do not meet the preset non-ignorable conditions.

[0028] In one embodiment, the preset non-ignorable condition includes at least one of the following:

[0029] The obstacle type belongs to the non-ignorable obstacle type recorded in the preset obstacle blacklist;

[0030] The size of the obstacle's minimum bounding rectangle is greater than or equal to the non-negligible lower limit of the obstacle size;

[0031] The obstacle is located directly in front of the autonomous driving vehicle.

[0032] In one embodiment, the apparatus further comprises:

[0033] The third determination module is used to determine the security level of the release instruction before the first determination module determines the target obstacle that meets the preset ignore condition; wherein the security levels of the release instructions issued by cloud operation and maintenance personnel of different levels are different; according to the security level of the release instruction, the value of the security parameter is determined; according to the value of the security parameter, the preset ignore condition and / or the preset exit condition is determined.

[0034] In one embodiment, the preset ignoring condition includes: the distance between the obstacle and the autonomous driving vehicle is less than a preset distance upper limit and greater than a preset distance lower limit; and the moving speed of the obstacle is less than a preset moving speed.

[0035] In one embodiment, the preset exit condition includes at least one of the following: the driving distance of the autonomous driving vehicle after resuming driving reaches a preset longitudinal release distance, a new obstacle is identified entering the longitudinal path of the autonomous driving vehicle, the time when the autonomous driving vehicle enters the release mode reaches a second preset time, and the autonomous driving vehicle receives a cancel release instruction issued by the cloud.

[0036] According to the third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method provided in the first aspect.

[0037] According to a fourth aspect, a computing device provided by an embodiment of the present invention includes a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method provided by the first aspect is implemented.

[0038] The embodiment of the present invention has the following technical effects: the autonomous driving vehicle automatically stops after encountering an obstacle, and after the parking time reaches a first preset time, the autonomous driving vehicle reports information to the cloud. When the cloud receives the blocking information, it determines whether the obstacle currently blocking the autonomous driving vehicle affects normal driving according to the reported current environmental information. If it does not affect normal driving, it will issue a travel instruction to the autonomous driving vehicle. After the autonomous driving vehicle receives the release instruction issued by the cloud, the autonomous driving vehicle will enter the release mode. In order to further ensure driving safety, after entering the release mode, it does not directly resume driving, but further judges whether the current obstacles meet the preset ignore conditions. If it is found that some obstacles meet the preset ignore conditions after judgment, the obstacles that meet the preset ignore conditions are taken as target obstacles. When performing driving planning, the target obstacles are not considered, but other obstacles other than the target obstacles are considered, and then it is decided whether to resume driving or keep the parking state. Moreover, the release mode is exited after certain conditions are met, thereby avoiding the potential safety hazards caused by the autonomous driving vehicle being in the release mode. In short, after the autonomous driving vehicle stops for a certain period of time due to obstacles, it will automatically report to the cloud, thereby triggering the remote assistance function of the cloud; even if the autonomous driving vehicle enters the release mode due to receiving the release command from the cloud, it must further screen out the target obstacles with preset ignore conditions; after meeting the preset exit conditions, it must exit the release mode in time. Through various means, the safety hazards of autonomous driving vehicles when encountering obstacles can be reduced to ensure safe driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 is a flow chart of a method for handling an obstacle of an autonomous driving vehicle in one embodiment of the present invention;

[0041] Figure 2 It is a structural block diagram of an obstacle handling device for an autonomous driving vehicle in one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0043] In a first aspect, an embodiment of the present invention provides a method for handling obstacles encountered by an autonomous driving vehicle, see Figure 1 The method comprises the following steps S110 to S140:

[0044] S110, when the duration of the parking of the autonomous driving vehicle due to the obstruction of an obstacle reaches a first preset duration, reporting obstruction information to the cloud; wherein the obstruction information includes current environment information of the autonomous driving vehicle;

[0045] The first preset duration can be set as needed, for example, 5 seconds.

[0046] Among them, the current environmental information of the autonomous driving vehicle, for example, the image reflecting the driving environment captured by the vehicle camera.

[0047] The blocking information may also include an identifier indicating that the autonomous driving vehicle stops due to an obstacle, for example, obj_stop = 1. In this way, the cloud can know that the autonomous driving vehicle stops due to an obstacle.

[0048] In actual scenarios, the autonomous vehicle automatically stops after encountering an obstacle. After the parking time reaches a first preset time, the autonomous vehicle reports information to the cloud. A clock timer can be introduced here, with the parking start time as t0, t as the current system time of the autonomous vehicle, and the first preset time tmax = 10s, when t-t0 equals 10s, the autonomous vehicle will report the blocking information to the cloud. For example, the blocking information includes: obj_stop = 1 and the image collected by the vehicle camera. After the cloud receives the blocking information, the cloud operation and maintenance personnel can determine whether the obstacle currently blocking the autonomous vehicle affects normal driving based on the reported image, and can even remotely observe the surrounding environment information of the autonomous vehicle through monitoring equipment. When the operation and maintenance personnel determine that the obstacle currently blocking the autonomous vehicle will not affect normal driving, they will issue a travel instruction to the autonomous vehicle.

[0049] S120, after receiving the release instruction issued by the cloud, entering the release mode; wherein, after receiving the blocking information, if the cloud determines according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle, then issuing the release instruction;

[0050] S130, in the release mode, determining a target obstacle that meets a preset ignore condition;

[0051] Specifically, it is determined whether each obstacle currently facing the autonomous driving vehicle meets the preset ignore condition, and the ignore attribute obs_ignore of the obstacle that meets the preset ignore condition is set to 1, and the ignore attribute label obs_ignore of the obstacle that does not meet the preset ignore condition is set to 0. Among them, the obstacle with obs_ignore being 1 is the target obstacle.

[0052] In one embodiment, the preset ignoring condition may include: the distance between the obstacle and the autonomous driving vehicle is less than a preset distance upper limit and greater than a preset distance lower limit; and the moving speed of the obstacle is less than a preset moving speed.

[0053] It can be seen that the above preset ignore conditions include two conditions, one is the condition corresponding to the distance, and the other is the condition corresponding to the speed. Only when both conditions are met can the preset ignore conditions be considered to be met. If the above distance corresponding conditions are met, it means that the obstacle is within a certain distance range in front of the autonomous driving vehicle, and it is not too close or too far. If it is too close, the obstacle may be in the blind spot of the autonomous driving vehicle, and the safety hazard is relatively large. At this time, the obstacle cannot be ignored. Only when it is not too close can the obstacle be ignored. If it is too far, the cloud or the autonomous driving vehicle may not accurately judge the size, type and other information of the obstacle, so it cannot be ignored. If the above speed corresponding conditions are met, it means that the obstacle is in a stopped or slow-moving state, and it will not cause a major safety hazard to the autonomous driving vehicle, so it can be considered to be ignored. If the speed of the obstacle is fast, it will cause a major safety hazard to the autonomous driving vehicle, so it cannot be ignored.

[0054] Therefore, the preset ignoring condition is considered to be met only when the above two conditions are met, which can greatly reduce the safety risks of autonomous driving vehicles.

[0055] S140. When performing driving planning in the release mode, the target obstacle is ignored, and the release mode is exited when the autonomous driving vehicle meets a preset exit condition.

[0056] It can be seen that after receiving the release command sent from the cloud, the autonomous driving vehicle will enter the release mode. In order to further ensure driving safety, after entering the release mode, it does not directly resume driving, but further judges whether the current obstacles meet the preset ignore conditions. As the name implies, the preset ignore condition refers to the condition that the existence of obstacles does not affect driving and can be ignored. In the actual scene, there can be multiple obstacles or one obstacle at present. If it is found through judgment that all obstacles meet the preset ignore conditions, driving planning can be carried out, and these obstacles are not considered during driving planning, and driving is resumed according to the driving planning scheme. If it is found through judgment that some obstacles meet the preset ignore conditions and some obstacles do not meet the preset ignore conditions, obstacles that meet the preset ignore conditions are not considered during driving planning, but obstacles that do not meet the preset ignore conditions are considered. For example, a driving plan is planned according to obstacles that do not meet the preset ignore conditions. The driving planning scheme may include starting acceleration, speed, driving path, etc. If the starting acceleration in the driving planning scheme is 0, it can be considered that driving cannot be resumed, otherwise driving can be resumed. That is, if there are obstacles that do not meet the preset ignore conditions among the current obstacles of the autonomous driving vehicle, it will further determine whether to continue to stay parked or resume driving based on these obstacles. If it resumes driving, it will plan the starting acceleration, speed, etc. After resuming driving, it will exit the release mode after meeting certain conditions. In this way, when a new obstacle appears, the above operation will be repeated to ensure the subsequent driving safety of the autonomous driving vehicle. If it is always in the release mode, it will affect the subsequent driving safety of the autonomous driving vehicle.

[0057] In one embodiment, the preset exit condition may include at least one of the following:

[0058] (1) The distance traveled by the autonomous driving vehicle after resuming driving reaches the preset longitudinal release distance;

[0059] (2) recognizing that a new obstacle has entered the longitudinal path of the autonomous vehicle;

[0060] (3) The duration of the autonomous driving vehicle entering the release mode reaches a second preset duration;

[0061] (4) The autonomous driving vehicle receives a release cancellation instruction issued by the cloud.

[0062] With respect to the above (1), the mileage of the autonomous driving vehicle when it stops is recorded as s0, and the mileage s1 is recorded in real time after resuming driving. When the resumed driving mileage s1-s0 reaches the preset longitudinal release distance, it is considered that the vehicle has passed through the area where there was an obstacle before, and therefore it is considered that the preset exit condition is met at this time.

[0063] Regarding the above (2), when a new obstacle enters the longitudinal path of the autonomous driving vehicle, the camera captures the new obstacle and the autonomous driving vehicle exits the release mode. The autonomous driving vehicle stops at a certain distance in front of the new obstacle and reports the blocking information to the cloud after the parking time reaches the first preset time, thereby entering a new round of processes. It can be seen that when a new obstacle enters the longitudinal path of the autonomous driving vehicle, it is considered that the preset exit condition is met at this time, which can ensure that the new round of processes will not be affected by the previous obstacles.

[0064] With respect to the above (3), the moment when the autonomous driving vehicle enters the release mode is recorded as moment t_0, the current system moment of the autonomous driving vehicle is t1, and the difference between moment t1 and moment t_0 is the duration of the autonomous driving vehicle entering the release mode. If the duration of the autonomous driving vehicle entering the release mode reaches a second preset duration, it is considered that the autonomous driving vehicle has been in the release mode for a long enough time. If driving is resumed, this duration can ensure that the autonomous driving vehicle can drive through the obstacle area. Therefore, it is considered that the preset exit condition is met at this time.

[0065] Regarding (4) above, when encountering some special situations, the cloud will issue a cancel release command to the autonomous driving vehicle. For example, the cloud learns through the GPS system, weather system, and real-time news that there are special situations such as sandstorms and landslides a certain distance ahead of the vehicle, but the autonomous driving vehicle still cannot see the special situation in its field of vision and therefore cannot stop or turn around in time. If the cloud issues a cancel release command, the autonomous driving vehicle will not ignore the obstacle and continue to drive, but will stop to avoid danger ahead. It is also possible that the operation and maintenance personnel did not observe the environment enough and issued an erroneous release command, and issued a cancel release command again after discovering the error.

[0066] In actual applications, due to the dynamic changes in the external environment, if the release mode is not exited in time, it may cause safety risks. The operation and maintenance personnel may also fail to observe the environment sufficiently and issue unreasonable release instructions. Setting the above preset exit conditions can ensure timely exit from the release mode and reduce safety risks.

[0067] In one embodiment, the method provided by the embodiment of the present invention may further include:

[0068] In the release mode, after resuming driving, the driving speed of the autonomous driving vehicle is controlled to be less than a preset speed.

[0069] That is, during the release process after resuming driving, you must maintain a low speed to ensure driving safety.

[0070] In one embodiment, before determining the target obstacle that meets the preset ignoring condition, the method may further include:

[0071] In the release mode, determine whether each obstacle meets the preset non-ignorable conditions;

[0072] Correspondingly, the determining of the target obstacle that meets the preset ignoring condition includes:

[0073] Among the obstacles that do not meet the preset non-ignorable conditions, target obstacles that meet the preset ignorable conditions are selected.

[0074] That is to say, after entering the release mode, first determine whether each obstacle meets the preset non-ignorable conditions. As the name implies, the preset non-ignorable conditions refer to the pre-set conditions that consider that obstacles cannot be ignored. There is no conflict between the preset non-ignorable conditions and the preset ignore conditions. The two screen obstacles in different aspects. If it is found through judgment that some obstacles meet the preset non-ignorable conditions and some obstacles do not meet the preset non-ignorable conditions, then in S130, obstacles that meet the preset ignore conditions are selected as target obstacles from the obstacles that do not meet the preset non-ignorable conditions. In S140, the target obstacle is ignored when performing driving planning. Instead, obstacles that meet the preset non-ignorable conditions, obstacles that do not meet the preset non-ignorable conditions and do not meet the preset ignore conditions, etc. can be considered to decide whether to continue to stay parked or resume driving.

[0075] Here, before executing the step of determining the target obstacles that meet the preset ignore conditions, a judgment is made as to whether each obstacle meets the preset non-ignorable conditions. This can avoid the operation and maintenance personnel issuing erroneous release instructions due to insufficient observation of the environment, and the safety risks caused by the autonomous driving vehicle ignoring dangerous obstacles.

[0076] Furthermore, the preset non-ignorable condition includes at least one of the following:

[0077] (1) The obstacle type belongs to the non-ignorable obstacle type recorded in the preset obstacle blacklist;

[0078] (2) The size of the smallest bounding rectangle of the obstacle is greater than or equal to the lower limit of the obstacle size that cannot be ignored;

[0079] (2) The obstacle is located directly in front of the autonomous driving vehicle.

[0080] Regarding the above (1), for example, the types of obstacles that cannot be ignored recorded in the preset obstacle blacklist may include pedestrians and vehicles. Even if the autonomous driving vehicle is in the release mode, if the obstacle in front is a person or a car, it cannot resume driving and remains parked.

[0081] Regarding the above (2), generally speaking, non-dangerous obstacles that affect the parking of the autonomous driving vehicle, such as leaves or noise points, are small in size and can be ignored. However, some obstacles are relatively large in size. The larger the obstacle, the greater the danger it may cause. Therefore, it is considered that the larger obstacle meets the non-ignorable condition. In S140, it is necessary to further consider the larger obstacle to decide whether to continue to stay parked or resume driving. Among them, the size of the obstacle is determined, for example, according to the length or width of the smallest circumscribed rectangular frame of the obstacle.

[0082] Regarding the above (3), some obstacles may be located on the front side of the autonomous driving vehicle, and some obstacles may be located directly in front of the autonomous driving vehicle. Although the obstacles located on the side front are in the field of view of the vehicle's camera, they have a relatively small impact on the autonomous driving vehicle, while the obstacles located directly in front may cause greater safety hazards. Because it is believed that the obstacles located directly in front of the autonomous driving vehicle meet the non-negligible condition, it is necessary to further consider the obstacles located directly in front of the autonomous driving vehicle in S140 to decide whether to continue to stay parked or resume driving.

[0083] In one embodiment, before determining the target obstacle that meets the preset ignoring condition, the following steps may also be included:

[0084] Determining a security level of the release instruction; wherein the security levels of the release instructions issued by cloud operation and maintenance personnel of different levels are different;

[0085] Determining the value of the security parameter according to the security level of the release instruction;

[0086] The preset ignore condition and / or the preset exit condition is determined according to the value of the security parameter.

[0087] That is to say, different cloud operation and maintenance personnel have different levels, and the security levels of the release instructions issued are different. Specifically, cloud operation and maintenance personnel with higher levels are more professional, so the release instructions issued are more accurate, so the values ​​of the determined security parameters can be broader, and the broader the values, the lower the corresponding security restrictions. The professionalism of cloud operation and maintenance personnel with lower security levels is worse than that of cloud operation and maintenance personnel with higher levels, so the accuracy of the release instructions issued by cloud operation and maintenance personnel with lower security levels is also worse, so the values ​​of the determined security parameters need to be more stringent, and the more stringent the values, the higher the corresponding security restrictions, thus achieving flexible adjustment of the values ​​of security parameters. The security parameters can be preset values ​​such as the preset upper limit value of the distance, the preset lower limit value of the distance, and the preset moving speed in the preset ignore conditions, or preset values ​​such as the preset longitudinal release distance and the second preset duration in the preset exit conditions, or the lower limit value of the obstacle size in the preset non-ignorable conditions. Therefore, in addition to determining the preset ignore condition and / or the preset exit condition according to the value of the security parameter, a preset non-ignorable condition may also be determined according to the value of the security parameter.

[0088] For example, the levels of operation and maintenance personnel are divided into two types: ordinary and professional. The preset lower limit value of the preset distance in the preset ignore condition used after the ordinary operation and maintenance personnel issue the operation instruction is greater than the preset lower limit value of the preset distance in the preset ignore condition used after the professional operation and maintenance personnel issue the operation instruction.

[0089] It can be seen that the lower the level of the operation and maintenance personnel, the lower the security level of the release instruction, and the higher the security limit force of the corresponding security parameters. The higher the level of the operation and maintenance personnel, the higher the security level of the release instruction, and the lower the security limit force of the corresponding security parameters. The security parameters are various preset values ​​used in the process of troubleshooting. That is, in order to further improve the security of the remote release function, operation and maintenance personnel of different levels can issue release instructions of different security levels. Release instructions of different security levels correspond to different values ​​of security parameters used in the release process, thereby achieving different restriction capabilities.

[0090] In summary, the method provided by the embodiment of the present invention mainly involves multiple aspects: the autonomous driving vehicle will automatically report to the cloud after stopping for a certain period of time due to obstacles, thereby triggering the remote assistance function of the cloud. Specifically, the human experience and knowledge of the operation and maintenance personnel in the cloud can be used to better help the autonomous driving vehicle to make judgments; even if the autonomous driving vehicle enters the release mode due to receiving the release command from the cloud, it is necessary to further screen out the target obstacles with preset ignore conditions, and then ignore the target obstacles and consider other obstacles during driving planning, so as to decide whether to resume driving or continue to stay in the parking state, so as to ensure driving safety; during the process of resuming driving, certain safety monitoring must also be carried out, for example, the speed after resuming driving is controlled, etc.; after the preset exit conditions are met, the release mode must be exited in time to ensure subsequent safe driving. It can be seen that the embodiment of the present invention reduces the safety hazards of autonomous driving vehicles through various means to ensure safe driving.

[0091] In a second aspect, an embodiment of the present invention provides an obstacle handling device for an autonomous driving vehicle, see Figure 2 , the device 100 comprises:

[0092] The information reporting module 110 is used to report the blocking information to the cloud when the autonomous driving vehicle stops due to the blocking of an obstacle for a first preset time; wherein the blocking information includes the current environment information of the autonomous driving vehicle;

[0093] A mode setting module 120, configured to enter a release mode after receiving a release instruction issued by the cloud; wherein, after receiving the blocking information, the cloud issues the release instruction if it is determined according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle;

[0094] A first determination module 130 is used to determine a target obstacle that meets a preset ignore condition in a release mode;

[0095] The recovery driving module 140 is used to ignore the target obstacle when performing driving planning in the release mode, and exit the release mode when the autonomous driving vehicle meets the preset exit conditions.

[0096] In one embodiment, the device may further include:

[0097] The speed control module is used to control the driving speed of the autonomous driving vehicle to be less than a preset speed after resuming driving in the release mode.

[0098] In one embodiment, the device may further include:

[0099] A second determination module, used for determining whether each obstacle meets a preset non-ignorable condition in a release mode before the first determination module determines the target obstacle that meets the preset ignorable condition;

[0100] Correspondingly, the first determination module is specifically used to: select target obstacles that meet the preset ignorable conditions from obstacles that do not meet the preset non-ignorable conditions.

[0101] In one embodiment, the preset non-ignorable condition includes at least one of the following:

[0102] The obstacle type belongs to the non-ignorable obstacle type recorded in the preset obstacle blacklist;

[0103] The size of the obstacle's minimum bounding rectangle is greater than or equal to the non-negligible lower limit of the obstacle size;

[0104] The obstacle is located directly in front of the autonomous driving vehicle.

[0105] In one embodiment, the apparatus further comprises:

[0106] The third determination module is used to determine the security level of the release instruction before the first determination module determines the target obstacle that meets the preset ignore condition; wherein the security levels of the release instructions issued by cloud operation and maintenance personnel of different levels are different; according to the security level of the release instruction, the value of the security parameter is determined; according to the value of the security parameter, the preset ignore condition and / or the preset exit condition is determined.

[0107] In one embodiment, the preset ignoring condition includes: the distance between the obstacle and the autonomous driving vehicle is less than a preset distance upper limit and greater than a preset distance lower limit; and the moving speed of the obstacle is less than a preset moving speed.

[0108] In one embodiment, the preset exit condition includes at least one of the following: the driving distance of the autonomous driving vehicle after resuming driving reaches a preset longitudinal release distance, a new obstacle is identified entering the longitudinal path of the autonomous driving vehicle, the time when the autonomous driving vehicle enters the release mode reaches a second preset time, and the autonomous driving vehicle receives a cancel release instruction issued by the cloud.

[0109] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the second aspect can be found in the corresponding parts of the method provided in the first aspect and will not be repeated here.

[0110] In a third aspect, an embodiment of the present invention provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0111] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program code stored in the storage medium.

[0112] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0113] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0114] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0115] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0116] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0117] In a fourth aspect, an embodiment of the present specification provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method in any embodiment of the specification.

[0118] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the computing device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0119] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification and claims, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a process, method or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0120] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for handling obstacles encountered by an autonomous driving vehicle, characterized in that: include: When the autonomous driving vehicle is stopped due to an obstacle and the parking time reaches a first preset time, reporting the blocking information to the cloud; wherein the blocking information includes the current environment information of the autonomous driving vehicle; After receiving the release command issued by the cloud, entering the release mode; wherein, after receiving the blocking information, if the cloud determines according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle, then issuing the release command; In the release mode, determine the target obstacles that meet the preset ignore conditions; When performing driving planning in the release mode, the target obstacle is ignored, and the release mode is exited when the autonomous driving vehicle meets a preset exit condition.

2. The method according to claim 1, characterized in that Also includes: In the release mode, after resuming driving, the driving speed of the autonomous driving vehicle is controlled to be less than a preset speed.

3. The method according to claim 1, characterized in that: Before determining the target obstacle that meets the preset ignoring condition, the method further includes: In the release mode, determine whether each obstacle meets the preset non-ignorable conditions; Correspondingly, the determining of the target obstacle that meets the preset ignoring condition includes: selecting the target obstacle that meets the preset ignoring condition from the obstacles that do not meet the preset non-ignorable condition.

4. The method according to claim 3, characterized in that The preset non-ignorable condition includes at least one of the following: The obstacle type belongs to the non-ignorable obstacle type recorded in the preset obstacle blacklist; The size of the obstacle's minimum bounding rectangle is greater than or equal to the non-negligible lower limit of the obstacle size; The obstacle is located directly in front of the autonomous driving vehicle.

5. The method according to claim 1, characterized in that Before determining the target obstacle that meets the preset ignoring condition, the method further includes: Determining a security level of the release instruction; wherein the security levels of the release instructions issued by cloud operation and maintenance personnel of different levels are different; Determining the value of the security parameter according to the security level of the release instruction; The preset ignore condition and / or the preset exit condition is determined according to the value of the security parameter.

6. The method according to claim 1, characterized in that The preset ignoring conditions include: the distance between the obstacle and the autonomous driving vehicle is less than a preset distance upper limit and greater than a preset distance lower limit; and the moving speed of the obstacle is less than a preset moving speed.

7. The method according to claim 1, characterized in that The preset exit condition includes at least one of the following: the driving distance of the autonomous driving vehicle after resuming driving reaches a preset longitudinal release distance, a new obstacle is identified entering the longitudinal path of the autonomous driving vehicle, the duration of the autonomous driving vehicle entering the release mode reaches a second preset duration, and the autonomous driving vehicle receives a cancel release instruction issued by the cloud.

8. An obstacle handling device for an autonomous driving vehicle, characterized in that: include: An information reporting module, configured to report blocking information to the cloud when the autonomous driving vehicle is stopped due to an obstacle for a first preset time period; wherein the blocking information includes current environment information of the autonomous driving vehicle; A mode setting module, configured to enter a release mode after receiving a release instruction issued by the cloud; wherein, after receiving the blocking information, the cloud issues the release instruction if it is determined according to the current environment information that the obstacle does not affect the passage of the autonomous driving vehicle; A first determination module is used to determine a target obstacle that meets a preset ignore condition in a release mode; The recovery driving module is used to ignore the target obstacle when performing driving planning in the release mode, and exit the release mode when the automatic driving vehicle meets the preset exit conditions.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

10. A computing device, characterized in that: The method comprises a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 7 is implemented.

Images