A method and device for identifying takeover type of unmanned equipment

Abstract

The present specification discloses a takeover type identification method, device, storage medium and electronic device for unmanned equipment. Based on the pre-established correspondence between event types and identification methods, after determining the takeover event to be identified and the event type of the takeover event to be identified, the takeover event to be identified can be identified by the identification method corresponding to the event type to obtain an identification result, thereby determining whether the event type of the takeover event to be identified is a risk takeover or a non-risk takeover. It can be considered that the identification method corresponding to the event type of the takeover event to be identified is a relatively accurate identification method for identifying the takeover event to be identified in the event type of the takeover event to be identified, thereby using the identification result of the takeover event to be identified by the identification method corresponding to the event type of the takeover event to be identified as the target identification result of the takeover event to be identified, so as to improve the accuracy of the identified target identification result.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for identifying the takeover type of unmanned equipment. Background Art

[0002] With the development of autonomous driving technology, autonomous vehicles can rely on artificial intelligence, visual computing, radar, monitoring devices and global positioning systems to work together, allowing computers to automatically and safely control motor vehicles without active human operation.

[0003] However, at present, in the development stage of autonomous driving technology, autonomous driving vehicles put into use must also have the function of takeover so that humans can intervene to control driving when the autonomous driving vehicle faces abnormal situations such as missing maps, complex road conditions, etc.

[0004] After a takeover event occurs, based on the analysis of the cause of the takeover event and the need to iterate the autonomous driving algorithm, it is necessary to identify the risk level of the takeover event in order to describe the risk of collision if the target device continues to drive under the control of the autonomous driving system without taking over the autonomous driving vehicle.

[0005] In the prior art, takeover events can be identified manually, but the efficiency of manual identification is low. How to improve the efficiency of identifying takeover events is a problem that needs to be solved urgently. Summary of the invention

[0006] This specification provides a takeover type identification method, device, storage medium and electronic device for unmanned equipment to partially solve the above-mentioned problems existing in the prior art.

[0007] This manual adopts the following technical solutions:

[0008] This specification provides a method for identifying the takeover type of unmanned equipment, including:

[0009] Determining a takeover event to be identified, wherein the takeover event to be identified is generated when the target device is taken over from an autonomous driving state;

[0010] Determining the event type of the takeover event to be identified according to the collected data corresponding to the takeover event to be identified;

[0011] Determine an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type as a target identification result of the takeover event to be identified, wherein the identification result includes risk takeover and non-risk takeover, and the correspondence between the event type and the identification method is established in advance.

[0012] Optionally, determining an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type specifically includes:

[0013] Acquire the recognition result of the takeover event to be identified input by the user as the first recognition result of the takeover event to be identified; simulate the takeover event to be identified, and determine the second recognition result of the takeover event to be identified according to the obtained simulation result;

[0014] An identification method corresponding to the event type is determined, and an identification result obtained by the determined identification method is used as a target identification result of the takeover event to be identified.

[0015] Optionally, determining an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type specifically includes:

[0016] Determine an identification method corresponding to the event type;

[0017] When the identification method corresponding to the event type is the first identification method, the identification result of the takeover event to be identified input by the user is obtained and used as the target identification result of the takeover event to be identified; when the identification method corresponding to the event type is the second identification method, the takeover event to be identified is simulated, and the identification result determined according to the simulation result is used as the target identification result of the takeover event to be identified.

[0018] Optionally, simulating the takeover event to be identified specifically includes:

[0019] Obtain the target device's own driving status data and surrounding environment data when it is taken over from the autonomous driving state;

[0020] A simulation scenario is constructed based on the driving state data and surrounding environment data of the target device, and the driving state of the target device without being taken over is simulated in the constructed simulation scenario to obtain a simulation result output by the simulation system.

[0021] Optionally, determining a second identification result of the takeover event to be identified according to the obtained simulation result specifically includes:

[0022] If the target device generates risks within the specified time period, the risk takeover is taken as the second identification result of the takeover event to be identified; if the target device does not generate risks within the specified time period, the non-risk takeover is taken as the second identification result of the takeover event to be identified.

[0023] Optionally, a correspondence between event types and identification methods is pre-established, specifically including:

[0024] Determine each sample takeover event, a standard identification result of each sample takeover event, and an event type of each sample takeover event;

[0025] For each sample takeover event, obtaining a recognition result of the takeover event to be identified input by the user as a first recognition result of identifying the sample takeover event by a first recognition method, simulating the sample takeover event, and obtaining a recognition result determined according to the simulation result as a second recognition result of identifying the sample takeover event by a second recognition method;

[0026] For each event type, based on the difference between the first identification result of each sample takeover event in the event type and the standard identification result, and the difference between the second identification result of each sample takeover event in the takeover event category and the standard identification result, an identification method corresponding to the event type is selected from the first identification method and the second identification method.

[0027] Optionally, according to the difference between the first identification result of each sample takeover event in the event type and the standard identification result and the difference between the second identification result of each sample takeover event in the takeover event category and the standard identification result, selecting an identification method corresponding to the event type from the first identification method and the second identification method specifically includes:

[0028] Selecting a number of designated sample takeover events whose standard recognition results are designated recognition results from each sample takeover event included in the event type;

[0029] According to the difference between the first identification result of the specified sample takeover event in the event type and the standard identification result and the difference between the second identification result of the specified sample takeover event in the takeover event category and the standard identification result, the identification method corresponding to the event type is selected from the first identification method and the second identification method.

[0030] Optionally, the method further comprises:

[0031] When the identification result of the event cannot be obtained by the identification method corresponding to the event type, the identification result of the takeover event to be identified by other identification methods is used as the target identification result of the takeover event to be identified.

[0032] This specification provides a device for identifying the takeover type of unmanned equipment, including:

[0033] An event determination module, used for determining a takeover event to be identified;

[0034] A type determination module, used to determine the event type of the takeover event to be identified;

[0035] An identification module is used to determine an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type as a target identification result of the takeover event to be identified, wherein the correspondence between the event type and the identification method is pre-established.

[0036] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for identifying the takeover type of unmanned equipment is implemented.

[0037] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the takeover type identification method of the unmanned equipment when executing the program.

[0038] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0039] In the takeover type identification method for unmanned equipment provided in the present specification, based on the pre-established correspondence between event types and identification methods, after determining the takeover event to be identified and the event type of the takeover event to be identified, the takeover event to be identified can be identified by the identification method corresponding to the event type to obtain an identification result, thereby determining whether the event type of the takeover event to be identified is a risk takeover or a non-risk takeover. It can be considered that the identification method corresponding to the event type of the takeover event to be identified is a more accurate identification method for identifying the takeover event to be identified in the event type of the takeover event to be identified, thereby using the identification result of the takeover event to be identified by the identification method corresponding to the event type of the takeover event to be identified as the target identification result of the takeover event to be identified, so as to improve the accuracy of the identified target identification result. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0041] Figure 1 A flowchart of a method for identifying a takeover type of unmanned equipment in this specification;

[0042] Figure 2 A schematic diagram of a takeover type identification device for unmanned equipment provided in this manual;

[0043] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this manual. DETAILED DESCRIPTION

[0044] In addition to the above-mentioned method of identifying takeover events entirely manually, takeover events can also be identified through machine learning models. However, the recognition accuracy of machine learning models is usually lower than that of manual identification.

[0045] Below, this specification provides a takeover type identification method for unmanned equipment, and uses the identification result of the takeover event to be identified using the identification method corresponding to the event type of the takeover event to be identified as the target identification result of the takeover event to be identified, so as to improve the accuracy of the identified target identification result.

[0046] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0047] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0048] Figure 1 The following is a flow chart of a method for identifying the takeover type of an unmanned device in this specification, which specifically includes the following steps:

[0049] S100: Determine a takeover event to be identified.

[0050] In the method for identifying the takeover type of unmanned equipment provided in this specification, the unmanned equipment is referred to as a target equipment in this specification, and the target equipment may be an autonomous driving vehicle or a vehicle with an assisted driving function. The target equipment may be a delivery vehicle used in the delivery field.

[0051] The takeover type identification method for unmanned equipment provided in this specification can be executed by a server or a terminal device, wherein when the execution subject is a server, the server can be any existing server, such as a cluster server, a distributed server, etc., and when the execution subject is a terminal device, the terminal device can be any existing electronic device, such as a laptop, a tablet computer, a mobile device, etc., or the target device itself, and this specification does not limit this. In the following, this specification takes the execution subject as a server as an example for explanation, and the server is referred to as an identification platform.

[0052] In the embodiments of this specification, in order to ensure the safety of the target device itself and the road, the target device will be equipped with a manual takeover function when it is put into use, wherein manual takeover means that the target device switches from driving under the control of the automatic driving system to driving under manual control after takeover.

[0053] Generally speaking, manual takeover is divided into near-field takeover and remote takeover. Among them, near-field takeover requires the target device to be equipped with a near-field safety officer. When the target device is taken over in the near-field, the near-field safety officer can directly control the driving of the target device through the vehicle control systems such as the steering wheel, accelerator, and brake. Remote takeover means that the control personnel sends a control signal to the target device based on the communication connection between the control personnel and the target device, thereby remotely controlling the driving of the target device.

[0054] In the embodiments of this specification, there is no restriction on whether the takeover method of the target device is near-field takeover or remote takeover. Whenever the target device switches from the automatic driving state to the manual control state, it can be considered that the target device is taken over.

[0055] In one embodiment of this specification, when the target device is taken over from the automatic driving state, a takeover event to be identified can be generated to describe the takeover fact. The takeover type identification method for unmanned equipment provided in this specification (hereinafter referred to as the takeover type identification method) is used to identify the takeover event to be identified generated by any method of this specification.

[0056] Of course, regarding the timing of executing the takeover type identification method provided in this specification, this specification provides the following two examples. The first is that after the above-mentioned takeover event to be identified is generated, the takeover type identification method provided in this specification is executed to determine the generated takeover event to be identified and identify it. The second is that the takeover type identification method provided in this specification is executed at a specified period, and the takeover events to be identified generated within the specified time period are identified.

[0057] By using the takeover type identification method provided in this specification, an identification result of the takeover event to be identified can be obtained. Specifically, the identification result is a description of the takeover event to be identified in a certain aspect. Exemplarily, when the identification result is a description of the event risk of the takeover event to be identified, the identification result can be the risk level of the takeover event to be identified. For another example, when the identification result is a description of the speed of takeover of the takeover event to be identified, the identification result can be a high-speed takeover, a medium-speed takeover, and a low-speed takeover, etc. For example only, the takeover type identification method provided in this specification is used to identify the event risk of the takeover event to be identified. In this case, the identification result obtained is the risk level of the takeover event to be identified. The risk level can be several. Exemplarily, the risk level can include two levels: risk takeover and non-risk takeover.

[0058] Among them, it can be considered that for each takeover event to be identified, risk takeover means that if the target device is not manually taken over, the target device will continue to drive under the control of the automatic driving system, which will cause risks. In contrast, non-risk takeover means that if the target device is not manually taken over, the target device will continue to drive under the control of the automatic driving system without causing risks. Among them, risks can refer to the risks of collision, violation, fall, etc. of the target device.

[0059] S102: Determine the event type of the takeover event to be identified according to the collected data corresponding to the takeover event to be identified.

[0060] In one embodiment of the present specification, each generated takeover event to be identified corresponds to an event type, and the event type is used to represent the event attribute of the takeover event to be identified.

[0061] In one embodiment of the present specification, several event types are predetermined. For each takeover event to be identified, the event type of the takeover event to be identified can be selected from the several event types predetermined for the takeover event to be identified, that is, the event type of the takeover event to be identified can be classified.

[0062] Based on different classification indicators, the event types preset for the takeover event to be identified may be different. For example, when the classification indicator is the problem that causes the takeover, the event type may include missed obstacle detection, detection device failure, etc., and when the classification indicator is the speed at which the target device is taken over, the event type may include high-speed takeover, medium-speed takeover, low-speed takeover, etc.

[0063] The embodiments of this specification make the following distinction between the event type and the identification result of the takeover event to be identified, that is, the event type and the identification result can be understood as the classification of the takeover event to be identified from different dimensions and under different classification indicators, that is, the event type and the identification result are preset as categories under different dimensions.

[0064] Furthermore, merely as an example, in the following embodiments of this specification, the classification indicator corresponding to the event type is the reason that caused the target device to be taken over, that is, the event type may include obstacle missed detection, detection equipment failure, etc.

[0065] In the first embodiment of the present specification, the event type of the event to be taken over may be determined. For example, the event type of the event to be taken over may be determined based on the collected data corresponding to the event to be identified.

[0066] Among them, the collected data corresponding to the takeover event to be identified may include the driving status data of the target device itself when it is taken over from the automatic driving state and the surrounding environment data collected by the collection device carried by itself.

[0067] Hereinafter, this specification provides two methods for determining the event type of the takeover event to be identified:

[0068] The first method is to respond to the event type received from the user input and use the event type received from the user input as the event type of the takeover event to be identified. The user may determine the input event type based on the collected data corresponding to the takeover event to be identified. The user may be an operator who manually identifies the event type of the takeover event to be identified.

[0069] The second method is to input the collected data corresponding to the takeover event to be identified into a pre-trained machine learning model to obtain the event type output by the machine learning model. Of course, the machine learning model may include a classifier, in which each class is set as each event type. The machine learning model can be any existing machine learning model, such as fully connected layers (FC), etc., and this specification does not limit this.

[0070] S104: Determine an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type as a target identification result of the takeover event to be identified, wherein the correspondence between the event type and the identification method is pre-established.

[0071] In the embodiments of this specification, it is a priori assumed that for different event types, the most accurate identification methods for identifying the takeover events to be identified in these different event types are also different. Among them, for different identification methods, the subject of identifying the takeover event to be identified may be different, or the steps of identifying the takeover event to be identified may be different, and this specification does not limit this.

[0072] Therefore, in the takeover type identification method provided in the present specification, a corresponding relationship is established in advance between the event type and the identification method, so as to determine the identification result of the takeover event to be identified according to the event type of the takeover event to be identified. That is, when a takeover event to be identified occurs, the event type of the takeover event to be identified is first classified to obtain the event type of the takeover event to be identified, and then, based on the mapping relationship between the event type and each identification method, the identification result of identifying the takeover event to be identified by the identification method corresponding to the event type is determined as the target identification result of the takeover event to be identified.

[0073] Among them, the identification method corresponding to the event type of the takeover event to be identified is regarded as a relatively accurate identification method for identifying the takeover event to be identified in the event type of the takeover event to be identified.

[0074] There can be multiple identification methods. Taking the above example in which the identification results include risk takeover and non-risk takeover, for example, the identification result of the takeover event to be identified input by the user can be obtained. For another example, the takeover event to be identified can be simulated, and the identification result of the takeover event to be identified can be determined based on the obtained simulation results. For another example, any existing machine learning model can be used to input the information of the takeover time to be identified into a pre-trained machine learning model to obtain the identification result output by the machine learning model, and so on.

[0075] In the following, the embodiments of this specification are described by taking the identification results including the first identification result and the second identification result as an example, wherein the identification result obtained by identifying the takeover event to be identified by the first identification method is the first identification result, and the identification result obtained by identifying the takeover event to be identified by the second identification method is the second identification result.

[0076] Exemplarily, identifying the takeover event to be identified by a first identification method may specifically include: obtaining an identification result of the takeover event to be identified input by a user, i.e., obtaining an identification result of the takeover event to be identified in response to the received user input, as the first identification result of the takeover event to be identified; identifying the takeover event to be identified by a second identification method may specifically include: simulating the takeover event to be identified, and determining a second identification result of the takeover event to be identified based on the obtained simulation result.

[0077] Based on the two identification methods provided in the above example, after determining the event type of the takeover event to be identified by any of the above methods, this specification provides the following two methods to determine the identification result of the takeover event to be identified based on the pre-established correspondence between the event type and the identification method:

[0078] The first one is to first use various identification methods to identify the takeover event to be identified, and after obtaining the identification results identified by various identification methods, select the target identification result of the takeover event to be identified from each identification result according to the correspondence between the event type and the identification method. Specifically, the identification result of the takeover event to be identified input by the user can be obtained as the first identification result of the takeover event to be identified; the takeover event to be identified is simulated, and the second identification result of the takeover event to be identified is determined according to the obtained simulation result. Then, the identification method corresponding to the event type can be determined, and the identification result obtained by the determined identification method can be used as the target identification result of the takeover event to be identified. Furthermore, when the first identification result and the second identification result are the same, the first identification result and the second identification result can be directly used as the target identification result without determining the identification method corresponding to the takeover event to be identified.

[0079] The second method is to first determine the identification method corresponding to the event type of the takeover event to be identified from various identification methods based on the correspondence between the event type and the identification method, and then use the identification result of the takeover event to be identified by the identification method corresponding to the event type as the target identification result of the takeover event to be identified. Specifically, the identification method corresponding to the event type can be determined first, and then, when the identification method corresponding to the event type is the first identification method, the identification result of the takeover event to be identified input by the user is obtained and used as the target identification result of the takeover event to be identified; when the identification method corresponding to the event type is the second identification method, the takeover event to be identified is simulated, and the identification result determined according to the obtained simulation result is used as the target identification result of the takeover event to be identified.

[0080] By any of the above methods, the target identification result of the takeover event to be identified can be obtained. Of course, those skilled in the art can understand that other identification methods can also be used to identify the takeover event to be identified and obtain the identification result of the takeover event to be identified, and this specification does not limit this.

[0081] In addition, when the identification result of the event cannot be obtained by the identification method corresponding to the event type, the identification result of the takeover event to be identified by other identification methods can also be used as the target identification result of the takeover event to be identified. For example, when the takeover event to be identified can only be identified by the first identification method or the second identification method, the identified identification result is used as the target identification result of the takeover event to be identified.

[0082] In one embodiment of the present specification, based on the determined target recognition results, the autonomous driving system that controls the driving of the target device can be evaluated, the degree of risk faced by the target device during actual driving can be evaluated, and guidance can be provided in the process of updating and optimizing the autonomous driving system based on any of the above evaluation results.

[0083] In the above Figure 1 In the takeover type identification method for unmanned equipment provided, based on the pre-established correspondence between event types and identification methods, after determining the takeover event to be identified and the event type of the takeover event to be identified, the identification result of identifying the takeover event to be identified by the identification method corresponding to the event type can be determined as the target identification result of the takeover event to be identified. It can be considered that the identification method corresponding to the event type of the takeover event to be identified is a more accurate identification method for identifying the takeover event to be identified in the event type of the takeover event to be identified, so that the identification result of the takeover event to be identified by the identification method corresponding to the event type of the takeover event to be identified is used as the target identification result of the takeover event to be identified, so as to improve the accuracy of the identified target identification result.

[0084] With respect to the above-mentioned second identification method, this specification provides the following embodiments to exemplarily illustrate a method for identifying a takeover event to be identified by using the second identification method.

[0085] Specifically, during the driving process, the target device can obtain its own driving state data (such as speed, acceleration, direction, etc.), and can also record the environmental data during the driving process through its own sensors (such as cameras, radars, etc.) and obtain surrounding environment data. The surrounding environment data may include traffic road data, traffic light data, and the type of obstacles (such as motor vehicles, non-motor vehicles, pedestrians, etc.), the location of obstacles, etc.

[0086] Then, based on the driving status data and surrounding environment data of the target device, any existing method can be used to simulate and reproduce the scene in which the target device is located during or before the takeover in the simulation system to obtain the constructed simulation scene and the simulation objects contained in the simulation scene.

[0087] Next, based on the simulation system, the driving state of the target device without being taken over can be simulated in the simulation scenario to obtain a simulation result output by the simulation system, so as to determine a second identification result of the takeover event to be identified based on the simulation result.

[0088] In one embodiment of this specification, if the target device generates a risk within a specified time period, the risk takeover is used as the second identification result of the takeover event to be identified; if the target device does not generate a risk within a specified time period, the non-risk takeover is used as the second identification result of the takeover event to be identified. The generation of risk may refer to the risk of collision, falling, etc. of the target device.

[0089] Taking the risk of collision of the target device as an example, when the distance between the target device and the simulated obstacle in the simulation scene is less than the specified safety distance (for example, 2 meters), it can be considered that the target device has a collision risk. Furthermore, it can be set that if the target device has a risk such as a collision with a simulated obstacle within a specified time period, the risk takeover is used as the second identification result of the takeover event to be identified; if the target device has a risk such as a collision with a simulated obstacle within a specified time period, the non-risk takeover is used as the second identification result of the takeover event to be identified. The embodiments of this specification do not limit how to set the risk of the target device.

[0090] Exemplarily, a correspondence may be established in advance between each event type and each identification method in the following manner.

[0091] Each sample takeover event may be obtained first, and a standard recognition result of each sample takeover event and an event type of each sample takeover event may be determined. The standard recognition result may be considered to be an accurate recognition result of the sample takeover event. For example, it may be a recognition result determined by an expert in the field.

[0092] Then, for each sample takeover event, the identification result of the takeover event to be identified input by the user can be obtained as a first identification result of the sample takeover event identified by the first identification method, and the sample takeover event can be simulated by any of the above methods to obtain an identification result determined according to the simulation result, as a second identification result of the sample takeover event identified by the second identification method.

[0093] Next, for each event type, based on the difference between the first identification result of each sample takeover event in the event type and the standard identification result (hereinafter referred to as the first difference) and the difference between the second identification result of each sample takeover event in the takeover event category and the standard identification result (hereinafter referred to as the second difference), an identification method corresponding to the event type can be selected from the first identification method and the second identification method.

[0094] It should be noted that when the first difference is smaller than the second difference, the selected identification method corresponding to the event type may be the first identification method, and when the second difference is smaller than the first difference, the selected identification method corresponding to the event type may be the second identification method. When the first difference is equal to the second difference, the selected identification method corresponding to the event type may be the first identification method or the second identification method, and this specification does not limit this.

[0095] Furthermore, a difference threshold may be pre-set. When both the first difference and the second difference are greater than the first difference threshold, it may be considered that the accuracy of the first identification method and the second identification method in identifying the takeover event of this event type is not ideal. In this case, the first identification method or the second identification method may be designated as the identification method corresponding to the event type. When the difference between the first difference and the second difference is less than the second difference threshold, it may be considered that the first identification method and the second identification method have little difference in identification accuracy when identifying the takeover event of this event type. In this case, the first identification method or the second identification method may be designated as the identification method corresponding to the event type. This specification does not limit whether the designated identification method is the first identification method or the second identification method.

[0096] In addition, since the accuracy requirements for the identification results of different categories may be different when dealing with the identification of takeover events, for example, in the above example, in order to ensure the accurate identification of takeover events with a higher risk level, the identification accuracy requirement for risk takeovers may be higher. Therefore, in the embodiments of the present specification, the type of identification result that is more concerned, more important, and has a higher identification accuracy requirement can be used as the designated identification result. Then, when determining the identification method corresponding to the event type, several designated sample takeover events whose standard identification results are designated identification results can be selected from the sample takeover events included in the event type. Then, based on the difference between the first identification result of the designated sample takeover event in the event type and the standard identification result and the difference between the second identification result of the designated sample takeover event in the takeover event category and the standard identification result, the identification method corresponding to the event type is selected from the first identification method and the second identification method.

[0097] Of course, driven by experience, it is also possible to a priori establish a correspondence between certain event types and a certain identification method.

[0098] Exemplarily, the first identification method is to respond to the identification result of the takeover event to be identified by the received user input as the first identification result of the takeover event to be identified, and the second identification method is to simulate the takeover event to be identified and determine the second identification result of the takeover event to be identified based on the obtained simulation result. In this case, a correspondence can be established between the event type of the takeover event to be identified that cannot be simulated by the simulation system and the first identification result, such as a laser radar failure of the target device when the takeover occurs, etc. This manual does not elaborate on this.

[0099] The above is a method for identifying the takeover type of unmanned equipment provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding device for identifying the takeover type of unmanned equipment, such as Figure 2 shown.

[0100] Figure 2 A schematic diagram of a takeover type identification device for unmanned equipment provided in this specification, the device comprising:

[0101] An event determination module 200, configured to determine a takeover event to be identified, wherein the takeover event to be identified is generated when a target device is taken over from an autonomous driving state;

[0102] A type determination module 202, configured to determine the event type of the takeover event to be identified based on the collected data corresponding to the takeover event to be identified;

[0103] The identification module 204 is used to determine the identification result of the takeover event to be identified by using the identification method corresponding to the event type as the target identification result of the takeover event to be identified, wherein the identification result includes risk takeover and non-risk takeover, and the correspondence between the event type and the identification method is pre-established.

[0104] Optionally, the identification result includes risk takeover and non-risk takeover; the event determination module 200 is also used to generate a takeover event to be identified when the target device is taken over from the automatic driving state.

[0105] Optionally, the identification module 204 is specifically used to obtain the identification result of the takeover event to be identified input by the user as the first identification result of the takeover event to be identified; simulate the takeover event to be identified, and determine the second identification result of the takeover event to be identified based on the simulation result obtained; determine the identification method corresponding to the event type, and use the identification result obtained by the determined identification method as the target identification result of the takeover event to be identified.

[0106] Optionally, the identification module 204 is specifically used to determine an identification method corresponding to the event type;

[0107] When the identification method corresponding to the event type is the first identification method, the identification result of the takeover event to be identified input by the user is obtained and used as the target identification result of the takeover event to be identified; when the identification method corresponding to the event type is the second identification method, the takeover event to be identified is simulated, and the identification result determined according to the simulation result is used as the target identification result of the takeover event to be identified.

[0108] Optionally, the identification module 204 is specifically used to obtain the target device's own driving status data and surrounding environment data when the target device is taken over from the automatic driving state; construct a simulation scene based on the driving status data and surrounding environment data of the target device, and simulate the driving state of the target device under the condition of not being taken over in the constructed simulation scene to obtain a simulation result output by the simulation system.

[0109] Optionally, the identification module 204 is specifically used to, if the target device generates a risk within a specified time period, use the risk takeover as the second identification result of the takeover event to be identified; if the target device does not generate a risk within the specified time period, use the non-risk takeover as the second identification result of the takeover event to be identified.

[0110] Optionally, the identification module 204 is specifically used to determine each sample takeover event, a standard identification result of each sample takeover event, and an event type of each sample takeover event; for each sample takeover event, obtain the identification result of the takeover event to be identified input by the user as a first identification result of identifying the sample takeover event by a first identification method, simulate the sample takeover event, and obtain an identification result determined according to the simulation result as a second identification result of identifying the sample takeover event by a second identification method; for each event type, select an identification method corresponding to the event type from the first identification method and the second identification method according to the difference between the first identification result and the standard identification result of each sample takeover event in the event type and the difference between the second identification result and the standard identification result of each sample takeover event in the takeover event category.

[0111] Optionally, the identification module 204 is specifically used to select several specified sample takeover events whose standard identification results are specified identification results from the sample takeover events included in the event type; and select an identification method corresponding to the event type from the first identification method and the second identification method based on the difference between the first identification result and the standard identification result of the specified sample takeover event in the event type and the difference between the second identification result and the standard identification result of the specified sample takeover event in the takeover event category.

[0112] Optionally, the identification module 204 is also used to, when the identification result of the event cannot be identified by the identification method corresponding to the event type, use the identification result of the takeover event to be identified by other identification methods as the target identification result of the takeover event to be identified.

[0113] The present specification also provides a computer-readable storage medium storing a computer program, which can be used to execute the above-mentioned method for identifying the takeover type of unmanned equipment.

[0114] This manual also provides Figure 3 The structural diagram of the electronic device shown in FIG. Figure 3 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above-mentioned takeover type identification method for unmanned equipment.

[0115] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0116] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0117] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0118] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0119] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0120] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0124] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0125] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0126] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0127] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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 process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0128] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0130] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0131] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for identifying the takeover type of unmanned equipment, characterized in that: include: Determining a takeover event to be identified, wherein the takeover event to be identified is generated when the target device is taken over from an autonomous driving state; Determining the event type of the takeover event to be identified according to the collected data corresponding to the takeover event to be identified; Determine an identification result of identifying the takeover event to be identified by using the identification method corresponding to the event type as a target identification result of the takeover event to be identified, wherein the identification result includes risk takeover and non-risk takeover, and the correspondence between the event type and the identification method is pre-established; The determining of the identification result of identifying the takeover event to be identified by using the identification method corresponding to the event type specifically includes: Determine an identification method corresponding to the event type; When the identification method corresponding to the event type is the first identification method, the identification result of the takeover event to be identified input by the user is obtained and used as the target identification result of the takeover event to be identified; when the identification method corresponding to the event type is the second identification method, the takeover event to be identified is simulated, and the identification result determined according to the simulation result is used as the target identification result of the takeover event to be identified.

2. The method according to claim 1, characterized in that Determining an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type specifically includes: Acquire the recognition result of the takeover event to be identified input by the user as the first recognition result of the takeover event to be identified; simulate the takeover event to be identified, and determine the second recognition result of the takeover event to be identified according to the obtained simulation result; An identification method corresponding to the event type is determined, and an identification result obtained by the determined identification method is used as a target identification result of the takeover event to be identified.

3. The method according to any one of claims 1 or 2, characterized in that: The simulation of the takeover event to be identified specifically includes: Obtain the target device's own driving status data and surrounding environment data when it is taken over from the autonomous driving state; A simulation scenario is constructed based on the driving state data and surrounding environment data of the target device, and the driving state of the target device without being taken over is simulated in the constructed simulation scenario to obtain a simulation result output by the simulation system.

4. The method according to claim 3, characterized in that Determining a second identification result of the takeover event to be identified according to the obtained simulation result specifically includes: If the target device generates risks within the specified time period, the risk takeover is taken as the second identification result of the takeover event to be identified; if the target device does not generate risks within the specified time period, the non-risk takeover is taken as the second identification result of the takeover event to be identified.

5. The method according to claim 1, characterized in that Establish the correspondence between event types and identification methods in advance, including: Determine each sample takeover event, a standard recognition result of each sample takeover event, and an event type of each sample takeover event; for each sample takeover event, obtain a recognition result of the takeover event to be recognized input by a user as a first recognition result of the sample takeover event recognized by a first recognition method, simulate the sample takeover event, and obtain a recognition result determined according to the simulation result as a second recognition result of the sample takeover event recognized by a second recognition method; For each event type, based on the difference between the first identification result of each sample takeover event in the event type and the standard identification result, and the difference between the second identification result of each sample takeover event in the takeover event category and the standard identification result, an identification method corresponding to the event type is selected from the first identification method and the second identification method.

6. The method according to claim 5, characterized in that According to the difference between the first identification result of each sample takeover event in the event type and the standard identification result and the difference between the second identification result of each sample takeover event in the takeover event category and the standard identification result, selecting an identification method corresponding to the event type from the first identification method and the second identification method specifically includes: Selecting a number of designated sample takeover events whose standard recognition results are designated recognition results from each sample takeover event included in the event type; According to the difference between the first identification result of the specified sample takeover event in the event type and the standard identification result and the difference between the second identification result of the specified sample takeover event in the takeover event category and the standard identification result, the identification method corresponding to the event type is selected from the first identification method and the second identification method.

7. The method according to claim 1, characterized in that The method further comprises: When the identification result of the event cannot be obtained by the identification method corresponding to the event type, the identification result of the takeover event to be identified by other identification methods is used as the target identification result of the takeover event to be identified.

8. A device for identifying the takeover type of unmanned equipment, characterized in that: The device specifically comprises: An event determination module, used for determining a takeover event to be identified; A type determination module, used to determine the event type of the takeover event to be identified; An identification module is used to determine an identification result of identifying the takeover event to be identified by using an identification method corresponding to the event type as a target identification result of the takeover event to be identified, wherein the correspondence between the event type and the identification method is pre-established; the determination of the identification result of identifying the takeover event to be identified by using the identification method corresponding to the event type specifically includes: Determine an identification method corresponding to the event type; When the identification method corresponding to the event type is the first identification method, the identification result of the takeover event to be identified input by the user is obtained and used as the target identification result of the takeover event to be identified; when the identification method corresponding to the event type is the second identification method, the takeover event to be identified is simulated, and the identification result determined according to the simulation result is used as the target identification result of the takeover event to be identified.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

Images