Method for detecting automatic control system, control method, chip, equipment and medium

Abstract

The invention provides a method for detecting an automatic control system, a control method, a chip, equipment and a medium, and the method for detecting the automatic control system comprises the steps: obtaining a perception map for a target scene generated by the automatic control system based on target scene data; wherein the target scene data is collected by a mobile device in the target scene; obtaining a truth value map of the target scene obtained by performing truth value labeling on the target scene data; and comparing the perception map with the truth value map based on a set index set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene, wherein the index set comprises indexes associated with the position of the mobile device in the perception map.

Description

Technical Field

[0001] The present disclosure relates to the field of automatic control technology, and more specifically, to a method for detecting an automatic control system, a control method for a movable device, a chip, an electronic device, a movable device, and a computer-readable storage medium. Background Art

[0002] For movable devices such as vehicles, they can achieve unmanned automatic movement through the matching automatic control system. Specifically, the automatic control system determines the scene information through the scene data collected by the movable device, and then realizes the mobile control of the movable device. It can be seen that the scene perception ability of the automatic control system is crucial to realize the mobile control of the movable device. It is necessary to test the scene perception ability of the automatic control system to improve the perception accuracy and stability of the automatic control system based on the detection results. The existing detection method is based on the detection object within the perception range, and it is impossible to determine the perception ability of the automatic control system to pay attention to the object required to complete the mobile control of the equipment, which affects the effectiveness of the detection. Summary of the invention

[0003] In view of this, an embodiment of the present disclosure proposes a new technical solution for detecting the scene perception capability of an automatic control system.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for detecting an automatic control system is provided, the method comprising:

[0005] A method for obtaining a perception map of a target scene generated by an automatic control system based on target scene data is provided; wherein the target scene data is collected by a movable device in the target scene;

[0006] Acquire a true value map of the target scene based on true value annotation of the target scene data;

[0007] The perception map and the true map are compared based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene; wherein the set indicator set includes an indicator associated with the position of the movable device in the perception map.

[0008] Optionally, the set indicator set includes at least one indicator of a local indicator associated with the location and a global indicator associated with the location; wherein,

[0009] The local indicator associated with the position includes: an indicator of the scene perception capability detected based on a local area of ​​the perception map, the local area being an area determined based on the position of the movable device in the perception map;

[0010] The global metric associated with the location includes an metric of the scene perception capability based on the entire area of ​​the perception map and object detection associated with the location.

[0011] Optionally, the perception map indicates the passable area of ​​the movable device in the target scene perceived by the automatic control system; the truth map indicates the passable area of ​​the movable device in the target scene determined based on the truth value annotation; and the set indicator set includes indicators associated with the passable area.

[0012] Optionally, the set indicator set is a first indicator set matching a first movement task corresponding to the target scene;

[0013] The first mobile task is a mobile task in a set of set tasks, and the set of set tasks also includes a second mobile task. A second indicator set matching the second mobile task is different from a first indicator set matching the first mobile task.

[0014] Optionally, the target scene data includes multiple frames of data, the same frame of data corresponds to the same timestamp, and different frames of data correspond to different timestamps; the perception map includes multiple perception map segments corresponding one-to-one to the multiple frames of data, and the true value map includes multiple true value map segments corresponding one-to-one to the multiple frames of data;

[0015] The comparing the perception map and the truth map based on the set indicator set to obtain a detection result representing the scene perception capability of the automatic control system for the target scene includes:

[0016] Based on the set indicator set, the perception map fragments and the true map fragments corresponding to the same frame data are compared respectively to obtain the detection result.

[0017] Optionally, in the case where the first mobile task is a first type of task, the set indicator set includes a local indicator for detecting the scene perception capability based on a local area of ​​the perception map;

[0018] In the case where the first mobile task is a second type of task, the indicator in the indicator set is a global indicator for detecting the scene perception capability based on the entire area of ​​the perception map.

[0019] Optionally, the global indicator is an indicator shared by different mobile tasks, and the comparing the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes:

[0020] Comparing the perception map and the truth map based on the global indicator to obtain a first detection result for the automatic control system;

[0021] When the first movement task is the second type of task, outputting the first detection result as the detection result;

[0022] In the case where the first movement task is a task of the first type, determining a local indicator matching the first movement task;

[0023] Comparing the perception map and the truth map based on the determined local indicator to obtain a second detection result for the automatic control system;

[0024] The first detection result and the second detection result are output as the detection result.

[0025] Optionally, the global indicator associated with the position includes a first global indicator for detecting a contour difference of a traversable area, and the detection result includes an indicator value of the automatic control system for the first global indicator; and the comparing the perception map and the true value map based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes:

[0026] A set of sampling rays is emitted from the position of the movable device in the perception map toward the periphery, and contour deviation values ​​of a first contour of the traversable area indicated by the perception map relative to a second contour of the traversable area indicated by the true map are collected through the sampling rays; wherein the contour deviation values ​​are determined based on a first intersection point of the sampling rays with the first contour and a second intersection point of the sampling rays with the second contour;

[0027] An index value of the automatic control system for the first global index is determined according to the contour deviation values ​​collected by the group of sampling rays.

[0028] Optionally, the local indicator associated with the position includes a first local indicator for detecting an obstacle boundary error, and the detection result includes an indicator value of the automatic control system for the first local indicator; and the comparing the perception map and the true value map based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes:

[0029] determining, based on the perception map, a target obstacle within a first set range of the movable device;

[0030] Based on each target obstacle, taking the real boundary of the target obstacle in the truth map as a reference, determining a set offset of the perceived boundary of the target obstacle in the perception map relative to the real boundary as an indicator value of the automatic control system for the first local indicator;

[0031] The set offset is an offset of a visible portion of the perceived boundary within the visible range of the movable device relative to the real boundary.

[0032] Optionally, the local indicator associated with the position includes a second local indicator for detecting the boundary accuracy of the target entry area in the passable area, and the detection result includes an indicator value of the automatic control system for the second local indicator; the comparison of the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes:

[0033] Based on the perception map, determining a target entry area within a second set range of the movable device;

[0034] For each target entry area, the true value map and the perception map are compared in a traversable portion in an extension area of ​​the target entry area to obtain an index value of the automatic control system for the second local index.

[0035] According to a second aspect of the present disclosure, a control method for a movable device is further provided. The control method is implemented by a first automatic control system, and the method includes:

[0036] Acquire first scene data collected by a first movable device;

[0037] Based on the first scene data, controlling the movement of the first movable device;

[0038] Among them, the first automatic control system is obtained by adjusting the parameter value of the second automatic control system, the adjustment is performed based on the detection result of the scene perception capability of the second automatic control system for at least one target scene, the detection result is obtained based on the comparison result of the perception map and the true value map for indicators in an indicator set, the indicator set includes indicators associated with the position of the movable device in the perception map, the perception map is generated by the second automatic control system based on second scene data collected by the second movable device in the target scene, and the true value map is obtained by annotating the second scene data with true values.

[0039] According to a third aspect of the present disclosure, a chip according to some embodiments is provided, which may include:

[0040] a storage unit for storing a computer program; and,

[0041] A processing unit, wherein the processing unit is configured to implement the method according to the first aspect and / or the second aspect of the present disclosure when executing the computer program stored in the storage unit.

[0042] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method described in the first aspect and / or the second aspect.

[0043] According to a fifth aspect of the present disclosure, a mobile device according to some embodiments is provided, and the mobile device may include a chip according to the third aspect of the present disclosure; or include an electronic device according to the fourth aspect of the present disclosure; or may include:

[0044] processor;

[0045] a memory for storing processor-executable instructions;

[0046] The processor is configured to implement the method according to the first aspect and / or the second aspect of the present disclosure when executing the instructions stored in the memory.

[0047] According to a sixth aspect of the present disclosure, a non-volatile computer-readable storage medium is also provided, on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor.

[0048] According to the method provided by the embodiment of the present disclosure, based on the index associated with the position of the movable device in the perception map, the perception map generated by the automatic control system based on the target scene data is compared with the true value map obtained based on the true value annotation of the target scene data, thereby obtaining a detection result reflecting the scene perception ability of the automatic control system for the target scene. Here, since the index associated with the position can obtain the perception deviation based on the position, and the position of the movable device in the scene is highly correlated with the automatic control system's completion of the mobile task in the target scene, therefore, based on such an index, the automatic control system is detected, which can achieve the focus on the object that the automatic control system needs to pay attention to in order to complete the device movement control, thereby improving the effectiveness of the detection and the system optimization based on the detection results.

[0049] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0051] Figure 1 is a schematic diagram of an intelligent network connection system to which the method provided by the embodiment of the present disclosure can be applied;

[0052] Figure 2 is based on Figure 1 A schematic diagram of a movable device provided by the illustrated embodiment;

[0053] Figure 3 is a flowchart of a method for detecting an automatic control system according to some embodiments;

[0054] Figure 4 is a schematic diagram of comparing a perception map and a truth map for a first local metric according to some examples;

[0055] Figure 5 is a schematic diagram of comparing a perception map and a truth map for a second local metric according to some examples;

[0056] Figure 6 is a schematic diagram of comparing a perception map and a truth map for a first global metric according to some examples;

[0057] Figure 7 is a schematic diagram comparing the perception map and the truth map for the second type of indicators based on some examples;

[0058] Figure 8 is a flowchart of a method for detecting an automatic control system according to other embodiments;

[0059] Fig. 9 is a flowchart of a control method of a movable device according to some embodiments;

[0060] Fig.10 is a schematic diagram of the composition structure of a chip according to some embodiments;

[0061] Fig.11 is a schematic diagram of a composition structure of an electronic device according to some embodiments;

[0062] Fig.12 It is a schematic diagram of the composition structure of the mobile device according to some embodiments. DETAILED DESCRIPTION

[0063] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0064] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0065] Technologies, methods and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods and equipment should be considered as part of the specification.

[0066] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0067] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0068] It should be noted that all data acquisition actions in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0069] The present disclosure relates to a scheme for detecting the scene perception capability of an automatic control system for a mobile device. In an embodiment of the present disclosure, the automatic control system is a system that senses the scene in which the mobile device is located based on scene data collected by sensors carried by the mobile device to determine the passable area of ​​the mobile device in the scene, and then controls the movement of the mobile device in the scene. Taking a vehicle as an example, the automatic control system for the vehicle can be referred to as an automatic driving system. The automatic control system can be deployed on a mobile device, or on a server that is communicatively connected to the mobile device, or on a mobile device and a server, without limitation here.

[0070] In the relevant technologies for detecting the scene perception ability of automatic control systems, it is mainly based on the overall precision (Precision), recall (Recall) and accuracy (Accuracy) of the automatic control system's perception results of scene data to determine whether the scene perception ability of the automatic control system meets the application requirements; among them, the precision rate is the proportion of the positive categories recognized by the system that are actually positive categories; the recall rate is the proportion of all actually positive categories that are correctly recognized as positive categories by the system; the accuracy rate is the proportion of samples correctly recognized by the system to the total samples.

[0071] The above indicators focus on reflecting the overall perception ability of the automatic control system for the scene, lack scene relevance, and cannot reflect the perception ability of the automatic control system for the objects that need to be paid attention to in order to complete the mobile control of the equipment, that is, it is impossible to accurately detect the automatic control system, which limits the performance optimization of the automatic control system, affects the perception effect of the automatic control system for the objects that need to be paid attention to, and further affects the safety of mobile control. To this end, the embodiment of the present disclosure proposes a method for detecting an automatic control system to improve the accuracy and effectiveness of the detection. Accordingly, the embodiment of the present disclosure also proposes an optimization method for optimizing the automatic control system based on the detection results of the automatic control system, and a control method for controlling the movement of a movable device based on the optimized automatic control system.

[0072] Figure 1 An intelligent network connection system 100 to which the method provided by the embodiment of the present disclosure can be applied is schematically provided. Figure 1 As shown, the intelligent network connection system 100 may include: a movable device 101, a server 102, and a user terminal 103.

[0073] In some examples, the movable device 101 may be a vehicle with an automatic driving function, a robot that can move autonomously, and the like. Among them, automatic driving is also called unmanned driving or intelligent driving. Vehicles with automatic driving functions can achieve driving tasks such as environmental perception, decision planning, and control execution. The level of automatic driving can refer to the automobile intelligence classification standard formulated by the Society of Automotive Engineers (SAE). For example, L0 is manual driving, L1 is assisted driving, L2 is partial automatic driving, L3 is conditional automatic driving, L4 is highly automatic driving, and L5 is fully automatic driving. The above classification method of automatic driving levels is only used as an example, and the embodiments of the present disclosure do not limit the classification standards and levels of automatic driving.

[0074] In some examples, the server 102 may be a single server or a distributed server cluster consisting of multiple servers, and its deployment method may include a local server and / or a cloud server. The server 102 may communicate with the mobile device 101 and / or the user terminal 103 based on a communication network, and provide various services for the mobile device 101 and / or the user terminal 103. For example, the server may receive the perception data sent by the mobile device, and provide the mobile device with services such as high-precision maps, data analysis, and decision-making planning. For another example, the server may receive query instructions or control instructions sent by the user terminal, and provide corresponding services to the user.

[0075] In some examples, the user terminal 103 may be any form of electronic device that provides services to users, such as a personal computer, a laptop, a smart tablet, a smart phone, a smart wearable device, etc. The user may interact with the mobile device or server through the human-computer interaction terminal configured by the mobile device 101, or may interact with the mobile device or server through the user terminal 103, for example, querying the status and / or parameters of the mobile device through the user terminal, or controlling the mobile device to perform set tasks and / or modify configuration parameters, etc.; wherein the user terminal 103 runs an application based on the intelligent network connection system to achieve interaction with the mobile device or server, and the application may be a local application, a web application, a small program, etc., which is not limited here.

[0076] In some examples, the above application running on the user terminal 103 can provide authentication or authorization services for the user, and the user who is successfully authenticated and granted the corresponding authority can query and / or control the removable device within the scope of the granted authority.

[0077] The mobile device 101, the server 102 and the user terminal 103 can communicate with each other through the communication link provided by the communication network 104. The communication network 104 may include one or more networks of any type, for example, the communication network 104 may include the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a public switched telephone network (PSTN), a satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC and other networks providing communication, or a combination of the above multiple networks. The communication networks between the mobile device 101 and the server 102, between the user terminal 103 and the server 102, and between the user terminal 103 and the mobile device 101 may be the same or different.

[0078] It should be noted that Figure 1 The structure of the intelligent network system 100 shown in the figure is only illustrative. The intelligent network system in the embodiment of the present disclosure is not limited to the above structure, and may include more or less devices as needed, and may also combine or split the devices. For example, the intelligent network system may not include Figure 1 The user terminal in.

[0079] The method provided in the embodiment of the present disclosure may be implemented by the mobile device 101, or by the server 102, or by the mobile device 101 and the server 102. In addition, it should be understood by those skilled in the art that the method for detecting the automatic control system and the optimization method provided in the embodiment of the present disclosure may also be implemented by other devices with data processing capabilities independent of the intelligent network system, and it is only necessary to import the scene data collected by the mobile device into the device, and this is not limited here.

[0080] Figure 2 is based on Figure 1 The embodiment shown is a schematic diagram of a mobile device 101. Figure 2 As shown, the mobile device 101 may include a perception component 1011, a computing platform 1012, an execution component 1013, etc. The perception component 1011, the computing platform 1012, and the execution component 1013 may be connected via a bus or other means.

[0081] In some examples, the perception component 1011 can be used to collect information about the movable device itself or outside, and the perception component 1011 can include a visual sensing unit and a motion sensing unit. The visual sensing unit can include one or more cameras. The motion sensing unit can include a wheel speed meter and / or an inertial measurement unit (IMU). In another example, the perception component 1011 can also include a radar, a positioning and navigation unit, etc., which are not limited here. The radar can include at least one of a laser radar, a millimeter wave radar, an ultrasonic radar, or other radars. The wheel speed meter can be of any type, such as a magnetoelectric wheel speed meter, a photoelectric wheel speed meter, a mechanical wheel speed meter, a Hall effect wheel speed meter, or a visual wheel speed meter. The positioning and navigation unit can include at least one of a GPS system, a Beidou system, or other global positioning systems.

[0082] In some examples, the computing platform 1012 may include a device with computing capabilities, which is used to process the perception information collected by the perception component 1011 to obtain control information, and send corresponding control instructions to the execution component 1013, so that the execution component 1013 performs corresponding actions, thereby realizing control of the mobile device 101. For example, the computing platform 1012 can perform positioning and mapping (Simultaneous Localization and Mapping, SLAM), path planning, behavior decision-making and other behaviors on the mobile device, thereby realizing autonomous control of the mobile device. The computing platform 1012 may include at least one processor and at least one memory, and each processor may execute instructions stored in the memory alone or together to implement the method provided in the embodiment of the present disclosure. The processor in the embodiment of the present disclosure may include at least one of a central processing unit (CPU), a graphic processing unit (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), a microcontroller unit (MCU) or other processors. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. In addition to storing instructions, the memory can also store data, such as high-precision maps, path information, location, direction, speed and other data of movable devices. The data stored in the memory can be obtained and used by the processor.

[0083] In some examples, the computing platform of the mobile device can independently perform computing tasks, or can communicate with a server to complete computing tasks. For example, the computing platform of the mobile device can cooperate with the server to complete corresponding computing tasks.

[0084] The computing platform 1012 may be set in the mobile device 101, and part or all of the computing platform 1012 may also be set in a server corresponding to the mobile device. For example, some functions of the computing platform 1012 with higher real-time requirements are set in the mobile device, and other functions with lower real-time requirements are set in the server corresponding to the mobile device.

[0085] In some examples, the execution component 1013 is used to execute corresponding actions based on the control of the computing platform 1012, so that the movable device 101 completes the moving task. The execution component 1013 may include, for example, a power component, a brake component, a transmission component, a steering component, and the like.

[0086] It should be noted that Figure 2 The structure of the mobile device 101 shown in the figure is only illustrative. The mobile device in the embodiment of the present disclosure is not limited to the above structure, and may include more or fewer components as needed, and the device may be combined or split. For example, the mobile device may not include the above computing platform. For another example, the mobile device may also include a communication component, an interface component, a multimedia component, an input component, an output component, etc.

[0087] Combine the following Figure 1 The shown system illustrates various embodiments of the present disclosure.

[0088] <First Embodiment>

[0089] Figure 3 A schematic flow chart of a method for detecting an automatic control system according to some embodiments is shown.

[0090] like Figure 3 As shown, the method of the embodiment of the present disclosure may include the following steps S310 to S330:

[0091] Step S310, obtaining a perception map of the target scene generated by the automatic control system based on the target scene data.

[0092] In this embodiment, the target scene data is collected by the mobile device in the target scene when performing a mobile task. The mobile task can be any task that can be completed by the automatic control system. The mobile task is related to the target scene. For example, a vehicle performs a parking task in a parking lot scene, and a vehicle performs a driving task or a lane change task in a road scene.

[0093] The mobile device may collect target scene data through a sensing component carried thereon. The sensing component includes at least one of a camera and a radar. Accordingly, the target scene data may include at least one of image data collected by a camera and point cloud data collected by a radar.

[0094] The target scene data is data that feeds back the content of the target scene, and can be used to determine scene element information of the target scene. The scene element information includes static element information and dynamic element information.

[0095] The target scene data may include multiple frames of data. Figure 2Taking the mobile device 101 in the example, the sensing component 1011 of the mobile device 101 can collect data at a set sampling frequency, and the same frame data corresponds to the same timestamp, and different frame data corresponds to different timestamps. The timestamp is used to mark the sampling time of the data. It can be understood that the same frame data corresponds to the same timestamp, which does not mean that the sampling time of these data is strictly aligned. In practical applications, a time window for alignment can be set, that is, data collected within a time window can be considered to correspond to the same timestamp.

[0096] In some examples, due to the limited movement of the movable device, the scene data collected by the sensing component in two samplings will not change in a way that affects the positioning accuracy, where the movement includes distance and angle. For example, in a parking lot scene, the scene elements are mainly parking spaces and pillars. If the movement of the vehicle is limited, the scene elements within the radiation range of the sensing component 1011 will not change substantially. Therefore, it is also possible to select key frame data based on the movement of the movable device 101 in the scene for processing corresponding to the method of this embodiment, without having to process each frame of data collected, to reduce the amount of data processing. For example, key frame data can be selected from the data collected by the movable device based on the setting that the movement of the movable device between two adjacent key frames should be greater than or equal to a set threshold.

[0097] The perception map may include multiple perception map segments, where the perception map segments are generated based on single-frame data, and different perception map segments are generated based on different single-frame data. The perception map may also be a spliced ​​map formed by splicing multiple perception map segments.

[0098] In this embodiment, the perception map can be a map from a bird's-eye view, which can also be called a bird's-eye view (BEV). According to the detection needs, the map can be a two-dimensional view or a three-dimensional view with height information. The bird's-eye view can present scene information in a simple way, which is conducive to the comparison between the perception map and the true value map.

[0099] The automatic control system can be provided with at least one model, and data processing, scene element detection, free space detection, etc. are performed through at least one model to generate a perception map, which will not be elaborated here.

[0100] Step S320, obtaining a true value map of the target scene based on true value annotation of the scene data.

[0101] In this embodiment, the true value of the target scene data can be produced based on a true value production method known to those skilled in the art, that is, the scene elements represented by the target scene data are labeled with true values, thereby obtaining a true value map. The true value labeling can be fully automated based on the model, or it can be manually labeled or calibrated, which is not limited here.

[0102] The truth map and the perception map have the same structural form to facilitate comparison. For example, when the perception map includes multiple perception map segments, the truth map includes multiple truth map segments. For another example, when the perception map is a spliced ​​map, the truth map is also a spliced ​​map. For another example, when the perception map is a bird's-eye view, the truth map is also a bird's-eye view, etc.

[0103] Step S330, comparing the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene.

[0104] In this embodiment, the indicator set includes at least one indicator. At least some of the indicators in the indicator set are indicators associated with the position of the movable device in the perception map. In this disclosure, the indicators associated with the position of the movable device in the perception map are referred to as first-category indicators, and the indicators unrelated to the position are referred to as second-category indicators. In some examples, in addition to the first-category indicators, the indicator set may also include second-category indicators, which are not limited here.

[0105] In this embodiment, the association with the position may be reflected in that the map area concerned by the indicator is related to the position of the movable device in the perception map.

[0106] In this embodiment, the association with the position may also be reflected in that the determination of the index value is related to the position of the movable device in the perception map. That is, the index value is determined based on an object related to the position of the movable device in the perception map.

[0107] Since the position of the movable device in the target scene is highly correlated with the completion of the mobile task by the automatic control system, the first type of indicator may also be an indicator associated with the mobile task corresponding to the target scene.

[0108] In addition to dividing indicators into the first category and the second category from the perspective of location relevance, indicators can also be divided into global indicators and local indicators from the perspective of indicator radiation range. Local indicators refer to indicators of the scene perception capability of the automatic control system based on the detection objects in the local area of ​​the perception map. Local indicators can perform fine-grained detection of the perception capability of the local area that the automatic control system needs to pay attention to when performing mobile tasks. Global indicators refer to indicators of the scene perception capability of the automatic control system based on the detection objects in the entire area of ​​the perception map. Global indicators can measure the overall perception accuracy of the automatic control system for the target environment to support the optimization of the automatic control system from the perspective of overall perception capability.

[0109] The first type of indicators in the set indicator set may be global indicators, local indicators, or both global indicators and local indicators. The second type of indicators in the set indicator set may also include at least one of local indicators and global indicators.

[0110] In some examples, the first category of indicators in the set indicator set includes local indicators, that is, the set indicator set includes local indicators associated with the location, and the local area concerned by the local indicator is the area within the set range of the movable device. For the safety of the automatic control system to complete the mobile task in the target scene, the perception ability of the automatic control system in the close range of the movable device is crucial. Therefore, through the local indicators associated with the location, the perception ability of the automatic control system in the neighboring area that needs to be paid attention to in order to complete the mobile control of the device can be determined, so as to avoid the detection results being balanced by other areas with lower correlation, and realize the refined detection of the automatic control system, which is conducive to improving the effectiveness of the detection results in optimizing the performance of the automatic control system, thereby improving the safety of the automatic control system in the mobile control of the device.

[0111] In addition, since the automatic control system determines the passable area of ​​the movable device in the scene by perceiving the scene, which is a key part of the automatic control system's ability to control the safe movement of the movable device in the scene, in some examples, the scene perception capability of the automatic control system can be detected based on the automatic control system's detection of the passable area, that is, the indicator set can include indicators associated with the passable area to achieve a focus on the detection effect of the passable area. In this regard, the perception map generated by the automatic control system based on the target scene data can indicate the passable area of ​​the movable device in the target scene perceived by the automatic control system, and the true value map can indicate the passable area of ​​the movable device in the target scene determined based on the true value annotation. In this way, by comparing the perception map and the true value map, the indicator value of the indicator associated with the passable area can be determined, and then from the perspective of determining the passable area, the scene perception capability of the automatic control system can be detected.

[0112] In this example, it is set that the indicators associated with the passable area in the indicator set can have an intersection with the first category of indicators, that is, an indicator in the indicator set can be either a first category indicator or an indicator associated with the passable area. For example, the indicators in the indicator set can all be indicators associated with the passable area, and this is not limited here.

[0113] For the detection of the passable area, since the accuracy of the detection of the passable area depends on the accuracy of the obstacle boundary detection, in some examples, the first type of indicators may include a first local indicator for detecting the obstacle boundary error, and the first local indicator is also an indicator associated with the passable area, so as to determine the detection capability of the automatic control system for the obstacle boundary and the passable area through the first type of indicators. In this example, the detection result includes the indicator value of the automatic control system for the first local indicator.

[0114] In this example, step S330 compares the perception map and the truth map based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene, which may include the following steps: based on the perception map, determining the target obstacles within a first set range of the movable device; and, based on each target obstacle, taking the real boundary of the target obstacle in the truth map as a reference, determining a set offset of the perceived boundary of the target obstacle in the perception map relative to the real boundary as the indicator value of the automatic control system for the first local indicator.

[0115] In this example, the first set range can be represented by a distance relative to the movable device, or by a square area of ​​a certain size with the movable device as the geometric center, etc., where the distance or the size of the square area can be set according to the target scene or mobile task, and is not limited here.

[0116] In this example, the target obstacles may be all obstacles within the first set range, or obstacles of a set type based on the target scene or mobile task setting, that is, for different target scenes or mobile tasks, the obstacle types used as the detection object of the first local indicator may be the same or different. For example, the target scene is a parking lot, the mobile task is a parking task, and the target obstacles are other vehicles, pillars, etc. within the first set range. For another example, the target scene is a road scene, the moving person is a lane change task, and the target obstacles are other vehicles, pedestrians, etc. within the first set range.

[0117] In this example, the set offset may include at least one of an average offset, a maximum offset, a minimum offset, an offset along a set direction, and the like.

[0118] Furthermore, the set direction can be determined based on the visible range of the movable device in the perception map, that is, the set offset can be the offset of the visible part of the perception boundary within the visible range of the movable device relative to the real boundary. Here, since the visible part of the perception boundary is the part that affects the movement of the movable device, the set offset can only take the offset of the visible part, for example, the set offset is the maximum offset, average offset or offset in the set direction of the visible part. This can not only improve the effectiveness of the indicator for detecting the execution ability of the automatic control system for the mobile task, but also reduce the amount of data processing and improve the detection efficiency.

[0119] Figure 4 A portion of a perception map for a parking task is schematically shown. The perception map is generated by an automatic control system based on scene data collected by vehicle X1. Other vehicles X2 in the perception map are target obstacles located within a first set range of vehicle X1. When determining the set offset of the perception boundary W2 of vehicle X2 in the perception map relative to the real boundary W2′ of vehicle X2 in the truth map, rays can be emitted with the geometric center O of the real boundary W2′ as the emission point. The length of the line segment between each ray and the two intersection points of the perception boundary W2 and the real boundary W2′ is the offset of the perception boundary W2 along the ray direction. The set offset may include the offset of the perception boundary W2 along at least one ray direction, and the set offset may also be calculated from the offsets of the perception boundary W2 along multiple ray directions, which is not limited here.

[0120] like Figure 4 As shown, when determining the set offset, for example, the geometric center O of the real boundary W2′ can be used as the emission point to emit four rays d1, d2, d3, and d4 shown in dotted lines along the width direction and the length direction of the vehicle X2. The offsets corresponding to the four rays are L1, L2, L3, and L4, respectively. The offset of the perception boundary W2 along the direction of the ray d1 belongs to the offset within the visible range of the vehicle X1, that is, the intersection of the ray d1 and the perception boundary W2 belongs to the visible part of the perception boundary W2, while the offsets along the directions of the rays d2 and d3 are blocked by the vehicle X2, and the offset along the direction of the ray d4 is blocked by the pillar W1. Therefore, in Figure 4 In the example, the index value of the first local index can be taken as the offset L1 in the direction of the ray d1.

[0121] Of course, those skilled in the art will understand that Figure 4 In the example, more rays can be emitted with the geometric center O as the emission point. If the intersection points of multiple rays with the perception boundary W2 all belong to the visible part of the perception boundary, the average or maximum value of the offsets corresponding to these rays can be calculated as the set offset, which is not limited here.

[0122] In addition, the passable area is used by the automatic control system to determine the target entry area for the mobile task, and the extended area of ​​the target entry area is the area that the automatic control system must pass through to control the movable device to move from other areas to the target entry area. Therefore, the automatic control system's perception of the passable part of the extended area outside the target entry area is also crucial for safe driving. In this regard, in some examples, the first type of indicator may include a second local indicator for detecting the boundary accuracy of the target entry area in the passable area, and accordingly, the detection result includes the indicator value of the automatic control system for the second local indicator.

[0123] In this example, step S330 compares the perception map and the truth map based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene, which may include the following steps: based on the perception map, determining a target entry area within a second set range of the movable device; and, for each target entry area, comparing the truth map with the perception map for a passable portion in an extended area of ​​the target entry area to obtain an indicator value of the automatic control system for the second local indicator.

[0124] In this example, the second set range can be represented by a distance relative to the movable device, or by a square area of ​​a certain size with the movable device as the geometric center, etc., where the distance or the size of the square area can be set according to the target scene or mobile task, and is not limited here.

[0125] In this example, the target entry area is related to the target scene or mobile task. For example, when performing a parking task in a parking lot, the target entry area is an empty parking space. For another example, when performing a lane change task on the road, the target entry area is an empty space in the adjacent lane.

[0126] For each target entry area, an extended area of ​​the target entry area is determined in the perception map, and the extended area can be obtained by offsetting the boundary of at least one side of the target entry area outward by a set distance.

[0127] Figure 5 A portion of a perception map for a parking task is schematically shown, where the perception map is generated by the automatic control system based on scene data collected by vehicle X1. Figure 5 The perception map in indicates that there is an empty parking space C1 in front of the left side of the vehicle X1, and the empty parking space C1 is the target entry area. When determining the index value of the automatic control system for the second local index, the left and right boundaries of the empty parking space C1 can be offset outward by a set distance, for example, by 30 cm-50 cm, to obtain the extension area F1 of the empty parking space C1.

[0128] In this example, the intersection over union (IoU) of the passable parts in the perception map and the truth map of each extended area can be calculated, and the average or maximum value of the IoU of the extended areas of all target entry areas is used as the index value of the second local index. It should be clear to those skilled in the art that here, the index value of the second local index can also be obtained by calculating the precision, recall rate or accuracy of the perception of the passable part in the extended area, which is not limited here.

[0129] Still Figure 5 For example, for the extended area F1, assuming that the passable part of the extended area F1 in the perception map is the first area A, and the passable part of the extended area F1 in the true value map is the second area B, then the intersection-union ratio of the extended area F1 can be expressed as: the area of ​​the intersection of the first area A and the second area B divided by the area of ​​the union of the first area A and the second area B.

[0130] In some examples, with respect to the first type of indicators, a first global indicator may also be set to detect the overall contour difference of the traversable area, so as to conduct targeted detection of the perception accuracy of the automatic control system for the part that affects the mobile decision. In this example, the detection result includes the indicator value of the automatic control system for the first global indicator. In this example, step S330 compares the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene, which may include the following steps: emitting a set of sampling rays from the position of the movable device in the perception map to the periphery, and collecting the contour deviation value of the first contour of the traversable area indicated by the perception map relative to the second contour of the traversable area indicated by the true value map through the sampling rays; and, according to the contour deviation value collected by a set of sampling rays, determining the indicator value of the automatic control system for the first global indicator.

[0131] In this example, the contour deviation value between the first contour and the second contour can be determined based on the first intersection point of the sampling ray with the first contour and the second intersection point of the sampling ray with the second contour. The contour deviation value can be determined based on the length of the line segment between the first intersection point and the second intersection point of the same sampling ray, or based on the position coordinates of multiple first intersection points and the position coordinates of multiple second intersection points collected by a group of sampling rays.

[0132] When determining the contour deviation value between the first contour and the second contour based on the position coordinates of multiple first intersections and the position coordinates of multiple second intersections, the minimum matching distance between the multiple first intersections and the multiple second intersections can be calculated. For example, the first intersection is matched with the multiple second intersections respectively to obtain the distance between the first intersection and each second intersection, and the minimum matching distance is used as the contour deviation value based on the first intersection, thereby obtaining multiple contour deviation values ​​based on the multiple first intersections.

[0133] In this example, see Figure 6 , a set of sampling rays can be emitted in four directions: forward, backward, left, and right, with vehicle X1 as the emission point. Figure 6 Some sampling rays are schematically shown, and the density of the sampling rays can be set as needed. Here, a launch point can be selected on the vehicle to launch the sampling ray, for example, the geometric center of the vehicle is used as the launch point, or multiple launch points can be selected on the vehicle to launch the sampling ray, for example, multiple launch points are set on the contour line of the vehicle to launch the sampling ray, etc., which is not limited here.

[0134] In this example, in order to improve the accuracy of sampling, valid samples can be selected by setting a sampling threshold. For example, samples with contour deviation values ​​within the sampling threshold range are set as valid samples, and the index values ​​of the first entire index are determined based on the valid samples. Samples with contour deviation values ​​exceeding the sampling threshold are considered to be abnormal samples and are discarded.

[0135] In addition, in some examples, at least one global indicator as a second type of indicator may be set to examine the overall detection effect of the automatic control system on the traversable area. These global indicators may include at least one indicator of intersection over union (IoU), precision, recall, and accuracy for traversable area detection. This can be done by comparing the traversable area in the perception map with the traversable area in the true value map to determine the indicator values ​​of intersection over union (IoU), precision, recall, and accuracy.

[0136] In order to facilitate the calculation of the index values ​​of the above indicators, the perception map and the true value map can be gridded, that is, the map is divided into multiple grids of a set size, one grid represents a pixel in the map, and the grid is used as the smallest unit for indicator calculation, which is conducive to improving detection efficiency.

[0137] See also Figure 7, taking the global index as the second type of index as an example, we can count the first pixel TN that is inaccessible in both the true map GT and the perception map PE, the second pixel TP that is accessible in both the true map and the perception map, the third pixel FP that is inaccessible in the true map but accessible in the perception map, and the fourth pixel FN that is accessible in the true map but inaccessible in the perception map. Based on the above statistics, we can easily calculate the index values ​​of intersection-over-union, precision, recall and accuracy.

[0138] Regarding the map comparison in step S330, in the example where the perception map includes multiple perception map segments and the truth map includes multiple truth map segments, the perception map segments and the truth map segments corresponding to the same frame data can be compared based on the set indicator set to obtain the detection result. That is, between the multiple perception map segments and the multiple truth map segments, based on the corresponding data frames, multiple map segment pairs are formed, and in step S330, each map segment pair is compared to obtain the detection result.

[0139] In such an example, the detection result may include a single-frame detection result of each indicator for each map segment pair, and / or an average value of each indicator based on multiple single-frame detection results. The multidimensionality of the detection result is conducive to problem location, so as to optimize the automatic control system in a targeted manner to meet the use requirements of different scenarios or specific scenarios.

[0140] According to step S310 to step S330, the method of this embodiment compares the perception map with the true map based on at least the index associated with the position of the movable device in the perception map to detect the scene perception capability of the automatic control system. Here, since the index associated with the position can obtain the perception deviation based on the position, the method of this embodiment can determine the safety of the mobile control performed by the automatic control system in the target scene to complete the mobile task, thereby improving the effectiveness of the detection and further system optimization.

[0141] <Second Embodiment>

[0142] In the second embodiment, the scene perception capability of the automatic control system can be specifically detected by distinguishing movement tasks, so as to improve the perception capability of the automatic control system for various scenes through the detection results of different movement tasks.

[0143] In this embodiment, the target scene corresponds to the first mobile task in the set task set, for example, the target scene is a parking lot, the first mobile task is a parking task, and the set task set also includes a second mobile task, the second mobile task is, for example, a lane change task or a driving task in a lane, etc. In this embodiment, the set indicator set is a first indicator set that matches the first mobile task, and the first indicator set that matches the second mobile task is different from the second indicator set that matches the first mobile task.

[0144] In this embodiment, different indicator sets may include different indicator types. For example, the first indicator set includes global indicators and local indicators, while the second indicator set only includes global indicators. For another example, both the first indicator set and the second indicator set include global indicators and local indicators, but the two have different types of local indicators.

[0145] In this embodiment, different indicator sets may also include: the indicator types are the same, but the indicators target different objects. For example, the first indicator set and the second indicator set both include the first local indicator, but the target obstacles targeted by the first local indicator in the first indicator set include vehicles and pillars, while the target obstacles targeted by the first local indicator in the second indicator set include vehicles and pedestrians, etc.

[0146] In some examples, for driving tasks that have no special requirements for the perception accuracy of the neighboring area, detection can be performed only through global indicators to improve the detection efficiency of the automatic control system. That is, the set task set can have mobile tasks that only match global indicators, such as driving tasks within the lane. In this example, the mobile tasks in the set task set can be divided into two categories from the perspective of whether the indicator set matched by the mobile task includes local indicators. The indicator set matched by the first category of tasks at least includes local indicators, while the indicator set matched by the second category of tasks only has global indicators.

[0147] Since the global indicator is used to detect the overall perception effect of the automatic control system, it can adapt to all mobile tasks. Therefore, in some examples, different mobile tasks in the set of tasks can share the global indicator. That is to say, the difference in the indicator set is mainly reflected in the setting of local indicators. By setting matching local indicators for mobile tasks, targeted detection can be performed on the objects that the automatic control system should pay attention to when performing corresponding mobile tasks.

[0148] In such an example, Figure 8 As shown, the method for detecting the automatic control system may include the following steps:

[0149] Step S810, obtaining a perception map of a target scene generated by an automatic control system based on target scene data; wherein the target scene data is collected from the target scene by a movable device.

[0150] Step S820, obtaining a true value map of the target scene based on true value annotation of the target scene data.

[0151] Step S8301, comparing the perception map and the true value map based on the global index to obtain a first detection result for the automatic control system.

[0152] Step S8302, determine whether the first moving task is a first-category task, if not, it means the first moving task is a second-category task, and execute step S8303, if yes, execute step S8304.

[0153] Step S8303: output the first detection result as the final detection result.

[0154] Step S8304: determine a local indicator that matches the first movement task, and compare the perception map and the true map based on the determined local indicator to obtain a second detection result for the automatic control system.

[0155] Step S8305: output the first detection result and the second detection result as the final detection result.

[0156] In this example, step S8301 is decoupled from step S8302 so that step S8301 and step S8302 can be executed synchronously, which is beneficial to improving detection efficiency.

[0157] <Third Embodiment>

[0158] This embodiment provides an optimization method for an automatic control system, which may include the following steps:

[0159] Step S310, obtaining a perception map of a target scene generated by the automatic control system based on target scene data; wherein the target scene data is collected in the target scene by a movable device.

[0160] Step S320, obtaining a true value map of the target scene based on true value annotation of the target scene data.

[0161] Step S330, comparing the perception map and the true map based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene; wherein the indicator set includes an indicator associated with the position of the movable device in the perception map.

[0162] Step S340, optimizing the automatic control system based on the detection result to obtain an optimized automatic control system.

[0163] The optimization in this embodiment may be an adjustment of any part of the automatic control system. The optimization includes adjusting the parameter value of the automatic control system. The optimization may also include adjusting the system structure of the automatic control system, such as adjusting the model composition of the automatic control system, or adjusting the network structure of at least one model in the automatic control system, etc., which is not limited here.

[0164] In this embodiment, since the detection results can reflect the deficiencies of the automatic control system in scene perception, the automatic control system can be optimized to overcome such deficiencies based on the detection results, thereby improving the performance of the automatic control system in a targeted manner, especially by combining the index values ​​of location-related indicators to improve the safety of its execution of mobile tasks.

[0165] <Fourth Embodiment>

[0166] This embodiment provides a control method for a movable device, which is implemented by a first automatic control system configured for a first movable device, such as Fig. 9 As shown, the method may include the following steps S910 and S920:

[0167] Step S910: Acquire first scene data collected by a first movable device.

[0168] The first movable device can collect the first scene data through at least one sensor carried thereon, which will not be elaborated here.

[0169] Step S920: Control the movement of the first movable device based on the first scene data.

[0170] In this embodiment, the first automatic control system can determine the passable area in the corresponding scene based on the first scene data, and then plan the moving path based on the determined passable area and the moving task, and control the movement of the first movable device according to the moving path to complete the moving task.

[0171] In this embodiment, the first automatic control system is obtained by adjusting the parameter value or system structure of the second automatic control system, that is, the first automatic control system is obtained by optimizing the second automatic control system. The parameter value here can be a model parameter value of the automatic control system. The system structure can include the network structure and / or model composition of the model, etc., which are not limited here.

[0172] The above adjustment is performed based on the detection result of the scene perception capability of the second automatic control system for at least one target scene, and the detection result is obtained based on the comparison result of the perception map and the true value map for an indicator set, and the indicator set includes indicators associated with the position of the movable device in the perception map. The perception map is generated by the second automatic control system based on the second scene data collected by the second movable device in the target scene, and the true value map is obtained by marking the second scene data with true values.

[0173] In this embodiment, the first automatic control system may be a universal automatic control system obtained through multi-scenario detection optimization.

[0174] In this embodiment, the first automatic control system can also be an automatic control system dedicated to some scenarios. That is to say, at least two automatic control systems can be configured for the movable device. The movable device can call the automatic control system adapted to the current scenario to perform mobile tasks, so that the movable device has excellent mobility in different scenarios. In order to achieve lightweight automatic control systems, these automatic control systems can share at least part of the model and part of the parameter values. During optimization, only specific parts of the system need to be adjusted for different scenarios to improve optimization efficiency.

[0175] In this embodiment, the first removable device and the second removable device may be the same removable device or different removable devices, which is not limited here.

[0176] The system optimization of this embodiment can be performed offline or online, which is not limited here.

[0177] <Fifth Embodiment>

[0178] This embodiment provides a chip capable of implementing the method of the embodiment of the present disclosure, such as Fig.10 As shown, the chip 1000 includes a storage unit 1020 and a processing unit 1010. The storage unit 1020 is used to store a computer program. The processing unit 1010 is configured to implement a method according to any embodiment of the present disclosure when executing the computer program stored in the storage unit.

[0179] Chip 1000 may be a processor chip having data processing capabilities.

[0180] Chip 1000 may be a processor chip used in an automated driving control unit (ADCU), etc.

[0181] The chip 1000 may be a system on a chip (SOC), which integrates multiple processors, multiple memories, I / O interfaces, etc. to achieve a miniaturized design of the controller.

[0182] <Sixth Embodiment>

[0183] This embodiment provides an electronic device, such as Fig.11 As shown, the electronic device 1100 includes a memory 1102 and a processor 1101, the memory 1102 is used to store a computer program run by the processor 1101, and the processor 1101 is configured to implement a method according to any embodiment of the present disclosure when executing the computer program stored in the memory 1102.

[0184] The electronic device may be a controller of a movable device, such as an intelligent driving domain controller of a vehicle, or a central controller of a vehicle, etc.

[0185] The electronic device may also be a server, etc., which is not limited here.

[0186] <Seventh Embodiment>

[0187] This embodiment provides a movable device. The movable device may include the chip 1000 according to the fifth embodiment or the electronic device 1100 according to the sixth embodiment. In this case, the electronic device 1100 may be a controller of the movable device.

[0188] In some embodiments, Fig.12 As shown, the removable device 1200 may also include a memory 1202 and a processor 1201, wherein the memory 1202 is used to store a computer program run by the processor 1201, and the processor 1201 is configured to implement a method according to any embodiment of the present disclosure when executing the computer program stored in the memory 1202.

[0189] The movable device 1200 is, for example, a vehicle with intelligent driving function, or an intelligent robot of any form, etc., which is not limited here.

[0190] The embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any method in the aforementioned embodiments of the present disclosure is implemented. Optionally, the computer-readable storage medium may be a non-transitory storage medium, but is not limited thereto, and may also be a transient storage medium.

[0191] The embodiments of the present disclosure further provide a computer program product, which may include a computer program. When the computer program is executed by a processor, any method in the aforementioned embodiments of the present disclosure can be implemented.

[0192] The above embodiments focus on explaining the differences from other embodiments, and the same or similar parts between different embodiments can be referenced to each other.

[0193] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement any method in the foregoing embodiments of the present disclosure.

[0194] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0195] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0196] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, which may include object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0197] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0198] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so as to produce a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device for implementing the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions make the computer, programmable data processing device, and / or other equipment work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0199] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0200] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and the module, a program segment or a part of an instruction contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions. It should be noted that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0201] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for detecting an automatic control system, characterized in that: include: Acquire a perception map of a target scene generated by an automatic control system based on target scene data; wherein the target scene data is collected by a movable device in the target scene; Acquire a true value map of the target scene based on true value annotation of the target scene data; The perception map and the true map are compared based on a set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene; wherein the set indicator set includes an indicator associated with the position of the movable device in the perception map.

2. The method according to claim 1, characterized in that The set indicator set includes at least one indicator of a local indicator associated with the location and a global indicator associated with the location; wherein, The local indicator associated with the position includes: an indicator of the scene perception capability detected based on a local area of ​​the perception map, the local area being an area determined based on the position of the movable device in the perception map; The global metric associated with the location includes an metric of the scene perception capability based on the entire area of ​​the perception map and object detection associated with the location.

3. The method according to claim 1, characterized in that The perception map indicates the passable area of ​​the movable device in the target scene perceived by the automatic control system; the truth map indicates the passable area of ​​the movable device in the target scene determined based on the truth value annotation; the set indicator set includes indicators associated with the passable area.

4. The method according to claim 1, characterized in that The set indicator set is a first indicator set that matches the first movement task corresponding to the target scene; The first mobile task is a mobile task in a set of set tasks, and the set of set tasks also includes a second mobile task. A second indicator set matching the second mobile task is different from a first indicator set matching the first mobile task.

5. The method according to claim 1, characterized in that The target scene data includes multiple frames of data, the same frame of data corresponds to the same timestamp, and different frames of data correspond to different timestamps; the perception map includes multiple perception map segments corresponding to the multiple frames of data one by one, and the true value map includes multiple true value map segments corresponding to the multiple frames of data one by one; The comparing the perception map and the truth map based on the set indicator set to obtain a detection result representing the scene perception capability of the automatic control system for the target scene includes: Based on the set indicator set, the perception map fragments and the true map fragments corresponding to the same frame data are compared respectively to obtain the detection result.

6. The method according to claim 4, characterized in that In the case where the first mobile task is a first type of task, the set indicator set includes a local indicator for detecting the scene perception capability based on a local area of ​​the perception map; In the case where the first mobile task is a second type of task, the indicator in the indicator set is a global indicator for detecting the scene perception capability based on the entire area of ​​the perception map.

7. The method according to claim 6, characterized in that The global indicator is an indicator shared by different mobile tasks. The comparison of the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes: Comparing the perception map and the truth map based on the global indicator to obtain a first detection result for the automatic control system; When the first movement task is the second type of task, outputting the first detection result as the detection result; In the case where the first movement task is a task of the first type, determining a local indicator matching the first movement task; Comparing the perception map and the truth map based on the determined local indicator to obtain a second detection result for the automatic control system; The first detection result and the second detection result are output as the detection result.

8. The method according to claim 2, characterized in that: The global indicator associated with the position includes a first global indicator for detecting a contour difference of a traversable area, and the detection result includes an indicator value of the automatic control system for the first global indicator; the comparison of the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes: A set of sampling rays is emitted from the position of the movable device in the perception map toward the periphery, and the sampling rays are used to collect: a contour deviation value of a first contour of the traversable area indicated by the perception map relative to a second contour of the traversable area indicated by the true map; wherein the contour deviation value is determined based on a first intersection point of the sampling ray with the first contour, and a second intersection point of the sampling ray with the second contour; An index value of the automatic control system for the first global index is determined according to the contour deviation values ​​collected by the group of sampling rays.

9. The method according to claim 2, characterized in that: The local indicator associated with the position includes a first local indicator for detecting an obstacle boundary error, and the detection result includes an indicator value of the automatic control system for the first local indicator; the comparison of the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception capability of the automatic control system for the target scene includes: determining, based on the perception map, a target obstacle within a first set range of the movable device; Based on each target obstacle, taking the real boundary of the target obstacle in the truth map as a reference, determining a set offset of the perceived boundary of the target obstacle in the perception map relative to the real boundary as an indicator value of the automatic control system for the first local indicator; The set offset is an offset of a visible portion of the perceived boundary within the visible range of the movable device relative to the real boundary.

10. The method according to claim 2, characterized in that The local indicator associated with the position includes a second local indicator for detecting the boundary accuracy of the target entry area in the passable area, and the detection result includes an indicator value of the automatic control system for the second local indicator; the comparison of the perception map and the true value map based on the set indicator set to obtain a detection result reflecting the scene perception ability of the automatic control system for the target scene includes: Based on the perception map, determining a target entry area within a second set range of the movable device; For each target entry area, the true value map and the perception map are compared in a traversable portion in an extension area of ​​the target entry area to obtain an index value of the automatic control system for the second local index.

11. A control method for a movable device, the control method being implemented by a first automatic control system, characterized in that: The method comprises: Acquire first scene data collected by a first movable device; Based on the first scene data, controlling the movement of the first movable device; Among them, the first automatic control system is obtained by adjusting the parameter value of the second automatic control system, the adjustment is performed based on the detection result of the scene perception capability of the second automatic control system for at least one target scene, the detection result is obtained based on the comparison result of the perception map and the true value map for indicators in an indicator set, the indicator set includes indicators associated with the position of the movable device in the perception map, the perception map is generated by the second automatic control system based on second scene data collected by the second movable device in the target scene, and the true value map is obtained by annotating the second scene data with true values.

12. A chip, characterized in that: The chip comprises: the chip comprises a processing unit, and the processing unit is used to execute the method as claimed in any one of claims 1 to 11.

13. An electronic device, characterized in that: The system comprises a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method according to any one of claims 1 to 11.

14. A movable device, characterized in that: comprising the chip according to claim 12, or the electronic device according to claim 13; or, The removable device comprises: a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method according to any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that: A computer program is stored thereon, which implements the method according to any one of claims 1 to 11 when executed by a processor.

Images