Automatic driving operation processing method and device, equipment and storage medium

Abstract

The invention discloses an automatic driving operation processing method and device, equipment and a storage medium. The method comprises the steps that coordinate information of a target at a current timestamp is obtained, two or more continuous driving operations about to be executed for the target and a reference coordinate system corresponding to each driving operation can be roughly determined based on the current coordinate information, and the reference coordinate system is a map coordinate system, an odometer coordinate system or a projection coordinate system; and calculating a conversion matrix between different reference coordinate systems according to an association relationship between driving operations, performing coordinate system conversion on the obtained coordinate information based on the calculated conversion matrix, and executing corresponding driving operation processing based on a conversion result. Therefore, it is guaranteed that the obtained positioning information is real and accurate, the problem of positioning distortion is avoided, abnormal driving behaviors such as sudden braking, dragon drawing and re-planning are reduced, and the driving safety of the automatic driving vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, specifically to technical fields such as intelligent transportation and autonomous driving, and in particular to an autonomous driving operation processing method, device, equipment and storage medium. Background Art

[0002] In autonomous driving, "relative position information" is widely used as input for positioning, perception, prediction, decision-making, planning and other driving operations. Generally, autonomous driving expects to use a global map (such as a high-precision map collected in advance). In scenes such as tunnels, global positioning information cannot be accurately obtained. In this case, it is expected to use a local map (such as lane lines and road boundaries perceived online). The autonomous driving system in the map coordinate system cannot switch between the global map and the local map without feeling. In addition, in order to control costs, the global map of the autonomous driving system Figure 1 It is usually a 2D map, that is, it does not contain elevation information.

[0003] Most current L4 autonomous driving solutions calculate "relative position" in the map coordinate system. When global positioning information is distorted due to the inability to switch between the global map and the local map based on the map coordinate system (such as when positioning drift occurs in tunnels, long corridors, or other reasons), the relative position information calculated by the map coordinate system will also be distorted, causing abnormal autonomous driving behavior. For example, Figure 1 In the scenario shown, the obstacle's speed is incorrectly predicted, leading to the ego vehicle (autonomous vehicle) incorrectly braking or maneuvering. There is a stationary obstacle to the right of the ego vehicle's forward direction. Due to positioning information deviation, the ego vehicle's position at the subsequent timestamp is offset to the left. As a result, the obstacle's relative position between the previous and next timestamps is calculated to be moving to the left, causing the stationary obstacle to be mistakenly identified as a dynamic obstacle, resulting in abnormal driving behavior.

[0004] Therefore, it is urgent to find a new way to handle driving operations to solve the abnormal driving behaviors such as sudden braking, dragon drawing, large control errors, and frequent re-planning caused by the above problems. Summary of the Invention

[0005] The present application provides an autonomous driving operation processing method, device, equipment and storage medium to solve the problem of abnormal driving behaviors such as sudden braking and dragon drawing caused by inaccurate positioning information and relative position information.

[0006] The technical solution is as follows:

[0007] In a first aspect, a method for processing an autonomous driving operation is provided, comprising:

[0008] Obtaining coordinate information of a target in the autonomous driving scene at a current timestamp; wherein the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements;

[0009] Determining at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation, wherein the driving operations are divided into a first type of driving operation and a second type of driving operation according to type, and the at least two driving operations include at least the second type of driving operation, the reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometer coordinate system or a projected coordinate system related to the odometer coordinate system, and the projected coordinate system satisfies: a horizontal plane of the projected coordinate system is parallel to a horizontal plane of the map coordinate system, and a parameter of each coordinate axis changes continuously with the odometer coordinate system;

[0010] Based on the correlation between driving operations, the transformation matrix between different reference coordinate systems is calculated;

[0011] The coordinate information is converted into a coordinate system based on the conversion matrix, and corresponding autonomous driving operation processing is performed based on the conversion result.

[0012] In a possible implementation, obtaining image semantic feature information of the area to be detected includes:

[0013] When the autonomous driving vehicle enters the second type of scene from the first type of scene, switching the map information referenced for obtaining coordinate information and / or performing driving operations from global map information to local map information;

[0014] When the autonomous driving vehicle enters the first type of scene from the second type of scene, the map information referenced for obtaining coordinate information and / or performing driving operations is switched from local map information to global map information;

[0015] Among them, the first type of scene is the scene that can be covered by high-precision maps, and the second type of scene is the local scene that is prone to cause distortion of location information.

[0016] In one possible implementation, the first type of driving operation includes at least: routing operations;

[0017] The second type of driving operation includes at least: perception operation, positioning operation, prediction operation, decision operation, planning operation and control operation;

[0018] Among them, the reference coordinate systems corresponding to the perception operation and positioning operation are both odometer coordinate systems, and the reference coordinate systems corresponding to the prediction operation, decision operation, planning operation and control operation are all projected coordinate systems.

[0019] In one possible implementation, based on the correlation between driving operations, the transformation matrix between different reference coordinate systems is calculated, including:

[0020] determining any two driving operations having a direct transmission relationship based on information transmission directions between the plurality of driving operations;

[0021] When it is determined that the reference coordinate systems corresponding to the two driving operations are different, a conversion matrix between the two different reference coordinate systems at the current timestamp is determined according to the positioning output result.

[0022] In one possible implementation,

[0023] The projected coordinate system is the odometry horizontal projected coordinate system; then:

[0024] The conversion matrix from the odometry horizontal projection coordinate system to the map coordinate system is: the projection matrix from the vehicle coordinate system to the map coordinate system × the inverse matrix of the projection matrix from the vehicle coordinate system to the odometry coordinate system;

[0025] The conversion matrix from the map coordinate system to the odometry horizontal projection coordinate system is: the inverse matrix of the conversion matrix from the odometry horizontal projection coordinate system to the map coordinate system;

[0026] The conversion matrix from the odometer coordinate system to the odometer horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometer horizontal projection coordinate system × the conversion matrix from the odometer coordinate system to the map coordinate system;

[0027] The conversion matrix from the odometry horizontal projection coordinate system to the odometry coordinate system is: the inverse matrix of the conversion matrix from the odometry coordinate system to the odometry horizontal projection coordinate system;

[0028] The conversion matrix from the vehicle coordinate system to the odometry horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometry horizontal projection coordinate system × the conversion matrix from the vehicle coordinate system to the map coordinate system;

[0029] The conversion matrix from the odometer horizontal projection coordinate system to the vehicle body coordinate system is: the inverse matrix of the conversion matrix from the vehicle body coordinate system to the odometer horizontal projection coordinate system;

[0030] The projection matrix is: the coordinates of the two axes corresponding to the horizontal plane of the corresponding transformation matrix and the axis corresponding to the heading angle are retained, and the coordinates of the axis vertical to the horizontal plane and the axis corresponding to the pitch angle and roll angle are set to zero.

[0031] In a second aspect, an autonomous driving operation processing device is provided, comprising:

[0032] An acquisition module, configured to acquire coordinate information of a target in the autonomous driving scene at a current timestamp; wherein the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements;

[0033] a determination module, configured to determine at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation, wherein the driving operations are divided into a first type of driving operation and a second type of driving operation according to type, the at least two driving operations include at least the second type of driving operation, the reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometer coordinate system or a projected coordinate system related to the odometer coordinate system, wherein the projected coordinate system satisfies: a horizontal plane thereof is parallel to a horizontal plane of the map coordinate system, and a parameter of each coordinate axis varies continuously with the odometer coordinate system;

[0034] A calculation module, used for calculating the transformation matrix between different reference coordinate systems based on the correlation relationship between driving operations;

[0035] A conversion module is used to perform coordinate system conversion on the coordinate information based on the conversion matrix, and perform corresponding autonomous driving operation processing based on the conversion result.

[0036] In a third aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method of the above-mentioned aspect and any possible implementation manner.

[0037] In a fourth aspect, an electronic device is provided, including:

[0038] at least one processor; and

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0041] In a fifth aspect, an autonomous driving vehicle is provided, comprising the electronic device as described above.

[0042] The beneficial effects of the technical solution provided by this application include at least:

[0043] It can be seen from the above technical solution that in order to adapt to the changes in driving scenes and select appropriate map information to determine the relative position, the embodiment of the present application uses the odometer coordinate system and the projection coordinate system to replace the map coordinate system to assist the autonomous driving vehicle in accurately performing the corresponding driving operations. Specifically, the coordinate information of the target at the current timestamp can be obtained first, and then based on the current coordinate information, two or more consecutive driving operations to be performed on the target can be roughly determined, as well as the reference coordinate system corresponding to each driving operation. The reference coordinate system here is a map coordinate system, an odometer coordinate system or a projection coordinate system. Afterwards, based on the correlation between the driving operations, the conversion matrix between different reference coordinate systems is calculated. Finally, the obtained coordinate information can be converted to a coordinate system based on the calculated conversion matrix, and the corresponding driving operation processing can be performed based on the conversion result. Since the coordinate information is based on the odometry coordinate system or the projection coordinate system throughout the entire processing process, it is possible to quickly and flexibly switch between global map information and local map information when encountering scene switching scenarios, thereby ensuring that the acquired positioning information is true and accurate, avoiding the problem of positioning distortion caused by the inability of the map coordinate system to flexibly and accurately switch map types, reducing the occurrence of abnormal driving behaviors such as sudden braking, drawing dragons, and re-planning, and improving the driving safety of autonomous vehicles; at the same time, it also improves the applicability of autonomous driving scenarios and reduces the rate of manual takeover.

[0044] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0046] Figure 1 This is a schematic diagram of the position of an obstacle relative to an autonomous driving vehicle, showing two timestamps in the prior art provided by an embodiment of the present application.

[0047] Figure 2 This is a schematic diagram of the steps of a driving operation processing method proposed in an embodiment of the present application.

[0048] Figure 3 It is a specific flow chart of the driving operation processing solution provided by this application.

[0049] Figure 4 This is a schematic diagram of an autonomous driving vehicle passing through a tunnel provided in an embodiment of the present application.

[0050] Figure 5 It is a structural diagram of a driving operation processing device proposed in an embodiment of the present application.

[0051] Figure 6 Schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0053] Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] It should be noted that the terminal devices involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0055] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0056] It should be noted that the following content of this application will involve terms related to autonomous driving and driving operations. For ease of understanding, the relevant terms are explained as follows.

[0057] Manual takeover rate: the number of manual takeovers corresponding to a fixed mileage;

[0058] Host vehicle: The autonomous vehicle, which can also be defined as the ego vehicle relative to other autonomous vehicles;

[0059] Odom coordinate system: Also known as the odometry coordinate system, it is a non-fixed, movable coordinate system. It represents the coordinate system of the robot relative to its starting position calculated based on encoder information (such as wheel odometry data) or other motion sensors (such as visual odometry, inertial measurement unit, etc.);

[0060] Replanning: During autonomous driving, when a vehicle encounters environmental changes, obstacles, new traffic signals, or other unforeseen circumstances, the system needs to recalculate or adjust its trajectory.

[0061] Three-dimensional coordinate transformation: In three-dimensional space, coordinate transformation usually involves rotation, translation and scaling. These transformations can be represented by a 4x4 homogeneous coordinate transformation matrix;

[0062] 3D rotation: In 3D space, rotation transformations can be composed by combining rotations around the X, Y, and Z axes. These rotations can be represented by Euler angles (yaw-pitch-roll) or quaternions.

[0063] In view of the fact that the relative position and other information determined in the map coordinate system mentioned in the background technology may be distorted because it is not possible to use appropriate map information as a reference when the scene changes, the present application proposes an autonomous driving operation processing solution. The inventive concept is that in order to adapt to the selection of appropriate map information to determine the relative position when the driving scene changes, the odometer coordinate system and the projection coordinate system can be used to replace the map coordinate system to assist the autonomous driving vehicle to accurately perform the corresponding driving operation. In the specific implementation, the coordinate information of the target at the current timestamp can be obtained first, and then based on the current coordinate information, two or more consecutive driving operations to be performed on the target can be roughly determined, as well as the reference coordinate system corresponding to each driving operation. The reference coordinate system here is mainly the odometer coordinate system or the projection coordinate system corresponding to the second type of driving operation. Afterwards, according to the correlation between the driving operations, the conversion matrix between different reference coordinate systems is calculated. Finally, the obtained coordinate information can be converted to a coordinate system based on the calculated conversion matrix, and the corresponding driving operation processing can be performed based on the conversion result. Since coordinate information is based on the odometry coordinate system or the projected coordinate system throughout the entire processing process, it is possible to quickly and flexibly switch between global and local map information when encountering scene switching scenarios. This ensures that the acquired positioning information is true and accurate, avoids the problem of positioning distortion caused by the map's inability to flexibly and accurately switch map types, reduces the occurrence of abnormal driving behaviors such as sudden braking, drawing dragons, and re-planning, and improves the driving safety of autonomous vehicles. At the same time, it also improves the applicability of autonomous driving scenarios and reduces the rate of manual takeover.

[0064] The driving operation processing scheme involved in this application is described in detail below through specific embodiments.

[0065] refer to Figure 2 The figure shows a schematic diagram of the steps of a driving operation processing method proposed in one embodiment of the present application. The execution subject of the driving operation processing method can be a driving operation processing device, wherein the processing device can be a software module with computing and data processing capabilities, or an electronic device integrated with a similar software module. Optionally, the execution subject of the driving operation processing method in the present application can be an autonomous driving vehicle, or a related processing module integrated in the autonomous driving vehicle.

[0066] Figure 2 The autonomous driving operation processing method shown may specifically include the following steps:

[0067] Step 202: Obtain coordinate information of a target in the autonomous driving scene at a current timestamp; wherein the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements.

[0068] The coordinate information here can be the location information of the target at the current timestamp, which can be obtained by detection by perception sensors or calculation by other sensors. The targets involved in the autonomous driving scenario of this application can be the autonomous driving vehicle itself, or obstacles near the autonomous driving vehicle, such as other autonomous driving vehicles, pedestrians, bicycles or electric vehicles, etc., or map elements in an electronic map, such as buildings, intersections, traffic lights, street lights, road signs, signs, etc. For map elements, their coordinate information can be directly queried and obtained from the electronic map.

[0069] It should be understood that the target can also be other factors that can affect the driving of autonomous vehicles on the road, such as hurricanes or clouds caused by weather conditions. This involves tracking the location of these dynamic elements. Where technically feasible and permitted by laws and regulations, accurate location information can be obtained through certain prediction ports.

[0070] Step 204: Determine at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation, wherein the driving operations are divided into a first type of driving operation and a second type of driving operation according to their types, and the at least two driving operations include at least the second type of driving operation. The reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometer coordinate system or a projected coordinate system related to the odometer coordinate system. The projected coordinate system satisfies the following requirements: its horizontal plane is parallel to the horizontal plane of the map coordinate system, and the parameters of each coordinate axis change continuously with the odometer coordinate system.

[0071] Optionally, in the present application, the first type of driving operation includes at least: routing operation; the second type of driving operation includes at least: perception operation, positioning operation, prediction operation, decision-making operation, planning operation and control operation; wherein, the reference coordinate systems corresponding to the perception operation and positioning operation are both odometer coordinate systems, and the reference coordinate systems corresponding to the prediction operation, decision-making operation, planning operation and control operation are all projected coordinate systems.

[0072] In specific implementations, perception operations are performed in the odom coordinate system, and obstacles (such as vehicles, non-motorized vehicles, pedestrians, etc.) and map elements (such as lane lines, map boundaries, and crosswalks) are output in odom coordinates. Positioning operations are performed in the odom coordinate system, outputting the vehicle's position in the odom coordinate system. Routing operations are performed in the map coordinate system, outputting the vehicle's planned route in the map coordinate system. Prediction operations are performed in the odom footprint coordinate system. Decision operations are performed in the odom footprint coordinate system. Planning operations are performed in the odom footprint coordinate system. Control operations are performed in the odom footprint coordinate system.

[0073] In fact, the driving operation of this application also includes reference line operation, that is, inputting the planned route in the map coordinate system and outputting the reference line of the vehicle in the odom footprint coordinate system.

[0074] It should be understood that, in the present application, at least one of the driving operations involved has a reference coordinate system that is an odometer coordinate system or a projected coordinate system related to the odometer coordinate system. Because this application primarily concerns coordinate conversion between driving operations, even for driving operations such as routing that use a map coordinate system as a reference coordinate system, there will be corresponding driving operations that require coordinate system conversion, such as reference line operations associated with routing.

[0075] Step 206: Calculate the transformation matrix between different reference coordinate systems based on the association relationship between the driving operations.

[0076] It should be noted that the association relationship may be an execution order relationship between driving operations, or a signal transmission relationship between driving operations, etc. This application is not limited to this.

[0077] Optionally, when calculating the transformation matrix between different reference coordinate systems based on the correlation between driving operations, any two driving operations with a direct transmission relationship can be determined based on the information transmission direction between multiple driving operations; when it is determined that the reference coordinate systems corresponding to the two driving operations are different, the transformation matrix between the two different reference coordinate systems at the current timestamp is determined according to the positioning output result.

[0078] For example, if the target's upcoming driving operations are determined to be perception, positioning, and prediction, then there is no signal transmission relationship between the perception and positioning operations, and the two are executed in parallel order. Therefore, there is no need to determine a transformation matrix between these two driving operations. However, there is a signal transmission relationship between the perception and prediction operations, and the signal transmission direction is determined to be from perception to prediction, with no other driving operations involved in between. Therefore, the reference coordinate systems corresponding to these two driving operations can be further determined. If the reference coordinate systems are the same, no processing is required. If the reference coordinate systems are different, for example, the perception operation corresponds to the odom coordinate system, and the prediction operation corresponds to the odom footprint coordinate system, then the transformation matrix between these two reference coordinate systems needs to be calculated.

[0079] In the present application, the projected coordinate system is the odometry horizontal projection coordinate system, i.e., the odom footprint coordinate system; then, the following transformation matrix may exist:

[0080] ① The conversion matrix from the odom footprint→map odometry horizontal projection coordinate system to the map coordinate system is: the projection matrix from the vehicle coordinate system to the map coordinate system × the inverse matrix of the projection matrix from the vehicle coordinate system to the odometry coordinate system;

[0081] ②The conversion matrix from the map→odom footprint map coordinate system to the odometry horizontal projection coordinate system is the inverse matrix of the conversion matrix from the odometry horizontal projection coordinate system to the map coordinate system.

[0082] ③ The conversion matrix from odom→odom footprint odometry coordinate system to odometry horizontal projection coordinate system is: conversion matrix from map coordinate system to odometry horizontal projection coordinate system × conversion matrix from odometry coordinate system to map coordinate system;

[0083] ④ The conversion matrix from odom footprint to odom odometry horizontal projection coordinate system to odometry coordinate system is: the inverse matrix of the conversion matrix from odometry coordinate system to odometry horizontal projection coordinate system;

[0084] ⑤ The conversion matrix from baselink→odom footprint vehicle coordinate system to odometry horizontal projection coordinate system is: conversion matrix from map coordinate system to odometry horizontal projection coordinate system × conversion matrix from vehicle coordinate system to map coordinate system;

[0085] ⑥ The conversion matrix from the odom footprint to the baselink odometry horizontal projection coordinate system to the vehicle body coordinate system is the inverse matrix of the conversion matrix from the vehicle body coordinate system to the odometry horizontal projection coordinate system.

[0086] The projection matrix is: the coordinates of the two axes corresponding to the horizontal plane of the corresponding transformation matrix and the axis corresponding to the heading angle are retained, and the coordinates of the axis vertical to the horizontal plane and the axis corresponding to the pitch angle and roll angle are set to zero.

[0087] It should be understood that in the present application, the corresponding transformation matrices for driving operations in different reference coordinate systems are different in each frame.

[0088] Step 208: Process the coordinate information based on the conversion matrix, and perform corresponding driving operation processing based on the conversion result.

[0089] After determining the conversion matrix between the driving operations involved, the coordinate information and the results of the coordinate information after driving operation processing can be gradually converted into coordinate systems according to the corresponding conversion matrix, and the corresponding driving operation processing can be performed at the corresponding driving operation node according to the result of each conversion.

[0090] For example, after determining the conversion matrix corresponding to perception→prediction, the coordinate information can be input into the perception module to perform the perception operation, and the result of the perception operation can be coordinate transformed based on the conversion matrix. After that, the conversion result is used as the input of the prediction module to perform the corresponding prediction operation.

[0091] Optionally, in the present application, when the autonomous driving vehicle enters the second type of scene from the first type of scene, the map information used for obtaining coordinate information and / or performing driving operations is switched from global map information to local map information; when the autonomous driving vehicle enters the first type of scene from the second type of scene, the map information used for obtaining coordinate information and / or performing driving operations is switched from local map information to global map information; wherein, the first type of scene is a scene that can be covered by a high-precision map, and the second type of scene is a local scene that is prone to cause distortion of location information.

[0092] For example, the first type of scene may be outside a tunnel, and the second type of scene may be inside a tunnel. The autonomous vehicle switches back and forth between outside the tunnel, inside the tunnel, and outside the tunnel. Based on the coordinate transformation scheme in steps 202 through 208 above, the autonomous vehicle can flexibly switch between the global map and the local map, ensuring stable, continuous, and safe driving of the autonomous vehicle and avoiding positioning distortion.

[0093] It should be noted that part or all of the execution entities of steps 202 to 208 may be applications located in the local terminal, or may be functional units such as plug-ins or software development kits (SDKs) provided in the applications located in the local terminal, or may be processing engines located in network-side servers, or may be distributed systems located on the network side, for example, processing engines or distributed systems in autonomous driving platforms on the network side, etc. This embodiment does not specifically limit this.

[0094] It is understandable that the application may be a native program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0095] It should be noted that the specific implementation process provided in this implementation can be combined with the various specific implementation processes provided in the aforementioned implementations to implement the blind spot detection method of this embodiment. Detailed descriptions can be found in the relevant content of the aforementioned implementations and will not be repeated here.

[0096] In order to better understand the method of the embodiment of the present application, the method of the embodiment of the present application is described below with reference to the accompanying drawings and specific application scenarios.

[0097] Figure 3 This is a specific flow chart of the driving operation processing solution provided by this application. Assume that the driving operations determined by this processing thread include: second-category driving operations such as perception operations, positioning operations, prediction operations, decision-making operations, planning operations, and control operations, as well as first-category driving operations such as routing operations and reference line operations. Figure 3 As shown in , the reference coordinate system corresponding to perception operations and positioning operations is the odom coordinate system, the reference coordinate system corresponding to prediction operations, decision operations, planning operations, and control operations is the odom footprint coordinate system, the reference coordinate system corresponding to routing operations is the map coordinate system, and the reference coordinate systems corresponding to reference line operations are the map coordinate system (input) and the odom footprint coordinate system (output).

[0098] according to Figure 2 In the processing method shown, the corresponding reference coordinate system can be determined for each driving operation first, and then the corresponding transformation matrix can be calculated based on the relationship between the driving operations. Figure 3As shown, the perception module serves as the starting point, and its input can be the requested map information or the coordinate information obtained by other sensors. After the perception operation is processed, the output result can be transmitted to the prediction module or to the planning module, and the reference coordinate systems corresponding to the prediction module and the planning module are the same, both of which are odom footprint coordinate systems. Therefore, it is only necessary to calculate the conversion matrix odom→odom footprint between the odom coordinate system and the odomfootprint coordinate system corresponding to the perception operation. After using the conversion matrix to perform coordinate system conversion processing on the output result of the perception module, it is transmitted to the prediction module and the planning module respectively for the corresponding driving operation. It should be understood that the driving operation here can be understood as the internal operation related to driving performed by the corresponding module, rather than the actual driving operation. Similarly, the modules corresponding to other driving operations can also be followed Figure 3 The corresponding coordinate transformation and driving operations are performed in sequence in the process.

[0099] When requesting map information in the odom or odom footprint coordinate systems, the map request can be converted from the odom or odom footprint coordinate systems to the map coordinate system to facilitate accurate search in the map coordinate system. The requested map results are then converted from the map coordinate system to the odom or odom footprint coordinate system and returned to the module corresponding to the driving operation for processing.

[0100] like Figure 4 As shown in the figure, this example uses an autonomous vehicle traveling through a tunnel to illustrate the entire process before, during, and after entering the tunnel. Before entering the tunnel, perception and positioning are performed based on a global map. After entering the tunnel, the global map is directly switched to a local map. Because the reference coordinate system for the entire prediction, decision-making, planning, and control module is the odom / odom footprint coordinate system, the vehicle's coordinates are stable and continuous during this switching process, eliminating the need for any additional switching or redundant logic. Furthermore, this reduces issues such as sudden braking, re-planning, and re-planning when positioning information is distorted, improving safety and reducing the need for manual takeover.

[0101] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0102] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] Figure 5 FIG. 1 shows a structural block diagram of an automatic driving operation processing device provided by an embodiment of the present application. Figure 5 As shown. The autonomous driving operation processing device 500 of this embodiment may include an acquisition module 501, a determination module 502, a calculation module 503, and a conversion module 504. The acquisition module 501 is configured to acquire coordinate information of a target in the autonomous driving scene at the current timestamp; the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements. The determination module 502 is configured to determine at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation. The driving operations are divided into a first type of driving operation and a second type of driving operation according to their type, and the at least two driving operations include at least the second type of driving operation. The reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometry coordinate system or a projected coordinate system related to the odometry coordinate system. The projected coordinate system satisfies the following conditions: its horizontal plane is parallel to the horizontal plane of the map coordinate system, and the parameters of each coordinate axis continuously change with the odometry coordinate system. The calculation module 503 is configured to calculate the transformation matrix between different reference coordinate systems based on the association between the driving operations. The conversion module 504 is used to perform coordinate system conversion on the coordinate information based on the conversion matrix, and perform corresponding autonomous driving operation processing based on the conversion result.

[0104] It should be noted that part or all of the autonomous driving operation processing device of this embodiment may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in an autonomous driving platform on the network side, etc. This embodiment does not specifically limit this.

[0105] It is understandable that the application may be a native program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0106] Optionally, in a possible implementation of this embodiment, when the autonomous driving vehicle enters the second type of scene from the first type of scene, the conversion module 504 will also obtain coordinate information and / or switch the map information used for reference in performing driving operations from global map information to local map information; and, when the autonomous driving vehicle enters the first type of scene from the second type of scene, the conversion module 504 will also obtain coordinate information and / or switch the map information used for reference in performing driving operations from local map information to global map information; wherein, the first type of scene is a scene that can be covered by a high-precision map, and the second type of scene is a local scene that is prone to cause distortion of location information.

[0107] Optionally, in a possible implementation of this embodiment, the first type of driving operation includes at least: routing operation; the second type of driving operation includes at least: perception operation, positioning operation, prediction operation, decision-making operation, planning operation and control operation; wherein, the reference coordinate systems corresponding to the perception operation and positioning operation are both odometer coordinate systems, and the reference coordinate systems corresponding to the prediction operation, decision-making operation, planning operation and control operation are all projected coordinate systems.

[0108] Optionally, in a possible implementation of this embodiment, when the calculation module 503 calculates the transformation matrix between different reference coordinate systems based on the association relationship between driving operations, it is specifically used to determine any two driving operations with a direct transmission relationship based on the information transmission direction between multiple driving operations; when it is determined that the reference coordinate systems corresponding to the two driving operations are different, determine the transformation matrix between the two different reference coordinate systems at the current timestamp according to the positioning output result.

[0109] Optionally, in a possible implementation of this embodiment, the projected coordinate system is an odometer horizontal projected coordinate system; then:

[0110] The conversion matrix from the odometry horizontal projection coordinate system to the map coordinate system is: the projection matrix from the vehicle coordinate system to the map coordinate system × the inverse matrix of the projection matrix from the vehicle coordinate system to the odometry coordinate system;

[0111] The conversion matrix from the map coordinate system to the odometry horizontal projection coordinate system is: the inverse matrix of the conversion matrix from the odometry horizontal projection coordinate system to the map coordinate system;

[0112] The conversion matrix from the odometer coordinate system to the odometer horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometer horizontal projection coordinate system × the conversion matrix from the odometer coordinate system to the map coordinate system;

[0113] The conversion matrix from the odometry horizontal projection coordinate system to the odometry coordinate system is: the inverse matrix of the conversion matrix from the odometry coordinate system to the odometry horizontal projection coordinate system;

[0114] The conversion matrix from the vehicle coordinate system to the odometry horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometry horizontal projection coordinate system × the conversion matrix from the vehicle coordinate system to the map coordinate system;

[0115] The conversion matrix from the odometer horizontal projection coordinate system to the vehicle body coordinate system is: the inverse matrix of the conversion matrix from the vehicle body coordinate system to the odometer horizontal projection coordinate system;

[0116] The projection matrix is: the coordinates of the two axes corresponding to the horizontal plane of the corresponding transformation matrix and the axis corresponding to the heading angle are retained, and the coordinates of the axis vertical to the horizontal plane and the axis corresponding to the pitch angle and roll angle are set to zero.

[0117] In this embodiment, the coordinate information of the target at the current timestamp can be obtained. Based on the current coordinate information, two or more driving operations to be performed on the target can be roughly determined, as well as the reference coordinate system corresponding to each driving operation. The reference coordinate system here can be a map coordinate system, an odometry coordinate system, or a projected coordinate system. Subsequently, based on the correlation between the driving operations, a transformation matrix between the different reference coordinate systems is calculated. Finally, the obtained coordinate information can be converted to a coordinate system based on the calculated transformation matrix, and the corresponding driving operation processing is performed based on the conversion result. Since the coordinate information is based on the odometry coordinate system or the projected coordinate system throughout the entire processing process, it is possible to quickly and flexibly switch between global map information and local map information when encountering scene switching. This ensures that the obtained positioning information is accurate and reliable, avoids the problem of positioning distortion caused by the inability of the map coordinate system to flexibly and accurately switch between map types, reduces the occurrence of abnormal driving behaviors such as sudden braking, swerving, and re-planning, and improves the driving safety of autonomous vehicles. At the same time, it also improves the applicability of autonomous driving scenarios and reduces the rate of manual takeover.

[0118] One embodiment of the present application provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the autonomous driving operation processing method as described above.

[0119] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the autonomous driving operation processing method as described above.

[0120] One embodiment of the present application provides an autonomous driving vehicle, including the electronic device described above. Specifically, the autonomous driving vehicle can be a vehicle of level L2 or above.

[0121] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0122] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0123] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0124] Multiple components in the electronic device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0125] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the method for handling autonomous driving operations. For example, in some embodiments, the method for handling autonomous driving operations can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for handling autonomous driving operations described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method for handling autonomous driving operations by any other suitable means (e.g., via firmware).

[0126] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, at least one input device, and at least one output device.

[0127] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0128] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0131] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0132] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0133] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for processing an automatic driving operation, characterized in that: include: Obtaining coordinate information of a target in an autonomous driving scene at a current timestamp; wherein the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements; Determine at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation, wherein the driving operations are divided into a first type of driving operation and a second type of driving operation according to their types, the at least two driving operations at least include the second type of driving operation, the reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometer coordinate system or a projection coordinate system related to the odometer coordinate system, and the projection coordinate system satisfies: its horizontal plane is parallel to the horizontal plane of the map coordinate system, and the parameters of each coordinate axis change continuously with the odometer coordinate system; Based on the correlation between driving operations, the transformation matrix between different reference coordinate systems is calculated; The coordinate information is converted into a coordinate system based on the conversion matrix, and corresponding autonomous driving operation processing is performed based on the conversion result.

2. The method according to claim 1, characterized in that The method further comprises: When the autonomous driving vehicle enters the second type of scene from the first type of scene, the map information referenced for obtaining coordinate information and / or performing driving operations is switched from global map information to local map information; When the autonomous driving vehicle enters the first type of scene from the second type of scene, the map information referenced for obtaining coordinate information and / or performing driving operations is switched from local map information to global map information; Among them, the first type of scenes are scenes that can be covered by high-precision maps, and the second type of scenes are local scenes that are prone to cause distortion of location information.

3. The method according to claim 1 or 2, characterized in that The first type of driving operations at least includes: routing operations; The second type of driving operation includes at least: perception operation, positioning operation, prediction operation, decision operation, planning operation and control operation; Among them, the reference coordinate systems corresponding to the perception operation and positioning operation are all odometer coordinate systems, and the reference coordinate systems corresponding to the prediction operation, decision-making operation, planning operation and control operation are all projection coordinate systems.

4. The method according to claim 3, characterized in that Based on the relationship between driving operations, the transformation matrix between different reference coordinate systems is calculated, including: Determine any two driving operations having a direct transmission relationship based on information transmission directions between the plurality of driving operations; When it is determined that the reference coordinate systems corresponding to the two driving operations are different, a conversion matrix between the two different reference coordinate systems at a current timestamp is determined according to the positioning output result.

5. The method according to claim 4, characterized in that The projection coordinate system is the odometer horizontal projection coordinate system; then: The conversion matrix from the odometer horizontal projection coordinate system to the map coordinate system is: the projection matrix from the vehicle coordinate system to the map coordinate system × the inverse matrix of the projection matrix from the vehicle coordinate system to the odometer coordinate system; The conversion matrix from the map coordinate system to the odometer horizontal projection coordinate system is: the inverse matrix of the conversion matrix from the odometer horizontal projection coordinate system to the map coordinate system; The conversion matrix from the odometer coordinate system to the odometer horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometer horizontal projection coordinate system × the conversion matrix from the odometer coordinate system to the map coordinate system; The conversion matrix from the odometer horizontal projection coordinate system to the odometer coordinate system is: the inverse matrix of the conversion matrix from the odometer coordinate system to the odometer horizontal projection coordinate system; The conversion matrix from the vehicle coordinate system to the odometer horizontal projection coordinate system is: the conversion matrix from the map coordinate system to the odometer horizontal projection coordinate system × the conversion matrix from the vehicle coordinate system to the map coordinate system; The transformation matrix from the odometer horizontal projection coordinate system to the vehicle body coordinate system is: the inverse matrix of the transformation matrix from the vehicle body coordinate system to the odometer horizontal projection coordinate system; Among them, the projection matrix is: the coordinates of the two axes corresponding to the horizontal plane of the corresponding transformation matrix and the axis corresponding to the heading angle are retained, and the coordinates of the axis of the vertical horizontal plane and the axis corresponding to the pitch angle and the roll angle are set to zero.

6. An automatic driving operation processing device, characterized in that: include: An acquisition module, used to acquire coordinate information of a target in an autonomous driving scene at a current timestamp; wherein the target includes one or more of the following: the autonomous driving vehicle itself, obstacles near the autonomous driving vehicle, and map elements; a determination module, configured to determine at least two driving operations to be performed on the target, and a reference coordinate system corresponding to each driving operation, wherein the driving operations are divided into a first type of driving operation and a second type of driving operation according to their types, the at least two driving operations at least include the second type of driving operation, the reference coordinate system corresponding to the first type of driving operation is a map coordinate system, and the reference coordinate system corresponding to the second type of driving operation is an odometer coordinate system or a projection coordinate system related to the odometer coordinate system, and the projection coordinate system satisfies: its horizontal plane is parallel to the horizontal plane of the map coordinate system, and the parameters of each coordinate axis change continuously with the odometer coordinate system; A calculation module, used for calculating the transformation matrix between different reference coordinate systems based on the correlation relationship between driving operations; A conversion module is used to perform coordinate system conversion on the coordinate information based on the conversion matrix, and perform corresponding autonomous driving operation processing based on the conversion result.

7. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the automatic driving operation processing method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the automatic driving operation processing method according to any one of claims 1-5.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the autonomous driving operation processing method according to any one of claims 1 to 5.

10. An autonomous driving vehicle comprising the electronic device described in claim 7.

Images