Perception data processing method, device and electronic equipment for autonomous driving

Abstract

The present disclosure provides a method, apparatus, electronic device, and storage medium for processing perception data for autonomous driving, relating to the field of computer technology, and in particular to the fields of autonomous driving, autonomous parking, the Internet of Things, and intelligent transportation. A specific implementation scheme comprises: determining obstacle center position information corresponding to each piece of at least one piece of sensed obstacle information; for each piece of obstacle center position information, in response to detecting that the position located by the obstacle center position information is within a predefined area, determining a filtering condition and target obstacle center position information whose position is within the predefined area; and in response to detecting that first target obstacle information corresponding to the target obstacle center position information satisfies the filtering condition, filtering the first target obstacle information from the at least one piece of obstacle information.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to the fields of autonomous driving, autonomous parking, the Internet of Things, and intelligent transportation. Specifically, it relates to a method, device, electronic device, and storage medium for processing perception data for autonomous driving. Background Art

[0002] An autonomous car, also known as a robotic car, self-driving car, or driverless car, is a vehicle capable of sensing its environment and driving with little or no human input. Autonomous vehicles use a combination of sensors to perceive their surroundings, such as radar, lidar, sonar, global positioning systems, odometry, and inertial measurement units. Advanced control systems interpret this sensory information to identify appropriate navigation paths, obstacles, and relevant landmarks. Summary of the Invention

[0003] The present disclosure provides a method, device, electronic device, and storage medium for processing perception data for autonomous driving.

[0004] According to one aspect of the present disclosure, a method for processing perception data for autonomous driving is provided, comprising: determining obstacle center position information corresponding to each piece of at least one piece of sensed obstacle information; for each piece of obstacle center position information, in response to detecting that a position located by the obstacle center position information is within a predefined area, determining a filtering condition and target obstacle center position information whose position is within the predefined area; and in response to detecting that first target obstacle information corresponding to the target obstacle center position information satisfies the filtering condition, filtering the first target obstacle information from the at least one piece of obstacle information.

[0005] According to another aspect of the present disclosure, a perception data processing device for autonomous driving is provided, comprising: a first determination module for determining obstacle center position information corresponding to each obstacle information in at least one sensed obstacle information; a second determination module for determining, for each obstacle center position information, a filtering condition and target obstacle center position information whose located position is within a predefined area in response to detecting that the position located by the obstacle center position information is within the predefined area; and a filtering module for filtering first target obstacle information corresponding to the target obstacle center position information from the at least one obstacle information in response to detecting that the first target obstacle information satisfies the filtering condition.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the perception data processing method for autonomous driving of the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the perception data processing method for autonomous driving of the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the perception data processing method for autonomous driving of the present disclosure.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0011] Figure 1 Schematically illustrates an exemplary system architecture of a perception data processing method and apparatus applicable to autonomous driving according to an embodiment of the present disclosure;

[0012] Figure 2 A flowchart of a method for processing perception data for autonomous driving according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 The following schematically shows an overall flow chart of a method for processing perception data for autonomous driving according to an embodiment of the present disclosure;

[0014] Figure 4 A block diagram schematically shows a perception data processing device for autonomous driving according to an embodiment of the present disclosure; and

[0015] Figure 5 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0016] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure 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 disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0017] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0018] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0019] In the driving scenarios of autonomous vehicles, there may be some special obstacles that have no impact on the vehicle's driving safety or that can be guaranteed not to affect the vehicle's driving by mandatory path planning.

[0020] While implementing the concepts of this disclosure, the inventors discovered that detecting and identifying special obstacles presents significant challenges for autonomous vehicles operating in scenarios involving them. For example, when using perception algorithms to identify special obstacles, there can be issues with incorrect type recognition or unstable obstacle boundary recognition. This can cause the vehicle to brake suddenly or even briefly to avoid these obstacles, even when they detect them. This can lead to poor user experience and reduced autonomous driving efficiency. For another example, in some special scenarios, such as narrow roads with obstacles such as cones placed at the edge, or narrow roads with double yellow lines on the left and fences on the right, the planning and control module downstream of the autonomous vehicle can expand the obstacle boundaries. For example, when the main vehicle is traveling on a narrow road with double yellow lines on the left and fences on the right, a buffer is required to be added to the detected fence obstacles. This can cause the vehicle to stall even when obstacle recognition is stable. In addition, the perception algorithm has generalization problems. For example, the laser radar point cloud of the platform looks similar to the point cloud structure presented by a real vehicle from certain angles. When identification is performed based on the perception algorithm, the platform will be identified as a vehicle. Adjusting the parameters in the perception algorithm cannot effectively solve the problem of misidentification by the perception algorithm. If the relevant models or parameters are further optimized and adjusted, other unnecessary problems may arise.

[0021] The present disclosure provides a method, apparatus, electronic device, and storage medium for processing perception data for autonomous driving. The method includes: determining obstacle center position information corresponding to each piece of at least one piece of obstacle information sensed; for each piece of obstacle center position information, in response to detecting that the position located by the obstacle center position information is within a predefined area, determining a filtering condition and target obstacle center position information whose position is within the predefined area; and in response to detecting that first target obstacle information corresponding to the target obstacle center position information satisfies the filtering condition, filtering the first target obstacle information from the at least one piece of obstacle information.

[0022] Figure 1 An exemplary system architecture of a perception data processing method and apparatus for autonomous driving according to an embodiment of the present disclosure is schematically illustrated.

[0023] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure. This does not mean that the embodiments of the present disclosure cannot be applied to other devices, systems, environments, or scenarios. For example, in another embodiment, an exemplary system architecture to which the method and apparatus for processing perception data for autonomous driving may be applied may include a terminal device, but the terminal device may implement the method and apparatus for processing perception data for autonomous driving provided by the embodiments of the present disclosure without interacting with a server.

[0024] like Figure 1 As shown, the system architecture 100 according to this embodiment may include an information acquisition terminal 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the information acquisition terminal 101 and the server 103. The network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0025] The information collection terminal 101 interacts with the server 103 via the network 102 to receive or send information, etc. The information collection terminal 101 is used, for example, to collect obstacle perception information based on multiple sampling moments.

[0026] The server 105 may be a server that provides various services, such as a background processing server that processes obstacle sensing information provided by the information acquisition terminal 101 (for example only). The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system. It solves the management difficulties and weak business scalability of traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server for a distributed system, or a server integrated with a blockchain.

[0027] It should be noted that the perception data processing method for autonomous driving provided by the embodiment of the present disclosure can generally be executed by the server 103. Accordingly, the perception data processing device for autonomous driving provided by the embodiment of the present disclosure can generally be set in the server 103. The perception data processing method for autonomous driving provided by the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 103 and can communicate with the information acquisition terminal 101 and / or the server 103. Accordingly, the perception data processing device for autonomous driving provided by the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 103 and can communicate with the information acquisition terminal 101 and / or the server 103.

[0028] For example, the information collection terminal 101 may sense obstacle information and then transmit the sensed obstacle information to the server 103. The server 103 then determines obstacle center location information corresponding to each piece of at least one piece of obstacle information sensed. For each piece of obstacle center location information, in response to detecting that the location of the obstacle center location information is within a predefined area, a filtering condition is determined. In response to detecting that first target obstacle information corresponding to the obstacle center location information satisfies the filtering condition, the first target obstacle information is filtered out of the at least one piece of obstacle information. Alternatively, the obstacle information may be processed by a server or server cluster capable of communicating with the information collection terminal 101 and / or the server 103.

[0029] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0030] Figure 2 A flowchart of a method for processing perception data for autonomous driving according to an embodiment of the present disclosure is schematically shown.

[0031] like Figure 2 As shown, the method includes operations S210 to S230.

[0032] In operation S210 , obstacle center position information corresponding to each obstacle information of at least one sensed obstacle information is determined.

[0033] In operation S220 , for each obstacle center position information, in response to detecting that the obstacle center position information is located within a predefined area, a filtering condition and target obstacle center position information located within the predefined area are determined.

[0034] In operation S230 , in response to detecting that the first target obstacle information corresponding to the target obstacle center position information satisfies a filtering condition, the first target obstacle information is filtered out from the at least one obstacle information.

[0035] According to embodiments of the present disclosure, obstacle information may include information such as the location, shape, and size of all physical objects that can be sensed by an information collection device or sensor device. Physical objects may include at least one of stationary objects and moving objects. For example, obstacle information may be used to characterize all stationary or moving obstacles sensed by on-board sensors. Obstacle center location information may be determined based on the sensed obstacle information and a sensing algorithm. Obstacle center location information may include at least one of two-dimensional location information and three-dimensional location information.

[0036] According to an embodiment of the present disclosure, the predefined area range may include at least one of a plane range and a spatial range. The predefined area range may be used to define at least one of an area that does not affect the vehicle's driving process, an area corresponding to an obstacle that does not affect the vehicle's driving process, an area corresponding to the center position of an obstacle that does not affect the vehicle's driving process, and other areas that can be filtered out. The predefined area range may be determined by first determining a plurality of predefined coordinate points and then forming a polygon based on the plurality of predefined coordinate points.

[0037] For example, during vehicle driving, obstacles that do not affect vehicle driving may include stationary objects placed in the actual environment. The coordinates of stationary objects in the HD map coordinate system can be fixed and will not shift with the movement of the vehicle. In addition, the obstacle information transmitted by the on-board sensors to the downstream planning and control module can also be established in the HD map coordinate system. Based on this, the location information of at least one of the obstacle information, such as the obstacle information sensed in certain scenarios and the obstacle information determined based on certain perception algorithms, can be confined within a specific range of the HD map, and the above-mentioned predefined area range can be determined based on the specific range.

[0038] According to an embodiment of the present disclosure, the filtering conditions may include at least one of the following: the obstacle represented by the obstacle information is a vehicle of a predefined model, the obstacle represented by the obstacle information is the ground, the obstacle represented by the obstacle information is a fence, the obstacle represented by the obstacle information is vegetation, and the obstacle represented by the obstacle information is other predefined objects, and may not be limited thereto.

[0039] According to an embodiment of the present disclosure, the predefined area range and filtering conditions can be pre-configured in the information collection device or sensor device, and the configuration parameters can be read in a timely manner to achieve filtering processing of certain obstacles.

[0040] For example, an autonomous driving software system may include multiple modules such as a perception module, a decision module, a planning module, and a control module. The information used to define the predefined area range and filtering conditions can be configured within the perception module. The configuration method may include: first, based on the filtering requirements of special obstacles, define the relevant Prot o Structure, Prot o The structure can define the data format of configuration parameter information related to predefined area ranges and filtering conditions. Then, by adding configuration parameter information to the defined Proto structure, a configuration file containing predefined area ranges and filtering conditions is generated. Proto refers to the writing of an object, which can be called an implicit prototype. An object's implicit prototype points to the prototype of the constructor that constructs the object, allowing instances to access the properties and methods defined in the constructor prototype.

[0041] It should be noted that the Proto structure and the content of the configuration parameters can be maintained by the perception team, and the maintenance measures may include at least one of modification and update.

[0042] According to an embodiment of the present disclosure, with respect to the obstacle center position information of each obstacle sensed during vehicle travel, when target obstacle center position information is detected whose located position is within a predefined area, a strategy for filtering out first target obstacle information corresponding to the target obstacle center position information based on a filtering condition can be triggered. By further determining other attribute information of the first target obstacle information based on the filtering condition, first target obstacle information that does not affect vehicle travel can be filtered out from the detected obstacle information.

[0043] The above-described embodiments of the present disclosure, combined with predefined area ranges and filtering conditions, provide a perception-assisted capability in addition to the perception algorithm. This implements a filtering strategy that can stably filter out specific obstacles in specific scenarios, improving the accuracy of obstacle sensing results. Furthermore, in the field of autonomous driving, the proper use of this filtering strategy can improve vehicle traffic efficiency while ensuring safe and reliable traffic flow, effectively enhancing autonomous driving capabilities.

[0044] In conjunction with specific embodiments, Figure 2 The method shown is further explained.

[0045] According to an embodiment of the present disclosure, the filtering condition may include multiple filtering sub-conditions. Determining the filtering condition may include: in response to receiving a selection operation for a target filtering sub-condition among the multiple filtering sub-conditions, determining the target filtering sub-condition as the filtering condition.

[0046] According to embodiments of the present disclosure, obstacles in different scenarios may have specific characteristics. Based on the scenario characteristics and obstacle-related properties, filtering conditions can be defined in batches according to different filtering ranges. This definition process may also include: first, defining a Proto structure. Then, based on the Proto structure, defining configuration parameter information. Subsequently, based on the predefined Proto structure, multiple new filtering strategies for obstacle information can be added in combination with the configuration parameter information before the obstacle information is serialized and sent to the downstream planning and control module.

[0047] For example, you can define an integer variable filter_method in the public Proto for the filtering method, and use a number to represent the corresponding filtering method. For example, the number 0 represents filtering based on predefined obstacle types, the number 1 represents filtering based on predefined obstacle subtypes, the number 2 represents filtering based on predefined point cloud categories, and the number 9 represents direct filtering. Depending on the value of the filter_method field, by selecting different numbers, you can select different filtering methods as the filtering conditions to be adopted.

[0048] It should be noted that, according to the category of obstacle information, other filtering methods may be defined, and the corresponding filtering methods may be defined in combination with other numbers for easy selection.

[0049] According to an embodiment of the present disclosure, a filter array filter_list can be defined based on the filter_method field. The filter array can define information related to obstacles that can be filtered out by the filtering method. For example, for a filtering method that filters based on predefined obstacle types, a filter array can be defined for obstacle information related to at least one obstacle type, such as people or vehicles. For a filtering method that filters based on predefined obstacle subtypes, a filter array can be defined for obstacle information further refined based on the predefined obstacle types. For example, after further refinement of vehicles, a filter array can be defined for obstacle information related to at least one obstacle type, such as bicycles, cars, trucks, and tricycles. For a filtering method that filters based on predefined point cloud categories, a filter array can be defined for point cloud information representing at least one of the following: ground, vegetation, fences, and other unknown information. Direct filtering can directly filter out obstacles whose location, as determined by the obstacle center position information, falls within a predefined area.

[0050] According to embodiments of the present disclosure, when a user selects a filtering method, only certain types of obstacle information corresponding to that filtering method can be filtered out. For example, by selecting to filter based on predefined obstacle types, the user can filter out only obstacle information of types such as pedestrians and vehicles, while retaining other obstacle information. By selecting to filter based on predefined point cloud categories, the user can filter out only obstacle information such as ground, vegetation, and fences, while retaining other obstacle information.

[0051] Through the above-described embodiments of the present disclosure, by defining multiple filtering sub-conditions in batches, the configuration of relevant information for the filtering conditions can be simplified. By selecting a target filtering sub-condition as the filtering condition to be adopted, unnecessary security risks caused by filtering too much obstacle information can be avoided.

[0052] According to an embodiment of the present disclosure, to determine the scope of a predefined area and filtering conditions, the method for processing perception data for autonomous driving may further include: in response to detecting that a vehicle has traveled into a target area, obtaining predefined filtering conditions associated with the target area. Based on the predefined filtering conditions, determining the scope of a target predefined area and target filtering conditions for filtering obstacle information sensed by onboard sensors associated with the vehicle.

[0053] According to an embodiment of the present disclosure, both the predefined area range and the filtering conditions can be pre-configured in a system module that has a communication relationship with the information collection device or sensor device, such as within the autonomous driving software system. A Patch node can be set within the autonomous driving software system to send various configuration parameter information, such as predefined area range and filtering conditions, to other modules. Patch can refer to a memory patch, a file patch, etc., or it can be a computer command program that can modify file applications.

[0054] According to an embodiment of the present disclosure, configuration parameter information such as effective predefined area ranges and filtering conditions can be set based on the cybertron framework. Cybertron is a scheduling framework for various algorithm modules based on the operating system layer, which can be responsible for message communication, resource allocation, and operation scheduling between modules. The Patch module can provide a fixed interface for sending configuration parameter information related to a specific area when the vehicle travels to the area. The perception module can subscribe to the required configuration parameter information and set a callback function. When the Patch module sends the configuration parameter information outward, the perception module can receive the relevant configuration parameter information. Then, based on the callback function, the predefined relevant parameter values ​​in the relevant configuration parameter information can be obtained to obtain the target predefined area range and target filtering conditions related to the specific area. The target predefined area range and target filtering conditions can be assigned to the perception filtering strategy. Based on the perception filtering strategy, the obstacle information detected by the vehicle in the specific area can be processed.

[0055] It should be noted that when the Patch module and other modules such as the perception module need to interact with each other through messages, the communication method of node parameters in the ROS (Robot Operating System) system can also be used for implementation.

[0056] Through the above-mentioned embodiments of the present disclosure, by setting up a Patch module to achieve information interaction between modules, the consistency of filtering strategy processing within the system can be effectively guaranteed. In addition, according to the area the vehicle enters, the predefined area range and filtering conditions of the corresponding area are obtained, which can effectively reduce the amount of data during information transmission. The predefined area range and filtering conditions configured for each area facilitate maintenance and management. For a specific area, combining the predefined area range and filtering conditions to perform information processing can also effectively improve information processing efficiency.

[0057] According to an embodiment of the present disclosure, the method for processing perception data for autonomous driving may further include: in response to detecting that the location of the obstacle center position information is outside a predefined area, determining second target obstacle information corresponding to the obstacle center position information, and controlling vehicle travel based on the second target obstacle information.

[0058] According to an embodiment of the present disclosure, when a vehicle travels into a specific area, the Patch module can send configuration parameter information such as the defined predefined area range and filtering conditions, which will be acquired and loaded by the perception module. The perception module can loop through the obstacle information of each obstacle sensed by the on-board sensor and determine whether the center position of the obstacle is within the predefined area range. If not, the second target obstacle information can be determined. When the second target obstacle information is detected, the filtering strategy can be skipped and the output tag of the second target obstacle information can be set to true to control the vehicle's travel according to the second target obstacle information.

[0059] Through the above-described embodiments of the present disclosure, obstacle information that may affect vehicle movement can be filtered based on a predefined area, effectively resolving the issue of unstable detection and recognition of specific obstacles by perception algorithms. Controlling vehicle movement based on this filtered obstacle information can effectively improve vehicle efficiency and autonomous driving capabilities in specific scenarios.

[0060] According to an embodiment of the present disclosure, the perception data processing method for autonomous driving may further include: controlling the driving of the vehicle based on the obstacle information after filtering out the first target obstacle information from the at least one obstacle information.

[0061] According to an embodiment of the present disclosure, for obstacle information whose center position is within a predefined area, namely, first target obstacle information, a corresponding filtering method can be selected based on the value of a predefined filter_method field. Then, based on the filtering conditions defined in the filter_list corresponding to the selected filtering method, it can be determined whether the first target obstacle information meets the selected filtering conditions. If the first target obstacle information meets the selected filtering conditions, the output flag of the first target obstacle information can be set to false. If the first target obstacle information does not meet the selected filtering conditions, the output flag of the first target obstacle information can be set to true.

[0062] According to the embodiments of the present disclosure, only obstacle information with an output label of true can be serialized and sent to the downstream planning and control module to control vehicle movement. Obstacle information with an output label of false is filtered out within the perception module to filter out special obstacle information and not be output to the downstream planning and control module. This can prevent sudden braking or even light braking of the vehicle due to special scenarios or obstacles.

[0063] Through the above-mentioned embodiments of the present disclosure, obstacle information that has no impact on vehicle driving can be filtered out based on a predefined area range and filtering conditions, and the vehicle's driving can be controlled according to the obstacle information remaining after filtering, which can effectively improve the vehicle's traffic efficiency and automatic driving capabilities in special scenarios.

[0064] According to an embodiment of the present disclosure, a Boolean policy switch can be added to the Proto structure. When the switch is off, it can be indicated that the above filtering policy is not enabled. When the filtering policy needs to be used in a specific scenario, the switch can be manually enabled in the configuration file.

[0065] Through the above-mentioned embodiments of the present disclosure, the robustness of code logic can be improved, and the filtering strategy can be compatible with diverse application scenarios.

[0066] Figure 3 The overall flow chart of the perception data processing method for autonomous driving according to an embodiment of the present disclosure is schematically shown.

[0067] like Figure 3 As shown, the method includes operations S310 to S360.

[0068] In operation S310 , obstacle center position information corresponding to each obstacle information of at least one sensed obstacle information is determined.

[0069] In operation S320, is the center of the obstacle located within the predetermined area? If so, only operation S330 is performed; if not, operation S360 is performed.

[0070] In operation S330 , different filtering conditions are selected based on the value of the filter_method field.

[0071] In operation S340 , does the obstacle information meet the selected filtering condition? If so, operation S350 is executed; if not, operation S360 is executed.

[0072] In operation S350 , the obstacle information is filtered out from the at least one obstacle information.

[0073] In operation S360 , the obstacle information is stored.

[0074] According to an embodiment of the present disclosure, the perception module can sense at least one obstacle based on a perception algorithm. Each obstacle can correspond to obstacle center position information representing the center position of the obstacle. Predefined area ranges and filtering conditions can be predefined and stored in the perception module or another system that communicates with the perception module, such as a vehicle-mounted system. A patch module can be configured within the system to establish communication between different modules, ensuring consistent filtering strategies across modules within the system.

[0075] According to an embodiment of the present disclosure, for each sensed obstacle information, it can be determined whether the position of the obstacle center corresponding to the obstacle information is within the predefined area. If so, a filtering condition can be selected to further filter the obstacle information. If it is determined that the obstacle information also meets the selected filtering condition, indicating that the obstacle can be filtered out, the obstacle is filtered out. If it is determined that the obstacle information does not meet the selected filtering condition, indicating that the obstacle should not be filtered out, the obstacle is stored. If it is determined that the position of the obstacle center corresponding to the obstacle information is outside the predefined area, indicating that the obstacle should not be filtered out, the obstacle is stored. The stored obstacle information can be input into the planning control module for further processing. For example, the driving of the vehicle can be controlled based on the stored obstacle information.

[0076] The above-described embodiments of the present disclosure, combined with predefined area ranges and filtering conditions, provide a perception-assisted capability in addition to the perception algorithm. This implements a filtering strategy that can stably filter out specific obstacles in specific scenarios, improving the accuracy of obstacle sensing results. Furthermore, in the field of autonomous driving, the proper use of this filtering strategy can improve vehicle traffic efficiency while ensuring safe and reliable traffic flow, effectively enhancing autonomous driving capabilities.

[0077] Figure 4 A block diagram of a perception data processing device for autonomous driving according to an embodiment of the present disclosure is schematically shown.

[0078] like Figure 4 As shown, the perception data processing device 400 for autonomous driving includes a first determination module 410 , a second determination module 420 and a filtering module 430 .

[0079] The first determining module 410 is configured to determine obstacle center position information corresponding to each obstacle information of the at least one obstacle information sensed.

[0080] The second determination module 420 is used to determine, for each obstacle center position information, a filtering condition and target obstacle center position information whose located position is within the predefined area in response to detecting that the location of the obstacle center position information is within the predefined area.

[0081] The filtering module 430 is configured to filter out the first target obstacle information from the at least one obstacle information in response to detecting that the first target obstacle information corresponding to the target obstacle center position information satisfies a filtering condition.

[0082] According to an embodiment of the present disclosure, the filtering condition includes a plurality of filtering sub-conditions. The second determining module includes a determining unit.

[0083] The determining unit is configured to, in response to receiving a selection operation on a target filtering sub-condition among the plurality of filtering sub-conditions, determine the target filtering sub-condition as the filtering condition.

[0084] According to an embodiment of the present disclosure, the perception data processing device for autonomous driving further includes an acquisition module and a third determination module.

[0085] The acquisition module is configured to acquire a predefined filtering condition related to the target area in response to detecting that the vehicle has traveled into the target area.

[0086] The third determining module is used to determine, according to the predefined filtering condition, a target predefined area range and a target filtering condition for filtering obstacle information sensed by an onboard sensor related to the vehicle.

[0087] According to an embodiment of the present disclosure, at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor. The autonomous driving perception data processing device further includes a fourth determination module and a first control module.

[0088] The fourth determining module is configured to determine second target obstacle information corresponding to the obstacle center position information in response to detecting that the position where the obstacle center position information is located is outside the predefined area.

[0089] The first control module is used to control the driving of the vehicle according to the second target obstacle information.

[0090] According to an embodiment of the present disclosure, at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor. The autonomous driving perception data processing device further includes a second control module.

[0091] The second control module is configured to control the driving of the vehicle according to the obstacle information obtained by filtering out the first target obstacle information from the at least one obstacle information.

[0092] According to an embodiment of the present disclosure, the filtering conditions include at least one of the following: the obstacle represented by the obstacle information is a vehicle of a predefined model, the obstacle represented by the obstacle information is the ground, the obstacle represented by the obstacle information is a fence, the obstacle represented by the obstacle information is vegetation, and the obstacle represented by the obstacle information is other predefined objects.

[0093] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0094] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and 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 perception data processing method for autonomous driving of the present disclosure.

[0095] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a computer to execute the perception data processing method for autonomous driving of the present disclosure.

[0096] According to an embodiment of the present disclosure, a computer program product includes a computer program, which implements the perception data processing method for autonomous driving of the present disclosure when executed by a processor.

[0097] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure 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, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0098] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0099] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0100] The computing unit 501 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 501 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 501 performs the various methods and processes described above, such as the perception data processing method for autonomous driving. For example, in some embodiments, the perception data processing method for autonomous driving can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the perception data processing method for autonomous driving described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the perception data processing method for autonomous driving by any other suitable means (e.g., via firmware).

[0101] 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, the at least one input device, and the at least one output device.

[0102] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes 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 chart and / or block diagram 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.

[0103] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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 disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0108] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing perception data for autonomous driving, comprising: determining obstacle center position information corresponding to each obstacle information of the at least one obstacle information sensed; For each piece of obstacle center position information, in response to detecting that the position located by the obstacle center position information is within a predefined area, determining a filtering condition, and using the obstacle center position information as target obstacle center position information; In response to detecting that first target obstacle information corresponding to the target obstacle center position information satisfies the filtering condition, setting an output label of the first target obstacle information to a first label; In response to detecting that the first target obstacle information does not meet the filtering condition, setting the output label of the first target obstacle information to a second label; In response to detecting that the position located by the obstacle center position information is outside the predefined area, setting the output label of the second target obstacle information corresponding to the obstacle center position information as a second label; Sending the obstacle information with the output label as the second label to the planning control module; Obstacle information with an output tag of the first tag is filtered out from the at least one obstacle information to avoid sending the obstacle information with an output tag of the first tag to the planning control module.

2. The method according to claim 1, wherein The filtering condition includes a plurality of filtering sub-conditions; Determining the filtering conditions includes: In response to receiving a selection operation on a target filtering sub-condition among the plurality of filtering sub-conditions, the target filtering sub-condition is determined as the filtering condition.

3. The method according to claim 1, further comprising: In response to detecting that the vehicle travels into the target area, obtaining a predefined filtering condition related to the target area; as well as According to the predefined filtering condition, a target predefined area range and a target filtering condition for filtering obstacle information sensed by an onboard sensor associated with the vehicle are determined.

4. The method according to claim 1, wherein The at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor; The method further comprises: In response to detecting that the position located by the obstacle center position information is outside the predefined area, determining second target obstacle information corresponding to the obstacle center position information; and The driving of the vehicle is controlled according to the second target obstacle information.

5. The method according to claim 1, wherein The at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor; The method further comprises: The driving of the vehicle is controlled according to the obstacle information obtained by filtering out the first target obstacle information from the at least one obstacle information.

6. The method according to claim 1, wherein The filtering condition includes at least one of the following: The obstacles represented by the obstacle information are vehicles of predefined models; The obstacle represented by the obstacle information is the ground; The obstacle represented by the obstacle information is a fence; The obstacles represented by the obstacle information are vegetation; as well as The obstacles represented by the obstacle information are other predefined objects.

7. A perception data processing device for autonomous driving, comprising: a first determining module, configured to determine obstacle center position information corresponding to each obstacle information of at least one obstacle information sensed; a second determining module configured to determine, for each piece of obstacle center position information, a filtering condition in response to detecting that the position located at the obstacle center position information is within a predefined area, and use the obstacle center position information as target obstacle center position information; as well as a filtering module configured to, in response to detecting that first target obstacle information corresponding to the target obstacle center position information satisfies the filtering condition, set an output tag of the first target obstacle information to a first tag; in response to detecting that the first target obstacle information does not satisfy the filtering condition, set the output tag of the first target obstacle information to a second tag; in response to detecting that the position located by the obstacle center position information is outside the predefined area, set the output tag of second target obstacle information corresponding to the obstacle center position information to a second tag; and send the obstacle information with the second tag as the output tag to the planning control module; Obstacle information with an output tag of the first tag is filtered out from the at least one obstacle information to avoid sending the obstacle information with an output tag of the first tag to the planning control module.

8. The device according to claim 7, wherein The filtering condition includes a plurality of filtering sub-conditions; The second determining module includes: The determining unit is configured to, in response to receiving a selection operation for a target filtering sub-condition among the plurality of filtering sub-conditions, determine the target filtering sub-condition as the filtering condition.

9. The apparatus according to claim 7, further comprising: an acquisition module, configured to acquire a predefined filtering condition related to the target area in response to detecting that a vehicle has traveled into the target area; as well as The third determining module is configured to determine, based on the predefined filtering condition, a target predefined area range and a target filtering condition for filtering obstacle information sensed by an onboard sensor associated with the vehicle.

10. The device according to claim 7, wherein The at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor; The device further comprises: a fourth determining module, configured to determine, in response to detecting that the position located by the obstacle center position information is outside the predefined area, second target obstacle information corresponding to the obstacle center position information; and The first control module is used to control the driving of the vehicle according to the second target obstacle information.

11. The device according to claim 7, wherein The at least one obstacle information is used to represent obstacle information sensed by a vehicle-mounted sensor; The device further comprises: The second control module is configured to control the driving of the vehicle according to the obstacle information obtained by filtering out the first target obstacle information from the at least one obstacle information.

12. The device according to claim 7, wherein The filtering condition includes at least one of the following: The obstacles represented by the obstacle information are vehicles of predefined models; The obstacle represented by the obstacle information is the ground; The obstacle represented by the obstacle information is a fence; The obstacles represented by the obstacle information are vegetation; as well as The obstacles represented by the obstacle information are other predefined objects.

13. 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 perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images