CN114511840A

CN114511840A - Perception data processing method and device for automatic driving and electronic equipment

Info

Publication number: CN114511840A
Application number: CN202210189936.8A
Authority: CN
Inventors: 司马兵
Original assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Current assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-05-17

Abstract

The disclosure provides a perception data processing method and device for automatic driving, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the fields of automatic driving, autonomous parking, internet of things, intelligent transportation and the like. The specific implementation scheme is as follows: determining obstacle center position information corresponding to each of the sensed at least one obstacle information; for each piece of obstacle central position information, in response to detecting that the position located by the obstacle central position information is located within a predefined area range, determining a filtering condition and target obstacle central position information of which the located position is located within the predefined area range; and in response to detecting that the first target obstacle information corresponding to the target obstacle center position information meets the filtering condition, filtering the first target obstacle information from the at least one obstacle information.

Description

Perception data processing method and device for automatic driving and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to the fields of autonomous driving, autonomous parking, internet of things, and intelligent transportation, and in particular, to a method and an apparatus for processing sensed data of autonomous driving, an electronic device, and a storage medium.

Background

An autonomous vehicle, also known as a robotic vehicle, an autonomous vehicle, or an unmanned vehicle, is a vehicle that is capable of sensing its environment and driving with little or no manual input. Autonomous vehicles incorporate a variety of sensors to sense the surrounding environment, such as radar, lidar, sonar, global positioning systems, odometers, and inertial measurement units. Advanced control systems interpret the sensed information to identify appropriate navigation paths, obstacles, and associated landmarks.

Disclosure of Invention

The disclosure provides a perception data processing method and device for automatic driving, an electronic device and a storage medium.

According to an aspect of the present disclosure, there is provided a perception data processing method of automatic driving, including: determining obstacle center position information corresponding to each of the sensed at least one 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 range, determining a filtering condition and target obstacle center position information of which the located position is within the predefined area range; and in response to detecting that first target obstacle information corresponding to the target obstacle center position information meets the filtering condition, filtering the first target obstacle information from the at least one obstacle information.

According to another aspect of the present disclosure, there is provided a perception data processing apparatus for automatic driving, including: a first determination module for determining obstacle center position information corresponding to each of the sensed at least one obstacle information; a second determination module, configured to determine, for each obstacle center position information, a filtering condition and target obstacle center position information of which the located position is within a predefined area range in response to detecting that the position where the obstacle center position information is located is within the predefined area range; and a filtering module, configured to filter 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 the filtering condition.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the autonomous driving perception data processing method of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the perception data processing method of automatic driving of the present disclosure.

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

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 schematically illustrates an exemplary system architecture to which the perception data processing method and apparatus of automatic driving may be applied, according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a perception data processing method of autonomous driving according to an embodiment of the present disclosure;

fig. 3 schematically shows an overall flowchart of a perception data processing method of automatic driving according to an embodiment of the present disclosure;

fig. 4 schematically shows a block diagram of a perception data processing apparatus for automatic driving according to an embodiment of the present disclosure; and

FIG. 5 illustrates a schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.

In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.

In the driving scene of the automatic driving vehicle, there may be some special obstacles which have no influence on the driving safety of the vehicle or can ensure that the driving of the vehicle is not influenced by the forced planning of the path.

The inventor finds that in the process of implementing the disclosed concept, during the process of running of the automatic driving vehicle under the scene including the special obstacles, the detection and identification of the special obstacles have great challenges. For example, when a special obstacle is identified based on a perception algorithm, there may be a problem of a type identification error or an unstable obstacle boundary identification, so that even if a vehicle perceives the special obstacle, a sudden brake or a sudden brake may occur in order to avoid the obstacle, which may cause poor user experience and reduce the automatic driving passing efficiency. For another example, in some special scenes, such as narrow roads, where some obstacles such as cones are placed at the edges of the roads, and scenes where double yellow lines are arranged on the left sides of the narrow roads and fences are placed on the right sides of the narrow roads, the planning control module at the downstream of the automatic driving vehicle may expand the boundaries of the obstacles, and when the main vehicle runs on the narrow roads where double yellow lines are arranged on the left sides and fences are placed on the right sides, it is necessary to add traffic buffering to the sensed and detected barriers, so that even if the obstacles are identified stably, the vehicle may still be in a standstill. In addition, the perception algorithm has a generalization problem, for example, the laser radar point cloud at the platform looks similar to the point cloud structure presented by the real vehicle from some angles, when the recognition is performed based on the perception algorithm, the platform is recognized as the vehicle, the problem of misrecognition of the perception algorithm can not be well solved by adjusting the parameters in the perception algorithm, and if the related model or parameters are continuously optimized and adjusted, other unnecessary problems may be caused.

The disclosure provides a perception data processing method and device for automatic driving, an electronic device and a storage medium. The perception data processing method for automatic driving comprises the following steps: determining obstacle center position information corresponding to each of the sensed at least one obstacle information; for each piece of obstacle central position information, in response to detecting that the position located by the obstacle central position information is located within a predefined area range, determining a filtering condition and target obstacle central position information of which the located position is located within the predefined area range; and in response to detecting that the first target obstacle information corresponding to the target obstacle center position information meets the filtering condition, filtering the first target obstacle information from the at least one obstacle information.

Fig. 1 schematically illustrates an exemplary system architecture of a perception data processing method and apparatus to which automatic driving may be applied according to an embodiment of the present disclosure.

It should be noted that fig. 1 is only an example of a system architecture 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, and does not mean that the embodiments of the present disclosure may not 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 of automatic driving may be applied may include a terminal device, but the terminal device may implement the method and apparatus for processing perception data of automatic driving provided by the embodiment of the present disclosure without interacting with a server.

As shown in fig. 1, the system architecture 100 according to this embodiment may include an information collecting terminal 101, a network 102, and a server 103. Network 102 is the medium used to provide a communication link between information collecting terminal 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The information collection terminal 101 interacts with the server 103 via the network 102 to receive or transmit information and the like. The information collection terminal 101 is used to collect obstacle sensing information based on a plurality of sampling times, for example.

The server 105 may be a server providing various services, for example, a background processing server (for example only) that processes according to the obstacle sensing information provided by the information collecting terminal 101. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service extensibility in a traditional physical host and a VPS service ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be noted that the perception data processing method for automatic driving provided by the embodiment of the present disclosure may also be generally executed by the server 103. Accordingly, the perception data processing device for automatic driving provided by the embodiment of the present disclosure may be generally disposed in the server 103. The perception data processing method for automatic driving provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 103 and can communicate with the information collecting terminal 101 and/or the server 103. Correspondingly, the perception data processing device for automatic driving provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster that is different from the server 103 and can communicate with the information collecting terminal 101 and/or the server 103.

For example, the information collecting terminal 101 may sense obstacle information, then send the sensed obstacle information to the server 103, determine, by the server 103, obstacle center position information corresponding to each of the at least one piece of sensed obstacle information, determine, for each piece of obstacle center position information, a filtering condition in response to detecting that a position where the obstacle center position information is located is within a predefined area range, and filter, in response to detecting that first target obstacle information corresponding to the obstacle center position information satisfies the filtering condition, the first target obstacle information from the at least one piece of obstacle information. Or the obstacle information is processed by a server or a server cluster capable of communicating with the information acquisition terminal 101 and/or the server 103.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically shows a flowchart of a perception data processing method of automatic driving according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S230.

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

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

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, filtering the first target obstacle information from the at least one obstacle information.

According to an embodiment of the present disclosure, the obstacle information may include information that can be based on the position, shape, size, and the like of all the physical objects sensed by the information collecting device or the sensor device. The physical object may include at least one of a stationary object and a moving object. For example, obstacle information may be used to characterize obstacle information sensed by an onboard sensor so as to be stationary or moving. The obstacle center position information may be determined from the sensed obstacle information and a sensing algorithm. The obstacle center position information may include at least one of two-dimensional position information, three-dimensional position information, and the like.

According to an embodiment of the present disclosure, the predefined area range may include at least one of a planar range, a spatial range, and the like. The predefined area range can be used for defining at least one of an area which does not affect the running process of the vehicle, an area corresponding to an obstacle which does not affect the running process of the vehicle, an area corresponding to the central position of the obstacle which does not affect the running process of the vehicle, other filterable areas and the like. The predefined area range may be determined by first determining a plurality of predefined coordinate points and then determining a polygon from the plurality of predefined coordinate points.

For example, during vehicle travel, obstacles that do not affect vehicle travel may include stationary objects placed in the actual environment. The coordinates of the stationary object in the high-precision map coordinate system can be fixed and do not deviate along with the movement of the vehicle. In addition, the obstacle information transmitted to the downstream planning control module by the vehicle-mounted sensor can be established in a high-precision map coordinate system. Based on this, the position information of at least one of the obstacle information sensed in some scenes and the obstacle information determined based on some perception algorithms may be defined within a specific range of the high-precision map, from which the above-mentioned predefined area range may be determined.

According to an embodiment of the present disclosure, the filtering condition may include at least one of an obstacle represented by the obstacle information being a vehicle of a predefined vehicle type, an obstacle represented by the obstacle information being a ground, an obstacle represented by the obstacle information being a fence, an obstacle represented by the obstacle information being vegetation, and an obstacle represented by the obstacle information being another predefined object, and the like, and may not be limited thereto.

According to the embodiment of the disclosure, both the predefined area range and the filtering condition can be pre-configured in the information acquisition device or the sensor device, and the configuration parameters can be read timely, so that filtering processing of certain obstacles is realized.

For example, an autopilot software system may include a perception module, a decisionThe system comprises a plurality of modules such as a module, a planning module and a control module. Information defining the predefined area range and the filtering condition may be configured inside the perception module. The configuration method can comprise the following steps: firstly, defining related Prot under public directory based on filtering requirement of special barrier_oStructure, Prot_oThe structure may define a data format of the configuration parameter information related to the predefined area range and the filtering condition. Then, adding configuration parameter information in the defined Proto structure to obtain a configuration file comprising the predefined area range and the filtering condition. Proto refers to the writing of an object, which may be referred to as an implicit prototype, an implicit prototype of an object points to a prototype of the constructor that constructed the object, enabling instances to access properties and methods defined in the constructor prototype.

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

According to the embodiment of the disclosure, in the case that the target obstacle center position information of which the located position is located within the predefined area range is detected, the strategy of filtering the first target obstacle information corresponding to the target obstacle center position information based on the filtering condition may be triggered for the obstacle center position information of each obstacle sensed in the vehicle driving process, and the first target obstacle information which does not affect the vehicle driving may be filtered from the detected obstacle information by further judging the other attribute information of the first target obstacle information based on the filtering condition.

By the embodiment of the disclosure, the sensing auxiliary capacity is provided outside the sensing algorithm by combining the predefined area range and the filtering condition, a filtering strategy is realized, the special obstacles in a special scene can be stably filtered, and the accuracy of the obstacle sensing result is improved. In addition, in the automatic driving field, the filtering strategy is reasonably utilized, the vehicle passing efficiency can be improved on the premise of ensuring the safety and reliability of the passing process, and the automatic driving capacity can be effectively improved.

The method shown in fig. 2 is further described below with reference to specific embodiments.

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

According to the embodiment of the disclosure, the obstacles in different scenes can have a tendency characteristic, and based on the scene tendency and the obstacle-related characteristic, the filtering condition can be defined according to different batches of the filtering range. The defining process may also include: first, the Proto structure is defined. Then, based on the Proto structure, configuration parameter information is defined. Then, based on a predefined Proto structure, a plurality of filtering strategies for the obstacle information can be added in combination with the configuration parameter information before the obstacle information is serialized and sent to a downstream planning control module.

For example, a filter _ method of a filtering method may be defined in the common Proto, and the corresponding filtering method may be represented by a number. Such as filtering based on a predefined obstacle type, as indicated by the numeral 0, filtering based on a predefined obstacle subtype, as indicated by the numeral 1, filtering based on a predefined point cloud category, as indicated by the numeral 2, and direct filtering, as indicated by the numeral 9. According to the value of the filter _ method field, different filtering methods can be selected as the filtering conditions to be adopted by selecting different numbers.

It should be noted that, according to the category of the obstacle information, other filtering methods may also be defined, and the corresponding filtering method may be defined in combination with other numbers to facilitate selection.

According to the embodiment of the disclosure, on the basis of the filter _ method field, a filtering array filter _ list can be defined, and the relevant information of the obstacles which can be filtered by the filtering method can be defined in the filtering array. For example, for a filtering method for filtering based on predefined obstacle types, a filtering array of obstacle information related to at least one type of obstacles such as people and vehicles can be defined. For the filtering method based on the predefined obstacle subtype for filtering, obstacle information after further refinement on the basis of the predefined obstacle subtype can be defined, for example, after vehicles are further refined, a filtering array of obstacle information related to at least one type of obstacles such as bicycles, cars, trucks, tricycles and the like can be defined. For a filtering method for filtering based on predefined point cloud categories, a filtering array of point cloud information representing at least one of ground, vegetation, fences, other unknown information and the like can be defined. The direct filtering characterization can directly filter out the obstacle of which the position located by the obstacle center position information is within the range of the predefined area.

According to the embodiment of the disclosure, when a user selects a certain filtering method, only certain kinds of obstacle information corresponding to the filtering method can be filtered. For example, when the user can filter the obstacle information based on the predefined obstacle type, only the obstacle information of the types of pedestrians, vehicles and the like can be filtered, and other obstacle information is reserved. When the user selects to filter based on the predefined point cloud category, only the information of obstacles such as ground, vegetation, fences and the like can be filtered, and the information of other obstacles and the like is reserved.

By the embodiment of the disclosure, the filtering condition is defined in a mode of defining a plurality of filtering sub-conditions in batch, and the configuration of the relevant information of the filtering condition can be simplified. By selecting the target filtering sub-condition as the filtering condition to be adopted, unnecessary safety risks caused by excessive filtering obstacle information can be avoided.

According to an embodiment of the present disclosure, to determine the predefined area range and the filtering condition, the perception data processing method of the automatic driving may further include: in response to detecting that the vehicle is driven into the target area, a predefined filtering condition associated with the target area is obtained. And determining a target predefined area range and a target filtering condition for filtering the obstacle information sensed by the vehicle-mounted sensor related to the vehicle according to the predefined filtering condition.

According to the embodiment of the disclosure, the predefined area range and the filtering condition can be configured in advance in a system module having a communication relationship with the information acquisition device or the sensor device, such as can be configured inside an automatic driving software system. A Patch node may be set inside the autopilot software system and used for sending various configuration parameter information, such as information of predefined area range, filtering condition, and the like, to other modules. Patch may refer to a memory Patch, a file Patch, etc., and may also be a computer command program that may modify a file application.

According to the embodiment of the disclosure, the effective configuration parameter information such as the predefined area range and the filtering condition can be set based on the cybertron framework. The cybertron is a scheduling framework of each algorithm module based on an operating system layer and can be responsible for message communication, resource allocation, operation scheduling and the like among the modules. The Patch module may provide a fixed interface for enabling configuration parameter information related to a specific area to be sent out when the vehicle travels to the area. The perception module can subscribe the needed configuration parameter information and set the callback function. In the case where the Patch module sends configuration parameter information out, the awareness module may receive the relevant configuration parameter information. Then, based on the callback function, the predefined relevant parameter value in the relevant configuration parameter information is obtained, and the target predefined area range and the target filtering condition related to the specific area are obtained. The target predefined area range and the target filtering condition can be assigned to the perception filtering strategy, and based on the perception filtering strategy, the obstacle information detected by the vehicle in the specific area can be processed.

It should be noted that, when other modules such as the Patch module and the perception module need to perform message interaction, the communication mode of the node parameters in the ROS (Robot Operating System) System may also be used.

Through the embodiment of the disclosure, the information interaction among the modules is realized by setting the Patch module, and the consistency of filtering strategy processing in the system can be effectively ensured. In addition, according to the area that the vehicle drives into, obtain predefined regional scope and filtering condition of corresponding area, can effectively reduce the data bulk in the information transmission process. And the maintenance and management are facilitated aiming at the predefined area range and the filtering condition configured by the subareas. And aiming at the determined area, the information processing is carried out by combining the determined predefined area range and the filtering condition, and the information processing efficiency can be effectively improved.

According to an embodiment of the present disclosure, the perception data processing method of automatic driving may further include: and determining second target obstacle information corresponding to the obstacle center position information in response to detecting that the position located by the obstacle center position information is outside the predefined area range. And controlling the vehicle to run according to the second target obstacle information.

According to the embodiment of the disclosure, when the vehicle runs into a specific area, the Patch module may send the defined configuration parameter information such as the predefined area range and the filtering condition, and the configuration parameter information is acquired and loaded by the perception module. The sensing module can cycle through the obstacle information of each obstacle sensed by the vehicle-mounted sensor and judge whether the center position of the obstacle is located in the predefined area range. If not, second target obstacle information may be determined. When the second target obstacle information is detected, the filtering strategy can be skipped, and the output label of the second target obstacle information is set to true, so that the vehicle can be controlled to run according to the second target obstacle information.

Through the embodiment of the disclosure, the obstacle information which influences the vehicle running can be obtained based on the screening of the predefined area range, and the problem of unstable detection and identification of the sensing algorithm on the special obstacle can be effectively solved. The vehicle is controlled to run according to the screened obstacle information, and the traffic efficiency and the automatic driving capability of the vehicle in a special scene can be effectively improved.

According to an embodiment of the present disclosure, the perception data processing method of automatic driving may further include: and controlling the vehicle to run according to the obstacle information after the first target obstacle information is filtered out from the at least one obstacle information.

According to the embodiment of the disclosure, for the obstacle information of which the center position of the obstacle is located in the predefined area range, that is, the first target obstacle information, the corresponding filtering method may be selected based on the value of the predefined filter _ method field. Then, it may be determined whether the first target obstacle information satisfies the selected filtering condition based on the filtering condition defined in the filter _ list corresponding to the selected filtering method. In the case where the first target obstacle information satisfies the selected filtering condition, the output label of the first target obstacle information may be set to false. In a case where the first target obstacle information does not satisfy the selected filtering condition, the output tag of the first target obstacle information may be set to true.

According to the embodiment of the disclosure, only the obstacle information with the output tag of true can be serialized and sent to the downstream planning control module to control the running of the vehicle. And filtering the obstacle information with the false output label to finish filtering the special obstacle information in the sensing module, and not outputting the special obstacle information to a downstream planning control module so as to avoid sudden braking or inching of the vehicle caused by special scenes or special obstacles.

Through the embodiment of the disclosure, the barrier information which has no influence on the vehicle running can be filtered based on the predefined area range and the filtering condition, the running of the vehicle is controlled according to the residual barrier information after filtering treatment, and the traffic efficiency and the automatic driving capability of the vehicle in a special scene can be effectively improved.

According to the embodiment of the disclosure, a boolean policy switch may be added to the Proto structure, and when the switch is turned off, it may be characterized that the filtering policy is not turned on. The switch may be manually turned on in a configuration file when it is desired to use the filtering strategy in a particular scenario.

Through the embodiment of the disclosure, the robustness of code logic can be improved, and filtering strategies can be compatible with diversified application scenes.

Fig. 3 schematically shows an overall flowchart of a perception data processing method of automatic driving according to an embodiment of the present disclosure.

As shown in fig. 3, the method includes operations S310 to S360.

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

Is the center of the obstacle located within a predetermined area in operation S320? If yes, only operation S330 is needed; if not, operation S360 is performed.

In operation S330, different filtering conditions are selected based on the value of the filter _ method field.

In operation S340, whether the obstacle information satisfies a selected filtering condition? If yes, perform operation S350; if not, operation S360 is performed.

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

In operation S360, the obstacle information is stored.

According to an embodiment of the present disclosure, the sensing module may sense at least one obstacle information based on a sensing algorithm. Each piece of obstacle information may correspond to obstacle center position information representing a center position of the obstacle. The predefined area range and the filtering condition can be predefined and stored in the sensing module or other systems having a communication relationship with the sensing module, such as a vehicle-mounted system. The Patch module can be arranged in the system and used for establishing communication between different modules, so that the filtering strategies of the modules in the system are kept consistent.

According to an embodiment of the present disclosure, for each sensed obstacle information, it may be determined whether a position at which an obstacle center corresponding to the obstacle information is located is within a predefined area range. If so, a filtering condition can be selected to further filter the obstacle information. And if the obstacle information is determined to meet the selected filtering condition, the obstacle can be filtered, and the obstacle is filtered. And if the obstacle information is determined not to meet the selected filtering condition, the obstacle is characterized not to be filtered, and the obstacle is stored. And if the center of the obstacle corresponding to the obstacle information is determined to be located outside the range of the predefined area, the obstacle is characterized not to be filtered, and the obstacle is stored. The stored obstacle information may be input to the planning control module for further processing. For example, the running of the vehicle or the like may be controlled based on the stored obstacle information.

Fig. 4 schematically shows a block diagram of a perception data processing apparatus for automatic driving according to an embodiment of the present disclosure.

As shown in fig. 4, the sensing data processing apparatus 400 for automatic driving includes a first determining module 410, a second determining module 420, and a filtering module 430.

A first determining module 410 for determining obstacle center position information corresponding to each of the sensed at least one obstacle information.

And a second determining module 420, configured to determine, for each obstacle center position information, a filtering condition and target obstacle center position information of which the located position is within the predefined area range in response to detecting that the located position of the obstacle center position information is within the predefined area range.

The filtering module 430 is configured to filter 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.

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

A determining unit, configured to determine a target filtering sub-condition as a filtering condition in response to receiving a selection operation for the target filtering sub-condition from the plurality of filtering sub-conditions.

According to the embodiment of the disclosure, the perception data processing device for automatic driving further comprises an obtaining module and a third determining module.

The acquisition module is used for responding to the detection that the vehicle runs into the target area, and acquiring the predefined filtering condition related to the target area.

And the third determination module is used for determining a target predefined area range and a target filtering condition for filtering the obstacle information sensed by the vehicle-mounted sensor related to the vehicle according to the predefined filtering condition.

According to an embodiment of the present disclosure, at least one obstacle information is used to characterize the obstacle information sensed by the onboard sensor. The perception data processing device for automatic driving further comprises a fourth determination module and a first control module.

And the fourth determination module is used for determining second target obstacle information corresponding to the obstacle center position information in response to detecting that the position located by the obstacle center position information is located outside the range of the predefined area.

And the first control module is used for controlling the running of the vehicle according to the second target obstacle information.

According to an embodiment of the present disclosure, at least one obstacle information is used to characterize the obstacle information sensed by the onboard sensor. The perception data processing device for automatic driving further comprises a second control module.

And the second control module is used for controlling the vehicle to run according to the obstacle information in the at least one piece of obstacle information after the first target obstacle information is filtered.

According to an embodiment of the present disclosure, the filtering condition includes at least one of: the obstacle represented by the obstacle information is a vehicle of a predefined vehicle type, 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.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the autonomous driving perception data processing method of the present disclosure.

According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the perception data processing method of automatic driving of the present disclosure.

According to an embodiment of the present disclosure, a computer program product comprising a computer program which, when executed by a processor, implements the perception data processing method of autopilot of the present disclosure.

FIG. 5 illustrates a schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the device 500 comprises a computing unit 501 which may perform various suitable 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. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

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

The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having 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 dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as the perception data processing method of the automatic driving. For example, in some embodiments, the perception data processing method of autonomous driving may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may 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 above-described perception data processing method of the automatic driving may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured in any other suitable way (e.g., by means of firmware) to perform the perception data processing method of autonomous driving.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, 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 may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, 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: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or in a sequence, or may be executed in a different sequence, and the present disclosure is not limited herein as long as the desired result of the technical solution of the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A perception data processing method for automatic driving comprises the following steps:

determining obstacle center position information corresponding to each of the sensed at least one 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 range, determining a filtering condition and target obstacle center position information of which the located position is within the predefined area range; 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 obstacle information.

2. The method of claim 1, wherein the filtering condition comprises a plurality of filtering sub-conditions;

the determining the filtering condition comprises:

in response to receiving a selection operation for a target filtering sub-condition into a plurality of filtering sub-conditions, determining the target filtering sub-condition as the filtering condition.

3. The method of claim 1, further comprising:

in response to detecting that a vehicle is driven into a target area, acquiring a predefined filtering condition related to the target area; and

and determining a target predefined area range and a target filtering condition for filtering the obstacle information sensed by the vehicle-mounted sensor related to the vehicle according to the predefined filtering condition.

4. The method of claim 1, wherein the at least one obstacle information is used to characterize obstacle information sensed by an onboard sensor;

the method further comprises the following steps:

in response to detecting that the position located by the obstacle center position information is outside the predefined area range, determining second target obstacle information corresponding to the obstacle center position information; and

and controlling the running of the vehicle according to the second target obstacle information.

5. The method of claim 1, wherein the at least one obstacle information is used to characterize obstacle information sensed by an onboard sensor;

the method further comprises the following steps:

and controlling the vehicle to run according to the obstacle information obtained after the first target obstacle information is filtered out from the at least one obstacle information.

6. The method of claim 1, wherein the filtering condition comprises at least one of:

the obstacle represented by the obstacle information is a vehicle of a predefined vehicle type;

the obstacle represented by the obstacle information is the ground;

the barrier represented by the barrier information is a fence;

the obstacle represented by the obstacle information is vegetation; and

the obstacle characterized by the obstacle information is another predefined object.

7. An automatic driving perception data processing apparatus, comprising:

a first determination module for determining obstacle center position information corresponding to each of the sensed at least one obstacle information;

a second determination module, configured to determine, for each obstacle center position information, a filtering condition and target obstacle center position information of which the located position is within a predefined area range in response to detecting that the position where the obstacle center position information is located is within the predefined area range; and

and the filtering module is used for filtering 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 meets the filtering condition.

8. The apparatus of claim 7, wherein the filtering condition comprises a plurality of filtering sub-conditions;

the second determining module includes:

a determining unit, configured to determine a target filtering sub-condition of a plurality of filtering sub-conditions as the filtering condition in response to receiving a selection operation for the target filtering sub-condition.

9. The apparatus of claim 7, further comprising:

the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for responding to the detection that a vehicle runs into a target area and acquiring a predefined filtering condition related to the target area; and

and the third determining module is used for determining a target predefined area range and a target filtering condition for filtering the obstacle information sensed by the vehicle-mounted sensor related to the vehicle according to the predefined filtering condition.

10. The apparatus of claim 7, wherein the at least one obstacle information is used to characterize obstacle information sensed by an onboard sensor;

the device further comprises:

a fourth determination module, configured to determine, in response to detecting that the position where the obstacle center position information is located is outside the predefined area range, second target obstacle information corresponding to the obstacle center position information; and

11. The apparatus of claim 7, wherein the at least one obstacle information is used to characterize obstacle information sensed by an onboard sensor;

the device further comprises:

12. The apparatus of claim 7, wherein the filtering condition comprises at least one of:

the obstacle represented by the obstacle information is the ground;

the barrier represented by the barrier information is a fence;

the obstacle represented by the obstacle information is vegetation; and

13. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.

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