Perception method, device and system

Abstract

The invention provides a sensing method, device and system. The sensing device obtains a first feature model corresponding to a first area through which the intelligent driving equipment needs to pass, the first feature model is one of a plurality of feature models, and different feature models in the plurality of feature models are used for sensing feature obstacles in different areas. The sensing device senses a first obstacle set in the first area according to the first feature model. The method provided by the invention can be applied to automatic driving vehicles such as intelligent vehicles and electric vehicles, and can reduce the conditions of missing detection and false detection caused by insufficient sensing capability of a sensing algorithm, thereby improving the driving safety.

Description

Perception method, device and system Technical Field

[0001] The present application relates to the field of autonomous driving, and more specifically, to perception methods, devices, and systems. Background Art

[0002] Autonomous driving technology has become a growing research hotspot. However, road conditions vary significantly across regions (for example, wildlife is rare on urban roads, but likely on mountain roads). Even the same perception algorithm can have significant differences in its ability to detect animals in different areas. This can lead to perception biases in the perception system when a vehicle is driving on unfamiliar roads (for example, false or missed obstacle detections), which can compromise the safety of the autonomous driving system.

[0003] Therefore, how to reduce the perception deviation of the autonomous driving system on roads in different areas to improve the perception accuracy of the autonomous driving system in different areas and thus improve vehicle driving safety has become an urgent problem to be solved.

[0004] Summary of the Invention

[0005] The present application provides a perception method, device, and system that can reduce the perception deviation of intelligent driving equipment on roads in different areas, improve the perception accuracy of intelligent driving equipment for characteristic obstacles in different areas, and thus improve driving safety.

[0006] The intelligent driving devices involved in this application may include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, the intelligent driving device can be a vehicle, which is a vehicle in the broad sense, and can be a transportation tool (such as a commercial vehicle, a passenger car, a motorcycle, a flying car, a train, etc.), an industrial vehicle (such as a forklift, a trailer, a tractor, etc.), an engineering vehicle (such as an excavator, a bulldozer, a crane, etc.), agricultural equipment (such as a mower, a harvester, etc.), amusement equipment, a toy vehicle, etc. This application does not specifically limit the type of vehicle. For another example, the intelligent driving device can be a vehicle such as an airplane or a ship.

[0007] In a first aspect, a perception method is provided, which can be executed by an intelligent driving device; or, it can also be executed by a chip or circuit used for an intelligent driving device; or, when the intelligent driving device is a vehicle, it can also be executed by the vehicle's mobile data center (MDC), or it can also be executed by the vehicle's electronic control unit (ECU), such as an on-board unit (OBU) or a control component in a telematics box (T-Box), which is not limited in this application.

[0008] The method includes: obtaining a first feature model corresponding to a first area that an intelligent driving device needs to pass through, where the first feature model is one of multiple feature models, and different feature models among the multiple feature models are used to perceive feature obstacles in different areas; and perceiving a first obstacle set in the first area based on the first feature model.

[0009] In some possible implementations, when it is determined that the intelligent driving device is about to reach or has reached the first area, the first feature model is obtained.

[0010] In the above technical solution, when the intelligent driving device is about to or already in a first area, by acquiring a first feature model corresponding to the first area, characteristic obstacles in the first area can be identified, helping to improve the intelligent driving device's perception accuracy in that area. Furthermore, when the intelligent driving device travels to different areas, it can perceive different characteristic obstacles corresponding to different areas by acquiring the feature models corresponding to those areas. This can reduce missed detections and false detections caused by insufficient perception capabilities of the perception algorithm, thereby improving driving safety.

[0011] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: perceiving a second obstacle set in the first area according to a second feature model of the intelligent driving device; controlling the intelligent driving device to travel according to a union of the first obstacle set and the second obstacle set within a first preset range of the intelligent driving device; controlling the intelligent driving device to travel according to the first obstacle set outside the first preset range and within a second preset range of the intelligent driving device; and controlling the intelligent driving device to travel according to a third obstacle set outside the second preset range, wherein the third obstacle set includes obstacles common to the first obstacle set and the second obstacle set.

[0012] Exemplarily, the first feature model is trained based on data from a first area, which includes information about characteristic obstacles in that area. Therefore, the first feature model can detect characteristic obstacles in that area. The second feature model is the intelligent driving device's own feature model. This second feature model can be trained based on data from an area where the intelligent driving device frequently travels, or it can be trained based on sensor data acquired during historical travel by one or more intelligent driving devices. It should be understood that the areas where the intelligent driving device frequently travels may not include the first area. Furthermore, the second feature model can detect obstacles on roads where the intelligent driving device frequently travels; alternatively, the second feature model can detect obstacles common to multiple roads, such as small cars, bicycles, and motorcycles. It should be understood that the historical travel history of one or more intelligent driving devices may include travel through the first area, but due to insufficient data, the second feature model may not be able to accurately detect characteristic obstacles in that first area.

[0013] Therefore, perceiving obstacles in the first area based on the first characteristic model can improve the accuracy of perceiving characteristic obstacles in the first area.

[0014] For example, the first preset range may be a range of 30 meters from the intelligent driving device, and the second preset range may be a range of 60 meters from the intelligent driving device. Alternatively, the first preset range and the second preset range may also be other values.

[0015] Specifically, within a first preset range of the intelligent driving device, controlling the intelligent driving device to travel according to the union of the first obstacle set and the second obstacle set may be performed by controlling the intelligent driving device to travel according to obstacles within the first preset range from the union of the first obstacle set and the second obstacle set. Outside the first preset range but within a second preset range of the intelligent driving device, controlling the intelligent driving device to travel according to the first obstacle set may be performed by controlling the intelligent driving device to travel according to obstacles within the first obstacle set that are outside the first preset range and within the second preset range. Outside the second preset range of the intelligent driving device, controlling the intelligent driving device to travel according to the third obstacle set may be performed by controlling the intelligent driving device to travel according to obstacles within the third obstacle set that are outside the second preset range.

[0016] In the above technical solution, different obstacle sets are used to plan the driving path of the intelligent driving device for different preset ranges. For example, within a range close to the intelligent driving device, path planning is performed based on the obstacles in the union of the first and second obstacle sets (which may be larger in number). Meanwhile, within areas farther from the intelligent driving device, path planning is performed using only the obstacles shared by the first and second obstacle sets (which may be smaller in number). Because the intelligent driving device may be in motion during the path planning process, the above method ensures that the number of obstacles considered transitions from zero to a smaller number, and then to a larger number, as the path planning progresses from farther to closer. This helps improve the smoothness of the planning algorithm, reduces unnecessary computing power waste, and helps save energy.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: determining a first perception level based on the first obstacle set and the second obstacle set, the first perception level indicating the perception accuracy of the intelligent driving device when passing through the first area.

[0018] In the above technical solution, by evaluating the perception level of the intelligent driving device in the first area, the next time the intelligent driving device drives to the first area, the perception algorithm required for obstacle recognition can be determined according to the first perception level.

[0019] In combination with the first aspect, in some implementations of the first aspect, the method further includes: sending identification information of the first area and information of the first perception level to a server, so that the server updates the perception level corresponding to the first area.

[0020] In the above technical solution, sending the information of the first perception level to the server can enable the server to update the perception level corresponding to the first area, thereby enabling the server to indicate more accurate perception accuracy to the intelligent driving equipment that needs to pass through the first area, reducing safety accidents caused by misjudgment of the perception level of the first area, and helping to improve driving safety.

[0021] In combination with the first aspect, in certain implementations of the first aspect, obtaining the first feature model corresponding to the first area where the intelligent driving device is located includes: receiving information of the first feature model sent by a roadside device in the first area, and the roadside device is located at the entrance of the first area.

[0022] In this technical solution, the intelligent driving device obtains information about the first feature model from the roadside device, eliminating the need for the intelligent driving device to store the first feature model, thus conserving storage space. Furthermore, since the roadside device is deployed at the entrance to the first area, there's no need to deploy multiple roadside devices to cover the entire road, nor is there a need for perception-based roadside equipment, significantly reducing the cost of deploying roadside equipment.

[0023] In combination with the first aspect, in certain implementations of the first aspect, before receiving the information of the first feature model sent by the roadside equipment in the first area, the method also includes: sending information of the sensor of the intelligent driving device to the roadside equipment; receiving the information of the first feature model sent by the roadside equipment in the first area includes: receiving the information of the first feature model sent by the roadside equipment based on the information of the sensor.

[0024] Optionally, the sensor information may include information about the sensor type; or, the sensor information may also be other information that can indicate the sensor type. In one example, taking an intelligent driving device as an example, the sensor information may include a vehicle identification number (VIN). In some possible implementations, the roadside equipment may determine the type of sensor used by the vehicle based on the VIN code.

[0025] In the above technical solution, the information of the first feature model is sent by the receiving roadside device based on the information of the sensor, so that the first feature model is determined based on the information of the sensor of the intelligent driving device, which can ensure the compatibility of the first feature model with the sensor data of the intelligent driving device.

[0026] In combination with the first aspect, in certain implementations of the first aspect, the sending of the sensor information of the intelligent driving device to the roadside device includes: receiving information of a third perception level sent by the roadside device, the third perception level indicating the recommended perception accuracy corresponding to the first area; when the perception accuracy of the second perception level is less than the perception accuracy of the third perception level, sending the sensor information of the intelligent driving device to the roadside device, wherein the second perception level indicates the current perception accuracy corresponding to the first area or the default perception accuracy of the intelligent driving device.

[0027] In some possible implementations, the second perception level indicates the current perception accuracy corresponding to the first area. When the current perception accuracy corresponding to the first area is greater than or equal to the recommended perception accuracy corresponding to the first area, the intelligent driving device determines the feature model based on the perception accuracy indicated by the second perception level, and then performs obstacle identification.

[0028] In the above technical solution, when the recommended perception accuracy is greater than the default perception accuracy of the intelligent driving device or the current perception accuracy corresponding to the first area, obstacle perception can be performed based on the first feature model obtained from the roadside device, which helps to reduce false detections and missed detections caused by insufficient perception accuracy and helps to improve driving safety.

[0029] In combination with the first aspect, in certain implementations of the first aspect, when the second perception level indicates the current perception accuracy corresponding to the first area, the method also includes: sending identification information of the first area to the server; and receiving information of the second perception level sent by the server based on the identification information.

[0030] In some possible implementations, the second perception level sent by the server is determined based on the perception levels reported by multiple intelligent driving devices traveling in the first area. For example, among the perception levels reported by multiple intelligent driving devices, the most commonly used perception level is determined to be the second perception level.

[0031] In the above technical solution, the perception accuracy can be determined based on the perception level information obtained from the server, and then it can be determined whether it is necessary to obtain the first feature model from the roadside equipment, which helps to reduce safety accidents caused by misjudgment of the perception level and helps to improve driving safety.

[0032] A second aspect provides a perception method that can be performed by a roadside unit (RSU); alternatively, it can be performed by a chip or circuit used in the RSU. In this application, the RSU can communicate with the intelligent driving device and may include, for example, a high-performance computing unit required for data processing. In some possible implementations, the RSU may also include perception devices such as cameras, millimeter-wave radar, and lidar.

[0033] The method includes: receiving information from a sensor of an intelligent driving device that needs to pass through a first area, sent by the intelligent driving device; determining a first feature model based on the sensor information, the first feature model being one of a plurality of feature models, different feature models among the plurality of feature models being used to perceive feature obstacles in different areas, the first feature model corresponding to the first area; and sending information from the first feature model to the intelligent driving device, so that the intelligent driving device perceives a first obstacle set in the first area based on the first feature model.

[0034] In the above technical solution, by sending the first feature model corresponding to the first area to the intelligent driving device that needs to pass through the first area, it helps the intelligent driving device to identify the characteristic obstacles in the first area based on the first feature model, helps to improve the perception accuracy of the intelligent driving device in the area, and can reduce the missed detection and false detection caused by insufficient perception ability of the perception algorithm, thereby improving driving safety.

[0035] In combination with the second aspect, in certain implementations of the second aspect, before receiving the information of the sensor of the intelligent driving device that needs to be sent by the intelligent driving device in the first area, the method also includes: sending perception level information to the intelligent driving device, where the perception level indicates the recommended perception accuracy corresponding to the first area.

[0036] In the above technical solution, the roadside equipment can directly send the third perception level information to the intelligent driving device without the need for a request from the intelligent driving device, which helps to save signaling.

[0037] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: sending identification information of the first area to the intelligent driving device.

[0038] In the above technical solution, sending the identification information of the first area to the intelligent driving device helps the intelligent driving device determine the area where it is located, and then determines whether it needs to obtain the first feature model, which helps to improve driving safety.

[0039] In a third aspect, a perception device is provided, which includes an acquisition unit and a first processing unit, wherein the acquisition unit is used to: acquire a first feature model corresponding to a first area that the intelligent driving device needs to pass through, the first feature model being one of multiple feature models, and different feature models among the multiple feature models are used to perceive characteristic obstacles in different areas; the first processing unit is used to: perceive a first obstacle set in the first area based on the first feature model.

[0040] In combination with the third aspect, in certain implementations of the third aspect, the device further includes a second processing unit and a third processing unit, wherein the second processing unit is used to: perceive a second obstacle set in the first area according to a second feature model of the intelligent driving device; the third processing unit is used to: within a first preset range of the intelligent driving device, control the intelligent driving device to travel according to the union of the first obstacle set and the second obstacle set; outside the first preset range and within a second preset range of the intelligent driving device, control the intelligent driving device to travel according to the first obstacle set; and outside the second preset range, control the intelligent driving device to travel according to a third obstacle set, wherein the third obstacle set includes obstacles common to the first obstacle set and the second obstacle set.

[0041] In combination with the third aspect, in certain implementations of the third aspect, the device also includes a fourth processing unit, which is used to: determine a first perception level based on the first obstacle set and the second obstacle set, and the first perception level indicates the perception accuracy of the intelligent driving device when passing through the first area.

[0042] In combination with the third aspect, in certain implementations of the third aspect, the device further includes a first communication unit, which is used to: send identification information of the first area and information of the first perception level to the server, so that the server updates the perception level corresponding to the first area.

[0043] In combination with the third aspect, in certain implementations of the third aspect, the device also includes a second communication unit, and the acquisition unit is used to: obtain information of the first feature model sent by the roadside equipment of the first area and received by the second communication unit, and the roadside equipment is located at the entrance of the first area.

[0044] In combination with the third aspect, in certain implementations of the third aspect, the second communication unit is further used to: send sensor information of the intelligent driving device to the roadside device; and receive information of the first feature model sent by the roadside device based on the sensor information.

[0045] In combination with the third aspect, in certain implementations of the third aspect, the second communication unit is also used to: receive information on a third perception level sent by the roadside device, the third perception level indicating the recommended perception accuracy corresponding to the first area; when the perception accuracy of the second perception level is less than the perception accuracy of the third perception level, send information on the sensor of the intelligent driving device to the roadside device, wherein the second perception level indicates the current perception accuracy corresponding to the first area or the default perception accuracy of the intelligent driving device.

[0046] In combination with the third aspect, in certain implementations of the third aspect, when the second perception level indicates the current perception accuracy corresponding to the first area, the first communication unit is also used to: send identification information of the first area to the server; and receive information on the second perception level sent by the server based on the identification information.

[0047] In a fourth aspect, a perception device is provided, which includes a first communication unit and a determination unit, wherein the first communication unit is used to: receive information from a sensor of an intelligent driving device that needs to pass through a first area and is sent by the intelligent driving device; the determination unit is used to: determine a first feature model based on the sensor information, the first feature model being one of a plurality of feature models, different feature models among the plurality of feature models being used to perceive feature obstacles in different areas, and the first feature model corresponding to the first area; the first communication unit is also used to: send information of the first feature model to the intelligent driving device, so that the intelligent driving device perceives a first obstacle set in the first area based on the first feature model.

[0048] In combination with the fourth aspect, in certain implementations of the fourth aspect, the device also includes a second communication unit, which is used to: send perception level information to the intelligent driving device before the first communication unit receives information about the sensor of the intelligent driving device sent by the intelligent driving device, and the perception level indicates the recommended perception accuracy corresponding to the first area.

[0049] In combination with the fourth aspect, in certain implementations of the fourth aspect, the apparatus further includes a third communication unit, which is further used to: send identification information of the first area to the intelligent driving device.

[0050] In a fifth aspect, a perception device is provided, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method in any possible implementation of the first aspect or the second aspect.

[0051] Optionally, the above-mentioned processing unit may include at least one processor, and the above-mentioned storage unit may be a memory, wherein the memory may be a storage unit within the chip (for example, a register, a cache, etc.), or a storage unit located outside the chip within the intelligent driving device (for example, a read-only memory, a random access memory, etc.).

[0052] In a sixth aspect, an intelligent driving device is provided, which includes the device in any one of the implementation methods of the third aspect above.

[0053] In combination with the sixth aspect, in some implementations of the sixth aspect, the intelligent driving device is a vehicle.

[0054] In a seventh aspect, a roadside device is provided, which includes the device in any one of the implementation methods of the fourth aspect.

[0055] In the eighth aspect, a perception system is provided, which includes the device described in any one of the third aspects and the device described in any one of the fourth aspects, or includes the intelligent driving equipment described in any one of the sixth aspects and the roadside equipment described in any one of the seventh aspects.

[0056] In combination with the eighth aspect, in certain implementations of the eighth aspect, the perception system may further include a server, which is used to: receive identification information of the first area that needs to be sent by an intelligent driving device in the first area; and send information of a second perception level to the intelligent driving device based on the identification information, where the second perception level indicates a current perception accuracy corresponding to the first area.

[0057] In a ninth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in any one of the possible implementations of the first or second aspect.

[0058] It should be noted that the above-mentioned computer program code may be stored in whole or in part on a first storage medium, wherein the first storage medium may be packaged together with the processor or separately from the processor.

[0059] In a tenth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores instructions. When the instructions are executed by a processor, the processor implements the method in any possible implementation of the first aspect or the second aspect.

[0060] In an eleventh aspect, a chip is provided, which includes a circuit for executing the method in any possible implementation of the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] FIG1 is a schematic diagram of a scenario in which a vehicle perceives an obstacle;

[0062] FIG2 is a functional block diagram of an intelligent driving device provided in an embodiment of the present application;

[0063] FIG3 is a schematic block diagram of a perception system architecture provided in an embodiment of the present application;

[0064] FIG4 is a schematic diagram of an application scenario of the perception method provided in an embodiment of the present application;

[0065] FIG5 is a schematic flow chart of a sensing method provided in an embodiment of the present application;

[0066] FIG6 is a schematic flow chart of a sensing method according to an embodiment of the present application;

[0067] FIG7 is a schematic flow chart of a sensing method according to an embodiment of the present application;

[0068] FIG8 is a schematic diagram of an obstacle set provided in an embodiment of the present application;

[0069] FIG9 is a schematic diagram of a scenario in which obstacles are determined according to a preset range according to an embodiment of the present application;

[0070] FIG10 is a schematic block diagram of a sensing device provided in an embodiment of the present application;

[0071] FIG11 is a schematic block diagram of a sensing device provided in an embodiment of the present application;

[0072] FIG12 is a schematic block diagram of a sensing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0073] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" refers to one or more, and "more than one" refers to two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0074] In the embodiments of this application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity, or content of the described objects. The use of prefixes such as ordinal numbers in the embodiments of this application to distinguish description objects does not constitute a limitation on the described objects. For a statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0075] With the development of autonomous driving technology, developers are increasingly focusing on the accuracy of a vehicle's perception of surrounding obstacles to ensure driving safety. Under current technology, while driving, a vehicle processes sensor data (or sensor data) acquired by its perception system to obtain information about surrounding obstacles, and then plans its route based on this information. To improve the accuracy of a vehicle's perception of road information, the perception data from roadside equipment (ROE) can be combined with the vehicle's perception data to determine surrounding obstacle information. As shown in Figure 1, while driving on a road, a vehicle can exchange information with RSE (or roadside infrastructure) through vehicle-to-infrastructure (V2I) communication. RSE can be located adjacent to the road and acquire perception data within the perception device's detection range (as shown in Figure 1). Because the detection range of RSEs is relatively limited, multiple RSEs are required to cover the entire road.

[0076] The above technical solution, on the one hand, relies on perception data from multiple roadside devices to improve the accuracy of obstacle perception around the vehicle, which increases the cost of promoting and popularizing autonomous driving technology. On the other hand, when the vehicle combines the perception data from the roadside devices with the vehicle's perception data to determine obstacle information, it still uses the vehicle's perception algorithm, which is generally trained based on perception data from areas where the vehicle frequently travels. This can lead to perception bias when the vehicle is driving on unfamiliar roads. For example, when a vehicle that frequently drives on urban roads drives on mountain roads, the perception algorithm may make false or missed detections of obstacles, such as wild animals, because it has not been trained on mountain road data. In the former case (i.e., false detection), the movement speed or path of obstacles (such as falsely detected wild animals) may be incorrectly predicted during subsequent vehicle route planning, resulting in an unsafe planned vehicle route, such as a collision with the obstacle. In the latter case (i.e., missed detection), the impact of obstacles on the vehicle may be completely ignored during route planning, seriously affecting driving safety.

[0077] In view of this, the embodiments of the present application provide a perception method, apparatus, and system. When an intelligent driving device (such as a vehicle) travels to a certain area, it can obtain a feature model corresponding to the area (such as the first feature model described below). Because the feature model is trained based on data from the area, it can perceive characteristic obstacles in the area based on the feature model. This can reduce the perception deviation of the intelligent driving device on roads in different areas, improve the perception accuracy of the intelligent driving device in different areas, and thus improve driving safety. The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0078] Figure 2 is a functional block diagram of an intelligent driving device 100 provided in an embodiment of the present application. The intelligent driving device 100 may include a perception system 120 and a computing platform 150, wherein the perception system 120 may include several sensors for sensing information about the environment surrounding the intelligent driving device 100. For example, the perception system 120 may include a positioning system, which may be a global positioning system (GPS), a Beidou system, or other positioning systems. The perception system 120 may include one or more of an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0079] Some or all functions of the intelligent driving device 100 can be controlled by a computing platform 150. The computing platform 150 may include processors 151 to 15n (n is a positive integer). A processor is a circuit capable of processing signals. In one implementation, the processor can be a circuit capable of reading and executing instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions, and some or all of the processors 151 to 15n may call the instructions in the memory to implement corresponding functions.

[0080] Exemplarily, the computing platform 150 may include at least one of an MDC, a vehicle domain controller (VDC), and a chassis domain controller (CDC); or may include other computing platforms, such as an in-car application-server (ICAS) controller, a body domain controller (BDC), a special equipment system (SAS), a media graphics unit (MGU), a body super core (BSC), an ADAS super core, etc., which is not limited in this application. The ICAS may include at least one of the following: a vehicle control server ICAS1, an intelligent driving server ICAS2, an intelligent cockpit server ICAS3, and an infotainment server ICAS4.

[0081] The intelligent driving device 100 may include an advanced driving assistant system (ADAS). The ADAS uses multiple sensors in the perception system 120 (including but not limited to: lidar, millimeter-wave radar, camera device, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the surroundings of the intelligent driving device, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, intelligent driving device positioning, path planning, driver monitoring / reminders, etc., thereby improving the safety, automation and comfort of the intelligent driving device.

[0082] Before introducing the perception method, the system architecture applicable to the perception method provided in the embodiment of the present application is first introduced.

[0083] Figure 3 shows a schematic block diagram of the perception system architecture provided by an embodiment of the present application. The perception system includes a roadside data processing center 200, a cloud server 300, and a vehicle-side data processing center 400. The roadside data processing center 200 can be a computing platform installed in roadside equipment, or a server used to control roadside equipment; the vehicle-side data processing center 400 can be the computing platform 150 installed in the intelligent driving device 100 shown in Figure 2, or a server used to control the intelligent driving device 100.

[0084] Specifically, the roadside data processing center 200 includes: a broadcast module 210 and a deployment module 220. Among them, the broadcast module 210 is used to send identification information of the area that the roadside device is responsible for (for example, the area identification number) and information suggesting the perception accuracy of the intelligent driving device in the area (hereinafter referred to as the recommended perception accuracy) to the intelligent driving device within the detection range of the roadside device. The deployment module 220 is used to receive sensor information sent by the intelligent driving device, and then send information of the feature model of the area it is responsible for to the intelligent driving device based on the sensor information. The feature model is used to perceive the characteristic obstacles in the area that the roadside device is responsible for. It should be noted that the "characteristic obstacles" of a certain area involved in the embodiments of the present application may be obstacles that are unique to the area and different from other areas, such as wild animals in mountainous areas, or people wearing clothes with regional characteristics, or vehicles unique to the area, etc.

[0085] Cloud server 300 includes a transceiver module 310 and a query module 320. Transceiver module 310 receives area identification information from intelligent driving devices. Query module 320 determines the perception accuracy corresponding to the area based on the area identification information and then transmits the corresponding perception accuracy information to the intelligent driving devices via transceiver module 310. Optionally, the perception accuracy corresponding to the area, as determined by cloud server 300, is the perception accuracy most commonly used by intelligent driving devices in the area.

[0086] The vehicle-side data processing center 400 includes: a regional perception scheduling node 410, a regional perception node 420, a first fusion node 430, a perception node 440, a second fusion node 450, a regional fusion node 460, and a regulation and control node 470. The regional perception scheduling node 410 is configured to exchange information with the road-side data processing center 200 and the cloud server 300, including but not limited to: receiving regional identification information and recommended perception accuracy information from the broadcast module 210; transmitting intelligent driving device sensor information to the deployment module 220; receiving feature model information from the deployment module 220 and deploying the feature model to the regional perception node 420 and the first fusion node 430; transmitting regional identification information to the transceiver module 310; and receiving regional perception accuracy information from the transceiver module 310. The regional perception node 420 is configured to process sensor data from the intelligent driving device's perception system based on the feature model information received from the road-side data processing center 200 to obtain obstacle information around the intelligent driving device. In some possible implementations, area perception node 420 includes one or more subnodes, each of which is used to determine obstacle information (such as the location and type of the obstacle) based on a type of sensor data. For example, area perception node 420 includes subnodes 421, 422, and 423, where subnode 421 is used to determine obstacle information based on lidar data, subnode 422 is used to determine obstacle information based on camera data, and subnode 423 is used to determine obstacle information based on GPS data. First fusion node 430 is used to fuse the obstacle information processed by area perception node 420 to obtain a first obstacle set. This fusion process can be understood as further determining the type of obstacle and its location around the intelligent driving device based on the obstacle information determined by each subnode in area perception node 420. Perception node 440 is used to process sensor data from the intelligent driving device's perception system based on the intelligent driving device's own feature model to obtain obstacle information around the intelligent driving device. In some possible implementations, perception node 440 may include one or more subnodes. Second fusion node 450 is configured to fuse the obstacle information processed by sensing node 440 to obtain a second obstacle set. Regional fusion node 460 may include a receiving management module 461, a fusion evaluation module 462, and a sending management module 463. Receiving management module 461 is configured to receive obstacle set information from first fusion node 430 and second fusion node 450 and send it to fusion evaluation module 462. Fusion evaluation module 462 is configured to determine a new obstacle set based on the obstacle set information and send it to sending management module 463. Sending management module 463 is configured to send the new obstacle set information to regulation and control node 470.The regulation and control node 470 plans the driving path of the intelligent driving device according to the new obstacle set and generates a control signal to control the driving of the intelligent driving device.

[0087] It should be understood that the system architecture shown in FIG3 is merely an example. In a specific implementation, the system may include more or fewer modules or nodes, and the modules or nodes may be deleted or added according to actual conditions.

[0088] The perception accuracy involved in this application can be understood as the accuracy of perceiving obstacles. The higher the perception accuracy, the smaller the chance of false detection or missed detection of obstacles.

[0089] In the perception system shown in Figure 3 , the roadside data processing center 200 can be installed in a roadside device. As shown in Figure 4 , the roadside device can be installed at the entrance of its responsible area (e.g., the first area), for example, at least one of entrances a, b, and c shown in Figure 4 . It should be understood that the roadside device communicates with the intelligent driving device within its detection range and transmits relevant information about its responsible area to the intelligent driving device, such as identification information of the area and / or information on recommended perception accuracy.

[0090] FIG5 shows a schematic flow chart of a perception method 500 provided in an embodiment of the present application. This method 500 can be executed by the intelligent driving device 100 shown in FIG2 , or by one or more processors of the computing platform 150 shown in FIG2 , or by the vehicle-side data processing center 400 shown in FIG3 . The following description uses the intelligent driving device as an example, and this method 500 may include steps S501 and S502.

[0091] S501: Obtain a first feature model corresponding to a first area that the intelligent driving device needs to pass through, where the first feature model is one of a plurality of feature models, and different feature models among the plurality of feature models are used to perceive feature obstacles in different areas.

[0092] The "characteristic obstacles" of a region may be obstacles unique to that region and different from those in other regions, such as wild animals in mountainous areas or people wearing clothing characteristic of the region. It should be understood that the first characteristic model corresponding to the first region is used to identify the characteristic obstacles in the first region.

[0093] Exemplarily, the first area can be divided according to geographical location; or it can be divided according to administrative area; or it can be divided according to geographical location and administrative area, for example, the Qinling Nature Reserve (geographical location) in Shaanxi Province (administrative area) is divided into the first area; or it can be divided according to other basis.

[0094] For example, when the first feature model is acquired, the intelligent driving device may have entered the first area, or the intelligent driving device may not have entered the first area but has entered the detection range of the roadside device in the first area.

[0095] Optionally, the intelligent driving device can obtain the first feature model from information about the first feature model received from the roadside device; or, the intelligent driving device can obtain the first feature model based on information about the first feature model received from the roadside device. In one example, upon detecting the intelligent driving device, the roadside device sends information about the first feature model to the intelligent driving device. In another example, upon determining that the intelligent driving device has entered the first area, it requests the first feature model from the roadside device. In response to the request, the roadside device sends information about the first feature model to the intelligent driving device.

[0096] In some possible implementations, the intelligent driving device has traveled through a first area before, and the intelligent driving device may store a first feature model corresponding to the first area. When the intelligent driving device determines that it has traveled to the first area, it searches for the first feature model in its stored historical information.

[0097] For example, the intelligent driving device may determine that it has traveled to the first area by, but is not limited to: determining that it has traveled to the first area based on sensor information (such as a GPS signal) obtained from a perception system; or determining that it has traveled to the first area based on identification information of the first area received from a roadside device in the first area. The identification information of the first area may be an area number or other information capable of identifying the first area.

[0098] S502: Sense a first obstacle set in the first area according to the first feature model.

[0099] Exemplarily, the intelligent driving device processes sensor data from the perception system according to the first characteristic model to perceive a first set of obstacles in the first area. It should be understood that the first set of obstacles may include characteristic obstacles in the first area.

[0100] Furthermore, a driving path can be planned for the intelligent driving device based on the first obstacle set, thereby controlling the driving of the intelligent driving device.

[0101] Optionally, the intelligent driving device may also perceive a second set of obstacles in the first area based on a second feature model. This second feature model is the intelligent driving device's own feature model and may be trained based on sensor data acquired during historical driving. This second feature model can be used to perceive obstacles on roads frequently traveled by the intelligent driving device. It should be understood that the characteristic obstacles in the first area may not be perceived or may not be accurately perceived based on this second feature model.

[0102] Optionally, a driving path can be planned for the intelligent driving device based on the first obstacle set and the second obstacle set, thereby controlling the driving of the intelligent driving device. The perception method provided in the embodiment of the present application can identify the characteristic obstacles of the first area by obtaining the first feature model corresponding to the first area when the intelligent driving device is about to or has already driven in the first area, which helps to improve the perception accuracy of the intelligent driving device in the area. Furthermore, when the intelligent driving device drives to different areas, it can perceive different characteristic obstacles corresponding to different areas. Therefore, it can reduce the cases of missed detection and false detection caused by insufficient perception ability of the perception algorithm, thereby improving driving safety.

[0103] FIG6 shows a schematic flow chart of a perception method 600 provided in an embodiment of the present application. This method 600 can be executed by a roadside device that interacts with the intelligent driving device 100 shown in FIG2 , or by a computing platform of the roadside device, or by the roadside data processing center 200 shown in FIG3 . The following description uses execution by a roadside device as an example. This method 600 may include steps S601-S603.

[0104] S601: Receive sensor information of an intelligent driving device that needs to be sent by an intelligent driving device in a first area.

[0105] Illustratively, the first area may be the first area in method 500 , and its division method may refer to the description in method 500 , which will not be repeated here.

[0106] Exemplarily, the sensor information may include information about the sensor type, such as information indicating that the sensor is a radar or a camera. Alternatively, the sensor information may be other information that can indicate the sensor type. In one example, taking an intelligent driving device as an example, the sensor information may include a VIN code. In some possible implementations, the roadside equipment may determine the type of sensor used by the vehicle based on the VIN code. It should be understood that the formats of sensor data output by different types of sensors are different, and different feature models may be required in the process of processing the data of different sensors to obtain perception results (such as obstacle sets).

[0107] S602: Determine a first feature model based on the information from the sensor. The first feature model is one of a plurality of feature models. Different feature models in the plurality of feature models are used to sense characteristic obstacles in different areas. The first feature model corresponds to the first area.

[0108] Exemplarily, the first feature model may be the first feature model in method 500 .

[0109] S603: Send information of the first feature model to the intelligent driving device, so that the intelligent driving device perceives a first obstacle set in the first area according to the first feature model.

[0110] In some possible implementations, the information about the first feature model may include the first feature model, or the information about the first feature model may also be information that can identify or acquire the first feature model.

[0111] The perception method provided in the embodiment of the present application, by sending a first feature model corresponding to the first area to the intelligent driving device that needs to pass through the first area, helps the intelligent driving device to identify characteristic obstacles in the first area based on the first feature model, helps to improve the perception accuracy of the intelligent driving device in the area, and can reduce missed detections and false detections caused by insufficient perception capabilities of the perception algorithm, thereby improving driving safety.

[0112] The above descriptions of the perception method provided by the embodiments of the present application, as applied to an intelligent driving device and a roadside device, are respectively described in conjunction with Figures 5 and 6. The following description of the specific process of the intelligent driving device perceiving an obstacle set based on the first feature model is exemplified in conjunction with Figure 7.

[0113] Figure 7 shows a schematic flow chart of a perception method 700 provided in an embodiment of the present application. Method 700 is an extension of method 500 and method 600. For example, method 700 can be executed in parallel with method 500 and method 600. Exemplarily, the steps executed by the roadside device in method 700 can be executed by the road-side data processing center 200 shown in Figure 3, the steps executed by the intelligent driving device in method 700 can be executed by the vehicle-side data processing center 400 shown in Figure 3, and the steps executed by the server in method 700 can be executed by the cloud server 300 shown in Figure 3. It should be understood that the steps or operations of the perception method shown in Figure 7 are merely examples, and the embodiment of the present application can also perform other operations or variations of the various operations in Figure 7. In addition, the various steps in Figure 7 can be executed in a different order than that presented in Figure 7, and it is possible that not all operations in Figure 7 need to be executed.

[0114] The method 700 may include:

[0115] S701: When the roadside device recognizes the intelligent driving device, it sends identification information of the first area and information of the third perception level to the intelligent driving device.

[0116] Exemplarily, the identification information of the first area may be the identification information of the first area in the above embodiment, for example, an area number, or other information capable of identifying the first area.

[0117] Optionally, the roadside equipment may send identification information of the first area and information of a third perception level to the intelligent driving device, where the third perception level indicates a recommended perception accuracy. The recommended perception accuracy may be the accuracy with which the intelligent driving device is recommended to perceive obstacles in the area to ensure driving safety.

[0118] In some possible implementations, the roadside equipment is provided at an entrance of the first area.

[0119] S702: The intelligent driving device sends identification information of the first area to the server.

[0120] S703: The server determines a second perception level according to the identification information of the first area.

[0121] The second perception level indicates the current perception accuracy of the first area.

[0122] In some possible implementations, the second perception level may be determined by the server according to perception level information reported by an intelligent driving device passing through the first area.

[0123] S704: The server sends information of the second perception level to the intelligent driving device.

[0124] In some possible implementations, S703 may be skipped and S704 may be directly executed, that is, the server sends information of the second perception level to the intelligent driving device according to the identification information of the first area.

[0125] S705: The intelligent driving device determines that the perception accuracy indicated by the second perception level is less than the perception accuracy indicated by the third perception level.

[0126] For example, the second perception level may indicate the current perception accuracy of the first area, or may also indicate the default perception accuracy of the intelligent driving device. The default perception accuracy may be set when the intelligent driving device leaves the factory, or may be set by the user of the intelligent driving device.

[0127] In some possible implementations, steps S702 to S704 may not be performed, and step S705 may be performed directly after step S701. That is, if the intelligent driving device does not obtain information indicating the perception accuracy of the first area from the server, the intelligent driving device determines whether its default perception accuracy is less than the perception accuracy indicated by the third perception level.

[0128] It should be understood that when the perceptual accuracy indicated by the second perceptual level is less than the perceptual accuracy indicated by the third perceptual level, S706 is continued to be executed.

[0129] In some possible implementations, if the perception accuracy indicated by the second perception level is greater than or equal to the perception accuracy indicated by the third perception level, the intelligent driving device may perceive the surrounding obstacles based on the feature model currently used (such as the intelligent driving device's own feature model, i.e., the second feature model below); or the intelligent driving device may determine the feature model used to perceive obstacles based on the perception accuracy indicated by the second perception level.

[0130] S706: The intelligent driving device sends sensor information of the intelligent driving device to the roadside device.

[0131] Exemplarily, the information of the sensor may be the information of the sensor in method 600 .

[0132] S707: The roadside equipment determines a first feature model corresponding to the first area based on the information from the sensor.

[0133] In some possible implementations, the roadside device further determines an execution file and dependencies associated with the first feature model, and sends them to the intelligent driving device along with the first feature model.

[0134] S708: The roadside device sends information of the first feature model to the intelligent driving device.

[0135] In some possible implementations, S707 may be skipped and S708 may be directly executed, that is, the roadside device sends information of the first feature model to the intelligent driving device based on the information from the sensor.

[0136] S709: The intelligent driving device perceives a first obstacle set in the first area according to the first feature model.

[0137] In some possible implementations, the intelligent driving device deploys a first feature model (for example, deploys the first feature model to the area perception node 420 in FIG. 3 ), and processes sensor data from the perception system according to the first feature model to obtain a first obstacle set.

[0138] In some possible implementations, the suggested perception accuracy indicated by the third perception level in S701 may also be used to characterize the accuracy of obstacle perception based on the first feature model.

[0139] S710: The intelligent driving device perceives a second obstacle set in the first area according to a second feature model of the intelligent driving device.

[0140] In some possible implementations, the default perception accuracy of the intelligent driving device involved in S705 may also be used to characterize the accuracy of obstacle perception based on the second feature model.

[0141] In some possible implementations, S709 and S710 may also be executed simultaneously.

[0142] S711: The intelligent driving device controls the driving of the intelligent driving device according to the first obstacle set and the second obstacle set.

[0143] Illustratively, the Hungarian matching algorithm is used to match obstacles in the first obstacle set and the second obstacle set to obtain a new obstacle set, and then the driving path of the intelligent driving device is planned according to the new obstacle set.

[0144] In some possible implementations, the new obstacle set obtained by matching two obstacle sets may be as shown in Figure 8. Block 810 represents the first obstacle set, which includes obstacles 5 through 10, and block 820 represents the second obstacle set, which includes obstacles 1 through 7. Obstacle sets A, B, and C are the new obstacle sets obtained by matching the first and second obstacle sets. Specifically, obstacle set A includes obstacles 1 through 4, obstacle set B includes obstacles 5 through 7, and obstacle set C includes obstacles 8 through 10. It should be understood that obstacle set B (or the third obstacle set) includes obstacles shared by the first and second obstacle sets. Obstacle set A is the obstacle set obtained by removing the obstacles in obstacle set B from the second obstacle set, and obstacle set C is the obstacle set obtained by removing the obstacles in obstacle set B from the first obstacle set.

[0145] Furthermore, the information of the above obstacle sets A, B, and C is sent to the regulation and control module (such as the regulation and control node 470) so that it plans the driving path of the intelligent driving device according to the above obstacle information.

[0146] In some possible implementations, different obstacle sets are used to plan the driving path of an intelligent driving device for different preset ranges. For example, within a first preset range of the intelligent driving device, the intelligent driving device is controlled based on the union of the first and second obstacle sets; outside the first preset range but within the second preset range of the intelligent driving device, the intelligent driving device is controlled based on the first obstacle set; and outside the second preset range, the intelligent driving device is controlled based on a third obstacle set.

[0147] In the embodiments of this application, "within" may include the number itself, while "outside" may not include the number itself. For example, "within 30 meters of the intelligent driving device" includes the range within or equal to 30 meters of the intelligent driving device; "outside 30 meters of the intelligent driving device" includes the range greater than 30 meters of the intelligent driving device.

[0148] Taking vehicle 910 in Figure 9 as an example, an intelligent driving device can perform path planning within a first preset range 920 of vehicle 910 based on obstacle sets A', B', and C'. A' is the set of obstacles within vehicle 910's first preset range 920 from obstacle set A; B' is the set of obstacles within vehicle 910's first preset range 920 from obstacle set B; and C' is the set of obstacles within vehicle 910's first preset range 920 from obstacle set C. The union of obstacle sets A', B', and C' can also be understood as the union of the first obstacle set and the second obstacle set, consisting of the obstacles within vehicle 910's first preset range 920.

[0149] Outside the first preset range 920 of vehicle 910 and within the second preset range 930 of vehicle 910, path planning can be performed based on obstacle sets B" and C". B" is the set of obstacles in obstacle set B that are outside the first preset range 920 of vehicle 910 and within the second preset range 930 of vehicle 910; C" is the set of obstacles in obstacle set C that are outside the first preset range 920 of vehicle 910 and within the second preset range 930 of vehicle 910. The union of obstacle sets B" and C" can also be understood as the union of the first obstacle set and the second obstacle set, which are the set of obstacles that are outside the first preset range 920 of vehicle 910 and within the second preset range 930 of vehicle 910.

[0150] Outside the second preset range 930 of vehicle 910, path planning can be performed based on obstacle set B'". B'' is the set of obstacles in obstacle set B that are outside the second preset range 930 of vehicle 910. Obstacle set B'' can also be understood as the set of obstacles in the third obstacle set that are outside the second preset range 930 of vehicle 910.

[0151] For example, the first preset range (or first preset range 920) may be 30 meters from the intelligent driving device (or vehicle 910), and the second preset range (or second preset range 930) may be 60 meters from the intelligent driving device (or vehicle 910). It should be understood that the above setting of the preset range is merely an example, and in a specific implementation, other preset ranges may also be used. For example, the preset range may be determined using the closest in-path vehicle (CIPV) method, and the value of the preset range may be different at different locations of the intelligent driving device.

[0152] S712: The intelligent driving device determines a first perception level according to the first obstacle set and the second obstacle set.

[0153] It should be understood that the first perception level indicates the perception accuracy of the intelligent driving device when passing through the first area. The perception accuracy of the intelligent driving device when passing through the first area can also be understood as the perception accuracy of the intelligent driving device within the first area.

[0154] Exemplarily, the intelligent driving device determines a first perception level based on obstacle sets A, B, and C. Specifically, the intelligent driving device determines the cumulative number of matches s, the cumulative number of regional false detections fd, and the cumulative number of regional missed detections lf. The cumulative number of matches s is the total number of obstacles included in obstacle set B determined one or more times, the cumulative number of regional false detections fd is the total number of obstacles included in obstacle set A determined one or more times, and the cumulative number of regional missed detections lf is the total number of obstacles included in obstacle set C determined one or more times. Furthermore, the false detection rate a and the accuracy rate b are calculated according to the following formulas:

[0155]

[0156]

[0157] Furthermore, the first perception level is determined based on the false positive rate a and the accuracy rate b. For example, the relationship between the perception level, the false positive rate, and the accuracy rate can be shown in Table 1. It should be understood that the lower the false positive rate and the higher the accuracy rate, the higher the perception accuracy indicated by the perception level. As shown in Table 1, a higher perception level value represents a higher perception accuracy, i.e., the perception accuracy indicated by perception level 1 is lower than the perception accuracy indicated by perception level 2, and so on. For example, when the false positive rate a is less than or equal to the false positive rate threshold corresponding to perception level 1, and the false positive rate a is greater than the false positive rate threshold corresponding to perception level 2, and the accuracy rate b is greater than or equal to the accuracy rate threshold corresponding to perception level 1, and the accuracy rate b is less than the accuracy rate threshold corresponding to perception level 2, the first perception level is determined to be perception level 1. For example, a0 to a3 shown in Table 1 can be 30%, 20%, 10%, and 5%, respectively, and b0 to b3 can be 80%, 85%, 90%, and 95%, respectively. Alternatively, a0 to a3 and b0 to b3 can also take other values. In some possible implementations, the perception level can also be determined in conjunction with the time c required for the perception algorithm to perceive an obstacle. For example, if the false detection rate a and the accuracy rate b each meet the conditions corresponding to Perception Level 1, and the time required for the perception algorithm to perceive an obstacle is greater than or equal to the time threshold corresponding to Perception Level 1, and less than the time threshold corresponding to Perception Level 2, the first perception level is determined to be Perception Level 1. For example, c0 to c3 shown in Table 1 can be 0.005 hours, 0.010 hours, 0.015 hours, and 0.020 hours, respectively, or other values ​​can be used.

[0158] Table 1 Correspondence between perception level, false detection rate and accuracy

[0159] Perception level false detection rate threshold accuracy threshold duration threshold 1a0b0c02a1b1c13a2b2c24a3b3c3

[0160] It should be understood that the relationship between the perception level and the false detection rate and accuracy rate shown in Table 1 is only an example. In the specific implementation process, more or fewer perception levels can be divided.

[0161] In some possible implementations, the intelligent driving device may save the information of the first perception level, and when driving to the first area next time, the intelligent driving device may determine the perception algorithm required for obstacle recognition based on the first perception level.

[0162] S713: The intelligent driving device sends identification information of the first area and information of the first perception level to the server.

[0163] It should be understood that the intelligent driving device sends the identification information of the first area and the information of the first perception level to the server, so that the server updates the perception level corresponding to the first area.

[0164] In some possible implementations, when the first perception level is different from the second perception level received in S704 , the intelligent driving device sends information about the first perception level to the server.

[0165] In some possible implementations, S712 and S713 may not be performed.

[0166] The perception method provided in the embodiments of the present application can obtain a first feature model corresponding to the first area from a roadside device when the intelligent driving device is about to or already traveling in a first area. Based on this first feature model, characteristic obstacles in the first area can be identified, helping to improve the perception accuracy of the intelligent driving device in that area. Furthermore, when the intelligent driving device travels to different areas, it can perceive different characteristic obstacles corresponding to different areas. This can reduce the occurrence of missed detections and false detections caused by insufficient perception capabilities of the perception algorithm, thereby improving driving safety. The perception method provided in the embodiments of the present application can also use different obstacle sets to plan the driving path of the intelligent driving device for different preset ranges, helping to improve the smoothness of the planning algorithm, reduce unnecessary waste of computing power, and help save energy. In addition, the implementation of the perception method provided in the embodiments of the present application allows roadside devices to be deployed only at the entrance of the area, eliminating the need to set up multiple roadside devices to cover the entire road. There is also no need to deploy perception-type roadside devices, which can significantly reduce the cost of deploying roadside devices. In addition, the embodiment of the present application can also evaluate the perception level of the intelligent driving device in the first area, so that the server can update the perception level corresponding to the first area, thereby reducing safety accidents caused by misjudgment of the perception level of the first area, and helping to improve driving safety.

[0167] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0168] The method provided in the embodiment of the present application is described in detail above with reference to Figures 3 to 9. The apparatus provided in the embodiment of the present application will be described in detail below with reference to Figures 10 to 12. It should be understood that the description of the apparatus embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above, and for the sake of brevity, no further description will be given here.

[0169] FIG10 shows a schematic block diagram of a sensing device 1000 according to an embodiment of the present application. The device 1000 includes an acquisition unit 1010 and a first processing unit 1020 .

[0170] The apparatus 1000 may include units for executing the method in Figure 5 or Figure 7. Furthermore, each unit in the apparatus 1000 and the above-mentioned other operations and / or functions are for implementing the corresponding processes of the method embodiment in Figure 5 or Figure 7.

[0171] When the apparatus 1000 is used to execute the method 500 in FIG. 5 , the acquiring unit 1010 may be used to execute S501 in the method 500 , and the first processing unit 1020 may be used to execute S502 in the method 500 .

[0172] Specifically, the acquisition unit 1010 is used to: obtain a first feature model corresponding to a first area that the intelligent driving device needs to pass through, where the first feature model is one of multiple feature models, and different feature models among the multiple feature models are used to perceive feature obstacles in different areas; the first processing unit 1020 is used to: perceive the first obstacle set in the first area based on the first feature model.

[0173] Optionally, the device 1000 further includes a second processing unit and a third processing unit, wherein the second processing unit is used to: perceive a second obstacle set in the first area according to a second feature model of the intelligent driving device; the third processing unit is used to: control the intelligent driving device to travel according to the union of the first obstacle set and the second obstacle set within a first preset range of the intelligent driving device; control the intelligent driving device to travel according to the first obstacle set outside the first preset range and within a second preset range of the intelligent driving device; and control the intelligent driving device to travel according to a third obstacle set outside the second preset range, wherein the third obstacle set includes obstacles common to the first obstacle set and the second obstacle set.

[0174] Optionally, the apparatus further includes a fourth processing unit configured to determine a first perception level based on the first obstacle set and the second obstacle set, wherein the first perception level indicates a perception accuracy of the intelligent driving device when passing through the first area.

[0175] Optionally, the device further includes a first communication unit, configured to send identification information of the first area and information of the first perception level to a server, so that the server updates the perception level corresponding to the first area.

[0176] Optionally, the apparatus further includes a second communication unit, and the acquisition unit 1010 is configured to acquire information of the first feature model received by the second communication unit and sent by a roadside device in the first area, where the roadside device is located at an entrance of the first area.

[0177] In some possible implementations, the first communication unit and the second communication unit may be the same communication unit, or may be different communication units, which is not specifically limited in the embodiments of the present application.

[0178] Optionally, the second communication unit is further used to: send sensor information of the intelligent driving device to the roadside device; and receive information of the first feature model sent by the roadside device based on the sensor information.

[0179] Optionally, the second communication unit is also used to: receive information on a third perception level sent by the roadside device, the third perception level indicating the recommended perception accuracy corresponding to the first area; when the perception accuracy of the second perception level is less than the perception accuracy of the third perception level, send information on the sensor of the intelligent driving device to the roadside device, wherein the second perception level indicates the current perception accuracy corresponding to the first area or the default perception accuracy of the intelligent driving device.

[0180] Optionally, when the second perception level indicates a current perception accuracy corresponding to the first area, the first communication unit is further configured to: send identification information of the first area to a server; and receive information of the second perception level sent by the server according to the identification information.

[0181] Exemplarily, the acquisition unit 1010 may include the regional perception scheduling node 410 shown in FIG3 ; the first processing unit 1020 may include the regional perception node 420 and the first fusion node 430 shown in FIG3 ; the second processing unit may include the perception node 440 and the second fusion node 450 shown in FIG3 ; the third processing unit may include the regional fusion node 460 shown in FIG3 , or the third processing unit may include the regional fusion node 460 and the regulation and control node 470 shown in FIG3 ; the fourth processing unit may include the regional fusion node 460 shown in FIG3 ; the first communication unit or the second communication unit may include the regional perception scheduling node 410 shown in FIG3 .

[0182] In some possible implementations, the acquisition unit 1010 and the first communication unit (and / or the second communication unit) may be the same unit, or the acquisition unit 1010 includes the first communication unit (and / or the second communication unit).

[0183] During a specific implementation, the operations performed by the acquisition unit 1010 and the first processing unit 1020 can be performed by the same processor, or by different processors, for example, by multiple processors. In one example, one or more processors can be connected to one or more sensors in the perception system 120 in Figure 2, obtain information such as the type and location of obstacles around the intelligent driving device from the one or more sensors, and process the information according to the first feature model and / or the second feature model to obtain an obstacle set (e.g., a first obstacle set and / or a second obstacle set). Furthermore, the one or more processors can also control the driving path of the intelligent driving device based on the obstacle set. For example, during a specific implementation, the one or more processors can be processors located in the vehicle computer, or can also be processors located in other vehicle-mounted terminals. In one example, during a specific implementation, the device 1000 can be a chip located in the vehicle computer or other vehicle-mounted terminal. In another example, during a specific implementation, the device 1000 can be a computing platform 150 located in the intelligent driving device, as shown in Figure 2.

[0184] Figure 11 shows a schematic block diagram of a perception device 1100 provided in an embodiment of the present application. The device 1100 includes a first communication unit 1110 and a determination unit 1120.

[0185] The apparatus 1100 may include units for executing the method in Figure 6 or Figure 7. Furthermore, each unit in the apparatus 1100 and the other operations and / or functions described above are for implementing corresponding processes of the method embodiments in Figure 6 or Figure 7.

[0186] When the device 1100 is used to execute the method 600 in FIG. 6 , the first communication unit 1110 may be used to execute S601 and S603 in the method 600 , and the determination unit 1120 may be used to execute S602 in the method 600 .

[0187] Specifically, the first communication unit 1110 is used to: receive information from the sensor of the intelligent driving device that needs to be sent by the intelligent driving device in the first area; the determination unit 1120 is used to: determine a first feature model based on the sensor information, the first feature model is one of multiple feature models, and different feature models among the multiple feature models are used to perceive characteristic obstacles in different areas, and the first feature model corresponds to the first area; the first communication unit 1110 is also used to: send information of the first feature model to the intelligent driving device, so that the intelligent driving device perceives the first obstacle set in the first area according to the first feature model.

[0188] Optionally, the device also includes a second communication unit, which is used to: send perception level information to the intelligent driving device before the first communication unit 1110 receives the information of the sensor of the intelligent driving device sent by the intelligent driving device, and the perception level indicates the recommended perception accuracy corresponding to the first area.

[0189] In some possible implementations, the first communication unit and the second communication unit may be the same communication unit, or may be different communication units, which is not specifically limited in the embodiments of the present application.

[0190] Optionally, the apparatus further includes a third communication unit, and the third communication unit is further configured to: send identification information of the first area to the intelligent driving device.

[0191] In some possible implementations, the third communication unit and the second communication unit may be the same communication unit; or, the third communication unit and the first communication unit may be the same communication unit; or, the first communication unit, the second communication unit, and the third communication unit may all be the same communication unit, or they may also be different communication units.

[0192] Exemplarily, the first communication unit 1110 may include the deployment module 220 shown in FIG3 ; the determination unit 1120 may also include the deployment module 220 shown in FIG3 ; the second communication unit may include the broadcast module 210 shown in FIG3 ; the third communication unit may include the broadcast module 210 shown in FIG3 .

[0193] During a specific implementation, the operations performed by the first communication unit 1110 and the determination unit 1120 may be performed by the same processor, or may be performed by different processors, for example, by multiple processors. During a specific implementation, the one or more processors may be processors provided in a roadside device, such as a processor provided in a computing platform of the roadside device. In one example, during a specific implementation, the apparatus 1100 may be a chip provided in the roadside device. In another example, during a specific implementation, the apparatus 1100 may be a computing platform provided in the roadside device.

[0194] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps performed by the above embodiment.

[0195] It should be understood that the division of the various units in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or they may be physically separated. Furthermore, the units in the device may be implemented in the form of a processor calling software; for example, the device includes a processor connected to a memory storing instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or the functions of the various units in the device. The processor may be a general-purpose processor, such as a CPU or a microprocessor, and the memory may be a memory within the device or external to the device. Alternatively, the units in the device may be implemented in the form of hardware circuits, and the functions of some or all of the units may be implemented through the design of the hardware circuits. The hardware circuits may be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units may be implemented through the design of the logical relationships between the components within the circuits. In another implementation, the hardware circuit may be implemented using a PLD, such as an FPGA, which may include a large number of logic gate circuits. The connections between the logic gate circuits are configured using a configuration file to implement the functions of some or all of the above units. All units of the above apparatus may be implemented entirely in the form of software called by a processor, or entirely in the form of hardware circuits, or partially in the form of software called by a processor and the rest in the form of hardware circuits.

[0196] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, and the like.

[0197] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0198] In addition, the various units in the above devices can be fully or partially integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the device. The type of the at least one processor can be different, for example, including a CPU and FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0199] Figure 12 is a schematic block diagram of a sensing device according to an embodiment of the present application. The sensing device 1200 shown in Figure 12 may include: a processor 1210, a transceiver 1220, and a memory 1230. The processor 1210, the transceiver 1220, and the memory 1230 are connected via an internal connection path. The memory 1230 is used to store instructions, and the processor 1210 is used to execute the instructions stored in the memory 1230, so as to receive / send some parameters through the transceiver 1220. Optionally, the memory 1230 may be coupled to the processor 1210 via an interface or integrated with the processor 1210.

[0200] It should be noted that the transceiver 1220 may include but is not limited to a transceiver device such as an input / output interface to implement communication between the device 1200 and other devices or a communication network.

[0201] In some possible implementations, the device 1200 can be set in the road-side data processing center 200 shown in Figure 3, or in the cloud server 300, or in the vehicle-side data processing center 400.

[0202] In some possible implementations, the apparatus 1200 may be provided within the intelligent driving device 100 shown in FIG. 2 . The processor 1210 may be a general-purpose CPU, microprocessor, ASIC, GPU, or one or more integrated circuits, configured to execute relevant programs to implement the perception method of the present invention. The processor 1210 may also be an integrated circuit chip with signal processing capabilities. In a specific implementation, the various steps of the perception method of the present invention may be performed by hardware integrated logic circuits or software instructions within the processor 1210. The processor 1210 may also be a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software module can be located in a storage medium such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers, which are well-known in the art. The storage medium is located in memory 1230, and processor 1210 reads information in memory 1230 and, in conjunction with its hardware, executes the sensing method of the embodiment of the present application.

[0203] The memory 1230 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0204] Transceiver 1220 uses a transceiver device, such as, but not limited to, a transceiver, to enable communication between device 1200 and other devices or communication networks. For example, when device 1200 is installed in an intelligent driving device, transceiver 1220 can receive information about the first feature model; when device 1200 is installed in roadside equipment, transceiver 1220 can transmit information about the first feature model. For another example, when device 1200 is installed in an intelligent driving device, transceiver 1220 can transmit identification information of a first area and information about a first perception level; when device 1200 is installed in a cloud server, transceiver 1220 can receive identification information of the first area and information about the first perception level.

[0205] An embodiment of the present application also provides a perception system, which includes the device 1000 shown in Figure 10 and the device 1100 shown in Figure 11; or, the perception system includes the above-mentioned intelligent driving device and roadside equipment.

[0206] Optionally, the perception system may further include a server, which is used to: receive identification information of the first area that needs to be sent by the intelligent driving device in the first area; and send information of a second perception level to the intelligent driving device based on the identification information, where the second perception level indicates the current perception accuracy corresponding to the first area.

[0207] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer implements the method in the embodiment of the present application.

[0208] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer implements the method in the embodiment of the present application.

[0209] An embodiment of the present application also provides a chip, including a circuit, for executing the method in the embodiment of the present application.

[0210] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0211] It should be understood that in the embodiment of the present application, the memory may include a read-only memory (ROM) and a random access memory (RAM), and provide instructions and data to the processor.

[0212] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0213] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0214] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0215] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0216] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0217] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0218] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0219] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A perception method, characterized in that: include: Obtaining a first feature model corresponding to a first area that the intelligent driving device needs to pass through, where the first feature model is one of a plurality of feature models, and different feature models among the plurality of feature models are used to sense characteristic obstacles in different areas; A first obstacle set in the first area is sensed according to the first feature model.

2. The method according to claim 1, wherein The method further comprises: sensing a second obstacle set in the first area according to a second feature model of the intelligent driving device; Controlling the intelligent driving device to travel according to a union of the first obstacle set and the second obstacle set within a first preset range of the intelligent driving device; outside the first preset range and within a second preset range of the intelligent driving device, controlling the intelligent driving device to travel according to the first obstacle set; and Outside the second preset range, the intelligent driving device is controlled to travel according to a third obstacle set, wherein the third obstacle set includes obstacles common to the first obstacle set and the second obstacle set.

3. The method according to claim 2, wherein The method further comprises: A first perception level is determined according to the first obstacle set and the second obstacle set, where the first perception level indicates a perception accuracy of the intelligent driving device when passing through the first area.

4. The method according to claim 3, wherein The method further comprises: The identification information of the first area and the information of the first perception level are sent to a server, so that the server updates the perception level corresponding to the first area.

5. The method according to any one of claims 1 to 4, characterized in that The obtaining of a first feature model corresponding to the first area where the intelligent driving device is located includes: Receive information about the first feature model sent by a roadside device in the first area, where the roadside device is located at an entrance of the first area.

6. The method according to claim 5, wherein Before receiving the information of the first feature model sent by the roadside equipment in the first area, the method further includes: Sending information from the sensor of the intelligent driving device to the roadside device; The receiving information of the first feature model sent by the roadside equipment in the first area includes: Receive information of the first feature model sent by the roadside equipment according to information of the sensor.

7. The method according to claim 6, wherein The sending of sensor information of the intelligent driving device to the roadside device includes: receiving information of a third perception level sent by the roadside device, where the third perception level indicates a recommended perception accuracy corresponding to the first area; When the perception accuracy of the second perception level is less than the perception accuracy of the third perception level, information of the sensor of the intelligent driving device is sent to the roadside device, wherein the second perception level indicates the current perception accuracy corresponding to the first area or the default perception accuracy of the intelligent driving device.

8. The method according to claim 7, wherein When the second perception level indicates a current perception accuracy corresponding to the first area, the method further includes: Sending identification information of the first area to a server; receiving information of the second perception level sent by the server according to the identification information.

9. A perception method, characterized in that: include: receiving information from a sensor of the intelligent driving device that needs to be sent by the intelligent driving device in the first area; determining a first feature model based on information from the sensor, where the first feature model is one of a plurality of feature models, different feature models among the plurality of feature models are used to sense characteristic obstacles in different areas, and the first feature model corresponds to the first area; Information of the first feature model is sent to the intelligent driving device, so that the intelligent driving device perceives a first obstacle set in the first area according to the first feature model.

10. The method according to claim 9, wherein Before receiving the information of the sensor of the intelligent driving device that needs to be sent by the intelligent driving device in the first area, the method further includes: Sending perception level information to the intelligent driving device, where the perception level indicates a recommended perception accuracy corresponding to the first area.

11. The method according to claim 9 or 10, wherein: The method further comprises: Send identification information of the first area to the intelligent driving device.

12. A sensing device, characterized in that: It includes an acquisition unit and a first processing unit, wherein, The acquisition unit is used for: Obtaining a first feature model corresponding to a first area that the intelligent driving device needs to pass through, where the first feature model is one of a plurality of feature models, and different feature models among the plurality of feature models are used to sense characteristic obstacles in different areas; The first processing unit is configured to: A first obstacle set in the first area is sensed according to the first feature model.

13. The device according to claim 12, wherein The device further includes a second processing unit and a third processing unit, wherein: The second processing unit is configured to: sensing a second obstacle set in the first area according to a second feature model of the intelligent driving device; The third processing unit is configured to: Controlling the intelligent driving device to travel according to a union of the first obstacle set and the second obstacle set within a first preset range of the intelligent driving device; outside the first preset range and within a second preset range of the intelligent driving device, controlling the intelligent driving device to travel according to the first obstacle set; and Outside the second preset range, the intelligent driving device is controlled to travel according to a third obstacle set, wherein the third obstacle set includes obstacles common to the first obstacle set and the second obstacle set.

14. The device according to claim 13, wherein The apparatus further includes a fourth processing unit, configured to: A first perception level is determined according to the first obstacle set and the second obstacle set, where the first perception level indicates a perception accuracy of the intelligent driving device when passing through the first area.

15. The device according to claim 14, wherein The apparatus further includes a first communication unit, wherein the first communication unit is configured to: The identification information of the first area and the information of the first perception level are sent to a server, so that the server updates the perception level corresponding to the first area.

16. The device according to any one of claims 12 to 15, characterized in that The device further includes a second communication unit, and the acquiring unit is configured to: The information of the first feature model sent by the roadside equipment in the first area is acquired and received by the second communication unit, where the roadside equipment is located at an entrance of the first area.

17. The device according to claim 16, wherein The second communication unit is further configured to: Sending information from the sensor of the intelligent driving device to the roadside device; Receive information of the first feature model sent by the roadside equipment according to information of the sensor.

18. The device according to claim 17, wherein The second communication unit is configured to: receiving information of a third perception level sent by the roadside device, where the third perception level indicates a recommended perception accuracy corresponding to the first area; When the perception accuracy of the second perception level is less than the perception accuracy of the third perception level, information of the sensor of the intelligent driving device is sent to the roadside device, wherein the second perception level indicates the current perception accuracy corresponding to the first area or the default perception accuracy of the intelligent driving device.

19. The device according to claim 18, wherein When the second perception level indicates a current perception accuracy corresponding to the first area, the first communication unit is further configured to: Sending identification information of the first area to the server; receiving information of the second perception level sent by the server according to the identification information.

20. A sensing device, characterized in that: It includes a first communication unit and a determination unit, wherein: The first communication unit is configured to: receiving information from a sensor of the intelligent driving device that needs to be sent by the intelligent driving device in the first area; The determining unit is configured to: determining a first feature model based on information from the sensor, where the first feature model is one of a plurality of feature models, different feature models among the plurality of feature models are used to sense characteristic obstacles in different areas, and the first feature model corresponds to the first area; The first communication unit is further configured to: Information of the first feature model is sent to the intelligent driving device, so that the intelligent driving device perceives a first obstacle set in the first area according to the first feature model.

21. The device according to claim 20, characterized in that The apparatus further includes a second communication unit, wherein the second communication unit is configured to: Before the first communication unit receives the information of the sensor of the intelligent driving device sent by the intelligent driving device, information of a perception level is sent to the intelligent driving device, where the perception level indicates a recommended perception accuracy corresponding to the first area.

22. The device according to claim 20 or 21, characterized in that The apparatus further includes a third communication unit, configured to: Send identification information of the first area to the intelligent driving device.

23. A sensing device, characterized in that: include: memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 8.

24. A sensing device, characterized in that: include: memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 9 to 11.

25. An intelligent driving device, characterized in that: Comprising the device according to any one of claims 12 to 19 and 23.

26. A roadside equipment, characterized in that: Comprising the device according to any one of claims 20 to 22 and 24.

27. A perception system, characterized in that: It includes the intelligent driving device as described in claim 25 and the roadside equipment as described in claim 26.

28. The system of claim 27, wherein: The system further includes a server, the server being configured to: receive identification information of the first area sent by an intelligent driving device that needs to pass through the first area; Information about a second perception level is sent to the intelligent driving device according to the identification information, where the second perception level indicates a current perception accuracy corresponding to the first area.

29. A chip, characterized in that: The method comprises a circuit for performing the method according to any one of claims 1 to 11.

Images