Data processing method and device

Abstract

The invention discloses a data processing method and device, and the method comprises the steps: obtaining the driving data of a vehicle, and determining the driving state of the vehicle according to the driving data; wherein the driving state is used for indicating the processing priority of the detection data of the vehicle in different directions; therefore, according to the processing priorities of the detection data in different directions of the vehicle, the detection data are processed in sequence. All detection data is divided into multiple parts based on the processing priorities, and the multiple parts of detection data have different processing priorities, so that a chip in the domain controller can be prevented from processing all detection data at the same time. The chip only processes part of detection data at the same time, so that the requirement on the computing power of the chip can be undoubtedly reduced. In other words, the chip sequentially processes all detection data in time, so that the computing power requirement of the chip can be reduced, and the cost of the required chip is reduced.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a data processing method and device. Background Art

[0002] With the advent and widespread use of the internet, intelligent driving technology (short for "smart driving") has become increasingly mature. Intelligent driving relies on artificial intelligence, sensors, communication and positioning technologies to assist humans in driving vehicles. It has the ability to perceive the surrounding environment, make decisions, and execute driving tasks.

[0003] To achieve intelligent driving, a large number of devices (such as lidar, millimeter-wave radar, cameras, etc.) are generally required for detection. In this way, the vehicle can perceive the surrounding environment, make decisions, and execute driving tasks based on the detection data of these devices.

[0004] Due to the large number and variety of devices, the amount of detection data is large. In order to process this detection data, this undoubtedly leads to high computing power requirements for the domain controller (or on-board chip) that processes this detection data, which in turn increases the cost of the required on-board chip. Summary of the Invention

[0005] The embodiments of the present invention provide a data processing method and apparatus for sequentially processing detection data, thereby avoiding processing a large amount of detection data at the same time, thereby reducing the computing power requirements of a chip for processing the detection data and reducing the cost of the required chips.

[0006] In a first aspect, an embodiment of the present invention provides a data processing method, which can be applied to an on-board chip (hereinafter referred to as the chip) in a domain controller; specifically, the chip obtains driving data of the vehicle, and then determines the driving status of the vehicle based on the driving data; wherein the driving status is used to indicate the processing priority of detection data in different directions of the vehicle; to this end, the detection data in different directions of the vehicle are processed in sequence according to the processing priority of the detection data in different directions of the vehicle.

[0007] In the above technical solution, the processing priority of the vehicle's detection data from different directions can be divided into multiple copies, each with different processing priorities. This allows the chip to avoid processing all the detection data simultaneously, but instead processes part of the detection data simultaneously, which undoubtedly reduces the chip's computing power requirements. In other words, the chip processes all the detection data in a timely manner, which reduces the chip's computing power requirements and thus reduces the cost of the required chip.

[0008] In one possible implementation, the driving state is a straight-ahead state or a non-straight-ahead state; based on this, the straight-ahead state indicates that the processing priority of the vehicle's detection data in the first direction and the second direction is greater than the processing priority of the vehicle's detection data in the third direction and the fourth direction; wherein the first direction is the vehicle's driving direction, the second direction is a direction with an angle α with the first direction, 0°<α≤90°, the third direction is a direction opposite to the vehicle's driving direction, and the fourth direction is a direction with an angle β with the third direction, 0°<β<90°; the non-straight-ahead state indicates that the processing priority of the vehicle's detection data in the second direction and the fourth direction is greater than the processing priority of the vehicle's detection data in the first direction and the third direction.

[0009] In the above implementation, taking the vehicle's forward motion as an example, the first direction is the vehicle's front direction (or the vehicle's forward direction), the second direction may include the left front direction and the right front direction, the third direction is the vehicle's rear direction (or the vehicle's rearward direction), and the fourth direction may include the left rear direction and the right rear direction. When the vehicle is traveling straight ahead, it is more important to pay attention to the environment ahead to avoid rear-end collisions, so a higher processing priority is assigned to the detection data in the first and second directions. When the vehicle is not traveling straight ahead (such as when turning or changing lanes), it is more important to pay attention to the environment behind to avoid collisions with vehicles in other lanes, so a higher processing priority is assigned to the detection data in the second and fourth directions.

[0010] In one possible implementation, the driving data includes one or more of the following: steering wheel angle, angular velocity, and wheel angle; based on this, the driving state of the vehicle is determined according to the driving data, including: when it is determined that the steering wheel angle, and / or angular velocity, and / or wheel angle are less than or equal to a first threshold, determining that the driving state of the vehicle is a straight-ahead state; when it is determined that the steering wheel angle, and / or angular velocity, and / or wheel angle are greater than the first threshold, determining that the driving state of the vehicle is a non-straight-ahead state.

[0011] In one possible implementation, the driving data also includes the driving speed; based on this, the detection data from different directions of the vehicle are processed in sequence according to the processing priority of the detection data from different directions of the vehicle, including: determining the processing range of the detection data according to the driving speed, and the driving speed is positively correlated with the processing range; according to the processing priority of the detection data from different directions of the vehicle, the detection data within the processing range are processed in sequence.

[0012] In the above implementation, detection data outside the processing range is eliminated according to the vehicle's driving speed. This can further reduce the detection data that needs to be processed, thereby reducing the computing power requirements of the chip and improving data processing efficiency.

[0013] In one possible implementation, determining the processing range of the detection data based on the driving speed includes: if the driving speed is less than or equal to the second threshold, determining the processing range of the detection data to be the first range; if the driving speed is greater than the second threshold and less than or equal to the third threshold, determining the processing range of the detection data to be the second range; wherein the third threshold is greater than the second threshold, and the second range is greater than the first range; if the driving speed is greater than the third threshold, determining the processing range of the detection data to be the third range; wherein the third range is greater than the second range.

[0014] In the above implementation, the processing range of the detection data is divided into three levels according to the vehicle's driving speed to avoid computing pressure on the chip due to too many processing range levels.

[0015] In a possible implementation, the detection data includes one or more of the following: laser point cloud, visual image.

[0016] In a second aspect, an embodiment of the present invention provides a data processing device, comprising: an acquisition module for acquiring driving data of a vehicle; a processing module for determining the driving status of the vehicle based on the driving data, wherein the driving status is used to indicate the processing priority of detection data in different directions of the vehicle; and according to the processing priority of the detection data in different directions of the vehicle, the detection data in different directions of the vehicle are processed in sequence.

[0017] In one possible implementation, the driving state is a straight-ahead state or a non-straight-ahead state; the straight-ahead state indicates that the processing priority of the detection data of the vehicle in the first direction and the second direction is greater than the processing priority of the detection data of the vehicle in the third direction and the fourth direction; wherein, the first direction is the vehicle driving direction, the second direction is the direction with an angle α with the first direction, 0°<α≤90°, the third direction is the direction opposite to the vehicle driving direction, and the fourth direction is the direction with an angle β with the third direction, 0°<β<90°; the non-straight-ahead state indicates that the processing priority of the detection data of the vehicle in the second direction and the fourth direction is greater than the processing priority of the detection data of the vehicle in the first direction and the third direction.

[0018] In one possible implementation, the driving data includes one or more of the following: steering wheel angle, angular velocity, and wheel angle; based on this, the processing module is specifically used to: when it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel angle are less than or equal to a first threshold, determine that the driving state of the vehicle is a straight-ahead state; when it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel angle are greater than the first threshold, determine that the driving state of the vehicle is a non-straight-ahead state.

[0019] In one possible implementation, the driving data also includes a driving speed; the processing module is specifically used to: determine a processing range of the detection data based on the driving speed, and the driving speed is positively correlated with the processing range; and process the detection data within the processing range in sequence according to the processing priority of the detection data in different directions of the vehicle.

[0020] In one possible implementation, the processing module is specifically used to: if the driving speed is less than or equal to a second threshold, determine that the processing range of the detection data is a first range; if the driving speed is greater than the second threshold and less than or equal to a third threshold, determine that the processing range of the detection data is a second range; wherein, the third threshold is greater than the second threshold, and the second range is greater than the first range; if the driving speed is greater than the third threshold, determine that the processing range of the detection data is a third range; wherein, the third range is greater than the second range.

[0021] In a possible implementation, the detection data includes one or more of the following: laser point cloud, visual image.

[0022] In a third aspect, embodiments of the present invention further provide a vehicle comprising the data processing device and the perception device described in the second aspect; wherein the perception device is configured to generate detection data. Optionally, the perception device comprises one or more of the following: a laser radar, a millimeter-wave radar, and a camera.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer device, including:

[0024] a memory for storing program instructions;

[0025] The processor is used to call the program instructions stored in the memory and execute the data processing method described in the first aspect according to the obtained program.

[0026] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the data processing method described in the first aspect above.

[0027] In a sixth aspect, an embodiment of the present invention further provides a computer program product, wherein the computer program product includes an executable program, and the executable program is executed by a processor to execute the data processing method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 A schematic diagram of a vehicle equipped with a sensing device according to an embodiment of the present invention;

[0030] Figure 2 A flowchart of a data processing method provided by an embodiment of the present invention;

[0031] Figure 3 A schematic structural diagram of a data processing device provided by an embodiment of the present invention;

[0032] Figure 4 A schematic structural diagram of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0034] In recent years, with the development of artificial intelligence and sensors, autonomous driving has gradually become a major driving force for innovation in the automotive industry. Autonomous driving (also known as "smart driving") relies on artificial intelligence, sensors, and communication and positioning technologies to assist humans in driving vehicles. It has the ability to perceive the surrounding environment, make decisions, and execute driving tasks.

[0035] In the relevant technical solutions, a vehicle with intelligent driving capabilities (hereinafter referred to as an intelligent driving vehicle) generally includes multiple on-board devices (such as perception devices, domain controllers). Among them, the perception device may include a laser radar, a millimeter-wave radar, a camera and other related sensors (such as a speed sensor, etc.). The perception device can generate a point cloud (or laser point cloud) based on the laser radar, and can also obtain information about obstacles around the vehicle based on the emission-reflection of the millimeter-wave radar and the ultrasonic radar, and can also collect visual images (such as pictures); the domain controller includes an on-board chip (hereinafter referred to as a chip), a memory, and other related devices. The domain controller is installed with an operating system and an application. Based on this, the domain controller can perceive the surrounding environment of the intelligent driving vehicle based on this information (such as laser point cloud and visual image), determine whether there are obstacles, passing pedestrians and vehicles around the intelligent driving vehicle, and thus decide whether the intelligent driving vehicle avoids obstacles and various risks on the road, helping people drive vehicles more safely and conveniently, and realizing intelligent driving.

[0036] Because sensing devices include a wide variety of components (e.g., multiple cameras, multiple LiDARs, and multiple millimeter-wave radars), the amount of data detected by these devices is large. Processing this massive amount of detection data (such as laser point clouds and visual images) undoubtedly requires high computing power for the onboard chips (hereinafter referred to as chips) in the domain controller that processes this detection data, increasing the cost of the required chips.

[0037] Therefore, there is an urgent need for a data processing method to reduce the amount of detection data that needs to be processed, thereby reducing the computing power requirements of the chip that processes the detection data and reducing the cost of the required chip.

[0038] Figure 1 A schematic diagram of a vehicle equipped with a sensing device according to an embodiment of the present invention is provided. Figure 1 The vehicle has intelligent driving capability. The data processing method provided by the embodiment of the present invention can be applied to the vehicle-mounted chip of the vehicle. Since the present invention mainly processes detection data (such as laser point cloud, visual image), Figure 1 The sensing device is introduced only as an example.

[0039] refer to Figure 1 The perception device includes 9 cameras (a1, a2, a3, a4, a5, a6, a7, a8, and a9), 5 millimeter-wave radars (b1, b2, b3, b4, and b5), and 6 lidars (c1, c2, c3, c4, c5, and c6).

[0040] Taking the vehicle moving forward as an example, the direction of travel (or the vehicle's front direction) is the vehicle's front direction. Cameras a1, a4, and a5 are used to capture visual images from the vehicle's front direction, cameras a6 and a7 are used to capture visual images from the vehicle's side front direction (a6 captures the right front direction, and a7 captures the left front direction), cameras a8 and a9 are used to capture visual images from the vehicle's rear direction (or the vehicle's rear end), and cameras a2 and a3 are used to capture visual images from the vehicle's side rear direction (a2 captures the right rear direction, and a3 captures the left rear direction).

[0041] Millimeter-wave radar b1 is used to generate a laser point cloud in the front direction of the vehicle, millimeter-wave radars b2 and b3 are used to generate laser point clouds in the side-front direction of the vehicle (b2 generates the right front direction, b3 generates the left front direction), and millimeter-wave radars b4 and b5 are used to generate a laser point cloud in the side-rear direction of the vehicle (b4 generates the right rear direction, b5 generates the left rear direction).

[0042] LiDARs C1 and C4 are used to generate laser point clouds in the front direction of the vehicle, LiDARs C2 and C3 are used to generate laser point clouds in the side and front direction of the vehicle (C2 generates the right front direction, and C3 generates the left front direction), and LiDARs C5 and C6 are used to generate laser point clouds in the side and rear direction of the vehicle (C5 generates the right rear direction, and C6 generates the left rear direction).

[0043] It should be noted that the above Figure 1 This is just an example. The sensing device may also include other devices, such as a speed sensor, an angular velocity sensor, a gyroscope, etc., and the number of each device may be one or more, which is not limited by the present invention.

[0044] The following combines the above Figure 1 The description is used to illustrate a data processing method provided by an embodiment of the present invention, which can be applied to an on-board chip (hereinafter referred to as chip) in a domain controller. Figure 2 A flow chart of a data processing method provided by an embodiment of the present invention is shown as follows: Figure 2 As shown in the figure, the process specifically includes:

[0045] Step 210: Acquire vehicle driving data.

[0046] In the embodiment of the present invention, the driving data refers to the data of the current vehicle driving, which can reflect the driving state of the vehicle. Optionally, the driving state includes but is not limited to a straight state, a non-straight state (such as turning, changing lanes, etc.), a deceleration state, an acceleration state, an accelerated straight state, a decelerated straight state, and the like. It should be noted that the driving state can be artificially divided according to the driving environment of the vehicle, and the driving state can be divided into multiple states, the number of which is not limited by this application.

[0047] In other words, the driving state is preconfigured. Since driving data is used to determine the driving state, the driving data used to determine the driving state (or the driving data required to be obtained) can also be preconfigured. For example, if the driving state is divided into a straight state and a non-straight state, then the driving data required to be obtained is the wheel deviation angle.

[0048] In addition, based on the different divisions of driving states, the driving data that needs to be obtained may also be different. For example, if the division of driving states includes straight-ahead states and non-straight-ahead states, then the driving data that needs to be obtained is the wheel deflection angle; if the division of driving states includes acceleration states and deceleration states, then the driving data that needs to be obtained is acceleration. For ease of understanding, this application takes the driving state including straight-ahead states and non-straight-ahead states as an example, and the driving data is used to determine whether the vehicle is driving straight. To this end, the driving data obtained may include one or more of the following: steering wheel angle, angular velocity, and wheel deflection angle.

[0049] It should be noted that the driving data may be detected by an onboard sensor and sent to the chip, such as a speed sensor, an angular velocity sensor, a gyroscope, etc. The present invention does not limit the source of the driving data.

[0050] Step 220: Determine the driving state of the vehicle based on the driving data; wherein the driving state is used to indicate the processing priority of the detection data of different directions of the vehicle.

[0051] In the embodiment of the present invention, based on the pre-configured number of driving state divisions, the driving data corresponding to each driving state is compared with a preset threshold value to determine which driving state the vehicle is currently in.

[0052] For ease of description, the following is an example of two driving states, namely, a straight-ahead state and a non-straight-ahead state. It should be noted that the driving state may also include more states (such as a deceleration state, an acceleration state, etc.), which are not limited in this application.

[0053] In one possible implementation, the chip can use any data (steering wheel angle, angular velocity, or wheel deflection angle) to determine the vehicle's driving state. For example, when the chip determines that the steering wheel angle, angular velocity, or wheel deflection angle is less than or equal to a first threshold, it determines that the vehicle's driving state is a straight-ahead state; conversely, when the chip determines that the steering wheel angle, angular velocity, or wheel deflection angle is greater than the first threshold, it determines that the vehicle's driving state is a non-straight-ahead state; wherein the first threshold can be a value preset based on experience, such as 0, which is not limited by the present invention. This method of determining the vehicle's driving state is simple and can avoid placing a large computational burden on the chip.

[0054] In one possible implementation, the chip may use a combination of multiple data to determine the vehicle's driving state. Specifically, the chip determines that the vehicle's driving state is a straight-ahead state when the steering wheel angle, and / or angular velocity, and / or wheel deflection angle are less than or equal to a first threshold; conversely, the chip determines that the vehicle's driving state is a non-straight-ahead state when the steering wheel angle, and / or angular velocity, and / or wheel deflection angle are greater than the first threshold. For example, the chip determines that the vehicle's driving state is a straight-ahead state when both the steering wheel angle and angular velocity are less than or equal to a first threshold; conversely, the chip determines that the vehicle's driving state is a non-straight-ahead state when either the steering wheel angle or angular velocity is greater than the first threshold. Alternatively, the chip determines that the vehicle's driving state is a straight-ahead state when both the steering wheel angle and wheel deflection angle are less than or equal to a first threshold; conversely, the chip determines that the vehicle's driving state is a non-straight-ahead state when either the steering wheel angle or wheel deflection angle is greater than the first threshold. It is understood that the at least two data used to determine the vehicle's driving state may be combined in various ways, which are not detailed herein. This method of determining the driving state of a vehicle takes into account many factors, which can ensure the accuracy and reliability of determining the driving state of the vehicle.

[0055] In one possible implementation, the straight-ahead state can also be pre-divided into a decelerating straight-ahead state and an accelerating straight-ahead state. To this end, the chip can further determine the driving state based on other parameters (such as acceleration). Similarly, the non-straight-ahead state can also be pre-divided into a decelerating non-straight-ahead state and an accelerating non-straight-ahead state. Taking into account the possibility of multiple combinations of pre-divided driving states and the corresponding driving data to be obtained, this application will not go into too much detail here, and will only take the straight-ahead state and the non-straight-ahead state as an example, but will not be limited to this.

[0056] It should be noted that a vehicle can only be in one driving state (such as a straight state or a non-straight state) at a given moment. In addition, the driving environments that need to be paid attention to in the straight state and the non-straight state are generally different. For example, a vehicle in the straight state needs to pay more attention to the environment in front to avoid rear-end collisions, while in the non-straight state (such as turning and changing lanes), it needs to pay more attention to the rear environment to avoid collisions with vehicles in other lanes. For this reason, according to the characteristics of the driving environment that needs to be paid attention to, the processing priority of the detection data in different directions corresponding to the two driving states is also different.

[0057] Specifically, the straight state indicates that the processing priority of the detection data of the vehicle in the first direction and the second direction is greater than the processing priority of the detection data of the vehicle in the third direction and the fourth direction. Figure 1 The second direction is the direction with an angle α with the first direction (as described above Figure 1), 0°<α≤90° (may include the direction perpendicular to the vehicle body in the horizontal direction), the third direction is the direction opposite to the vehicle travel direction (as mentioned above Figure 1 The fourth direction is the direction with an angle β with the third direction (as described above Figure 1 (hereinafter referred to as the lateral and rearward directions), 0°<β<90° (generally excluding the direction perpendicular to the horizontal direction of the vehicle body). It should be noted that the first direction, the second direction, the third direction, and the fourth direction may be pre-defined directions, and any two directions may be different. In some embodiments, more directions may be pre-defined, such as a fifth direction, etc., and the present invention does not limit the number of directions.

[0058] refer to Figure 1 The detection data in the first direction may include visual images collected by cameras a1, a4, and a5, the laser point cloud generated by the millimeter-wave radar b1, and the laser point cloud generated by the laser radars c1 and c4; the detection data in the second direction may include visual images collected by cameras a6 and a7, the laser point cloud generated by the millimeter-wave radars b2 and b3, and the laser point cloud generated by the laser radars c2 and c3; the detection data in the third direction may include visual images collected by cameras a8 and a9; the detection data in the fourth direction may include visual images collected by cameras a2 and a3, the laser point cloud generated by the millimeter-wave radars b4 and b5, and the laser point cloud generated by the laser radars c5 and c6.

[0059] Based on the above description, since the straight-ahead state indicates that the processing priority of the vehicle's detection data in the first and second directions is higher than the processing priority of the vehicle's detection data in the third and fourth directions, the chip prioritizes the following data when processing the detection data: visual images collected by cameras a1, a4, a5, a6, and a7, laser point clouds generated by millimeter-wave radars b1, b2, and b3, and laser point clouds generated by lidars c1, c2, c3, and c4. After processing these data or after a preset time interval (such as 10ms), the chip then processes the following remaining data: visual images collected by cameras a2, a3, a8, and a9, laser point clouds generated by millimeter-wave radars b4 and b5, and laser point clouds generated by lidars c5 and c6.

[0060] Optionally, the processing priorities of the vehicle's detection data in the first and second directions can be the same or different. This can be further divided based on data such as the vehicle's speed, or pre-configured. Similarly, the processing priorities of the vehicle's detection data in the third and fourth directions can be the same or different.

[0061] It should be noted that the present invention takes the example of dividing the processing priority of the detection data into two levels (the first direction and the second direction are one level, and the third direction and the fourth direction are another level), but is not limited to two levels, that is, the present invention does not limit the number of levels of processing priority. In some embodiments, the number of levels of processing priority of the detection data can be corresponding to the number of pre-divided directions. For example, the processing priority of the detection data is divided into four levels, corresponding to the first direction, the second direction, the third direction and the fourth direction, respectively. In other words, the first direction, the second direction, the third direction and the fourth direction correspond to different detection data processing priorities.

[0062] Non-straight travel status indication: The processing priority of the vehicle's detection data in the second and fourth directions is higher than the processing priority of the vehicle's detection data in the first and third directions. It can be seen that the processing priority of the detection data indicated by the non-straight travel status is opposite to the processing priority of the detection data indicated by the straight travel status. For a detailed description, please refer to the above content and will not be repeated here.

[0063] In summary, by prioritizing the processing of detection data in different directions, all detection data can be divided into multiple copies (two copies in the above example). In this way, the chip can avoid processing all detection data at the same time and instead process them in sequence. This will undoubtedly reduce the concurrency requirements for the chip and, in turn, reduce the computing power requirements for the chip.

[0064] In the embodiment of the present invention, the detection data includes the laser point cloud and visual image described above. In addition, it may also include high-precision map information and other data that can be used to perceive the surrounding environment, which is not limited in the embodiment of the present invention.

[0065] Step 230 : Process the detection data from different directions of the vehicle in sequence according to the processing priorities of the detection data from different directions of the vehicle.

[0066] In one possible implementation, the chip can process the vehicle's detection data from different directions sequentially based on their processing priorities. For example, when traveling straight ahead, the chip processes the detection data from the first and second directions at the current moment. After processing the detection data from the first and second directions is complete, or after a preset time interval has elapsed, the chip processes the detection data from the third and fourth directions. The preset time interval can be a value preset based on experience and is not limited in this disclosure.

[0067] In one possible implementation, the driving data also includes the driving speed; based on this, the chip can determine the processing range of the detection data according to the driving speed; and then process the detection data within the processing range in sequence according to the processing priority of the detection data in different directions of the vehicle. Among them, the driving speed is positively correlated with the processing range. The following example takes three levels of processing ranges as an example. If the chip determines that the driving speed is less than or equal to the second threshold, the processing range of the detection data is determined to be the first range; if the chip determines that the driving speed is greater than the second threshold and less than or equal to the third threshold, the processing range of the detection data is determined to be the second range; if the chip determines that the driving speed is greater than the third threshold, the processing range of the detection data is determined to be the third range. Among them, the third threshold is greater than the second threshold, the second range is greater than the first range, and the third range is greater than the second range. The above thresholds and ranges can be values ​​based on empirical thresholds, and the present invention is not limited thereto.

[0068] For example, the second threshold is 60 (the unit can be km / h, which will not be repeated later), the third threshold is 80, the first range is within 60m in front of the vehicle, the second range is within 80m in front of the vehicle, and the third range is all ranges in front of the vehicle. Taking the straight-ahead state as an example, when the vehicle's driving speed is below 60km / h, the chip processes the detection data within 60m in the first and second directions. After the detection data within 60m in the first and second directions is processed, or after a preset time interval, the detection data within 60m in the third and fourth directions is processed. Similarly, when the vehicle's driving speed is 60-80km / h, the chip processes the detection data within 80m in the first and second directions. After the detection data within 80m in the first and second directions is processed, or after a preset time interval, the detection data within 80m in the third and fourth directions is processed.

[0069] It should be noted that the processing range can be further divided into more levels, and this is not limited by the present invention. As can be seen, by eliminating detection data outside the processing range based on the detection data's processing range, the amount of detection data required to be processed by the chip can be further reduced, thereby lowering the chip's computing power requirements and improving the chip's efficiency in processing detection data. This embodiment of the present invention divides the detection data processing range into three levels to avoid placing computing pressure on the chip due to excessive processing range levels.

[0070] In summary, by prioritizing detection data from different vehicle directions, all detection data is divided into multiple copies. This allows the chip to process all detection data sequentially, rather than simultaneously. This undoubtedly reduces the chip's concurrent computing power requirements. In other words, the chip processes all detection data sequentially, reducing the chip's computing power requirements and, consequently, the chip's cost.

[0071] Based on the same technical concept, Figure 3 A structural diagram of a data processing device provided by an embodiment of the present invention is exemplarily shown, and the device can execute the above-mentioned data processing method.

[0072] like Figure 3 As shown, the device specifically includes:

[0073] The acquisition module 301 is used to acquire the driving data of the vehicle; the processing module 302 is used to determine the driving status of the vehicle based on the driving data, and the driving status is used to indicate the processing priority of the detection data of different directions of the vehicle; according to the processing priority of the detection data of different directions of the vehicle, the detection data of different directions of the vehicle are processed in turn.

[0074] In one possible implementation, the driving state is a straight-ahead state or a non-straight-ahead state; the straight-ahead state indicates that the processing priority of the detection data of the vehicle in the first direction and the second direction is greater than the processing priority of the detection data of the vehicle in the third direction and the fourth direction; wherein, the first direction is the vehicle driving direction, the second direction is the direction with an angle α with the first direction, 0°<α≤90°, the third direction is the direction opposite to the vehicle driving direction, and the fourth direction is the direction with an angle β with the third direction, 0°<β<90°; the non-straight-ahead state indicates that the processing priority of the detection data of the vehicle in the second direction and the fourth direction is greater than the processing priority of the detection data of the vehicle in the first direction and the third direction.

[0075] In one possible implementation, the driving data includes one or more of the following: steering wheel angle, angular velocity, and wheel angle; based on this, the processing module 302 is specifically used to: when it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel angle are less than or equal to a first threshold, determine that the driving state of the vehicle is a straight-ahead state; when it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel angle are greater than the first threshold, determine that the driving state of the vehicle is a non-straight-ahead state.

[0076] In one possible implementation, the driving data also includes a driving speed; the processing module 302 is specifically used to: determine the processing range of the detection data based on the driving speed, and the driving speed is positively correlated with the processing range; and process the detection data within the processing range in sequence according to the processing priority of the detection data in different directions of the vehicle.

[0077] In one possible implementation, the processing module 302 is specifically used to: if the driving speed is less than or equal to a second threshold, determine that the processing range of the detection data is a first range; if the driving speed is greater than the second threshold and less than or equal to a third threshold, determine that the processing range of the detection data is a second range; wherein, the third threshold is greater than the second threshold, and the second range is greater than the first range; if the driving speed is greater than the third threshold, determine that the processing range of the detection data is a third range; wherein, the third range is greater than the second range.

[0078] In a possible implementation, the detection data includes one or more of the following: laser point cloud, visual image.

[0079] Based on the above embodiments, an embodiment of the present invention further provides a device that can implement the data processing method in the above embodiments and has the functions of the above data processing device. Figure 4 As shown, the device 400 includes: a transceiver 401, a processor 402, and a memory 403. The transceiver 401, the processor 402, and the memory 403 are interconnected.

[0080] Optionally, the transceiver 401, the processor 402, and the memory 403 are interconnected via a bus 404. The bus 404 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, and a control bus. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0081] The transceiver 401 is used to receive and send signals to achieve communication with other devices.

[0082] The functions of the processor 402 may refer to the description in the above embodiments and will not be repeated here.

[0083] The processor 402 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The processor 402 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. When implementing the above functions, the processor 402 may be implemented through hardware, or may also execute corresponding software implementations through hardware. The steps of the method disclosed in conjunction with the above embodiments of the present invention may be directly reflected as being executed by the processor 402, or as being executed by a combination of hardware and software modules in the processor 402.

[0084] The memory 403 is used to store program instructions and data. Specifically, the program instructions may include program code, which includes computer operation instructions. The memory 403 may include volatile memory (volatile memory), such as random access memory (RAM); it may also include non-volatile memory (non-volatile memory), such as at least one disk memory, hard disk drive (HDD), or solid state drive (SSD). The memory 403 can also be any other medium that can be used to carry or store program code in the form of instructions or data structures and can be accessed by a computer, and the present invention is not limited to this. The processor 402 executes the program instructions stored in the memory 403 to implement the above functions, thereby realizing the method provided in the above embodiment.

[0085] Based on the above embodiments, the present invention further provides a vehicle comprising the above-mentioned data processing device and a sensing device; wherein the sensing device is configured to generate detection data. Optionally, the sensing device comprises one or more of the following: a laser radar, a millimeter-wave radar, and a camera.

[0086] Based on the above embodiments, the present invention further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a computer, the computer executes the method provided in the above embodiments.

[0087] Optionally, the above-mentioned computer may include, but is not limited to, communication devices such as terminal devices and network devices.

[0088] The storage medium may be any available medium that can be accessed by a computer. By way of example and not limitation, computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0089] Based on the same technical concept, an embodiment of the present invention further provides a computer device, including:

[0090] a memory for storing program instructions;

[0091] The processor is used to call the program instructions stored in the memory and execute the above data processing method according to the obtained program.

[0092] Based on the same technical concept, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the data processing method in the above area.

[0093] Based on the same technical concept, an embodiment of the present invention further provides a chip, which is used to read a computer program stored in a memory to implement the method provided in the above embodiment. Optionally, the chip may include a processor, which is coupled to the memory and is used to read the computer program stored in the memory to implement the method provided in the above embodiment. Optionally, the chip may also include components such as a memory, a communication interface, and a power supply module. The memory is used to store computer programs; the communication interface is used to receive and send data; and the power supply unit is used to power the processor.

[0094] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A data processing method, characterized in that: include: Obtain vehicle driving data; determining a driving state of the vehicle according to the driving data, wherein the driving state is used to indicate a processing priority of detection data of different directions of the vehicle; The detection data from different directions of the vehicle are processed in sequence according to the processing priority of the detection data from different directions of the vehicle.

2. The method according to claim 1, wherein The driving state is a straight driving state or a non-straight driving state; The straight-ahead state indicates that the processing priority of the detection data of the vehicle in the first direction and the second direction is greater than the processing priority of the detection data of the vehicle in the third direction and the fourth direction; wherein the first direction is the vehicle's traveling direction, the second direction is a direction with an angle α with the first direction, 0°<α≤90°, the third direction is a direction opposite to the vehicle's traveling direction, and the fourth direction is a direction with an angle β with the third direction, 0°<β<90°; The non-straight-travel state indicates that a processing priority of the detection data of the vehicle in the second direction and the fourth direction is greater than a processing priority of the detection data of the vehicle in the first direction and the third direction.

3. The method according to claim 2, wherein The driving data includes one or more of the following: steering wheel angle, angular velocity, wheel deflection angle; Determining the driving state of the vehicle according to the driving data includes: When it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel deflection angle are less than or equal to a first threshold, determining that the driving state of the vehicle is a straight-ahead state; When it is determined that the steering wheel angle, and / or the angular velocity, and / or the wheel deflection angle are greater than the first threshold, it is determined that the driving state of the vehicle is a non-straight driving state.

4. The method according to claim 3, wherein The driving data also includes driving speed; The processing of the detection data of the vehicle in different directions in sequence according to the processing priority of the detection data of the vehicle in different directions includes: determining a processing range of the detection data according to the driving speed, wherein the driving speed is positively correlated with the processing range; The detection data within the processing range are processed in sequence according to the processing priority of the detection data in different directions of the vehicle.

5. The method according to claim 4, wherein Determining the processing range of the detection data according to the driving speed includes: If the driving speed is less than or equal to a second threshold, determining that the processing range of the detection data is a first range; If the driving speed is greater than the second threshold and less than or equal to a third threshold, determining that the processing range of the detection data is a second range; wherein the third threshold is greater than the second threshold, and the second range is greater than the first range; If the driving speed is greater than the third threshold, the processing range of the detection data is determined to be a third range; wherein the third range is greater than the second range.

6. The method according to any one of claims 1 to 5, characterized in that The detection data includes one or more of the following: laser point cloud, visual image.

7. A data processing device, characterized in that: include: An acquisition module, used to acquire vehicle driving data; A processing module is used to determine the driving status of the vehicle based on the driving data, and the driving status is used to indicate the processing priority of the detection data in different directions of the vehicle; according to the processing priority of the detection data in different directions of the vehicle, the detection data in different directions of the vehicle are processed in sequence.

8. A vehicle, characterized in that: It comprises a data processing device and a sensing device as claimed in claim 7; wherein the sensing device is used to generate detection data.

9. A computer device, characterized in that: include: a memory for storing program instructions; A processor, configured to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 6 according to the obtained program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

Images