An intelligent driving vehicle environment perception method, system, device and medium

Abstract

The application provides a kind of intelligent driving vehicle environment perception method, system, equipment and medium, first acquire the image of target vehicle in test scene, and identify image, determine lane line, obstacle and passable space in image;Again identify the distance of target vehicle and surrounding vehicle, the driving speed of surrounding vehicle, the azimuth angle information of surrounding vehicle and target vehicle;Then fuse lane line, obstacle, passable space, the distance of target vehicle and surrounding vehicle, the driving speed of surrounding vehicle and the azimuth angle information of surrounding vehicle and target vehicle, and determine the safe driving speed of target vehicle, acceleration decision information, deceleration decision information and steering decision information based on fusion result;Finally feedback to target vehicle, to carry out intelligent driving control to target vehicle.The application can meet the use needs of simulation test, function test, road test, multi-scene application and the like by constructing the multi-modal technology system of environment perception design.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, system, device and medium for environmental perception of intelligent driving vehicles. Background Technology

[0002] With the rapid development of demand for intelligent driving experiences, assisted driving, autonomous driving, and driverless driving have become the development directions for research and application of intelligent automotive technologies. Vehicle safety is the core and focus of intelligent driving, and environmental perception, task planning, behavioral decision-making, and control execution—all related to vehicle safety—are the main technical aspects of intelligent driving research and application. Environmental perception, as a prerequisite, is both a prerequisite input for achieving driving safety and a crucial guarantee for the realization of safety functions. The comprehensiveness, accuracy, precision, and real-time performance of perception results are directly related to the rationality of the system architecture design.

[0003] Currently, roads, traffic, and obstacles within passable spaces constitute an extremely complex external environment for perception. Some targets are also in a dynamic state of change. Furthermore, factors such as weather, lighting, rain, fog, obstruction, intrusion, and high overlap of longitudinal targets increase the uncertainty of perception, posing a significant challenge to the stable implementation of intelligent driving functions. In addition to perceiving external vehicle information, vehicles must also accurately perceive their own status, relative distances to obstacles, speeds, and orientations during dynamic driving. Therefore, due to the complexity of vehicle environmental perception, current applications suffer from the following main shortcomings:

[0004] 1) Incomplete detection range creates blind spots. Due to the large size of some vehicles (such as commercial vehicles), with large height and length dimensions, the cab and cargo box are separate, and the cab and cargo box are usually not the same width. The cab needs to be tilted. The superstructure of special vehicles also needs to be tilted. The sensor installation and layout need to be carefully deployed and calibrated to achieve full-area perception. Otherwise, it will lead to insufficient near-field perception around the vehicle, especially the identification of low obstacles around the vehicle. Long-term use poses a high risk of danger and injury.

[0005] 2) Insufficient forward sensing distance and range limits the safe driving of vehicles at medium and high speeds. Commercial vehicles are heavy and have great driving inertia, so they need to sense driving conditions at medium and long distances in advance and slow down in advance. Emergency braking can cause great harm to people and cargo, which is not conducive to scenario expansion and application.

[0006] 3) Single sensors, limited by hardware quality, perception capabilities, and environmental conditions, impact vehicle safety and are only suitable for single driver assistance or warning functions. Common combinations of visual perception cameras and cameras can effectively perceive and recognize textures, colors, and numbers. However, their main shortcomings include blinding in strong light and backlight, and functional deficiencies in low light and dim environments. Furthermore, the potential for virtual imaging in a darkroom due to installation behind the windshield is a major point of criticism. Additionally, pixel limitations lead to estimation errors between distant imaging pixels and actual distance values, making accurate depth and distance assessment a significant weakness of camera vision. Millimeter-wave radar lacks sufficient height perception capabilities, is sensitive to metal and obstructions, and exhibits large blind spots near the vehicle due to its small field of view. Ultrasonic radar only provides near-field perception and has insufficient distance accuracy. The limitations of sensor near-field distance detection accuracy in meeting the millimeter-level high-precision positioning requirements of special scenarios such as airport baggage carts and passenger boarding vehicles hinder vehicle deployment, normal operation, and replication. No single sensor is adequate for advanced autonomous driving; multi-sensor perception fusion is the future direction of intelligent driving.

[0007] 4) The effects of perception results outside the passable space can trigger system functions, leading to unexpected impacts on driving comfort. This is especially true on curves. Filtering the data area improves the applicability of the recognition algorithm, meeting the needs of higher vehicle speeds and complex road scenarios.

[0008] 5) The perception system design suffers from insufficient portability and reusability in various vehicle models and application scenarios. The design scheme lacks strong scenario portability, making it difficult to replicate in batches and apply in mass production, which is detrimental to the development of intelligent automotive applications. Summary of the Invention

[0009] In view of the shortcomings of the prior art described above, the purpose of this application is to provide an environmental perception method and system for intelligent driving vehicles, so as to solve the problems existing in the environmental perception of intelligent driving vehicles in the prior art.

[0010] To achieve the above and other related objectives, this application provides a method for environmental perception in intelligent driving vehicles, comprising the following steps:

[0011] The system acquires images of the target vehicle in a test scenario and identifies lane lines, obstacles, and passable spaces within the images; the target vehicle may be a real-time or pre-determined vehicle.

[0012] The system identifies the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information of the surrounding vehicles relative to the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle.

[0013] The information on lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth angle between surrounding vehicles and the target vehicle are fused together, and the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are determined based on the fusion results.

[0014] The safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are fed back to the target vehicle to enable intelligent driving control of the target vehicle.

[0015] In one embodiment of this application, the process of acquiring an image of the target vehicle in a test scenario and identifying lane lines, obstacles, and passable space from the image includes:

[0016] Install one or more image capturing devices on the target vehicle;

[0017] The image of the target vehicle in the test scenario is obtained by using one or more image capturing devices to capture images of the target vehicle in the test scenario, either in a driving state or a stopped state. This image is denoted as the target image.

[0018] The target image is identified to determine the lane lines, obstacles, and passable space within it.

[0019] In one embodiment of this application, the test scenario includes a test site scenario and driving condition status;

[0020] The test site scenarios include at least one of the following: closed site road scenario, semi-open site road scenario, and open site road scenario;

[0021] The driving conditions include at least one of the following: traffic control, road conditions, traffic environment conditions, route setting, vehicle driving status, and driving speed limit.

[0022] In one embodiment of this application, before acquiring an image of the target vehicle in a test scenario, the method further includes: acquiring a pre-determined list of vehicle intelligent driving levels and test function requirements, and determining the test scenario based on the vehicle intelligent driving levels and the list of test function requirements;

[0023] The vehicle's intelligent driving levels include: Level 1, Level 2, Level 3, Level 4, and Level 5 intelligent driving levels; and the intelligence level of Level 5 is greater than that of Level 4, the intelligence level of Level 4 is greater than that of Level 3, the intelligence level of Level 3 is greater than that of Level 2, and the intelligence level of Level 2 is greater than that of Level 1.

[0024] In one embodiment of this application, the process of identifying the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle includes:

[0025] Multiple sensors are installed on the target vehicle, and data from each sensor is recorded when the target vehicle is in a driving or stationary state in the test scenario.

[0026] The data from each sensor is analyzed to identify the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle.

[0027] In one embodiment of this application, the plurality of sensors include: a lidar sensor, a millimeter-wave radar sensor, and an ultrasonic radar sensor.

[0028] In one embodiment of this application, the image capturing device includes at least one of the following: a monocular camera, a binocular camera, and a surround-view camera.

[0029] This application also provides an intelligent driving vehicle environmental perception system, the system comprising:

[0030] An image perception module is used to acquire images of a target vehicle in a test scenario, wherein the target vehicle includes real-time or pre-determined vehicles;

[0031] An image recognition module is used to recognize the image and determine the lane lines, obstacles, and passable space in the image;

[0032] The sensor perception module is used to identify the distance between the target vehicle and surrounding vehicles, the driving speed of the surrounding vehicles, and the azimuth information of the surrounding vehicles and the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle;

[0033] The data fusion module is used to fuse the lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between surrounding vehicles and the target vehicle, and to determine the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle based on the fusion results.

[0034] The intelligent driving module is used to feed back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle in order to perform intelligent driving control on the target vehicle.

[0035] This application also provides a computer device, including:

[0036] processor; and,

[0037] A computer-readable medium storing instructions that, when executed by the processor, cause the device to perform any of the methods described above.

[0038] This application also provides a computer-readable medium having instructions stored thereon, the instructions being loaded by a processor and executed as described in any of the above methods.

[0039] As described above, this application provides a method, system, device, and medium for environmental perception in intelligent driving vehicles, which has the following beneficial effects:

[0040] This application first acquires images of the target vehicle in a test scenario and identifies lane lines, obstacles, and passable space in the images. Then, it identifies the distance between the target vehicle and surrounding vehicles, the speed of surrounding vehicles, and the azimuth information between the target vehicle and surrounding vehicles. Next, it fuses the information on lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between the target vehicle and surrounding vehicles. Based on the fusion result, it determines the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information. Finally, it feeds back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle for intelligent driving control. Therefore, this application, starting from the functional requirements of intelligent driving, constructs a multimodal technology system for environmental perception design, which can cover centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road test perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It is adaptable to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and even achieves functional coverage for closed scenarios, fixed routes, and open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications. Attached Figure Description

[0041] Figure 1 This is a schematic diagram illustrating an exemplary system architecture that applies the technical solutions in one or more embodiments of this application;

[0042] Figure 2 This is a flowchart illustrating an intelligent driving vehicle environment perception method provided in one embodiment of this application.

[0043] Figure 3 This is a schematic diagram of the architecture of a vehicle perception function provided in one embodiment of this application;

[0044] Figure 4 This is a schematic diagram illustrating the path for achieving intelligent driving function requirements according to an embodiment of this application;

[0045] Figure 5 This is a schematic diagram of the overall technical architecture for intelligent driving perception provided in one embodiment of this application;

[0046] Figure 6 This is a schematic diagram of the sensor field of view and detection distance provided in one embodiment of this application;

[0047] Figure 7 This is a schematic diagram of the hardware structure of an intelligent driving vehicle environmental perception system provided in one embodiment of this application.

[0048] Figure 8 This is a schematic diagram of the hardware structure of a computer device suitable for implementing one or more embodiments of this application. Detailed Implementation

[0049] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0051] Figure 1 A schematic diagram of an exemplary system architecture that can apply the technical solutions of one or more embodiments of this application is shown. Figure 1 As shown, the system architecture 100 may include terminal device 110, network 120, and server 130. Terminal device 110 may include various electronic devices such as smartphones, tablets, laptops, and desktop computers. Server 130 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, such as a wired communication link or a wireless communication link.

[0052] Depending on the implementation requirements, the system architecture in this application embodiment can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group composed of multiple server devices. In addition, the technical solutions provided in this application embodiment can be applied to terminal device 110, or to server 130, or can be implemented jointly by terminal device 110 and server 130. This application does not impose any special limitations on this.

[0053] In one embodiment of this application, the terminal device 110 or server 130 can acquire images of the target vehicle in a test scenario, identify the lane lines, obstacles, and passable space in the images, and then identify the distance between the target vehicle and surrounding vehicles, the driving speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle. Next, the lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, driving speed of the surrounding vehicles, and azimuth information between the surrounding vehicles and the target vehicle are fused together, and based on the fusion result, the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are determined. Finally, the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are fed back to the target vehicle for intelligent driving control. By utilizing terminal device 110 or server 130 to execute the environmental perception method for intelligent driving vehicles, starting from the functional requirements of intelligent driving, a multimodal technology system for environmental perception design can be constructed. This system covers centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road test perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It can adapt to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and even achieve functional coverage for closed scenarios, fixed routes, and open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications.

[0054] The above section introduced the exemplary system architecture of the application of the technical solution of this application. Next, we will continue to introduce the intelligent driving vehicle environment perception method of this application.

[0055] Figure 2 A schematic flowchart of an intelligent driving vehicle environment perception method according to an embodiment of this application is shown. Specifically, in an exemplary embodiment, as follows... Figure 2 As shown in the figure, this embodiment provides an environmental perception method for intelligent driving vehicles, which includes the following steps:

[0056] S210, acquire an image of the target vehicle in the test scenario, and identify the lane lines, obstacles, and passable space in the image; the target vehicle includes real-time or pre-determined vehicles. In this embodiment, the target vehicle includes real-time or pre-determined commercial vehicles, private vehicles, public vehicles, etc. The test scenario in this embodiment includes a test site scenario and driving condition states; wherein, the test site scenario includes at least one of the following: closed site road scenario, semi-open site road scenario, and open site road scenario; the driving condition states include at least one of the following: traffic control, road conditions, traffic environment state, route setting, vehicle driving state, and driving speed limit. As an example, this embodiment first identifies six types of element characteristics of the test scenario, identifying the geometric features, physical features, and logical features of the test scenario, and obtaining direct elements such as distance, width, height, speed, azimuth angle, positioning, and timing, which serve as inputs and constraints for subsequent matching, simulation, and testing of vehicle functions. The test scenarios for intelligent driving commercial vehicles are shown in Table 1 below.

[0057] Table 1 Test Scenarios for Intelligent Driving Commercial Vehicles

[0058]

[0059] As shown in Table 1, closed environments and open highways offer better conditions for intelligent driving applications due to their lower speeds and simpler environments. However, complex urban road environments present the true test and challenge for all types of intelligent driving. Therefore, this embodiment places higher demands on the front-end perception architecture, requiring thorough analysis and adaptation.

[0060] S220, identifying the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle. Specifically, the process of identifying the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle in this embodiment includes: installing multiple sensors on the target vehicle and recording the data of each sensor when the target vehicle is in a driving state or a stopped state in the test scenario; parsing the data of each sensor to identify the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle. The multiple sensors include: lidar sensors, millimeter-wave radar sensors, and ultrasonic radar sensors. In this embodiment, the sensors installed on the target vehicle are as follows: Figure 3 As shown. In Figure 3In this embodiment, the target vehicle is equipped with a front lidar, a left lidar, a right lidar, a rear lidar, and a millimeter-wave radar. The front lidar, left lidar, right lidar, and rear lidar are connected to a network switch via Ethernet. The network switch is connected to the automated control unit (ACU) via Ethernet. The millimeter-wave radar is connected to the automated control unit (ACU) via a CAN bus (Controller Area Network).

[0061] S230, the lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information of surrounding vehicles and the target vehicle are fused, and based on the fusion result, the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are determined. Figure 3 As shown, this embodiment constructs the overall technical architecture of connected and cooperative autonomous driving, which, even in its simplified form, can also meet different assisted driving function requirements. The camera vision perception system, acting as an environmental information perception unit, sends video images to the Automated Control Unit (ACU) via a switch for image processing, identifying lane lines, obstacles, and passable space. Similarly, millimeter-wave radar identifies the distance, speed, and azimuth angle of the vehicle ahead, which the ACU calculates and verifies. LiDAR, used in higher-level autonomous driving, combines the functions of the former two, improving the completeness and accuracy of environmental and target recognition. All data is fused in the ACU controller, defining target categories, distances, speeds, and angles, determining the vehicle's location and its relative position to each target, determining the vehicle's safe driving speed, acceleration / deceleration, and steering decisions, and sending the decision results to the chassis controllers in real time via a gateway. This controls the drive, transmission, steering, and upper body functions, returning real-time data to the ACU as one of the bases for the next decision, and continuously controlling the vehicle's intelligent driving functions.

[0062] S240, the safe driving speed of the target vehicle, the acceleration decision information of the target vehicle, the deceleration decision information of the target vehicle, and the steering decision information of the target vehicle are fed back to the target vehicle to perform intelligent driving control on the target vehicle.

[0063] Therefore, this embodiment, starting from the functional requirements of intelligent driving, constructs a multimodal technology system for environmental perception design, which can cover centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road test perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It is adaptable to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and even achieves functional coverage for closed scenarios, fixed routes, and open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications.

[0064] In an exemplary embodiment, the process of acquiring an image of a target vehicle in a test scenario and identifying lane lines, obstacles, and passable space from the image includes: mounting one or more image capturing devices on the target vehicle; capturing images of the target vehicle in a driving or stopped state in the test scenario using the one or more image capturing devices to obtain an image of the target vehicle in the test scenario, denoted as the target image; and identifying lane lines, obstacles, and passable space from the target image. As an example, such as... Figure 3 As shown, the image capturing devices installed on the target vehicle in this embodiment include, but are not limited to: monocular camera, binocular camera, and surround-view camera.

[0065] According to the above description, in an exemplary embodiment, before acquiring the image of the target vehicle in the test scenario, the method further includes: acquiring a pre-determined list of vehicle intelligent driving levels and test function requirements, and determining the test scenario based on the vehicle intelligent driving levels and the test function requirements list; wherein, the vehicle intelligent driving levels include: L1 level intelligent driving level, L2 level intelligent driving level, L3 level intelligent driving level, L4 level intelligent driving level, and L5 level intelligent driving level; and the intelligence level of L5 level intelligent driving level is greater than that of L4 level intelligent driving level, the intelligence level of L4 level intelligent driving level is greater than that of L3 level intelligent driving level, the intelligence level of L3 level intelligent driving level is greater than that of L2 level intelligent driving level, and the intelligence level of L2 level intelligent driving level is greater than that of L1 level intelligent driving level. Specifically, the main path for identifying intelligent driving function requirements in this embodiment is as follows: Figure 4 As shown. In Figure 4In this embodiment, the implementation of L0-L2 level driving assistance functions such as warning, keeping, and collision avoidance mainly relies on the sensors and recognition algorithms described in ①, with the execution system ④ responding accordingly. This includes sound, light, vibration, and even reducing power to issue warning signals, alerting the driver to correct the current vehicle state and promptly control driving safety. For L3 and above autonomous driving, since the main entity operating the vehicle in real time shifts to the autonomous driving system, more accurate, complete, and real-time environmental perception results are required as input; task planning and behavioral decision-making are needed to replace manual operation; more complex operating system software and powerful computing power are required to achieve precise control of the vehicle. Furthermore, the vehicle's real-time motion state parameters are used as input for a new round of correction and matching with the next perception. As described in this embodiment, whether it is a single driving assistance function or a complex autonomous driving function, environmental perception is always of paramount importance for safe vehicle operation.

[0066] Whether it's autonomous single-vehicle intelligence or intelligent vehicles under the connected vehicle-road cooperative technology route, the limitations of single-type sensor environmental perception are increasingly constrained by safety concerns. Multi-sensor fusion, leveraging complementary strengths to jointly construct a safe, efficient, and real-time perception system has become an important research and application direction. Even with the development and maturity of vehicle-road cooperative systems, the perception capabilities of onboard systems remain a crucial means and guarantee for vehicle driving safety. According to the requirements of intelligent driving functions, corresponding perception technology solutions can be combined and set to adapt to the needs of environmental perception functions with varying degrees of complexity. Therefore, in another exemplary embodiment of this application, this embodiment provides an intelligent driving vehicle environmental perception method, including the following steps: identifying the main paths to achieve intelligent driving function requirements; defining the applicable associations between different usage scenarios and intelligent driving functions; deploying the overall technical architecture of vehicle perception functions; and performing vehicle perception according to the overall technical architecture.

[0067] Specifically, the process of identifying the main paths to achieve intelligent driving function requirements includes: First, the implementation of L0-L2 level driving assistance functions such as warning, keeping, and collision avoidance mainly relies on the sensors and recognition algorithms mentioned in ①, with the execution system ④ responding accordingly. This includes sound, light, vibration, and even reducing power to issue warning signals, alerting the driver to correct the current vehicle state and promptly control driving safety. Second, for L3 and above autonomous driving, since the main entity operating the vehicle in real time changes to the autonomous driving system, more accurate, complete, and real-time environmental perception results are required as input; task planning and behavioral decision-making are needed to replace manual operation; more complex operating system software and powerful computing power are required to achieve precise control of the vehicle, and the real-time motion state parameters of the vehicle are also used as input for a new round of correction and matching with the next perception. As can be seen from the above, whether it is a single driving assistance function or a complex autonomous driving function, environmental perception is always of paramount importance for the safe operation of the vehicle.

[0068] The process of defining the applicable associations between different usage scenarios and intelligent driving functions includes: identifying six types of scenario characteristics, including geometric, physical, and logical features. The technical focus is on direct elements such as distance, width, height, speed, azimuth, positioning, and timing, which serve as inputs and constraints for subsequent matching, simulation, and testing of vehicle functions. Specifically, closed scenarios and open highways, especially the former, offer better conditions for intelligent driving applications due to their lower speeds and relatively simpler environments. However, complex urban road environments present the true test and challenge for various types of intelligent driving. Therefore, the front-end perception architecture requires higher standards and thorough analysis. Furthermore, this embodiment analyzes the correspondence between scenarios and the requirements of different autonomous driving levels based on scenario feature recognition. Different functional combinations and selections are set according to scenario constraints to determine design operating conditions and ensure the effectiveness and safety of the technical solution for the corresponding scenarios. The association and matching relationships between scenarios and the requirements of different autonomous driving levels are shown in Table 2. In Table 2, "●" indicates applicable, "◎" indicates optional, and "—" indicates not recommended.

[0069] Table 2 shows the correlation and matching relationship between scenarios and the requirements of different levels of autonomous driving.

[0070]

[0071]

[0072] Figure 3A general technical architecture for connected and collaborative autonomous driving was constructed, which, even when simplified, can accommodate different assisted driving function requirements. The overall technical architecture for deploying vehicle perception functions, and the process of vehicle perception according to this architecture, includes: a camera vision perception system, acting as an environmental information perception system, sends video images to the autonomous driving controller (ACU) via a switch for image processing, identifying lane lines, obstacles, and passable space; similarly, millimeter-wave radar identifies the distance, speed, and azimuth angle of the vehicle ahead, which the ACU calculates and verifies; lidar, used for higher-level autonomous driving, combines the functions of the former two, improving the completeness and accuracy of environmental and target recognition. All data is fused in the ACU controller, defining target categories, distances, speeds, and angles, determining the vehicle's location and its relative position to each target, determining the vehicle's safe driving speed, acceleration / deceleration, and steering decisions, and sending the decision results to the chassis controllers in real time via a gateway. This controls the drive, transmission, steering, and upper body functions, and returns real-time data to the ACU as one of the bases for the next decision. This iterative control enables the vehicle's intelligent driving functions. Therefore, in this embodiment, regardless of whether it's an autonomous single-vehicle intelligence or an intelligent vehicle under the connected vehicle-road cooperative technology route, the limitations of single-type sensor environmental perception are increasingly constrained by safety concerns. Multi-sensor fusion, leveraging complementary strengths to jointly construct a safe, efficient, and real-time perception system has become an important research and application direction. Even with the development and maturity of vehicle-road cooperative systems, the perception capabilities of onboard systems remain a crucial means and guarantee for vehicle driving safety. According to the functional requirements of intelligent driving, corresponding perception technology solutions can be combined and configured to adapt to the environmental perception needs of varying complexity.

[0073] To meet the needs of different usage scenarios, match the functions indicated in Table 2, and then... Figure 4 The combination of the indicated sensor functions allows for the development of corresponding perception system solutions. For example, for driver assistance functions such as lane departure warning, a combination of vision and short-range millimeter-wave radar can be used, with the appropriate number deployed based on the vehicle's external dimensions. This achieves ideal results while effectively controlling costs, facilitating the promotion and application of technology and products, and enabling product upgrades. Similarly, when facing the demands of complex environments, in addition to fully utilizing the advantages of visual perception systems in color, texture, and brightness perception, long-range millimeter-wave radar with advantages in longitudinal distance and speed perception must be added to achieve controllable distance and speed. Furthermore, for Level 3 and above autonomous driving, high-precision maps provide dynamic support, along with high-precision positioning equipment such as GNSS+RTK+IMU, enabling beyond-line-of-sight information interaction. In systems enabling remote driving and networked operation, V2X vehicle-to-everything (V2X) communication and roadside perception systems are further employed to meet the needs of high-level autonomous driving.

[0074] Furthermore, when deploying a sensing system, such as Figure 6 As shown, after the field of view and detection distance parameters of various sensors are determined in this embodiment, the system can be deployed. The main adjustments and verifications are made to the system's detectable range, and a three-dimensional envelope perception system that can cover everything from directional perception to full-domain perception, and combine far, medium and near / high, medium and low ranges can be established to meet the usage requirements of single or combined functions, as well as the needs of autonomous driving systems.

[0075] In summary, this application provides an environmental perception method for intelligent driving vehicles. First, it acquires an image of the target vehicle in a test scenario and identifies lane lines, obstacles, and passable space within the image. Next, it identifies the distance between the target vehicle and surrounding vehicles, the speed of surrounding vehicles, and the azimuth information between the target vehicle and surrounding vehicles. Then, it fuses the information on lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between the target vehicle and surrounding vehicles. Based on the fusion result, it determines the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information. Finally, it feeds back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle for intelligent driving control. Therefore, this application, starting from the functional requirements of intelligent driving, constructs a multimodal technology system for environmental perception design. This system can cover centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road testing perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It is adaptable to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and ultimately achieves functional coverage for closed scenarios, fixed routes, and even open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications. Based on a systematic analysis of the usage scenarios and characteristics of intelligent driving commercial vehicles and different levels of intelligent driving functions, this method proposes a process-oriented design approach and table lookup analysis approach for conducting perception system design. First, the design approach has strong practicality. Based on scenario feature analysis, it can better propose combined solutions that meet the functional requirements of driving. It is both technically sound and economically efficient, avoiding the recognition defects caused by insufficient systematic analysis and the high costs and higher performance requirements of hardware systems caused by overly redundant and complex technical solutions. Secondly, following the above process, multiple technical paths for realizing functional requirements can be explored, verifying the effectiveness of using different types of perception systems to address the same functional requirements in different scenarios. For example, for L3 autonomous logistics vehicles used in the park, which travel at low speeds, a system based on LiDAR as the core perception system has been established. This system not only meets L3 perception requirements but also enables assisted driving functions such as AEBS, eliminating the need for millimeter-wave radar design and deployment, thus reducing operating costs and system complexity.

[0076] like Figure 7 As shown, this application also provides an intelligent driving vehicle environmental perception system, the system comprising:

[0077] The image perception module 710 is used to acquire images of the target vehicle in the test scenario, wherein the target vehicle includes real-time or pre-determined vehicles. In this embodiment, the target vehicle includes real-time or pre-determined commercial vehicles, private vehicles, public vehicles, etc. The test scenario in this embodiment includes a test site scenario and driving condition states; wherein, the test site scenario includes at least one of the following: closed site road scenario, semi-open site road scenario, and open site road scenario; the driving condition states include at least one of the following: traffic control, road conditions, traffic environment state, route setting, vehicle driving state, and driving speed limit. As an example, this embodiment first identifies six types of characteristic elements of the test scenario, identifying geometric features, physical features, and logical features of the test scenario, and obtaining direct elements such as distance, width, height, speed, azimuth angle, positioning, and timing, which serve as inputs and constraints for subsequent matching, simulation, and testing of vehicle functions. The test scenarios for intelligent driving commercial vehicles are shown in Table 3 below.

[0078] Table 3 Test Scenarios for Intelligent Driving Commercial Vehicles

[0079]

[0080]

[0081] As shown in Table 3, closed environments and open highways offer better conditions for intelligent driving applications due to their lower speeds and simpler environments. However, complex urban road environments present the true test and challenge for all types of intelligent driving. Therefore, this embodiment places higher demands on the front-end perception architecture, requiring thorough analysis and adaptation.

[0082] Image recognition module 720 is used to recognize the image and determine the lane lines, obstacles and passable space in the image;

[0083] The sensor perception module 730 is used to identify the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle. Specifically, the process of identifying the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle in this embodiment includes: installing multiple sensors on the target vehicle and recording the data of each sensor when the target vehicle is in a driving state or a stationary state in the test scenario; parsing the data of each sensor to identify the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle. The multiple sensors include: a lidar sensor, a millimeter-wave radar sensor, and an ultrasonic radar sensor. In this embodiment, the sensors installed on the target vehicle are as follows: Figure 3 As shown. In Figure 3 In this embodiment, the target vehicle is equipped with a front lidar, a left lidar, a right lidar, a rear lidar, and a millimeter-wave radar. The front lidar, left lidar, right lidar, and rear lidar are connected to a network switch via Ethernet. The network switch is connected to the automated driving controller (ACU) via Ethernet. The millimeter-wave radar is connected to the automated driving controller (ACU) via a CAN bus (Controller Area Network).

[0084] The data fusion module 740 is used to fuse the lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between the surrounding vehicles and the target vehicle, and to determine the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle based on the fusion results. Figure 3As shown, this embodiment constructs the overall technical architecture of connected and cooperative autonomous driving, which, even in its simplified form, can also meet different assisted driving function requirements. The camera vision perception system, acting as an environmental information perception unit, sends video images to the Automated Control Unit (ACU) via a switch for image processing, identifying lane lines, obstacles, and passable space. Similarly, millimeter-wave radar identifies the distance, speed, and azimuth angle of the vehicle ahead, which the ACU calculates and verifies. LiDAR, used in higher-level autonomous driving, combines the functions of the former two, improving the completeness and accuracy of environmental and target recognition. All data is fused in the ACU controller, defining target categories, distances, speeds, and angles, determining the vehicle's location and its relative position to each target, determining the vehicle's safe driving speed, acceleration / deceleration, and steering decisions, and sending the decision results to the chassis controllers in real time via a gateway. This controls the drive, transmission, steering, and upper body functions, returning real-time data to the ACU as one of the bases for the next decision, and continuously controlling the vehicle's intelligent driving functions.

[0085] The intelligent driving module 750 is used to feed back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle in order to perform intelligent driving control on the target vehicle.

[0086] Therefore, this embodiment, starting from the functional requirements of intelligent driving, constructs a multimodal technology system for environmental perception design, which can cover centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road test perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It is adaptable to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and even achieves functional coverage for closed scenarios, fixed routes, and open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications.

[0087] In an exemplary embodiment, the process of acquiring an image of a target vehicle in a test scenario and identifying lane lines, obstacles, and passable space from the image includes: mounting one or more image capturing devices on the target vehicle; capturing images of the target vehicle in a driving or stopped state in the test scenario using the one or more image capturing devices to obtain an image of the target vehicle in the test scenario, denoted as the target image; and identifying lane lines, obstacles, and passable space from the target image. As an example, such as... Figure 3As shown, the image capturing devices installed on the target vehicle in this embodiment include, but are not limited to: monocular camera, binocular camera, and surround-view camera.

[0088] According to the above description, in an exemplary embodiment, before acquiring the image of the target vehicle in the test scenario, the system further includes: acquiring a pre-determined list of vehicle intelligent driving levels and test function requirements, and determining the test scenario based on the vehicle intelligent driving levels and the test function requirements list; wherein, the vehicle intelligent driving levels include: L1 level intelligent driving level, L2 level intelligent driving level, L3 level intelligent driving level, L4 level intelligent driving level, and L5 level intelligent driving level; and the intelligence level of L5 level intelligent driving level is greater than that of L4 level intelligent driving level, the intelligence level of L4 level intelligent driving level is greater than that of L3 level intelligent driving level, the intelligence level of L3 level intelligent driving level is greater than that of L2 level intelligent driving level, and the intelligence level of L2 level intelligent driving level is greater than that of L1 level intelligent driving level. Specifically, the main path for identifying intelligent driving function requirements in this embodiment is as follows: Figure 4 As shown. In Figure 4 In this embodiment, the implementation of L0-L2 level driving assistance functions such as warning, keeping, and collision avoidance mainly relies on the sensors and recognition algorithms described in ①, with the execution system ④ responding accordingly. This includes sound, light, vibration, and even reducing power to issue warning signals, alerting the driver to correct the current vehicle state and promptly control driving safety. For L3 and above autonomous driving, since the main entity operating the vehicle in real time shifts to the autonomous driving system, more accurate, complete, and real-time environmental perception results are required as input; task planning and behavioral decision-making are needed to replace manual operation; more complex operating system software and powerful computing power are required to achieve precise control of the vehicle. Furthermore, the vehicle's real-time motion state parameters are used as input for a new round of correction and matching with the next perception. As described in this embodiment, whether it is a single driving assistance function or a complex autonomous driving function, environmental perception is always of paramount importance for safe vehicle operation.

[0089] Whether it's autonomous single-vehicle intelligence or intelligent vehicles under the connected vehicle-road cooperative technology route, the limitations of single-type sensor environmental perception are increasingly constrained by safety concerns. Multi-sensor fusion, leveraging complementary strengths to jointly construct a safe, efficient, and real-time perception system has become an important research and application direction. Even with the development and maturity of vehicle-road cooperative systems, the perception capabilities of onboard systems remain a crucial means and guarantee for vehicle driving safety. According to the requirements of intelligent driving functions, corresponding perception technology solutions can be combined and configured to adapt to the environmental perception needs of varying complexity. Therefore, in another exemplary embodiment of this application, this embodiment provides an intelligent driving vehicle environmental perception system, including the following steps: identifying the main paths to achieve intelligent driving function requirements; defining the applicable associations between different usage scenarios and intelligent driving functions; deploying the overall technical architecture of vehicle perception functions; and performing vehicle perception according to the overall technical architecture.

[0090] Specifically, the process of identifying the main paths to achieve intelligent driving function requirements includes: First, the implementation of L0-L2 level driving assistance functions such as warning, keeping, and collision avoidance mainly relies on the sensors and recognition algorithms mentioned in ①, with the execution system ④ responding accordingly. This includes sound, light, vibration, and even reducing power to issue warning signals, alerting the driver to correct the current vehicle state and promptly control driving safety. Second, for L3 and above autonomous driving, since the main entity operating the vehicle in real time changes to the autonomous driving system, more accurate, complete, and real-time environmental perception results are required as input; task planning and behavioral decision-making are needed to replace manual operation; more complex operating system software and powerful computing power are required to achieve precise control of the vehicle, and the real-time motion state parameters of the vehicle are also used as input for a new round of correction and matching with the next perception. As can be seen from the above, whether it is a single driving assistance function or a complex autonomous driving function, environmental perception is always of paramount importance for the safe operation of the vehicle.

[0091] The process of defining the applicable associations between different usage scenarios and intelligent driving functions includes: identifying six types of scenario characteristics, including geometric, physical, and logical features. The technical focus is on direct elements such as distance, width, height, speed, azimuth, positioning, and timing, which serve as inputs and constraints for subsequent matching, simulation, and testing of vehicle functions. Specifically, closed scenarios and open highways, especially the former, offer better conditions for intelligent driving applications due to their lower speeds and relatively simpler environments. However, complex urban road environments present the true test and challenge for various types of intelligent driving. Therefore, the front-end perception architecture requires higher standards and thorough analysis. Furthermore, this embodiment analyzes the correspondence between scenarios and the requirements of different autonomous driving levels based on scenario feature recognition. Different functional combinations and selections are set according to scenario constraints to determine design operating conditions and ensure the effectiveness and safety of the technical solution for the corresponding scenarios. The association and matching relationships between scenarios and the requirements of different autonomous driving levels are shown in Table 4. In Table 4, "●" indicates applicable, "◎" indicates optional, and "—" indicates not recommended.

[0092] Table 4 shows the correlation and matching relationship between scenarios and the requirements of different levels of autonomous driving.

[0093]

[0094]

[0095] Figure 3A general technical architecture for connected and collaborative autonomous driving was constructed, which, even when simplified, can accommodate different assisted driving function requirements. The overall technical architecture for deploying vehicle perception functions, and the process of vehicle perception according to this architecture, includes: a camera vision perception system, acting as an environmental information perception system, sends video images to the autonomous driving controller (ACU) via a switch for image processing, identifying lane lines, obstacles, and passable space; similarly, millimeter-wave radar identifies the distance, speed, and azimuth angle of the vehicle ahead, which the ACU calculates and verifies; lidar, used for higher-level autonomous driving, combines the functions of the former two, improving the completeness and accuracy of environmental and target recognition. All data is fused in the ACU controller, defining target categories, distances, speeds, and angles, determining the vehicle's location and its relative position to each target, determining the vehicle's safe driving speed, acceleration / deceleration, and steering decisions, and sending the decision results to the chassis controllers in real time via a gateway. This controls the drive, transmission, steering, and upper body functions, and returns real-time data to the ACU as one of the bases for the next decision. This iterative control enables the vehicle's intelligent driving functions. Therefore, in this embodiment, regardless of whether it's an autonomous single-vehicle intelligence or an intelligent vehicle under the connected vehicle-road cooperative technology route, the limitations of single-type sensor environmental perception are increasingly constrained by safety concerns. Multi-sensor fusion, leveraging complementary strengths to jointly construct a safe, efficient, and real-time perception system has become an important research and application direction. Even with the development and maturity of vehicle-road cooperative systems, the perception capabilities of onboard systems remain a crucial means and guarantee for vehicle driving safety. According to the functional requirements of intelligent driving, corresponding perception technology solutions can be combined and configured to adapt to the environmental perception needs of varying complexity.

[0096] To meet the needs of different usage scenarios, match the functions indicated in Table 4, and then... Figure 4 The combination of the indicated sensor functions allows for the development of corresponding perception system solutions. For example, for driver assistance functions such as lane departure warning, a combination of vision and short-range millimeter-wave radar can be used, with the appropriate number deployed based on the vehicle's external dimensions. This achieves ideal results while effectively controlling costs, facilitating the promotion and application of technology and products, and enabling product upgrades. Similarly, when facing the demands of complex environments, in addition to fully utilizing the advantages of visual perception systems in color, texture, and brightness perception, long-range millimeter-wave radar with advantages in longitudinal distance and speed perception must be added to achieve controllable distance and speed. Furthermore, for Level 3 and above autonomous driving, high-precision maps provide dynamic support, along with high-precision positioning equipment such as GNSS+RTK+IMU, enabling beyond-line-of-sight information interaction. In systems enabling remote driving and networked operation, V2X vehicle-to-everything (V2X) communication and roadside perception systems are further employed to meet the needs of high-level autonomous driving.

[0097] Furthermore, when deploying a sensing system, such as Figure 6 As shown, after the field of view and detection distance parameters of various sensors are determined in this embodiment, the system can be deployed. The main adjustments and verifications are made to the system's detectable range, and a three-dimensional envelope perception system that can cover everything from directional perception to full-domain perception, and combine far, medium and near / high, medium and low ranges can be established to meet the usage requirements of single or combined functions, as well as the needs of autonomous driving systems.

[0098] In summary, this application provides an intelligent driving vehicle environmental perception system. First, it acquires images of the target vehicle in a test scenario and identifies lane lines, obstacles, and passable space within the images. Next, it identifies the distance between the target vehicle and surrounding vehicles, the speed of surrounding vehicles, and the azimuth information between the target vehicle and surrounding vehicles. Then, it fuses the information on lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between the target vehicle and surrounding vehicles. Based on the fusion results, it determines the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information. Finally, it feeds back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle for intelligent driving control. Therefore, this application, starting from the functional requirements of intelligent driving, constructs a multimodal technology system for environmental perception design. This system can cover centimeter-level positioning accuracy combined with inertial navigation and vehicle-road cooperative road testing perception. It can completely construct a multimodal, modular, detachable, and combinable technical solution, achieving synergy in function, technology, and cost. It is adaptable to various scenarios, from driver assistance warnings to assisted driving in different scenarios, and ultimately achieves functional coverage for closed scenarios, fixed routes, and even open road testing, verification, and demonstration applications of autonomous commercial vehicles. It can meet different usage needs such as simulation testing, functional testing, road testing, and multi-scenario applications. Based on a systematic analysis of the usage scenarios and characteristics of intelligent driving commercial vehicles and different levels of intelligent driving functions, this system proposes a process-oriented design approach and table lookup analysis approach for conducting perception system design. First, the design approach has strong practicality. Based on scenario feature analysis, it can better propose combined solutions that meet the functional requirements of driving. It is both technically sound and economically efficient, avoiding the recognition defects caused by insufficient systematic analysis in the adopted solutions, and also avoiding the high costs and higher performance requirements of hardware systems caused by overly redundant and complex technical solutions. Secondly, following the above process, multiple technical paths for realizing functional requirements can be explored, verifying the effectiveness of using different types of perception systems to address the same functional requirements in different scenarios. For example, for L3 autonomous logistics vehicles used in the park, which travel at low speeds, a system based on LiDAR as the core perception system has been established. This system not only meets L3 perception requirements but also enables assisted driving functions such as AEBS, eliminating the need for millimeter-wave radar design and deployment, thus reducing operating costs and system complexity.

[0099] It should be noted that the intelligent driving vehicle environment perception system and the intelligent driving vehicle environment perception method provided in the above embodiments belong to the same concept. The specific ways in which each module and unit performs operations have been described in detail in the method embodiments, and will not be repeated here. In practical applications, the intelligent driving vehicle environment perception system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above, and this is not a limitation here.

[0100] This application also provides a computer device, which may include: one or more processors; and one or more machine-readable media storing instructions thereon, which, when executed by the one or more processors, cause the device to perform... Figure 2 The method described. Figure 8 A schematic diagram of the structure of a computer device 1000 is shown. (See attached diagram.) Figure 8 As shown, the computer device 1000 includes: a processor 1010, a memory 1020, a power supply 1030, a display unit 1040, and an input unit 1060.

[0101] The processor 1010 is the control center of the computer device 1000. It connects various components via interfaces and lines, and executes various functions of the computer device 1000 by running or executing software programs and / or data stored in the memory 1020, thereby providing overall monitoring of the computer device 1000. In this embodiment, when the processor 1010 calls the computer program stored in the memory 1020, it executes... Figure 2 The method described herein. Optionally, the processor 1010 may include one or more processing units; preferably, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. In some embodiments, the processor and memory may be implemented on a single chip; in some embodiments, they may also be implemented on separate chips.

[0102] The memory 1020 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, various applications, etc.; the data storage area may store data created based on the use of the computer device 1000, etc. In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device, etc.

[0103] The computer device 1000 also includes a power supply 1030 (such as a battery) that supplies power to various components. The power supply can be logically connected to the processor 1010 through a power management system, thereby enabling the management of charging, discharging, and power consumption.

[0104] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the computer device 1000. In this embodiment, it is mainly used to display the display interfaces of various applications in the computer device 1000, as well as text, images, and other objects displayed on the display interfaces. The display unit 1040 may include a display panel 1050. The display panel 1050 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0105] The input unit 1060 can be used to receive information such as numbers or characters input by the user. The input unit 1060 may include a touch panel 1070 and other input devices 1080. The touch panel 1070, also known as a touch screen, can collect touch operations on or near the touch panel 1070 by the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1070).

[0106] Specifically, the touch panel 1070 can detect user touch operations and the signals generated by these operations, convert them into touch point coordinates, send them to the processor 1010, and receive and execute commands from the processor 1010. Furthermore, the touch panel 1070 can be implemented using various types of touch technologies, including resistive, capacitive, infrared, and surface acoustic wave. Other input devices 1080 can include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0107] Of course, the touch panel 1070 can cover the display panel 1050. When the touch panel 1070 detects a touch operation on or near it, it transmits the information to the processor 1010 to determine the type of touch event. Subsequently, the processor 1010 provides corresponding visual output on the display panel 1050 based on the type of touch event. Although in Figure 8 In this embodiment, the touch panel 1070 and the display panel 1050 are two separate components to realize the input and output functions of the computer device 1000. However, in some embodiments, the touch panel 1070 and the display panel 1050 can be integrated to realize the input and output functions of the computer device 1000.

[0108] The computer device 1000 may also include one or more sensors, such as pressure sensors, gravity acceleration sensors, proximity sensors, etc. Of course, depending on the specific application requirements, the computer device 1000 may also include other components such as cameras.

[0109] This application also provides a computer-readable storage medium storing instructions that, when executed by one or more processors, enable the device to perform the functions described in this application. Figure 2 The method described.

[0110] It will be understood by those skilled in the art that Figure 8 This is merely an example of a computer device and does not constitute a limitation on the device. The device may include more or fewer components than illustrated, or a combination of certain components, or different components. For ease of description, the above sections are divided into modules (or units) according to their functions and described separately. Of course, in implementing this application, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0111] Those skilled in the art will understand that this application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application, and should be understood to be achievable by computer program instructions for each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams. These computer program instructions may be applied to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0112] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for environmental perception in intelligent driving vehicles, characterized in that, The method includes the following steps: The system acquires images of the target vehicle in a test scenario and identifies lane lines, obstacles, and passable spaces within the images; the target vehicle may be a real-time or pre-determined vehicle. The system identifies the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information of the surrounding vehicles relative to the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle. The information on lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth angle between surrounding vehicles and the target vehicle are fused together, and the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle are determined based on the fusion results. The safe driving speed of the target vehicle, the acceleration decision information of the target vehicle, the deceleration decision information of the target vehicle, and the steering decision information of the target vehicle are fed back to the target vehicle to perform intelligent driving control on the target vehicle. The method further includes: defining the applicable association between different usage scenarios and intelligent driving functions, including: identifying the characteristics of test scenario elements, identifying the geometric features, physical features and logical features of the test scenario, and using distance, width, height, speed, azimuth angle, positioning and timing as direct elements as input and constraint conditions for matching, simulating and testing the intelligent driving functions of the target vehicle. The method further includes: deploying an overall technical architecture for vehicle perception functions; performing vehicle perception according to the overall technical architecture, including: a camera vision perception system, acting as an environmental information perception system, sends video images to the autonomous driving controller via a switch for image processing to identify lane lines, obstacles, and passable spaces; millimeter-wave radar identifies the distance, speed, and azimuth information of the vehicle in front, which the autonomous driving controller calculates and verifies; all data is fused in the autonomous driving controller to define the target category, distance, speed, and angle, and to determine the vehicle's location and its relative position to each target, thereby determining the vehicle's safe driving speed, acceleration / deceleration, and steering decision information; the decision results are sent to the chassis controllers in real time via a gateway to control and execute drive, transmission, steering, and upper body functions, and the real-time data is returned to the autonomous driving controller as one of the bases for the next decision.

2. The intelligent driving vehicle environmental perception method according to claim 1, characterized in that, The process of acquiring images of the target vehicle in a test scenario and identifying lane lines, obstacles, and passable space from these images includes: Install one or more image capturing devices on the target vehicle; The image of the target vehicle in the test scenario is obtained by using one or more image capturing devices to capture images of the target vehicle in the test scenario, either in a driving state or a stopped state. This image is denoted as the target image. The target image is identified to determine the lane lines, obstacles, and passable space within it.

3. The intelligent driving vehicle environmental perception method according to claim 1 or 2, characterized in that, The test scenario includes the test site scenario and driving conditions; The test site scenarios include at least one of the following: closed site road scenario, semi-open site road scenario, and open site road scenario; The driving conditions include at least one of the following: traffic control, road conditions, traffic environment conditions, route setting, vehicle driving status, and driving speed limit.

4. The intelligent driving vehicle environmental perception method according to claim 3, characterized in that, Before acquiring an image of the target vehicle in the test scenario, the method further includes: acquiring a pre-determined list of vehicle intelligent driving levels and test function requirements, and determining the test scenario based on the vehicle intelligent driving levels and the list of test function requirements; The vehicle's intelligent driving levels include: Level 1, Level 2, Level 3, Level 4, and Level 5 intelligent driving levels; and the intelligence level of Level 5 is greater than that of Level 4, the intelligence level of Level 4 is greater than that of Level 3, the intelligence level of Level 3 is greater than that of Level 2, and the intelligence level of Level 2 is greater than that of Level 1.

5. The intelligent driving vehicle environmental perception method according to claim 3, characterized in that, The process of identifying the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information of the surrounding vehicles relative to the target vehicle includes: Multiple sensors are installed on the target vehicle, and data from each sensor is recorded when the target vehicle is in a driving or stationary state in the test scenario. The data from each sensor is analyzed to identify the distance between the target vehicle and surrounding vehicles, the speed of the surrounding vehicles, and the azimuth information between the surrounding vehicles and the target vehicle.

6. The intelligent driving vehicle environmental perception method according to claim 5, characterized in that, The multiple sensors include: lidar sensors, millimeter-wave radar sensors, and ultrasonic radar sensors.

7. The intelligent driving vehicle environmental perception method according to claim 2, characterized in that, The image capturing device includes at least one of the following: a monocular camera, a binocular camera, and a surround-view camera.

8. An environmental perception system for intelligent driving vehicles, characterized in that, The system includes: An image perception module is used to acquire images of a target vehicle in a test scenario, wherein the target vehicle includes real-time or pre-determined vehicles; An image recognition module is used to recognize the image and determine the lane lines, obstacles, and passable space in the image; The sensor perception module is used to identify the distance between the target vehicle and surrounding vehicles, the driving speed of the surrounding vehicles, and the azimuth information of the surrounding vehicles and the target vehicle; the surrounding vehicles include vehicles within a preset distance range from the target vehicle; The data fusion module is used to fuse the lane lines, obstacles, passable space, distance between the target vehicle and surrounding vehicles, speed of surrounding vehicles, and azimuth information between surrounding vehicles and the target vehicle, and to determine the safe driving speed, acceleration decision information, deceleration decision information, and steering decision information of the target vehicle based on the fusion results. The intelligent driving module is used to feed back the target vehicle's safe driving speed, acceleration decision information, deceleration decision information, and steering decision information to the target vehicle in order to perform intelligent driving control on the target vehicle. The system also includes: defining the applicable association between different usage scenarios and intelligent driving functions, including: identifying the characteristics of test scenario elements, identifying the geometric, physical and logical features of the test scenario, and using distance, width, height, speed, azimuth, positioning and timing as direct elements as input and constraints for matching, simulating and testing the intelligent driving functions of the target vehicle. The system also includes: an overall technical architecture for deploying vehicle perception functions; vehicle perception is performed according to the overall technical architecture, including: a camera vision perception system, as an environmental information perception system, sends video images to the autonomous driving controller via a switch for image processing to identify lane lines, obstacles, and passable spaces; millimeter-wave radar identifies the distance, speed, and azimuth information of the vehicle in front, which the autonomous driving controller calculates and verifies; all data is fused in the autonomous driving controller to define the target category, distance, speed, and angle, and to determine the vehicle's location and its relative position to each target, in order to determine the vehicle's safe driving speed, acceleration / deceleration, and steering decision information; the decision results are sent to the chassis controllers in real time via a gateway to control and execute drive, transmission, steering, and upper body functions, and the real-time data is returned to the autonomous driving controller as one of the bases for the next decision.

9. A computer device, characterized in that, include: processor; and, A computer-readable medium storing instructions that, when executed by the processor, cause the device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, It stores instructions that are loaded by a processor and executed as described in any one of claims 1 to 7.

Images