Autonomous driving active collision avoidance method, device, equipment, and storage medium based on pre-set collision routes at intersections.

Abstract

This invention discloses an autonomous driving active collision avoidance method, device, equipment, and storage medium based on a preset collision route at an intersection, relating to the field of autonomous vehicle control technology. The method includes: acquiring current road attribute parameters; comparing the current road attribute parameters with preset intersection attribute values ​​to obtain an intersection scenario determination result; retrieving intersection collision route data from pre-stored data based on the intersection scenario determination result, the intersection collision route data including the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles; performing intersection matching on the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles to obtain high-risk intersection points; performing risk prediction based on the high-risk intersection points to obtain risk prediction results, and adjusting the vehicle's driving state according to the risk prediction results. By proactively adjusting the vehicle's driving state through the pre-judgment of the preset collision route at the intersection, the method avoids the risk of high-risk intersection collisions.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle control technology, and in particular to an autonomous driving active collision avoidance method, device, equipment and storage medium based on a preset collision route at an intersection. Background Technology

[0002] With the rapid development of autonomous driving technology, the ability of vehicles to navigate autonomously in complex traffic environments has become a core indicator for measuring the safety of autonomous driving systems. Intersections, as key nodes in road traffic networks, are characterized by mixed pedestrian and vehicle traffic, multi-directional traffic flow convergence, obstructed visibility, and a high frequency of unexpected events, making them high-risk scenarios for autonomous driving collisions. Improving the safety of autonomous vehicles navigating intersections and reducing collision risks has become an important social demand for promoting the large-scale application of autonomous driving technology.

[0003] Current autonomous driving intersection collision avoidance solutions primarily rely on onboard cameras, radar, and other sensors to perceive surrounding dynamic targets in real time and execute braking or steering maneuvers upon detecting a collision risk. This type of solution employs a control mechanism of real-time perception and passive avoidance, resulting in a lag in risk prediction and a low tolerance for errors when facing unexpected situations such as lateral vehicles or pedestrians crossing the road. Furthermore, existing technologies lack prior data support for inherent high-risk intersection points, relying solely on real-time environmental data to determine risks. This fails to cover sensor blind spots and hidden potential collision risks, and onboard sensors are susceptible to interference from external environmental factors such as rain, snow, strong light, and obstructions, leading to insufficient perception stability. Therefore, improving the active collision avoidance capabilities of autonomous vehicles in intersection scenarios has become a pressing technical problem that needs to be solved.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide an autonomous driving active collision avoidance method, device, equipment, and storage medium based on a pre-set collision route at an intersection, aiming to solve the technical problem of insufficient active collision avoidance capability of autonomous vehicles in intersection scenarios.

[0006] To achieve the above objectives, the present invention provides an autonomous driving active collision avoidance method based on a pre-set collision route at an intersection. The autonomous driving active collision avoidance method based on a pre-set collision route at an intersection includes the following steps: Get the current road attribute parameters; The current road attribute parameters are compared with the preset intersection attribute values ​​to obtain the intersection scene determination result; Based on the intersection scene determination result, the intersection collision route data is retrieved from the pre-stored data. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectory of surrounding vehicles. The intersection and high-risk intersection points at the intersection are obtained by performing intersection matching between the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles. Risk prediction is made based on the high-risk intersection points, and the vehicle driving status is adjusted accordingly.

[0007] In one embodiment, the step of obtaining the current road attribute parameters includes: Send a data request instruction to the map data server so that the map data server returns a map data package according to the data request instruction; Receive the map data packet returned by the map data server; The integrity of the map data packet is verified, and the verification result is obtained. When the verification result indicates that the data is complete, the map data package is stored in the local cache to obtain the local cache update result; Read map data from the local cache and extract current road attribute parameters from the map data.

[0008] In one embodiment, the step of comparing the current road attribute parameters with preset intersection attribute values ​​to obtain an intersection scene determination result includes: Read the preset intersection attribute values; Extract the attribute identifier field from the current road attribute parameters; The attribute identifier field is compared with the preset intersection attribute value to obtain the attribute comparison result; When the attribute comparison results indicate that the two are consistent, the current driving scenario is determined to be an intersection scenario, and an intersection scenario determination result is obtained.

[0009] In one embodiment, the step of retrieving intersection collision route data from pre-stored data based on the intersection scene determination result, wherein the intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles, includes: The intersection scene determination result is analyzed to obtain the intersection signage information; The target data storage address is obtained by querying the pre-stored data index based on the intersection sign information; Read the original intersection data according to the target data storage address; The original intersection data is parsed to obtain intersection collision route data, which includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles.

[0010] In one embodiment, the step of matching the vehicle's travel trajectory with the potential collision trajectories of surrounding vehicles to obtain high-risk intersection points at the intersection includes: The vehicle's travel trajectory is projected onto the intersection's plane coordinate system to obtain the first trajectory coordinate sequence; The potential collision trajectories of the surrounding vehicles are projected onto the intersection plane coordinate system to obtain the second trajectory coordinate sequence; Spatial intersection analysis is performed on the first trajectory coordinate sequence and the second trajectory coordinate sequence to obtain the trajectory intersection region; The intersection density is calculated within the intersection area of ​​the trajectories to obtain the intersection density value; The intersection locations where the intersection density value is greater than the preset density threshold are identified as high-risk intersection locations.

[0011] In one embodiment, the step of performing risk prediction based on the high-risk intersection locations, obtaining risk prediction results, and adjusting the vehicle's driving state according to the risk prediction results includes: Obtain the vehicle's current location and current speed; Calculate the remaining distance between the current location of the vehicle and the high-risk intersection point; The estimated arrival time is calculated based on the remaining distance and the current speed of the vehicle. When the estimated arrival time is less than a preset time threshold, a risk prediction result is generated, and the vehicle driving status is adjusted according to the risk prediction result.

[0012] In one embodiment, the step of calculating the estimated arrival time based on the remaining distance and the vehicle's current speed includes: Obtain the preset and historical traffic duration statistics for the intersection; Calculate the time correction coefficient based on the preset passage time of the intersection and the historical passage time statistics; The estimated arrival time is calculated based on the remaining distance, the current speed of the vehicle, and the time correction factor.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection, the device comprising: The parameter acquisition module is used to obtain the current road attribute parameters; The comparison module is used to compare the current road attribute parameters with the preset intersection attribute values ​​to obtain the intersection scene determination result; The route retrieval module is used to retrieve intersection collision route data from pre-stored data based on the intersection scene determination result. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles. The trajectory intersection matching module is used to perform intersection matching between the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles to obtain high-risk intersection points at the intersection. The risk prediction and control module is used to predict risks based on the high-risk intersection points, obtain risk prediction results, and adjust the vehicle driving status according to the risk prediction results.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection. The device includes: a memory, a processor, and an autonomous driving active collision avoidance program based on a pre-set collision route at an intersection stored in the memory and executable on the processor. The autonomous driving active collision avoidance program based on a pre-set collision route at an intersection is configured to implement the steps of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an autonomous driving active collision avoidance program based on a preset collision route at an intersection. When the autonomous driving active collision avoidance program based on the preset collision route at an intersection is executed by a processor, it implements the steps of the autonomous driving active collision avoidance method based on the preset collision route at an intersection as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the autonomous driving active collision avoidance method based on a preset collision route at an intersection as described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: By pre-collecting and solidifying intersection collision route data, the system identifies intersection scenarios based on road attribute parameters and retrieves pre-stored data during vehicle operation. It then performs intersection matching between the vehicle's trajectory and the potential collision trajectories of surrounding vehicles to identify high-risk intersection points. Based on these points, it makes advance risk predictions and proactively adjusts the vehicle's driving state. This eliminates the need to rely on real-time sensors to detect dynamic targets to identify potential collision risks at intersections, accurately covering inherent high-risk intersection points. This achieves a shift from passive avoidance to proactive prevention, effectively improving the safety redundancy of autonomous vehicles in intersection scenarios. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection, as provided in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection, as provided in this application. Figure 3 This is a schematic diagram of the module structure of an autonomous driving active collision avoidance device based on a preset collision route at an intersection, according to an embodiment of this application. Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the autonomous driving active collision avoidance method based on a preset collision route at an intersection, as described in this application embodiment.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an autonomous driving active collision avoidance device based on a preset collision route at an intersection. The following description uses an autonomous driving active collision avoidance device based on a preset collision route at an intersection as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, the embodiments of this application provide an autonomous driving active collision avoidance method based on a preset collision route at an intersection, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection, as described in this application.

[0026] In this embodiment, the autonomous driving active collision avoidance method based on a pre-set collision route at the intersection includes steps S10 to S50: Step S10: Obtain the current road attribute parameters; It should be noted that the current road attribute parameter is a data field used to identify the road type of the current driving path. In this embodiment, this parameter corresponds to the road attribute, which is abbreviated as road_attr. When this parameter takes a value of 2, it indicates that the current path is an intersection area. This parameter comes from basic road data and is a key basis for distinguishing between ordinary roads and intersection scenarios.

[0027] Understandably, obtaining the current road attribute parameters involves reading from the data source and identifying the road type identifier corresponding to the current driving path to determine whether the current location is an intersection area. This step provides basic data support for subsequent intersection scenario determination and is the starting point of the intersection active collision avoidance process.

[0028] The beneficial effect of this step is that by obtaining road attribute parameters, it is possible to quickly identify intersection scenarios, providing triggering conditions for subsequent retrieval of pre-stored collision route data, and achieving accurate positioning of intersection scenarios.

[0029] In one feasible implementation, step S10 includes steps A11 to A15: Step A11: Send a data request command to the map data server so that the map data server returns a map data package according to the data request command; It should be noted that the map data server is a backend service node that stores and manages basic road data. This node is responsible for responding to data access requests and returning the corresponding road data content. This server establishes data interaction with the vehicle-mounted terminal through a communication link, providing raw data support for intersection scene recognition.

[0030] It should be noted that a data request command is an access command initiated by the vehicle-mounted device to the data server to request specific road data. This command includes a request identifier and target data range information. The initiation of this command marks the beginning of the data acquisition process and is a prerequisite for subsequently receiving data packets.

[0031] It should be noted that a map data package is a collection of data containing road attribute information returned by the map data server in response to a request. This data package organizes basic road data in a specific format. This data package is the raw data source for extracting current road attribute parameters, and its completeness directly affects the accuracy of subsequent intersection recognition.

[0032] Understandably, sending a data request command to the map data server is a process in which the vehicle-mounted device actively initiates data access, establishing a data transmission channel with the server. This step enables the map data server to return the corresponding map data package based on the request content, laying the foundation for obtaining road attribute parameters.

[0033] The benefit of this step is that by requesting data from the server, the latest road attribute information can be obtained in a timely manner, ensuring the timeliness of data for intersection scene recognition.

[0034] Step A12: Receive the map data packet returned by the map data server; Understandably, receiving the map data packet returned by the map data server is the process by which the vehicle-mounted device obtains the server's response data. Through this process, the data in transit is loaded into the local processing unit. After this step is completed, the map data packet enters a locally processable state, providing an object for subsequent data verification.

[0035] The benefit of this step is that by receiving map data packets, the basic road data is transmitted from the server to the vehicle, providing raw materials for local data parsing.

[0036] Step A13: Perform integrity verification on the map data package and obtain the verification result; It should be noted that integrity verification is a process of checking the content integrity and format correctness of the received map data packets. This process confirms that the data packets have not been missing or corrupted during transmission. This verification mechanism ensures that the data processed in subsequent steps is valid and usable, avoiding intersection recognition errors due to data loss.

[0037] It should be noted that the verification result is a status indicator output after integrity verification processing, used to characterize whether the data packet is complete and valid. This result is presented as either "pass" or "fail." This result directly determines whether the map data packet enters the local storage stage and is a key node in data quality control.

[0038] Understandably, performing integrity checks on map data packets is a process to verify whether the data packets remain intact and usable after transmission. This check can identify transmission anomalies or data corruption. The check yields a result, which is used to determine whether the data packet can proceed to subsequent storage and parsing stages.

[0039] The benefit of this step is that by verifying the integrity of data packets, damaged or missing data can be filtered out, preventing erroneous data from entering subsequent processing and improving the data reliability of intersection scene recognition.

[0040] Step A14: When the verification result indicates that the data is complete, store the map data package in the local cache and obtain the local cache update result; It should be noted that the local cache is a storage area configured inside the vehicle terminal for temporarily storing road data. This area supports fast read and write access to ensure data retrieval efficiency. After storing map data packages in the local cache, road attribute parameters can be read directly locally without repeatedly requesting the server.

[0041] It should be noted that the local cache update result is a status feedback output after the map data packet is completely stored locally. This feedback indicates that the cached content has been synchronized and updated. This result confirms that the local data is consistent with the latest acquired map data packet, providing availability assurance for subsequent read operations.

[0042] Understandably, when the verification result indicates that the data is complete, storing the map data packet to the local cache is a storage operation that writes the verified data to the local fast access area. This operation yields a local cache update result, which confirms that the data in the local cache has been updated with the latest received map data packet content.

[0043] The benefit of this step is that by storing the complete data packet in the local cache, it enables fast local access to road data, reduces repeated network requests, and improves the response speed of intersection scene recognition.

[0044] Step A15: Read map data from the local cache and extract the current road attribute parameters from the map data.

[0045] Understandably, reading map data from the local cache is an operation that retrieves stored basic road data from the local quick access area, and this operation loads the cached data into the processing unit. Extracting the current road attribute parameters from the map data is the process of separating and identifying the road type identifier field from the complete basic road data. This process yields the current road attribute parameters, which are used for subsequent intersection scene determination.

[0046] The benefit of this step is that by reading and extracting road attribute parameters from the local cache, the intersection identification information of the current path can be quickly obtained, providing real-time data basis for triggering intersection scenarios.

[0047] Step S20: Compare the current road attribute parameters with the preset intersection attribute values ​​to obtain the intersection scene determination result; It should be noted that the preset intersection attribute value is a pre-set road attribute value used to identify the intersection area; in this embodiment, this value is 2. This value serves as the baseline threshold for intersection scene determination; intersection scene recognition is triggered when the current road attribute parameters match this value.

[0048] It should be noted that the intersection scene determination result represents the conclusion that the current driving scene belongs to the intersection area, and this conclusion is presented in the form of consistency or inconsistency. This result directly determines whether to initiate the subsequent process of retrieving pre-stored collision route data, and is the scene triggering basis for the intersection active collision avoidance mechanism.

[0049] Understandably, comparing the current road attribute parameters with the preset intersection attribute values ​​is a numerical matching process. This comparison determines whether the current road attribute parameters are equal to the preset intersection attribute values. This comparison yields an intersection scenario determination result, which is used to determine whether the current driving scenario is an intersection scenario.

[0050] The beneficial effect of this step is that by comparing with the preset intersection attribute values, it can accurately distinguish between ordinary roads and intersection scenarios, avoid initiating unnecessary collision route analysis in non-intersection scenarios, and improve processing efficiency and scenario targeting.

[0051] In one feasible implementation, step S20 includes steps A21 to A24: Step A21: Read the preset intersection attribute values; Understandably, reading the preset intersection attribute value is an operation that retrieves the intersection identifier baseline value from the local configuration or preset parameter library; in this embodiment, this value is 2. This reading operation obtains the preset intersection attribute value, which serves as the baseline reference for subsequent comparisons.

[0052] The beneficial effect of this step is that by reading the preset intersection attribute values, a benchmark standard for intersection scene determination is established, ensuring the consistency and accuracy of the basis for intersection recognition.

[0053] Step A22: Extract the attribute identifier field from the current road attribute parameters; It should be noted that the attribute identifier field is the specific numerical content in the current road attribute parameters used to characterize the road type category. In this embodiment, this field corresponds to the value of the road attribute parameter. This field is the object being compared in the comparison operation, and its value directly reflects the road type attribute of the current path.

[0054] Understandably, extracting the attribute identifier field from the current road attribute parameters is the process of separating the specific type identifier value from the current road attribute parameters. This extraction operation yields the attribute identifier field, which is used to compare the values ​​with preset intersection attribute values.

[0055] The benefit of this step is that by extracting the attribute identifier field, the key values ​​used for intersection determination can be accurately obtained, avoiding redundant processing of the complete data structure and improving comparison efficiency.

[0056] Step A23: Compare the attribute identifier field with the preset intersection attribute values ​​to obtain the attribute comparison results; It should be noted that the attribute comparison result is the matching status conclusion output after comparing the attribute identifier field with the preset intersection attribute value. This conclusion indicates whether the two values ​​are the same. This result is the direct basis for determining whether the current scene is an intersection scene and decides whether to initiate intersection collision route data retrieval.

[0057] Understandably, comparing the attribute identifier field with the preset intersection attribute value is an equivalence judgment process. This comparison determines whether the current road attribute parameter value is equal to the preset intersection attribute value. The comparison yields an attribute comparison result, which indicates whether the current driving scenario meets the intersection scenario conditions.

[0058] The benefit of this step is that it enables intersection scene determination in a simple and efficient way through numerical comparison, reducing complex computational overhead and improving the real-time performance of scene recognition.

[0059] Step A24: When the attribute comparison results indicate that the two are consistent, determine that the current driving scenario is an intersection scenario and obtain the intersection scenario determination result.

[0060] Understandably, when the attribute comparison results indicate that the two match, determining the current driving scenario as an intersection scenario is part of the scenario determination conclusion generation process. When the attribute identifier field is equal to the preset intersection attribute value, it is determined that the current location is in an intersection area. This determination process yields the intersection scenario determination result, which confirms that the current driving scenario is an intersection scenario.

[0061] The benefit of this step is that when the attributes match, the intersection scene is identified, which can accurately trigger the active collision avoidance process at the intersection, ensuring that subsequent collision route analysis is only initiated in the intersection scene, thus improving the targeting of scene processing.

[0062] Step S30: Based on the intersection scene determination result, retrieve the intersection collision route data from the pre-stored data. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles. It should be noted that the pre-stored data is a local, intersection-specific data resource that is pre-verified and stored after scene verification and trajectory collection at intersections of different structures through real-vehicle data acquisition. This data resource includes collision route information for each intersection, providing prior data support for the prediction of risks during vehicle operation.

[0063] It should be noted that the intersection collision route data is pre-collected and fixed collision risk trajectory data for specific intersections. This data includes the vehicle's travel trajectory and the potential collision trajectory of surrounding vehicles. This data is the basic material for identifying high-risk points at intersections, and by pre-fixing it, potential risks can be identified without real-time sensing.

[0064] It should be noted that the vehicle's trajectory is pre-collected data on the vehicle's expected travel path within the intersection area. This data reflects the sequence of spatial position changes as the vehicle passes through the intersection. This trajectory is the vehicle's side reference trajectory in dual-trajectory matching, used for intersection analysis with the trajectories of surrounding vehicles.

[0065] It should be noted that the potential collision trajectory of surrounding vehicles is pre-collected or deduced data on the possible driving paths of surrounding vehicles within the intersection area that may conflict with this vehicle. This data reflects the spatial position change sequence of other vehicles as they pass through the intersection. This trajectory is the external reference trajectory in dual-trajectory matching, used to identify high-risk points where the trajectory of this vehicle may conflict with that of the vehicle itself.

[0066] Understandably, retrieving intersection collision route data from pre-stored data based on the intersection scenario determination result is a process of reading the corresponding intersection collision risk data from local pre-stored resources based on the scenario trigger conclusion. This retrieved intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles, used for subsequent intersection matching analysis.

[0067] The beneficial effect of this step is that by retrieving intersection collision route data from pre-stored data, it is possible to obtain the intersection's unique risk trajectory before the dynamic target appears, thereby achieving advance risk prediction and breaking through the limitations of traditional real-time perception and passive risk avoidance.

[0068] In one feasible implementation, step S30 includes steps A31 to A34: Step A31: Analyze the intersection scene determination results to obtain intersection signage information; It should be noted that intersection identification information is a unique identifier used to distinguish different intersection scenarios. This data is associated with the intersection scenario determination result and is used to locate pre-stored data for a specific intersection. This identifier is a key retrieval condition for pre-stored data index queries, ensuring that the retrieved data accurately corresponds to the current intersection.

[0069] Understandably, parsing the intersection scene determination result is the process of extracting intersection identifiers from the scene conclusions of the prior determination, and obtaining intersection identifier information through this parsing. This identifier information is used to locate the data storage location of the collision route corresponding to the current intersection in the pre-stored data.

[0070] The beneficial effect of this step is that by parsing the intersection scene determination results to obtain intersection signage information, it is possible to establish a mapping relationship between the current scene and the pre-stored data, ensuring that the data retrieved later is accurately matched with the current intersection.

[0071] Step A32: Query the pre-stored data index based on the intersection sign information to obtain the target data storage address; It should be noted that the pre-stored data index is a pre-built retrieval directory used for quickly locating the data storage location of intersection collision route data. This directory records the correspondence between intersection sign information and data storage addresses. This index supports rapid data location based on intersection signs, improving data retrieval efficiency.

[0072] It should be noted that the target data storage address is the address information output after the pre-stored data index query, pointing to the actual storage location of the collision route data at a specific intersection. This address is the direct basis for reading the original intersection data, and the pre-stored collision route data of the corresponding intersection can be accessed through this address.

[0073] Understandably, querying the pre-stored data index based on intersection sign information is a process of finding the corresponding data storage location in the search directory based on the intersection's identification identifier. This query yields the target data storage address, which points to the specific storage location of the current intersection collision route data.

[0074] The benefit of this step is that it allows for quick location of the target data storage address through index lookup, avoiding traversing all pre-stored data, greatly improving data retrieval efficiency, and ensuring the real-time performance of intersection collision avoidance response.

[0075] Step A33: Read the original intersection data according to the target data storage address; It should be noted that the raw intersection data is the unparsed raw data of intersection collision routes stored at the target data storage address. This data records intersection trajectory information in a specific format. This data is the raw form of the intersection collision route data before parsing and needs to be converted into a usable format through data parsing.

[0076] Understandably, retrieving raw intersection data based on the target data storage address is the process of retrieving the original intersection trajectory data from the physical storage medium according to the storage address. This retrieval yields the raw intersection data, which provides the initial material for subsequent data analysis.

[0077] The benefit of this step is that by directly reading the original intersection data through the target address, the pre-stored trajectory information of the current intersection can be accurately obtained, avoiding data misreading and ensuring the accuracy of the data source for subsequent analysis.

[0078] Step A34: Perform data parsing on the original intersection data to obtain intersection collision route data, which includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles.

[0079] Understandably, parsing raw intersection data involves converting the raw intersection trajectory data into structured, usable data. This parsing identifies and separates the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles. The resulting intersection collision route data, containing both the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles, provides standardized input for subsequent dual-trajectory intersection matching.

[0080] The benefit of this step is that by parsing the original intersection data, the raw data is converted into structured trajectory data, ensuring that the vehicle's travel trajectory and the potential collision trajectory of surrounding vehicles are in the same format, thus laying a data foundation for subsequent intersection matching.

[0081] Step S40: Perform intersection matching between the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles to obtain high-risk intersection points at the intersection; It should be noted that high-risk intersection points are spatial locations identified by matching the travel trajectory of a vehicle with the potential collision trajectories of surrounding vehicles. These points are inherent conflict zones caused by the fixed road structure within the intersection, serving as spatial targets for risk prediction and proactive risk avoidance strategy development.

[0082] Understandably, matching the travel trajectory of a vehicle with the potential collision trajectories of surrounding vehicles involves spatial correlation analysis of the two trajectories to identify conflict areas. This matching yields high-risk intersection points at the intersection, which represent high-risk spatial locations where the vehicle and surrounding vehicles may experience trajectory conflicts within the intersection.

[0083] The beneficial effect of this step is that by matching the intersection of the two trajectories, it can accurately locate the inherent high-risk collision points at the intersection, effectively cover the hidden potential collision risks that sensors cannot identify, and make up for the blind spot defects of traditional real-time perception technology.

[0084] In one feasible implementation, step S40 includes steps A41 to A45: Step A41: Project the vehicle's travel trajectory onto the intersection's plane coordinate system to obtain the first trajectory coordinate sequence; It should be noted that the intersection plane coordinate system is a two-dimensional coordinate reference system used to characterize the spatial relationships of intersections. This coordinate system establishes a plane coordinate mapping with a specific location at the intersection as the origin. This coordinate system provides a unified spatial measurement benchmark for trajectory projection, ensuring that different trajectories can be correlated and analyzed within the same spatial framework.

[0085] It should be noted that the first trajectory coordinate sequence is a set of discrete coordinate points formed by projecting the vehicle's trajectory onto the intersection's plane coordinate system. This set records the vehicle's positional changes in the intersection space according to the traffic flow sequence. This coordinate sequence is the vehicle's side trajectory data in spatial intersection analysis and is used for conflict detection with the second trajectory coordinate sequence.

[0086] Understandably, projecting the vehicle's trajectory onto the intersection's plane coordinate system is the process of converting the vehicle's trajectory from its original data format into a unified spatial coordinate representation. This projection yields a first trajectory coordinate sequence, which represents the vehicle's expected travel path in the intersection space in the form of coordinate points.

[0087] The benefit of this step is that by projecting the vehicle's travel trajectory onto a unified coordinate system, spatial standardization of the trajectory data is achieved, providing a unified measurement benchmark for subsequent spatial correlation analysis with the trajectories of surrounding vehicles.

[0088] Step A42: Project the potential collision trajectories of surrounding vehicles onto the intersection plane coordinate system to obtain the second trajectory coordinate sequence; It should be noted that the second trajectory coordinate sequence is a set of discrete coordinate points formed by projecting the potential collision trajectories of surrounding vehicles onto the intersection's plane coordinate system. This set records the positional changes of surrounding vehicles in the intersection space according to the traffic flow sequence. This coordinate sequence is the external trajectory data in spatial intersection analysis, used for collision detection with the first trajectory coordinate sequence.

[0089] Understandably, projecting the potential collision trajectories of surrounding vehicles onto the intersection's plane coordinate system is a process of converting these trajectories from their original data format into a unified spatial coordinate representation. This projection yields a second trajectory coordinate sequence, which represents the potential driving paths of surrounding vehicles in the intersection space in the form of coordinate points.

[0090] The benefit of this step is that by projecting the potential collision trajectories of surrounding vehicles onto a unified coordinate system, the spatial standardization of external trajectory data is achieved, ensuring that the two trajectories are comparable and analyzable within the same spatial framework.

[0091] Step A43: Perform spatial intersection analysis on the first trajectory coordinate sequence and the second trajectory coordinate sequence to obtain the trajectory intersection region; It should be noted that spatial intersection analysis is a process of determining the geometric intersection relationship between the first trajectory coordinate sequence and the second trajectory coordinate sequence within the same spatial framework. This process identifies whether the two trajectories overlap or intersect in space. This analysis is the core computational step in locating trajectory conflict areas, providing spatial basis for determining high-risk locations at intersections.

[0092] It should be noted that the trajectory intersection region is the geographical area where the coordinate sequences of the first and second trajectories, identified after spatial intersection analysis, intersect or overlap spatially. This region is a candidate area where the two trajectories may spatially conflict and is the target of subsequent intersection density calculations.

[0093] Understandably, performing spatial intersection analysis on the first and second trajectory coordinate sequences is the process of determining whether the two trajectories have a spatial intersection relationship. This analysis yields the trajectory intersection area, which identifies the geographical range where the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles may intersect.

[0094] The beneficial effect of this step is that, through spatial intersection analysis, it is possible to filter out candidate areas with spatial conflicts in trajectory from the entire intersection range, narrowing the scope of subsequent risk analysis and improving the efficiency of high-risk point identification.

[0095] Step A44: Calculate the intersection density within the trajectory intersection area to obtain the intersection density value; It should be noted that the intersection density value is a quantitative indicator characterizing the frequency of trajectory intersections or the severity of conflicts within a trajectory intersection area. This indicator reflects the density of intersections between two trajectories within a specific area. This value serves as a quantitative basis for distinguishing between general intersection areas and high-risk intersection points; a higher value indicates a more concentrated collision risk.

[0096] Understandably, calculating the intersection density within the trajectory intersection area is a process of quantitatively assessing the concentration of risk in the trajectory conflict zone. This calculation yields an intersection density value, which characterizes the spatial distribution density of collision risk within the trajectory intersection area.

[0097] The beneficial effect of this step is that by calculating the intersection density value, qualitative trajectory intersections can be transformed into quantitative risk indicators, providing a numerical basis for accurately screening high-risk locations and avoiding risk misjudgment caused by subjective judgment.

[0098] Step A45: Identify intersection locations with intersection density values ​​greater than the preset density threshold as high-risk intersection locations.

[0099] It should be noted that the preset density threshold is a pre-set critical density value used to distinguish between general intersection areas and high-risk intersection points. This threshold serves as a benchmark for comparing intersection density values; when the intersection density value exceeds this threshold, the corresponding location is identified as a high-risk location that needs to be avoided.

[0100] Understandably, identifying intersection locations with intersection density values ​​exceeding a preset density threshold as high-risk intersection points is a process of filtering high-risk spatial locations from trajectory intersection areas based on a quantified threshold. This identification of high-risk intersection points represents the fixed spatial location within the intersection where the collision risk is most concentrated.

[0101] The beneficial effect of this step is that by screening high-risk intersection points at intersections through preset density thresholds, it is possible to accurately locate the inherent high-risk collision areas at intersections in a quantitative manner, providing clear spatial targets for subsequent risk prediction and proactive risk avoidance control.

[0102] Step S50: Based on the high-risk intersection points, risk prediction is made to obtain the risk prediction results, and the vehicle driving status is adjusted according to the risk prediction results.

[0103] It should be noted that the risk prediction result is a conclusion representing the current traffic risk status, generated based on the analysis of high-risk intersection points. This conclusion includes information on the risk level or the presence of risk. This result is the direct basis for generating vehicle control commands, used to determine whether to adjust the vehicle's driving status and the specific adjustment strategy.

[0104] Understandably, risk prediction based on high-risk intersection points is a process of assessing collision risk by combining the vehicle's current state with the spatial relationship between these high-risk points. This prediction yields a risk assessment result, which triggers adjustments to the vehicle's driving behavior to proactively avoid high-risk collision areas at intersections.

[0105] The beneficial effect of this step is that it can predict risks based on high-risk intersections, identify risks based on prior data before dynamic targets appear, and proactively adjust vehicle driving status to avoid high-risk areas at intersections, thus realizing a shift in collision avoidance logic from passive avoidance to proactive prevention.

[0106] This embodiment provides an autonomous driving active collision avoidance method based on pre-set collision routes at intersections. By pre-collecting and pre-determining intersection collision route data, the method identifies intersection scenarios based on road attribute parameters during vehicle operation. It retrieves and matches the vehicle's trajectory from pre-stored data with potential collision trajectories of surrounding vehicles to identify high-risk intersection points. Based on these points, it performs proactive risk prediction and adjusts the vehicle's driving state accordingly. This eliminates the need for real-time sensor detection of dynamic targets to identify potential collision risks at intersections, accurately covering inherent high-risk intersection points and shifting the collision avoidance logic from passive avoidance to proactive prevention. Furthermore, by pre-determining intersection-specific collision route data, it provides prior risk data support for intelligent driving, effectively compensating for sensor blind spots and improving intersection traffic safety redundancy. Additionally, by combining dual-trajectory matching with the actual road structure at the intersection, it can pinpoint inherent collision points caused by the fixed road structure, enhancing the scenario-specificity of the avoidance strategy. This means that the pre-stored data resources, which are constructed by the actual vehicle traversing intersections in advance to complete scene verification and trajectory collection, provide a data foundation for the identification of risks in advance during the driving process.

[0107] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S50 includes steps S501 to S504: Step S501: Obtain the current location information and current speed of the vehicle; It should be noted that the vehicle's current location information is positioning data representing the vehicle's real-time spatial coordinates within the road network. This data is provided by the onboard positioning device and reflects the vehicle's current geographical location. This information is the foundational data for calculating the spatial relationship between the vehicle and high-risk intersections, providing a location reference for calculating the remaining distance.

[0108] It should be noted that the vehicle's current speed is a rate data representing the instantaneous speed of the vehicle's movement at the current moment. This data is calculated differentially by the onboard speed sensor or positioning device. This speed is a key parameter for assessing the time required for the vehicle to reach high-risk intersections, directly affecting the timeliness of risk prediction.

[0109] Understandably, obtaining the vehicle's current location and speed involves reading real-time vehicle status data from the onboard sensing and positioning unit. This acquired data is used to calculate the remaining distance and estimated arrival time.

[0110] The beneficial effect of this step is that by acquiring the vehicle's real-time location and speed information, a dynamic correlation is established between the vehicle's current state and high-risk points at intersections, providing real-time status input for quantitative assessment of collision risks.

[0111] Step S502: Calculate the remaining distance between the vehicle's current location and the high-risk intersection point; It should be noted that the remaining distance is the spatial interval between the vehicle's current location and the high-risk intersection point. This length represents the remaining path distance between the vehicle's current position and the high-risk collision point. This distance is one of the core input parameters for calculating the estimated arrival time, directly reflecting the urgency of the space required for the vehicle to approach the high-risk point.

[0112] Understandably, calculating the remaining distance between the vehicle's current location and a high-risk intersection point is a process of measuring the path length from the vehicle's current location to the high-risk collision point. This calculated remaining distance is used, in conjunction with the vehicle's speed, to assess the estimated time it will take for the vehicle to reach the high-risk point.

[0113] The beneficial effect of this step is that by calculating the remaining distance, the spatial relationship between the vehicle and the high-risk location is quantified into a specific path length, providing a spatial measurement basis for risk prediction in the time dimension.

[0114] Step S503: Calculate the estimated arrival time based on the remaining distance and the vehicle's current speed; It should be noted that the estimated arrival time is the length of time it will take for the vehicle to reach the high-risk intersection from its current location, calculated based on the remaining distance and the vehicle's current speed. This time is a key quantitative indicator for risk assessment; by comparing it with a preset time threshold, it can be determined whether there is an imminent collision risk.

[0115] Understandably, calculating the estimated arrival time based on the remaining distance and the vehicle's current speed is a process of extrapolating the travel time based on spatial distance and speed of movement. This calculated estimated arrival time is then used to determine the urgency of the risk compared to a preset time threshold.

[0116] The beneficial effect of this step is that by calculating the estimated arrival time, spatial distance is transformed into a quantitative risk indicator in the time dimension, which makes risk prediction have a clear time reference standard and improves the accuracy and operability of the prediction.

[0117] In one feasible implementation, step S503 includes steps A51 to A53: Step A51: Obtain the preset passage time and historical passage time statistics for the intersection; It should be noted that the preset passage time at an intersection is a pre-set reference value representing the baseline time required for vehicles to pass through a specific intersection. This value is determined based on the road structure characteristics and standard traffic conditions of the intersection. This duration provides a baseline time reference for calculating the estimated arrival time, and is used to correct theoretical times calculated solely based on distance and speed.

[0118] It should be noted that historical travel time statistics are empirical time data obtained by accumulating and statistically analyzing the actual travel time of past vehicles at specific intersections. This data reflects the actual time consumption patterns at intersections. These statistics are used to correct the discrepancy between theoretical calculations and actual road conditions, making time estimates closer to actual traffic situations.

[0119] Understandably, obtaining the preset and historical traffic duration statistics for an intersection involves reading the intersection's time baseline data and empirical statistics from a local pre-stored database or a cloud server. These two data points are used to calculate a time correction factor to optimize time estimation.

[0120] The beneficial effect of this step is that by obtaining the preset and historical traffic duration statistics of the intersection, and introducing actual traffic experience data of the intersection, it makes up for the limitations of purely theoretical calculations and makes the estimated arrival time more consistent with the actual traffic patterns of the intersection.

[0121] Step A52: Calculate the time correction coefficient based on the preset passage time of the intersection and the historical passage time statistics; It should be noted that the time correction coefficient is a weighted correction parameter calculated by combining the preset travel time of the intersection with the historical travel time statistics. This coefficient is used to adjust the theoretical time calculation results. It represents the proportion of time deviation between actual road conditions and ideal conditions. This coefficient is used to weight and correct the theoretical estimated time based on distance and speed, so that the final estimated time takes into account the actual traffic characteristics of the intersection.

[0122] Understandably, calculating the time correction coefficient based on the preset travel time at the intersection and historical travel time statistics is a process of generating time-weighted adjustment parameters. This calculation integrates the baseline time and historical statistical time to obtain the correction coefficient. This calculated time correction coefficient is used to adjust the theoretically estimated arrival time based on actual road conditions.

[0123] The beneficial effect of this step is that by calculating the time correction coefficient, a mapping relationship is established between the theoretical travel time and the actual intersection travel experience, so that the estimated arrival time can reflect the actual traffic conditions at the intersection and improve the accuracy of time prediction.

[0124] Step A53: Calculate the estimated arrival time based on the remaining distance, the vehicle's current speed, and the time correction factor.

[0125] Understandably, calculating the estimated arrival time based on the remaining distance, the vehicle's current speed, and the time correction factor is a process of extrapolating time by integrating spatial distance, speed of movement, and actual road condition correction parameters. This calculated estimated arrival time is the predicted time to reach the high-risk intersection after correction by the time correction factor.

[0126] The beneficial effect of this step is that by introducing a time correction coefficient to weight and correct the theoretical time, the estimated arrival time takes into account both vehicle kinematics characteristics and actual intersection traffic experience, which significantly improves the accuracy of time prediction and the reliability of risk assessment.

[0127] Step S504: When the estimated arrival time is less than a preset time threshold, a risk prediction result is generated to adjust the vehicle's driving status based on the risk prediction result.

[0128] It should be noted that the preset time threshold is a pre-set time threshold used to determine the urgency of a risk. This threshold represents the minimum time that a vehicle must allow to complete a risk response before arriving at a high-risk intersection. This threshold is the criterion for triggering the generation of risk prediction results; when the estimated arrival time is less than this threshold, an imminent collision risk is considered to exist.

[0129] Understandably, when the estimated arrival time is less than a preset time threshold, generating a risk prediction result is a process of outputting a risk status indicator based on the judgment of time urgency. When the estimated arrival time is less than the preset time threshold, a risk prediction result is generated, which is used to trigger adjustments to the vehicle's driving status to proactively avoid high-risk collision areas at intersections.

[0130] The beneficial effect of this step is that by generating a risk prediction result when the estimated arrival time is less than a preset time threshold, an active risk avoidance response can be triggered with a clear time threshold standard, ensuring that vehicle control commands are generated in a timely manner when the risk is urgent, thereby improving the timeliness of active collision avoidance response at intersections.

[0131] This embodiment provides an autonomous driving active collision avoidance method based on a pre-set collision route at an intersection. By acquiring the vehicle's current location and speed, it calculates the remaining distance between the vehicle's current location and a high-risk intersection point. Then, based on the remaining distance and the vehicle's current speed, it calculates the estimated arrival time. When the estimated arrival time is less than a preset time threshold, a risk prediction result is generated, and the vehicle's driving state is adjusted accordingly. This transforms the spatial relationship between the vehicle and the high-risk intersection point into a time-dimensional risk quantification indicator, enabling accurate risk assessment based on time urgency. Furthermore, by introducing a time correction coefficient calculated from the preset intersection passage time and historical passage time statistics, the theoretically estimated arrival time is corrected for actual road conditions, making the time prediction more closely match the actual traffic patterns at the intersection. Additionally, generating a risk prediction result based on the comparison between the estimated arrival time and the preset time threshold can promptly trigger an active avoidance response when the collision risk is imminent, improving the timeliness and reliability of intersection collision avoidance control.

[0132] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the autonomous driving active collision avoidance method based on the pre-set collision route at the intersection. Any simple modifications based on this technical concept are within the protection scope of this application.

[0133] This application also provides an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection. Please refer to [link / reference]. Figure 3 The autonomous driving active collision avoidance device based on the pre-set collision route at the intersection includes: Parameter acquisition module 10 is used to acquire the current road attribute parameters; The comparison module 20 is used to compare the current road attribute parameters with the preset intersection attribute values ​​to obtain the intersection scene determination result; The route retrieval module 30 is used to retrieve intersection collision route data from pre-stored data based on the intersection scene determination result. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectory of surrounding vehicles. The trajectory intersection matching module 40 is used to match the trajectory of the vehicle and the potential collision trajectory of surrounding vehicles to obtain the high-risk intersection points at the intersection. The risk prediction and control module 50 is used to predict risks based on high-risk intersections and obtain risk prediction results, so as to adjust the vehicle driving status according to the risk prediction results.

[0134] The autonomous driving active collision avoidance device based on a pre-set collision route at an intersection provided in this application adopts the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection as described in the above embodiments, and can solve the technical problem of insufficient active collision avoidance capability of autonomous vehicles in intersection scenarios. Compared with the prior art, the beneficial effects of the autonomous driving active collision avoidance device based on a pre-set collision route at an intersection provided in this application are the same as the beneficial effects of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection provided in the above embodiments, and other technical features in the autonomous driving active collision avoidance device based on a pre-set collision route at an intersection are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0135] In one embodiment, the parameter acquisition module 10 is further configured to send a data request instruction to the map data server so that the map data server returns a map data packet according to the data request instruction; Receive map data packets returned by the map data server; Perform integrity verification on the map data package and obtain the verification result; When the verification result indicates that the data is complete, the map data package is stored in the local cache, and the local cache update result is obtained; Read map data from the local cache and extract the current road attribute parameters from the map data.

[0136] In one embodiment, the comparison module 20 is also used to read preset intersection attribute values; Extract the attribute identifier field from the current road attribute parameters; The attribute identifier field is compared with the preset intersection attribute values ​​to obtain the attribute comparison results. When the attribute comparison results indicate that the two are consistent, the current driving scenario is determined to be an intersection scenario, and the intersection scenario determination result is obtained.

[0137] In one embodiment, the route retrieval module 30 is also used to parse the intersection scene determination result to obtain intersection signage information; The target data storage address is obtained by querying the pre-stored data index based on the intersection sign information; Read the original intersection data based on the target data storage address; Data parsing is performed on the original intersection data to obtain intersection collision route data, which includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles.

[0138] In one embodiment, the trajectory intersection matching module 40 is further configured to project the vehicle's travel trajectory onto the intersection plane coordinate system to obtain a first trajectory coordinate sequence; Projecting the potential collision trajectories of surrounding vehicles onto the intersection's plane coordinate system yields a second trajectory coordinate sequence; Spatial intersection analysis is performed on the first trajectory coordinate sequence and the second trajectory coordinate sequence to obtain the trajectory intersection region; Intersection density is calculated within the trajectory intersection area to obtain the intersection density value; Intersections with intersection density values ​​greater than a preset density threshold are identified as high-risk intersection points.

[0139] In one embodiment, the risk prediction and control module 50 is also used to obtain the current location information of the vehicle and the current driving speed of the vehicle; Calculate the remaining distance between the vehicle's current location and the high-risk intersection point; The estimated arrival time is calculated based on the remaining distance and the vehicle's current speed. When the estimated arrival time is less than a preset time threshold, a risk prediction result is generated, and the vehicle's driving status is adjusted according to the risk prediction result.

[0140] In one embodiment, the risk prediction and control module 50 is further used to obtain the preset passage time and historical passage time statistics of the intersection; The time correction factor is calculated based on the preset passage time at the intersection and the historical passage time statistics. The estimated arrival time is calculated based on the remaining distance, the vehicle's current speed, and a time correction factor.

[0141] This application provides an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection. The autonomous driving active collision avoidance device based on a pre-set collision route at an intersection includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection as described in Embodiment 1 above.

[0142] The following is for reference. Figure 4This document illustrates a structural schematic diagram of an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection, suitable for implementing embodiments of this application. The autonomous driving active collision avoidance device based on a pre-set collision route at an intersection in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The autonomous driving active collision avoidance device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0143] like Figure 4 As shown, an automated driving active collision avoidance device based on a pre-set collision route at an intersection may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the automated driving active collision avoidance device based on the pre-set collision route at the intersection. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the autonomous driving active collision avoidance device based on a pre-set collision route at an intersection to wirelessly or wiredly communicate with other devices to exchange data. Although the figure shows an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0144] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0145] The autonomous driving active collision avoidance device based on a pre-set collision route at an intersection provided in this application employs the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection as described in the above embodiments, and can solve the technical problem of insufficient active collision avoidance capability of autonomous vehicles in intersection scenarios. Compared with the prior art, the beneficial effects of the autonomous driving active collision avoidance device based on a pre-set collision route at an intersection provided in this application are the same as the beneficial effects of the autonomous driving active collision avoidance method based on a pre-set collision route at an intersection provided in the above embodiments, and other technical features in the autonomous driving active collision avoidance device based on a pre-set collision route at an intersection are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0146] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0147] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0148] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the autonomous driving active collision avoidance method based on a preset collision route at an intersection in the above embodiments.

[0149] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0150] The aforementioned computer-readable storage medium may be included in an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection; or it may exist independently and not be installed in an autonomous driving active collision avoidance device based on a pre-set collision route at an intersection.

[0151] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by an autonomous driving active collision avoidance device based on a preset collision route at an intersection, the autonomous driving active collision avoidance device based on the preset collision route at the intersection causes the following: it acquires current road attribute parameters; compares the current road attribute parameters with preset intersection attribute values ​​to obtain an intersection scenario determination result; retrieves intersection collision route data from pre-stored data based on the intersection scenario determination result, the intersection collision route data including the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles; performs intersection matching on the vehicle's travel trajectory and potential collision trajectories of surrounding vehicles to obtain high-risk intersection points; and performs risk prediction based on the high-risk intersection points to obtain a risk prediction result, thereby adjusting the vehicle's driving state according to the risk prediction result.

[0152] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0154] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0155] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described autonomous driving active collision avoidance method based on a preset collision route at an intersection. This addresses the technical problem of insufficient active collision avoidance capability of autonomous vehicles in intersection scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the autonomous driving active collision avoidance method based on a preset collision route at an intersection provided in the above embodiments, and will not be elaborated upon here.

[0156] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described autonomous driving active collision avoidance method based on a preset collision route at an intersection.

[0157] The computer program product provided in this application can solve the technical problem of insufficient active collision avoidance capability of autonomous vehicles in intersection scenarios. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the autonomous driving active collision avoidance method based on preset collision routes at intersections provided in the above embodiments, and will not be repeated here.

[0158] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An autonomous driving active collision avoidance method based on a pre-set collision route at an intersection, characterized in that, The method includes: Get the current road attribute parameters; The current road attribute parameters are compared with the preset intersection attribute values ​​to obtain the intersection scene determination result; Based on the intersection scene determination result, the intersection collision route data is retrieved from the pre-stored data. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectory of surrounding vehicles. The intersection and high-risk intersection points at the intersection are obtained by performing intersection matching between the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles. Risk prediction is made based on the high-risk intersection points, and the vehicle driving status is adjusted accordingly.

2. The method as described in claim 1, characterized in that, The step of obtaining the current road attribute parameters includes: Send a data request instruction to the map data server so that the map data server returns a map data package according to the data request instruction; Receive the map data packet returned by the map data server; The integrity of the map data packet is verified, and the verification result is obtained. When the verification result indicates that the data is complete, the map data package is stored in the local cache to obtain the local cache update result; Read map data from the local cache and extract current road attribute parameters from the map data.

3. The method as described in claim 1, characterized in that, The step of comparing the current road attribute parameters with preset intersection attribute values ​​to obtain the intersection scene determination result includes: Read the preset intersection attribute values; Extract the attribute identifier field from the current road attribute parameters; The attribute identifier field is compared with the preset intersection attribute value to obtain the attribute comparison result; When the attribute comparison results indicate that the two are consistent, the current driving scenario is determined to be an intersection scenario, and an intersection scenario determination result is obtained.

4. The method as described in claim 1, characterized in that, The step of retrieving intersection collision route data from pre-stored data based on the intersection scene determination result, wherein the intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles, includes: The intersection scene determination result is analyzed to obtain the intersection signage information; The target data storage address is obtained by querying the pre-stored data index based on the intersection sign information; Read the original intersection data according to the target data storage address; The original intersection data is parsed to obtain intersection collision route data, which includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles.

5. The method as described in claim 1, characterized in that, The step of matching the vehicle's travel trajectory with the potential collision trajectories of surrounding vehicles to obtain high-risk intersection points includes: The vehicle's travel trajectory is projected onto the intersection's plane coordinate system to obtain the first trajectory coordinate sequence; The potential collision trajectories of the surrounding vehicles are projected onto the intersection plane coordinate system to obtain the second trajectory coordinate sequence; Spatial intersection analysis is performed on the first trajectory coordinate sequence and the second trajectory coordinate sequence to obtain the trajectory intersection region; The intersection density is calculated within the intersection area of ​​the trajectories to obtain the intersection density value; The intersection locations where the intersection density value is greater than the preset density threshold are identified as high-risk intersection locations.

6. The method as described in claim 1, characterized in that, The step of performing risk prediction based on the high-risk intersection locations, obtaining risk prediction results, and adjusting vehicle driving status according to the risk prediction results includes: Obtain the vehicle's current location and current speed; Calculate the remaining distance between the current location of the vehicle and the high-risk intersection point; The estimated arrival time is calculated based on the remaining distance and the current speed of the vehicle. When the estimated arrival time is less than a preset time threshold, a risk prediction result is generated, and the vehicle driving status is adjusted according to the risk prediction result.

7. The method as described in claim 6, characterized in that, The step of calculating the estimated arrival time based on the remaining distance and the vehicle's current speed includes: Obtain the preset and historical traffic duration statistics for the intersection; Calculate the time correction coefficient based on the preset passage time of the intersection and the historical passage time statistics; The estimated arrival time is calculated based on the remaining distance, the current speed of the vehicle, and the time correction factor.

8. An autonomous driving active collision avoidance device based on a pre-set collision route at an intersection, characterized in that, The device includes: The parameter acquisition module is used to obtain the current road attribute parameters; The comparison module is used to compare the current road attribute parameters with the preset intersection attribute values ​​to obtain the intersection scene determination result; The route retrieval module is used to retrieve intersection collision route data from pre-stored data based on the intersection scene determination result. The intersection collision route data includes the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles. The trajectory intersection matching module is used to perform intersection matching between the vehicle's travel trajectory and the potential collision trajectories of surrounding vehicles to obtain high-risk intersection points at the intersection. The risk prediction and control module is used to predict risks based on the high-risk intersection points, obtain risk prediction results, and adjust the vehicle driving status according to the risk prediction results.

9. An autonomous driving active collision avoidance device based on a pre-set collision route at an intersection, characterized in that, The device includes: a memory, a processor, and an autonomous driving active collision avoidance program based on a preset collision route at an intersection, stored in the memory and executable on the processor, wherein the autonomous driving active collision avoidance program based on a preset collision route at an intersection is configured to implement the steps of the autonomous driving active collision avoidance method based on a preset collision route at an intersection as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores an autonomous driving active collision avoidance program based on a preset collision route at an intersection. When the processor executes the autonomous driving active collision avoidance program based on the preset collision route at an intersection, it implements the steps of the autonomous driving active collision avoidance method based on a preset collision route at an intersection as described in any one of claims 1 to 7.

Images