A vehicle autonomous return control method and device without satellite navigation and a medium

Abstract

The application discloses a kind of vehicle autonomous return control method, device and medium without satellite navigation, the method includes the following steps: to unmanned vehicle executes before departure preparation inspection operation, obtains preparation inspection result;According to preparation inspection result, unmanned vehicle is controlled to carry out journey detection;According to the feedback data of unmanned vehicle in journey detection, obtain the driving vehicle condition data and environmental detection data of unmanned vehicle;According to driving vehicle condition data and environmental detection data, point cloud map is constructed;The map quality of point cloud map is judged, and according to map quality, unmanned vehicle is selected to execute self-driving return operation or phased return operation;The application can be when unmanned vehicle investigates and explores road, according to the vehicle condition data of unmanned vehicle, intelligently infers the location of unmanned vehicle, and when returning, according to the aforementioned vehicle condition data and inference data, intelligently control unmanned vehicle to enter adaptive return trajectory and autonomous return mode of environment, realizes the autonomous road exploration return of unmanned vehicle under satellite system and satellite signal without needing.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to the field of autonomous return-to-home control for unmanned vehicles, and particularly to a method, device, and medium for autonomous return-to-home control of vehicles without the need for satellite navigation. Background Technology

[0002] Currently, in the application of military unmanned vehicles, there are often scenarios where remotely controlled unmanned vehicles are used for forward reconnaissance. In this scenario, the unmanned vehicle is remotely controlled to go to a location area to conduct environmental reconnaissance and collect feedback image information. After the reconnaissance is completed, the unmanned vehicle needs to return to the corresponding starting position. In order to ensure the accurate and rapid return of the unmanned vehicle, the existing technology uses a satellite positioning system to assist the unmanned vehicle in returning. When the unmanned vehicle is conducting outward reconnaissance, the latitude and longitude coordinates of the unmanned vehicle are recorded, and the trajectory of the unmanned vehicle is recorded. When returning, the unmanned vehicle is autonomously controlled to return along the outward trajectory.

[0003] The current unmanned vehicle return method relies excessively on satellite positioning systems and satellite signals. When the satellite positioning system malfunctions or the satellite signal is interfered with, the unmanned vehicle cannot return autonomously. Summary of the Invention

[0004] The purpose of this invention is to address the aforementioned problems in the prior art by providing a vehicle autonomous return control method, device, and medium that does not require satellite navigation. This solves the problem that existing autonomous return control methods for unmanned vehicles that rely on satellite positioning systems and satellite signals cannot perform autonomous return when the satellite positioning system malfunctions or the satellite signal is interfered with.

[0005] To solve the above-mentioned technical problems, the specific technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a vehicle autonomous return-to-home control method without satellite navigation, comprising the following steps:

[0007] Perform pre-departure checks on the driverless vehicle and obtain the check results;

[0008] Based on the inspection results, the unmanned vehicle is controlled to perform outbound journey detection.

[0009] Based on the feedback data from the unmanned vehicle during the outbound journey detection, the driving condition data and environmental detection data of the unmanned vehicle are obtained.

[0010] A point cloud map is constructed based on the vehicle condition data and the environmental detection data.

[0011] The quality of the point cloud map is determined, and the autonomous vehicle is selected to perform either a self-driving return operation or a phased return operation based on the map quality.

[0012] As an improved approach, the test results include: normal test results and abnormal test results.

[0013] The step of controlling the unmanned vehicle to perform outbound journey detection based on the test results includes:

[0014] When the inspection result is normal, the first current position of the unmanned vehicle is set as the origin of the outbound detection, and the outbound detection mode of the unmanned vehicle is activated.

[0015] As an improved solution, the step of obtaining the autonomous vehicle's driving condition data and environmental detection data based on the feedback data from the autonomous vehicle during the outbound journey detection includes:

[0016] Set the position interval value;

[0017] Based on the feedback data and the location interval value, the driving condition data of the unmanned vehicle during the outbound journey detection is periodically calculated;

[0018] Whenever the driving condition data is obtained, the environmental detection data that matches the driving condition data is acquired.

[0019] As an improved solution, the driving condition data includes: several predicted driving position data;

[0020] The environmental detection data includes: several environmental point cloud data that are respectively matched with several of the predicted driving position data;

[0021] The step of constructing a point cloud map based on the vehicle condition data and the environmental detection data includes:

[0022] The predicted driving location data and the environmental point cloud data are used as map construction data sources, and the point cloud map is constructed based on the map construction data sources and the point cloud coverage logic.

[0023] As an improved solution, determining the map quality of the point cloud map includes:

[0024] Calculate the location data of several point cloud center points corresponding to several of the environmental point cloud data;

[0025] The map quality of the point cloud map is determined based on the regularity of the point cloud map and the degree of deviation between the predicted driving position data and the center point position data of the point cloud.

[0026] As an improvement, the map quality includes: high quality and low quality;

[0027] The step of selecting whether to perform a self-driving return trip or a phased return trip for the unmanned vehicle based on the map quality includes:

[0028] When the map quality is high, the autonomous vehicle is selected to perform the self-driving return operation.

[0029] When the map quality is low, the unmanned vehicle will be selected to perform the phased return operation.

[0030] As an improved solution, the self-driven return operation includes:

[0031] Let the position data of several point cloud center points be used as several target trajectory points;

[0032] Construct the return target trajectory based on several of the aforementioned target trajectory points;

[0033] Let the return target trajectory be the target path of the unmanned vehicle, let the outbound detection origin be the return destination of the unmanned vehicle, and control the unmanned vehicle to autonomously return according to the target path and the return destination;

[0034] The phased return operation includes:

[0035] Let some of the predicted driving position data be used as several target position points;

[0036] The unmanned vehicle is controlled to autonomously return at intervals according to the specified position interval values ​​and several specified target position points.

[0037] As an improved approach, the pre-departure inspection of the unmanned vehicle, and the resulting inspection results, include:

[0038] The effectiveness of the radar signals, inertial navigation signals, and vehicle speed feedback signals associated with the unmanned vehicle is detected;

[0039] If the radar signal, the inertial navigation signal, and the vehicle speed feedback signal associated with the unmanned vehicle are all valid, then the test result is set to normal.

[0040] If the validity of the radar signal, the inertial navigation signal, or the vehicle speed feedback signal associated with the unmanned vehicle is invalid, then the test result is set as the test result abnormal.

[0041] On the other hand, the present invention also provides a vehicle autonomous return-to-home control device that does not require satellite navigation, comprising:

[0042] The unmanned vehicle detection unit is used to perform pre-departure inspections on unmanned vehicles and obtain the inspection results.

[0043] The unmanned vehicle outbound control unit is used to control the unmanned vehicle to perform outbound detection based on the test results.

[0044] The unmanned vehicle outbound control unit is also used to acquire the unmanned vehicle's driving condition data and environmental detection data based on the feedback data from the unmanned vehicle during the outbound detection.

[0045] A map building unit is used to build a point cloud map based on the vehicle condition data and the environmental detection data;

[0046] The return control unit is used to determine the map quality of the point cloud map and select whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality.

[0047] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the vehicle autonomous return-to-home control method without satellite navigation.

[0048] The beneficial effects of the technical solution of this invention are:

[0049] The autonomous vehicle return-to-home control method without satellite navigation described in this invention can intelligently infer the location of the unmanned vehicle (UAV) based on its vehicle condition data during reconnaissance and exploration. During return, based on the inferred location and the environmental point cloud data detected by the UAV, it intelligently identifies a suitable return trajectory for the current situation and intelligently controls the UAV to enter an autonomous return-to-home mode appropriate to the current trajectory. Ultimately, it achieves autonomous pathfinding and autonomous return for the UAV without relying on satellite systems and signals, overcoming the shortcomings of existing technologies, improving the functionality and versatility of UAVs, and enhancing the situational adaptability of autonomous driving technology. It has extremely high application value.

[0050] The autonomous vehicle return-to-home control device without satellite navigation described in this invention can achieve the following through the cooperation of an unmanned vehicle detection unit, an unmanned vehicle outbound control unit, a map building unit, and a return-to-home control unit: when the unmanned vehicle is conducting reconnaissance and exploration, it can intelligently infer the location of the unmanned vehicle based on the vehicle's condition data; and when returning, it can intelligently identify the unmanned vehicle's return trajectory suitable for the current situation based on the inferred location and the environmental point cloud data detected by the unmanned vehicle, and intelligently control the unmanned vehicle to enter the autonomous return-to-home mode suitable for the current return trajectory. Ultimately, it achieves autonomous path finding and autonomous return of the unmanned vehicle without relying on satellite systems and satellite signals, making up for the shortcomings of existing technologies, improving the functionality and universality of unmanned vehicles, and enhancing the situational adaptability of unmanned vehicle autonomous driving technology, thus having extremely high application value.

[0051] The computer-readable storage medium of this invention enables the unmanned vehicle detection unit, unmanned vehicle outbound control unit, unmanned vehicle outbound control unit, map building unit, and return control unit to cooperate, thereby realizing the vehicle autonomous return control method without satellite navigation described in this invention. The computer-readable storage medium of this invention effectively improves the operability of the vehicle autonomous return control method without satellite navigation. Attached Figure Description

[0052] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating the vehicle autonomous return-to-home control method without satellite navigation as described in Embodiment 1 of the present invention;

[0054] Figure 2 This is a schematic diagram of the logic flow of the vehicle autonomous return control method without satellite navigation described in Embodiment 1 of the present invention;

[0055] Figure 3 This is a schematic diagram of the architecture of the vehicle autonomous return control device without satellite navigation described in Embodiment 2 of the present invention;

[0056] The markings in the attached diagram are explained as follows:

[0057] 111. Unmanned vehicle detection unit; 112. Unmanned vehicle outbound control unit; 113. Map building unit; 114. Return control unit. Detailed Implementation

[0058] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby providing a clearer and more explicit definition of the scope of protection of the present invention.

[0059] In the description of this invention, it should be noted that the embodiments described in this invention are only some embodiments of this invention, not all embodiments; based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0060] The terms "first," "second," etc., used in this specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. Example 1

[0061] This embodiment provides a method for autonomous vehicle return-to-home control without satellite navigation, such as... Figure 1 and Figure 2 As shown, it includes the following steps:

[0062] S100: Perform pre-departure checks on the unmanned vehicle and obtain the check results;

[0063] S200: Control the unmanned vehicle to perform outbound journey detection based on the inspection results;

[0064] S300. Based on the feedback data from the unmanned vehicle during the outbound journey detection, obtain the driving condition data and environmental detection data of the unmanned vehicle.

[0065] S400: Construct a point cloud map based on the vehicle condition data and the environmental detection data;

[0066] S500: Determine the map quality of the point cloud map, and select whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality.

[0067] As one embodiment of the present invention, the pre-departure inspection operation for the unmanned vehicle to obtain the inspection results includes:

[0068] Before the autonomous vehicle departs from its initial position, various signals and functions on the vehicle need to be checked to ensure they are normal before departure. Therefore, map coordinates are initialized, and the validity of the radar signals, inertial navigation signals, and speed feedback signals associated with the autonomous vehicle is checked. If all three signals are valid, the check result is set to "check normal." If any one of these signals is invalid, the check result is set to "check abnormal." Specifically, during actual operation, the configured autonomous control unit reads data from the lidar, inertial navigation, and vehicle speed information fed back from the chassis VCU (vehicle control unit) via its communication interface, and verifies the validity of each signal. When all signals are normal, the check result is set to "check normal," allowing the autonomous vehicle to enter outbound mode for subsequent feedback. Simultaneously, map coordinates are initialized, and the current position of the autonomous vehicle is considered the map origin.

[0069] As one embodiment of the present invention, the inspection results include: normal inspection and abnormal inspection. Therefore, controlling the unmanned vehicle to perform outbound detection based on the inspection results includes: when the inspection result is normal, setting the first current position of the unmanned vehicle as the outbound detection origin and activating the outbound detection mode of the unmanned vehicle; the first current position is the aforementioned current position of the unmanned vehicle, and the outbound detection origin is the aforementioned map origin; the outbound detection mode is the aforementioned outbound mode of the unmanned vehicle, which is mainly used in the actual pathfinding operation of the unmanned vehicle;

[0070] In one embodiment of the present invention, the driving condition data includes: a plurality of predicted driving position data; the environmental detection data includes: a plurality of environmental point cloud data that are respectively matched with the plurality of predicted driving position data;

[0071] As one embodiment of the present invention, the step of obtaining the driving condition data and environmental detection data of the unmanned vehicle based on the feedback data of the unmanned vehicle in the outbound detection includes:

[0072] A position interval value is set, which is a distance interval set according to specific pathfinding requirements. Therefore, based on the position interval value and the feedback data obtained by the unmanned vehicle during its outward journey detection, the driving condition data of the unmanned vehicle during its outward journey detection is periodically calculated. Because this implementation is a periodic calculation, the driving condition data is actually calculated whenever the unmanned vehicle travels a distance corresponding to the position interval value during its outward journey. Therefore, there are multiple driving condition data sets, which are periodic data obtained based on the position interval value, namely the aforementioned predicted driving position data. Therefore, whenever the driving condition data is obtained, the environmental detection data matching the driving condition data is acquired. Correspondingly, the pathfinding scenario of the unmanned vehicle can be reconstructed based on the periodically obtained driving condition data and its corresponding environmental detection data. In this implementation, the driving condition data is based on the vehicle's three-axis acceleration and three-axis angular velocity fed back by inertial navigation during the unmanned vehicle's outward journey. The system uses speed data and the vehicle's speed signal to calculate the approximate position and trajectory of the autonomous vehicle on its outward journey. Specifically, due to signal noise, measurement errors, and computational model errors, the driving condition data calculated in this way is actually a rough estimate. The environmental detection data is the real-time environmental point cloud data accurately perceived and fed back by the autonomous vehicle for each driving condition. In practical applications, the predicted driving position data is the calculated coordinate position of the autonomous vehicle, with a position interval of 3 meters. Every 3 meters the autonomous vehicle travels, the calculated coordinate position and the corresponding point cloud of the surrounding environment obtained by the vehicle's LiDAR scan at that coordinate position are recorded in the autonomous control unit in a one-to-one correspondence. The aforementioned 3-meter value can be preset or dynamically adjusted according to the vehicle speed. Furthermore, when the autonomous vehicle is operated to return, the position and point cloud of the last frame of its journey must also be recorded to avoid losing the last moment's position and introducing calculation errors.

[0073] The step of constructing a point cloud map based on the driving condition data and the environmental detection data includes: using a plurality of predicted driving position data and a plurality of environmental point cloud data as map construction data sources, and constructing the point cloud map based on the map construction data sources and point cloud coverage logic; correspondingly, the point cloud map is SLAM (Simultaneous Localization and Mapping). SLAM (Single-Like Algebra) point cloud mapping; this step specifically involves matching and constructing a map based on the data source. During construction, the point cloud overlay logic involves aligning and covering the overlapping point cloud portions in every two adjacent environmental point cloud data sets, ultimately stitching together several environmental point cloud data sets. Correspondingly, after the point cloud map is constructed, a basis for determining the accurate driving trajectory is established. Because when perceiving environmental point cloud data, the autonomous vehicle must be located at the center of the environment, and the environmental point cloud data is precisely perceived data, calculating the center point coordinates of each environmental point cloud data set yields the corresponding precise location of the autonomous vehicle. Based on this precise location, the precise trajectory of the autonomous vehicle can be connected. After the point cloud map is constructed, it is transmitted back to the operators of the autonomous vehicle via a thumbnail or screenshot.

[0074] In one embodiment of the present invention, the map quality includes high quality and low quality; the determination of the map quality of the point cloud map includes: calculating the position data of the center points of the point clouds corresponding to the environmental point cloud data respectively, wherein the position data of the center points of the point clouds are the coordinates of the center point of each environmental point cloud data; the map quality of the point cloud map is determined according to the regularity of the point cloud map and the degree of deviation between the predicted driving position data and the position data of the center points of the point clouds respectively; the regularity of the point cloud map can be determined according to the tortuosity of the point cloud map, the overlap of point clouds, or the clarity and regularity of the trajectory formed by connecting the predicted driving position data, and the degree of deviation between the predicted driving position data and the position data of the center points of the point clouds respectively reflects the deviation between the initially calculated predicted driving position data and the accurate position data of the point clouds, thereby reflecting whether the initially calculated predicted driving position data is an accurate location point; correspondingly, in this embodiment, the degree of deviation is determined by the difference between the position data of the center points of the point clouds and the predicted driving position data, and by a preset error The method uses a threshold (e.g., an error threshold of ±0.5m) to compare the difference between the point cloud center point location data and the predicted driving position data with the error threshold. If the difference is not greater than the error threshold, the deviation is considered small; if the difference is greater than the error threshold, the deviation is considered large. In this embodiment, map quality can be judged manually. The regularity can be judged by manually identifying the clarity and regularity of the trajectory formed by connecting several predicted driving position data. For example, if the trajectory formed by connecting several predicted driving position data has large fluctuations, a high frequency of inflection points, and a large degree of tortuosity, then the regularity of the point cloud map is judged to be poor; if the trajectory formed by connecting several predicted driving position data has small fluctuations, a low frequency of inflection points, a low degree of tortuosity, and a smooth curve, then the regularity of the point cloud map is judged to be high. In this embodiment, when the regularity of the point cloud map is high and the aforementioned deviation is small, the map quality of the point cloud map is judged to be high; when the regularity of the point cloud map is poor and the aforementioned deviation is large, the map quality of the point cloud map is judged to be low.

[0075] As one embodiment of the present invention, the step of selecting whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality includes:

[0076] When the map quality is high, it means that the map point cloud data is accurate. The point cloud map can be used as a reference map for the self-driving return trip. Therefore, it is necessary to accurately calculate the position data (e.g., coordinate data) of the center point of each environmental point cloud data in the map. Connecting them can form an accurate return target trajectory. The unmanned vehicle can automatically and continuously return along this target trajectory. Therefore, the self-driving return trip operation is selected for the unmanned vehicle.

[0077] When the map quality is low, it indicates that the initially predicted position of the unmanned vehicle is significantly off. Considering that the environmental conditions encountered during the return trip will also deviate from the point cloud map when the position deviation is large, a segmented return is required. Therefore, the unmanned vehicle is selected to perform the segmented return operation.

[0078] As one embodiment of the present invention, the self-driving return operation includes: using the position data of several point cloud center points as several target trajectory points; constructing a return target track based on the several target trajectory points, that is, sequentially connecting the several target trajectory points to form a return target track; using the point cloud map as the navigation basis, using the return target track as the target path of the unmanned vehicle, using the outbound detection origin as the return destination of the unmanned vehicle, and controlling the unmanned vehicle to autonomously return according to the target path and the return destination. At this time, the unmanned vehicle can enter the autonomous path tracking mode, and then return along the precise trajectory of the outbound journey. At the same time, the unmanned vehicle relies on the aforementioned point cloud map for precise real-time positioning. During this return process, a relatively fast vehicle speed can be set, thereby achieving high-speed return of the unmanned vehicle with extremely high return efficiency.

[0079] As one embodiment of the present invention, the phased return operation includes: taking several predicted driving position data as several target position points; controlling the unmanned vehicle to perform intermittent autonomous return according to the position interval value and several target position points; correspondingly, for example, the aforementioned position interval value is 3 meters, then in this embodiment, under this phased return operation, due to the poor quality of the point cloud map, it is not possible to enter the real-time positioning mode relying on the map. At this time, it is necessary to determine a local travel position deviation every 3 meters (i.e., position interval value) for the coarse point cloud and its corresponding predicted coarse position (i.e., the aforementioned target position points). By controlling the unmanned vehicle to go to the coarse position, the position deviation is eliminated, so that the current environmental point cloud of the unmanned vehicle is consistent with the coarse point cloud. In this way, by continuously controlling the unmanned vehicle to match each coarse point cloud and coarse position, the unmanned vehicle can be gradually controlled to return to the starting point. Example 2

[0080] This embodiment is based on the same inventive concept as the vehicle autonomous return-to-home control method without satellite navigation described in Embodiment 1, and provides a vehicle autonomous return-to-home control device without satellite navigation, such as... Figure 3 As shown, it includes:

[0081] The unmanned vehicle detection unit 111 is used to perform pre-departure inspections on the unmanned vehicle and obtain the inspection results.

[0082] The unmanned vehicle outbound control unit 112 is used to control the unmanned vehicle to perform outbound detection based on the inspection results; the unmanned vehicle outbound control unit 112 obtains the driving condition data and environmental detection data of the unmanned vehicle based on the feedback data of the unmanned vehicle in the outbound detection.

[0083] Map building unit 113 is used to build a point cloud map based on the driving condition data and the environmental detection data;

[0084] The return control unit 114 is used to determine the map quality of the point cloud map and select whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality.

[0085] As one embodiment of the present invention, the test results include: normal test results and abnormal test results;

[0086] The step of controlling the unmanned vehicle to perform outbound journey detection based on the test results includes:

[0087] When the inspection result is normal, the first current position of the unmanned vehicle is set as the origin of the outbound detection, and the outbound detection mode of the unmanned vehicle is activated.

[0088] As one embodiment of the present invention, the unmanned vehicle outbound control unit 112 includes: a value setting module, a periodic calculation module, and a point cloud recording module;

[0089] In one embodiment of the present invention, the unmanned vehicle outbound control unit 112 acquires the unmanned vehicle's driving condition data and environmental detection data based on the feedback data from the unmanned vehicle during outbound detection, including:

[0090] The numerical setting module is used to set the position interval value;

[0091] The periodic calculation module is used to periodically calculate the driving condition data of the unmanned vehicle in the outbound detection based on the feedback data and the position interval value.

[0092] The point cloud recording module is used to acquire environmental detection data that matches the driving condition data whenever the driving condition data is obtained.

[0093] In one embodiment of the present invention, the driving condition data includes: a plurality of predicted driving position data; the environmental detection data includes: a plurality of environmental point cloud data that are respectively matched with the plurality of predicted driving position data;

[0094] As one embodiment of the present invention, the map building unit 113 constructs a point cloud map based on the driving condition data and the environmental detection data, including:

[0095] The map building unit 113 uses several of the predicted driving location data and several of the environmental point cloud data as map building data sources, and builds the point cloud map based on the map building data sources and point cloud coverage logic.

[0096] As one embodiment of the present invention, the return control unit 114 includes: a map recognition module, a self-driving control module, and a phased return control module;

[0097] In one embodiment of the present invention, the return control unit 114 determines the map quality of the point cloud map by: a map recognition module calculating the position data of several point cloud center points corresponding to several environmental point cloud data; and the map recognition module determining the map quality of the point cloud map based on the regularity of the point cloud map and the degree of deviation between several predicted driving position data and several point cloud center point position data.

[0098] As one embodiment of the present invention, the map quality includes: high quality and low quality;

[0099] In one embodiment of the present invention, the return control unit 114 selects to perform a self-driving return operation or a phased return operation on the unmanned vehicle according to the map quality, including: a self-driving control module is used to select to perform the self-driving return operation on the unmanned vehicle when the map quality is high; and a phased return control module is used to select to perform the phased return operation on the unmanned vehicle when the map quality is low.

[0100] In one embodiment of the present invention, the self-driven return operation includes: the self-driven control module designating the position data of several point cloud center points as several target trajectory points; the self-driven control module constructing a return target trajectory based on the several target trajectory points; the self-driven control module designating the return target trajectory as the target path of the unmanned vehicle, the self-driven control module designating the outbound detection origin as the return destination of the unmanned vehicle, and controlling the unmanned vehicle to autonomously return according to the target path and the return destination;

[0101] As one embodiment of the present invention, the phased return operation includes: the phased return control module designating several of the predicted driving position data as several target position points; and the phased return control module controlling the unmanned vehicle to perform intermittent autonomous return according to the position interval value and the several target position points.

[0102] In one embodiment of the present invention, the unmanned vehicle detection unit 111 performs a pre-departure inspection operation on the unmanned vehicle to obtain an inspection result, including: the unmanned vehicle detection unit 111 detects the validity of the radar signal, inertial navigation signal, and vehicle speed feedback signal associated with the unmanned vehicle; if the validity of the radar signal, inertial navigation signal, and vehicle speed feedback signal associated with the unmanned vehicle is valid, the unmanned vehicle detection unit 111 sets the inspection result as normal; if the validity of the radar signal, inertial navigation signal, or vehicle speed feedback signal associated with the unmanned vehicle is invalid, the unmanned vehicle detection unit 111 sets the inspection result as abnormal. Example 3

[0103] This embodiment provides a computer-readable storage medium, including:

[0104] The storage medium is used to store computer software instructions for implementing the satellite navigation-free autonomous vehicle return control method described in Embodiment 1 above. It includes a program for executing the above-described satellite navigation-free autonomous vehicle return control method. Specifically, the executable program can be built into the satellite navigation-free autonomous vehicle return control device described in Embodiment 2. In this way, the satellite navigation-free autonomous vehicle return control device can implement the satellite navigation-free autonomous vehicle return control method described in Embodiment 1 by executing the built-in executable program.

[0105] Furthermore, the computer-readable storage medium in this embodiment can be any combination of one or more readable storage media, wherein the readable storage medium includes an electrical, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.

[0106] Unlike existing technologies, this application presents a vehicle autonomous return-to-home control method, device, and medium that does not require satellite navigation. During unmanned vehicle (UAV) reconnaissance and exploration, the method intelligently infers the UAV's location based on its vehicle status data. During return-to-home, based on the inferred location and the environmental point cloud data detected by the UAV, it intelligently identifies a suitable return trajectory for the current situation and intelligently controls the UAV to enter an autonomous return-to-home mode appropriate to the current trajectory. Ultimately, this achieves autonomous pathfinding and return-to-home for UAVs without relying on satellite systems or signals, overcoming the shortcomings of existing technologies, improving the functionality and versatility of UAVs, and enhancing the situational adaptability of autonomous driving technology. It has extremely high application value.

[0107] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0108] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0109] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0110] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0111] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0113] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this paper, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for autonomous vehicle return control without satellite navigation, characterized in that, Includes the following steps: Perform pre-departure checks on the driverless vehicle and obtain the check results; Based on the inspection results, the unmanned vehicle is controlled to perform outbound journey detection. Based on the feedback data from the unmanned vehicle during the outbound journey detection, the driving condition data and environmental detection data of the unmanned vehicle are obtained. A point cloud map is constructed based on the vehicle condition data and the environmental detection data. Determine the map quality of the point cloud map, and select whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality. The step of obtaining the driving condition data and environmental detection data of the unmanned vehicle based on the feedback data of the unmanned vehicle in the outbound detection includes: setting a position interval value; periodically calculating the driving condition data of the unmanned vehicle in the outbound detection based on the feedback data and the position interval value; and obtaining the environmental detection data that matches the driving condition data whenever the driving condition data is obtained. The driving condition data includes: several predicted driving position data; the environmental detection data includes: several environmental point cloud data that are respectively matched with several predicted driving position data; the step of constructing a point cloud map based on the driving condition data and the environmental detection data includes: using several predicted driving position data and several environmental point cloud data as map construction data sources, and constructing the point cloud map based on the map construction data sources and point cloud coverage logic. The step of determining the map quality of the point cloud map includes: calculating the position data of several point cloud center points corresponding to several environmental point cloud data; and determining the map quality of the point cloud map based on the regularity of the point cloud map and the degree of deviation between several predicted driving position data and several point cloud center point position data. The map quality includes high quality and low quality; the step of selecting whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality includes: when the map quality is high quality, selecting to perform the self-driving return operation for the unmanned vehicle; when the map quality is low quality, selecting to perform the phased return operation for the unmanned vehicle. The self-driving return operation includes: using the position data of several point cloud center points as several target trajectory points; constructing a return target trajectory based on several target trajectory points; using the return target trajectory as the target path of the unmanned vehicle, setting the outbound detection origin as the return destination of the unmanned vehicle, and controlling the unmanned vehicle to autonomously return according to the target path and the return destination; The phased return operation includes: using several of the predicted driving position data as several target position points; controlling the unmanned vehicle to perform intermittent autonomous return according to the position interval value and the several target position points.

2. The vehicle autonomous return-to-home control method without satellite navigation according to claim 1, characterized in that: The test results include: normal test results and abnormal test results. The step of controlling the unmanned vehicle to perform outbound journey detection based on the test results includes: When the inspection result is normal, the first current position of the unmanned vehicle is set as the origin of the outbound detection, and the outbound detection mode of the unmanned vehicle is activated.

3. The vehicle autonomous return control method without satellite navigation according to claim 2, characterized in that: The pre-departure inspection of the unmanned vehicle, and the resulting inspection results, include: The effectiveness of the radar signals, inertial navigation signals, and vehicle speed feedback signals associated with the unmanned vehicle is detected; If the radar signal, the inertial navigation signal, and the vehicle speed feedback signal associated with the unmanned vehicle are all valid, then the test result is set to normal. If the validity of the radar signal, the inertial navigation signal, or the vehicle speed feedback signal associated with the unmanned vehicle is invalid, then the test result is set as the test result abnormal.

4. A vehicle autonomous return-to-home control device without satellite navigation, characterized in that, include: The unmanned vehicle detection unit is used to perform pre-departure inspections on unmanned vehicles and obtain the inspection results. The unmanned vehicle outbound control unit is used to control the unmanned vehicle to perform outbound detection based on the inspection results; the unmanned vehicle outbound control unit obtains the driving condition data and environmental detection data of the unmanned vehicle based on the feedback data of the unmanned vehicle in the outbound detection. A map building unit is used to build a point cloud map based on the vehicle condition data and the environmental detection data; The return control unit is used to determine the map quality of the point cloud map and select whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality. The autonomous vehicle outbound journey control unit includes: a value setting module, a periodic calculation module, and a point cloud recording module. The autonomous vehicle outbound journey control unit acquires the autonomous vehicle's driving condition data and environmental detection data based on feedback data from the autonomous vehicle during outbound journey detection. This includes: the value setting module setting position interval values; the periodic calculation module periodically calculating the autonomous vehicle's driving condition data during outbound journey detection based on the feedback data and the position interval values; and the point cloud recording module acquiring environmental detection data matching the driving condition data each time it is obtained. The driving condition data includes: several predicted driving position data; the environmental detection data includes: several environmental point cloud data that are respectively matched with several predicted driving position data; the map building unit constructs a point cloud map based on the driving condition data and the environmental detection data, including: the map building unit uses several predicted driving position data and several environmental point cloud data as map building data sources, and constructs the point cloud map based on the map building data sources and point cloud coverage logic; The return-to-home control unit includes: a map recognition module, a self-driving control module, and a phased return-to-home control module; the return-to-home control unit determines the map quality of the point cloud map, including: the map recognition module calculating the position data of several point cloud center points corresponding to several environmental point cloud data respectively; the map recognition module determining the map quality of the point cloud map based on the regularity of the point cloud map and the degree of deviation between several predicted driving position data and several point cloud center point position data respectively; The map quality includes high quality and low quality; the return control unit selects whether to perform a self-driving return operation or a phased return operation for the unmanned vehicle based on the map quality, including: the self-driving control module is used to select the self-driving return operation for the unmanned vehicle when the map quality is high quality; the phased return control module is used to select the phased return operation for the unmanned vehicle when the map quality is low quality. The self-driven return operation includes: the self-driven control module designating the position data of several point cloud center points as several target trajectory points; the self-driven control module constructing a return target trajectory based on the several target trajectory points; the self-driven control module designating the return target trajectory as the target path of the unmanned vehicle, the self-driven control module designating the outbound detection origin as the return destination of the unmanned vehicle, and controlling the unmanned vehicle to autonomously return according to the target path and the return destination; The phased return operation includes: the phased return control module designating several of the predicted driving position data as several target position points; and the phased return control module controlling the unmanned vehicle to perform intermittent autonomous return according to the position interval value and the several target position points.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the vehicle autonomous return-to-home control method without satellite navigation as described in any one of claims 1 to 3.

Images