Navigation method and device of autonomous vehicle, electronic device, and storage medium

Abstract

The application discloses a navigation method and device of an automatic driving vehicle, an electronic device, and a storage medium. The method comprises the following steps: obtaining fusion positioning data of a first automatic driving vehicle on a current road section, wherein the fusion positioning data comprises satellite positioning data, laser radar positioning data, and visual positioning data; determining a positioning state of the current road section according to the fusion positioning data; determining whether the current road section triggers a preset reporting condition according to the positioning state of the current road section; when the current road section triggers the preset reporting condition, determining positioning state information of the current road section and reporting the positioning state information to the cloud, so that the cloud sends the positioning state information of the current road section to a second automatic driving vehicle and makes the second automatic driving vehicle navigate according to the positioning state information. According to the application, the positioning state of the current road section is determined through the fusion positioning data of the vehicle end, and the cloud is reported when the positioning state is abnormal, so that more reference information is provided for route planning of other automatic driving vehicles, and the overall operation efficiency of the automatic driving vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a navigation method and device of an automatic driving vehicle, an electronic device and a storage medium. BACKGROUND

[0002] With the rapid development of automatic driving technology, regional operation vehicles such as ROBOTAXI (automatic driving taxi) and ROBOBUS (automatic driving bus) are landing in more and more cities, and due to the limitations of current single vehicle intelligence, many automatic driving vehicles are driven according to pre-set or calculated routes. Because the automatic driving vehicle is highly dependent on the road environment, if a temporary repair occurs on a road section, causing the road to be blocked, the automatic driving vehicle is difficult to accurately identify the related events, such as temporary fences, and still drives according to the set route.

[0003] The automatic driving vehicle drives according to the set operation route in the operation area, and the route of the ROBOBUS is relatively fixed, and the ROBOTAXI needs to receive real-time information such as accident road sections and traffic jam road sections sent by the cloud in real time during driving, so as to update the driving route, reduce the waiting time and driving risk.

[0004] However, in most cases, the above real-time information only includes perception level information such as temporary road repair and vehicle accident caused congestion, which can be monitored by the road end perception device and fed back to the cloud to complete information synchronization. However, for positioning information such as the strength of the satellite signal corresponding to the road section and environmental changes, the road end device does not provide, which affects the positioning accuracy of the automatic driving vehicle when encountering such situations, and further causes frequent parking protection or manual takeover, reducing the operation efficiency. SUMMARY

[0005] The embodiments of the present application provide a navigation method, device, electronic device and storage medium of an automatic driving vehicle, to provide more reference information for navigation planning of the automatic driving vehicle and improve the operation efficiency of the automatic driving vehicle.

[0006] The embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, the embodiments of the present application provide a navigation method of an automatic driving vehicle, and the method comprises:

[0008] obtaining fusion positioning data of a first automatic driving vehicle on a current road section, the fusion positioning data comprising satellite positioning data, laser radar positioning data and visual positioning data;

[0009] determining a positioning state of the current road section according to the fusion positioning data;

[0010] determining whether the current road segment triggers a preset reporting condition according to the positioning state of the current road segment;

[0011] In a case where the current road segment triggers the preset reporting condition, determining positioning state information of the current road segment and reporting the positioning state information to a cloud end, so that the cloud end sends the positioning state information of the current road segment to a second autonomous vehicle and makes the second autonomous vehicle navigate according to the positioning state information of the current road segment.

[0012] Optionally, the determining the positioning state of the current road segment according to the fused positioning data comprises:

[0013] determining a positioning error between the satellite positioning data and the laser radar positioning data according to the satellite positioning data and the laser radar positioning data, and determining a visual lateral correction error according to the visual positioning data;

[0014] determining the positioning state of the current road segment according to the positioning error between the satellite positioning data and the laser radar positioning data and the visual lateral correction error.

[0015] Optionally, the determining the positioning state of the current road segment according to the positioning error between the satellite positioning data and the laser radar positioning data and the visual lateral correction error comprises:

[0016] comparing the positioning error between the satellite positioning data and the laser radar positioning data with a first preset error threshold, and comparing the visual lateral correction error with a second preset error threshold;

[0017] if the positioning error between the satellite positioning data and the laser radar positioning data is greater than the first preset error threshold and the visual lateral correction error is greater than the second preset error threshold, determining that the positioning state of the current road segment is an abnormal positioning state;

[0018] otherwise, determining that the positioning state of the current road segment is a normal positioning state.

[0019] Optionally, the determining whether the current road segment triggers the preset reporting condition according to the positioning state of the current road segment comprises:

[0020] if the positioning state of the current road segment is the abnormal positioning state, determining that the current road segment triggers the preset reporting condition;

[0021] otherwise, determining that the current road segment does not trigger the preset reporting condition.

[0022] Optionally, the positioning state information of the current road segment includes a type of the abnormal positioning state, and the determining and reporting of the positioning state information of the current road segment to the cloud in the case that the current road segment triggers the preset reporting condition includes:

[0023] determining a lateral distance in the satellite positioning data according to the satellite positioning data, and determining a lateral distance in the laser radar positioning data according to the laser radar positioning data;

[0024] comparing the lateral distance in the satellite positioning data and the lateral distance in the laser radar positioning data with the visual positioning data respectively;

[0025] determining the type of the abnormal positioning state according to the comparison result, the type of the abnormal positioning state including a satellite positioning interference state and a laser radar positioning interference state.

[0026] Optionally, the method further includes:

[0027] obtaining positioning state information of a plurality of road segments sent by the cloud;

[0028] adjusting path costs of the road segments according to the positioning state information of the road segments to obtain adjusted path costs of the road segments;

[0029] performing navigation according to the adjusted path costs of the road segments to obtain a navigation result of the first autonomous vehicle.

[0030] In a second aspect, the embodiments of the present application further provide a navigation device of an autonomous vehicle, wherein the device includes:

[0031] a first obtaining unit, configured to obtain fusion positioning data of a first autonomous vehicle on a current road segment, the fusion positioning data including satellite positioning data, laser radar positioning data and visual positioning data;

[0032] a first determining unit, configured to determine a positioning state of the current road segment according to the fusion positioning data;

[0033] a second determining unit, configured to determine whether the current road segment triggers a preset reporting condition according to the positioning state of the current road segment;

[0034] a reporting unit, configured to determine positioning state information of the current road segment and report to the cloud in the case that the current road segment triggers the preset reporting condition, so that the cloud sends the positioning state information of the current road segment to a second autonomous vehicle and makes the second autonomous vehicle perform navigation according to the positioning state information of the current road segment.

[0035] In a third aspect, the embodiments of the present application further provide a vehicle-road-cloud collaborative system, which comprises a vehicle end, a cloud end and a road end. The vehicle end is configured to execute any of the above-mentioned methods. The cloud end is configured to receive the positioning state information of the road segment reported by the vehicle end and send the positioning state information to the corresponding road end. The road end is configured to receive the positioning state information of the road segment sent by the cloud end and monitor the positioning state information.

[0036] In a fourth aspect, the embodiments of the present application further provide an electronic device, which comprises:

[0037] a processor; and

[0038] a memory arranged to store computer-executable instructions that, when executed, cause the processor to execute any of the above-mentioned methods.

[0039] In a fifth aspect, the embodiments of the present application further provide a computer-readable storage medium storing one or more programs, which, when executed by an electronic device comprising a plurality of applications, cause the electronic device to execute any of the above-mentioned methods.

[0040] The above-mentioned at least one technical scheme adopted by the embodiments of the present application can achieve the following beneficial effects: The navigation method of the autonomous vehicle according to the embodiments of the present application first acquires fusion positioning data of a first autonomous vehicle on a current road segment, wherein the fusion positioning data comprises satellite positioning data, laser radar positioning data and visual positioning data. Then, the positioning state of the current road segment is determined according to the fusion positioning data. After that, it is determined whether the current road segment triggers a preset reporting condition according to the positioning state of the current road segment. Finally, in the case that the current road segment triggers the preset reporting condition, the positioning state information of the current road segment is determined and reported to the cloud end, so that the cloud end sends the positioning state information of the current road segment to a second autonomous vehicle and makes the second autonomous vehicle navigate according to the positioning state information of the current road segment. The navigation method of the autonomous vehicle according to the embodiments of the present application determines the positioning state of the current road segment through the fusion positioning data of the vehicle end, and reports to the cloud end when the positioning state of the current road segment is abnormal, thereby providing more road segment reference information for route planning of other autonomous vehicles, and further improving the overall operation efficiency of the autonomous vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and their description serve to explain the present application, but do not constitute improper limitations on the present application. In the drawings:

[0042] Figure 1 FIG. 1 is a flowchart of a navigation method of an autonomous vehicle according to an embodiment of the present application;

[0043] Figure 2 FIG. 1 is a schematic diagram of a navigation device of an autonomous vehicle according to an embodiment of the present application;

[0044] Figure 3 FIG. 2 is a schematic diagram of a vehicle-road-cloud collaborative system according to an embodiment of the present application;

[0045] Figure 4 FIG. 3 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0047] The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the drawings.

[0048] The embodiments of the present application provide a navigation method of an autonomous vehicle, as shown in FIG. 1, a schematic diagram of a flow of a navigation method of an autonomous vehicle according to an embodiment of the present application is provided, and the method at least includes the following steps S110 to S140: Figure 1

[0049] Step S110, obtaining fusion positioning data of a first autonomous vehicle on a current road section, the fusion positioning data including satellite positioning data, laser radar positioning data and visual positioning data.

[0050] When navigating the autonomous vehicle, the fusion positioning data of the first autonomous vehicle on the current road section needs to be obtained first, and the fusion positioning data mainly includes satellite positioning data obtained based on GNSS (Global Navigation Satellite System) / RTK (Real-time Kinematic), positioning data obtained based on laser SLAM (Simultaneous Localization And Mapping), and lateral correction results of lane lines obtained based on visual recognition. The satellite positioning data, the laser radar positioning data and the visual positioning data all refer to data processed after time synchronization.

[0051] Step S120, determining a positioning state of the current road section according to the fusion positioning data.

[0052] ​The positioning data based on the above several dimensions can further determine the positioning state of the current road section. The positioning state of the current road section can be understood as determining the positioning state of each positioning module of the autonomous vehicle on the current road section. The purpose of determining the positioning state is to reflect whether the positioning result of the subsequent other autonomous vehicle passing through the road section can meet the positioning accuracy requirement and whether the autonomous vehicle can travel according to the planned navigation route. The determination of the positioning state of the current road section may, for example, include whether the satellite positioning signal of the current road section is disturbed, whether the environment changes to cause the laser radar positioning data to be disturbed, and the like.

[0053] In step S130, it is determined whether the current road section triggers a preset reporting condition according to the positioning state of the current road section.

[0054] After determining the positioning state of the current road section, it can be further determined whether the current road section triggers a preset reporting condition according to the positioning state of each positioning module on the current road section. The preset reporting condition is mainly used to determine whether the abnormal situation can be reported in time when the positioning state of the current road section is abnormal. If the positioning state is normal, it can be considered that the current road section does not trigger the preset reporting condition. Conversely, if the positioning state of the current road section is abnormal and cannot meet the positioning accuracy requirement of the autonomous vehicle, it is considered that the current road section triggers the preset reporting condition, and the abnormal situation of the current road section needs to be reported to the cloud.

[0055] In step S140, in the case that the current road section triggers the preset reporting condition, the positioning state information of the current road section is determined and reported to the cloud, so that the cloud sends the positioning state information of the current road section to the second autonomous vehicle and makes the second autonomous vehicle navigate according to the positioning state information of the current road section.

[0056] In the case that it is determined that the current road section triggers the preset reporting condition, the positioning state information of the current road section reported to the cloud needs to be further determined, which may, for example, include the specific type of abnormal positioning and the like. After receiving the positioning state information of the road section, the cloud can synchronize the information to the roadside device corresponding to the road section and the second autonomous vehicle, so as to facilitate the second autonomous vehicle to refer to the received positioning state information of each road section for navigation planning, thereby avoiding the abnormal road section in advance and improving the operation efficiency of the autonomous vehicle.

[0057] The navigation method of the autonomous vehicle of the embodiment of the application determines the positioning state of the current road section through the fusion positioning data of the vehicle end, and reports to the cloud when the positioning state of the current road section is abnormal, thereby providing more road section reference information for the route planning of other autonomous vehicles, and thereby improving the overall operation efficiency of the autonomous vehicle.

[0058] In some embodiments of the present application, the determining the positioning state of the current road segment according to the fusion positioning data comprises: determining a positioning error between the satellite positioning data and the lidar positioning data according to the satellite positioning data and the lidar positioning data, and determining a vision lateral correction error according to the vision positioning data; and determining the positioning state of the current road segment according to the positioning error between the satellite positioning data and the lidar positioning data and the vision lateral correction error.

[0059] In the determining of the positioning state of the current road segment according to the fusion positioning data, the positioning error can be determined according to the fusion positioning data first, which mainly includes the positioning error between the satellite positioning data and the lidar positioning data and the vision lateral correction error. Then, the positioning state of the current road segment, including the satellite positioning state and the lidar positioning state, etc., can be determined according to the size of the positioning error between the satellite positioning data and the lidar positioning data and the size of the vision lateral correction error.

[0060] The satellite positioning data contains the satellite positioning position, and the lidar positioning data contains the lidar positioning position. Therefore, the satellite positioning position and the lidar positioning position can be compared to calculate the positioning error between the satellite positioning data and the lidar positioning data. The vision lateral correction error can be directly determined according to the lane line lateral deviation output by the vision sensor.

[0061] In some embodiments of the present application, the determining the positioning state of the current road segment according to the positioning error between the satellite positioning data and the lidar positioning data and the vision lateral correction error comprises: comparing the positioning error between the satellite positioning data and the lidar positioning data with a first preset error threshold, and comparing the vision lateral correction error with a second preset error threshold; if the positioning error between the satellite positioning data and the lidar positioning data is greater than the first preset error threshold, and the vision lateral correction error is greater than the second preset error threshold, then determining that the positioning state of the current road segment is an abnormal positioning state; otherwise, determining that the positioning state of the current road segment is a normal positioning state.

[0062] The positioning state defined by the embodiments of the present application mainly includes a normal positioning state and an abnormal positioning state. The normal positioning state refers to that the fusion positioning module of the autonomous vehicle can output a fusion positioning result meeting the positioning accuracy requirement on the road section. The abnormal positioning state refers to that the fusion positioning module of the autonomous vehicle cannot output a fusion positioning result meeting the positioning accuracy requirement on the road section. For example, the GNSS / RTK positioning signal is interfered to cause an inability to output accurate high-precision positioning information, or the environment of the road section changes obviously to cause a large laser SLAM positioning error, which cannot meet the accuracy requirement of the fusion positioning.

[0063] In the case that all sensors work normally and are not interfered by external factors, the positioning error should be within a preset threshold range, which can be denoted as a first preset error threshold thre, and contains the error of the algorithm itself. Further considering the error err_map in map making, the transverse correction result of the lane should also be within thre+err_map, which can be denoted as a second preset error threshold thre_max.

[0064] The first preset error threshold thre is used to measure the error size of the positioning error between the satellite positioning data and the laser radar positioning data, and the second preset error threshold thre_max is used to measure the error size of the visual transverse correction error. In the actual driving process, if the positioning error between the satellite positioning data and the laser radar positioning data at the current time k is greater than thre (in order to ensure that the transverse correction result of the lane is correct, the positioning error between the satellite positioning data and the laser radar positioning data can be used as a judgment condition of the transverse correction result of the lane), and the transverse correction result of the lane is greater than thre_max (the transverse correction result of the lane can be used as a judgment condition of the reduction of the fusion positioning accuracy), that is, it is proved that the confidence of the fusion positioning result (i.e., the fusion positioning result of the laser radar positioning data and the GNSS / RTK positioning data) except the transverse correction result of the lane has been reduced at the time k. In the subsequent case that there is no lane or the lane recognition is interfered, such as vehicle shielding, ground water, snow, etc., the autonomous vehicle may deviate from the normal driving trajectory at any time. Therefore, this case can judge that the positioning state of the current road section is an abnormal positioning state.

[0065] In some embodiments of the present application, after determining the positioning state of the current road section according to the positioning error, the road condition of the current road section can be further confirmed according to the behavior of the autonomous vehicle, such as manual takeover, speed reduction or parking, etc., so as to improve the accuracy of the positioning state judgment.

[0066] In some embodiments of the present application, the determining whether the current road segment triggers the preset reporting condition according to the positioning state of the current road segment comprises: if the positioning state of the current road segment is an abnormal positioning state, determining that the current road segment triggers the preset reporting condition; otherwise, determining that the current road segment does not trigger the preset reporting condition.

[0067] When it is judged that the positioning state of the current road segment is an abnormal positioning state, it indicates that the satellite positioning signal or the laser radar positioning of the road segment may be interfered, causing the autonomous vehicle to be unable to obtain a fusion positioning result meeting the positioning accuracy requirement when passing through the road segment, and thus the abnormal positioning state of the road segment needs to be reported to the cloud in a timely manner, so as to timely inform other autonomous vehicles through the cloud and ensure the smoothness of the overall operation of the autonomous vehicle. Of course, if the positioning state of the current road segment is a normal positioning state, there is no need to report.

[0068] In some embodiments of the present application, the positioning state information of the current road segment comprises a type of abnormal positioning state, and the determining the positioning state information of the current road segment and reporting to the cloud in the case that the current road segment triggers the preset reporting condition comprises: determining a lateral distance in the satellite positioning data according to the satellite positioning data, and determining a lateral distance in the laser radar positioning data according to the laser radar positioning data; comparing the lateral distance in the satellite positioning data and the lateral distance in the laser radar positioning data with the visual positioning data respectively; and determining the type of the abnormal positioning state according to the comparison result, the type of the abnormal positioning state comprising a satellite positioning interference state and a laser radar positioning interference state.

[0069] When it is determined that the abnormal positioning state of the current road segment needs to be reported to the cloud, the specific information to be reported can be determined first, for example, can comprise an ID identification of the current road segment, a type of abnormal positioning state, for example, whether GNSS / RTK positioning is interfered or laser radar positioning is interfered, and whether the vehicle is normally driven or not.

[0070] When the type of the abnormal positioning state is determined, the lateral distance x1 at the current time can be first decomposed from the satellite positioning data at the current time, and the lateral distance x2 at the current time can also be decomposed from the laser radar positioning data, and the lateral distance x1 and the lateral distance x2 are compared with the lane line lateral correction result x3 in the visual positioning data at the corresponding time respectively, if the lane line lateral correction result x3 is closer to the lateral distance x1, it indicates that the abnormal positioning state is a laser radar positioning interference state, and if the lane line lateral correction result x3 is closer to the lateral distance x2, it indicates that the abnormal positioning state is a satellite positioning interference state, that is, the lane line lateral correction result is used to further identify whether the satellite positioning is abnormal or the laser radar positioning is abnormal.

[0071] In some embodiments of the present application, the method further comprises: obtaining positioning state information of the plurality of road segments sent by the cloud; adjusting the path cost of each road segment according to the positioning state information of each road segment to obtain the adjusted path cost of each road segment; and performing navigation according to the adjusted path cost of each road segment to obtain the navigation result of the first autonomous vehicle.

[0072] For the first autonomous vehicle, the positioning state information of each road segment sent by the cloud can also be received in real time during actual driving, so that the positioning state information of each road segment can be referred to for navigation path planning. For example, if the positioning state information of the road segments sent by the cloud indicates that the current road segment A and road segment B are in an abnormal positioning state, the path cost corresponding to road segment A and road segment B can be increased when the path planning is performed based on a path planning algorithm such as the A* algorithm, so that the generated planning route can avoid road segment A and road segment B as much as possible, thereby ensuring the smoothness of the overall operation of the autonomous vehicle and improving the operation efficiency.

[0073] The embodiments of the present application also provide a navigation device 200 of an autonomous vehicle, as shown in Figure 2 The structure schematic diagram of the navigation device of the autonomous vehicle in the embodiments of the present application is provided, and the device 200 at least comprises: a first acquisition unit 210, a first determination unit 220, a second determination unit 230, and a reporting unit 240, wherein:

[0074] The first acquisition unit 210 is configured to acquire fusion positioning data of the first autonomous vehicle in a current road segment, wherein the fusion positioning data comprises satellite positioning data, laser radar positioning data, and visual positioning data.

[0075] The first determination unit 220 is configured to determine the positioning state of the current road segment according to the fusion positioning data.

[0076] The second determination unit 230 is configured to determine whether the current road segment triggers a preset reporting condition according to the positioning state of the current road segment.

[0077] The reporting unit 240 is configured to determine the positioning state information of the current road segment and report the same to the cloud in the case that the current road segment triggers the preset reporting condition, so that the cloud sends the positioning state information of the current road segment to the second autonomous vehicle and makes the second autonomous vehicle perform navigation according to the positioning state information of the current road segment.

[0078] In some embodiments of the present application, the first determining unit 220 is specifically configured to: determine a positioning error between the satellite positioning data and the lidar positioning data according to the satellite positioning data and the lidar positioning data, and determine a visual lateral correction error according to the visual positioning data; and determine the positioning state of the current road segment according to the positioning error between the satellite positioning data and the lidar positioning data and the visual lateral correction error.

[0079] In some embodiments of the present application, the first determining unit 220 is specifically configured to: compare the positioning error between the satellite positioning data and the lidar positioning data with a first preset error threshold, and compare the visual lateral correction error with a second preset error threshold; if the positioning error between the satellite positioning data and the lidar positioning data is greater than the first preset error threshold, and the visual lateral correction error is greater than the second preset error threshold, determine that the positioning state of the current road segment is an abnormal positioning state; otherwise, determine that the positioning state of the current road segment is a normal positioning state.

[0080] In some embodiments of the present application, the second determining unit 230 is specifically configured to: if the positioning state of the current road segment is an abnormal positioning state, determine that the current road segment triggers the preset reporting condition; otherwise, determine that the current road segment does not trigger the preset reporting condition.

[0081] In some embodiments of the present application, the positioning state information of the current road segment includes a type of abnormal positioning state, and the reporting unit 240 is specifically configured to: determine a lateral distance in the satellite positioning data according to the satellite positioning data, and determine a lateral distance in the lidar positioning data according to the lidar positioning data; compare the lateral distance in the satellite positioning data and the lateral distance in the lidar positioning data with the visual positioning data respectively; and determine the type of abnormal positioning state according to the comparison result, the type of abnormal positioning state including a satellite positioning interference state and a lidar positioning interference state.

[0082] In some embodiments of the present application, the device further comprises: a second acquisition unit configured to acquire positioning state information of a plurality of road segments sent by the cloud; an adjustment unit configured to adjust a path cost of each road segment according to the positioning state information of each road segment to obtain an adjusted path cost of each road segment; and a navigation unit configured to perform navigation according to the adjusted path cost of each road segment to obtain a navigation result of the first autonomous vehicle.

[0083] It can be understood that the navigation device of the automatic driving vehicle described above can realize each step of the navigation method of the automatic driving vehicle provided in the foregoing embodiments, and the related explanations about the navigation method of the automatic driving vehicle are all applicable to the navigation device of the automatic driving vehicle, which will not be repeated here.

[0084] The embodiments of the present application also provide a vehicle-road-cloud cooperative system, which comprises a vehicle end, a cloud end and a road end, the vehicle end is configured to execute any of the methods described above, the cloud end is configured to receive the positioning state information of the road section reported by the vehicle end and send the positioning state information to the corresponding road end, and the road end is configured to receive the positioning state information of the road section sent by the cloud end and monitor the positioning state information.

[0085] As shown in Figure 3 The vehicle-road-cloud cooperative system of the embodiments of the present application mainly comprises a vehicle end, a cloud end and a road end. Based on the communication among the vehicle, the road and the cloud, the vehicle end can realize any of the methods described in the foregoing embodiments. The cloud end is mainly configured to receive the positioning state information of the road section reported by each vehicle end and send the positioning state information to the road end device corresponding to the road section, and can also synchronize the positioning state information to other vehicle ends, so that each vehicle end can refer to the positioning state information of each road section to plan a path.

[0086] After receiving the positioning state information of the corresponding road section sent by the cloud end, the road end can further confirm and monitor the positioning state information. When the road end monitors that the positioning state of the road section has been restored, the road end can synchronize the monitoring result to the cloud end, and the cloud end can synchronize the information to all operating vehicles, so that the operating vehicles can restore the path cost of the road section to normal in real-time navigation path planning.

[0087] The confirmation and monitoring strategy adopted by the road end can be to confirm or monitor the positioning state of the road section according to the stability of the GNSS / RTK positioning signal of the road section and the situation affecting the laser positioning precision of the road section, such as temporary long-distance fencing, large vehicles parked on both sides, etc.

[0088] Of course, specific influencing factors can be added to the list of road conditions affecting the laser radar positioning according to actual conditions. This list can be established according to requirements. The roadside camera can determine whether the current laser radar positioning is affected according to the recognition situation, or determine whether the current laser radar positioning is affected according to the similarity algorithm to calculate the similarity between the current image and the image under normal road conditions. The higher the similarity, the lower the influence, and vice versa.

[0089] In summary, the vehicle-road-cloud cooperative system of the present application at least achieves the following technical effects:

[0090] 1) Using a combination of multiple positioning information, accurately determine whether one or more positioning results are disturbed for a long time, such as satellite signal interference under a viaduct;

[0091] 2) Using a combination of vehicle-road-cloud, real-time discovery of road conditions on the positioning disturbed section, so that the autonomous vehicle can avoid in advance, real-time monitoring of the road conditions on the positioning disturbed section, which can eliminate the avoidance after the road conditions recover, and ensure the smoothness of the overall operation of the autonomous vehicle;

[0092] 3) The vehicle end uses interference grading to adjust the cost of the positioning disturbed section, so that the vehicle can select the optimal route when planning the real-time navigation path.

[0093] Figure 4 is a structural schematic diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 4 At the hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The memory can include a memory such as a random-access memory (RAM), and can also include a non-volatile memory such as at least one disk memory. Of course, the electronic device can also include other hardware required by the business.

[0094] The processor, network interface, and memory can be connected to each other through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, and a control bus. For ease of representation, Figure 4 Only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0095] The memory is used to store programs. Specifically, the program can include program code, and the program code includes computer operation instructions. The memory can include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0096] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs, and forms a navigation device of the autonomous vehicle at the logical level. The processor executes the program stored in the memory, and is specifically used to perform the following operations:

[0097] Acquire the fused positioning data of the first autonomous vehicle on the current road segment, wherein the fused positioning data includes satellite positioning data, lidar positioning data and visual positioning data;

[0098] The positioning status of the current road segment is determined based on the fused positioning data;

[0099] Determine whether the current road segment has triggered the preset reporting conditions based on the current road segment's location status;

[0100] When the preset reporting conditions are triggered on the current road segment, the location status information of the current road segment is determined and reported to the cloud, so that the cloud sends the location status information of the current road segment to the second autonomous vehicle and enables the second autonomous vehicle to navigate according to the location status information of the current road segment.

[0101] The above is as stated in this application. Figure 1 The method executed by the navigation device of the autonomous vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0102] The electronic device can also perform Figure 1The method is executed by a navigation device of an autonomous vehicle, and the navigation device of the autonomous vehicle is enabled to perform the functions of the embodiment shown in Figure 1 The functions of the embodiment shown in the method executed by the navigation device of the autonomous vehicle are not repeated here.

[0103] The embodiment of the present application also provides a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which, when executed by an electronic device comprising a plurality of application programs, enable the electronic device to perform the method Figure 1 The method is executed by a navigation device of an autonomous vehicle, and the navigation device of the autonomous vehicle is enabled to perform the functions of the embodiment shown in

[0104] Obtaining fusion positioning data of the first autonomous vehicle on a current road section, the fusion positioning data comprising satellite positioning data, laser radar positioning data and visual positioning data;

[0105] Determining a positioning state of the current road section according to the fusion positioning data;

[0106] Determining whether the current road section triggers a preset reporting condition according to the positioning state of the current road section;

[0107] In the case that the current road section triggers the preset reporting condition, determining positioning state information of the current road section and reporting to the cloud end, so that the cloud end sends the positioning state information of the current road section to a second autonomous vehicle and enables the second autonomous vehicle to perform navigation according to the positioning state information of the current road section.

[0108] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0109] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device for implementing the functions described in the flowcharts and / or block diagrams. Figure 1 The flow or the combination of the flows and / or blocks Figure 1an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0110] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks. Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks. ​ an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0112] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0113] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or a combination of non-volatile memories. The memory is an example of computer-readable media.

[0114] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information. The information can be computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0115] It is also to be noted that the terms "comprising", "including", and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0116] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code.

[0117] The embodiments of the present application described above are only used to explain the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail, those skilled in the art will understand that the present application can make various modifications and changes without departing from the spirit and scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method of navigation of an autonomous vehicle, wherein, The method comprises: acquiring fusion positioning data of a first autonomous vehicle on a current road section, the fusion positioning data comprising satellite positioning data, laser radar positioning data and visual positioning data; determining a positioning state of the current road section according to the fusion positioning data; determining whether the current road section triggers a preset reporting condition according to the positioning state of the current road section; in the case that the current road section triggers the preset reporting condition, determining positioning state information of the current road section and reporting to the cloud end, so that the cloud end sends the positioning state information of the current road section to a second autonomous vehicle and makes the second autonomous vehicle navigate according to the positioning state information of the current road section.

2. The method of claim 1, wherein, The determination of the positioning state of the current road section according to the fusion positioning data comprises: determining a positioning error between the satellite positioning data and the laser radar positioning data according to the satellite positioning data and the laser radar positioning data, and determining a visual lateral correction error according to the visual positioning data; determining the positioning state of the current road section according to the positioning error between the satellite positioning data and the laser radar positioning data and the visual lateral correction error.

3. The method of claim 2, wherein, The determination of the positioning state of the current road section according to the positioning error between the satellite positioning data and the laser radar positioning data and the visual lateral correction error comprises: comparing the positioning error between the satellite positioning data and the laser radar positioning data with a first preset error threshold, and comparing the visual lateral correction error with a second preset error threshold; if the positioning error between the satellite positioning data and the laser radar positioning data is greater than the first preset error threshold, and the visual lateral correction error is greater than the second preset error threshold, determining that the positioning state of the current road section is an abnormal positioning state; otherwise, determining that the positioning state of the current road section is a normal positioning state.

4. The method of claim 1, wherein, The determination of whether the current road section triggers the preset reporting condition according to the positioning state of the current road section comprises: if the positioning state of the current road section is an abnormal positioning state, determining that the current road section triggers the preset reporting condition; otherwise, determining that the current road section does not trigger the preset reporting condition.

5. The method of claim 1, wherein, The positioning state information of the current road section comprises a type of abnormal positioning state, and the determination of the positioning state information of the current road section and the reporting to the cloud end in the case that the current road section triggers the preset reporting condition comprises: determining a lateral distance in the satellite positioning data according to the satellite positioning data, and determining a lateral distance in the laser radar positioning data according to the laser radar positioning data; comparing the lateral distance in the satellite positioning data and the lateral distance in the laser radar positioning data with the visual positioning data respectively; determining the type of the abnormal positioning state according to the comparison result, the type of the abnormal positioning state comprising a satellite positioning interference state and a laser radar positioning interference state.

6. The method of claim 1, wherein, The method further comprises: acquiring positioning state information of a plurality of road sections sent by the cloud end; The path cost of each road segment is adjusted according to the positioning state information of each road segment, and an adjusted path cost of each road segment is obtained; Navigation is performed according to the adjusted path cost of each road segment, and a navigation result of the first autonomous vehicle is obtained.

7. A navigation device for an autonomous vehicle, wherein, The device comprises: A first acquisition unit configured to acquire fusion positioning data of the first autonomous vehicle on a current road segment, the fusion positioning data comprising satellite positioning data, laser radar positioning data and visual positioning data; A first determination unit configured to determine a positioning state of the current road segment according to the fusion positioning data; A second determination unit configured to determine whether the current road segment triggers a preset reporting condition according to the positioning state of the current road segment; A reporting unit configured to determine the positioning state information of the current road segment and report it to the cloud end in the case that the current road segment triggers the preset reporting condition, so that the cloud end sends the positioning state information of the current road segment to a second autonomous vehicle and makes the second autonomous vehicle perform navigation according to the positioning state information of the current road segment. 8.A vehicle-road-cloud cooperative system, the system comprising: A vehicle end, a cloud end and a road end, the vehicle end is configured to perform the method of any one of claims 1-6, the cloud end is configured to receive the positioning state information of the road segment reported by the vehicle end and send it to the corresponding road end, and the road end is configured to receive the positioning state information of the road segment sent by the cloud end and perform monitoring. 9.An electronic device comprising: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-7. 10.A computer readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including multiple applications, cause the electronic device to perform the method of any one of claims 1-7.

Images