Unmanned aerial vehicle dynamic triggering control method and system for unmanned flow vehicle

Abstract

The application provides an unmanned aerial vehicle dynamic triggering control method and system for unmanned flow vehicles, and relates to the technical field of automatic driving.The method comprises the following steps: a data processing module acquires and monitors the visual confidence of the unmanned flow vehicle in real time, and acquires the safety boundary contraction rate and the high dynamic range image overexposure index of the unmanned flow vehicle at the current time when it is monitored that the visual confidence is below the preset visual confidence threshold for a continuous preset time length; whether the current condition meets the preset unmanned aerial vehicle starting condition is judged according to the visual confidence, the safety boundary contraction rate and the high dynamic range image overexposure index; if yes, the data processing module starts the unmanned aerial vehicle arranged in the unmanned aerial vehicle module through the unmanned aerial vehicle module of the unmanned flow vehicle, and activates the communication link between the unmanned aerial vehicle and the unmanned flow vehicle through the communication module of the unmanned flow vehicle.The application can reduce the energy consumption of the unmanned aerial vehicle, and at the same time, the running safety of the unmanned flow vehicle in the long tail scene is taken into account.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and specifically to a method and system for dynamic triggering control of unmanned aerial vehicles for unmanned logistics vehicles. Background Technology

[0002] Currently, unmanned logistics vehicles based on pure vision solutions experience a significant decrease in visual confidence when encountering long-tail scenarios such as strong light, severe weather, and severe obstruction (the actual measurement shows a decrease of over 40%), and visual confidence is one of the important factors affecting the operational safety of unmanned logistics vehicles.

[0003] To compensate for this deficiency, existing technologies employ drones for continuous escort. Drones have a wide field of view, and the image data they collect can provide supplementary perception for purely visual unmanned logistics vehicles. However, because drones are used for continuous escort, this approach suffers from high energy consumption.

[0004] Therefore, how to reduce the energy consumption of drones while ensuring the safe operation of unmanned logistics vehicles in long-tail scenarios has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, in order to solve the above-mentioned technical problems, the present invention provides a method and system for dynamic triggering control of unmanned aerial vehicles for unmanned logistics vehicles.

[0006] The present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for dynamic triggering control of unmanned aerial vehicles for unmanned logistics vehicles, comprising:

[0008] The data processing module acquires and monitors the visual confidence level of the unmanned logistics vehicle in real time;

[0009] When the data processing module detects that the visual confidence level is continuously lower than the preset visual confidence threshold for a preset duration, the data processing module obtains the safety boundary contraction rate and high dynamic range image overexposure index of the unmanned logistics vehicle at the current moment.

[0010] The data processing module determines whether the current conditions meet the preset drone start-up conditions based on the visual confidence level, the safety boundary shrinkage rate, and the high dynamic range image overexposure index, and obtains the judgment result.

[0011] If the judgment result is yes, the data processing module starts the drone deployed in the drone module through the drone module of the unmanned logistics vehicle, and activates the communication link between the drone and the unmanned logistics vehicle through the communication module of the unmanned logistics vehicle.

[0012] Optionally, based on the visual confidence level, the safety boundary shrinkage rate, and the high dynamic range image overexposure index, it is determined whether the current conditions meet the preset drone launch conditions, specifically including:

[0013] Determine whether the shrinkage rate of the safety boundary is greater than a preset shrinkage rate threshold;

[0014] If the safety boundary shrinkage rate is greater than a preset shrinkage rate threshold, then determine whether the high dynamic range image overexposure index is greater than a preset index threshold.

[0015] If the overexposure index of the high dynamic range image is greater than the preset index threshold, a comprehensive risk index is calculated based on the visual confidence level, the safety boundary shrinkage rate, and the overexposure index of the high dynamic range image.

[0016] Determine whether the comprehensive risk index is greater than a preset threshold.

[0017] If the comprehensive risk index is greater than the preset index threshold, then the current conditions are determined to meet the preset drone launch conditions.

[0018] Optionally, the formula for calculating the comprehensive risk index is as follows:

[0019]

[0020] in, The aforementioned comprehensive risk indicator; , , These are the weighting coefficients; The visual confidence level; The shrinkage rate of the safety boundary; The overexposure index of the high dynamic range image.

[0021] Optionally, the drone module includes: a catapult control unit and a drone storage compartment;

[0022] The data processing module activates the drone deployed within the drone module of the unmanned logistics vehicle, specifically including:

[0023] The data processing module sends an ejection command to the ejection control unit;

[0024] The ejection control unit responds to the ejection command and controls the UAV to be ejected from the UAV storage compartment and launched into the air.

[0025] Optionally, the communication link includes a millimeter-wave communication link and a cellular network communication link.

[0026] Optionally, the cellular network communication link is the default communication link;

[0027] The data processing module is also used for:

[0028] When the detected electromagnetic interference intensity is greater than the preset interference intensity threshold, the communication link is switched to the millimeter-wave communication link.

[0029] Secondly, the present invention also provides a drone dynamic triggering control system for unmanned logistics vehicles, comprising: a data processing module, a drone module, and a communication module;

[0030] The data processing module, the drone module, and the communication module are used to execute the drone dynamic triggering control method for unmanned logistics vehicles as described above.

[0031] Optionally, the drone module includes: a catapult control unit and a drone storage compartment.

[0032] Optionally, the drone storage compartment includes: a compartment body, a canopy, a wireless charging device, and an ejection mechanism;

[0033] The wireless charging device and the ejection mechanism are located in the space enclosed by the cabin and the canopy;

[0034] The wireless charging device is used to charge the drone.

[0035] The ejection mechanism is used to control the drone to be ejected from the drone storage compartment when the drone is started.

[0036] This invention employs the above technical solutions. By considering three indicators closely related to long-tail scenarios—visual confidence of the unmanned logistics vehicle, safety boundary contraction rate, and high dynamic range image overexposure index—when determining whether the current conditions meet the preset drone launch conditions, this invention can improve the coverage of long-tail scenarios, thereby ensuring the operational safety of the unmanned logistics vehicle in long-tail scenarios to a certain extent. Furthermore, by only launching the drone when it is determined that the current conditions meet the preset drone launch conditions, the invention utilizes the perception data acquired by the drone to assist the unmanned logistics vehicle in making driving decisions, thereby reducing the drone's energy consumption. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1This is a schematic diagram of the structure of a drone dynamic triggering control system for unmanned logistics vehicles provided in an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram of the structure of a drone storage compartment provided in an embodiment of the present invention;

[0040] Figure 3 This is a flowchart illustrating a method for dynamic triggering control of unmanned aerial vehicles for unmanned logistics vehicles, provided by an embodiment of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0042] To make this plan easier to understand, the following explanations are provided for some technical terms that may be involved:

[0043] Visual confidence score: Used to quantify the degree of certainty with which an onboard perception system detects and identifies objects (such as vehicles, pedestrians, lane lines, etc.). The visual confidence score ranges from 0 to 1. Under normal lighting conditions, the visual confidence score is typically stable above 0.95.

[0044] Safety boundary contraction rate: The safety boundary refers to the area that a vehicle plans for safe driving within the next few seconds based on its current environmental perception and motion state. When the perception system's performance deteriorates and it cannot accurately identify obstacles in the distance or to the side, the vehicle will adopt a conservative strategy for safety reasons, causing the planned safety boundary to contract rapidly. The rate of this contraction is called the safety boundary contraction rate. The safety boundary contraction rate is measured as a percentage of the area contracted per second. For example, when an unidentifiable area suddenly appears in front of the vehicle, the safety boundary may contract rapidly inward at a rate of 14.3% per second.

[0045] High Dynamic Range (HDR) Image Overexposure Index: To cope with scenes of drastic lighting changes, automotive cameras typically use High Dynamic Range (HDR) imaging mode. However, even in this mode, instantaneous extremely high illumination (such as an ambient light level jumping from 50 lux inside a tunnel to 100,000 lux at the exit) can still cause a large number of pixels on the image sensor to reach saturation (i.e., the pixel value reaches its maximum value, such as 255). The HDR image overexposure index is the percentage of saturated pixels in the image. A high overexposure index (e.g., exceeding 30%) directly indicates that the information acquired by the visual sensor has been severely distorted.

[0046] Figure 1 This is a schematic diagram of a drone dynamic triggering control system for unmanned logistics vehicles provided in an embodiment of the present invention. This drone dynamic triggering control system for unmanned logistics vehicles is integrated onto the unmanned logistics vehicle. Figure 1 As shown, this system includes: a data processing module 11, a drone module 12, a communication module 13, and a vehicle-mounted vision module 14.

[0047] The data processing module 11, the drone module 12, the communication module 13, and the vehicle vision module 14 work together to implement the drone dynamic triggering control method for unmanned logistics vehicles provided by the present invention.

[0048] The vehicle-mounted vision module 14 can consist of eight industrial-grade cameras deployed around the perimeter of the unmanned logistics vehicle, such as two front-view cameras (one wide-angle and one telephoto), two rear-view cameras, and two side-view cameras on each of the left and right sides of the vehicle. These cameras can provide a 360-degree field of view around the vehicle and continuously acquire high-definition image data at a high frame rate (e.g., 30 frames per second). The image data stream acquired by the vehicle-mounted vision module 14 is transmitted to the data processing module 11 in real time.

[0049] The data processing module 11 is the core of the system's decision-making process. In terms of hardware implementation, the functions of the data processing module 11 can be realized by the onboard computing platform of the unmanned logistics vehicle.

[0050] The drone module 12 includes a catapult control unit 121 and a drone storage compartment 122.

[0051] Figure 2 This is a structural schematic diagram of a drone storage compartment provided in an embodiment of the present invention. Figure 2 As shown, the drone storage compartment 122 includes: a compartment body 21, a cover 22, a wireless charging device 23, and an ejection mechanism 24.

[0052] The wireless charging device 23 and the ejection mechanism 24 are located in the space enclosed by the cabin 21 and the hatch 22.

[0053] The hatch 22 can be made of carbon fiber, which allows the hatch 22 to achieve an IP67 protection rating.

[0054] The wireless charging device 23 is used to charge the drone. The charging voltage can be 48V DC, enabling rapid charging of the drone (10% charge in 90 seconds). During the charging process, the drone contacts the wireless charging point, and the wireless charging device 23 draws power from the power source of the unmanned logistics vehicle to charge the drone.

[0055] The ejection mechanism 24 can specifically be a spring ejection mechanism, used to control the drone to be ejected from the drone storage compartment and taken into the air when the drone is started. The ejection stroke can be 0.5m.

[0056] The ejection control unit 121 is equipped with an electromagnetic lock release mechanism, which responds to the control commands of the data processing module 11 and controls the working state of the ejection mechanism 24 to eject the drone from the drone storage compartment 122 into the air.

[0057] It should be noted that the above-mentioned structures (such as data processing module 11, communication module 13, vehicle vision module 14, ejection control unit 121, wireless charging device 23 and ejection mechanism 24) are all existing technologies, so their specific structural composition will not be described in detail here.

[0058] When the drone is inside the cabin 21, its folding rotor is in a folded state. After the drone is started, its folding rotor can unfold within 1.2 seconds. This helps to improve the response speed of the drone in this application.

[0059] Figure 3 This is a flowchart illustrating a dynamic triggering control method for unmanned logistics vehicles provided in an embodiment of the present invention. Figure 3 As shown, this process includes:

[0060] Step 301: The data processing module acquires and monitors the visual confidence level of the unmanned logistics vehicle in real time.

[0061] Step 302: When the data processing module detects that the visual confidence level is continuously lower than the preset visual confidence level threshold for a preset duration, the data processing module obtains the safety boundary contraction rate and high dynamic range image overexposure index of the unmanned logistics vehicle at the current moment.

[0062] The preset duration can be 3 seconds, and the preset visual confidence threshold can be 0.85. For example, when a vehicle exits a tunnel, the camera is instantly exposed to strong light, causing severe overexposure of the image. This results in the visual confidence score remaining below 0.85 for 3.2 seconds. In this case, it is determined that the visual confidence score remains below the preset visual confidence threshold for a continuous preset duration.

[0063] It should be noted that the data processing module calculates visual confidence, safety boundary shrinkage rate, and high dynamic range image overexposure index based on the image data stream acquired by the vehicle vision module. The calculation methods for these three indicators are existing technologies, so they will not be elaborated here.

[0064] Understandably, if the data processing module does not detect a situation where the visual confidence level is continuously lower than the preset visual confidence level threshold for a preset duration, the unmanned logistics vehicle will maintain a pure vision mode.

[0065] Step 303: The data processing module determines whether the current conditions meet the preset drone startup conditions based on visual confidence level, safety boundary shrinkage rate, and high dynamic range image overexposure index, and obtains the judgment result. If the judgment result is yes, then proceed to step 304.

[0066] In addition, if the judgment result is yes, preset alarm actions can also be executed, such as sending alarm prompts to preset terminals, so that staff can be informed in a timely manner that there is an operational risk to the unmanned logistics vehicle and that it is necessary to activate drones to assist the unmanned logistics vehicle in making driving decisions.

[0067] Step 304: The data processing module starts the drone deployed within the drone module of the unmanned logistics vehicle and activates the communication link between the drone and the unmanned logistics vehicle through the vehicle's communication module. The drone sends its generated image data to the data processing module through this communication link. The image data generated by the drone can specifically be a halo-free bird's-eye view.

[0068] Furthermore, to reduce hardware costs, drones can reuse the onboard RTK (Real-Time Kinematic) positioning module of unmanned logistics vehicles and share base stations with them. Specifically, the drone can connect to the onboard RTK positioning module of the unmanned logistics vehicle via the aforementioned communication link.

[0069] This invention employs the above technical solutions. By considering three indicators closely related to long-tail scenarios—visual confidence of the unmanned logistics vehicle, safety boundary contraction rate, and high dynamic range image overexposure index—when determining whether the current conditions meet the preset drone launch conditions, this invention can improve the coverage of long-tail scenarios, thereby ensuring the operational safety of the unmanned logistics vehicle in long-tail scenarios to a certain extent. Furthermore, by only launching the drone when it is determined that the current conditions meet the preset drone launch conditions, the invention utilizes the perception data acquired by the drone to assist the unmanned logistics vehicle in making driving decisions, thereby reducing the drone's energy consumption.

[0070] In this embodiment of the invention, determining whether the current conditions meet the preset drone launch conditions based on visual confidence level, safety boundary shrinkage rate, and high dynamic range image overexposure index may specifically include:

[0071] (1) Determine whether the safety boundary shrinkage rate is greater than the preset shrinkage rate threshold.

[0072] The preset shrinkage rate threshold can be equal to 10% / S.

[0073] (2) If the safety boundary shrinkage rate is greater than the preset shrinkage rate threshold, then determine whether the overexposure index of the high dynamic range image is greater than the preset index threshold.

[0074] The preset index threshold can be equal to 120 dB.

[0075] Understandably, if the safety boundary contraction rate is not greater than the preset contraction rate threshold, the unmanned logistics vehicle will maintain a pure vision mode.

[0076] (3) If the overexposure index of the high dynamic range image is greater than the preset index threshold, the comprehensive risk index is calculated based on the visual confidence level, the safety boundary shrinkage rate and the overexposure index of the high dynamic range image.

[0077] The value of the comprehensive risk index can reflect the magnitude of the vehicle operation risk; the higher the value, the greater the risk.

[0078] (4) Determine whether the comprehensive risk index is greater than the preset index threshold.

[0079] The preset threshold value can be 0.75.

[0080] (5) If the comprehensive risk index is greater than the preset index threshold, then the current conditions are determined to meet the preset drone start-up conditions.

[0081] In this embodiment of the invention, the formula for calculating the comprehensive risk index is as follows:

[0082]

[0083] in, As a comprehensive risk indicator; , , These are the weighting coefficients; Visual confidence level; The safety margin contraction rate; The overexposure index for high dynamic range images.

[0084] Considering that visual confidence determines the reliability of risk assessment, safety boundary contraction reflects whether a risk has occurred, and high dynamic range (HDR) image overexposure index reflects local conditions, visual confidence is given the highest weight, followed by safety boundary contraction, and then HDR image overexposure index. This improves the overall reliability of the comprehensive risk index. In a specific example... The value can be 0.6. The value can be 0.3. The value can be 0.1.

[0085] In this embodiment of the invention, the drone module includes: a catapult control unit and a drone storage compartment.

[0086] The data processing module activates the drones deployed within the drone module of the unmanned logistics vehicle, which may specifically include:

[0087] (1) The data processing module sends the ejection command to the ejection control unit.

[0088] (2) The ejection control unit responds to the ejection command and controls the UAV to be ejected from the UAV storage compartment and take off.

[0089] Launching drones into the air via catapults can improve their response speed.

[0090] In this embodiment of the invention, the communication link includes a millimeter-wave communication link and a cellular network communication link.

[0091] Specifically, the millimeter-wave communication link can operate at a frequency of 60 GHz. Thus, when electromagnetic interference intensity is greater than 30 dBm, a 60 GHz millimeter-wave link can ensure a latency of less than 5 ms, achieving high-speed and stable data transmission and meeting the stringent real-time requirements of unmanned logistics vehicles.

[0092] In this embodiment of the invention, the cellular network communication link is the default communication link.

[0093] The data processing module can also be used for:

[0094] When the detected electromagnetic interference intensity exceeds the preset interference intensity threshold, the communication link will be switched to a millimeter-wave communication link.

[0095] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0096] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0097] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0098] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0099] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0100] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0101] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0102] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0103] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for dynamic triggering control of unmanned aerial vehicles (UAVs) for unmanned logistics vehicles, characterized in that, include: The data processing module acquires and monitors the visual confidence level of the unmanned logistics vehicle in real time; When the data processing module detects that the visual confidence level is continuously lower than the preset visual confidence threshold for a preset duration, the data processing module obtains the safety boundary contraction rate and high dynamic range image overexposure index of the unmanned logistics vehicle at the current moment. The data processing module determines whether the current conditions meet the preset drone start-up conditions based on the visual confidence level, the safety boundary shrinkage rate, and the high dynamic range image overexposure index, and obtains the judgment result. Based on the visual confidence level, the safety boundary contraction rate, and the high dynamic range image overexposure index, it is determined whether the current conditions meet the preset drone launch conditions. Specifically, this includes: determining whether the safety boundary contraction rate is greater than a preset contraction rate threshold; if the safety boundary contraction rate is greater than the preset contraction rate threshold, then determining whether the high dynamic range image overexposure index is greater than a preset index threshold; if the high dynamic range image overexposure index is greater than the preset index threshold, then calculating a comprehensive risk index based on the visual confidence level, the safety boundary contraction rate, and the high dynamic range image overexposure index; determining whether the comprehensive risk index is greater than a preset index threshold; if the comprehensive risk index is greater than the preset index threshold, then determining that the current conditions meet the preset drone launch conditions. If the judgment result is yes, the data processing module starts the drone deployed in the drone module through the drone module of the unmanned logistics vehicle, and activates the communication link between the drone and the unmanned logistics vehicle through the communication module of the unmanned logistics vehicle.

2. The UAV dynamic triggering control method for unmanned logistics vehicles according to claim 1, characterized in that, The formula for calculating the comprehensive risk index is as follows: in, The aforementioned comprehensive risk indicator; , , These are the weighting coefficients; The visual confidence level; The shrinkage rate of the safety boundary; The overexposure index of the high dynamic range image.

3. The UAV dynamic triggering control method for unmanned logistics vehicles according to claim 1, characterized in that, The drone module includes: a catapult control unit and a drone storage compartment; The data processing module activates the drone deployed within the drone module of the unmanned logistics vehicle, specifically including: The data processing module sends an ejection command to the ejection control unit; The ejection control unit responds to the ejection command and controls the UAV to be ejected from the UAV storage compartment and launched into the air.

4. The UAV dynamic triggering control method for unmanned logistics vehicles according to claim 1, characterized in that, The communication links include millimeter-wave communication links and cellular network communication links.

5. The UAV dynamic triggering control method for unmanned logistics vehicles according to claim 4, characterized in that, The cellular network communication link is the default communication link; The data processing module is also used for: When the detected electromagnetic interference intensity is greater than the preset interference intensity threshold, the communication link is switched to the millimeter-wave communication link.

6. A dynamic triggering control system for unmanned logistics vehicles, characterized in that, include: Data processing module, drone module, and communication module; The data processing module, the drone module, and the communication module are used to execute the drone dynamic triggering control method for unmanned logistics vehicles as described in any one of claims 1 to 5.

7. The UAV dynamic triggering control system for unmanned logistics vehicles according to claim 6, characterized in that, The drone module includes: a catapult control unit and a drone storage compartment.

8. The UAV dynamic triggering control system for unmanned logistics vehicles according to claim 7, characterized in that, The drone storage compartment includes: a compartment body, a canopy, a wireless charging device, and an ejection mechanism; The wireless charging device and the ejection mechanism are located in the space enclosed by the cabin and the canopy; The wireless charging device is used to charge the drone. The ejection mechanism is used to control the drone to be ejected from the drone storage compartment when the drone is started.

Images