Method, apparatus, device and storage medium for estimating the deployment quantity of unmanned delivery vehicles on road segments

Abstract

An embodiment of the present invention discloses a method and device for estimating the deployment quantity of unmanned delivery vehicles on road sections. The method includes: First, obtain the driving state information and vehicle information of the unmanned delivery vehicle, and perform parameter calibration on the unmanned delivery vehicle; Second, based on the parameter calibration of the unmanned delivery vehicle, construct a model of the unmanned delivery vehicle and other vehicles, and combine the road design specifications to model the basic urban road sections under different traffic environments; Then, through simulation technology, conduct simulation and evaluation of the impact of the deployment of unmanned delivery vehicles, and determine the deployment quantity model of unmanned delivery vehicles on the basic urban road sections through the deployment quantity; Finally, combine the deployment model of the unmanned delivery vehicle to form an estimation device for the deployment of unmanned delivery vehicles on road sections. This device can realize the output of the estimated value of the deployment quantity of unmanned delivery vehicles on the basic urban road sections by inputting the basic information of the unmanned delivery vehicle and the geometric structure of the urban road sections.

Description

Technical Field

[0001] The present invention belongs to the field of traffic control, and more specifically, relates to a method, device, equipment and storage medium for estimating the deployment quantity of unmanned delivery vehicles on roads. Background Art

[0002] With the continuous development of the e-commerce industry and the express delivery industry, problems such as a single transportation mode, a sharp increase in transportation costs, and low transportation efficiency have gradually become more serious. The last-mile delivery has long been the most costly and polluting link in the entire logistics distribution process. Especially during special shopping festivals, the influx of a large number of express orders has sharply increased the pressure on logistics distribution. With the success of the on-road experiment of unmanned driving technology, the proposal of unmanned delivery technology provides a new solution to alleviate the problems of human resource waste and low efficiency in the last-mile logistics distribution process.

[0003] However, with the continuous increase in the number of unmanned delivery vehicles, the impact of unmanned delivery vehicles on urban traffic operation will also continue to increase. Therefore, to promote the coordinated development of the urban unmanned logistics industry and traffic order and ensure the safe and efficient operation of the unmanned logistics industry, it is necessary to further strengthen the research on the impact of the deployment quantity of unmanned delivery vehicles. As a new type of vehicle, the current patent applications for unmanned delivery vehicles mainly focus on the research and development of the whole vehicle, while there is still a blank in the method for estimating the deployment quantity of unmanned delivery vehicles based on the impact of the deployment of unmanned delivery vehicles on traffic operation, which cannot meet the current management requirements for the deployment and operation of unmanned delivery vehicles and is not conducive to the standardized management of unmanned delivery vehicles. Therefore, the method and device for estimating the deployment quantity of unmanned delivery vehicles on roads proposed by the present invention are of practical significance. Summary of the Invention

[0004] In view of at least one of the above problems, an embodiment of the present invention provides a method and device for estimating the deployment quantity of unmanned delivery vehicles on roads to solve the problem that there is no standardized deployment rule for current unmanned delivery vehicles. In view of the impact of the deployment of unmanned delivery vehicles on road traffic and combined with simulation technology, a method and device for estimating the deployment quantity of unmanned delivery vehicles on roads are provided.

[0005] In a first aspect, an embodiment of the present invention provides a method for estimating the deployment quantity of unmanned delivery vehicles on roads, the method including: obtaining the vehicle driving information, vehicle information, and road information of unmanned delivery vehicles; according to the obtained delivery vehicle information and road information, performing parameter calibration and model construction of the unmanned delivery vehicle model and the road model, setting an acceptable determination threshold for the impact of unmanned delivery vehicle deployment by evaluating the impact of unmanned delivery vehicle deployment on road traffic, calculating the recommended value of the deployment quantity of unmanned delivery vehicles under different road conditions based on the simulation density of unmanned delivery vehicles, and determining a fitting curve for the deployment of multiple types of urban roads with the same unmanned delivery vehicle based on the deployment quantity of unmanned delivery vehicles.

[0006] A method for estimating the deployment quantity of driverless delivery vehicles on road sections includes: obtaining the driving state information and vehicle information of driverless delivery vehicles as the target objects, and at the same time obtaining the actual situation of the urban road network to construct a target driverless delivery vehicle model, other vehicle models, and a target urban basic road section model; according to the target driverless delivery vehicle model and the road model, using simulation testing means to determine the deployment quantity of driverless delivery vehicles under the conditions of the target delivery vehicle and the target road section based on the evaluation of the impact of driverless delivery vehicle deployment, and outputting and feeding back the recommended value of driverless delivery vehicle deployment to the management personnel.

[0007] Preferably, the obtained driving state information and vehicle information of driverless delivery vehicles include at least one of the following: the length, height, width, front axle position, wheelbase, and rear axle position of driverless delivery vehicles; at least one of the running speed, expected acceleration, expected deceleration, following model, lateral spacing, and driving rules of driverless delivery vehicles.

[0008] Preferably, the obtained urban road information includes at least one of the following: the actual length of urban roads, the actual road width, the actual number of lanes, the length of urban roads in the planning stage, the road width in the planning stage, and the number of lanes in the planning stage; the traffic capacity data of urban roads and / or the traffic flow composition of urban roads.

[0009] Preferably, the construction of the urban road section driverless delivery vehicle operation simulation model includes the following steps: constructing a driverless delivery vehicle model based on the driving state information and vehicle information of driverless delivery vehicles; constructing motor vehicle and non-motor vehicle models; constructing a target urban basic road model and traffic flow conditions based on urban road information.

[0010] Preferably, the driverless delivery vehicle deployment evaluation method includes the following steps: relying on the driverless delivery vehicle and other vehicle models, road models, and road traffic flow to conduct simulation experiments under different driverless delivery vehicle deployment quantity conditions; based on the driverless delivery vehicle deployment experiments under different simulation traffic flows, testing the impact of driverless delivery vehicle deployment on the running speed of other road traffic, and setting an acceptable threshold for the impact; calculating the number of delivery vehicles that can be carried by driverless delivery vehicles under different road lengths based on the instantaneous density of the driverless delivery vehicle simulation experiment operation; constructing a deployment fitting curve of driverless delivery vehicles based on road length based on different road condition simulation experiments, and establishing a basic road section deployment model for driverless delivery vehicles.

[0011] Preferably, the management personnel can determine the deployment value of the driverless delivery vehicle according to their own management needs; the simulation results of the driverless delivery vehicle under the condition of the same driverless delivery vehicle model will be fitted, so as to obtain the deployment curve of the driverless delivery vehicle in the same environment, which is convenient for quickly outputting the deployment quantity of the driverless delivery vehicle under different road conditions; when the constructed driverless delivery vehicle model and road environment are consistent with the stored historical driverless delivery vehicle simulation background, the simulation module can be not triggered and the historical fitting curve can be directly relied on for output.

[0012] In a second aspect, an embodiment of the present invention provides a device for estimating the deployment quantity of a driverless delivery vehicle on a road section, the device includes: a parameter setting module, configured to input geometric parameter information of the driverless delivery vehicle, driving state information, road traffic parameters, and a traffic impact judgment threshold; a driverless delivery vehicle operation simulation module, configured to construct a model with the parameters in the parameter setting module, and combine general motor vehicle and non-motor vehicle models to conduct driverless delivery vehicle simulation experiments under different road conditions and different driverless delivery vehicle models, and output simulation results; a fitting module for estimating the deployment quantity of the driverless delivery vehicle, configured to calibrate the impact of the driverless delivery vehicle deployment by using the traffic impact judgment threshold, determine the deployment quantity of the driverless delivery vehicle, and fit the deployment curve; a module for issuing suggestions on the deployment of the driverless delivery vehicle, configured to output the simulation results of the driverless delivery vehicle and provide the traffic management personnel with the deployment quantity of the driverless delivery vehicle on the current road.

[0013] Preferably, a device for estimating the deployment quantity of a driverless delivery vehicle on a road section includes:

[0014] A parameter setting module, which includes three functions: vehicle model parameter setting, road traffic parameter setting, and traffic impact threshold setting; the vehicle model parameter setting function is used to input geometric parameter information of the driverless delivery vehicle and driving state information of the driverless delivery vehicle; the road traffic parameter setting function is used to input the width, length, number of lanes of the motor vehicle lane, and the length, width, and isolation method of the non-motor vehicle lane, as well as traffic flow and traffic flow composition; the traffic impact threshold setting function is used to determine the acceptable degree of the impact of the driverless delivery vehicle deployment on traffic, as a judgment condition for estimating the deployment quantity of the driverless delivery vehicle;

[0015] A driverless delivery vehicle operation simulation module, configured to construct a model with the parameters in the parameter setting module, combine motor vehicle and non-motor vehicle models, conduct driverless delivery vehicle simulation experiments under different road conditions and different driverless delivery vehicle models, and output at least one of the motor vehicle operation state data, non-motor vehicle operation state data, and driverless delivery vehicle state data obtained from the simulation experiments;

[0016] The unmanned delivery vehicle deployment fitting module is used to calibrate the impact of unmanned delivery vehicle deployment by using the traffic impact threshold, determine the number of unmanned delivery vehicles under different road conditions within the acceptable range of the impact of unmanned delivery vehicle deployment, and perform a deployment curve fitting on the number of unmanned delivery vehicles under different road lengths to construct an unmanned delivery vehicle deployment model;

[0017] The unmanned delivery vehicle deployment recommendation release module is used to output the simulation results of unmanned delivery vehicles and provide the number of unmanned delivery vehicles under the current road length, width, and isolation method to traffic management personnel.

[0018] Thirdly, an embodiment of the present invention provides an electronic device, including a memory and a processor. The memory stores program instructions executable by the processor, and the processor can execute the following method by invoking the program instructions: Relying on the input unmanned delivery vehicle information and road information, calibrate the unmanned delivery vehicle and road model parameters, complete the model construction, and perform traffic simulations under different unmanned delivery vehicle flows. If it is determined that the impact of the unmanned delivery vehicle deployment on the preset traffic flow reaches the judgment threshold, define the deployment quantity corresponding to the current density of unmanned delivery vehicles, and be able to output and store the current unmanned delivery vehicle deployment quantity, and transmit it to the display interface for display.

[0019] Fourthly, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program and experimental results are stored. The computer program can execute the following method: Relying on the input unmanned delivery vehicle information and road information, calibrate the unmanned delivery vehicle and road model parameters, complete the model construction, and perform traffic simulations under different unmanned delivery vehicle flows. If it is determined that the impact of the unmanned delivery vehicle deployment on the preset traffic flow reaches the judgment threshold, define the deployment quantity corresponding to the current density of unmanned delivery vehicles, and be able to output and store the current unmanned delivery vehicle deployment quantity, and transmit it to the display interface for display. The stored experimental results include: the unmanned delivery vehicle model, road model, and traffic model in the experiment, the impact of unmanned delivery vehicle deployment after the experiment, the deployment quantity of delivery vehicles, and the deployment curve of unmanned delivery vehicles.

[0020] Fifthly, an embodiment of the present invention provides a computer-readable storage medium, on which all experimental results are stored. The stored experimental results include: the unmanned delivery vehicle model, road model, and traffic model in the experiment, the impact of unmanned delivery vehicle deployment after the experiment, the deployment quantity of delivery vehicles, and the deployment curve of unmanned delivery vehicles.

[0021] In a sixth aspect, an embodiment of the present invention provides a display device and an input device. The display device can be used to display the parameter calibration situation of the unmanned delivery vehicle and the road, the influence judgment threshold, and the delivery volume of the unmanned delivery vehicle. The input device is mainly used for inputting data of the vehicle model parameters of the unmanned delivery vehicle, the road model parameters, and the traffic influence judgment threshold..

[0022] Through the simulation experiment on the impact of the delivery volume of the unmanned delivery vehicle on urban traffic, the embodiment of the present invention gives the delivery quantity of the unmanned delivery vehicle on urban sections, standardizes the delivery rules of the unmanned delivery vehicle, can effectively support the standardized management of the unmanned delivery vehicle, and reduces the impact of the unmanned delivery vehicle on urban road traffic on the premise of ensuring the logistics transportation demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flow chart of the method for estimating the delivery volume of the unmanned delivery vehicle on a road section according to the present invention;

[0024] Figure 2 It is a schematic diagram of the simulation experiment of the unmanned delivery vehicle under the condition of separating motor vehicles and non-motor vehicles according to the present invention;

[0025] Figure 3 It is a fitting curve of the delivery quantity of the unmanned delivery vehicle under the condition of separating motor vehicles and non-motor vehicles according to the present invention;

[0026] Figure 4 It is a schematic structural diagram of the device for estimating the delivery volume of the unmanned delivery vehicle on a road section according to the present invention;

[0027] Figure 5 It is a schematic physical structure diagram of the electronic device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] Figure 1 It is a schematic flow chart of the method for estimating the delivery volume of the unmanned delivery vehicle on a road section provided by the embodiment of the present invention. As Figure 1 shown, the embodiment of the present invention provides a method for estimating the delivery volume of the unmanned delivery vehicle on a road section. The method is applied to determining the delivery quantity of the unmanned delivery vehicle on urban sections and includes:

[0030] S101. Obtain the driving state information and vehicle information of the unmanned delivery vehicle, and determine the road geometric information in combination with the actual road network and specification standards.

[0031] Specifically, the unmanned delivery vehicle information includes vehicle information and vehicle driving information. By means of actual measurement, obtain the three-dimensional geometric information such as the length, height, and width of the unmanned delivery vehicle to be put on this road, as well as the physical information of the delivery vehicle such as the position of the front axle, the position of the rear axle, and the wheelbase of the vehicle. In addition, relying on the test results of the unmanned delivery vehicle test site, obtain the driving state information such as the running speed, expected acceleration, expected deceleration, following model, safe lateral spacing, and driving rules (driving on the left / right) of the unmanned delivery vehicle.

[0032] Furthermore, obtain the road information of the unmanned delivery vehicle to be put. Based on actual measurement, obtain the road geometric information such as the road length, road width, number of lanes, and isolation method of this road. For roads that have not been completed, it is necessary to rely on the urban road design specifications and design plans to obtain information such as the urban road length, road width, number of lanes, and isolation method. Secondly, rely on the urban road design specifications to obtain the urban road capacity data, and design the urban road traffic flow based on the smoothness level. Finally, rely on traffic surveys to obtain the traffic flow composition of urban roads (motor vehicle traffic flow composition and non-motor vehicle traffic flow composition).

[0033] S102. Build a model of the unmanned delivery vehicle and the urban section, rely on traffic simulation means to evaluate the impact of the unmanned delivery vehicle on the basic urban section, determine the unmanned delivery vehicle delivery volume under different road conditions, and feedback the unmanned delivery vehicle delivery suggestions to traffic management personnel.

[0034] Specifically, calibrate the model parameters of the unmanned delivery vehicle based on the driving state information and vehicle information of the unmanned delivery vehicle, build a delivery vehicle model, build motor vehicle and non-motor vehicle models based on existing standards and research results according to research needs, and set up an urban road model and a road traffic flow environment based on the road information. Design simulation experiments under different unmanned delivery vehicle flows based on the vehicle model and the road model, obtain data such as the running speed, flow, and delay of other traffic modes after the unmanned delivery vehicle is put, calibrate the acceptable degree of the impact of the delivery vehicle on other traffic after it is put, and set an impact judgment threshold. If the running parameters of other traffic under the simulation flow of the unmanned delivery vehicle reach the set impact judgment threshold, the delivery volume corresponding to the density of the current unmanned delivery vehicle running on the road is the number of unmanned delivery vehicles that can be put on this road model. Finally, based on various types of road models, fit the unmanned delivery vehicle delivery volume to establish a general unmanned delivery vehicle section delivery model.

[0035] In an embodiment of the present invention, in view of the standardized management requirements of driverless delivery vehicles, by combining the concept of traffic simulation with traffic impact assessment, it is determined that the impact of the deployment of driverless delivery vehicles on road traffic shall not exceed the acceptable impact threshold, and the acceptable impact threshold may be a 5% decrease in speed. Specifically, the preset time threshold is determined according to actual situations such as road shape, size, isolation method, and management requirements. If the impact of the deployment of the driverless delivery vehicle on other traffic on the road exceeds the acceptable impact threshold, the current number of deployed driverless delivery vehicles is determined as the recommended value of the number of deployed driverless delivery vehicles.

[0036] In an embodiment of the present invention, the impact of the deployment of driverless delivery vehicles under the condition of motor-vehicle and non-motor-vehicle separation is introduced for the road scenario described above, where the acceptable impact threshold is a 5% decrease in speed.

[0037] First, the driverless delivery vehicle information acquisition is more based on the requirements of regional trial operation. It is determined that the current length of the driverless delivery vehicle is 2.5 m, the width is 1.0 m, the height is 1.7 m, the front axle length is 0.49 m, and the rear axle length is 2.22 m. The expected speed of the driverless delivery vehicle is determined to be 12 - 14 km / h, the acceleration time from 0 - 10 km / h does not exceed 4 s, the acceleration time from 0 - 20 km / h does not exceed 7.6 s, the lateral spacing is 0.5 m, and the driving direction is to drive on the right. Based on the policy requirements for the current management of driverless delivery vehicles as non-motor vehicles, a non-motor vehicle following model is set for the driverless delivery vehicle based on existing research.

[0038] Second, it is determined that the road section is a motor-vehicle and non-motor-vehicle separated road, with road lengths of 150 m, 200 m, 250 m, 300 m, 350 m, 400 m, 450 m, road widths of 2 m, 2.5 m, 3 m, 3.5 m, 4 m, 4.5 m, 5 m, the road isolation method is motor-vehicle and non-motor-vehicle separation, and the driverless delivery vehicle travels on the non-motor vehicle lane. Based on traffic surveys, the proportion of electric bicycles and bicycles is approximately 7:3. Relying on the regulations on the traffic capacity of non-motor vehicle lanes in the "Urban Road Engineering Design Specification" and combining with the non-motor vehicle lane smoothness calculation formula (Formula 1), the non-motor vehicle flow of urban roads is calculated as shown in Table 1.

[0039]

[0040] Where: q —— is the equivalent bicycle traffic volume converted to 1 hour during the observation period (bikes / h)

[0041] c —— is the corresponding traffic capacity of the non-motor vehicle lane (bikes / (h·m))

[0042] W —— is the corresponding non-motor vehicle lane width (m)

[0043] Table 1

[0044]

[0045] Next, using existing simulation technologies, relying on the parameter calibration results of the unmanned delivery vehicle and the road model calibration results in the simulation platform, an unmanned delivery vehicle simulation model and an urban road simulation scenario are constructed. At the same time, bicycle and electric bicycle models are constructed based on existing research, and simulation experiments are carried out with different unmanned delivery vehicle flows.

[0046] Figure 2 It is a schematic diagram of the simulation experiment of the unmanned delivery vehicle under the condition of mixed motor vehicle and non-motor vehicle traffic, which includes electric bicycles, non-motor vehicles and unmanned delivery vehicles. The unmanned delivery vehicle adopts the driving rule of keeping to the right, and bicycles and non-motor vehicles adopt the driving rule of keeping to either side.

[0047] Furthermore, relying on the output of the simulation experiment, the running speed, flow and vehicle density of non-motor vehicles are obtained, and the reduction of the non-motor vehicle speed under different numbers of unmanned delivery vehicles put into use is calculated and compared with the influence judgment threshold. If the speed reduction is less than the set threshold (a 5% reduction), it is judged that the current number of unmanned delivery vehicles put into use can continue to increase. When the non-motor vehicle speed reduction is greater than 5%, it is judged that the current unmanned delivery vehicle flow has reached the upper limit, and if the number of unmanned delivery vehicles put into use continues to increase, it will seriously affect the normal operation of non-motor vehicles. At this time, based on the density of unmanned delivery vehicles on the road, the number of unmanned delivery vehicles that can be put into use currently can be calculated according to formula (Equation 2) (Table 2).

[0048]

[0049] Where: m — the number of vehicles that can be put into use simultaneously on a road of length l;

[0050] k u — the instantaneous average density of unmanned delivery vehicles;

[0051] l — the length of the non-motor vehicle lane.

[0052] Table 2

[0053]

[0054] Finally, according to the results of the number of unmanned delivery vehicles put into use, the number of unmanned delivery vehicles put into use with different widths is fitted according to the road length to obtain the number of unmanned delivery vehicles put into use under different road lengths and road widths for the same unmanned delivery vehicle. Figure 3It is a fitting curve of the number of unmanned delivery vehicles put into use under the condition of separated operation of motor vehicles and non-motor vehicles with different lengths and widths of non-motor vehicle lanes. When the curve is generated, it will be stored in a computer-readable storage medium. If the model of the unmanned delivery vehicle remains unchanged and the road traffic conditions also remain unchanged, the number of such unmanned delivery vehicles put into use on urban roads can be calculated based on this curve, and the estimated values of the number of unmanned delivery vehicles for all road lengths and road widths can be obtained through interpolation method.

[0055] Figure 4 It is a schematic structural diagram of the device for estimating the number of unmanned delivery vehicles put into use in a section provided by an embodiment of the present invention. As Figure 3 shown, the device includes: a parameter setting module, an unmanned delivery vehicle operation simulation module, an unmanned delivery vehicle put-in quantity fitting module, and an unmanned delivery vehicle put-in suggestion publishing module, where:

[0056] The parameter setting module 401 is used to obtain vehicle model parameters and road traffic model parameters.

[0057] Specifically, the parameter setting module 401 includes three functions: vehicle model parameter setting, road traffic parameter setting, and traffic impact threshold setting. The vehicle model parameter setting function is used to input geometric parameter information such as the length, width, height, and wheelbase of the unmanned delivery vehicle, as well as driving state information such as the speed, expected acceleration, following model, and lateral spacing of the unmanned delivery vehicle. The road traffic parameter setting function is used to input the separated form of motor vehicles and non-motor vehicles on the road where the unmanned delivery vehicle travels, as well as the width, length, and number of lanes of the lane. In addition, the input of parameters such as road traffic flow and traffic flow parameters is also carried out in this function; the traffic impact threshold setting function is used to determine the acceptable degree of the impact of the unmanned delivery vehicle put-in on traffic. Managers can set a traffic impact judgment threshold as a judgment condition for determining the number of unmanned delivery vehicles put into use.

[0058] The unmanned delivery vehicle operation simulation module 402 is used to model the parameters set in the parameter setting module 401 and construct a simulation model. The unmanned delivery vehicle operation simulation module 402 relies on existing simulation software to construct the vehicle model and road model of the unmanned delivery vehicle, set the traffic flow and traffic flow composition according to the actual investigation results, and combine the actual separation method of the road and the operation management rules of the unmanned delivery vehicle to set general motor vehicle and non-motor vehicle models, conduct simulation experiments under different road conditions and different unmanned delivery vehicle traffic flows, and output the operation state data of motor vehicles / non-motor vehicles and the state data of unmanned delivery vehicles obtained from the simulation.

[0059] The unmanned delivery vehicle delivery volume fitting module 403 is used to evaluate the traffic operation impact on the simulation results output by the unmanned delivery vehicle operation simulation module 402 by using the traffic impact judgment threshold. If the operation state of motor vehicles / non-motor vehicles reaches the traffic impact judgment threshold, it is considered that the number of unmanned delivery vehicles calculated from the delivery vehicle density corresponding to the current unmanned delivery vehicle delivery flow condition is the delivery volume that the current road can bear. At the same time, if the current delivery vehicle model and the road traffic model are the same as those in the historical test, the delivery vehicle delivery volumes obtained from multiple experiments will be curve-fitted for the delivery curve. If the input unmanned delivery vehicle model and the road traffic model remain unchanged later, and the road length and width required for testing are within the historical test data, interpolation and other methods can be directly used to determine the number of unmanned delivery vehicles by calling the fitted curve.

[0060] The unmanned delivery vehicle delivery suggestion publishing module 404 is used to publish the delivery volume result obtained by the unmanned delivery vehicle delivery volume fitting module 403, and provide the traffic management personnel with the number of unmanned delivery vehicles under the required road length, width and isolation method.

[0061] The unmanned delivery vehicle section delivery volume estimation device provided by the embodiment of the present invention specifically executes the processes of the above method embodiments. For details, please refer to the content of the above method embodiments, which will not be repeated here.

[0062] Figure 5 This is a schematic physical structure diagram of the electronic device provided by the embodiment of the present invention. Refer to Figure 5 The electronic device includes: a processor 501, a memory 502 and a bus 503; wherein, the processor 501 and the memory 502 communicate with each other through the bus 503; the processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above method embodiments, for example, including: constructing a vehicle model and a road model according to the unmanned delivery vehicle information and road information; realizing traffic simulation under different traffic flow conditions and outputting the operation state parameters of traffic participants; judging the impact of the unmanned delivery vehicle on road traffic according to the traffic impact judgment threshold, and determining the delivery volume of the unmanned delivery vehicle according to the unmanned delivery vehicle density; combining the unmanned delivery volume to fit the delivery volumes of the delivery vehicles under different road lengths, widths and traffic conditions with the same unmanned delivery vehicle model and road model to form a delivery model, and finally publishing the unmanned delivery vehicle delivery volume to the management personnel based on the delivery volume obtained from the simulation and the delivery model.

[0063] In addition, when the logical instructions in the above-mentioned memory 502 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Fundamentally speaking, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium, and the instructions in this software product can execute all or part of the steps of the methods described in the various embodiments of the present invention by devices with independent computing functions such as computers (personal computers, servers, or network devices, etc.). The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0064] The embodiments of the present invention also provide a computer-readable storage medium 504, which is connected to the processor 501 through the bus 503. All experimental results are stored on this computer-readable storage medium 504, for example, including: the construction results of the unmanned delivery vehicle model, the road model construction results, and the traffic parameter model setting results during the model construction after parameter input. The preservation of the model is mainly to enable the direct call of the model during the subsequent construction of the same model. At the same time, when the same model is input, if only the road geometric parameters change, the placement model curve can be directly called to quickly determine the number of unmanned delivery vehicles to be placed, thereby improving the operation efficiency of the device. In addition, the computer-readable storage medium 504 also stores the number of delivery vehicles placed after the experiment and the placement curve of the unmanned delivery vehicle. The preservation of the number of placements can support the fitting of the delivery vehicle placement curve, and the storage of the placement curve can achieve the rapid output of the number of unmanned delivery vehicles to be placed based on historical output results.

[0065] The embodiments of the present invention also provide a display device 505 and an input device 506. The display device 505 is mainly used to display the calibration situation of the unmanned delivery vehicle and the road model and to output the number of unmanned delivery vehicles to be placed. The display device 505 is connected to the processor 501 through the bus 503, and management personnel can observe the accuracy of parameter input and the results output by the device in real time through the display device 505. The input device 506 is mainly used for inputting data such as the vehicle model parameters of the unmanned delivery vehicle, the road model parameters, and the traffic impact judgment threshold. The input device 506 is connected to the processor 501 through the bus 503 and can provide a data source for the operation of the processor 501.

[0066] The embodiments of the electronic device and the like described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0067] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An estimation method for the deployment quantity of unmanned delivery vehicles on road segments, characterized in that, it includes: Obtain the driving state information and vehicle information of the unmanned delivery vehicle as the target object, and at the same time obtain the actual situation of the urban road network, and construct the target unmanned delivery vehicle model, other vehicle models and the basic road model of the target urban road segments; According to the target unmanned delivery vehicle model and the road model, use simulation testing means to determine the deployment quantity of unmanned delivery vehicles under the conditions of the target delivery vehicle and the target road segments based on the evaluation of the impact of unmanned delivery vehicle deployment, and output and feedback the recommended value of the unmanned delivery vehicle deployment to the management personnel; The obtained driving state information and vehicle information of the unmanned delivery vehicle include: At least one of the length, height, width, front axle position, wheelbase, and rear axle position of the unmanned delivery vehicle; At least one of the running speed, expected acceleration, expected deceleration, following model, lateral spacing, and driving rules of the unmanned delivery vehicle; Calibrate the parameters of the unmanned delivery vehicle model based on the driving state information and vehicle information of the unmanned delivery vehicle, construct the unmanned delivery vehicle model, motor vehicle and non-motor vehicle models, set the urban road model and the road traffic flow environment based on the road information; design simulation experiments under different unmanned delivery vehicle flows based on the motor vehicle, non-motor vehicle models and the road model, obtain the running speed, flow and delay data of other traffic modes after the deployment of the unmanned delivery vehicle, calibrate the acceptable degree of the impact of the deployment of the unmanned delivery vehicle on other traffic and set the impact judgment threshold; if the other traffic operation parameters under the simulated flow of the unmanned delivery vehicle reach the set impact judgment threshold, the deployment quantity corresponding to the density of the current unmanned delivery vehicle running on the road is the number of unmanned delivery vehicles that can be deployed on this road under this road model. Finally, based on various types of road models, fit the deployment quantity of the unmanned delivery vehicle to establish a general unmanned delivery vehicle road segment deployment model; The obtained urban road information includes: At least one of the actual urban road length, actual road width, actual number of lanes, urban road length in the planning stage, road width in the planning stage, and number of lanes in the planning stage.

2. The estimation method according to claim 1, characterized in that, the unmanned delivery vehicle deployment evaluation method includes the following steps: Based on the instantaneous density of the unmanned delivery vehicle simulation experiment operation, calculate the number of delivery vehicles that the unmanned delivery vehicle can carry under different road lengths; Based on the simulation experiments under different road conditions, construct a fitting curve for the deployment of the unmanned delivery vehicle based on the road length, and establish a basic road segment deployment model for the unmanned delivery vehicle.

3. The estimation method according to claim 1, characterized in that, it includes: The management personnel can determine the deployment value of the unmanned delivery vehicle according to their own management needs; The simulation results of the unmanned delivery vehicle under the condition of the same unmanned delivery vehicle model will be fitted, so as to fit the deployment curve of the unmanned delivery vehicle in the same environment, which is convenient for quickly outputting the deployment quantity of the unmanned delivery vehicle under different road conditions. When the constructed unmanned delivery vehicle model and road environment are consistent with the stored historical unmanned delivery vehicle simulation background, it is possible to directly rely on the historical fitting curve output without triggering the simulation module.

4. An estimation device for the deployment quantity of unmanned delivery vehicles on a section of road Characterized in that It includes: A parameter setting module, which includes three functions: vehicle model parameter setting, road traffic parameter setting, and traffic impact threshold setting; The vehicle model parameter setting function is used to input the geometric parameter information of the unmanned delivery vehicle and the driving state information of the unmanned delivery vehicle; the road traffic parameter setting function is used to input the width, length, number of lanes of the motor vehicle lane, and the length, width, and isolation method of the non-motor vehicle lane, as well as the traffic flow and traffic flow composition; the traffic impact threshold setting function is used to determine the acceptable degree of the impact of the deployment of unmanned delivery vehicles on traffic, as the judgment condition for estimating the deployment quantity of unmanned delivery vehicles; An unmanned delivery vehicle operation simulation module, which is used to construct a model with the parameters in the parameter setting module, combine the motor vehicle and non-motor vehicle models, conduct unmanned delivery vehicle simulation experiments under different road conditions and different unmanned delivery vehicle models, and output at least one of the motor vehicle operation state data, non-motor vehicle operation state data, and unmanned delivery vehicle state data obtained from the simulation experiments; An unmanned delivery vehicle deployment quantity fitting module, which is used to calibrate the impact of the deployment of unmanned delivery vehicles using the traffic impact threshold, determine the deployment quantity of unmanned delivery vehicles under different road section conditions within the acceptable range of the impact of the deployment of unmanned delivery vehicles, and conduct a deployment curve fitting on the deployment quantity of unmanned delivery vehicles under different road lengths to construct an unmanned delivery vehicle deployment model; An unmanned delivery vehicle deployment recommendation release module, which is used to output the simulation results of the unmanned delivery vehicle and provide the deployment quantity of the unmanned delivery vehicle under the current road length, width, and isolation method to traffic management personnel; The obtained driving state information and vehicle information of the unmanned delivery vehicle include: At least one of the length, height, width, front axle position, wheelbase, and rear axle position of the unmanned delivery vehicle; At least one of the running speed, expected acceleration, expected deceleration, following model, lateral spacing, and driving rules of the unmanned delivery vehicle; Based on the driving state information and vehicle information of the unmanned delivery vehicle, calibrate the parameters of the unmanned delivery vehicle model, construct the unmanned delivery vehicle model, motor vehicle, and non-motor vehicle models, and set the urban road model and road traffic flow environment based on the road information; design simulation experiments under different unmanned delivery vehicle flows based on the motor vehicle, non-motor vehicle models, and road models, obtain the running speed, flow, and delay data of other traffic modes after the deployment of the unmanned delivery vehicle, calibrate the acceptable degree of the impact on other traffic after the deployment of the unmanned delivery vehicle and set the impact judgment threshold; if the other traffic operation parameters under the simulated flow of the unmanned delivery vehicle reach the set impact judgment threshold, the deployment quantity corresponding to the density of the current unmanned delivery vehicle running on the road is the number of unmanned delivery vehicles that can be deployed on this road model. Finally, based on multiple types of road models, fit the deployment quantity of the unmanned delivery vehicle to establish a general unmanned delivery vehicle section deployment model; The obtained urban road information includes: At least one of the actual urban road length, actual road width, actual number of lanes, urban road length in the planning stage, road width in the planning stage, and number of lanes in the planning stage.

5. An electronic device, characterized in that, it includes: At least one processor, which can conduct simulation experiments on unmanned delivery vehicles, complete the fitting work of the delivery volume, and can execute the estimation method described in any one of claims 1 to 3; And it includes at least one memory communicatively connected to the processor, and the memory stores program instructions that can be executed by the processor.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores experimental results, can realize the storage of simulation experiment results and delivery fitting results. The experimental results are the output results of the estimation method described in any one of claims 1 to 3, including vehicle models, road models, and delivery volumes, and can support the rapid invocation of the results.

7. A display device, characterized in that, The display device can be used to display the calibration situation of the unmanned delivery vehicle and / or the delivery volume of the unmanned delivery vehicle of the estimation method described in any one of claims 1 to 3.

Images