METHOD FOR DETERMINING A TRANSPORT INFRASTRUCTURE, ELECTRONIC COMPUTING DEVICE FOR PERFORMING A PROCEDURE, AS WELL AS COMPUTER PROGRAM AND DATA CARRIER

Description

[0001] The invention relates to a method for determining a traffic infrastructure based on height data of a height monitoring object according to patent claim 1. Furthermore, the invention relates to an electronic computing device for carrying out a method for determining a traffic infrastructure according to patent claim 4. Furthermore, the invention relates to a computer program according to patent claim 5 and an electronically readable data carrier according to patent claim 6, which are each suitable for reproducing the steps of the method for determining a traffic infrastructure.

[0002] As the electrification of transport progresses, the transport infrastructure must be adapted. For example, the infrastructure for supplying energy to vehicle propulsion systems must be rethought, as fueling is increasingly being replaced by electricity instead of gasoline or diesel. Therefore, a charging infrastructure with charging infrastructure components, such as charging stations, for electrical energy or electricity is increasingly needed.

[0003] To operate charging stations efficiently, so that their operation is ecologically and economically viable, it is advantageous to select a suitable location for each charging station. Special planning tools are now available for site selection. These tools can use and process data to determine the appropriate location and, in addition, the performance of a charging station. Such planning tools are primarily used for scientific research purposes, as demonstrated, for example, by the publication by Y. Ahn and H. Yeo "Using real taxi trajectory data generated identity map of charging infrastructure." Commercial providers, in contrast, often place their charging stations at strategically important locations, i.e., preferably on busy routes, regardless of the appropriateness of the location.

[0004] Furthermore, Yang Jie et al. in "A data-driven optimization-based approach for siting and sizing of electric taxi charging stations" (TRANSPORTATION RESEARCH. PART C, EMERGING TECHNOLOGIES, Vol. 77, pages 462-477) present a data-driven, optimization-based approach for allocating chargers for battery-electric vehicle taxis in a city, with the goal of minimizing infrastructure investments.

[0005] In "Siting public electric vehicle charging stations in Beijing using big-data informed travel patterns of the taxi fleet" (TRANSPORTATION RESEARCH PART D: TRANSPORT AND ENVIRONMENT, Vol. 33, December 1, 2014 (2014-12-01), pages 39-46), Hua Gai et al. show how data on the travel routes of 11,880 taxis in Beijing are used to evaluate how travel patterns derived from big-data can influence the development of public charging infrastructure.

[0006] Michele De Gennaro et al. show in "Customer-driven design of the recharge infrastructure and Vehicle-to-Grid in urban areas: A large-scale application for electric vehicles deployment" (ENERGY, ELSEVIER, AMSTERDAM, NL, Vol. 82, 14 February 2015(2015-02-14), pages 294-311) how driving pattern databases and data mining can be used to design a charging infrastructure.

[0007] Furthermore, US 2013 0 222 158 A1 describes a charging infrastructure for electric vehicles. DE 10 2010 020 298 A1 describes a method for capturing traffic data from digital aerial image sequences.

[0008] The object of the present invention is therefore to provide a method, a computing device, a computer program and a data carrier, each of which can determine the utilization of a traffic infrastructure in such a way that the determination can be used particularly advantageously for planning a charging infrastructure.

[0009] This object is achieved according to the invention by the subject matter of the independent patent claims. Advantageous embodiments and further developments of the invention are specified in the dependent patent claims as well as in the description and drawings.

[0010] A first aspect of the invention shows a method according to the invention for determining a traffic infrastructure based on height data of a height-monitoring object. The method according to the invention comprises several steps: In step a) of the method, the height data acquired by at least one sensor unit of the at least one height-monitoring object is evaluated. Furthermore, in step a) an evaluation data set is generated based on the height data. The height data can, for example, contain electromagnetic information across the entire electromagnetic range or a sub-range of the electromagnetic spectrum. This sub-range of the electromagnetic spectrum can, for example, lie in a range visible to the human eye and / or in an infrared range and / or an ultraviolet range and / or a radio range, for example for radar images.Advantageously, the altitude data contains information in wavelength ranges of the electromagnetic spectrum which are particularly advantageously suited to transporting or containing information or features of a traffic infrastructure. The altitude monitoring object is capable of positioning the sensor unit, which can be a photo camera, for example, at a height above a ground or a partial area of ​​the earth's surface such that the ground or the partial area can be observed or recorded from above by the sensor unit. For example, the altitude monitoring object can be a satellite, a balloon and / or an aircraft. For example, in the aforementioned case where the sensor unit is a camera, satellite images are recorded by a satellite. In the case of an aircraft or a balloon, the altitude data can be aerial photographs.Depending on how or with what the method is carried out, for example by an electronic computing device, the elevation data can be received by the same, for example via an interface, so that the elevation data are thus ready for evaluation. The data can be stored in a memory area or a memory device of the computing device after receipt or during receipt and kept ready for retrieval. Evaluation can be understood as the elevation data being prepared depending on their nature in such a way that they can advantageously be kept available for steps b) and / or c) of the method. In step b) of the method, at least one component of the traffic infrastructure is identified from the evaluation data set.The transport infrastructure is in particular at least partially a road network which can include or have entrances and exits, intersections as well as parking spaces or storage facilities and other components. At least one of the mentioned components is recognized or derived from the evaluation data set based on the elevation data or their evaluation. In a further step c) of the method, at least one user of the transport infrastructure is identified from the evaluation data set. For the example of the road network, the user of the transport infrastructure is thus, for example, a vehicle which is recognized by step c) of the method. In a step d) of the method, a utilization of the at least one component by the at least one user of the transport infrastructure is determined, in particular based on the evaluation data set.In this case, step d) advantageously takes place after identifying the at least one component and identifying the at least one user (steps b) and c)), so that the utilization can be determined particularly advantageously. One advantage of the method according to the invention is that, based on the utilization, planning of a charging infrastructure, in particular for electrically powered vehicles, is particularly advantageously enabled. A further advantage of the method, which is or can be carried out in an automated manner, is that it can be carried out particularly cost-effectively compared to previous methods which, for example, manually determine a location for a charging infrastructure component.Furthermore, the method makes it possible, based on capacity utilization, to perform calculations or determine parameters that could facilitate the general expansion of the transport infrastructure, particularly a distribution network. The information obtained through the method or the data generated could be used in subsequent steps, for example, to carry out distribution network planning. Furthermore, it is possible that, in addition to the direct benefit for determining the transport infrastructure and thus the charging infrastructure or distribution network, other, particularly indirect and not yet measurable, usage scenarios might also arise.

[0011] According to the invention, at least one location for a charging infrastructure component, such as a charging station for supplying at least one electrical energy storage device of an electrically powered motor vehicle with electrical energy, is determined based on the determined capacity utilization, in particular in a further step e) of the method. In other words, the method makes it possible to determine a particularly advantageous location for the charging infrastructure component depending on the capacity utilization, since the method according to the invention enables a particularly accurate estimation of the demand for the transport infrastructure or the charging infrastructure component assigned to it.

[0012] When planning transport infrastructure, or in particular charging infrastructure, the placement or correct location for charging stations for electrically powered vehicles or electric vehicles is particularly important. A major challenge in this regard is the correct determination of a parking location and parking duration for these electric vehicles. This can be determined particularly advantageously using the method according to the invention by determining the utilization. Thus, the utilization can advantageously be determined with regard to the parking location and the parking duration, wherein additionally or alternatively traffic flow data for the utilization can also be determined, which, however, can play at least only a minor role in determining the at least one location for at least one charging infrastructure component.The advantage of the method is that, by determining the capacity utilization, conclusions can be drawn about the parking duration or the length of stay of at least one electrically powered vehicle at at least one specific location, in particular at the parking location. The method according to the invention thus makes it possible to meaningfully expand or supplement the charging infrastructure during planning, thereby improving the quality of the planning. Advantageously, elevation data is evaluated for this purpose, allowing conclusions to be drawn about the time dependence of capacity utilization. This allows conclusions to be drawn particularly advantageously for the selection of the location.

[0013] According to the invention, at least one of the steps of the method, i.e. at least the evaluation and / or the respective identification and / or determination of the utilization and / or the location, is carried out by at least one learning algorithm and / or at least one neural network. Both the algorithm and the neural network are variations of machine learning. Essentially, two approaches can be pursued in machine learning: First, symbolic approaches, such as propositional logic systems, in which the knowledge—both the examples and the induced rules—is explicitly represented, which can be expressed, for example, by the algorithm. Second, subsymbolic systems, such as, in particular, artificial neural networks, which function according to the model of the human brain and in which the knowledge is represented implicitly.Combinations of the at least one algorithm and the at least one neural network are also conceivable. In this case, the algorithm can be capable of learning, in particular self-learning, and can be executed, for example, by the neural network or the neural network receives instructions according to the learning algorithm. This means that the method or at least one step of the method can be carried out automatically, with a quasi-artificial intelligence being able to carry out at least one method step. The learning algorithm can be used to initiate the neural network. If, for example, the height data are images, the neural network or the learning algorithm or the artificial intelligence can, for example, particularly advantageously recognize patterns in these, on the basis of which, for example, the component or the user can be particularly advantageously identified.For example, especially if the elevation data includes a temporal sequence, it is possible to determine in a particularly advantageous manner how long a vehicle has been parked at a specific location, in particular a parking lot as a component of the traffic infrastructure. In addition, it is also possible to evaluate characteristics of the surroundings of this location, for example, so that the location for the charging infrastructure component can be determined particularly advantageously. The neural network or the learning algorithm can be trained using training data, with the training or learning taking place in particular through deep learning and / or reinforcement learning.The learning algorithm can be used in particular for image processing, whereby it can be achieved that structures and patterns of, for example, cities and thus of at least one component of the traffic infrastructure and vehicles can be recognized by artificial intelligence. Generated image features can be categorized, for example, from different layers of the algorithm or the neural network, which can ultimately be assigned to previously defined categories, which can be viewed as a classification of the component. Thus, for example, the method can be used to locate the number of parked cars or vehicles, particularly for at least one defined point in time.This results in the advantage, for example, that significant insights into mobility behavior, particularly with regard to the use of vehicles, in particular electric ones, of a population, for example in a city or a country, can be obtained. In summary, the altitude data is advantageously processed using machine learning or deep learning, artificial intelligence (AI) or, in particular, heuristic optimization methods. In this case, the learning algorithm can, for example, identify at least one vehicle from the altitude data and determine its parking time, whereby a hybrid algorithm is preferably used. With a hybrid algorithm, it is possible, for example, to rely on an assessment, in particular a human assessment, for difficult questions where the learning algorithm is unable to identify the vehicle.This can be done, in particular, during a training phase of the algorithm or network, so that the process can advantageously learn recognition or identification. The training data is preferably particularly comprehensive, i.e., it contains as much data as possible that can be conclusive for learning the identification. By using the learning algorithm and / or the neural network, the process can be carried out particularly efficiently and thus, for example, in a particularly short time.

[0014] According to the invention, additional background data is included in the evaluation data set, so that the utilization of the traffic infrastructure can be determined depending on the background data.

[0015] According to the invention, the background data comprises at least one model for a distribution network and data from a geographic information system (GIS), traffic data, and at least one statistic about user behavior. In other words, for a particularly advantageous determination of the evaluation by the method, background data can be used that contains information that is advantageous for a precise analysis of the traffic infrastructure and thus for the identification, evaluation, and / or determination. For example, the background data can contain at least the model of the distribution network, which overlaps, in particular geographically, with the traffic infrastructure. The distribution network is preferably a distribution network for electrical energy and thus a power grid.By incorporating information about a power grid into the evaluation data, the selection of a location for a charging infrastructure component can be particularly advantageous, as this can be done particularly efficiently depending on the distribution network or power grid, since the amount of energy available through the distribution network is known. Additionally or alternatively, GIS data can be used as background data and thus in the evaluation dataset. A geographic information system is a framework for capturing, managing, and analyzing data, which has its origins primarily in geography. This geographic information system analyzes the spatial location and organizes information layers into visualizations, for example, using maps and 3D scenes.The data provided by the geographic information system thus makes it possible, for example, to advantageously identify patterns in the elevation data, which allows, for example, the location planning of the charging infrastructure component to be carried out particularly advantageously. Additionally or alternatively, traffic data, which in particular contain, for example, traffic volume, can be used as the background data, so that it is generally possible to correlate charging infrastructure with general traffic volumes in addition to, for example, the time the vehicle is parked at the parking facility. Furthermore, the background data can contain at least one statistic on user data, which contains, for example, the length of time a person spends in a supermarket or the distance between home and work or the like, which can also be taken into account in the location selection.Furthermore, if not derivable from the elevation data itself, additional infrastructure data, for example, can be included as background data. This allows, for example, a distinction to be made between a residential and a commercial area, so that, for example, any noise pollution caused by the charging infrastructure due to traffic can be taken into account. Additionally or alternatively, further background data can be used, which is particularly suitable for supplementing and / or supporting the determination of the location of the charging infrastructure component in such a way that the location is selected in such a way that the benefit for the user of the traffic infrastructure is particularly great.

[0016] In an advantageous embodiment of the invention, a parking space for at least one vehicle or the vehicle is identified as the component, and / or a vehicle, in particular an electrically powered vehicle, such as an electric vehicle, which represents a motor vehicle, is identified as the user. It should be noted here that, due to the recording angle, which is essentially perpendicular to the ground, it is difficult to characterize vehicles, particularly with regard to their drive type, from the altitude data, which in particular comprise an aerial photograph or a satellite image. For this purpose, certain type features would have to make the drive type clearly identifiable even in a top view of the vehicle.However, this is not necessary for planning or determining the utilization of the transport infrastructure component, as it can be assumed that the shift towards electromobility will continue. This makes it particularly advantageous to learn or determine at least one location for the charging infrastructure component by determining the utilization. Thus, the proportion of electric vehicles relative to the total number of vehicles increases, which allows, for example, an estimate to be made based on this proportion. This allows conclusions to be drawn about the electric vehicles parked in the area or region under consideration based on the proportion of the total vehicle fleet.In addition, the elevation data, which in particular includes aerial photographs and / or satellite images, can be used to differentiate, for example, between a passenger car as a vehicle and, for example, a local public transport bus as a vehicle. This makes it possible, for example, to advantageously determine the type of charging infrastructure component in addition to planning the location of the charging infrastructure component. For example, it is advantageous for a bus to have a larger charging current available in order to be able to charge the bus's energy storage device particularly efficiently, and in particular particularly quickly. The parking option is also a much more important component for planning the location of the charging infrastructure component than, for example, a section of road on which the vehicles travel, since charging is not possible there, at least not using a charging station.Alternatively or additionally, if the charging infrastructure component, for example, is coils embedded in a roadway for inductive charging, a section of road within which a vehicle moves at a particularly slow and / or constant speed could be used to determine the utilization of the traffic infrastructure. Ground data may be advantageous for recording speed compared to elevation data.

[0017] In a further advantageous embodiment of the invention, ground data from a ground sensor unit is included in the evaluation data set and evaluated. Thus, the utilization of the traffic infrastructure is determined based on the ground data. The ground sensor unit can be, for example, cameras, such as surveillance cameras. Depending on the type of charging infrastructure, such as a charging station or an inductive charging coil, appropriate cameras can be used. For example, the surveillance camera of a traffic monitoring system and / or the surveillance camera of a parking lot, such as a charging station or a public parking lot, can be used for a road section.This makes it possible to use redundant data to determine the utilization of the traffic infrastructure component, making the process particularly efficient. Furthermore, the ground data can be used to distinguish between vehicle drive types in a particularly advantageous way. This could allow the proportion of electric vehicles relative to the total number of vehicles or the entire vehicle fleet to be determined.

[0018] A second aspect of the invention relates to an electronic computing device which is designed to carry out the described method.

[0019] A third aspect of the invention relates to a computer program according to the invention, which implements a method according to the invention on an electronic computing device. The computer program can also be in the form of a computer program product that can be loaded directly into a memory or memory area of ​​the computing device, with program means for executing a method according to the invention when the computer program product is executed, in particular, in the computing device or by the computing device.

[0020] A fourth aspect of the invention relates to an electronically readable data carrier. The electronically readable data carrier according to the invention comprises electronically readable control information stored thereon, which comprises at least one computer program according to the invention or is configured such that it carries out a method according to the invention when the data carrier is used in an electronic computing device.

[0021] The properties and developments of the method according to the invention described above and below, as well as the corresponding advantages, are transferable mutatis mutandis to the further aspects of the invention, and vice versa. For this reason, an explicit formulation of the advantages and advantageous embodiments for the electronic computing device, the computer program, and the electronically readable data carrier is omitted here.

[0022] Further features, details and advantages of the invention will become apparent from the following description of a preferred embodiment and from the drawing.

[0023] The single figure shows a schematic diagram illustrating a method for determining a traffic infrastructure based on height data of a height monitoring object.

[0024] The single figure shows a schematic diagram 10, which sketches the processes and functional relationships of a method for determining a traffic infrastructure based on elevation data 12 of a height-monitoring object. For planning, in particular, a charging infrastructure that is considered dependent on a traffic infrastructure or part of it in order to implement the transition to electromobility as advantageously as possible, the method comprises several steps: In a first step, the elevation data 12, which is recorded by at least one sensor unit, which has, for example, a camera sensor, of the at least one height-monitoring object, is evaluated.Furthermore, in this step a) of the method, an evaluation data set is generated on the basis of the elevation data 12, which in particular contains the elevation data itself, for example, and is already prepared, for example by image recognition, for a subsequent identification of at least one component of the traffic infrastructure or of a user of the traffic infrastructure, for example by marking corresponding image locations. In a step b) of the method, the at least one component of the traffic infrastructure is now identified from or based on the evaluation data set. In a further step c) of the method, the at least one user of the traffic infrastructure is identified from or based on the evaluation data set. In a step d) of the method, a utilization 14 of the at least one component by the at least one user of the traffic infrastructure is determined.The utilization 14 can thus be understood as output information of the method and interpreted, for example, as an estimate of the demand for traffic infrastructure. In an advantageous embodiment of the method, depending on the determined utilization 14, in particular by a learning algorithm and / or a neural network, wherein the learning algorithm can initialize the neural network, the determination of a location for a charging infrastructure component of the charging infrastructure or for or in the traffic infrastructure takes place in a location determination module 16. The determination of the location can be carried out as step e) of the method. Steps a) to d) of the method can, for example, also be carried out, in addition to step e), by a neural network or a learning algorithm, wherein this can advantageously take place in a determination module 20.

[0025] The location determination module 16 provides the location as output 18, whereby for the output 18, the location determination module 16 can, for example, determine the amount of energy required at the location for provision based on the utilization 14 in addition to the location itself.

[0026] Advantageously, training data 22 can be provided for the respective neural network or the respective learning algorithm, which can be retrieved, for example, in a learning phase, for example, using deep learning. Furthermore, a hybrid approach can advantageously be used by a human user to improve the load determination, for example, using reinforcement learning, which can also be carried out independently by the respective learning algorithm or neural network depending on the training data 22.

[0027] In order for the method to be particularly advantageously used for planning a charging infrastructure, in particular, for example, in the form of inductive charging flaps and / or charging stations for electrically powered so-called electric vehicles, a parking facility for at least one vehicle, i.e., in particular, a parking space, is advantageously identified as the component, and / or a vehicle, in particular, a passenger car and / or a vehicle for local public transport, is / are identified as the user of the traffic infrastructure. In addition, external data 24 can be used for the method, wherein the external data 24 particularly advantageously comprises ground data 26 from a ground sensor unit, such as, for example, a surveillance camera, which is evaluated and included in the evaluation data set.Additionally or furthermore, the external data 24 may include background data 28, which may also be included in the evaluation data set, thereby determining the utilization 14 of the traffic infrastructure as a function of the background data 28. Additionally or alternatively, by including the ground data 26 in the external data 24, the former is included in the evaluation data, thereby determining the utilization 14 as a function of the background data.

[0028] The background data 28 can advantageously contain at least one model of a distribution network, in particular a power grid, which overlaps with the traffic infrastructure analyzed by the method. Additionally or alternatively, it can contain information from a geographic information system (GIS), which can particularly advantageously obtain information, for example, about geographical conditions or the like. Additionally or furthermore, traffic data can be part of the background data 28, which, for example, describes traffic volume. Additionally or furthermore, the background data 28 can contain at least one statistic about user behavior, for example, the length of time a person spends in a supermarket.For example, it is possible through statistics to determine the utilization 14 as accurately as possible in the altitude data 12 or for the utilization 14 using the altitude data 12 in combination with the background data 28 in a temporal sequence of the altitude data 12, for example because a recording for the altitude data 12 can only be made every quarter of an hour and the length of time a customer stays in a supermarket is only ten minutes.

[0029] The altitude reconnaissance object is preferably a satellite, so that the altitude data 12 are preferably satellite images. Additionally or alternatively, the altitude reconnaissance object can be an aircraft and / or a balloon or a comparable flying object, to each of which the sensor unit for recording the altitude data 12 is mounted. If the altitude data 12 is recorded by an aircraft or a balloon, it is preferably an aerial photograph.

[0030] The method advantageously enables, for example, planning for the development of the traffic infrastructure, since at least one location for at least one charging infrastructure component, in particular for electrically powered vehicles, can be advantageously determined, since, for example, a parking location and a parking duration of the vehicle can be advantageously determined for the utilization 14, so that a location determined for the charging infrastructure component can be selected as efficiently as possible.

[0031] The method described herein can also be in the form of a computer program or a computer program product that implements the method within a computing device. Likewise, an electronically readable data carrier with electronically readable control information stored thereon can be provided, which comprises at least one described computer program product and is configured such that, when the data carrier is used in, in particular, an electronic computing device, it carries out a described method. List of reference symbols

[0032] 10Diagram 12Elevation data 14Utilization 16Location determination module 18Output 20Determination module 22Training data 24External data 26Soil data 28Background data

Claims

1. Method for designing a traffic infrastructure on the basis of height data (12) of a height monitoring object, having the steps of: a) evaluating the height data (12) which are detected by at least one sensor unit of the at least one height monitoring object, and generating an evaluation dataset on the basis of the height data (12); b) identifying at least one component of the traffic infrastructure from the evaluation dataset; c) identifying at least one user of the traffic infrastructure from the evaluation dataset; d) determining a utilization (14) of the at least one component by the at least one user of the traffic infrastructure; and e) determining at least one location for at least one charging infrastructure component on the basis of the determined utilization (14), wherein at least one of the steps of the method is carried out by at least one learning algorithm and / or at least one neural network, and wherein background data (28) are additionally incorporated into the evaluation dataset and comprise at least one model of an energy quantity deliverable by a distribution network designed as an electricity grid and data of a geographic information system (GIS) and traffic data and at least one statistic relating to user behaviour.

2. Method according to Claim 1, wherein a parking facility for at least one vehicle is identified as the component and / or a vehicle is identified as the user.

3. Method according to one of the preceding claims, wherein ground data (26) of a ground sensor unit are evaluated and incorporated into the evaluation dataset.

4. Electronic computing device which is designed to carry out a method according to one of the preceding claims.

5. Computer program which is loadable directly into a memory of an electronic computing device, having program means in order to carry out the steps of the method according to one of Claims 1 to 3 when the program is executed in a computing device.

6. Electronically readable data carrier with electronically readable control information stored thereon, which comprises at least one computer program according to Claim 5 and is designed in such a way that it carries out a method according to one of Claims 1 to 3 when the data carrier is used in an electronic computing device.