DE102014015073A1 - Method for updating and / or extending a map data set of a limited environment - Google Patents

Abstract

Method for updating and / or expanding a map dataset of a limited environment (2), in particular a parking environment (2), used by mobile devices (3) with environmental sensors (16), wherein a current map dataset is sent to a mobile device operated within the environment (2) Device (3) is used and within the device (3) for locating the mobile device (3) within the environment (2) is used, wherein at least one not yet or different in the map data contained property of at least one feature in the environment (2 ) descriptive feature data from sensor data of the environmental sensors (16) of the mobile devices (3) and stored in the mobile devices (3) stored copy of the map data set, after which the extended map data sets to a central, the environment associated server device (18) transmitted and there taking into account the new and / or changed properties to be merged into an updated map record.

Description

The invention relates to a method for updating and / or expanding a map dataset of a limited environment, in particular a parking environment, driven by mobile devices with environmental sensors, wherein a current map dataset is transmitted to a mobile device operated within the environment and within the device for locating the mobile Device is used within the environment.

Mobile devices, such as motor vehicles, having a system for automatically guiding the mobile device are already known in the art. Such systems, for example fully autonomous vehicle systems, completely take over the longitudinal and transverse guidance of the mobile device in order to guide it to a destination. In the example of a motor vehicle, for limited environments, in particular parking environments such as car parks, it has been proposed to run a motor vehicle fully autonomously to a parking space within the parking environment or the like. In order to be able to realize this, it must be possible within the mobile device to determine the position relative to the destination and to select a trajectory which can be traveled by the mobile device and which leads to the destination.

Localization algorithms for mobile devices in limited environments are already known in the art. Common approaches include, for example, the use of Simultaneous Localization and Mapping (SLAM) algorithms and / or Monte Carlo Localization (MCL) algorithms. Usually, a position hypothesis is determined by evaluating data from sensors of the mobile device, in particular also from environmental sensors, whereby sensor data of at least part of these sensors are fused. Other input data that may go into the determination of a position hypothesis are ego data of the motor vehicle, for example, if its natural motion is to be taken into account starting from a known point. If different types of localization are used, positional hypotheses of the individual procedures can be combined to form an ultimately determined position of the mobile device.

As an example, let's look at the book's location "Probabilistic Robotics" by Sebastian Thrun, Wolfram Burgard and Dieter Fox, The MIT Press, ISBN 9780262201629 , referenced.

In order to support mobile devices within the limited environment in autonomous navigation, it is known to provide the mobile devices with map data sets that are to allow orientation and navigation within the limited environment. In this context, for example, it is known to derive map data of the limited environment from blueprints, to measure the limited environment, and the like. In this context, semantic data, in particular data for the purpose of identifying characteristics of the environment, is added manually. Such semantic data may include, for example, the identification of features of the environment as walls, doors, exits, signs, parking marks, and the like.

Such map data sets require a lot of manual effort to create them. In particular with regard to the said semantic data, which describe the meaning content of features of the environment, it is first of all true that they can change over time, after, for example, signs can be removed or slip off and the like. This creates a high manual tracking effort. Furthermore, such manually created map data sets contain potential inaccuracies, especially in the derivation of map data from building plans. For the fully automatic guidance of mobile devices, in particular motor vehicles, as well as other driving assistance functions, however, a highly accurate and highly reliable map material is needed. A need for manual map generation would complicate the introduction of such features due to high costs.

The invention is therefore based on the object of specifying a possibility for determining highly accurate, the environment with respect to as many properties descriptive map data sets for navigation in limited environments.

In order to solve this problem, it is provided according to the invention in a method of the type mentioned at the outset that at least one characteristic feature of at least one feature in the environment is determined from sensor data of the environmental sensors of the mobile devices and in the mobile device stored map of the map data set are stored, after which the thus expanded map data sets are transmitted to a central, the environment associated server device and merged there taking into account the new and / or changed properties to an updated map data record.

Mobile devices, in particular motor vehicles, exist in different equipment variants. Often it is therefore the case that one single mobile device can actually capture only certain characteristics of features of the environment in which the mobile device is operated. However, considering different mobile devices, there are often different configurations of environmental sensors, which allow to measure various characteristics of features, in particular objects, in an environment. The present invention proposes to utilize this data pool, which is already accumulated in the context of the operation of the mobile device, over the limited environment in which the mobile device is operated, in particular fully automatically or partially automatically, with respect to the map data record by providing the information of a plurality of Mobile facilities operating within the limited environment will be merged and used for continuous updating and, if necessary, expansion of the map data set.

In this case, the method according to the invention relates to the detection of characteristics of features via environmental sensors, thus not only the recording of a traveled route in order to create a road network structure composed of road sections from a plurality of traveled paths. Rather, it is about the most accurate mapping of a limited environment, especially a building, such as a parking garage, in which an increased purpose is also for semantic information on individual features, in particular for their purpose. This is clearly beyond approaches that only want to distinguish between passable and non-drivable areas, because it also the importance of characteristics of the environment semantic metadata collected and added to the map data set, which is advantageous not only at least partially, preferably fully automatic Leadership of the mobile devices can be used within the limited environment, but also can be used for assistance functions within the mobile devices or other devices, which will be discussed in more detail below.

Thus, the present invention allows maps of a limited environment, especially a parking garage, fully automated and accurate to create and / or to update, in particular different environmental sensors are used in different mobile devices, so that in particular an added value for mobile devices with less equipment ambient sensors due to additional information in the map data set arises.

It should be noted that it is well within the scope of the present invention to use the term "feature" for segments of an occupancy map that is part of the map dataset. For example, map data sets are known in which individual, for example, by a grid defined segments next to a "busy / free" information in the sense of "passable / not passable" more metadata, for example, in a tree structure assigned. Of course, however, the term "feature" may also refer to objects or parts of objects that exist within the limited environment.

It should also be pointed out that the expansion of the map data record can certainly also be understood as adding a map of the limited environment created by the motor vehicle itself if the motor vehicle is designed accordingly, for example by means of SLAM algorithms. Within the server device, for example a back-end server, it is then possible by algorithms of the card matching, which are based in particular on certain features / objects, to merge the corresponding card components. This also applies to the early stages of creating map datasets when different areas of the limited environment are to be detected and merged by different mobile devices.

The invention thus describes a possibility for the construction and exchange of card data sets of a limited environment in order to accumulate the measurements of a multiplicity of mobile devices by means of a backend solution, so that errors can be leveled out as well as always up-to-date map data sets of a large fleet of mobile devices, in particular To provide motor vehicles, and optionally other devices available. Mobile device environmental sensors are used to first determine or update characteristics of features of the environment, the map data sets are merged into a centralized server facility of the limited environment, and update the map data set that can be distributed to other mobile devices / devices so that not only is localization within the limited environment possible, but also distances / routes to destinations can be determined, which may also be appropriately selected and / or determined on the basis of semantic feature data describing the meaning of a feature of the environment.

It should be noted at this point that the map data record can possibly be interpreted as another environment sensor for mobile devices.

As already indicated, it is particularly advantageous if mobile devices with different environmental sensors are used. By employing a variety of environmental sensor features, a variety of feature features can also be captured as feature data and added to the map dataset to form as complete a picture as possible of the limited environment in the map dataset, as would be unavailable to individual mobile devices , By having the information of a plurality of mobile devices centrally collected and bundled in the current map data set, mobile devices can compensate for downsizing of their environmental sensors by the information in the map data set collected by other mobile devices.

Preferably, the card data set is transmitted to the respective mobile device when entering the environment. If the environment is, for example, a parking garage, it may be expedient to provide the current map data record in an access area, for example at a barrier, so that it can be used, for example as part of the localization, and updated accordingly / can be supplemented. It is also conceivable that the current map data record is transmitted by the server device as soon as a communication link between the server device and the mobile device can be established. Of course, it is also possible that, in particular on request, a further updated map data record can also be transmitted to mobile devices at later times, in particular if they move within the limited environment for a longer time. In the example of a parking garage or other parking environment, it may also be appropriate to transmit the map data record when restarting the mobile device after a longer life in its current form.

Accordingly, provision may be made for an extended map data record to be transmitted to the server device at each extension and / or when leaving the environment. On the one hand, it is conceivable that whenever new feature data is added to the map data record for updating and / or supplementing, a transmission to the server device also takes place. If traffic is more likely to be restricted, it may be more convenient to make retransmission to the server less frequently, such as when the mobile device is parked, and / or when leaving the environment. Of course, it is also possible to make a cyclic transmission of the extended map data set to the server device.

With regard to the mapping of the environment made here, it is of course expedient if the properties include a position of the feature. A particularly advantageous embodiment results if the properties comprise a class obtained as a result of a classification. In particular, systems that are designed for the autonomous management of the mobile device, but also a variety of other systems that may be provided in mobile devices, in particular vehicle systems, uses different classifications of objects / features of the environment. In this case, for example, classifiers can be used which are applied to the combined sensor data of the environmental sensors in order to identify features, in particular objects, in the surroundings of the mobile device and to treat them accordingly. For example, objects in the environment may be classified as other mobile devices, columns, markers, movable or immovable items, and the like. Such a classification is therefore a specific example for the determination of a semantic property, since a class contains indications of the significance of the feature, which can go far beyond the mere blocking degree for trajectories of the mobile device.

Consequently, in a further embodiment it is also expedient if the properties, in particular as a result of a classification, comprise at least one purpose of the feature, which is then stored correspondingly in the feature data. In particular, this may be a purpose that goes beyond the operation of the mobile device. Thus, the purpose of a wall in a parking garage is based on a supporting effect and structuring of the same; The purpose of a sign is the orientation of people within the limited environment. Especially for within the scope of the invention also envisaged, beyond the fully autonomous or semi-autonomous operation of the mobile device beyond applications, such as mobile devices, use such additional properties of features contained in the map data set for other functions that can then be implemented appropriately and accurately.

With regard to the classification and / or purpose as a property can be particularly advantageous features as signs within the environment and / or lane markings and / or parking marks and / or aids, especially fire extinguishers, by determining a class and / or purpose be identified. In this way, for example, functions are enabled that can lead people to the next exit and / or next extinguisher and the like. Straight mobile devices with higher-quality sensors, such as image processing, can recognize properties that describe the purpose / meaning of features, such as standardized signs on an output or the like. Of course, such additional semantic feature data can also be used in the context of the operation of the mobile device, for example, if it is the mobile device is a motor vehicle and it is relevant whether parking for certain groups of persons are identified or the like, for example in the case of woman parking.

A development of the invention in this context provides that the classification and / or the determination of the purpose from the sensor data using a present in the mobile device or transmitted from the server device to the mobile device auxiliary database, the mapping of sensor data to at least a class and / or purpose of the feature allowed. Thus, the tool is given to the mobile devices in a preferred embodiment of the server device itself in order to determine the desired semantic feature data can. Finally, the auxiliary database thus describes the appearance and / or other recognition properties of possible semantic feature data with regard to the recognizability by environmental sensors. Thus, the auxiliary database can for example contain a sub-database on exit and emergency exit signs and the like.

It has already been stated that, in a particularly expedient refinement, the properties of the features are determined anyway in the context of a function that evaluates the sensor data of the environmental sensors, so that no or less additional effort is required to contribute to the function of updating the map data record. For example, it can therefore be provided that the determination of the properties takes place at least partially as part of a localization of the own mobile device, in particular in the context of carrying out a SLAM method. In the context of SLAM methods, but also in other localization methods, a mapping of the surroundings of the mobile device often takes place anyway, possibly also with regard to the position determination of the mobile device in the card data record considered for this purpose. Thus, during the performance of a localization function, a large number of feature data is generated which describes properties of features in the environment of the mobile device, which can therefore also be used to update and / or supplement the map data record.

On the part of the server device it can be provided that an assignment of new and / or changed properties to a feature takes place by means of a map matching on the basis of predefined features on the part of the server device. Ultimately, therefore, the server device collects the expanded map data sets and reconciles them. Such methods are already known in the prior art under the keyword "map matching" and can be based, for example, on certain salient features. Of course, the map matching can also be simplified if a reliable self-localization of the mobile devices is possible and thus the feature data are in any case in clear relation to the other features contained in the map data record. Various, basically known embodiments are conceivable here.

In general, in the context of the self-localization of the mobile devices, it is expediently conceivable that markers which are uniquely identifiable within the environment are used to locate the mobile device. Localization methods have already been proposed which use unique markers, for example two-dimensional barcodes, which can be recognized by the environmental sensors so that a unique position can be determined, ie any sensor data from the environmental sensors and thus also the feature data in relation to a unique coordinate system limited environment can be set.

For the transmission of the map data records and possibly further information, a device-to-infrastructure communication, for example in the case of a motor vehicle, a motor vehicle-to-infrastructure communication (Car2x communication) can be used. In particular, the use of Wi-Fi connections is suitable. Concrete communication links with which mobile devices can communicate in a limited environment with a server device associated therewith have already been proposed and can be used in the context of the present invention.

As environment sensors particularly expedient at least one camera and / or at least one ultrasonic sensor and / or at least one radar sensor and / or at least one lidar sensor can be used. Cameras can be assigned to image processing facilities. A line detection in the sensor data of For example, cameras may make properties of ground markers, such as parking lot boundaries, identifiable; In the context of image processing, standardized symbols, for example emergency exit signs, can also be recognized in order to obtain semantic feature data. Radar sensors make it possible to detect metallic objects and their position, for example other mobile devices, in particular motor vehicles. By jointly evaluating sensor data from radar sensors and the camera, it is possible, for example, to adjust the position of another mobile device with recognized lane markings / parking space markings in order to determine the occupancy of a parking space, in particular a parking space, and the like. Ultrasonic sensors make it possible, for example, to detect a free space around the own mobile device, so that passable areas can be detected on the assumption that the mobile device starts on a passable route. In the case of a parking environment, parking spaces or parking spaces can be measured in depth. Lidar sensors make it possible, for example, to accurately measure object contours, especially as far as building features and the like are concerned.

Preferably, a scan matching method is used to associate the sensor data with a position in the map data set. Scanmatching methods are already known in the art and ultimately map the known position and orientation of the environmental sensor relative to a localized position of the mobile device in the map data set.

A further development of the invention provides that a path covered by the own mobile device with a traitability-indicating property is also stored in the map data record. In addition to the semantic feature data at the center of the method according to the invention, characteristics of features, in particular regions or segments, of the environment can also be derived from other systems of the mobile device. If a mobile device retraces a certain path, which can be tracked from mobile device odometry data, then the trafficability of that distance follows. However, distances traveled per se can also be expediently evaluated by the server device. Thus, for example, it may be provided that the server device identifies areas of the environment, in particular road damage and / or danger spots, which have been traveled around by comparing paths traveled by a plurality of mobile devices. Thus, if several mobile devices repeatedly pass around locations which have hitherto been marked as free in the map data record, this can be an indication of occupancy of these locations and / or damage in the roadway, which also constitutes important additional information in the map data record and in the planning of trajectories subsequent trips through other mobile devices can be considered. From such information, of course, further measures can be derived, for example, the infrastructure device can output information to appropriate persons, if, for example, with other feature data together, evidence of damage within the limited environment exist.

If the method according to the invention relates to a parking environment, it can also be used to determine current occupancy states of parking spaces from the extended map data records. The occupancy state of parking spaces is dynamically rapidly changeable information, which can thus easily be detected and noticed by changes in the extended map data sets. In addition to the constant improvement of the map, in particular by adding semantic feature data, it is thus also possible to derive a current occupancy information for parking spaces from the extended map data sets in the server device.

A particularly advantageous embodiment of the present invention provides that the feature property of various mobile devices relating to the same property of a feature is evaluated statistically by the server device, in particular using an outlier detection. After limited environments are mostly traveled by many mobile devices, especially in the case of motor vehicles in a parking environment, there is a large number of extended map data sets, which of course also makes it possible to perform a statistical evaluation, in particular to exclude individual faulty measurements of individual mobile devices and To improve the overall quality of the transmitted feature data, since ultimately several different measurements are made. In one embodiment, the feature data can also be accompanied by estimated error values on the part of the mobile device, which ultimately also provide information about the quality of the individual measurements and are reflected, for example, in a weighting of feature data of different mobile devices that relate to the same feature of the environment can find. Thus, in particular, errors are leveled out by the server device due to the statistical analysis.

As already explained, at least one characteristic contained in the map dataset expediently becomes at least one feature evaluated by a next to the localization further function of the mobile device, in particular by a driver assistance function. Thus, for example, an occupant can already be displayed in the mobile device itself, where the next exit from the limited environment is located, just as is possible, for example, in the case of parking garages for automatic teller machines or the like. Here, the semantic data, which attributes meaning to the map data set, proves to be extremely useful. Also in the selection of the destination, whether automatic or manual by a driver, assistive functions may be employed, for example, when it is known that the driver is a man and a parking lot is reserved for women and the like.

In a particularly advantageous embodiment of the present invention, however, provision is made for the card data record to be transmitted to a mobile terminal of a user, in particular a mobile telephone, where it is evaluated within the framework of a software application, in particular a navigation application. If the card data record is also present on a mobile terminal that is carried by a user of the mobile device, this can, for example after getting out of a motor vehicle, on the way back to his mobile device or the like additional assistance functions by the mobile End device to be deployed, use. For example, based on the map data set, the person may be navigated to the nearest possible exit, guided to a resource such as a fire extinguisher, and the like. Thus, the map data set improved beyond the mobile devices, in particular with respect to the semantic feature data, can be used profitably by the present invention.

Expediently, for the initial localization of the own mobile device in the map dataset, as already indicated, a predefined feature, in particular located at an entrance of the surroundings, can be detected. As an example of such detectable features is a barrier system called, which is often found at the entrance to a parking garage as a limited environment. This location is passed by all mobile devices that want to penetrate into the limited environment, so that a particularly simple determination of a start position for the localization within the limited environment is made possible.

It can also be provided that a GPS position determination is taken into account for identifying the environment and / or the initial position in the map data record. Thus, the mobile devices may have a GPS sensor that allows a corresponding absolute position determination in a geodetic coordinate system. On the basis of this geodetic position, it can be ascertained into which limited environment the motor vehicle is currently entering, wherein consideration of such a geodetic position is also expedient in the case of the initial positioning in the map data record. Finally, the identification of the limited environment also identifies the server device with which the mobile device is to contact.

As has already been indicated, the method according to the invention can be applied particularly advantageously to motor vehicles, so that a motor vehicle can be used as a mobile device. The limited environment may be in particular a parking environment, preferably a parking garage, or another limited building in which the motor vehicle is to navigate.

Summarizing the devices involved in the method of the present invention, the overall result is a system for updating and / or expanding a map dataset of a limited environment traveled by mobile devices having environmental sensors, which includes a server device associated with the limited environment. The server device is designed to transmit current map data sets to mobile devices which also belong to the system and which are operated in the limited environment, and to obtain from these extended map data sets, that is to say updated with feature data. The server device, which is stationary and which is an infrastructure, is further adapted to merge the obtained enhanced map data sets to determine a new current map data set. The mobile devices, in particular motor vehicles, in the limited environment are in turn provided with environmental sensors and configured, in particular in the case of properties of features of the environment that are not contained in the map data record and / or in relation to the map data record, to the map data set that is current from the sensor data of the environmental sensors have been determined, which are considered after the return of the map data set to the server device there in the context of updating the map data in general. The statements relating to the method according to the invention of course apply analogously to the system described here and the corresponding subdevices, in particular the server device and the mobile devices.

It should also be noted that it may also be appropriate, in addition to the mobile Devices also to consider other devices within the limited environment for map update, for example, the already mentioned mobile terminals, which often also have environmental sensors, especially cameras, thus can localize themselves within the map data set and determine characteristics of features of the environment, the equally useful the server device can be passed.

Further advantages and details of the present invention will become apparent from the embodiments described below and with reference to the drawing. Showing:

1 a park environment with mobile devices and a server device,

2 a flowchart of an embodiment of the method according to the invention, and

3 a driving situation of a motor vehicle in the limited environment.

1 shows a system in which the method according to the invention can be applied. Shown is a section 1 from a limited environment 2 , here a park environment in which as mobile facilities 3 motor vehicles 4 to be moved. The park environment 2 , which in the present case is a parking garage, is characterized by a variety of different features. walls 5 limit structurally passable and accessible areas, parking markings 6 indicate where to park more road and parking markings 7 . 8th . 9 should provide information to drivers of motor vehicles 4 give; signs 20 on the walls 5 For example, refer to exits and emergency exits, aids, such as fire extinguishers 10 , are on walls 5 hung, the walls 5 be through doors 11 interrupted, columns 12 carry the ceiling of the corresponding floor of the parking garage, at another as a cash machine 13 trained aids payments can be made and the like. In the present example shows the road marking 7 in which directions can be continued; the road marking 8th indicates a crosswalk and the parking mark 9 indicates a woman parking lot. motor vehicles 14 , which are currently not in operation, occupy individual parking lots.

In the present case are the motor vehicles 4 . 14 especially adapted to within the park environment 2 semi-automatically or fully automatically guided to be, so that they have a corresponding fully autonomous vehicle system, which, for example, by a control unit 15 is realized. environmental sensors 16 the motor vehicles 4 . 14 capture the environment, taking the motor vehicles 4 in the present case a different equipment to environmental sensors 16 have. Via a motor vehicle-to-x communication device 17 (Car2x communication device) can the motor vehicles 4 exchange communication information with each other and / or with infrastructure facilities.

Such infrastructure also includes the park environment 2 associated server device 18 that the motor vehicles 4 . 14 Information about the park environment 2 provides, in particular a current map data of the parking environment 2 , Approaches a motor vehicle 4 . 14 the park environment 2 , for example, based on a position information of a GPS sensor or due to the fact that in the range of the communication of the server device 18 is concluded that the server device 18 for the currently used parking environment 2 responsible is. Passes a motor vehicle 4 . 14 a driveway to the park environment 2 , in 1 for clarity, not shown in detail, in this case specifically a barrier device, the current map data set via a communication link 19 from the server device 18 to the corresponding motor vehicle 4 . 14 transfer. Incidentally, with this current map data record, an auxiliary database is also sent to the corresponding motor vehicle 4 . 14 transmitted to the motor vehicle 4 . 14 recognizing features of the environment 2 supported, for example by signs 20 , Roadway and / or parking markings 6 - 9 and the same.

The map dataset is used to locate the operated motor vehicle 4 within the park environment 2 to improve, which in particular on the basis of clearly detectable markers, for example, two-dimensional bar codes, can be improved. Through the environmental sensors 16 recorded sensor data can be merged and evaluated to the environment of the operated motor vehicle 4 evaluated in the context of the localization function and brought into line with the map dataset; However, it should be noted that other functions in the motor vehicle 4 Sensor data of the environmental sensors 16 can evaluate and access map data of the map dataset.

In the park environment 2 However, the method according to the invention is also carried out, that is, new or changed feature data on features of the parking garage, by the environmental sensors 16 the operated motor vehicles 4 will be added to the map record, which will be expanded and extended Map data record forms. The extended map data sets of the operated motor vehicles 4 be in the server setup 18 collected and merged into a new, updated map dataset. In this case, the retransmission of the extended map data record to the server device 18 with parking an operated motor vehicle 4 in a parking lot and / or when leaving the park environment 2 take place, but also at other times, for example cyclically.

An embodiment of the method according to the invention is intended with regard to 2 now be shown in more detail. There moves in a step S1 a motor vehicle 4 in the park environment 2 and receives over the communication link 19 the current map data record transmitted. While now in the following the motor vehicle 4 through the park environment 2 moved, are in the context of functions in the motor vehicle, in particular a localization function, but also of other functions, sensor data of the environmental sensors 16 evaluated, including in terms of characteristics of various features of the park environment 2 , In this case, a localization function, in particular, can be a SLAM localization. In other words, in step S2, a plurality of features of the parking environment are created 2 Characteristics of these features descriptive feature data, the properties being determined by the respective motor vehicle 4 can be determined by its equipment with environmental sensors 16 depends, but especially on the quality of these environmental sensors 16 , For example, an image processing device that is associated with a camera. As environmental sensors 16 can in motor vehicles 4 in addition to cameras and radar sensors, lidar sensors, ultrasonic sensors and the like are used in total. In determining properties of features of the park environment 2 the already mentioned auxiliary dataset is also considered.

In the present case, the determination of characteristics of the features comprises the determination of semantic feature data that go beyond the mere existence or position of features and describe the meaning of the features. For this purpose, in the control unit 15 of the motor vehicle 4 Classifiers are used that allow the assignment of features to a class, such as signage 20 , Parking markings 6 . 9 , Doors 11 , parked vehicles 14 and the same. This also creates information on a purpose of the characteristics as a property, because a sign 20 is indicative of, for example, an output, and the like, it being understood that the characteristics may go beyond the mere mention of the class and the purpose determination information carried thereby. To signage 20 For example, it can be determined if the sign 20 to a normal exit, an emergency exit, a cash machine, a fire extinguisher 10 or the like. Such features can not be achieved by anyone in the park environment 2 operated motor vehicles 4 be determined because their equipment with environmental sensors 16 is different; However, by adding them to the map record, motor vehicles can also be added 4 . 14 that comes from the sensor data of their environmental sensors 16 can not derive these characteristics that use information to operate functions of their vehicle systems.

In a step S3, it is then checked whether the feature data correspond to a change and / or supplement to the map data record. The mapping of features by environmental sensors 16 Characteristics in the map data set is due to the localization and the known mounting position and orientation of the environmental sensors 16 easily possible. It should be noted that the step S3 can basically also be omitted, if all by the operated motor vehicle 4 determined feature data are added to the map data set, but this is ideally avoided due to the high volume of data by in step S3, the expansion criteria are evaluated in terms of changing or adding new properties.

In a step S4, the motor vehicle in operation 4 saved copy of the map data record extended by the new / changed feature data.

In a step S5, the expanded map data set is sent to the server device 18 transferred back.

Steps S1-S8 according to 2 of course, by everyone within the park environment 2 operated motor vehicles 4 executed.

In a step S6, the server device makes 18 then collate the expanded map datasets to collectively evaluate them collectively to determine an updated, new, generally-used map dataset. If the underlying map dataset is already very accurate, so can the localization of the powered vehicles 4 be adopted, so that the to be made "Mapmatching" is accordingly easy to carry out; the map dataset is still under construction and will be completely new areas of the park environment 2 (ideally by several powered vehicles 4 ) can special features are used to establish the matching option between the extended map data records. Such procedures are already known in principle.

Then there is a statistical evaluation of the added new feature data with regard to whether the generally valid map data record must be updated. In this case, outlier detection in particular can be carried out in order to measure errors of individual powered motor vehicles 4 if possible not included in the map data record. In this evaluation step S7 is created using new information within the park environment 2 operated motor vehicles 4 Thus, an updated, optionally supplemented map data set, the, to other in the parking garage operated vehicles 4 can be used there for better orientation and better use of vehicle functions.

With regard to step S7, it should be pointed out that a further development of the method is provided, in step S4 also within the parking environment 2 covered path of the respective motor vehicle 4 To add to the map data set, as this conclusion can be drawn on properties by statistical evaluation, for example, if an actually passable place in the park environment 2 from all motor vehicles 4 is avoided, can be inferred damage to the road or the like.

As already mentioned, the map data set can not only be used in the context of self-localization of one within the parking environment 2 operated motor vehicle 4 be used, but also be used by other vehicle functions. For example, within a motor vehicle 4 . 14 a navigation information to the next output are output, if appropriate signs 20 are known in the map data set, but it is also possible to point out, for example, inappropriate parking or to take this into account in the choice of the destination, ie a parking lot. An example of a driving situation of this kind shows 3 looking into the front passenger area of a motor vehicle 4 showing in a driving situation, passing through the windshield 21 Parking space markings 6 and the marker pointing to a women's parking lot 9 can be seen. Even if now a built in the motor vehicle itself camera 22 or the associated image processing device is not capable of the parking mark 9 to recognize, this is in the map data record, which ultimately acts as a kind of additional environment sensor included so that a male driver, for example, a display device 23 in the motor vehicle 4 can be informed that the parking lot is a women's parking lot.

Similar configurations are also conceivable if certain aids are sought, for example automatic teller machines 13 , Fire extinguisher 10 and the same.

A further advantageous development results when the map data record not only within the park environment 2 operated motor vehicles 4 is made available, but also mobile devices 24 , compare 1 , especially mobile phones used by users of motor vehicles 4 . 14 be taken with you. Here too, a communication connection can be made 25 for example, a WLAN connection to the server device 18 build, so that the current map data set by, for example, a navigation software application 26 ("App") can be used to guide the user to an exit, a tool and the like, with appropriate instructions on a display 27 can be represented.

It should be noted that also in the mobile terminal 24 a localization function based on environmental data can be realized if corresponding environmental sensors, such as cameras, and / or intrinsic motion sensors, such as acceleration sensors, within the mobile terminal 27 are available, of course, other localization options can be used.

Finally, it should be pointed out that, within the scope of the procedure according to the invention, it is of course also possible to analyze the occupancy state of parking spaces on the basis of the extended map data sets.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited non-patent literature

• "Probabilistic Robotics" by Sebastian Thrun, Wolfram Burgard and Dieter Fox, The MIT Press, ISBN 9780262201629 [0004]

Claims (21)

Method for updating and / or extending a map data set of one of mobile devices ( 3 ) with environmental sensors ( 16 ), limited environment ( 2 ), in particular a parking environment ( 2 ), whereby a current map data record is sent to one within the environment ( 2 ) operated mobile device ( 3 ) and within the institution ( 3 ) for locating the mobile device ( 3 ) within the environment ( 2 ), characterized in that at least one property of at least one feature in the environment (not yet or otherwise contained in the map dataset) is used ( 2 ) descriptive feature data from sensor data of the environmental sensors ( 16 ) of the mobile facilities ( 3 ) and in the mobile facilities ( 3 stored) stored copy of the map data set, after which the thus expanded map data sets to a central, the environment associated server device ( 18 ) and merged there, taking into account the new and / or changed properties to an updated map data record. Method according to claim 1, characterized in that mobile devices ( 3 ) with different environmental sensors ( 16 ) be used. A method according to claim 1 or 2, characterized in that the map data record when entering the environment ( 2 ) to the respective mobile device ( 3 ) and an extended map dataset upon each extension and / or exit from the environment ( 2 ) to the server device ( 16 ) is transmitted. Method according to one of the preceding claims, characterized in that the properties comprise a class and / or position of the feature obtained as a result of a classification. Method according to one of the preceding claims, characterized in that the properties, in particular as a result of a classification, comprise at least one purpose of the feature. A method according to claim 4 or 5, characterized in that as features signs ( 20 ) within the environment ( 2 ) and / or road markings ( 7 . 8th ) and / or parking markings ( 6 . 9 ) and / or aids, in particular fire extinguishers ( 10 ) by identifying a class and / or purpose. Method according to one of claims 4 to 6, characterized in that the classification and / or the determination of the purpose from the sensor data using a in the mobile device ( 3 ) or from the server device ( 18 ) to the mobile device ( 3 ), which allows the mapping of sensor data to at least one class and / or purpose of the feature. Method according to one of the preceding claims, characterized in that the properties are at least partially determined in the context of a localization of the own mobile device ( 3 ), in particular in the context of implementing a SLAM process. Method according to one of the preceding claims, characterized in that an assignment of new and / or changed properties to a feature by a map matching on the basis of predefined features by the server device ( 18 ) he follows. Method according to one of the preceding claims, characterized in that within the environment uniquely identifiable markers for localization of the mobile device ( 3 ) be used. Method according to one of the preceding claims, characterized in that the transmission of the card data sets via a device-to-infrastructure communication, in particular a WLAN communication. Method according to one of the preceding claims, characterized in that as environment sensors ( 16 ) at least one camera ( 22 ) and / or at least one ultrasonic sensor and / or at least one radar sensor and / or at least one lidar sensor are used and / or a scan matching method is used to associate the sensor data with a position in the map dataset. Method according to one of the preceding claims, characterized in that one of the own mobile device ( 3 ) is stored with a trafficability indicative property in the map data record. Method according to claim 13, characterized in that the server device ( 18 ) by comparing it with several mobile devices ( 3 ) traveled roads around the area ( 2 ), in particular road damage and / or danger spots. Method according to one of the preceding claims, characterized in that in the case of a parking environment ( 2 ) current occupancy states of parking lots are determined from the expanded map data records. Method according to one of the preceding claims, characterized in that feature data relating to the same feature of various mobile devices ( 3 ) by the server device ( 18 ) are statistically evaluated, in particular using outlier detection. Method according to one of the preceding claims, characterized in that at least one characteristic of at least one feature contained in the map dataset is replaced by a function of the mobile device ( 3 ) is evaluated, in particular by a driver assistance function. Method according to one of the preceding claims, characterized in that the map data record is sent to a mobile terminal ( 24 ) of a user, in particular a mobile telephone, and is transmitted there as part of a software application ( 26 ), in particular a navigation application is evaluated. Method according to one of the preceding claims, characterized in that for the initial localization of the own mobile device ( 3 ) in the map dataset a predefined, especially at an entrance of the environment ( 2 ) feature is detected. Method according to one of the preceding claims, characterized in that in order to identify the environment ( 2 ) and / or the initial position in the map dataset a GPS position determination is taken into account. Method according to one of the preceding claims, characterized in that as a mobile device ( 3 ) a motor vehicle ( 4 . 14 ) and / or the environment ( 2 ) is a parking garage.

Images