Alarm system for warning vulnerable road users in a predefined road section

Abstract

The invention relates to an alarm system (1) for warning vulnerable road users in a given road section (2) comprising a receiving unit (4) with a communication interface (3) for receiving a plurality of movement data from detected road users relating to the road section (2), wherein a storage unit (10) is provided which has at least three or more prediction modules (5, 6, 7) with descending prediction quality, and wherein the first prediction module (5) is configured to predict at least one position of the detected road users when certain first conditions are met, and wherein the second prediction module (6) is configured to predict at least one position of the detected road users when the first conditions are not met and only certain second conditions are met, and wherein the third prediction module (7) is configured toto predict at least one position of the detected road users if the first conditions as well as the second conditions are not met, and wherein a test module (15) is provided which is designed to check whether the first conditions or the second conditions or the third conditions are met with regard to the road segment (2) and the road user, and in descending order of quality and depending on the conditions met, to select the prediction module (5, 6, 7) with the highest prediction quality, and wherein a processor (16) is provided which is trained to predict at least the future position of the detected road users based on the selected prediction module (5, 6, 7).

Description

[0001] The invention relates to an alarm system for warning vulnerable road users in a given road section, comprising a receiving unit with a communication interface for receiving a plurality of movement data from detected road users related to the road section.

[0002] Collision avoidance is a basic requirement for all drivers of vehicles, such as cars, trucks, and motorcycles, while traveling to a desired destination. It is known in the art to alert a vehicle user to the presence of nearby vehicles by detecting other vehicles with sensors, such as on-board radar systems. However, such systems are limited to detecting other vehicles within the sensor's range, typically within a few vehicle lengths.

[0003] However, there are already approaches to specify a general system for road sections to increase safety on a road network.

[0004] For example, US 9,659,496 B2 discloses a method and system for increasing safety on a road network, comprising: an interaction detector having a communication interface for receiving a plurality of monitoring vectors from a first vehicle and a second vehicle moving on the road network; an interaction risk module configured to determine from the plurality of monitoring vectors whether there is an interaction between the first vehicle and the second vehicle, wherein the interaction is determined without utilizing prior knowledge of a pre-planned route of each of the first vehicle and the second vehicle on the road network; and a message generator configured, in response to the interaction risk module determining an interaction, to generate a message to at least the second vehicle and to send the message to the second vehicle via the communication interface.

[0005] EP 3 690 396 A1 discloses a method for providing an advanced pedestrian assistance system for protecting a pedestrian who is engaged with a smartphone.The method comprises the following steps: the smartphone instructs a positioning unit to acquire first information, including location and speed information of the pedestrian, as well as location and speed information of the smartphone; instructing a recognition unit to acquire second information, including the danger status of hazardous areas near the pedestrian, as well as location and speed information of hazardous objects, with reference to images captured by phone cameras connected to the smartphone and with reference to the first information; instructing a control unit to calculate a pedestrian safety level of the pedestrian based on the first and second information and to transmit a danger warning to the pedestrian via the smartphone. In the non-patent literature "A Survey on Motion Prediction of Pedestrians and Vehicles for Autonomous Driving" (M. Gulzar, Y.Muhammad and N. Muhammad, IEEE Access, Vol. 9, pages 137957–137969, 2021), summarizes the literature on safe automated driving planning for autonomous vehicles. In particular, physics-based, learning-based, or scene-based models for predicting pedestrian and vehicle motion are discussed.

[0006] It is therefore an object of the invention to provide an improved, general, vehicle-independent alarm system for warning vulnerable road users in a given road section.

[0007] This task is solved by an alarm system to warn vulnerable road users in a given road section, comprising a receiving unit with a communication interface for receiving a plurality of movement data from detected road users related to the road section, and wherein a memory unit is provided which has at least three or more prediction modules with descending prediction quality, and wherein the first prediction module is designed to predict at least one prediction of the position of the detected road users when certain first conditions are met, and wherein the second prediction module is designed to predict at least one prediction of the position of the detected road users when the first conditions are not met and only certain second conditions are met, and wherein the third prediction module is designed to predict at least one prediction of the position of the detected road users when both the first conditions and the second conditions are not met,and wherein a test module is provided which is designed to check whether the first conditions or the second conditions or the third conditions are met with regard to the road section and the road user and to select the prediction module with the highest prediction quality in descending order of quality and depending on the met conditions, and wherein a processor is provided which is designed to predict at least the future position of the detected road users based on the selected prediction module.

[0008] Road sections can be the current road sections (locations) or a road section can be used as a representative for others, such as enough similar roundabouts / intersections, etc.

[0009] Road sections can include individual sections of a road network or several roads.

[0010] In particular, the first conditions include the second conditions.

[0011] The alarm system can, for example, be located on an infrastructure element such as a traffic light, on the road section or can be implemented in a cloud or edge cloud, etc.

[0012] The movement data can, for example, originate from the vehicles themselves as recorded sensor data, for example from the surrounding area ahead, or from camera systems that cover the entire road section. These camera systems can, for example, be located in a traffic light. Road users and their associated movement data (trajectories) can be extracted from this sensor data using conventional extraction methods. This sensor data is preferably transmitted and evaluated in real time. From the extracted sensor data, for example, a short past movement trajectory of the road users can be created as movement data.

[0013] The invention recognized that it is a major problem that the current assessment of whether a situation is potentially dangerous is carried out using only very simple methods. This involves either using only the current position of the road users or performing a simple extrapolation of current movement vectors / trajectories. However, this leads to the problem that warnings about dangerous situations are only issued when the road users have already come (too) close to one another. Due to this very late warning, however, it is very difficult or impossible for road users to react, which can even worsen the situation (emergency braking, incorrect evasive maneuvers).

[0014] Another problem is that simply extrapolating motion vectors exclusively only allows for a very inaccurate prediction. This leads to a large number of unnecessarily triggered warnings, which can cause a user / vehicle operator to deactivate such a warning system or unnecessarily distract the vehicle operator from the traffic situation too often, which can itself cause dangerous situations.

[0015] The alarm system according to the invention now resolves these problems. The alarm system according to the invention can very reliably detect the future position of road users. This allows a potentially dangerous situation to be detected more reliably.

[0016] At least three prediction modules with different descending prediction quality are provided, which provide a reliable prediction depending on the conditions that currently apply to the road section and road users.

[0017] It was recognized that the different prediction modules with different prediction qualities each require different prerequisites / conditions. Descending order means that the first prediction module has a higher prediction quality than the second prediction module, and the second prediction module has a higher prediction quality than the third prediction module.

[0018] The alarm system according to the invention always uses the prediction module with the highest prediction quality, in this case the first prediction module with the first conditions, and, if this is not possible because the first conditions are not met, uses the prediction module with fewer conditions, in this case the second prediction module with the second conditions, and only when neither of the first or second conditions is met, uses a third prediction module. This always results in a prediction with the highest prediction quality for this road section, depending on the conditions prevailing on this road section. This allows the position of road users to be predicted more accurately and with greater probability than with the prior art, which also allows future dangerous situations to be determined better and with greater probability.

[0019] In further development, the prediction quality includes at least the probability of occurrence and / or the accuracy of a road user's future position. If a probability of occurrence cannot be determined, it can be roughly estimated. Furthermore, other prediction qualities such as resolution and prediction period can also be included. In particular, the prediction modules are designed to predict the positions of road users as reliably as possible within a period of up to 5 seconds. If the future positions of road users are known, for example, with a resolution of 200 ms and a prediction horizon of 5 s, along with the associated probabilities and accuracies, potentially dangerous future situations can be determined more precisely and reliably.

[0020] In a further development, the movement data includes at least the current and previous position, speed, and direction of a road user over a short period of time, in particular a period of time just past up to a current point in time. Sensor data can be easily and reliably captured in real time using sensors mounted on the vehicle, drones, or cameras / sensors in the corresponding traffic control systems, such as traffic lights, and the movement data can be recognized as an extracted trajectory of the road user from this sensor data.

[0021] In a further refinement, the movement data includes data from other data sources used for traffic management in the relevant road section. The alarm system can thus use additional data sources, provided they are available. For example, the prediction or accuracy of the movement data can be further improved by using data such as current and future traffic light settings.

[0022] In a further embodiment, the first prediction module comprises, as a first condition, a trained artificial neural network for the road section or a sufficiently similar road section, as well as an HD (high-resolution) map for the relevant road section. The first prediction module is designed to predict a road user for the road section based on the trained artificial neural network, the road user's movement data, and the HD map. This allows for a very accurate prediction. An HD map is a high-resolution, high-definition map that contains a current image of reality, including guardrails, trees, ditches, and other traffic-relevant objects such as pedestrian paths and zebra crossings.

[0023] The movement data is input into the trained artificial neural network using the current locations of the road users in the HD map, which provides a highly accurate prediction of the road users. The artificial neural network, which is trained for this type of prediction, has been trained primarily using historical data, enabling an accurate prediction.

[0024] In further development, the artificial neural network is trained only for special cases related to specific road users and their future positions. These special cases could, for example, be a prediction of whether a vehicle will turn or drive straight ahead. Applying this to special cases has the advantage that less historical data is required for training, since the amount of available data is a limitation, especially for the application of machine learning methods.

[0025] In a further embodiment, the second prediction module comprises, as a second condition, an HD map for the road section, wherein the second prediction module is designed to carry out the prediction of a road user for the road section based on the HD map for the road section using the movement data of the road user.

[0026] If no artificial neural network is available for the given road section or a similar section, a prediction can be performed using an existing HD map using the second prediction module. Based on the movement data, i.e., the current and previous positions and directions of movement, possible future positions (future trajectories), for example, on lanes / sidewalks, are determined and assigned probabilities. For this purpose, further movement of the road user is assumed to obtain the future positions and future directions of movement.

[0027] In a further development, a high-precision HD map includes at least the streets, sidewalks, and traffic management elements such as zebra crossings. High-precision HD maps depict a road network with high accuracy, for example, down to the centimeter.

[0028] In a further embodiment, the third prediction module is configured to predict a road user's location on the road section based on an extrapolation using the road user's movement data. This corresponds to a simple extrapolation of the movement vectors / trajectories. This can be used in particular when, for example, a road user is not on a commonly used path, such as when a pedestrian is crossing the road at a prohibited location.

[0029] Furthermore, the processor can be configured to compare the predictions of each road user in pairs to determine potentially dangerous situations in corresponding time steps. If the future positions of the road users are known, for example, with a prediction horizon of 5 seconds, as well as the associated probabilities and accuracies, potentially dangerous future situations can be calculated from this. For this purpose, the predictions of the road users can be compared in pairs for each time step in the future.

[0030] In a further embodiment, the processor is designed to determine the dangerousness of a situation by means of at least one of the following factors: the size of an overlap area between two road users and / or based on a future acceleration of a road user and / or based on a future angle between two road users and / or the time until a possible collision between two road users and / or depending on the lanes used by the road users.

[0031] A larger overlap area between two road users means a higher risk. An increase in the future speed of one of the road users, particularly in the case of significant acceleration, also corresponds to a higher risk. The future angle between the road users can also be considered; for example, an approach directly from behind usually means a low risk, as it can be assumed that the road user approaching from behind will notice the vehicle in front. However, an approach from the side (angle other than zero) or an expected change in direction of travel is assumed to be a higher risk. The time until an expected collision can also be considered; for example, a shorter time until a collision with a more reliable prediction also means less time to react and therefore a higher risk.

[0032] The lanes used by two road users can also be considered; for example, using the same lane is assumed to be a low risk, as one's own lane is usually always in view, and a higher risk is assumed when lanes intersect, especially when a cycle path and a road intersect.

[0033] In particular, a combination of factors can be used to reliably identify a dangerous situation.

[0034] In a further refinement, the processor is designed to consider the type of road user as an additional factor when determining the danger of a situation. Thus, a danger between two pedestrians can be virtually ruled out, even with a very large overlap, for example, at a traffic light. However, a high risk can be assumed if a vehicle / truck is involved.

[0035] Furthermore, in a further embodiment, the processor is configured to evaluate detected dangerous situations using an evaluation value. This can be easily determined based on the identified factors mentioned above, such as the size of the overlap area, etc., i.e., these factors are then used to determine how dangerous future situations are.

[0036] In a further embodiment, the processor is designed to transmit an alarm to at least the road users involved in the dangerous situation once a predefined threshold value in relation to the assessment value is exceeded. If a certain threshold value is exceeded, an alarm is sent to the road users involved. In particular, this alarm comprises at least a message and the assessment value. Therefore, for example, the transmitted alarms with a low assessment value can be additionally filtered out on the road user's end device. This allows the vehicle user to influence how many alarms are displayed. In this way, a risk-averse vehicle user can prevent subjectively receiving too many alarms.

[0037] Further advantages and features of the invention will become apparent from the following description, in which exemplary embodiments of the invention are explained in detail with reference to the drawings. They show schematically: FIG 1 : schematic of the alarm system, FIG 2 : a prediction with the first prediction module, FIG 3 : a prediction with the second prediction module, FIG 4 : a prediction with the third prediction module.

[0038] FIG 1 shows schematically the alarm system 1 for warning vulnerable road users in a given road section 2 ( FIG 2 ). The alarm system 1 can, for example, be integrated at the roadside in an infrastructure element such as a traffic light or in a cloud or edge cloud.

[0039] The alarm system 1 comprises a receiving unit 4 with a communication interface 3 for receiving a large number of movement data from detected road users related to the road section 2. This movement data can be in the form of sensor data or extracted from it, which originates from lidar / radar and camera systems arranged on the vehicles or, for example, from sensor systems arranged on the surrounding infrastructure elements, such as traffic lights. The road users and their movement data, in particular movement trajectories, can be extracted from this sensor data. The extraction and transmission takes place in real time. The movement data comprises at least the current and previous position, speed and direction of a road user over a short period of time with a respective timestamp.

[0040] Alarm System 1 can also utilize additional data sources, if available. For example, the movement data can be further enhanced by using data from current and future traffic light sequences, thus also improving the forecast later.

[0041] Furthermore, the alarm system 1 has a storage unit 10. In At least three prediction modules 5, 6, 7 are stored therein, the first prediction module 5 having the highest prediction quality and the third prediction module 7 having the lowest prediction quality.

[0042] The three prediction modules 5, 6, 7 can be implemented as software modules.

[0043] Furthermore, additional prediction modules can also be stored.

[0044] Each of the prediction modules 5, 6, 7 is configured to predict the position of the detected road users when certain conditions linked to the prediction module 5, 6, 7 are met. Several prediction modules 5, 6, 7 are available for the prediction, each with different prediction quality but also requiring different prerequisites (conditions).

[0045] Prediction quality can be determined based on a resolution, a prediction horizon with associated probabilities, and an accuracy with respect to at least the future position of a road user. High prediction quality includes a high resolution, for example, one of 200 ms, and a prediction horizon of 5 s with associated probabilities and corresponding accuracies.

[0046] The first prediction module 5 is designed to predict at least one prediction of the position of the detected road users if certain first conditions are met.

[0047] The first prediction module 5 requires, as a first condition, a trained artificial neural network 8 for road section 2 or a sufficiently similar road section, as well as an HD map 9 for the relevant road section 2. This means that an artificial neural network 8 must be previously trained for this road section 2, and an HD map 9 must be available. An HD map 9 is a high-resolution, high-definition map that depicts at least the roads, sidewalks, and traffic guidance elements, such as zebra crossings, with high precision and accuracy down to the centimeter.

[0048] The artificial neural network 8 may have been trained using historical data.

[0049] It is also possible to use the first prediction module 5 only for special cases, such as predicting whether a vehicle will turn or drive straight ahead. Applying it to special cases has the advantage that less historical data is required for training, thus saving time and money.

[0050] The second prediction module 6 is configured to predict at least one prediction of the position of the detected road users if the first conditions are not met and only certain second conditions are met. The second conditions correspond to the presence of an HD map 9 for the corresponding road section 2. Based on the current and previous positions and directions of movement, possible lanes are calculated and assigned probabilities. Further movement of the road user on the detected lanes is then assumed to obtain the future positions and directions of movement.

[0051] Furthermore, the third prediction module 7 is configured to predict a road user's location on road section 2 based on an extrapolation using the road user's movement data. This can also be accomplished without an HD map 9 and without an artificial neural network 7. This corresponds to a simple extrapolation of the movement vectors / trajectories. This can be used in particular when, for example, a road user is not on a commonly used path, for example, when a pedestrian crosses the road at a prohibited location.

[0052] Furthermore, a test module 15 is provided which is designed to check whether the first or the second or the third conditions are present with regard to the road section 2 and the road user and, in doing so, selects the corresponding prediction module 5, 6, 7 in descending quality order and depending on the existing conditions.

[0053] The testing module 15 therefore always attempts to use the first prediction module 5 first, since this has the highest prediction quality, and only then, if the first conditions such as artificial neural network 8 are not met, to resort to the second prediction module 6 with the second conditions, here the HD map 9. If no HD map 9 is available for the road section 2 either, the third prediction module 7 is resorted to.

[0054] This means that the prediction module 5,6,7 with the highest prediction quality is always used, and only if this is not possible because the conditions for it are not met, the next lower prediction module 6,7 is used.

[0055] In a traffic situation, different prediction modules 5,6,7 can be used for different road users.

[0056] Subsequently, a prediction of at least the future position of the detected road users is generated by means of a processor 16 using the selected prediction module 5, 6, 7 for the road users.

[0057] If the future positions of the road users are known, for example, with a resolution of 200 ms and a prediction horizon of 5 s, with associated probabilities and accuracies, by the prediction modules 5, 6, 7, potentially future dangerous situations 12 can be determined by the processor 16. For this purpose, the predictions of the road users are compared in pairs by the processor 16 for each time step in the future.

[0058] To determine a dangerous situation 12 between road users, the processor 16 can use the following factors individually, but preferably in combination: the size of the overlap of a calculated area of ​​​​presence of road users. For example, a larger overlap area between two road users means a higher risk, the position of the overlap relative to the estimated position. For example, an overlap closer to the center of the estimated position means a higher risk, the future speed of the road users; for example, a higher speed, especially a significant acceleration, means a higher risk, an existing or future angle between the road users, for example, an approach directly from behind usually means a low risk, as it can be assumed that the road user approaching from behind has noticed the vehicle in front.However, when approaching from the side or when the direction of travel is expected to change, a higher risk is to be assumed, consideration of the lanes used by two road users; when using the same lane, a low risk is assumed, as one's own lane is usually always in sight, and a higher risk is assumed for intersecting lanes, particularly when a cycle path and a road intersect, a time until the expected collision; a shorter time until the collision means less time to react with a more reliable prediction and therefore a higher risk, the same or different type of road user; a danger between two pedestrians can be almost ruled out even with a very large overlap, for example at a traffic light, but a high risk is to be assumed if a vehicle / lorry is involved.

[0059] Furthermore, in a further embodiment, the processor 16 is configured to evaluate detected dangerous situations 12 using an evaluation value. This can be easily determined based on the identified factors above, such as the size of the overlap area, etc., i.e., an evaluation of how dangerous the future situation 12 is is now calculated from these factors.

[0060] If a certain threshold value is exceeded, the processor 16 sends a message as well as the evaluation value as an alarm to the road users involved.

[0061] This allows these alerts to be filtered on the road user's device based on their rating. For example, all alerts with an assessment value that is too low for the individual road user can be filtered out. This allows the road user to influence how many warnings are displayed. This allows a risk-averse road user to avoid subjectively receiving too many warnings.

[0062] FIG 2 shows a prediction with the first prediction module 5.

[0063] In this scenario, a car 13 coming from the east turns north and crosses the path of a cyclist 14, also coming from the east. The bicycle symbol 14 and the car symbol 13 represent the current positions of the road users involved.

[0064] The blue ellipses 11 represent the predicted locations of the bicycle 14 and the car 13.

[0065] In this example, an artificial neural network 8 was trained using historical data to determine whether a vehicle is traveling straight ahead or turning at this intersection based on the approach speed. The current movement data is then input into the thus trained neural network 8, which, using the HD map 9 for this intersection, generates predictions for both the car 13 and the cyclist 14.

[0066] The first prediction module 5 with the trained artificial neural network 8, which uses an HD map 9, can now detect early on that the car 13 will turn and thus a dangerous situation 12 will arise.

[0067] By using the first prediction module 5, a high prediction quality and, accordingly, a reliable forecast of the future positions of road users can be achieved. Thus, dangerous situations 12 can be detected accurately, reliably, and in a timely manner.

[0068] FIG 3 shows a prediction of the above scenario with the second prediction module 6. In this scenario, the car 13 coming from the east turns north and crosses the path of the cyclist 14, who is also coming from the east. The bicycle symbol 14 and the car symbol 13 represent the current positions of the road users involved. The blue ellipses 11 represent the predicted locations of the bicycle 14 and the car 13.

[0069] In this example, the prediction is made by the second prediction module 6 using the HD map 9. At this point, it can already be predicted that the car 13 could turn right, thereby creating a dangerous situation 12. However, there is uncertainty as to whether this will actually happen, as it is also possible that the car 13 will continue on its way in a straight line. By using the second prediction module 6, a medium prediction quality and, accordingly, a medium-reliable prediction for the future positions of road users can be achieved. This allows dangerous situations to be detected.

[0070] FIG 4shows a prediction of the above scenario with the third prediction module 7. In this same scenario, the car 13 coming from the east turns north again and crosses the path of a cyclist 14, also coming from the east. The bicycle symbol 14 and the car symbol 13 represent the current positions of the road users involved. The blue ellipses 11 represent the predicted locations of the bicycle 14 and the car 13.

[0071] In this example, the prediction is made by the third prediction module 7 by extrapolating the past and current motion vectors / motion data. The third prediction module 7 does not recognize that the car 13 will soon turn right. Accordingly, no alarm is issued.

[0072] By means of the alarm system 1 according to the invention with the at least three prediction modules with descending prediction quality, a potentially dangerous situation 12 can be better detected by always using the best possible prediction module 5, 6, 7 to determine the future positions of the road users. List of reference symbols:

[0073] 1 Alarm system 2 Road section 3 Communication interface 4 Receiving unit 5 First prediction module 6 Second prediction module 7 Third prediction module 8 Artificial neural network 9 HD map 10 Storage unit 11 Blue ellipses 12 Dangerous situation 13 Car 14 Bicycle 15 Test module 16 Processor

Claims

1. Alert system (1) for warning vulnerable road users in a given road section (2), comprising a receiver unit (4) with a communications interface (3) for receiving a multiplicity of movement data of detected road users in relation to the road section (2), characterized in that a memory unit (10) is provided, the latter having at least three or more prediction modules (5, 6, 7) with a decreasing prediction quality and the first prediction module (5) being designed to make at least one prediction of the position of the detected road users if specific first conditions are satisfied and the second prediction module (6) being designed to make at least one prediction of the position of the detected road users if the first conditions are not satisfied and only specific second conditions are satisfied, and the third prediction module (7) being designed to make at least one prediction of the position of the detected road users if the first conditions and the second conditions are not satisfied, and wherein a test module (15) is provided, the latter being designed to test whether the first conditions or the second conditions or the third conditions are satisfied in relation to the road section (2) and the road user and, in sequence of decreasing quality and depending on satisfied conditions, to select the prediction module (5, 6, 7) with the highest prediction quality, and wherein a processor (16) is provided, the latter being designed to predict at least the future position of the detected road users on the basis of the selected prediction module (5, 6, 7).

2. Alert system (1) according to Claim 1, characterized in that the prediction quality at least comprises the probability of occurrence and / or the accuracy of a future position.

3. Alert system (1) according to either of the preceding claims, characterized in that the movement data at least comprise the current and previous position, speed and direction of a road user over a short period of time.

4. Alert system (1) according to Claim 3, characterized in that the movement data comprise data from further data sources that serve for routing traffic in the relevant road section (2).

5. Alert system (1) according to any of the preceding claims, characterized in that the first prediction module (5) comprises a trained artificial neural network (8) for the road section (2) or a sufficiently similar road section (2) and an HD map (9, high definition map) for the relevant road section (2) as first conditions, and wherein the first prediction module (5) is designed to make the prediction on the basis of the trained artificial neural network (8) for a road user for the road section (2) using the movement data of the road user and the HD map (9).

6. Alert system (1) according to Claim 5, characterized in that the artificial neural network (8) is trained using historical data.

7. Alert system (1) according to Claim 5 or 6, characterized in that the artificial neural network (8) is only trained for special cases in relation to specific road users and their future positions.

8. Alert system (1) according to any of the preceding claims, characterized in that the second prediction module (6) comprises an HD map (9) for the road section (2) as its second condition, wherein the second prediction module (6) is designed to make the prediction in relation to a road user for the road section (2) on the basis of the HD map (9) for the road section (2), using the movement data of the road user.

9. Alert system (1) according to any of preceding Claims 4 to 8, characterized in that the HD map (9) at least comprises the roads and the pedestrian paths and the traffic routing elements.

10. Alert system (1) according to any of the preceding claims, characterized in that the third prediction module (7) is designed to make the prediction in relation to a road user for the road section (2) on the basis of an extrapolation using the movement data of the road user.

11. Alert system (1) according to any of the preceding claims, characterized in that the processor (16) is further designed to compare the prediction in relation to each road user in pairwise fashion in order to determine potentially hazardous situations in corresponding time steps.

12. Alert system (1) according to any of the preceding claims, characterized in that the processor (16) is designed to determine the hazardousness of a situation by means of at least one of the following factors: the size of an overlap region between two road users and / or on the basis of a future acceleration of a road user and / or on the basis of a future angle between two road users and / or the time to a potential collision between two road users and / or on the basis of the lanes used by the road users.

13. Alert system (1) according to Claim 12, characterized in that the processor (16) is designed to take account of the type of road user as a further factor when determining the hazardousness of a situation.

14. Alert system (1) according to any of the preceding claims, characterized in that the processor (16) is designed to assess recognized hazardous situations by means of an assessment value.

15. Alert system (1) according to Claim 14, characterized in that the processor (16) is designed to transmit an alert to at least the road users involved in the hazardous situation once a given threshold value in relation to the assessment value has been exceeded.

16. Alert system (1) according to Claim 15, characterized in that the alert comprises at least a notification and the assessment value.

Images