Method and system for determining a navigation route of a vehicle

Abstract

The invention relates to a method for determining a navigation route (1) of a vehicle, in which further road users (2) are detected by means of a sensor system (3), and sensor data generated by the sensor system (3) are evaluated by a computing device (4) in order to determine the behavior of the respective road user (2) in the road traffic. The method according to the invention is characterized in that the computing device (4) stores a database (5) comprising behavior limit values; -the computing device (4) compares the behavior observed by the road user (2) with the behavior limit values stored in the database (5) and counts the events (E) on the road section on which the road user (2) stays if the respective observed behavior of the road user (2) exceeds the associated behavior limit value; -the computing device (4) computes a hazard index (GI) for at least one road section as a function of the number and value of events counted over the respective road section over the specified time period; and-the navigation unit takes into account the risk index (GI) assigned to the respective route section for route planning, the route section of which the risk index (GI) exceeds a specified risk index threshold value being avoided in order to determine the navigation route (1).

Description

Technical Field

[0001] The present invention relates to a method for determining a navigation route for a vehicle of the type defined in more detail in the preamble of claim 1 and a system of the type defined in more detail in the preamble of claim 12. Background Technology

[0002] Participating in road traffic always carries the risk of accidents. In the future, with increased vehicle automation, and even fully autonomous control, this risk will decrease. The risk of accidents varies depending on the road segment and time of day. It may increase, particularly on busy roads and in challenging environments, such as construction sites or areas with a so-called "forest of signs." Furthermore, people are more or less capable of driving safely. Therefore, if someone on the road has poor vehicle control or tends to drive recklessly, the risk of an accident increases.

[0003] Vehicle users are striving to avoid stressful driving situations and accidents, which necessitates providing means to improve safety in road traffic.

[0004] DE 10 2021 000 596 A1 discloses a method for adjusting the driving behavior of a vehicle. This publication describes the observation of other road users and the determination of an individual road user's acceleration or deceleration capability based on those observations. Your own vehicle's driving behavior is adapted to the identified acceleration or deceleration capability. For example, if a slow-moving vehicle is detected to have only low mobility, an overtaking maneuver can be initiated at an appropriate location. Other road users can be detected via sensors installed on static infrastructure, vehicles in a fleet, or your own vehicle.

[0005] In addition, DE 10 2019 103 554 A1 describes an apparatus for detecting potential hazard curves.

[0006] Furthermore, DE 10 2018 217 828 A1 discloses a method and apparatus for adapting driving behavior to partially automated, highly automated, or fully automated vehicles. In this case, the driving behavior is adjusted based on internal data, wherein the internal data describes the safety status of the vehicle occupants, particularly the risk of injury.

[0007] Furthermore, US 2018 / 0107942 A1 discloses a framework for learning group-specific driving styles for autonomous vehicles. In this framework, the driving behavior of vehicles traveling around the autonomous vehicle is detected. Information describing the corresponding driving behavior is transmitted from the autonomous vehicle to a server. The server categorizes the driving behavior based on this information and then instructs the autonomous vehicle how it should behave to mimic the driving behavior. Summary of the Invention

[0008] The purpose of this invention is to provide an improved method for determining a vehicle's navigation route, by which the vehicle can be controlled particularly safely through road traffic.

[0009] According to the invention, this objective is achieved by a method for determining a vehicle's navigation route having the features of claim 1. Advantageous designs and improvements, as well as a system for performing the method, are derived from the relevant claims.

[0010] According to the present invention, an improved method for determining a vehicle's navigation route is provided, wherein additional traffic participants are detected by means of a sensor system, and sensor data generated by the sensor system is evaluated by a computing device to determine the behavior of the respective traffic participants in road traffic. - The computing device stores a database containing behavioral limit values; - The computing device compares the behavior observed by traffic participants with the behavior limits stored in the database, and if the corresponding observed behavior of a traffic participant exceeds the associated behavior limit, the event is counted on the road segment where the traffic participant is located; - The computing device calculates the hazard index of at least one road segment based on the number and value of events counted on the corresponding road segment within a specified time period; and - The navigation unit considers the hazard index assigned to the corresponding road segment for route planning, wherein, in order to determine the navigation route, road segments with hazard indices exceeding the prescribed hazard index threshold are avoided.

[0011] The method according to the invention allows for the identification of potentially hazardous road sections, which can then be omitted to determine the navigation route. Thus, vehicles are guided along safe road sections to their respective destinations, increasing driver comfort by avoiding stressful driving situations and reducing the general risk of accidents.

[0012] Vehicle users can program their navigation routes before embarking on their respective journeys. For this purpose, a vehicle-integrated navigation system is preferably used. Alternatively, a dedicated mobile terminal, such as a mobile navigation system or a smartphone with a navigation application, can also be used. The corresponding navigation unit, particularly in the form of the navigation system, then establishes a communication link to a computing device and obtains the corresponding hazard index for road segments that may be suitable for the navigation route.

[0013] Computing devices can also be integrated into vehicles. In this case, several computing devices implemented in different vehicles can collaborate as a single large computing device. A central computing device, i.e., a server or a network of servers, is particularly preferred.

[0014] In this context, sensor systems used to observe traffic participants can be integrated into static infrastructure, vehicles in a fleet, and / or even your own vehicle. Possible sensor systems include, for example, cameras, laser scanners (e.g., LiDAR), radar systems, and / or ultrasonic sensor systems. With the help of such sensor systems, depth information can be obtained, allowing scanning of the surrounding environment. Therefore, a computer-usable representation of the environment can be generated. Using image recognition algorithms, i.e., machine vision, the situation can be analyzed, classified, and evaluated in particularly different ways. Other sensor systems from the vehicle, such as acceleration sensors, wheel speed sensors, etc., can also be used. Therefore, sensor data can also be extracted from driver assistance systems such as ABS, ASR, airbag control units, etc. For example, vehicle speed, acceleration, accident occurrence, wheel rotation recognition, etc., can be determined.

[0015] It can also identify and track specific vehicles on road traffic using visual features. Furthermore, it can identify external boundary conditions, such as being in a construction site area, identifying marked forests, or the presence of adverse weather and / or visibility conditions.

[0016] Other traffic participants can also be vehicles, such as cars, trucks, vans, buses, or mini-vehicles, such as bicycles, scooters, skateboards, etc. Pedestrians can also be identified and considered as traffic participants.

[0017] The behavior of traffic participants can be assessed in specific ways. To specifically assess behavior, the driving (or walking) actions exhibited by the respective traffic participants can be evaluated. For example, this involves the acceleration and steering behavior of traffic participants, i.e., the degree to which the respective traffic participant accelerates or decelerates, or the suddenness of a steering maneuver. Furthermore, for example, the distance maintained with other traffic participants and / or the current speed of movement can be detected and assessed. Behavioral limits stored in a database are associated with the detectable behaviors. In this case, behavioral limits dependent on corresponding boundary conditions of the environment or driving situation can be defined. For example, the current speed limit of the road segment being traveled on can be used as the behavioral limit for the maximum tolerable speed of the traffic participant. Different road segments have different speed limits, and therefore different road segments may also have different behavioral limits. In the case of highway entrances or exits, behavioral limits with higher tolerance for vehicle acceleration than, for example, in urban traffic can be considered accordingly.

[0018] Other examples of observable and assessable behaviors include: following closely behind the vehicle in front, reckless overtaking, improper use of high beams, ignoring one-way streets, crossing lane markings or the median strip, honking illegally, making malicious gestures, driving in the emergency lane, and crossing an intersection before the yellow light has ended or even when the light is red.

[0019] The vehicle itself can be equipped with a device to detect driver fatigue or distraction, so that road sections where fatigued or distracted drivers are stationed in particular can be assessed as dangerous road sections.

[0020] Your own vehicle can be positioned relative to its environment in road traffic. With the help of the sensor system, other road users can be detected. Therefore, the relative distance to other road users can be determined from the depth information, and from this, the corresponding distance and speed of other road users can be derived, thus leading to corresponding behaviors.

[0021] In this context, the hazard index comprises the absolute number and value of events identified on a given road segment within a specified time period. For example, each event can be assigned a numerical value. The more severe the event, the higher the value may be.

[0022] The specified time period can be selected in different ways depending on various boundary conditions. For example, the specified time period can be several hours, days, weeks, or even months or years. The specified time period can also include the entire past observation period, i.e., from the start of the behavioral observation to the current point in time. For example, the specified time period can also depend on traffic density. Therefore, when a particularly large number of traffic participants are on a road segment, such as during peak hours, a different high-risk index can be determined for the same road segment compared to periods with low traffic volume. Changes in the road network can also be taken into account. For example, if a road segment is closed, for example due to necessary construction work, this may cause traffic participants to choose their preferred escape routes. Once a closure occurs, the risk index of the road segment with the preferred escape route can be recalculated. Accordingly, the specified time period coincides with the road closure period.

[0023] The specified time period can also be designed as a sliding time range, such as the last 15 minutes. To determine the risk level, historical data can also be considered; for example, the same time window can be viewed every day, such as from 8 a.m. to 10 a.m., and an average of several days can be generated for the corresponding time window.

[0024] The hazard index can be expressed as any desired value, such as ranging from 0 to 1.0 to 10.0 to 100. For example, a hazard index of 0 corresponds to a safe road section, while a hazard index of 1, 10, or 100 corresponds to a particularly dangerous road section.

[0025] The hazard threshold can also be selected at different heights depending on different conditions. Therefore, the hazard threshold for a road segment can be set manually by the user of the navigation unit, for example, by setting it to 5, 6, or 7. The hazard threshold can also be selected automatically, for example, based on the number of available avoidance routes. If many avoidance routes are considered, a particularly low hazard threshold can be selected so that one of the possible avoidance routes is preferably used. However, if few potential avoidance routes are available, the hazard threshold can be increased so that it is still preferable to drive on potentially hazardous road segments.

[0026] If the driver deviates from the navigation route set in this way and drives on a road where the hazard index exceeds the set hazard index threshold, a warning message can be issued in the vehicle, such as by emitting certain warning sounds or flashing certain warning lights, or by displaying a visual warning message on a display device.

[0027] Particularly dangerous road sections, those that frequently exhibit a relatively high risk index, can also be communicated to third parties. For example, situations where behavioral limits are frequently exceeded can be reported to traffic authorities. This allows traffic authorities to implement appropriate safety measures. For instance, devices for controlling driving speed, such as speed cameras, can be increasingly installed.

[0028] An advantageous improvement to the method according to the invention provides that, when a behavioral limit value is exceeded, the computing device assigns an assessment to the corresponding traffic participant and considers the assessments of traffic participants who remained on the road segment within a specified time period to calculate a hazard index. Therefore, traffic participants who contribute to an increase in the risk or hazard of a road segment can be identified. These traffic participants can be tracked in time and location, allowing for particularly reliable real-time adjustment of the hazard index for a specific road segment. For example, if there are currently a particularly large number of traffic participants with particularly high ratings on the corresponding road segment, the corresponding hazard index may also increase. The assessments also have values. For example, the hazard index of a road segment may also include the values ​​of all assessments currently added together on the corresponding road segment. High assessments can be tolerated before increasing the hazard index, for example, based on the length of the corresponding road segment, because there tends to be more vehicles on longer road segments than on shorter ones. Since vehicle density remains similar, more “dangerous” drivers can be tolerated on longer road segments.

[0029] According to another advantageous embodiment of the method according to the invention, the value of the event to be assigned to a road segment and / or the value of the assessment to be assigned to a traffic participant depends on the degree to which the associated behavioral limit value is exceeded. Therefore, if some traffic participants behave particularly recklessly, the danger of traveling on the road segment where the corresponding traffic participant is located will also increase. For example, road segments or traffic participants exceeding the current speed limit by, for example, 40%, are assigned events or assessments with higher values ​​than road segments or traffic participants exceeding the current speed limit by, for example, only 10%. This makes it possible to determine the corresponding danger index for the corresponding road segment with particular accuracy. Thus, for example, the danger index is determined relative to the corresponding road segment within a specified time period by summing the events multiplied by the corresponding values.

[0030] Another advantageous embodiment of the method according to the invention provides that the behavioral limits are determined according to applicable road traffic regulations. In each country, applicable road traffic regulations specify which behaviors are permitted and which must be punished in road traffic. Therefore, by selecting behavioral limits according to applicable road traffic regulations, limits applicable to the respective country can be defined. For example, different speed limits apply to different types of roads, such as urban roads, rural roads, or highways, for example, 50 km / h, 100 km / h, or 130 km / h. For example, a safe distance dependent on driving speed can be specified, and that distance can be taken into account accordingly. For example, relevant road traffic regulations may also specify in what circumstances honking the horn is permissible, the use of high beams, or that fines can be imposed for obscene gestures such as raising the middle finger.

[0031] According to another advantageous design of the method according to the invention, the computing device assigns events to road segments, the value of which depends on the current total number of traffic participants on the road segment, the average distance between traffic participants, particularly considering their standard deviation, and / or depends on the number of lane changes determined on the road segment within a specified time period. This makes it possible to more accurately determine the hazard index of the corresponding road segment, thereby more accurately assessing the risk of the corresponding road segment. Generally, if the traffic density of a road segment increases, the risk of an accident also increases. If traffic participants are particularly close to each other, the risk of rear-end collisions also increases. If some traffic participants deviate significantly from the behavior of other traffic participants, for example by maintaining excessively large or small safe distances, this may further increase the risk of accidents. Lane changing is a particularly dangerous traffic maneuver, especially in urban traffic, because it requires careful observation of traffic behind to prevent collisions with another traffic participant who is stuck in a blind spot. If a particularly large number of lane changes are detected on a specific road segment within a specific time interval, it also indicates that particularly risk-taking drivers are staying on the corresponding road segment.

[0032] Another advantageous embodiment of the method according to the invention provides that the computing device determines from sensor data the characteristics of the situation present when behavioral limits are exceeded, and executes a machine learning model that establishes a link between the determined characteristics of the situation and the corresponding exceedance of the corresponding behavioral limits. In this case, the characteristics of the situation describe the boundary conditions present in the corresponding traffic situation, such as low sunlight, vehicle user operation of radios, lingering at construction sites, being distracted by mobile terminals such as smartphones, etc. The characteristics of the situation can be determined from sensor data using proven methods. Machine vision methods are particularly useful for this purpose. Artificial intelligence-based analytical methods can also be used.

[0033] Then, using artificial intelligence in the form of machine learning models, a correlation is established between the characteristics of the situation present in the corresponding circumstances when the behavioral limit is exceeded. Therefore, the computing device can identify situations associated with particularly high hazard indices, thereby identifying accident risks. For example, if adverse visibility conditions exist, such as due to wet roads and low sunlight, the computing device can increase the hazard index before the corresponding behavioral limit is exceeded.

[0034] According to another advantageous design of the method according to the invention, it becomes possible to predict the hazard index of at least one road segment within a future timeframe using a computing device. If a vehicle user plans to travel from a starting point to a destination, in order to determine a navigation route, not only the current hazard index of the road segment can be considered, but also the hazard index that may occur when the vehicle reaches the corresponding road segment. This allows for a more accurate assessment of the potential risks of each road segment, thereby determining a more comfortable and safer navigation route. For example, if the discovered navigation route only includes road segments with a high hazard index due to increased traffic volume during peak hours near the end, but the peak hours have passed when the vehicle reaches those road segments, then those road segments can still be included in the navigation route because a low hazard index exists when the vehicle reaches them.

[0035] Predicting risk indices is possible even without using machine learning models. For example, the history of hazard indices established for a given road segment can be considered. Thus, for instance, an average hazard index occurring on the road segment within a specific time period can be generated. For this purpose, for example, for each road segment at each hour of the day, such as from 8:00 AM to 9:00 AM and from 9:00 AM to 10:00 AM, etc., the hazard index set for the corresponding time window on that road segment over the past seven days can be used to generate an average. For example, the hazard index at 10:45 AM can be predicted as early as 8:30 AM.

[0036] If an assessment is assigned to a traffic participant, a predicted navigation route can also be determined for that participant. For this purpose, for example, the navigation route set in the corresponding traffic participant's vehicle can be acquired and analyzed from a computing device, or the corresponding navigation route can be estimated. For example, if a lane change from the left lane to the right lane and a decrease in speed are detected on a highway, the computing device can thus estimate that the corresponding traffic participant will soon exit the highway. Therefore, when a risk-taking traffic participant leaves, the hazard index of the highway segment after the exit can be reduced, and the hazard index of, for example, the segment of rural road after the exit can be increased.

[0037] Another advantageous embodiment of the method according to the invention provides that the computing device determines from sensor data the characteristics of the situation present when behavioral limits are exceeded, and adjusts the height of at least one behavioral limit based on at least one characteristic of the situation. This makes it possible to tolerate “bad” or “illegal” driving behavior depending on the specific circumstances, if such illegal behavior is common or unavoidable due to external conditions. For example, if a vehicle frequently brakes particularly suddenly at a particular traffic light, this may be due to the brief green phase of the traffic light, rather than due to the risky driving style of the relevant road users. With this in mind, the hazard index cannot be increased accordingly for road sections containing these traffic lights. However, since this is often likely to be an unexpected driving maneuver, the hazard index can also be selectively increased. The preferred process can also be set, for example, by the user according to their preferences.

[0038] According to another advantageous design of the method according to the invention, when the distance-related length and / or time-related length of at least one segment of the navigation route calculated taking into account a hazard index exceeds a predetermined length threshold, the navigation unit increases the predetermined hazard index threshold for at least one segment of the navigation route determined without considering the hazard index, and then recalculates the navigation route. This allows the user to define a preference for tolerable detours or the resulting time delays, such that if the detour is too long, the navigation route still runs along potentially dangerous segments. To this end, a “normal” navigation route is first determined, i.e., a navigation route calculated according to a standard method. This is used as a comparison to determine the increase in path length in terms of distance and time to the navigation route determined taking into account the hazard index. The user can specify the tolerable degree of redirection in various ways. For example, the user can preset absolute distance-related and / or time-related tolerances. For example, the user can input that the navigation route determined taking into account the hazard index can be a few minutes, a few hours, or even a fraction or multiple thereof. This value can also depend on the total length of the navigation route; for example, due to redirection, the navigation route may become longer in terms of distance and / or time by up to 5%, 10%, or a fraction or multiple thereof. The user can also specify the hazard index and the rate of increase in permissible length. For example, a driver can specify routes to avoid with a hazard index > 0.7, increasing travel time or route length by up to 20%. Therefore, if the navigation route initially determined based on the hazard index is too long (exceeding the length threshold), the navigation unit increases the hazard index threshold for at least some road segments. Consequently, road segments that, despite having an increased hazard index, contribute to shorter travel time or distance are more likely to be included in the newly calculated navigation route.

[0039] If it is not possible to calculate a suitable navigation route while adhering to user-specified boundary conditions, the navigation unit can also output an error message, such as: "No matching navigation route with default settings found".

[0040] Another advantageous embodiment of the method according to the invention provides that the vehicle follows the navigation route in a manner that is at least partially automated. The vehicle can be at least partially automated or autonomously controlled. Therefore, the vehicle is able to follow the navigation route determined by the navigation unit, either independently or at least with assistance. The vehicle then travels on road sections where the risk of traffic accidents is reduced due to a lower hazard index. Thus, the risk of the at least partially automated vehicle being involved in an accident is reduced. This makes the at least partially automated vehicle safer to operate.

[0041] According to another advantageous design of the method according to the invention, vehicles with an increased risk index adopt increasingly defensive driving behaviors. For vehicles with at least partial automatic control, this can also reduce the risk of involvement in accidents. For example, the vehicle behaves "particularly cautiously" on dangerous road sections, thus maintaining a reduced speed, which can shorten braking distance and / or increase safe distance, thereby reducing the risk of rear-end collisions.

[0042] According to the invention, in a system comprising a sensor system, at least one vehicle, a computing device, and a navigation unit, the sensor system, vehicle, computing device, and navigation unit are configured to perform the aforementioned method. The sensor system may be part of a fixed infrastructure, integrated into vehicles in a fleet, or integrated into vehicles performing a journey along a navigation route. The vehicle may be any desired road vehicle, such as a car, truck, transport vehicle, bus, etc. The navigation unit may be a dedicated navigation system. The navigation unit may also be implemented by special navigation software running on the computing device. For this purpose, the navigation unit can determine the current location of the vehicle or the navigation unit separately by means of a location determination device. The computing device may be integrated into the vehicle. However, the computing device may also be designed as a central computing device external to the vehicle, such as a cloud server. The computing units integrated into the vehicles of the fleet may also collaborate as large, interconnected computing devices. Attached Figure Description

[0043] Other advantageous designs of the method for determining a vehicle's navigation route according to the invention and the system according to the invention can also be obtained from the embodiments described in more detail below with reference to the accompanying drawings.

[0044] in: Figure 1 A schematic plan showing the traffic situation is provided; Figure 2 A bar graph showing the dependence of the hazard index on the number and value of instances exceeding behavioral limits on a road segment within a specified time period is displayed; and Figure 3 A schematic diagram of a digital route map with two navigation routes having different definitions is shown. Detailed Implementation

[0045] By means of the invention for determining Figure 3 The method of navigating route 1 for the vehicle shown can avoid potentially dangerous road sections, thus allowing the vehicle to navigate road traffic with exceptional safety. In this case, the vehicle can be manually, at least partially automated, or even autonomously controlled.

[0046] The method according to the invention is based on observation by means of sensor system 3 Figure 1 The behavior of traffic participant 2 is shown. In this case, the sensor data generated by sensor system 3 is evaluated by computing device 4, for example, in... Figure 1 The text indicates a cloud server. For example... Figure 1 As shown, sensor system 3 can be integrated into fixed infrastructure and / or can be part of a corresponding vehicle involved in a traffic event.

[0047] The computing device 4 includes a database 5 storing behavioral limit values. In this case, the corresponding behavioral limit values ​​describe the permissible behavior of traffic participants 2 in a traffic event using specific reference values, such as maintaining a specific driving speed, a specific minimum distance between each other, the number of overtaking maneuvers performed per unit time, and the limit value of tolerable acceleration. Preferably, the behavioral limit values ​​are determined according to the applicable road traffic regulations of their respective countries.

[0048] exist Figure 1 In the illustrated embodiment, a vehicle 6.2 following a vehicle 6.3 traveling in the overtaking lane descends to a minimum distance predefined according to behavioral limits. This overtaking is recorded by cameras mounted on fixed infrastructure and cameras on the vehicle itself 6.1. The following vehicle 6.2 has distance radar, which also detects distances below the minimum. The individual traffic participants 2 and the static infrastructure transmit sensor data generated by the sensor system 3 to a computing device 4 for evaluation. This can be done wirelessly or via wired means. Specifically, the traffic participants 2 transmit sensor data wirelessly, while the fixed infrastructure transmits it via wired means.

[0049] The computing device 4 determines the corresponding behavior of traffic participant 2 from sensor data and compares it with the behavior limits stored in the database 5. Then, the computing device 4... Figure 2 The event E shown is assigned to road segments where a behavior limit value is exceeded. Preferably, the value of event E is selected based on whether the behavior limit value is exceeded. This means, for example, that the closer the following vehicle 6.2 is to the minimum distance from the preceding vehicle 6.3, the larger the value of event E. For example, if the following vehicle 6.2 is less than 1 meter from the minimum distance, the value of event E could be "2". However, if the following vehicle 6.2 is less than, for example, 5 meters from the minimum distance, the value of event E could be "3" or higher.

[0050] Computing device 4 aggregates the corresponding events E for each road segment within a time period defined separately for that road segment. Based on the quantity and value, computing device 4 determines... Figure 2 The danger index GI is shown.

[0051] Figure 2 An exemplary implementation illustrating the dependence of the hazard index GI on the corresponding event E (ExW) multiplied by the value W is shown. The hazard index GI is plotted on the horizontal axis of the graph, and the event E multiplied by the value W is plotted on the vertical axis. The value 30 on the vertical axis can be achieved through any conceivable combination of events and associated values, for example, through 30 events with a value of 1 or 10 events with a value of 3. For example, all events E multiplied by the value determined within a specified time period on a predetermined road segment would be summed. Figure 2 As shown, the hazard index GI increases gradually as the value of event E is multiplied by the value W. A continuous increase, as shown in Figure 7, is also possible. The hazard index GI can also increase gradually or decreasingly (not shown) as event E multiplied by the value W. Hazard indices on predetermined road segments determined from historical data between 8:00 AM and 9:00 AM on weekdays are indicated by shaded bars as examples.

[0052] Various formulas and rules can be defined to determine the hazard index GI based on the number and value of events E in the corresponding road segment. Different rules may also apply to different road segments. For example, it is preferable to assign a separate assessment to the corresponding traffic participant 2, which is accordingly included in the hazard index GI of the road segment in which the corresponding traffic participant 2 is currently located.

[0053] The navigation unit considers the hazard index (GI) determined in this way for route planning. Figure 3 The diagram shows the initially calculated navigation route 1.1, without considering the hazard index GI, and navigation route 1.2, calculated with the hazard index GI in mind. For each road segment, the hazard index GI appearing on that segment is plotted. For example, 0.6 is stored as the hazard index threshold. This results in road segments with a hazard index GI of 0.7 being excluded from navigation route 1.2, and corresponding detours are suggested. In this case, the user can specify how high the corresponding hazard index threshold should be, specifically as the ratio of the tolerance increase in distance or time-related length to the hazard index threshold. Therefore, potentially hazardous road segments can still be included in the corresponding navigation route 1 if the increase in travel distance or time due to including detours is too high.

[0054] The navigation unit can be integrated into the vehicle or configured as a dedicated mobile terminal. Therefore, a mobile navigation system or a navigation application, such as one running on a smartphone, can also be used as the navigation unit. The navigation unit only needs to be connected to a computing device 4 to obtain the corresponding hazard index GI and the corresponding adaptive route determination algorithm. Therefore, the corresponding computer program product and the corresponding computer-readable storage medium for storing the computer program product are also part of this invention.

Claims

1. A method for determining a navigation route (1) for a vehicle, wherein, Other traffic participants (2) are detected by means of a sensor system (3), and the sensor data generated by the sensor system (3) is evaluated by a computing device (4) to determine the behavior of the respective traffic participants (2) in road traffic. Its features are, - The computing device (4) stores a database (5) including behavioral limit values; - The computing device (4) compares the behavior observed by the traffic participant (2) with the behavior limit values ​​stored in the database (5), and if the corresponding observed behavior of the traffic participant (2) exceeds the associated behavior limit value, the event (E) is counted on the road segment where the traffic participant (2) is staying; - The computing device (4) calculates the hazard index (GI) of at least one road segment based on the number and value of events counted on the corresponding road segment within a specified time period; and - The navigation unit considers the hazard index (GI) assigned to the corresponding road segment for route planning, wherein, in order to determine the navigation route (1), road segments with hazard index (GI) exceeding the prescribed hazard index threshold are avoided.

2. The method according to claim 1, Its features are, When the behavior limit is exceeded, the computing device (4) assigns an assessment to the corresponding traffic participant (2) and takes into account the assessment of the traffic participant (2) who stayed on the road segment for a specified time period to calculate the hazard index (GI).

3. The method according to claim 1 or 2, Its features are, The value of an event to be assigned to a road segment and / or the value of an assessment to be assigned to a traffic participant (2) depends on the extent to which the associated behavioral limit value is exceeded.

4. The method according to any one of claims 1 to 3, Its features are, The behavioral limits are determined in accordance with applicable road traffic regulations.

5. The method according to any one of claims 1 to 4, Its features are, The computing device (4) assigns the event to the road segment, the value of which depends on the current total number of traffic participants (2) on the road segment, the average distance between the traffic participants (2) and each other, in particular taking into account their standard deviation and / or depends on the number of lane changes on the road segment determined within a specified time period.

6. The method according to any one of claims 1 to 5, Its features are, The computing device (4) determines the characteristics of the situation when the behavior limit is exceeded from the sensor data and executes a machine learning model that establishes a relationship between the determined characteristics of the situation and the corresponding exceedance of the corresponding behavior limit.

7. The method according to any one of claims 1 to 6, Its features are, The computing device (4) predicts the hazard index (GI) of at least one road segment within a future time range.

8. The method according to any one of claims 1 to 7, Its features are, The computing device (4) determines from sensor data the situation characteristics that exist when the behavior limit value is exceeded, and adjusts the height of at least one behavior limit value according to at least one situation characteristic.

9. The method according to any one of claims 1 to 8, Its features are, When the distance-related length and / or time-related length of at least one segment of the navigation route (1.2) calculated taking into account the hazard index (GI) exceeds a predetermined length threshold, the navigation unit adds a predetermined hazard index threshold to at least one segment of the navigation route (1.1) determined by ignoring the hazard index (GI), and then recalculates the navigation route (1).

10. The method according to any one of claims 1 to 9, Its features are, The vehicle follows the navigation route (1) in a manner that is at least partially automated.

11. The method according to claim 10, Its features are, Vehicles with an increased hazard index (GI) are exhibiting increasingly defensive driving behaviors.

12. A system comprising a sensor system (3), at least one vehicle, a computing device (4), and a navigation unit, Its features are, The sensor system (3), the vehicle, the computing device (4), and the navigation unit are configured to perform the method according to any one of claims 1 to 11.

Images