System and procedure for providing a hazard map

Abstract

Procedure for providing a hazard map, including the following steps: - Determining (S10) traffic situation data by means of an environment sensor device (16) of at least one vehicle (12) of a vehicle fleet, wherein the traffic situation data provide a traffic situation and driving behavior of road users in an environment of the vehicle (12); - Determining (S12) driver state data by means of an interior sensor device (18) of the vehicle (12) and driving behavior data (S14) by means of a vehicle sensor device (20), wherein the driver state data provide a state of a driver of the vehicle (12) and the driving behavior data provide a driving behavior of the vehicle (12); - Transmitting traffic situation data, driver condition data and driving behavior data together with a respective recording location and recording time at which the data were recorded to a computing device (14); - Determining (S16) a hazard assessment using traffic situation data, driver condition data and driving behavior data by an artificial intelligence of the computing device (14), wherein, using the hazard assessment, the recording location and the recording time, the hazard map with a time-varying hazard assessment for a given location is provided; - whereby the hazard map is provided to an operations control center (S18), which coordinates emergency vehicles depending on the hazard assessment for the respective location; - whereby emergency vehicles are proactively sent to locations with an increased risk assessment, with coordination being carried out automatically by the emergency vehicles receiving the location from the hazard map.

Description

[0001] The present invention relates to a method for providing a hazard map and a system configured to carry out the method.

[0002] To assess the risks associated with specific road sections, it is common practice to monitor these sections using video surveillance and analyze the data for hazardous situations and / or traffic volume. Historical data, such as accidents at a particular location, can also be used to identify dangerous sections and implement measures to improve safety. However, analyzing historical data and current traffic volume is merely a reaction to past events and does not allow for proactive action.

[0003] From DE 10 2010 055 370 A1, a method for creating a hazard map suitable for display by means of a motor vehicle's navigation system is known. The method is carried out by a data processing unit and comprises receiving data relating to potential hazard locations and linked to location information of the hazard location, and inputting hazard data into a digital map, thereby creating the hazard map by a data processing unit, wherein the hazard data is supplied to the data processing unit from at least one source from the group comprising the navigation system, at least one sensor device of the motor vehicle, driver input, a traffic message channel, weather data, accident statistics, and driver specifications.

[0004] German patent application DE 10 2012 014 457 A1 discloses a method for operating a motor vehicle in which external vehicle data, indicating the presence of a hazardous situation, is transmitted to a receiving device of the vehicle. A warning concerning this hazardous situation is communicated to the vehicle's user. In addition to the external vehicle data, internal vehicle data is also evaluated, which further indicates the presence of a hazardous situation. The warning is communicated to the vehicle's user based on the evaluation of both the external and internal vehicle data.

[0005] From US 2019 / 0 193 729 A1, methods and apparatus, including computer program products, are known that use techniques for detecting abnormal vehicle behavior.

[0006] From WO 2018 / 059 874 A1, a method and a device for creating a dynamic hazard map are known. In a reading step, at least one hazard signal is read via an interface to a vehicle. This signal represents at least one parameter read by the vehicle during a journey, indicating a hazard, and the vehicle's geographical position. In a classification step, the at least one hazard signal, or at least a combination signal consisting of the hazard signal and at least one other hazard signal, is classified into a hazard category. In an output step, a display signal is output using at least the hazard signal or the combination signal and the hazard category. The display signal includes at least the parameter and / or the geographical position and / or the hazard category on a map.

[0007] From GB 2 421 828 A a traffic hazard management system for a vehicle is known, which sends and receives data from sensors and other vehicles relating to traffic hazards.

[0008] From DE 10 2016 202 086 A1 a procedure for identifying dangerous situations in road traffic and for warning road users is known.

[0009] The object of the present invention is to increase road safety.

[0010] This problem is solved by the independent patent claims. Advantageous embodiments of the invention are disclosed in the dependent patent claims, the following description, and the figures.

[0011] The invention provides a method for generating a hazard map. The method comprises the following steps: acquiring traffic situation data by means of an environmental sensor device of at least one vehicle in a fleet, wherein the traffic situation data provides information about the traffic situation and the driving behavior of road users in the vicinity of the vehicle; acquiring driver state data by means of an interior sensor device of the vehicle and driving behavior data by means of a vehicle sensor device, wherein the driver state data provides information about the state of the driver of the vehicle and the driving behavior data provides information about the driving behavior of the vehicle. As a further step, the method comprises transmitting the traffic situation data, the driver state data, and the driver behavior data, together with the respective recording location and time, to a computing device.Finally, an artificial intelligence within the computing device determines a hazard assessment using traffic situation data, driver condition data, and driving behavior data. Based on this hazard assessment, the recording location, and the recording time, a hazard map with a time-varying hazard assessment for a given location is generated. This hazard map can then be made available, for example, to vehicles in the vehicle fleet, traffic infrastructure operators, and / or emergency control centers.

[0012] In other words, sensor data or swarm data are initially collected using the environmental sensors of at least one vehicle in a fleet, allowing conclusions to be drawn about the traffic situation and specific areas. In particular, an environmental sensor system, which may include one or more vehicle cameras, lidar sensors, radar sensors, and / or ultrasonic sensors, can determine traffic situation data in the vicinity of the recording vehicle. Preferably, image recognition algorithms can detect other vehicles, especially their number and / or movement patterns, and provide this information as traffic situation data. For example, heavy traffic can pose a greater risk than a clear road. Driving behavior, such as changes in direction and / or speed, can be detected, especially those that deviate from standard values, and stored in the traffic situation data.

[0013] In addition to traffic situation data, driving behavior data from the vehicle itself and driver state data can also be determined. Driver state data can be collected by an interior sensor system and may include, for example, the driver's level of fatigue or attention. This interior sensor system could include, for example, an interior camera, particularly one with gaze direction analysis. The vehicle sensor system, which determines the driving behavior data of the vehicle itself or the data-collecting vehicle, could include, for example, vehicle speed sensors, steering angle sensors, and / or distance sensors, enabling the analysis of the vehicle's driving behavior in traffic.Sensors from driver assistance systems and / or data from the vehicle's driver assistance systems can also be used to detect, for example, an intervention by these assistance systems and to use this information for a hazard assessment.

[0014] The data collected can then be transmitted to a computing device, preferably an external computing device, for example via a data transmission device, whereby the data is preferably anonymized before transmission. Furthermore, the respective data—that is, the traffic situation data, the driver status data, and the driving behavior data—can be transmitted along with the respective recording times and locations. Thus, the computing device, which is preferably a backend or server on the internet, can generate a hazard assessment from the data and supplement a digital map with this assessment. This hazard assessment can preferably be dynamic and continuously updated with the most current hazard information.Therefore, the assessment of the risk situation is based not only on the current and precise traffic volume, but also on observed conspicuous driving behavior of individual vehicles. Conspicuous driving behavior can include, for example, weaving, excessive speed, late deceleration in stop-and-go traffic, failure to use turn signals when changing lanes, overtaking on the right, rear-ending, wrong-way driving, and more.

[0015] To determine this hazard assessment, the computing device preferably incorporates a trained artificial intelligence (AI) learned from previous known events and hazards where comparable sensor data was available, enabling it to perform a hazard assessment. In addition to environmental data from other vehicles, the driver's own condition, such as fatigue, health, slow reaction times, and the intervention of driver assistance systems, can also be factored into the hazard assessment. The data can then be aggregated and interpreted by the computing device. The output of the computing device can then be a hazard assessment for each geographic area, which can be provided as a hazard map for each vehicle in the fleet and / or to traffic management systems and / or emergency control centers to improve road safety.

[0016] The invention offers the advantage of increasing awareness of dangerous areas or sections of road, thereby enabling proactive driving behavior and / or traffic infrastructure measures to be taken to reduce the danger.

[0017] Furthermore, it is planned that the hazard map will be made available to an emergency control center, which will coordinate emergency vehicles based on the hazard assessment for each location. Emergency vehicles will be proactively dispatched to locations with an increased hazard assessment, with the coordination being carried out automatically, as the emergency vehicles receive their location from the hazard map. This means that emergency control centers coordinating rescue services and / or patrol vehicles can also receive the hazard map to, for example, proactively dispatch emergency vehicles to locations with an increased hazard assessment. This coordination can preferably be carried out automatically, with the emergency vehicles receiving their destination from the hazard map. This will further improve road safety.

[0018] The invention also includes embodiments that offer additional advantages.

[0019] One embodiment provides that the hazard map is made available to a traffic management system, which, depending on the hazard assessment for the respective location, controls a traffic control device according to predefined hazard reduction measures to mitigate a hazardous situation at that location. In other words, the generated hazard map with the respective hazard assessments can be made available to infrastructure operators of traffic management systems, particularly via defined interfaces, whereby the traffic management systems can proactively control traffic control devices at respective locations with increased risk. Traffic control devices can, for example, be digital traffic displays that can provide speed limits, no-overtaking zones, and / or warning messages as predefined hazard reduction measures.In particular, traffic lights, for example at tunnels, can also be controlled if a hazard assessment indicates an increased risk for a tunnel. The traffic management systems can preferably be controlled automatically using the hazard map in order to reduce the hazardous situation at the location. This design offers the advantage of increasing road safety.

[0020] Another embodiment involves machine-training the artificial intelligence using predetermined traffic situation data, driver state data, driving behavior data, and actual hazardous events. In other words, the artificial intelligence can be machine-trained, particularly with predetermined data and accident or hazardous events, which may be derived, for example, from accident statistics. Here, the artificial intelligence can identify sensor data patterns from the predetermined data that frequently occur before accidents, and these sensor data patterns are then searched for in the recorded data when determining the hazard assessment. Furthermore, actual traffic events detected after the recording of the traffic situation data, driver state data, and driving behavior data can be fed back into the artificial intelligence model, thus continuously training the artificial intelligence.This design offers the advantage that the hazard assessment for the hazard map can be further improved.

[0021] Preferably, the environmental sensor system is designed to determine the traffic situation, including traffic volume, traffic signs, road layout, roadworks, and / or light and weather conditions. In other words, the traffic situation data encompasses a number of other road users, traffic signs, road layout (such as inclines, intersections, and / or curves), roadworks or damage, and weather or light conditions. Traffic signs can also include digital displays, for example, allowing for the determination of speed limits. The environmental sensor system can, for example, include a camera sensor, a lidar sensor, a radar sensor, and / or an ultrasonic sensor to determine this traffic situation data.

[0022] In a further advantageous embodiment, the environmental sensor device is designed to detect the driving behavior of road users, including speed, changes of direction, braking, overtaking, distances, wrong-way drivers, and / or the use of lighting equipment by other vehicles. In particular, the traffic situation data can include speeding by other vehicles, changes of direction such as sharp steering maneuvers and / or swerving, braking such as hard or delayed braking, risky overtaking maneuvers such as overtaking on the right, and / or the use or non-use of lighting equipment, such as driving without lights in poor lighting conditions, warning lights, and / or the failure to use turn signals.The lighting equipment of emergency vehicles, such as blue lights, can also indicate a dangerous situation.

[0023] Preferably, the interior sensor system determines the driver's state of attention by means of gaze direction detection and / or object recognition using an interior camera and / or contact sensors on the steering wheel. In other words, the driving behavior data can include the driver's state of attention, in particular fatigue, reaction time, and / or distraction. For example, gaze direction detection and / or object recognition can be used to determine whether a driver is distracted by objects in the interior, especially food, drinks, and / or mobile devices. Furthermore, contact sensors on the steering wheel can determine, for example, whether a driver has their hands on the steering wheel or not, which can contribute to hazard assessment.

[0024] Furthermore, it is preferably provided that the vehicle sensor device determines the vehicle's speed and / or sensor signals from a driver assistance system and / or error messages from a vehicle computer as part of the vehicle's driving behavior. In this way, the vehicle recording the data and its driving behavior can be monitored by the vehicle sensor device by using, for example, sensor signals from a driver assistance system, particularly situations in which the driver assistance system must intervene, and / or error messages from the vehicle computer, such as detected defects in the vehicle, for hazard assessment.

[0025] Another embodiment provides that the computing device is an external server located outside the vehicle, and the relevant data is transmitted wirelessly to the computing device. In particular, the hazard map generated by the computing device can also be distributed wirelessly. For example, the relevant data can be transmitted via WLAN, Bluetooth, and / or a mobile communication standard, especially 5G or LTE.

[0026] Another aspect of the invention relates to a system comprising at least one vehicle of a vehicle fleet and a computing device, wherein the vehicle has an environment sensor device, an interior sensor device, a vehicle sensor device and a data transmission device, wherein the environment sensor device is configured to determine traffic situation data comprising a traffic situation and driving behavior of road users in the vicinity of the vehicle, wherein the interior sensor device is configured to determine driver state data comprising a state of the driver of the vehicle, wherein the vehicle sensor device is configured to determine driving behavior data comprising a driving behavior of the vehicle, and wherein the data transmission device is configured to transmit the traffic situation data,to transmit the driver condition data and the driving behavior data, together with the respective recording location and time at which the data were recorded, to the computing device, wherein the computing device is designed to determine a hazard assessment using the traffic situation data, the driver condition data and the driving behavior data by means of artificial intelligence and to provide a hazard map with a time-varying hazard assessment for a respective location using the hazard assessment, the recording location and the recording time, wherein an operations control center is set up to automatically coordinate emergency vehicles depending on the hazard assessment of the provided hazard map for the respective location and to proactively send the emergency vehicles to locations with an increased hazard assessment,by the emergency vehicles receiving their location from the hazard map. In other words, the system can be configured to carry out the procedure according to one of the previous embodiments. This offers the same advantages and possibilities for variation as the previous method.

[0027] For use cases or application situations that may arise during the procedure and are not explicitly described here, it may be provided that, according to the procedure, an error message and / or a request for user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0028] The invention also includes the control device for the vehicle. The control device can comprise a data processing device or a processor unit configured to carry out an embodiment of the method according to the invention. For this purpose, the processor unit can comprise at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). Furthermore, the processor unit can comprise program code configured to carry out the embodiment of the method according to the invention when executed by the processor unit. The program code can be stored in a data memory of the processor unit.

[0029] The invention also includes further developments of the system according to the invention, which have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments of the system according to the invention are not described again here.

[0030] The vehicle is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

[0031] As a further solution, the invention also includes a computer-readable storage medium comprising program code which, when executed by a computer or a computer network, causes it to execute an embodiment of the method according to the invention. The storage medium can, for example, be provided at least partially as a non-volatile data storage medium (e.g., as flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data storage medium (e.g., as RAM - random access memory). The storage medium can be implemented in the processor circuit within its data storage. However, the storage medium can also be operated, for example, as a so-called app store server on the internet. The computer or computer network can provide a processor circuit with at least one microprocessor. The program code can be in binary code or assembly language and / or as source code of a programming language (e.g.,C) and / or be provided as a program script (e.g. Python).

[0032] The invention also includes combinations of the features of the described embodiments. The invention therefore also includes realizations that each exhibit a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

[0033] The following are exemplary embodiments of the invention described. This is illustrated by: Fig. 1 a system for providing a hazard map according to an exemplary embodiment; Fig. 2 a schematic process diagram according to an exemplary embodiment.

[0034] The exemplary embodiments described below are preferred embodiments of the invention. In these exemplary embodiments, the described components each represent individual features of the invention, which can be considered independently of one another and each further develops the invention independently. Therefore, the disclosure is intended to include combinations of features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

[0035] In the figures, identical reference symbols denote functionally equivalent elements.

[0036] In Fig. Figure 1 shows a system 10 for providing a hazard map according to an exemplary embodiment, wherein the system 10 comprises at least one vehicle 12 of a vehicle fleet and a computing device 14. The vehicle 12 can, for example, travel a section of road to provide the data for the hazard map and record its surroundings using an environmental sensor device 16. Furthermore, the vehicle 12 can have an interior sensor device 18, a vehicle sensor device 20, and a data transmission device 22.

[0037] To determine a hazard assessment, the environmental sensor device 16 can acquire traffic situation data encompassing the traffic situation and the driving behavior of road users in the vicinity of the vehicle 12. The environmental sensor device 16 may, for example, include a camera sensor, radar, lidar, and / or ultrasonic sensors that can analyze and interpret traffic volume and thus provide information about traffic density in its immediate surroundings. Furthermore, the driving behavior of other road users can be analyzed and interpreted, in particular the speed at which other road users travel the section of road and / or whether unusual changes of direction, braking maneuvers, overtaking maneuvers, and / or distances between road users are present.Furthermore, the traffic situation data can contain information about where and when the respective traffic situation and / or driving behavior was recorded.

[0038] In addition, driver status data can be determined by the interior sensor system 18, which includes, for example, an interior camera. For instance, the driver's level of attention can be determined by tracking their gaze direction in vehicle 12. Furthermore, the vehicle sensor system 20 can determine and interpret the driving behavior of the driver in vehicle 12 by receiving and evaluating, for example, vehicle sensor data and / or sensor signals from the vehicle's driver assistance systems. Here, too, the location of the vehicle 12 when this data was recorded and the corresponding time of recording can be stored.

[0039] The recorded data can then be wirelessly transmitted to the computing device 14 by the data transmission device 22, which may be, for example, a radio modem, in particular a WLAN modem and / or mobile communication modem, wherein the computing device 14 may preferably be a vehicle-external server in a data network, in particular the Internet.

[0040] The computing device 14 can include an artificial intelligence that is preferably machine-trained using predetermined traffic situation data, predetermined driver condition data, predetermined driving behavior data, and actual hazardous events, such as accidents. The artificial intelligence can determine a hazard assessment for the recording location at the recording time based on the data transmitted by the vehicle 12. A digital map can then be overlaid with this hazard assessment to provide the hazard map. For example, different hazard states can be indicated on the map according to a color scale.

[0041] The hazard map provided by the computing device 14 can preferably be subsequently made available to the vehicles of the fleet and / or a traffic control system and / or an operations control center. For example, a traffic control system can include traffic control devices that manage traffic on the route. These traffic control devices can be, for example, digitally controlled traffic signs that can display speed limits, no-overtaking zones, and / or traffic jam warnings. In particular, depending on the hazard map, the respective traffic control device at a location with an increased hazard assessment can be activated according to predefined hazard reduction measures, for example, by reducing the maximum permitted speed at that location.Alternatively or additionally, an operations control center, which is responsible for coordinating emergency vehicles, especially police, fire brigade and / or rescue vehicles, can, depending on the hazard assessment of the hazard map, send emergency vehicles in advance to endangered areas in order to shorten the travel time to a possible accident site.

[0042] In Fig. Figure 2 shows a schematic process diagram for providing a hazard map according to an exemplary embodiment. In step S10, traffic situation data can be determined by an environmental sensor device 16 of the vehicle 12, whereby a traffic situation can be interpreted in the traffic situation data by analyzing the environmental sensors. The traffic situation data can also include the driving behavior of other road users, which can also be detected and interpreted by the environmental sensor device 16.

[0043] In parallel, in step S12, driver condition data can be acquired by an interior sensor device 18, and in step S14, vehicle behavior data 12 can be acquired by a vehicle sensor device 20. These provide information on the driver's condition and the vehicle's behavior. Together with the acquisition time and location of the respective data, hazard assessments for each acquisition location can then be determined in step S16 after transmission to a computing device 14. For this purpose, an artificial intelligence within the computing device 14 can perform the hazard assessment based on previously trained data and actual hazardous events. The hazard assessment thus determined can then be used to generate a time-varying hazard map that indicates the hazard assessment for each acquisition location at the time of acquisition.

[0044] The hazard map can, for example, be provided in step S18 to traffic control systems and / or emergency control centers, which can then proactively dispatch patrol vehicles and / or rescue services to areas with an increased risk of danger. Alternatively or additionally, the hazard map can be provided to traffic control systems and / or infrastructure operators, who can, for example, proactively adjust speed limits at hazardous locations. Preferably, a feedback channel to the computing device 14 and the hazard assessment of step S16 can be provided, which feeds actual traffic events back to the artificial intelligence so that, as a self-learning system, it can continuously improve the hazard assessment.For example, data such as accident statistics from official databases of rescue control centers can be used, but also accidents perceived by the vehicle 12 or another vehicle in the fleet via the environment sensor device 16.

[0045] Another exemplary aspect is that vehicles in the fleet will be equipped with comprehensive environmental sensors for the individual perception, analysis, and real-time interpretation of traffic situations. A combination of this sensor data (swarm data) allows conclusions to be drawn about the traffic situation in specific areas. From this, an objective hazard assessment for the respective area, for example, for a section of road, can be derived. This hazard assessment can be transmitted to control centers and / or infrastructure. This enables proactive adjustments to traffic management systems, such as temporary speed reductions and / or warnings, as well as the deployment of various emergency services to the area.

[0046] The assessment of the risk situation is based not only on the current and precise traffic volume, but also on observed conspicuous driving behavior of individual vehicles. This can include, for example, weaving, excessive speed, late deceleration in stop-and-go traffic, failure to use turn signals when changing lanes, overtaking on the right, rear-ending, wrong-way driving, and others. Furthermore, the driver's own condition (e.g., fatigue, health, slow reaction times, intervention by driver assistance systems, and other factors) can be considered in the risk assessment. Ideally, all data on traffic volume and individual behavior can be evaluated anonymously.A hazard map can be created in a backend (computer 14) by using a self-learning system or model as input, which then provides a hazard assessment for each geographic area as output. Furthermore, actual events such as accidents can be incorporated into the self-learning model. This allows model parameters to be continuously adjusted to make increasingly accurate predictions based on the input data.

[0047] Additionally, health data from mobile devices can be aggregated and interpreted to identify potential threats in public spaces. Based on this information, an emergency response center can be put on alert. For example, a significantly elevated pulse rate might be detected in one or more passersby within a specific geographic area, indicating that an incident has occurred there and that emergency services may be required.

[0048] The generated hazard map for risk assessment can then be shared via a defined interface with, for example, control centers or infrastructure operators, who can then react proactively to the hazard assessment. Actual traffic incidents can be fed back into the self-learning model so that it can be further trained.

[0049] Overall, the examples show how the invention can provide a swarm data-based hazard evaluation for the intelligent control of emergency services and traffic management systems.

Claims

[1] Procedure for providing a hazard map, comprising the steps: - Determining (S10) traffic situation data by means of an environment sensor device (16) of at least one vehicle (12) of a vehicle fleet, wherein the traffic situation data provide a traffic situation and driving behavior of road users in an environment of the vehicle (12); - Determining (S12) driver state data by means of an interior sensor device (18) of the vehicle (12) and driving behavior data (S14) by means of a vehicle sensor device (20), wherein the driver state data provide a state of a driver of the vehicle (12) and the driving behavior data provide a driving behavior of the vehicle (12); - Transmitting traffic situation data, driver condition data and driving behavior data together with a respective recording location and recording time at which the data were recorded to a computing device (14); - Determining (S16) a hazard assessment using traffic situation data, driver condition data and driving behavior data by an artificial intelligence of the computing device (14), wherein, using the hazard assessment, the recording location and the recording time, the hazard map with a time-varying hazard assessment for a given location is provided; - whereby the hazard map is provided to an operations control center (S18), which coordinates emergency vehicles depending on the hazard assessment for the respective location; - whereby emergency vehicles are proactively sent to locations with an increased risk assessment, with coordination being carried out automatically by the emergency vehicles receiving the location from the hazard map. [2] Method according to claim 1, wherein the hazard map is provided to a traffic control system (S18) which, depending on the hazard assessment for the respective location, controls a traffic control device in accordance with specified hazard reduction measures to reduce a hazardous situation at the location. [3] Method according to one of the preceding claims, wherein the artificial intelligence is trained by machine using predetermined traffic situation data, driver condition data and driving behavior data and actually occurring hazardous events. [4] Method according to one of the preceding claims, wherein the environmental sensor device (16) determines the traffic situation as a traffic volume and / or traffic signs and / or route and / or roadworks and / or light and weather conditions. [5] Method according to one of the preceding claims, wherein the environment sensor device (16) determines the driving behavior of road users as speed and / or changes of direction and / or braking operations and / or overtaking operations and / or distances and / or wrong-way drivers and / or the use of lighting equipment of other vehicles. [6] Method according to one of the preceding claims, wherein the interior sensor device (18) determines the driver's state of attention by means of gaze direction detection and / or object recognition by an interior camera and / or contact sensors on a vehicle steering wheel. [7] Method according to one of the preceding claims, wherein the vehicle sensor device (20) determines the vehicle's (12) speed as the vehicle's (12) driving behavior and / or sensor signals from a vehicle's (12) driver assistance system and / or error messages from a vehicle computer. [8] Method according to one of the preceding claims, wherein the computing device (14) is a vehicle-external server and the respective data are transmitted wirelessly to the computing device (14). [9] System (10) comprising at least one vehicle (12) of a vehicle fleet and a computing device (14), wherein the vehicle (12) has an environment sensor device (16), an interior sensor device (18), a vehicle sensor device (20) and a data transmission device (22), wherein the environment sensor device (16) is configured to determine traffic situation data comprising a traffic situation and driving behavior of road users in the vicinity of the vehicle (12), wherein the interior sensor device (18) is configured to determine driver state data comprising a state of a driver of the vehicle (12), wherein the vehicle sensor device (20) is configured to determine driving behavior data comprising a driving behavior of the vehicle (12), and wherein the data transmission device (22) is configured to transmit the traffic situation data,to transmit the driver condition data and the driving behavior data together with a respective recording location and a recording time at which the data were recorded to the computing device (14), wherein the computing device (14) is configured to determine a hazard assessment using the traffic situation data, the driver condition data and the driving behavior data by means of artificial intelligence and to provide a hazard map with a time-varying hazard assessment for a respective location using the hazard assessment, the recording location and the recording time, wherein an operations control center is set up to automatically coordinate emergency vehicles depending on the hazard assessment of the provided hazard map for the respective location and to proactively send the emergency vehicles to locations with an increased hazard assessment by obtaining the location from the hazard map.

Images