Method for feedforward control of a driver assistance system

Abstract

The invention relates to a method (1) for feedforward control of a driver assistance system for preventing malfunctions and / or operational faults due to an absence of and / or optically imperceptible markings (2). The invention is characterised in that, in the event of successive instances of deactivation and activation of the driver assistance system over a period (t1), at least data for geolocating vehicles (3a, 3b) of a fleet are transferred to a central computing unit (4) so as to derive information from the data and provide it to other vehicles (3a, 3b) of the fleet, wherein a hotspot (5) is identified if there is an accumulation of such events at the same geographical location and a switch-off reason for deactivation of the driver assistance system is evaluated.

Description

[0001] Method for pre-controlling a driver assistance system

[0002] The invention relates to a method for pre-controlling a driver assistance system.

[0003] Driver assistance systems are primarily used to control the vehicle autonomously or at least semi-automatically. The vehicle's sensors can be used, for example, to implement a lane-keeping assistant. To guide the vehicle autonomously in the lane, the sensors must detect the surrounding roadside markings. Other driver assistance systems are also conceivable, for example, enabling automated adjustment of the speed limit. The vehicle's sensors must automatically detect speed limits displayed on the road or on signs.

[0004] Worn road surfaces, damaged or missing signage, and varying lighting conditions can negatively impact the functionality of driver assistance systems. For example, certain lighting fluctuations, such as those caused by shadows cast in avenues, urban canyons, bridge underpasses, or even when entering or exiting a tunnel, can cause the driver assistance system to fail.

[0005] EP 3291 134 A1 discloses a method for controlling a visual sensor of a vehicle, wherein the visual sensor is adjusted at an expected point along a route of a host vehicle at which a lighting fluctuation greater than or equal to a threshold value is expected to occur. Images captured by the visual sensor, map data of the vehicle, and coordinates of a GPS system are used to determine the point along the route. The location at which a lighting fluctuation occurs is derived from an underlying map. The disadvantage here is that only lighting fluctuations derived from known buildings can be taken into account. Temporary shadows, such as those caused by changes in vegetation or a different position of the sun, cannot be taken into account.

[0006] DE 102020 108 531 A1 describes a method for identifying potential hazards in road traffic. An event indicating a potential hazard is recorded and transmitted to a central processing unit along with a geolocation. If multiple vehicles detect a large number of similar events with this geolocation, this is entered into a map as a hotspot. The hotspots can be visualized on the map and reported to an authority for review. However, the disadvantage is that there is no notification to road users, so the danger continues to exist for the vehicles participating in the traffic.

[0007] Furthermore, the documents DE102007041121A1, DE102016213913A1 and DE102019131118A1 describe various procedures in vehicles in the event of malfunctions and / or malfunctions of optical environment detection systems.

[0008] The object of the present invention is to provide a method which overcomes the aforementioned disadvantages.

[0009] According to the invention, this object is achieved by a method for pre-controlling a driver assistance system having the features in claim 1, and in particular in the characterizing part of claim 1. Advantageous embodiments and further developments emerge from the dependent claims.

[0010] At the core of the method according to the invention, during consecutive deactivations and activations of the driver assistance system within a given period, at least data for the geolocation of vehicles in a fleet is transmitted to a central processing unit in order to derive information from the data and make it available to other vehicles in the fleet. If such events occur frequently at the same geographical location, a hotspot is identified and a reason for the deactivation of the driver assistance system is evaluated. This allows all vehicles in a fleet, in particular, to benefit from the information provided by different vehicles in the fleet. For example, information from the vehicle's backend can be used to determine the geographical position at which assistance systems must intervene in order to bridge an impending unavailability.The information from the backend is provided by the other vehicles in the fleet.

[0011] The method is designed for the pre-control of a driver assistance system to prevent malfunctions and / or malfunctions due to missing and / or visually imperceptible markings. Missing markings can arise, for example, due to wear or fading due to environmental influences. Visually imperceptible markings can result, for example, from shadows or suddenly changing lighting conditions when entering or exiting an avenue, a canyon of buildings, a bridge underpass, or a tunnel. The method can therefore prevent undesired functional interruptions of the driver assistance systems. Overall, increased functional availability is provided for the vehicle driver. In particular, additional sensors specifically designed for this type of pre-control can be dispensed with.

[0012] In particular, in the backend, preferably in the central processing unit, an intelligent decision can be derived from the mass of individual data points. Therefore, it is preferable to transmit the information derived from the raw data to other vehicles, rather than the raw data. In other words, an intelligent decision, particularly for feedforward control, can be derived from the mass of data points.

[0013] Pre-control specifically means that the vehicle can react in advance to a future situation. In particular, sensors such as cameras, radar sensors, or lidar sensors can react proactively to the future situation. For example, the aperture of the corresponding vehicle cameras can be adjusted to avoid glare or to capture sufficient light and brighten the image.

[0014] The period t1 can, in particular, be a short period of time, which is particularly atypical compared to normal vehicle behavior. Vehicle assistance systems are not usually deactivated, activated, deactivated, and activated in quick succession. For example, the period t1 can be a few seconds, such as, in particular, 0.2 seconds to 2 seconds, or, in particular, 0.5 seconds to 1 second.

[0015] A hotspot can therefore be understood as a spatial cluster of events of a certain type. This type can be characterized, for example, by a certain type of change in lighting or a certain type of disappearance of a marker.

[0016] Preferably, the vehicle assistance systems of vehicles that will pass the geographical location in the future can be pre-controlled in such a way that they can react automatically to the missing or visually imperceptible markings. For example, the aperture of at least one vehicle camera can be adjusted to achieve a good image or one sufficient for analysis even in changing lighting conditions. Likewise, an active steering function can be continued automatically.

[0017] According to a very advantageous development of the idea, it can be provided that vehicles in the fleet that have received pre-control send feedback to the central processing unit, whereby the pre-control parameters can be continuously optimized based on location and / or time. For example, specific aperture angles of the camera apertures, particularly in percent, as well as an indexing start time or aperture opening duration, can be stored. The vehicles can therefore, on the one hand, contain information, and, on the other hand, send feedback, particularly regarding any bridging success, back to the central processing unit.

[0018] According to an advantageous embodiment, the missing markings may be missing lane markings. These may not be completely present, for example, due to weather or other environmental influences. If such insufficient lane markings or road markings occur geostationarily, the method can be used to "bridge" them, so to speak.

[0019] A further advantageous embodiment can provide for the visually imperceptible markings to result from abrupt changes in lighting. This can occur, for example, when entering or exiting covered areas, such as a tunnel, an underpass, or an avenue. Such an abrupt change in lighting usually means that the sensors cannot react as abruptly. However, the method already "prepares" the sensors for the future situation.

[0020] According to a very advantageous development of the concept, the abrupt lighting changes can be provided at a tunnel exit or entrance. The method can therefore be specifically designed for functional limitations at tunnel exits or entrances. Strong lighting changes result at tunnel exits or entrances, so the cameras should be adjusted to the lighting change early on, i.e., especially shortly before the vehicle enters or exits the tunnel.

[0021] According to an advantageous embodiment, the pre-control can be performed by partially closing the aperture of at least one vehicle camera, so that the marking, which is not visually perceptible with the aperture fully open, can be detected. This can prevent, for example, abrupt changes in lighting from causing misinterpretation or deactivation of the driver assistance systems.

[0022] A further advantageous embodiment can provide for the feedforward control to occur by continuing the current steering function if the road course is known and / or the missing and / or visually imperceptible markings are only present for a spatially limited area. The spatially limited area is, in particular, small in relation to a distance traveled per unit of time. In particular, it must be ensured in the backend that the unavailability of the driver assistance system at the said geolocation typically only prevails for short periods of time and that no excessive steering interventions are necessary, since the road course is more or less straight and / or could be restored by extrapolation in the vehicle. This can, in particular, prevent "toggling" of the active steering function.

[0023] According to a very advantageous development of the idea, the pre-steering can be carried out by providing trajectories from the backend. This is particularly advantageous when the road layout requires at least limited steering. Thus, typical, promising trajectories for the corresponding location can be provided from the backend over a relatively short distance.

[0024] According to an advantageous embodiment, it can be provided that if the marking is still missing after the geographically localized hotspot has been exceeded, the driver assistance system is switched off. For example, information about a period of time for which the vehicle assistance system is expected to be unavailable can be made available to the driver assistance system from the backend. Preferably, the driver assistance system can apply bridging solutions for this duration, or a little longer, i.e. for the duration plus a delta. The duration should only be extended by a delta that is very small in relation to the duration of the unavailability. Preferably, the driver assistance system stops bridging as quickly as possible and is instead available again.

[0025] Further advantageous embodiments of the method according to the invention also emerge from the exemplary embodiment which is described in more detail below with reference to the figures.

[0026] Showing:

[0027] Fig. 1 a vehicle on a road with partially missing markings;

[0028] Fig. 2 is a schematic sectional view of an activation and deactivation of a driver assistance system according to Fig. 1; and

[0029] Fig. 3 shows an exemplary embodiment of the method when a vehicle exits a tunnel.

[0030] The illustration in Fig. 1 shows a vehicle 3a, 3b on a road with a partially missing marking 2. The vehicle 3a, 3b is part of a vehicle fleet, wherein the vehicles of the vehicle fleet are connected to a central processing unit, in particular via a wireless network connection. If the vehicle 3a, 3b is at the illustrated position on the road 7, an area is assigned directly in front of the vehicle in which a marking 2 is absent or invisible to the vehicle's sensors. The marking 2 is, in particular, a lane marking. Furthermore, it can be a sign indicating the maximum permissible speed, which is provided, for example, on the road surface or in the form of signs at the side of the road. The area 2 must be bridged for the vehicle assistance system, since it cannot operate in this area.For example, the vehicle assistance system is automatically deactivated if it cannot detect any markings. Furthermore, nonsensical misinterpretations can occur, indicating the absence of markings or imperceptible markings.

[0031] Fig. 2 shows a schematic sectional view of the activation and deactivation of a driver assistance system according to Fig. 1. The figure shown is a diagram, with a route shown on axis B and an activated or deactivated state of the vehicle assistance system shown on axis A. The vehicle assistance system is activated in the area marked 10. Area 2 corresponds to area 2 in Figure 1. As can be seen from the lowered curve, a temporary function shutdown occurs in this area, in particular due to dazzling of the sensors or the absence of markings. In this area 2, the functions are therefore bypassed by a pilot control 9.

[0032] Fig. 3 shows an exemplary embodiment of method 1 when a vehicle 3a, 3b exits a tunnel. Different vehicles 3a, 3b of a vehicle fleet can send data, such as a geolocation of the deactivation, a speed of the vehicle and / or a lighting state, to a central processing unit each time a respective driver assistance system is activated and deactivated. For example, activations of the driver assistance system that shortly follow deactivations can be aggregated as reactivation events in the central processing unit. This makes it possible to identify clusters that can be stored as so-called hotspots. In the illustration, the hotspot 5 is located at the tunnel exit 6, where a strong change in lighting occurs.The computing unit can automatically evaluate the underlying shutdown cycle of the vehicle assistance system, which in particular makes it possible to calculate individual properties of the hotspot 5. For example, the temporal extension of an expected unavailability of the vehicle assistance system can be determined. A data exchange 8 can take place between each of the vehicles 3a, 3b and the central computing unit 4. As a result, an error case can be sent from the vehicle 3a, 3b to the computing unit 4, and a feedforward control trigger with a location reference and / or time reference can be sent from the computing unit 4 to the vehicle 3a, 3b. In particular, a feedback loop can be implemented, whereby the feedforward control trigger can be continuously optimized in a location-specific and / or time-specific manner. For example, the ego vehicle can receive location-related and / or event-related feedforward control of its sensors or ADAS function.

Claims

Patent claims 1. Method (1) for pre-controlling a driver assistance system to avoid malfunctions and / or malfunctions due to missing and / or visually imperceptible markings (2), characterized in that in the case of successive deactivations and activations of the driver assistance system in a period (t1), at least data for the geolocation of vehicles (3a, 3b) of a fleet are transmitted to a central processing unit (4) in order to derive information from the data and to make it available to other vehicles (3a, 3b) of the fleet, wherein in the case of an accumulation of such events at the same geographical location, a hotspot (5) is identified and a reason for the deactivation of the driver assistance system is evaluated.

2. Method (1) according to claim 1, characterized in that a pre-control of the vehicle assistance systems of the vehicles (3a, 3b) which will drive past the geographical location in the future is carried out in such a way that the missing or optically imperceptible markings (2) can be reacted to automatically.

3. Method (1) according to claim 1 or 2, characterized in that Vehicles (3a, 3b) of the fleet that have received a feedforward control send feedback to the central processing unit (4), whereby parameters of the feedforward control can be continuously optimized in a location- and / or time-specific manner.

4. Method (1) according to one of claims 1 to 3, characterized in that the missing markings (2) are missing track markings.

5. Method (1) according to one of claims 1 to 4, characterized in that the optically imperceptible markings (2) result from abrupt changes in illumination.

6. Method (1) according to claim 5, characterized in that the abrupt lighting changes occur at a tunnel exit (6) or tunnel entrance.

7. Method (1) according to claim 5 or 6, characterized in that the pre-control is carried out by partially closing the aperture of at least one vehicle camera, so that the marking (2), which is not optically perceptible when the aperture is fully open, can be recognized.

8. Method (1) according to one of claims 1 to 7, characterized in that the pre-control is carried out by a continuation of the current steering function if the course of the road is known and / or the missing and / or optically imperceptible markings (2) are only present for a spatially limited area.

9. Method (1) according to one of claims 1 to 8, characterized in that the pre-control is carried out by providing trajectories from the backend.

10. Method (1) according to one of claims 1 to 9, characterized in that if the marking (2) is still missing after the geographically localized hotspot (5) is exceeded, the driver assistance system is switched off.

Images