Separate detection of a lane change intention and a lane change probability

Abstract

The invention relates to a system for a vehicle (1), wherein a sensor unit (3) is used to detect the surroundings of the vehicle (1); a control unit (5) determines the state of another road user (7), at least their lateral speed, from the sensor data; and, if the lateral speed falls below a specified threshold, the control unit (5) determines a measure of an intention to change lanes solely on the basis of components of the state which are not based on a movement of the other road user (7) and, if the lateral speed exceeds the threshold, the control unit determines the probability of an imminent lane change.

Description

[0001] 24-2703

[0002] 1

[0003] Separate detection of lane change intention and lane change probability

[0004] The invention relates to a system for a vehicle for detecting a lane-change intention and a lane-change probability of another road user, as well as a corresponding method for a vehicle.

[0005] Motor vehicles, especially passenger cars and trucks, are increasingly characterized by automated driving. For such automated driving, automatic detection of an impending lane change by another road user is often desired or necessary, particularly a lane change onto the lane currently occupied by the vehicle. Methods for the automated detection of an impending lane change maneuver by a target vehicle, i.e., another road user, are known in the prior art.

[0006] DE 102016 106 983 A1 relates to a method for detecting a possible lane change maneuver by a target vehicle, in which sensor data from at least one sensor of a home vehicle are received, wherein the sensor data describe an environment of the home vehicle and the target vehicle, a plurality of parameters for detecting the possible lane change maneuver are determined on the basis of the sensor data, wherein the plurality of parameters describe the target vehicle, a relative position between the home vehicle and the target vehicle and / or a movement of the target vehicle, and the possible lane change maneuver is detected on the basis of the plurality of parameters, wherein a probability value is determined for at least two of the parameters, which describes a probability for the possible lane change maneuver.An overall probability is determined from the respective probability values, and the possible lane-changing maneuver is recognized based on this overall probability.

[0007] DE 102018222 176 A1 also relates to a method for predicting whether a foreign vehicle will change lanes in the vicinity of an ego vehicle, based on observations of the ego vehicle's surroundings, comprising the following steps: the observations are fed to a plurality of individual classifiers; each individual classifier determines, according to an individual rule, from at least a subset of the observations, an individual probability that the foreign vehicle will change lanes; the driving situation in which the ego vehicle is located is defined as 24-2703

[0008] 2

[0009] The entire situation is classified into one of several discrete classes using a situation classifier; a set of weighting factors is determined, assigned to the class into which the situation classifier has classified the driving situation, which indicates the relative weighting of the individual classifiers for this driving situation; the individual probabilities are combined with the weighting factors to obtain an overall probability that the other vehicle will perform a lane change.

[0010] DE 102020214 203 A1 further relates to a method for determining the lane-change intention of another motor vehicle located in the immediate vicinity of a motor vehicle by means of an assistance system of the motor vehicle, in which the environment of the motor vehicle is detected by means of at least one environment detection device of the assistance system and an environment model for the environment is generated on the basis of the detected environment by means of an electronic computing device of the assistance system, and in which, depending on the generated environment model, at least one situation feature characterizing a lane change of the other motor vehicle is determined by means of the electronic computing device, wherein the lane-change intention is determined by means of a Bayesian network model of the electronic computing device depending on the at least one characterizing situation feature.wherein at least one situational feature characterizing the lane change of the other motor vehicle is a lane change motive for the other motor vehicle, wherein the lane change motive is determined depending on a relative distance of the other motor vehicle to an object in the environment, depending on a relative speed of the other motor vehicle to the object and depending on a type of object.

[0011] The object of the invention is to provide an improved assessment of the behavior of another road user for an automated vehicle.

[0012] The invention is defined by the features of the independent claims. Advantageous further developments and embodiments are the subject of the dependent claims.

[0013] A first aspect of the invention relates to a system for a vehicle, comprising a sensor unit and a control unit, wherein the sensor unit is configured to detect the vehicle's environment, including another road user, and to generate sensor data about the detected environment, wherein the control unit is configured to determine a state of the other road user from the sensor data, wherein the state comprises at least a lateral velocity of the other road user as a component of the state, and wherein the control unit is configured to, at a lateral velocity 24-2703

[0014] 3. Below a predetermined limit, determine a measure of the intention to change lanes by the other road user based solely on components of the state that are not based on a movement of the other road user, and above the limit, determine a probability of an impending or already existing lane change, and if the probability meets a first predetermined limit condition, automatically initiate an immediate emergency driving control intervention, and if the measure of intention to change lanes meets a second predetermined limit condition, decide whether the vehicle will behave cooperatively interacting with the other road user or not react to the detected intention.

[0015] In this document, the term "automated driving" or "automated vehicle control" refers to driving with automated longitudinal and / or lateral control. Automated driving can, for example, involve extended periods of driving on the highway or time-limited driving during parking maneuvers. The term "automated driving" encompasses automated driving at any level of automation. Examples of automation levels include assisted, partially automated, conditionally automated, highly automated, and fully automated driving (each with an increasing degree of automation). The five automation levels mentioned above correspond to SAE Levels 1 to 5 of the SAE J3016 standard (SAE - Society of Automotive Engineering) as of April 30, 2021. In assisted driving (SAE Level 1), the system performs longitudinal or lateral control in specific driving situations.In partially automated driving (SAE Level 2), the system takes over longitudinal and lateral control in certain driving situations, although the driver must continuously monitor the system, as with assisted driving. In conditionally automated driving (SAE Level 3), the system takes over longitudinal and lateral control in certain driving situations without the driver needing to continuously monitor the system; however, the driver must be able to take over vehicle control within a certain timeframe if requested by the system. In highly automated driving (SAE Level 4), the system takes over vehicle control in certain driving situations, even if the driver does not respond to a request to intervene, thus eliminating the driver as a fallback option. In fully automated driving (SAE Level 5), the system can perform all aspects of the dynamic driving task under any road and environmental conditions that a human driver can also handle.

[0016] Preferably, the system is a system according to SAE Level 2, in particular SAE Level 2+; particularly preferably, the system is a system according to at least SAE Level 2, 24-2703

[0017] 4. In particular, at least 2+. Furthermore, the system is preferably a system according to SAE Level 3. Furthermore, the system is preferably a system at least according to SAE Level 3.

[0018] Preferably, the vehicle is a vehicle of SAE Level 2, in particular 2+; particularly preferably, the vehicle is a vehicle of at least SAE Level 2, in particular at least 2+. Further preferred is a vehicle of SAE Level 3. Further preferred is a vehicle of at least SAE Level 3.

[0019] Information about the status of other road users is obtained by means of a sensor unit. This sensor unit is preferably integrated into the vehicle. Its sensor data is used by the control unit. The sensor unit particularly preferably includes a camera that generates image data of the vehicle's surroundings and, in particular, detects the other road user along with the lane and its lane markings on which the other road user is located, and outputs corresponding image data. Preferably, other road users of interest are those located in a lane adjacent to the vehicle's own lane and are evaluated accordingly by the processing unit. Furthermore, another road user who is currently in the vehicle's own lane and may change lanes may also be of interest.As an alternative to the camera unit, or in addition to it, one or more further sensors can be used, in particular a lidar system and / or a radar system.

[0020] The control unit evaluates the sensor data from the sensor unit by determining, in particular at a large number of successive time points, preferably as quickly as the sensor data rate and the data rate of the control unit allow, the current change in the lateral position of the other road user relative to a lane boundary of the lane being used by the other road user. This can be done at high data rates, for example 50 Hz, 100 Hz, 200 Hz, 500 Hz or 1 kHz. The determination of the lateral position is carried out in particular by image analysis if the sensor data from the sensor unit provides corresponding image data.

[0021] The lateral speed of another road user indicates, in particular, a change in distance over time to its lane boundary. A longitudinal coordinate of the road user with respect to the longitudinal direction of its lane is not considered here. Lateral speed is perpendicular to any longitudinal speed; lateral speed refers to a relationship to the lane boundary of the other road user's lane. The lane boundary can be a marking or a corresponding relief, or 24-2703

[0022] Five other elements are included to visually distinguish lanes, such as the lane of one's own vehicle and the lane of another road user, which are particularly adjacent to each other. The other road user is typically another vehicle, and can therefore be a passenger car.

[0023] If another road user's lateral speed relative to their lane marking exceeds a predefined limit, a conventional calculation can be performed to determine the probability of an imminent lane change by that other road user. Of interest here is the other road user's future lane change, specifically a possible lane change that they might make in the near future, particularly within the few seconds preceding the present. If this probability exceeds a predefined limit, the control unit reacts with an emergency driving control intervention. Such an intervention typically involves emergency braking and / or an evasive maneuver to avoid a collision with the other road user.

[0024] However, in cases where the other road user is moving slowly, the lateral speed is typically correspondingly low, and calculating the probability of such a lane change fails if it is primarily based on lateral speed. For example, in a traffic jam, the other road user may already have adopted a corresponding orientation that deviates significantly from the longitudinal direction of their lane. In other words, the other road user may have already oriented their vehicle for a lane change by adjusting the steering angle or activated a turn signal in the direction of the desired lane, but this lane change has not yet been executed due to the low or non-existent lateral speed, although the intention to do so is present and recognizable.In the preceding and following sections, when a lateral velocity is compared to a predefined limit, it is advantageous to use a magnitude of the lateral velocity. If the measure of intention fulfills a second predefined limit condition, the control unit makes a decision regarding how the vehicle should behave. While fulfilling the first predefined limit condition triggers an emergency driving control intervention based on the calculated probability, fulfilling the second limit condition, based on the calculated measure of intention, determines whether the vehicle should behave cooperatively, interacting with the other road user, or not reacting to the other road user. Cooperative interaction means yielding to the vehicle's own 24-2703.

[0025] 6

[0026] The vehicle and, optionally, an additional signal indicating its intention to yield, to facilitate the lane change of the other road user. The first and second boundary conditions can be implemented using threshold values.

[0027] Therefore, the system and its associated procedure advantageously distinguish between a mere intention to change lanes and a sufficiently high probability of the lane change actually occurring immediately to warrant a corresponding reaction. The predetermined threshold, above which lateral speed leads to a probability calculation and below which only an intention is determined, is preferably chosen such that expected inaccuracies and noise components remain below the threshold even if the actual lateral speed of the other road user is zero, thus correctly assuming an approximate lateral speed of the other road user.

[0028] The control unit's response varies accordingly: While an emergency driving control intervention, such as emergency braking and / or an evasive maneuver, is necessary if a sufficiently high probability of an actual or imminent lane change is detected above a certain threshold, this is not necessary if the control unit detects an intention to change lanes on the part of the other road user. Instead, the control unit decides, based on the current environmental conditions and / or its own driving state, whether the vehicle should cooperate or ignore the detected intention of the other road user. Ignoring the intention is preferred if the vehicle is approaching the other road user at a high relative speed.In a cooperative response, the vehicle itself, controlled by the control unit, can, for example, reduce its own speed, or signal to the other road user that it is yielding via car-to-car communication, or do so, for example, by briefly flashing the headlights.

[0029] According to an advantageous embodiment, the control unit is designed to determine the degree of intention to change lanes by the other road user based on a lateral distance of the front of the other road user's vehicle to a lane boundary of its lane.

[0030] According to a further advantageous embodiment, the control unit is designed to measure the degree of intention to change lanes by the other road user to 24-2703

[0031] 7

[0032] To determine the basis for the illumination status of a direction indicator of another road user.

[0033] According to a further advantageous embodiment, the control unit is designed to take into account the illumination state of the direction indicator:

[0034] - whether several consecutive blink cycles are detected without interruption, and / or

[0035] - whether the direction indicator is activated that is located on the side of the other road user that is closer to a first lane boundary than the opposite side of the other road user is to a second lane boundary opposite the first, and / or

[0036] - whether a lane adjacent to that of the other road user and facing the side of the other road user on which the direction indicator is activated is included in a digital data set.

[0037] According to another advantageous embodiment, the digital data set includes a sensorially detected lane or is stored as a digital map.

[0038] According to a further advantageous embodiment, the control unit is designed to determine the degree of intention to change lanes by the other road user based on the yaw angle of the other road user relative to its lane. The yaw angle refers to the orientation of the other road user around a vertical axis. In other words, the yaw angle is an angle of the other road user in a compass plane relative to its lane.

[0039] According to a further advantageous embodiment, the control unit is designed to determine, below a predetermined speed limit of the other road user, the degree of intention to change lanes by the other road user solely by means of its lateral distance to a lane boundary of its roadway and / or solely on the basis of a yaw angle of the other road user relative to its lane.

[0040] According to a further advantageous embodiment, the control unit is designed to use the yaw angle for determining the measure of an intention only if the other road user is not recognized as a truck, in particular not as a semi-trailer truck, and preferably not as a truck with a trailer.

[0041] According to a further advantageous embodiment, the control unit is designed to measure the degree of intention to change lanes by the other road user to 24-2703

[0042] 8

[0043] To determine the basis of a longitudinal distance between another road user and the end of their lane.

[0044] Preferably, the longitudinal distance of the other road user to the end of their lane is determined if a digital map or sensor-based environmental detection is used to determine that the other road user's lane is an acceleration lane which naturally ends after a certain distance.

[0045] A further aspect of the invention relates to a method for a vehicle, wherein a sensor unit of the vehicle detects the vehicle's environment, including another road user, and generates sensor data about the detected environment, wherein a control unit determines a state of the other road user from the sensor data, the state comprising at least a lateral velocity of the other road user as a component of the state, and wherein, at a lateral velocity below a predetermined limit, the control unit determines a measure of the other road user's intention to change lanes based solely on components of the state that are not based on a movement of the other road user, and above the limit, determines a probability of an impending or already occurring lane change, and at a probability,If a first predefined limit condition is met, an immediate emergency driving control intervention is automatically initiated, and if a measure of intention to change lanes is reached that meets a second predefined limit condition, a decision is made as to whether the vehicle will behave cooperatively interacting with the other road user or not react to the detected intention.

[0046] Advantages and preferred further developments of the proposed procedure result from an analogous and substantive transfer of the above statements made in connection with the proposed system.

[0047] Further advantages, features and details will become apparent from the following description, in which - possibly with reference to the drawing - at least one embodiment is described in detail.

[0048] They show:

[0049] Fig. 1: A bird's-eye view of the application of a system according to an embodiment of the invention. 24-2703

[0050] 9

[0051] Fig. 2: A method according to an embodiment of the invention.

[0052] The representations in the figures are schematic and not to scale.

[0053] Fig. 1 shows a bird's-eye view of a vehicle 1 equipped with a system for assessing the planned and actual behavior of another road user 7 with regard to a possible lane change. The illustration depicts an example situation in which the other road user 7 may be about to change from its current lane to the lane of the vehicle 1. However, the system is not necessarily limited to such a situation. The environment around the vehicle 1 is detected by a sensor unit 3 on the vehicle 1, and the sensor data is transmitted to the control unit 5 of the vehicle 1. The control unit 5 analyzes the sensor data using image recognition and determines the current state of the other road user 7 detected therein.The state has several components, one of which is the current lateral velocity of the other road user 7 relative to its lane. If the other road user 7 has a lateral velocity above a noise-cutting value close to zero, a standard procedure can be carried out to determine the probability of a future lane change, which is not currently occurring. If the probability exceeds a first predefined limit, the vehicle's control unit 5 initiates an emergency driving control intervention to avoid a collision, as an imminent lane change by the other road user 7 is assumed.In a situation where the other road user 7 is practically stationary and therefore has a lateral velocity of essentially zero, the magnitude of the lateral velocity cannot be used, or cannot be meaningfully used, to calculate the probability, since the lateral velocity is a component of the other road user 7's overall speed. Nevertheless, the other road user 7 may have an intention to perform such a lane change, for example, to merge from an acceleration lane onto a regular lane of a highway or other road in a traffic jam. Such an intention is determined using only static components of the other road user 7's state. Static components are all those components of the determined state that do not describe the speed of the other road user 7.Thus, the lateral velocity of the other road user 7 is no more used to determine the measure for the present intention than its rotation rates, in particular its yaw rate about a vertical axis. Rather, components of the state are used which are defined by 24-2703.

[0054] 10

[0055] The sensor unit 3 of vehicle 1 can determine the intention, but these are non-kinematic, in particular a signal from the turn signal of another road user 7, such as its yaw angle relative to the longitudinal axis of its current lane. In Fig. 1, this yaw angle is clearly visible; the front of the other road user 7 is significantly closer to a lane boundary between the lane of the vehicle 1 and the lane of the other road user 7, which indicates a clear intention to change lanes by the other road user 7. Furthermore, a speed-dependent selection of state components can be made to determine the intention: At low speeds, purely geometric factors can be considered, such as the aforementioned yaw angle or the distance of the other road user 7 from the end of its current lane.At higher speeds, other components of the detected state can also be used, such as taking into account the current speed when another road user 7 approaches such a lane end, in order to consider the urgency of a lane change.

[0056] Fig. 2 shows a method for a vehicle 1, wherein a sensor unit 3 of the vehicle 1 detects the environment of the vehicle 1, including another road user 7, S1, and generates sensor data about the detected environment S2, wherein a control unit 5 determines a state of the other road user 7 from the sensor data S3, wherein the state includes at least a lateral velocity of the other road user 7 as a component of the state, and wherein, at a lateral velocity below a predetermined limit, the control unit 5 determines a measure of an intention to change lanes by the other road user 7 only on the basis of components of the state S4 that are not based on a movement of the other road user 7, and above the limit, a probability of an impending or already occurring lane change is determined S5, and at a probability,If a first predefined limit condition is met, an immediate emergency driving control intervention is automatically initiated (S6), and if a measure of intention to change lanes is met that fulfills a second predefined limit condition, a decision is made (S7) as to whether the vehicle 1 will behave cooperatively interacting with the other road user 7 or will not react to the detected intention.

[0057] Although the invention has been further illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples and other variations can be derived from them by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the examples mentioned 24-2703

[0058] 11

[0059] The embodiments shown are merely examples and should not be interpreted in any way as limiting the scope of protection, the possible applications, or the configuration of the invention.

Claims

Patent claims 1. System for a vehicle (1) comprising a sensor unit (3) and a control unit (5), wherein the sensor unit (3) is configured to detect the environment of the vehicle (1) including another road user (7) and to generate sensor data about the detected environment, wherein the control unit (5) is configured to determine a state of the other road user (7) from the sensor data, wherein the state includes at least a lateral velocity of the other road user (7) as a component of the state, and wherein the control unit (5) is configured to determine, at a lateral velocity below a predetermined limit, a measure of the intention to change lanes by the other road user (7) only on the basis of components of the state that are not based on a movement of the other road user (7).and above the limit, to determine a probability of an impending or already occurring lane change, and if the probability meets a first predefined limit condition, to automatically initiate an immediate emergency driving control intervention, and if the measure of an intention to change lanes meets a second predefined limit condition, to make a decision as to whether the vehicle (1) behaves cooperatively interacting with the other road user (7) or does not react to the detected intention.

2. System according to claim 1, wherein the control unit (5) is configured to determine the measure of an intention to change lanes by the other road user (7) on the basis of a lateral distance of a vehicle front of the other road user (7) to a lane boundary of its lane.

3. System according to one of the preceding claims, wherein the control unit (5) is configured to determine the degree of intention to change lanes by the other road user (7) on the basis of the illumination state of a direction indicator of the other road user (7).

4. System according to claim 3, wherein the control unit (5) is configured to, in the lighting state of the Take into account the direction indicator: - whether several consecutive blink cycles are detected without interruption, and / or - whether the direction indicator is activated which is located on a side of the other road user (7) that is closer to a first lane boundary than an opposite side of the other road user (7) to a second lane boundary opposite the first, and / or - whether a lane adjacent to that of the other road user (7) and facing the side of the other road user (7) on which the direction indicator is activated is included in a digital data set.

5. System according to claim 4, wherein the digital data set comprises a sensorially detected lane or is stored as a digital map.

6. System according to one of the preceding claims, wherein the control unit (5) is configured to determine the measure of an intention to change lanes by the other road user (7) on the basis of a yaw angle of the other road user (7) relative to its lane.

7. System according to one of the preceding claims, wherein the control unit (5) is configured to determine, below a predetermined limit speed of the other road user (7), the degree of intention to change lanes by the other road user (7) solely by its lateral distance to a lane boundary of its roadway and / or on the basis of a yaw angle of the other road user (7) relative to its lane.

8. System according to any one of the preceding claims 6 to 7, wherein the control unit (5) is configured to use the yaw angle for determining the measure for an intention only if the other road user (7) is not recognized as a truck.

9. System according to any of the preceding claims, wherein the control unit (5) is configured to measure the intention to Lane changes by the other road user (7) are determined on the basis of a longitudinal distance of the other road user (7) to the end of his lane.

10. Method for a vehicle (1), wherein a sensor unit (3) of the vehicle (1) detects the vehicle's (1) environment, including another road user (7) (S1), and generates sensor data about the detected environment (S2), wherein a control unit (5) determines a state of the other road user (7) from the sensor data (S3), wherein the state includes at least a lateral velocity of the other road user (7) as a component of the state, and wherein, at a lateral velocity below a predetermined limit, the control unit (5) determines a measure of the other road user's (7) intention to change lanes only on the basis of components of the state (S4) that are not based on a movement of the other road user (7), and above the limit, determines a probability of an impending or already occurring lane change (S5).and if a probability that meets a first predefined limit condition, an immediate emergency driving control intervention is automatically carried out (S6), and if a measure of intention to change lanes meets a second predefined limit condition, a decision is made (S7) as to whether the vehicle (1) behaves cooperatively interacting with the other road user (7) or does not react to the detected intention.

Images