Selecting an action option regarding the longitudinal guidance of a motor vehicle with at least automated longitudinal guidance

Abstract

A driving system for automated driving with at least automated longitudinal guidance for a motor vehicle (300), wherein the driving system is configured to: - detect (200) an actual traffic situation (100) in the environment of the motor vehicle (300), which includes at least one other road user (310); - use (210) at least two alternative action options (130, 131) relating to the longitudinal guidance of the vehicle's own motor vehicle (300) based on the actual traffic situation (100) for a first time step; - determine (220) for each of these action options (130, 131) at least one possible future traffic situation (101-105) for the first time step as a consequence of the respective action option (130, 131); - perform an evaluation (250) for each of these possible future traffic situations (101-105); - select (260) one of these action options (130, 131) for the first time step depending thereon;wherein an action option (130, 131) reducing the speed of the own motor vehicle (300) is selected if a collision of the own motor vehicle (300) with the road user (310) is possible in at least one possible future traffic situation (101 - 105), and - the selected action option (130, 131) relating to the longitudinal guidance of the own motor vehicle (300) is executed (270).

Description

The invention relates to a driving system and a method for automated driving with at least automated longitudinal guidance.The term "automated driving" can be understood within the context of the document to mean driving with automated longitudinal or transverse guidance or autonomous driving with automated longitudinal and transverse guidance. The term "automated driving" includes automated driving with an arbitrary degree of automation. Exemplary degrees of automation are assisted, semi-automated, highly automated or fully automated driving. These degrees of automation have been defined by the Federal In Street Industry (BASt) (see BASt publication "Research Compact", Edition 11 / 2012). During assisted driving, the driver continuously performs the longitudinal or transverse guidance, while the system assumes the respective other function within certain limits. In partially automated driving (TAF), the system assumes the longitudinal and lateral guidance for a certain period of time and / or in specific situations, wherein the driver has to monitor the system permanently, as in assisted driving. In highly automated driving (HAF), the system assumes the longitudinal and transverse guidance for a certain period of time without the driver having to monitor the system permanently; however, the driver must be able to assume the vehicle guidance within a certain period of time. In fully automated driving (VAF), the system can automatically handle driving in all situations for a specific application; no driver is required for this application. The above-mentioned four degrees of automation according to the definition of BASt correspond to SAE levels 1 to 4 of the standard SAE J3016 (SAE-Society of Automotive Engineering). For example, the highly automated driving (HAF) according to BASt corresponds to level 3 of the standard SAE J3016. Furthermore, the SAE level 5 is also provided in the SAE J3016 as the highest degree of automation, which is not included in the definition of the BASt. The SAE level 5 corresponds to a non-driver driving, in which the system can automatically handle all situations such as a human driver throughout the trip; a driver is generally no longer required.Methods and devices for motor vehicles are known which influence the longitudinal guidance of an at least partially automated motor vehicle as a function of road users detected in the environment of the motor vehicle.DE 10 2006 046 697 A1 discloses a method in which position data are acquired from a road user located in an intersection. The acquired position data are evaluated and a forecast of the expected movement lines of the road user is created. On the basis of the forecast, it is determined whether conflicts are imminent between the host motor vehicle and the road user, whereupon countermeasures are initiated in order to prevent the conflicts.DE 10 2012 009 297 A1 discloses a method for assisting a driver in driving a vehicle, driver instructions being output as a function of a predicted future potential risk of collision and / or a risk of subsequent collision between the vehicle and other road users within the vehicle. Maneuver options of the vehicle and of the other road users are predicted on the basis of their probabilistically recognized intentions, wherein a plurality of competing situation hypotheses between the vehicle and all relevant other road users are determined on the basis of the maneuver options. In this case, for each situation hypothesis, a risk assessment of a respective potential or real collision risk and / or subsequent collision risk is carried out on the basis of logical context rules. In addition, motion hypothesis trajectory bundles are predicted and used for a determination of a probability of a real collision together with a motion margin between the vehicle and other road users. The situation hypotheses are hierarchically ordered in a priority list on the basis of the intentions as a function of the respective real or acute risk of collision and / or risk of subsequent collision. Furthermore, the driver of the vehicle is informed, warned and / or supported by means of the driver instructions on the basis of the priority list and a determined driver state of the driver and / or driver presets in a plurality of escalating levels, with the aid of an automatic intervention in a longitudinal and / or lateral control of the vehicle, with the information, warning and automatic intervention being carried out for the situation which has a risk of collision and / or a risk of subsequent collision with the highest priority in the priority list and a highest criticality which follows from this.DE 10 2016 113 903 A1 discloses a system comprising a computer which is programmed to identify from a first vehicle one or more second vehicles within a specified distance from the first vehicle. The computer is further programmed to receive data about operations from each of the second vehicles, including travel route data. The computer is programmed to identify a distribution of probabilities for each of a set of possible planned routes based on the data for each of the second vehicles. The computer is further programmed to determine a planned travel route for the first vehicle based on the respective distributions of probabilities of each of the set of possible planned travel routes for each of the second vehicles. The computer is further programmed to provide a command to at least one controller associated with the first vehicle based on the determined scheduled travel route.It is the object of the invention to specify an alternative approach for influencing the longitudinal guidance of a motor vehicle with at least partially automated longitudinal guidance.The object is achieved by the features of the independent claims. Advantageous embodiments are described in the dependent claims. It is pointed out that additional features of a claim dependent on an independent claim can form a separate invention which is independent of the combination of all features of the independent claim without the features of the independent claim or only in combination with a subset of the features of the independent claim and which can be made the subject matter of an independent claim, a divisional application or a subsequent application. This applies in the same way to technical teachings described in the description, which may form an invention independent of the features of the independent claims.A first aspect of the invention relates to a driving system for automated driving with at least automated longitudinal guidance for a motor vehicle.The driving system is configured to detect an actual traffic situation in the environment of the motor vehicle, which comprises at least one further road user in addition to the own vehicle.The actual traffic situation can in particular comprise spatial information relating to the own motor vehicle, the road user and / or the traffic infrastructure. This can be, for example, a position and / or an orientation of the own motor vehicle or of the road user.Alternatively or additionally, the actual traffic situation can also comprise, in particular, dynamic information about the state of the road user or of the traffic infrastructure. This can be, for example, an activation state of a direction indicator of the road user or the current state of a traffic light as traffic infrastructure.The detection of the actual traffic situation can take place in particular by means of sensors of the motor vehicle, for example at least by means of a camera, a laser scanner and / or an ultrasonic sensor.The road user can be, in particular, a motor vehicle, a cyclist, a pedestrian or any other road user.The driving system is furthermore configured to use at least two alternative action options relating to the longitudinal guidance of the host motor vehicle for a first time step, starting from the actual traffic situation.The action options relating to the longitudinal guidance of the host motor vehicle can be, in particular, action options which change the speed of the motor vehicle and, for example, increase or decrease the speed of the motor vehicle. Alternatively or additionally, the action options relating to the longitudinal guidance of the host motor vehicle can also be, in particular, action options which do not change the speed of the motor vehicle.The action options describe, in particular, possibilities for influencing the longitudinal guidance of the motor vehicle, which the motor vehicle can execute in the actual traffic situation. For example, the options for action of the motor vehicle are limited by the drive power of the motor vehicle and by the rules of physics.For each of these action options, at least one possible future traffic situation for the first time step is determined as a result of the respective action option.The action options can be selected from a set of predefined action options and parameterized, for example. Alternatively or additionally, the action options may also be freely determined without having been previously established.A possible future traffic situation can be, in particular, a hypothetical traffic situation which is not actually present at the current point in time. This can comprise, in particular, comparable to the actual traffic situation, spatial information about the own motor vehicle, the road user and / or the traffic infrastructure.Alternatively or additionally, the possible future traffic situation can also comprise dynamic information about the state of the road user or of the traffic infrastructure. A possible future traffic situation for the first time step can be derived from the actual traffic situation in particular by using a stochastic method. For this purpose, for example, the spatial position of a selected road user in a possible future traffic situation for the first time step can be determined by means of a random vector starting from the spatial position of the selected road user in the actual traffic situation.In a possible future traffic situation for the first time step, in particular the spatial position of the host motor vehicle can be determined in such a way that, starting from the spatial position of the host motor vehicle in the actual traffic situation, execution of an option of action relating to the longitudinal guidance of the host motor vehicle is assumed.For each of these possible future traffic situations, an evaluation is carried out, wherein the evaluation comprises in particular an evaluation of the risk potential and / or an evaluation of the driving comfort of the own motor vehicle.One of the action options relating to the longitudinal guidance of the own motor vehicle is selected as a function thereof for the first time step. In this case, in particular, the action option can be selected whose associated traffic situations exhibit the lowest possible risk potential and / or the highest possible driving comfort of the own motor vehicle.The selected option of action relating to the longitudinal guidance of the host motor vehicle is then carried out.In an advantageous embodiment, the driving system is configured to perform an evaluation for each of these possible future traffic situations by determining at least one cost value associated with the respective possible future traffic situation.The cost value can be determined in particular as a function of the spatial position or orientation of the own motor vehicle and / or of a further road user.Alternatively or additionally, the cost value can also be determined in particular as a function of the spatial relationship of the own motor vehicle, at least one road user and / or at least one object of the traffic infrastructure to one another. For example, the cost value can indicate the spatial distance between the own motor vehicle and a road user. In this case, a high cost value may be characteristic of a small spatial distance and a low cost value may be characteristic of a high spatial distance with otherwise the same other influencing variables. The cost value can thus represent, for example, the risk potential for the host motor vehicle.In a further advantageous embodiment, the driving system is configured to determine the cost value as a function of at least one option of action leading to the respective possible future traffic situation, in particular as a function of a braking process and / or an acceleration process of the host motor vehicle. For example, a high cost value may be characteristic of a change in the speed of the motor vehicle that is large in terms of amount. Alternatively, a low cost value may be characteristic of a small change in the speed of the motor vehicle in terms of amount.Alternatively or additionally, the cost value can also be characteristic, for example, of a change in the acceleration of the motor vehicle, wherein both a change in the sign of the acceleration acting on the own motor vehicle and the amount of the change in the acceleration can be taken into account. The cost value can thus represent, for example, the driving comfort of the own motor vehicle or depend on it.In a further advantageous embodiment, the driving system is configured to determine the cost value as a function of the respective possible future traffic situation itself, in particular as a function of a collision of the host vehicle with the road user in the respective possible future traffic situation. For example, a high cost value may be characteristic of a collision of the host motor vehicle with a road user. This high cost value characteristic of a collision can be greater, for example, by at least one order of magnitude than all other cost values without a collision.Alternatively or additionally, in particular a collision risk between the own motor vehicle and a road user can also be included in the cost value. For example, a high cost value may be characteristic of a collision risk, wherein the cost value for a collision risk may be lower than the cost value for an actual collision.In a further advantageous embodiment, the driving system is configured to determine each of these possible future traffic situations as a function of at least one possible movement of the road user.A possible movement of the road user can be determined in particular as a function of the degrees of freedom of the road user. If the road user is a motor vehicle, for example, then the movement options thereof are limited, inter alia, by the maximum steering angle thereof and the drive power thereof. Alternatively, if the road user is a pedestrian, then the movement options thereof are limited by their low movement speed in comparison to motorized road users.By determining possible future traffic situations depending on at least one possible movement of the road user, in particular only possible future traffic situations which can actually occur within the limits of physics are actually considered.Alternatively or additionally, a possible movement of the road user can be determined in particular as a function of the state of the road user himself. If the road user is a motor vehicle, for example, it can be concluded from an activated direction indicator of the road user that and in which direction the road user will turn.The determination of each of these possible future traffic situations as a function of at least one possible movement of the road user is based in particular on the idea that the number of possible future traffic situations can thereby be reduced in comparison with the number of all theoretically possible future traffic situations. As a result, the selection according to the invention of an option of action relating to the longitudinal guidance of the host motor vehicle can be effected more efficiently.In a further advantageous embodiment, the driving system is configured to ascertain a variable characteristic of the probability of occurrence of the respective possible future traffic situation for each of these possible future traffic situations, and to select the option of action as a function thereof.The probability of occurrence of the respective possible future traffic situation can be determined in particular as a function of the probabilities with which the road users change their spatial position and / or their state.For example, in a traffic situation on a traffic circle, the probability with which a motor vehicle as traffic participant leaves the traffic circle on the next possible exit can be taken into account.To determine this probability, the spatial orientation of the motor vehicle can be evaluated, for example. If the front of the motor vehicle is oriented in the direction of the closest possible exit of the circular traffic, then for example the probability that the motor vehicle leaves the circular traffic is higher than the probability that the motor vehicle does not leave the circular traffic.Alternatively or additionally, the probability of occurrence of the respective possible future traffic situation can be determined in particular as a function of the probabilities with which objects of the traffic infrastructure change their state.For example, in the case of a traffic light, it can be assumed that the probability of a change of state increases over time the longer the current state of the traffic light already exists.The probability of a traffic situation occurring can also be time-dependent, in particular. Thus, a possible future traffic situation over time may become more likely or less likely. For example, a vehicle may be moving towards an intersection where the vehicle has multiple turn options. If the vehicle is still far from the intersection, then each turn possibility may be substantially equally likely. However, as soon as the vehicle enters the intersection and points in the direction of an outward travel of the intersection, this one turn possibility can be assumed to be more likely than the other remaining turn possibilities.In a further advantageous embodiment, the driving system is configured to use the variable characteristic of the probability of occurrence of the possible future traffic situation as a weighting factor for the evaluation of the respective possible future traffic situation.Thus, in particular a first possible future traffic situation with a higher probability of occurrence than the second possible future traffic situation can be evaluated as higher than the second possible future traffic situation, if the traffic situations otherwise have the same evaluation.In a further advantageous embodiment, the driving system is configured to determine, for at least one of these possible future traffic situations, at least one action option relating to the longitudinal guidance of the host motor vehicle on the basis of the respective possible future traffic situation for at least one second time step.The at least one second time step follows the first time step. In particular, it can also be more than just one second time step, wherein these further, following time steps are equivalent to the second time step. Therefore, only the second time step is explicitly mentioned in this document.The at least one action option relating to the longitudinal guidance of the own motor vehicle for the second time step can be determined in particular analogously to the action options for the first time step. The determination of the action option for the second time step can differ here, for example, from the determination of the action option for the first time step in that instead of the actual traffic situation a possible future traffic situation represents the initial situation for the determination.For each of these action options for the second time step, at least one possible future traffic situation for the second time step is determined as a result of the respective action option for the second time step.The possible future traffic situations for the at least one second time step can be determined in particular analogously to the possible future traffic situations for the first time step.Because a possible future traffic situation for the second time step can thus be derived from a possible future traffic situation for the first time step, in particular a chain and / or a tree of consecutive possible future traffic situations can be generated.For each of these possible future traffic situations for the second time step, an evaluation is carried out, in particular analogously to carrying out an evaluation of the possible future traffic situations for the first time step.An action option for the first time step is selected, for example, depending on the evaluations of the possible future traffic situations for the first time step and depending on the evaluations of the possible future traffic situations for the at least one second time step.In this case, in particular the evaluations of the possible future traffic situations for the first time step and the evaluations of the possible future traffic situations for the second time step can be evaluated as a function of the tree structure in which all possible future traffic situations are linked to one another by means of action options.For example, for each action option for the first time step, the sum of the values of the evaluations of all possible future traffic situations may be determined, which may originate directly and / or indirectly from the action option. As a result, the action option best evaluated for a certain temporal horizon can be selected.Alternatively, for example, for the first time step, the option of action relating to the longitudinal guidance of the host motor vehicle can also be selected, from which the best-assessed path in the tree structure of the possible future traffic situations begins.In a further advantageous embodiment, an option of action relating to the longitudinal guidance of the host motor vehicle is a reduction in the speed of the host motor vehicle. A reduction in the speed of the motor vehicle can lead in particular to a reduction in the risk potential and, for example, to a reduction in the risk of collision with other road users.A second aspect of the invention relates to a method for automated driving with at least automated longitudinal guidance for a motor vehicle.In this case, an actual traffic situation in the environment of the motor vehicle, which comprises at least one further road user, is detected, and at least two alternative action options relating to the longitudinal guidance of the host motor vehicle are used for a first time step, starting from the actual traffic situation.For each of these possible action options, at least one possible future traffic situation is determined as a result of the respective action option, and an assessment is made for each of these possible future traffic situations.One of these action options is selected depending on this, and the selected action option relating to the longitudinal guidance of the own motor vehicle is executed.The above explanations regarding the driving system according to the invention according to the first aspect of the invention also apply in a corresponding manner to the method according to the invention according to the second aspect of the invention. Advantageous exemplary embodiments of the method according to the invention according to the second aspect of the invention that are not explicitly described at this point and in the patent claims correspond to the advantageous exemplary embodiments of the driving system according to the invention according to the first aspect of the invention that are described above or described in the patent claims.The invention is described below on the basis of an exemplary embodiment with the aid of the appended drawings. In these show: FIG. 1 shows an exemplary tree structure of traffic situations and action options, FIG. 2 shows an exemplary flow chart for the mode of operation of the driving system according to the invention, FIG. 3 ashows an exemplary traffic situation, and FIG. 3 b shows exemplary curves of probabilities.FIG. 1 shows an example tree structure of traffic situations 100- 109 and action options 130- 133.The actual traffic situation 100 represents the root node of the tree structure. The actual traffic situation 100 describes, for example, the spatial position of one's own vehicle 300 and of a plurality of additional road users 310, such as other motor vehicles or pedestrians (cf. FIG. 3 afor the positions).Starting from the actual traffic situation 100, two different action options 130, 131 relating to the longitudinal guidance of the own motor vehicle 300 are available to the own motor vehicle 300 for a first time step. These options for action can cause, for example, a change in the speed of the motor vehicle 300, such as, for example, an acceleration maneuver or a braking process.If the own motor vehicle 300 were to execute the action option 130, then no traffic situation would result from this alone, since it is not yet possible to infer a change in the spatial position of the additional road users 310 for the first time step alone from the action option 130. For this reason, the exemplary tree structure includes auxiliary nodes 120-123.Proceeding from the auxiliary node 120, various assumptions 140- 142 can be made for a change in the spatial position of the additional road users 310 for the first time step, for example by means of a stochastic process or by evaluating the degrees of freedom of movement of the additional road users 310. These assumptions can be interpreted, for example, as assumed, non-actual sensor values.Based on the assumptions 140- 142 for a change in the spatial position of the additional road users 310 and the action option 130 of the own motor vehicle 300, different possible future traffic situations 101- 103 result for the first time step.If the own motor vehicle 300 were to execute the option 131 of action, assumptions 143, 144 can likewise be made for a change in the spatial position of the additional road users 310. These assumptions 143, 144 may differ from the assumptions 140- 142, for example, but they may also be at least partially the same assumptions.Based on the assumptions 143, 144 for a change in the spatial position of the additional road users 310 and the action option 131 of the own motor vehicle 300, different possible future traffic situations 104, 105 result for the first time step.For a second time step following the first time step, two action options 132, 133 are again available to the own motor vehicle 300, for example, starting from the possible future traffic situation 104.If the own vehicle 300 were to execute the action option 132 in the second time step, assumptions 145, 146 can be made again for a change in the spatial position of the additional road users 310 for the second time step on the basis of the possible future traffic situation 104 for the first time step.Based on the assumptions 145, 146 for a change in the spatial position of the additional road users 310 and the action option 132 of the own motor vehicle 300, different possible future traffic situations 106, 107 result for the second time step. If the own motor vehicle 300 were to execute the action option 133 in the second time step, assumptions 147, 148 can likewise be made for a change in the spatial position of the additional road users 310 for the second time step on the basis of the possible future traffic situation 104 for the first time step.Based on the assumptions 147, 148 for a change in the spatial position of the additional road users 310 and the action option 133 of the own motor vehicle 300, different possible future traffic situations 108, 109 result for the second time step.FIG. 2 shows an exemplary flow chart for the mode of operation of the driving system according to the invention.In step 200, an actual traffic situation 100 in the environment of the host motor vehicle 300 is detected, for example, by means of the sensor system of the host motor vehicle 300.On the basis of the actual traffic situation 100, at least two alternative action options 130, 131 relating to the longitudinal guidance of the own motor vehicle 300 are used for a first time step in step 210. These can be selected, for example, from a predetermined set of possible action options.These options for action can be, for example, an increase 130 in the speed of the host motor vehicle 300 and a decrease 131 in the speed of the host motor vehicle 300.For each of these action options, possible future traffic situations 101- 105 are determined for the first time step in step 220. The possible future traffic situations 101- 105 assigned to an action option 130, 131 can in particular each describe different spatial positions of the other road users 310.The spatial positions of the other road users 310 can be determined in particular by assuming possible, observable movements of the other road users 310. If a road user 310 is located in a circular traffic, for example, possible, observable movements of this road user 310 are leaving 144 the circular traffic at the next exit or remaining 143 in the circular traffic. Of these two possible, observable movements 143, 144, one of a possible future traffic situation 104, 105 can be included, for example.In the following step 230, action options 132, 133 relating to the longitudinal guidance of the host motor vehicle 300 are used for a second time step. These action options 132, 133 are based, for example, on a possible future traffic situation 104 of the first time step.For each of these action options 132, 133, possible future traffic situations 106- 109 are determined in step 240 analogously to step 220 on the basis of possible, observable movements 145- 148 of the other road users 310.In step 250, all possible future traffic situations 101- 109 are evaluated, wherein both the possible future traffic situations 101- 105 of the first time step and the possible future traffic situations 106- 109 of the second time step are evaluated.This evaluation can include, in particular, properties of the possible future traffic situations 101- 109, such as, for example, the distance of the own vehicle 300 from the other road users 310. Since a large distance of the own vehicle 300 from the other road users 310 can be interpreted as a very safe state, a large distance can be evaluated comparatively positively. In contrast, for example, a collision of the host motor vehicle 300 with a road user 310 may be evaluated to be comparatively negative.If the evaluation is carried out, for example, by means of a cost function, the cost value can be, for example, in the opposite direction to the distance of the own motor vehicle 300 from the other road users 310. A large distance thus results in a low cost value. A collision of the host motor vehicle 300 with a road user 310 can in this case lead, for example, to a very high cost value.Alternatively or additionally, the action options 130- 133 leading to the respective future traffic situation 101- 109 can also be included in this evaluation. In particular, for this purpose, the influence of an action option 130- 133 on the driving comfort of the own motor vehicle 300 can be determined. For example, a change in the speed of the own motor vehicle 300 which is large in terms of amount is to be assessed rather negatively with regard to the driving comfort. For example, in this case, a comparatively high cost value can be incorporated into the evaluation of the possible future traffic situation 101- 109. Alternatively, in the case of a change in the speed of the own motor vehicle 300 that is small in terms of amount, only a comparatively low cost value can be included in the evaluation of the possible future traffic situation 101- 109.Alternatively or additionally, in particular the probability of occurrence of a possible future traffic situation 101- 109 can also be included in the evaluation of the possible future traffic situation 101- 109, for example in the form of a weighting factor. This can take account of the fact that a very probable possible future traffic situation 101- 109 can have a greater influence on the selection of an action option 130, 131 than a rather unlikely possible future traffic situation 101- 109.In step 260, an action option 130, 131 is selected for the first time step depending on step 250. For this purpose, the evaluations of the possible future traffic situations attributable to the action option 130, 131 can be combined, in particular for each action option 130, 131. For example, for a first action option 130, the evaluations of the possible future traffic situations 101- 103 that can be returned to the first action option can be summed up. For a second action option 131, the evaluations of the possible future traffic situations 104- 109 that can be returned to the second action option can likewise be summed up.If the evaluations are, for example, cost values, then that action option 130, 131 which has the lowest summed cost value can be selected for the first time step.In particular, if a collision of the own motor vehicle 300 with the further road user 310 can occur in a selected possible future traffic situation 107, this can have a great influence on the selection of the option of action 130, 131 relating to the longitudinal guidance of the own motor vehicle 300. If, for example, a very high cost value is assigned to a possible future traffic situation 107 because of the collision, which cost value is greater by at least an order of magnitude than the cost values of all other possible future traffic situations 101- 106, 108, 109, the selection of the action option 131 that can lead to the selected possible future traffic situation 107 is thereby very unlikely.In particular, this implicitly leads to the driving system according to the invention selecting comparatively careful action options 130, 131 that reduce the speed of the own motor vehicle 300 if at least one possible future traffic situation 107 is located in the tree structure, in which a collision of the own motor vehicle 300 with a further road user 310 is possible.An action option 130, 131 reducing the speed of the own motor vehicle 300 has, for example, the effect in turn that the time until the possible, actual occurrence of the collision is extended, whereby in turn more time is obtained for a more accurate determination of the actual behavior of the further road user 310.In step 270, the action option 130, 131 selected in step 260 is executed for the first time step. In this case, the longitudinal guidance of the own motor vehicle 300 is influenced in such a way as the selected option of action 130, 131 specifies. For example, the speed of the own motor vehicle 300 may be increased 130 or decreased 131.As soon as the second time step actually occurs, the driving system according to the invention can be executed again, in particular beginning with step 200, wherein the actual traffic situation 100 has changed apparently in the meantime. Alternatively or additionally, however, it is also possible at least to store intermediate results of individual sequence steps for the first time step in a memory module which the driving system comprises and to reuse them in the actual, second time step when the driving system is executed again.FIG. 3 ashows an exemplary traffic situation for illustrating the driving system according to the invention.One's own motor vehicle 300 is located in front of an intersection into which a vehicle 310 enters from the left as a further road user.For example, the host motor vehicle 300 plans to traverse the intersection on the path 301, whereas it is not unambiguously determinable for the host motor vehicle 300 whether the further road user 310 will traverse the intersection on the path 311 or whether the further road user 310 will turn right on the path 312.FIG. 3 bshows an exemplary time profile of probabilities that can be evaluated by the driving system according to the invention. Curve 321 indicates the time-dependent probability that further road user 310 is just crossing the intersection on path 311, and curve 322 indicates the time-dependent probability that further road user 310 is turning right on path 312. Over the time plotted on the abscissa, the probabilities that can be evaluated by the driving system change in such a way that up to a time t=9 s, the two possible movement paths 311, 312 appear to be substantially the same probability for the further road user 310. Starting from the time t=9 s, the probability 321 that the further road user 310 decides on the path 311 crossing the intersection rises rapidly.One reason for this can be, for example, that the further road user 310 is already very close to the intersection and has still not activated a turn signal indicator or its behavior must become recognizable due to the progress of the situation. From this, it can be concluded that the further road user 310 wishes to drive straight ahead.The movement path 311 of the road user 310, which directly crosses the intersection, can lead to a possible future traffic situation 107, in which a collision of the own motor vehicle 300 with the road user 310 is imminent.Since this possible future traffic situation 107 has a very high cost value, for example, the driving system according to the invention will likely tend to select 260 an action option 130, 131 that cannot lead to this possible future traffic situation 107 up to the time t=9 s. These action options 130, 131 tend to be action options 130, 131 that at least do not increase the speed of the motor vehicle 300. In particular, these are action options 130, 131 that reduce the speed of the motor vehicle 300 to generate a waiting behavior until further action options become apparent.

Claims

Driving system for automated driving with at least automated longitudinal guidance for a motor vehicle (300), wherein the driving system is configured to - capture (200) an actual traffic situation (100) in the environment of the motor vehicle (300), which comprises at least one further road user (310), - use (210) at least two alternative action options (130, 131) relating to the longitudinal guidance of the own motor vehicle (300) for a first time step starting from the actual traffic situation (100), - determine (220) for each of these action options (130, 131) at least one possible future traffic situation (101 - 105) for the first time step as a consequence of the respective action option (130, 131), - perform (250) an evaluation for each of these possible future traffic situations (101 - 105), - select (260) one of these action options (130, 131) as a function thereof for the first time step, wherein an action option (130, 131) reducing the speed of the own motor vehicle (300) is selected if a collision of the own motor vehicle (300) with the road user (310) is possible in at least one possible future traffic situation (101-105), and - the selected action option (130, 131) is executed (270) with respect to the longitudinal guidance of the own motor vehicle (300).The driving system according to claim 1, wherein the driving system is configured to - perform (250), for each of these possible future traffic situations (101-105), an evaluation by determining at least one cost value associated with the respective possible future traffic situation (101-105).Driving system according to Claim 2, wherein the driving system is set up to - determine (250) the cost value as a function of at least one option of action (130, 131) leading to the respective possible future traffic situation (101 - 105), in particular as a function of a braking process and / or an acceleration process of the own motor vehicle (300).Driving system according to Claim 2 or 3, wherein the driving system is set up to - determine (250) the cost value on the basis of the respective possible future traffic situation (101 - 105) itself, in particular on the basis of a collision of the host vehicle (300) with the road user (310) in the respective possible future traffic situation (101 - 105).Driving system according to one of the preceding claims, wherein the driving system is configured to - determine (220, 240) each of these possible future traffic situations (101 - 105) as a function of at least one possible movement (140 - 144) of a road user (310).Driving system according to one of the preceding claims, wherein the driving system is configured - to determine a variable characteristic of the probability of occurrence of the respective possible future traffic situation (101 - 105) for each of these possible future traffic situations (101 - 105), and - to select (260) the option of action (130, 131) as a function thereof.Driving system according to Claim 6, wherein the driving system is set up to - use (250) the variable which is characteristic of the probability of occurrence of the possible future traffic situation (101 - 105) as a weighting factor for the evaluation of the respective possible future traffic situation (101 - 105).Driving system according to one of the preceding claims, wherein the driving system is configured - to determine (230), for at least one of these possible future traffic situations (101 - 105) for the first time step, one or more action options (132, 133) relating to the longitudinal guidance of the own motor vehicle (300) on the basis of the respective possible future traffic situation (104) for at least one second time step, - to determine (240), for each of these action options (132, 133) for the second time step, at least one possible future traffic situation (106 - 109) for the second time step as a consequence of the respective action option (132, 133) for the second time step, - to perform (250) an evaluation for each of these possible future traffic situations (106 - 109) for the second time step, and - to perform (250) an action option (130, 131) for the first time step, depending on the evaluations of the possible future traffic situations ( 101- 105) for the first time step and depending on the evaluations of the possible future traffic situations ( 106- 109) for the at least one second time step ( 260).Driving system according to one of the preceding claims, wherein - an option of action (130 - 133) relating to the longitudinal guidance of the own motor vehicle (300) is a reduction in the speed of the own motor vehicle (300).Method for automated driving with at least automated longitudinal guidance for a motor vehicle (300), wherein - an actual traffic situation (100) in the environment of the motor vehicle (300), which comprises at least one further road user (310), is detected (200), - at least two alternative action options (130, 131) relating to the longitudinal guidance of the own motor vehicle (300) are used (210) for a first time step starting from the actual traffic situation (100), - for each of these action options (130, 131), at least one possible future traffic situation (101 - 105) is determined (220) as a result of the respective action option (130, 131), - for each of these possible future traffic situations (101 - 105), an evaluation is carried out (250), - one of these action options (130, 131) is selected (260) as a function thereof, wherein an action option (130, 131) reducing the speed of the own motor vehicle (300) is selected if a collision of the own motor vehicle (300) with the road user (310) is possible in at least one possible future traffic situation (101-105), and - the selected action option (130, 131) is executed (270) with respect to the longitudinal guidance of the own motor vehicle (300).

Images