Method for Planning a Target Trajectory of an Autonomous Vehicle

Abstract

The present invention relates to a method for planning a target trajectory for an autonomous vehicle (1), wherein for each object (2, 3) detected during a planning period, a quality value (Q) representing a measure of the reliability of the detection of the object (2, 3) is determined. For each object (2, 3), a minimum allowable acceleration (aQ) that is allowed when the vehicle (1) brakes towards the object (2, 3) is determined depending on the quality value (Q) of the object. A trajectory candidate and an object cost determined for the trajectory candidate are evaluated depending on the acceleration (ax(t)) set by each trajectory candidate and depending on the minimum allowable acceleration (aQ) when braking towards the object (2, 3). The selection of the target trajectory is made from a set of trajectory candidates depending on the trajectory cost, and additionally taking into account the evaluation of the trajectory candidates and the object costs determined for those trajectory candidates.

Description

Technical Field

[0001] The present invention relates to a method for planning a target trajectory of an autonomous vehicle as recited in the preamble of claim 1.

Background Art

[0002] From German Patent Application Publication No. 102020108857, a method for planning a target trajectory that a vehicle should automatically follow is known. This planning is based on the determination of a set of separate candidates for the target trajectory and the selection of one candidate from the determined set of candidates. The selection is based on a predetermined cost function. When changes in the surrounding conditions to be complied with and the driving tasks to be executed are confirmed, the cost function for the individual trajectory sections of the candidates is adapted to the changed surrounding conditions and driving tasks, thereby performing pre-control of the selection, whereby a lower cost is assigned to the trajectory sections that are more suitable for complying with the changed surrounding conditions and executing the changed driving tasks than to other trajectory sections. The target trajectory, as a data set, includes both information on the position path that the vehicle should follow when traveling on the target trajectory and information on the acceleration and traveling speed when the vehicle moves on the target trajectory. Furthermore, the set of trajectories including the selected target trajectory is discretized (a plurality of trajectories including the selected target trajectory are made separate), and at that time, a predetermined set of temporally ordered trajectory support points is determined in the forward region, and a set of trajectories passing through different trajectory support points in temporal order is determined. The set of trajectories passing through the trajectory support points in temporal order forms a group of trajectories that are considered as candidates when selecting the target trajectory. For each trajectory in the group of trajectories, the cost is determined using a predetermined cost function, and at that time, the total cost of the trajectory section is determined using the weighted sum of the costs of the trajectory sections determined for various surrounding conditions. The cost of a certain trajectory is determined using the sum of the total costs of its trajectory sections. Subsequently, as the target trajectory, the trajectory having the lowest cost is selected from the group of trajectories.

[0003] From German Patent Application Publication No. 10 2020 200 183, a method for controlling a vehicle is known in which, for the surroundings of the vehicle, a probabilistic free space map including static and dynamic objects is created, a trajectory of the vehicle is planned taking into account the probabilistic free space map, and is optimized using a cost function.

[0004] From German Patent Application Publication No. 10 2015 016 544, a method for determining an avoidance trajectory of a vehicle for driving around an obstacle is known, in which the avoidance trajectory is optimized with respect to a predetermined criterion, and the predetermined criterion includes an upper limit of the acceleration of the vehicle, a lower limit of the distance to the obstacle, and a lateral velocity at the end of the avoidance trajectory.

[0005] From German Patent Application Publication No. 10 2016 218 121, a method for planning a trajectory is known, in which, for planning the trajectory, a motion model of the host vehicle, objects related to collisions, and driving physical restrictions are used. Here, each of a plurality of possible trajectories is evaluated using a cost function, and subsequently, the trajectory having the minimum cost is selected.

SUMMARY OF THE INVENTION

PROBLEM TO BE SOLVED BY THE INVENTION

[0006] An object of the present invention is to provide a novel method for planning a target trajectory of an autonomous vehicle.

MEANS FOR SOLVING THE PROBLEM

[0007] According to the present invention, this object is achieved by a method having the features described in claim 1.

[0008] Advantageous embodiments of the present invention are the subject matter of the dependent claims.

[0009] In a method for planning a target trajectory for an automated vehicle, in particular a highly automated vehicle or an autonomous vehicle, a set of trajectory candidates is set for a predetermined planning period. Each trajectory candidate sets a path that the vehicle should follow if that trajectory candidate is selected as the target trajectory, and also sets an acceleration when the vehicle should follow that path. An object is detected within the planning period, and a trajectory cost is assigned to each trajectory candidate using a predetermined cost function, where the cost function includes an object cost that depends on (corresponds to) the detected object. Here, the object cost of an object for a certain trajectory candidate increases as the distance between the object and that trajectory candidate decreases. The target trajectory is selected from the set of trajectory candidates depending on the trajectory cost.

[0010] According to the invention, for each detected object, a quality value representing a measure of the reliability of the detection of the object is determined. For each object, depending on the quality value of that object, a minimum allowable acceleration is determined that is allowed when the vehicle brakes towards that object. The trajectory candidates, and the object costs determined for those trajectory candidates, are evaluated depending on the acceleration set by each trajectory candidate and depending on the minimum allowable acceleration when braking towards the object. The selection of the target trajectory is additionally performed taking into account the evaluation of the trajectory candidates and the object costs determined for those trajectory candidates.

[0011] By this method, in a traffic scenario with, for example, multiple objects, the quality of object detection, i.e., the probability of existence, can be taken into account, and the maximum brake intervention when automatically controlling the vehicle can be adapted accordingly. This ensures that a stronger brake intervention than is allowed is not performed only by objects with low detection quality. However, if a stronger brake intervention is required based on an object with higher detection quality, performing that stronger brake intervention remains an option. It is also possible to avoid driving past objects with low detection quality.

[0012] In one possible embodiment of this method, as the target trajectory, a trajectory candidate having the lowest trajectory cost is selected from the set of trajectory candidates. Therefore, the trajectory that has the least impact on the vehicle from the detected object and / or the trajectory with the fewest existing objects is selected as the target trajectory.

[0013] In another possible embodiment of this method, category classification is performed during evaluation, and in this category classification, an unfiltered category and a filtered category are distinguished. At this time, all object costs and corresponding (related, suitable) trajectory candidates are assigned to the unfiltered category. That is, the trajectory candidates are not filtered. Only the object costs and corresponding trajectory candidates for which the minimum value of the acceleration set by each trajectory candidate is greater than the minimum allowable acceleration of each object are assigned to the filtered category. As a result, only the trajectory candidates whose acceleration is within the allowable range determined by the minimum allowable acceleration can be assigned to the filtered category. That is, trajectory candidates that result in an unacceptable level of braking are not included in the filtered category. By considering category classification, the reliability of this method can be further improved.

[0014] In another possible embodiment of this method, when selecting the target trajectory, a trajectory candidate having the lowest trajectory cost is selected from the unfiltered category and the filtered category, respectively. For the two selected trajectory candidates, the minimum value of the acceleration set by each trajectory candidate is determined, and the candidate with the larger minimum value is selected as the target trajectory. This means that when there are multiple possible trajectories, a trajectory with a not-too-strong brake applied towards the object is selected as the target trajectory while maintaining the same level of safety, so the comfort of the vehicle occupants can be improved while maintaining the same level of safety.

[0015] Hereinafter, embodiments of the present invention will be described in detail based on the drawings.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Modes for Carrying Out the Invention

[0017] In any of the figures, corresponding parts are denoted by the same reference numerals.

[0018] In FIG. 1, when the automated driving vehicle 1, particularly a highly automated driving vehicle or a self-driving vehicle shown in detail in FIG. 6, follows the paths of the tracks T1 to Tn shown in FIG. 5, the acceleration ax(t) of the vehicle 1 depending on time t (as a function of time t) and the temporal progression of the longitudinal position x(t) of the vehicle 1 corresponding to the acceleration are shown.

[0019] Each of the tracks T1 to Tn is represented by its longitudinal position x(t), transverse position, and their derivatives, i.e., the longitudinal (vertical) and transverse (horizontal) velocities, and the longitudinal acceleration ax(t) and transverse acceleration up to the planning period (planning area, planning range, planning point) P. Here, the longitudinal position x(t) is derived by integrating the predefined acceleration ax(t). The acceleration ax(t) is defined such that the integrated longitudinal position x(t) satisfies the following determination conditions. x1(t) < x2(t) (1) And min(ax1(t)) < min(ax2(t)), provided that t = [0, P] (2)

[0020] Here, x1(t) = the longitudinal position x(t) when following track T1 x2(t) = the longitudinal position x(t) when following track T2 ax1(t) = the longitudinal acceleration when following track T1, ax2(t) = the longitudinal acceleration when following track T2 is.

[0021] In addition to the path that vehicle 1 should follow, for the tracks T1 to Tn, the acceleration profile (acceleration curve) when vehicle 1 follows that path is also set. Here, the acceleration ax(t) is the temporal acceleration profile (temporal acceleration curve) when following the tracks T1 to Tn. The acceleration ax(t) represents a negative acceleration when vehicle 1 decelerates. The acceleration ax(t) has a minimum value min(ax(t)).

[0022] Examples of the different temporal profiles of the accelerations ax1(t), ax2(t) of vehicle 1, and the corresponding temporal profiles of the longitudinal positions x1(t), x2(t) of vehicle 1, as well as the minimum values min(ax1(t)), min(ax2(t)) of the accelerations ax1(t), ax2(t) when the vehicle follows the paths of different tracks T1, T2 are shown in Figure 2.

[0023] In a method for planning a target trajectory for the autonomous vehicle 1, for example, a plurality of trajectories T1 to Tn are set in the form of a set of trajectories. The number of trajectories T1 to Tn is, for example, on the order of 1000.

[0024] Here, the following conditions apply. x1(t) < x2(t), provided that min(ax1(t)) < min(ax2(t)) (3)

[0025] This condition means that when min(ax1(t)) < min(ax2(t)), for any two trajectories T1 and T2, the trajectories T1 to Tn of the trajectory set are determined such that x1(t) < x2(t) holds. This is a peripheral condition applied when setting the trajectories T1 to Tn.

[0026] That is, in order to plan the target trajectory, a set of trajectory candidates for a predetermined planning period P is set, and each trajectory candidate sets the path that the vehicle 1 should follow when the trajectory candidate is selected as the target trajectory, and also sets the acceleration ax(t) when the vehicle 1 should follow that path.

[0027] In order to plan the target trajectory, objects 2 and 3 during the planning period P, which are shown in more detail in FIG. 6, are detected, and a trajectory cost is assigned to each trajectory candidate using a predetermined cost function. Here, the cost function includes an object cost that depends on the detected objects 2 and 3, and the object costs of objects 2 and 3 for a certain trajectory candidate increase as the distance between objects 2 and 3 and that trajectory candidate decreases. Subsequently, the target trajectory is selected from the set of trajectory candidates depending on the trajectory cost.

[0028] At this time, for each detected object 2 and 3, a measure of the reliability of the detection of the object 2 and 3, that is, a quality value Q representing the probability of the existence of the objects 2 and 3 around the vehicle 1 is determined.

[0029] Furthermore, for each object 2 and 3, depending on the quality value Q of that object, a minimum allowable acceleration aQ that is allowed when the vehicle 1 brakes toward the corresponding object 2 and 3 is determined.

[0030] Figure 3 shows such a minimum allowable acceleration aQ that depends on the detection reliability of objects 2 and 3, that is, depends on the quality value Q of objects 2 and 3. When the vehicle applies brakes, the minimum allowable acceleration aQ has a negative value. Since a negative acceleration is deceleration, the minimum allowable acceleration aQ simultaneously determines the maximum allowable deceleration.

[0031] The determination of the minimum allowable acceleration aQ allowed when applying brakes toward objects 2 and 3 is made in consideration of the following conditions. min(ax(t))≧aQ (4)

[0032] Here, min(ax(t)) is the minimum acceleration in orbits T1 to Tn, and when applying brakes, min(ax(t)) also becomes a negative value.

[0033] That is, in formula (4), it is checked whether the acceleration aQ when applying brakes remains within the allowable range, and this allowable range is determined by the quality value Q of the corresponding objects 2 and 3.

[0034] Here, it is important that for each value of the minimum allowable acceleration aQ, there exists at least one predetermined orbit T1 to Tn, and in this case, the following applies. min(ax(t))=aQ (5)

[0035] In Figure 3, both the minimum allowable acceleration aQ and the quality value are divided into low, medium, and high regions. It is clear that applying brakes with the maximum force is only allowed when objects 2 and 3 have a high quality value Q (represented by the non-hatched region). On the other hand, for objects 2 and 3 with medium and low quality values Q, such braking is not permitted (represented by the hatched region).

[0036] In order to avoid problems during the planning of the target trajectory when it is possible to avoid a collision between the vehicle 1 and objects 2, 3 with a low quality value Q only on the target trajectory using a brake stronger than that allowed, and further, the trajectory candidates and the object costs determined for those trajectory candidates are evaluated depending on the acceleration ax(t) set by each of the trajectory candidates and depending on the minimum allowable acceleration aQ when braking towards objects 2, 3, and the selection of the target trajectory is additionally carried out in consideration of the evaluation of the trajectory candidates and the object costs determined for those trajectory candidates.

[0037] Here, the object cost of an object is evaluated for each trajectory in the trajectory group. In this case, as already explained, the object costs of objects 2, 3 for a trajectory candidate increase as the longitudinal and transverse distances between objects 2, 3 and the trajectory candidate become smaller.

[0038] When there are a plurality of objects 2, 3, each of those objects 2, 3 may contribute to the object cost of the trajectory candidate. In such a case, it is examined which of the objects 2, 3 is most relevant, i.e., most contributing, with respect to the object cost, and the determination of the object cost for the trajectory candidate is made exclusively based on the most relevant objects 2, 3. In other words, objects 2, 3 with low relevance are not considered when determining the object cost.

[0039] When evaluating the trajectory candidates and the object costs determined for those trajectory candidates, a category classification is performed in which the unfiltered category A and the filtered category F shown in FIG. 5 are distinguished. At this time, all object costs and the corresponding trajectory candidates are assigned to the unfiltered category A. On the other hand, to the filtered category F, only the object costs and the corresponding trajectory candidates for which the minimum value min(ax(t)) of the acceleration set by each trajectory candidate is greater than the minimum allowable acceleration aQ of each of the objects 2, 3 are assigned.

[0040] Due to the quality values of objects 2 and 3, a maximum braking acceleration of aQ = -5 m / s towards those objects 2 and 3 is allowed, and in the corresponding trajectories T1 to Tn, when a braking is required such that the minimum acceleration min(ax(t)) decreases to a value of -2 m / s 2 the condition min(ax(t)) > aQ, that is, -2 m / s 2 > -5 m / s 2 is satisfied. The corresponding trajectories T1 to Tn and the object costs are assigned to both category A and category F. 2 Due to the quality values of objects 2 and 3, a maximum braking acceleration of aQ = -5 m / s towards those objects 2 and 3 is allowed, and in the corresponding trajectories T1 to Tn, when a braking is required such that the minimum acceleration min(ax(t)) decreases to a value of -6 m / s

[0041] the condition min(ax(t)) > aQ is not satisfied. In this case, the corresponding trajectories T1 to Tn and the object costs are assigned to unfiltered category A but not to filtered category F. 2 Figure 4 shows a possible example of the procedure of a method for determining the object cost. 2 In the first branch V1, it is checked whether all the trajectory candidates of the trajectory group have already been evaluated. In the affirmative case represented by the Yes branch J1, the method ends.

[0042] In the negative case represented by the No branch N1, in the second branch V2, it is checked whether all the objects 2 and 3 of the trajectory candidates have been evaluated. In the affirmative case represented by the Yes branch J2, in method step S1, the next trajectory candidate is selected and the method is restarted for that trajectory candidate.

[0043]

[0044]

[0045] ​​In the negative case represented by the branch N2 of No, in a further method step S2, the determination of the object cost for the corresponding objects 2, 3 of the corresponding orbit candidates is carried out.

[0046] Subsequently, in the third branch V3, the condition according to equation (4) is inspected, and it is determined whether the minimum acceleration in the corresponding orbits T1~Tn is greater than the minimum allowable acceleration aQ.

[0047] In the positive case represented by the branch J3 of Yes, in a further method step S3, in the unfiltered category A and the filtered category F, the object cost for the corresponding orbits T1~Tn is updated.

[0048] In the negative case represented by the branch N3 of No, in a further method step S4, the object cost for the corresponding orbits T1~Tn is updated only in the unfiltered category A.

[0049] After the execution of method step S3 or method step S4, in a further method step S5, the next objects 2, 3 of each orbit candidate are selected, and for those objects 2, 3, the inspection in branch V2 is continued.

[0050] That is, for each orbit T1~Tn in the orbit group and each object 2, 3 included in the set of the plurality of objects 2, 3, the object cost for each orbit T1~Tn is calculated. If the condition min(ax(t))>aQ is satisfied for each orbit T1~Tn and each object 2, 3, the object cost is assigned to both categories A and F, and if it is not satisfied, it is assigned only to the unfiltered category A.

[0051] When all the object costs for all possible combinations of the orbits T1~Tn have been calculated, the two best orbits T1~Tn are obtained from both categories A and F, and the target orbit is selected from the two orbits T1~Tn.

[0052] FIG. 5 shows a possible embodiment of the procedure of the method for such determination and selection.

[0053] Here, in method step S6, the trajectories T1 to Tn with the lowest cost are obtained from all the unfiltered Category A trajectories T1 to Tn.

[0054] In another method step S7, the trajectories T1 to Tn with the lowest cost are obtained from all the filtered Category F trajectories T1 to Tn.

[0055] Subsequently, at branch V, it is checked whether the minimum acceleration min(ax(t)) in the unfiltered Category A trajectories T1 to Tn is greater than or equal to the minimum acceleration min(ax(t)) in the filtered Category F trajectories T1 to Tn.

[0056] In the affirmative case represented by the Yes branch J, in method step S8, the corresponding trajectories T1 to Tn of the unfiltered Category A are selected as the target trajectories. In the negative case represented by the No branch N, in method step S9, the corresponding trajectories T1 to Tn of the unfiltered Category A are selected as the target trajectories.

[0057] FIG. 6 shows a plan view of a traffic scenario in which the vehicle 1 and a plurality of objects 2, 3 exist, where the object 2 has a low quality value Q and the object 3 has a high quality value Q.

[0058] For example, if the trajectory T5 is the most suitable cost (the most cost - efficient) trajectory candidate from the filtered Category F, and it is set (specified) that the acceleration ax(t) should be decreased to a value of, for example, - 5m / s 2 then min(ax5(t)) = - 5m / s 2 is applied.

[0059] In the unfiltered Category A, for example, the trajectory T1 is the most suitable cost trajectory candidate. The trajectory T1 is set (specified) to reduce the acceleration ax(t) to, for example, a value of -3 m / s 2 That is, min(ax1(t)) = -3 m / s 2 is applied.

[0060] -3 m / s 2 ≧ -5 m / s 2 In the case of, since the condition min(ax1(t)) ≧ min(ax5(t)) is satisfied, the trajectory T1 is selected as the target trajectory. On the other hand, if this condition is not satisfied, the trajectory T5 is selected as the target trajectory.

[0061] For example, in the case of min(ax1(t)) = -5 m / s 2 both the trajectories T1 and T5 are braked with the same acceleration ax(t) towards the forward object 3. The trajectory T1 also considers the object 2 with a low quality value Q. In contrast, it is not considered in the trajectory T5. Since the condition min(ax1(t)) ≧ min(ax5(t)) is also satisfied here, the trajectory T1 is selected as the target trajectory, and thus the object 2 with a low quality value Q is avoided.

Prior Art Documents

Patent Documents

[0062]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Claims

1. A method for planning a target trajectory of an automated vehicle (1), comprising: - A set of trajectory candidates for a predetermined planning period (P) is set, each trajectory candidate defining a path that the vehicle (1) should follow if the trajectory candidate is selected as the target trajectory, and defining an acceleration (ax(t)) of the vehicle when following the path; - Objects (2, 3) are detected within the planning period (P); - Using a predetermined cost function, a trajectory cost is assigned to each of the trajectory candidates, the cost function including an object cost that depends on the detected objects (2, 3), the object cost of an object (2, 3) for a trajectory candidate increasing as the distance between the object (2, 3) and the trajectory candidate decreases, and - The target trajectory is selected from the set of trajectory candidates depending on the trajectory cost, wherein in the method: - For each detected object (2, 3), a quality value (Q) representing a measure of the reliability of the detection of the object (2, 3) is determined; - For each object (2, 3), a minimum allowable acceleration (aQ) that is allowed when the vehicle (1) brakes towards the object (2, 3) is determined depending on the quality value (Q) of the object (2, 3); - The trajectory candidates and the object costs determined for the trajectory candidates are evaluated depending on the acceleration (ax(t)) set by each trajectory candidate and depending on the minimum allowable acceleration (aQ) when braking towards the objects (2, 3); - The selection of the target trajectory is additionally performed taking into account the evaluation of the trajectory candidates and the object costs determined for the trajectory candidates. A method, characterized in that.

2. The trajectory candidate having the lowest trajectory cost is selected from the set of trajectory candidates as the target trajectory. The method according to claim 1, characterized in that.

3. - During the evaluation, a category classification is performed; - In the category classification, a non-filtered category (A) and a filtered category (F) are distinguished; - All object costs and the corresponding trajectory candidates are assigned to the non-filtered category (A); - To the filtered category (F), only the object cost where the minimum value (min(ax(t))) of the acceleration (ax(t)) set by each of the respective trajectory candidates is greater than the minimum allowable acceleration (aQ) of each of the respective objects (2, 3) and the corresponding trajectory candidates are assigned. The method according to claim 1 or 2, characterized in that.

4. During the selection of the target trajectory, - From the unfiltered category (A) and the filtered category (F), the trajectory candidates having the lowest trajectory cost are respectively selected. - For the two selected trajectory candidates, the minimum value (min(ax(t))) of the acceleration (ax(t)) set by each of the respective trajectory candidates is respectively determined. - The trajectory candidate having the larger minimum value (min(ax(t))) is selected as the target trajectory. The method according to claim 3, characterized in that.

Images