Method and system for determining a free space trafficable by a vehicle

Abstract

The invention relates to a method for determining, by means of multiple free space segments (S0 - S3), a free space (F) which is trafficable by an ego-vehicle (2), based on which segments it is checked if the free space is trafficable by the ego-vehicle (2) without collisions.

Description

[0001] Method and system for determining a free space accessible to a vehicle

[0002] The invention relates to the field of vehicle assistance systems. In particular, the invention relates to a method and a system for determining the free space accessible to an ego vehicle.

[0003] Systems for planning a collision-free traversable space for a vehicle are generally known. In particular, systems are known that iteratively determine a collision-free traversable space for the entire prediction period based on an estimated trajectory of the ego vehicle and an estimated trajectory of a third-party vehicle (hereinafter referred to as the third-party vehicle trajectory).

[0004] The problem is that the calculation of the collision-free free space is very computationally intensive, since the iterative calculation of the free space is very complex due to the large number of objects that have to be taken into account and which may also be moving.

[0005] Based on this, it is the object of the invention to provide a method for determining a free space that can be driven through by an ego vehicle, which enables a reliable and computing resource-saving calculation of the free space that can be driven through without collision.

[0006] This object is achieved by a method having the features of independent claim 1. Preferred embodiments are the subject of the dependent claims. A system for determining a free space that can be driven through by the ego vehicle is the subject of independent claim 10. According to a first aspect, a method for determining a free space that can be driven through by an ego vehicle without collision is disclosed. The method comprises the following steps:

[0007] First, the ego trajectory of the ego vehicle and a third-vehicle trajectory of at least one third vehicle are estimated in a prediction period. The ego trajectory predicts the movement of the ego vehicle, and the third-vehicle trajectory predicts the movement of the third vehicle in the prediction period.

[0008] Subsequently, an initial clearance space is defined. This initial clearance space forms a basic framework for the clearance space to be determined, hereinafter also referred to as the second clearance space or final clearance space, which is forwarded to a trajectory planner to plan a collision-free trajectory for the ego vehicle. The initial clearance space is preferably determined without considering third-party objects, in particular without considering the predicted positions of moving objects, especially third-party vehicles.

[0009] Subsequently, based on the estimated ego trajectory, the future positions of the ego vehicle are determined at different times within the prediction period. In other words, the prediction period is temporally discretized, thereby defining multiple points in time within the prediction period. Based on the estimated ego trajectory, the positions occupied by the ego vehicle at these points in time are determined. These points in time can, in particular, be chosen equidistantly within the prediction period.

[0010] Based on the determined future positions of the ego vehicle, the first free space is then divided into free space segments. The successive free space segments preferably adjoin one another directly. The free space segments preferably have a length in the direction of travel that is greater than the vehicle length.

[0011] Based on the third-party vehicle trajectory, the future positions of the third-party vehicle are estimated at different times in the prediction period. These times correspond to the times used to determine the positions of the ego vehicle.

[0012] Subsequently, for each point in time within the prediction period, the future position of the third-party vehicle at that point in time is compared with the free space segment in which the ego vehicle is located at that point in time. In particular, it is determined whether the third-party vehicle is approaching the respective free space segment closer than a safety threshold or is at least partially located within the respective free space segment.

[0013] Subsequently, at least one free space segment is restricted if the estimated future position of the third-party vehicle at the respective time indicates that the third-party vehicle is approaching the free space segment in which the ego vehicle is located at that time, closer than a safety threshold, or that the third-party vehicle has at least partially penetrated this free space segment. "Restricting" is understood in particular to mean reducing the area of ​​the free space segment by modifying the lateral boundary of the free space segment, so that the width of the free space segment running transversely to the direction of travel is reduced. This creates at least partially modified free space segments.

[0014] Finally, a second, final free space is created by combining the free space segments, with at least one of the free space segments being modified. The method has the technical advantage that by dividing the free space extending over the entire prediction period into several free space segments, which are selected based on the position of the ego vehicle, and by checking separately for each free space segment whether a third-party vehicle is entering this free space segment at the exact time the ego vehicle is located in the free space segment, the computational complexity is significantly reduced. Furthermore, by taking the movement of the ego vehicle into account when creating the free space segments, it is possible to distinguish whether a predicted movement of a third-party vehicle is relevant for open space planning or not.

[0015] According to one embodiment, the first free space is tubular and runs along the estimated ego trajectory of the ego vehicle. Thus, the first free space forms a corridor within which the ego vehicle can generally move during the prediction period and which can be used as a basis for determining whether this first free space needs to be restricted due to third-party vehicles or other obstacles.

[0016] According to one exemplary embodiment, the free space segments each comprise the entire width of the first free space and each comprise a partial length of the first free space. The partial length runs in the direction of travel of the ego vehicle, and the width of the first free space is measured transversely to this direction of travel. In other words, the first free space is segmented only in the direction of travel of the ego vehicle, but not transversely to the direction of travel of the ego vehicle. This allows the first free space to be divided into free space segments that can be assigned to different points in time in the prediction period and different positions of the ego vehicle in the prediction period. According to one exemplary embodiment, the free space segments are each centered on the position that the ego vehicle has at a discrete point in time in the prediction period. The free space segment preferably has a length that is greater than the length of the ego vehicle.This makes it possible to determine a free space segment in which the ego vehicle is located at a given time. Likewise, the respective time allows the position of a third-party vehicle to be assigned to a free space segment in which the ego vehicle is located at that very time. This allows the determination of the free space that can be driven through without collisions to be made based on the relevant areas of the first free space.

[0017] According to one embodiment, the restriction of at least one free space segment comprises an at least partial reduction of the width of the free space segment, ie the free space segment is laterally delimited in such a way that there is no overlap with the third vehicle or a safety zone assigned to this third vehicle.

[0018] According to one embodiment, a safety zone is formed around the third-party vehicle. The clearance segment is restricted or trimmed if the estimated future position of the third-party vehicle at a certain point in time indicates an at least partial intrusion of the third-party vehicle's safety zone into the clearance segment in which the ego vehicle is located at that time. The safety zone can create a safety buffer that ensures that the second clearance segment, created by joining the clearance segments, is collision-free with a high degree of certainty.

[0019] According to one embodiment, the size of the safety zone is selected depending on the quality of the third-party vehicle trajectory. In particular, if the quality of the third-party vehicle trajectory is low, i.e., if the third-party vehicle trajectory is subject to a relatively high degree of uncertainty, the safety zone can be selected to be larger than if the quality of the third-party vehicle trajectory is high. This can significantly increase safety during assisted or autonomous driving processes.

[0020] According to one embodiment, the length of the free space segment is selected depending on the quality of the ego trajectory and / or the quality of the third-party vehicle trajectory. In particular, if the quality of the ego trajectory and / or the third-party vehicle trajectory is low, the length of the free space segment can be selected to be larger than for an ego trajectory and / or the third-party vehicle trajectory with a higher quality. This prevents inaccurate estimates of the position of the ego vehicle and / or the third-party vehicle from resulting in insufficient or no restrictions on the free space due to excessively fine discretization of the free space.

[0021] According to one embodiment, the length of the clearance segment is selected depending on the speed of the ego vehicle. In particular, the length of the clearance segments can be increased as the speed of the ego vehicle increases. This increases the safety of the planned clearance.

[0022] According to a further aspect, a system for determining a free space accessible to an ego vehicle is disclosed. The system comprises a computing unit configured to perform the following steps:

[0023] - Estimating the ego trajectory of the ego vehicle and a third vehicle trajectory of at least one third vehicle for a prediction period;

[0024] - Establishing an initial clearance; - Determining the future positions of the ego vehicle at different times in the prediction period based on the estimated ego trajectory;

[0025] - Dividing the first free space into free space segments based on the determined future positions of the ego vehicle;

[0026] - Estimating the future positions of the third-party vehicle at different times in the prediction period based on the third-party vehicle trajectory;

[0027] - For each point in time in the prediction period separately, comparing the future position of the third-party vehicle at the respective point in time with the free space segment in which the ego vehicle is located at that point in time;

[0028] - restricting at least one free space segment if the estimated future position of the third-party vehicle at the respective time indicates an approach of the third-party vehicle to the free space segment in which the ego vehicle is located at that time, closer than a safety threshold, or an at least partial penetration of the third-party vehicle at the respective time into the free space segment in which the ego vehicle is located at that time;

[0029] - Forming a second free space by joining the free space segments.

[0030] The terms “approximately”, “essentially” or “about” mean, in the sense of the invention, deviations from the exact value by + / - 10%, preferably by + / - 5% and / or deviations in the form of changes that are insignificant for the function.

[0031] Further developments, advantages, and possible applications of the invention will become apparent from the following description of exemplary embodiments and from the figures. All described and / or illustrated features, individually or in any combination, are fundamentally part of the invention, regardless of their summary in the claims or their reference back to them. The content of the claims is also incorporated into the description.

[0032] The invention is explained in more detail below with reference to exemplary embodiments and the figures. They show:

[0033] Fig. 1 shows an example of a schematic representation of a system for determining a collision-free driving space;

[0034] Fig. 2 shows, by way of example and schematically, a top view of a driving situation of an ego vehicle in which a free space planning based on several free space segments is applied; and

[0035] Fig. 3 shows an example of a block diagram illustrating the method steps of a method for determining a collision-free driving space.

[0036] Figure 1 shows, by way of example and schematically, a system 1 for determining a free space F that can be driven through by an ego vehicle 2. The system 1 is preferably provided in the ego vehicle 2. The system 1 comprises a computing unit 4. This computing unit 4 receives information from a sensor system 5 of the ego vehicle 2. The sensor system 5 is designed to detect the surroundings of the ego vehicle 2, such that the information provided by the sensor system 5 contains environmental information. The sensor system 5 can, for example, comprise one or more radar sensors, ultrasonic sensors, one or more lidar sensors and / or one or more cameras. The computing unit 4 is configured to determine, based on the environmental information, the free space F that can be driven through by the ego vehicle 2 without collision. The free space F can, for example, be defined by a left and a right boundary line.The left and right boundary lines can, for example, be formed by a line connecting a large number of support points.

[0037] The free space F determined by the computer unit 4 can be forwarded to a trajectory planner 6, which, based thereon, determines the ego trajectory traveled by the ego vehicle 2.

[0038] Fig. 2 schematically illustrates a traffic situation in which this can be used to determine a free space that can be driven through by the ego vehicle 2 without collision.

[0039] In the illustrated embodiment, the ego vehicle 2 is traveling in the direction of travel FR on a roadway that has multiple lanes for this direction of travel. The ego vehicle 2 is traveling, for example, in the right lane. An obstacle H is located in this lane, in the example shown, a stationary vehicle. This obstacle H must be avoided by the ego vehicle 2 by changing lanes. The obstacle H thus limits the collision-free space F.

[0040] In addition, the collision-free free space F is influenced by a third vehicle 3 that is in the left lane, for example, moving at a higher speed and changing lanes into the middle lane.

[0041] The determination of the free space F that can be driven through by the ego vehicle 2 without collision is carried out by defining a first free space, which is determined based on the expected movement of the ego vehicle in the prediction period, the segmentation of this first free space into several clear space segments SO - S3 that follow one another in the direction of travel FR, and the partial restriction of the first free space in the respective free space segment SO - S3 if an obstacle H, a third vehicle 3, etc. is located in the free space segment SO - S3. In other words, the free space planning is not carried out for an entire prediction period, which can be, for example, 0s to 5s, but the first free space, which indicates the spatial area in which the ego vehicle 2 will move during the prediction period, is segmented.Based on these free space segments SO - S3, it is then checked whether there is an obstacle, a third vehicle or similar in the respective free space segment SO - S3 at the time when the ego vehicle 2 is in this free space segment SO - S3, in order to focus the free space planning on relevant areas and thereby limit the necessary computing resources.

[0042] Below, the procedure is described in more detail based on Figure 2.

[0043] First, the ego trajectory ET of the ego vehicle 2 is estimated in a prediction period. This ego trajectory ET is preferably a rough estimate that can result from information from previous prediction periods. Likewise, a third-vehicle trajectory DT of a third-vehicle 3 is determined by the ego vehicle 2, wherein this third-vehicle 3 was detected, for example, by the sensor system 5 of the ego vehicle 2. When determining the third-vehicle trajectory DT, quality information can also be provided, which is a measure of the quality of the estimate of the third-vehicle trajectory DT. For example, the quality of the third-vehicle trajectory DT can be higher if the third-vehicle 3 has already been detected by the sensor system 5 of the ego vehicle 2 for a relatively long period of time than if the third-vehicle 3 was only recently detected.

[0044] Subsequently, a first free space is defined. This is preferably done based on the estimated ego trajectory ET of the ego vehicle 2. The first free space can, for example, be tube-shaped and have a length and a width, wherein the length extends in the direction of travel and at least substantially corresponds to the distance traveled by the ego vehicle 2 during the prediction period. The width of the first free space extends transversely, in particular perpendicularly, to the direction of travel FR of the ego vehicle 2. The first free space thus specifies a corridor in which the ego vehicle 2 can generally move during the prediction period without taking into account objects that restrict the free space.

[0045] Subsequently, based on the ego trajectory ET of the ego vehicle 2 and discrete times tO - 13 in the prediction period, the positions of the ego vehicle 2 in the future are determined. This position determination can refer exclusively to the position of the ego vehicle 2 in the direction of travel FR, i.e., the lateral position of the ego vehicle 2 does not need to be taken into account.

[0046] Fig. 2 shows the positions of the ego vehicle 2 at times t0 - 13. Based on these positions, the first free space can be segmented, with the free space segments S0 - S3 being formed by the segmentation. The free space segments S0 - S3 each extend over a partial length of the first free space in the direction of travel FR. Transversely to the direction of travel, these segments are limited by the boundaries of the first free space, as indicated by the bold lines in Fig. 2. The free space segments S0 - S3 are each assigned to a time t0 - 13 in the prediction period, for example, the free space segment S0 to time t0, the free space segment S1 to time t1, etc. Each free space segment S0 - S3 is centered around the position of the ego vehicle 2 at the respective time, as viewed in the direction of travel FR. The free space segment S0 - S3 has a length extending in the direction of travel FR that is greater than the length of the ego vehicle 2.The width of the free space segments SO - S3 corresponds to the width of the first free space.

[0047] Subsequently, one or more free space segments SO - S3 are restricted based on the objects or obstacles H that fall into the respective free space segments SO - S3 at the times tO - t3. In other words, an object or obstacle H is only used to restrict a free space segment SO - S3 if this object or obstacle H also falls at least partially into this free space segment SO - S3 at the time tO - t3 at which the ego vehicle 2 is located in the respective free space segment SO - S3. A safety zone S can be formed around an object or obstacle H. This safety zone S can, for example, be larger than the base area of ​​the object or obstacle H and thus form a safety buffer to take into account, for example, position estimates of the object or obstacle H that are subject to uncertainty. In Fig.2, the safety zone S around the obstacle H and the third vehicle 3 is indicated by a rectangular contour around the obstacle H and the third vehicle 3.

[0048] As previously explained, the future movement of the third-party vehicle 3 in the prediction period is described by a third-party vehicle trajectory DT. Based on this third-party vehicle trajectory DT, the position of the third-party vehicle 3 at times t0 - t13 can be determined.

[0049] If the third-party vehicle 3, an obstacle H or another object also penetrates into the respective free space segment SO - S3 or is located entirely within it at the time tO - 13 at which the ego vehicle 2 is located in the respective free space segment SO - S3 (for example the obstacle H and the third-party vehicle 3 in the free space segment S2 at the time t2), this free space segment SO - S3 is restricted or cut accordingly so that the object or obstacle H, including its possibly existing safety zone S, is located outside the respective free space segment SO - S3.

[0050] As can be seen in Fig. 2, neither the obstacle H nor the third vehicle 3 are located in the free space segments SO and S1. Thus, these remain unobstructed.

[0051] At time t2, at which the ego vehicle 2 is located in the free space segment S2, both the obstacle H and the third-party vehicle 3 are located in the free space segment S2. Therefore, the boundaries of the free space segment S2, which limit the width of the free space segment S2, are changed such that the third-party vehicle 3 and the obstacle H, including their possibly existing safety zone S, are located outside the free space segment S2. This is indicated in Fig. 2 by the angular shape of the lateral boundaries of the free space segment S2, shown in bold. The same applies analogously to the free space segment S3 and time t3.

[0052] After modifying one or more clearance segments, a second clearance segment is created by combining the clearance segments S0 - S3. This second clearance segment forms the collision-free traversable clearance segment during the prediction period, which can be used by the trajectory planner 6 to calculate collision-free trajectories.

[0053] The length of the

[0054] Clearance segments SO - S3 can be selected depending on the quality of the estimation of the own trajectory ET and / or the quality of the third-party vehicle trajectory DT. In particular, if the quality of the own trajectory ET and / or the third-party vehicle trajectory DT is low, the length of the clearance segments SO - S3 can be selected to be longer than in the case of a high quality of the own trajectory ET and / or the third-party vehicle trajectory DT, in order to increase the reliability of determining the collision-free clearance.

[0055] Alternatively or additionally, the length of the free space segments SO - S3 measured in the direction of travel FR of the ego vehicle 2 can depend on the speed of the ego vehicle 2. In particular, the length of the free space segments SO - S3 can be increased with increasing speed of the ego vehicle 2.

[0056] As previously explained, a safety zone S can be established around a third-party vehicle 3, which is used to restrict the clearance segments when the third-party vehicle 3 enters a clearance segment SO - S3 with its safety zone S. The size of the safety zone S, in particular the distance of the edge of the safety zone from the outer body line of the third-party vehicle 3, can be determined depending on the quality of the third-party vehicle trajectory DT. In particular, if the prediction of the third-party vehicle trajectory DT is uncertain and thus the quality of the third-party vehicle trajectory DT is low, the safety zone S can be selected to be larger than with a high quality in order to increase the reliability of determining the clearance to be traveled through without collision.

[0057] Fig. 3 shows a schematic block diagram illustrating the steps of the method for determining a free space accessible to an ego vehicle. First, the ego trajectory of the ego vehicle and a third-party vehicle trajectory of at least one third-party vehicle are estimated for a prediction period (S10).

[0058] In addition, a first free space is defined (S11 ).

[0059] Subsequently, based on the estimated ego trajectory, the future positions of the ego vehicle are determined at different times in the prediction period (S12).

[0060] Based on the determined future positions of the ego vehicle, the first free space is divided into free space segments (S13).

[0061] Based on the third-party vehicle trajectory, the future positions of the third-party vehicle are estimated at different times in the prediction period (S14).

[0062] Subsequently, for each point in time in the prediction period, the future position of the third-party vehicle at the respective point in time is compared with the free space segment in which the ego vehicle is located at that point in time (S15).

[0063] Subsequently, at least one free space segment is restricted or trimmed if the estimated future position of the third-party vehicle at the respective time indicates an approach of the third-party vehicle to the respective free space segment in which the ego vehicle is located at that time, closer than a safety threshold (the safety threshold can be specified, for example, by the safety zone) or an at least partial penetration of the third-party vehicle into this free space segment (S16). Finally, a second free space is formed by combining the free space segments (S17).

[0064] The invention has been described above using exemplary embodiments. It is understood that numerous changes and modifications are possible without departing from the scope of protection defined by the patent claims.

[0065] List of reference symbols 1 System

[0066] 2 Ego vehicle

[0067] 3 Third vehicle

[0068] 4 Computing unit

[0069] 5 Sensors 6 Trajectory planner

[0070] DT third-party vehicle trajectory

[0071] ET Egotrajectory

[0072] F Free space H Obstacle

[0073] S Security Zone

[0074] SO - S3 free space segment tO - 13 time

Claims

Patent claims 1 ) Method for determining a free space (F) that can be driven through by an ego vehicle (2), the method comprising the following steps: - estimating the ego trajectory (ET) of the ego vehicle (2) and a third vehicle trajectory (DT) of at least one third vehicle (3) for a prediction period (S10); - Defining a first free space (S11 ); - Determining the future positions of the ego vehicle (2) at different times (t1 - 13) in the prediction period based on the estimated ego trajectory (ET) (S12); - dividing the first free space into free space segments (SO - S3) based on the determined future positions of the ego vehicle (2) (S13); - Estimating the future positions of the third-party vehicle (3) at different times in the prediction period based on the third-party vehicle trajectory (DT) (S14); - For each time point (tO - 13) in the prediction period separately, comparing the future position of the third vehicle (3) at the respective time point (tO - 13) with the free space segment (SO - S3) in which the ego vehicle (2) is located at this time point (tO - 13) (S15); - restricting at least one free space segment (SO - S3) if the estimated future position of the third vehicle (3) at the respective time (tO - 13) indicates an approach of the third vehicle (3) to the free space segment (SO - S3) in which the ego vehicle (2) is located at this time, closer than a safety threshold value or an at least partial penetration of the third vehicle (3) at the respective time (tO - 13) into the free space segment (SO - S3) in which the ego vehicle (2) is located at this time (S16); Forming a second free space by joining the free space segments (SO - S3) (S17). 2) Method according to claim 1, characterized in that the first free space is formed like a tube and runs along the estimated ego trajectory (ET). 3) Method according to claim 1 or 2, characterized in that the free space segments (SO - S3) each comprise the entire width of the first free space and each comprise a partial length of the first free space. 4) Method according to one of the preceding claims, characterized in that the free space segments (SO - S3) are each formed centered on the position which the ego vehicle (2) has at a discrete time (tO - 13) in the prediction period. 5) Method according to one of the preceding claims, characterized in that the restriction of at least one free space segment (SO - S3) comprises an at least partial reduction of the width of the free space segment (SO - S3). 6) Method according to one of the preceding claims, characterized in that a safety zone (S) is formed around the third vehicle (3), and in that at least one free space segment (SO - S3) is restricted if the estimated future position of the third vehicle (3) indicates an at least partial penetration of the safety zone (S) into the respective free space segment (SO - S3). 7) Method according to claim 6, characterized in that the size of the safety zone (S) is selected as a function of the quality of the third-vehicle trajectory (DT). 8) Method according to one of the preceding claims, characterized in that the length of the free space segment (SO - S3) is selected as a function of the quality of the ego trajectory (ET) and / or the quality of the third vehicle trajectory (DT). 9) Method according to one of the preceding claims, characterized in that the length of the free space segment (SO - S3) is selected as a function of the speed of the ego vehicle (2). 10) System for determining a free space (F) that can be driven through by an ego vehicle (2), wherein the system (1) has a computing unit (4) configured to perform the following steps: - estimating the ego trajectory of the ego vehicle (2) and a third vehicle trajectory (DT) of at least one third vehicle (3) for a prediction period; - Determining an initial free space; - Determining the future positions of the ego vehicle (2) at different times (tO - 13) in the prediction period based on the estimated ego trajectory (ET); - dividing the first free space into free space segments (SO - S3) based on the determined future positions of the ego vehicle (2); - Estimating the future positions of the third-party vehicle (3) at the different times (tO - 13) in the prediction period based on the third-party vehicle trajectory (DT); - For each time point (tO - 13) in the prediction period, comparing the future position of the third vehicle (3) at the respective time point (tO - 13) with the Free space segment (SO - S3) in which the ego vehicle (2) is located at this time (tO - 13); - restricting at least one free space segment (SO - S3) if the estimated future position of the third vehicle (3) at the respective time (tO - 13) indicates an approach of the Third-party vehicle (3) to the free space segment (SO - S3) in which the ego vehicle (2) is located at this time, closer than a safety threshold or an at least partial penetration of the third-party vehicle (3) at the respective time (tO - 13) into the free space segment (SO - S3) in which the Ego vehicle (2) is located at this time; - Forming a second free space by joining the free space segments (SO - S3).

Images