Method for verifying the plausibility of a trajectory generated on the basis of swarm data for a motor vehicle, computer program product and assistance system that is at least partially assisted

Abstract

Method for verifying the plausibility of a trajectory (10) generated on the basis of swarm data (7) for a motor vehicle (1) that is at least partially assisted by means of an assistance system (2), comprising the steps: - Receiving the swarm data (7) by means of a swarm data receiving device (6) of the assistance system (2); - Detection of at least one other motor vehicle (11) in the immediate vicinity (5) of the motor vehicle (1) by means of a detection device (4) of the assistance system (2); - Determining a driving trajectory (12) of the other motor vehicle (11) using an electronic computing device (3) of the assistance system (2); - Comparing the trajectory (10) generated on the basis of the swarm data (7) with the driving trajectory (12) of the other motor vehicle (11) using the electronic computing device (3); and - Plausibility check of the swarm data (7) depending on the comparison using the electronic computing device (3), wherein a drivable trajectory (13) for the motor vehicle (1) is determined depending on the trajectory (10) generated on the basis of the swarm data (7) and the driving trajectory (12) and the comparison, and wherein interpolation is performed to determine the drivable trajectory (13) between the trajectory (10) generated on the basis of the swarm data (7) and the driving trajectory (12).

Description

[0001] The invention relates to a method for verifying the plausibility of a trajectory generated based on swarm data for an at least partially assisted motor vehicle using an assistance system. Furthermore, the invention relates to a computer program product and a corresponding assistance system.

[0002] Lateral and longitudinal guidance driver assistance systems, also known as travel assist systems, are already known from the state of the art. These systems can record the surroundings based on live camera tracks and, in turn, intervene in the lateral or longitudinal guidance of the vehicle. In particular, in situations where, for example, no live track is detected, no lateral guidance can be offered. Furthermore, so-called swarm data is already known from the state of the art. This data is generated based on historical data and describes, for example, vehicles in the same position in the past and have also followed corresponding trajectories. These trajectories can then be used to enable at least partially automated operation of the vehicle.In particular, if the control is implemented based on swarm data, it must be ensured that the swarm data is also plausible.

[0003] US 10 760 926 B2 describes a method for checking the plausibility of measured values ​​of a mobile device, wherein a sensor device of the mobile device generates at least one measured value, at least two items of information relating to the at least one measured value are received from the mobile device via a communication service, and the at least one measured value is checked for plausibility on the basis of the at least two items of information.

[0004] WO 2019 / 214828 A1 relates to a method for a following vehicle following a preceding vehicle, wherein a position and a course of the preceding vehicle are determined, a position and a course of the following vehicle are determined, then a path for the following vehicle is determined by adapting a curve to the positions and the course, and the following vehicle is controlled to move along the determined path.

[0005] US Patent No. 9,222,789 B2 describes an automatic pathfinding method for an ego or first vehicle. The method comprises receiving position information transmitted by at least one leading vehicle and creating a route based on the received position information.

[0006] In DE 10 2019 217 429 A1, parameters of the respective vehicle and / or the respective vehicle environment and / or time-related parameters are recorded by a large number of vehicles when traveling through the same section of road. Metadata to support longitudinal control when traveling along the section of road traveled is generated by statistically evaluating the parameters recorded by the large number of vehicles. The generated metadata is sent to a vehicle to support longitudinal control. The vehicle receives the metadata and uses it to support the longitudinal control of the vehicle when traveling along the same section of road. The section of road can include a curve, wherein the metadata is used to determine the curve, in particular the curve radius, and / or a recommended speed for the vehicle when traveling along the curve.

[0007] DE 10 2019 213 185 A1 relates to a method for lateral guidance of a vehicle, which comprises recording environmental data of a vehicle when traveling along a route, obtaining stored environmental data that were recorded by a plurality of other vehicles that are not currently traveling along the route when traveling along the route, checking the plausibility of the stored environmental data using the recorded environmental data and carrying out lateral guidance of the vehicle based on the plausibility-checked environmental data.

[0008] According to DE 10 2018 202 712 A1, to generate swarm trajectories for a given lane of a road section, a plurality of vehicles traveling in the given lane transmit their respective trajectories to a backend computer, which determines and stores a swarm trajectory from the transmitted trajectories for the given lane. Furthermore, the vehicles determine specified boundary conditions while traveling in the lane, and the determined boundary conditions are transmitted to the backend computer along with the respective trajectory. The backend computer determines and stores at least one swarm trajectory for the given lane as a function of at least one boundary condition from the transmitted trajectories and the boundary conditions.

[0009] DE 10 2015 013 085 A1 relates to a method for determining a desired lane path of a motor vehicle based on an object in the surroundings of the motor vehicle detected by an environment detection device of the motor vehicle. A first lane path is calculated using a filter algorithm based on the detected object, and a second lane path is determined based on a determined trajectory of the object with reference to the motor vehicle's own movement. The desired lane path is determined based on the first lane path and / or the second lane path only if a deviation of the first lane path from the second lane path is smaller than a predetermined limit.

[0010] The object of the present invention is to provide a method, a computer program product and an assistance system by means of which received swarm data can be checked for plausibility in a simple manner.

[0011] This problem is solved by a method, a computer program product, and an assistance system according to the independent patent claims. Advantageous embodiments are specified in the subclaims.

[0012] One aspect of the invention relates to a method for checking the plausibility of a trajectory generated on the basis of swarm data for an at least partially assisted motor vehicle by means of an assistance system. The swarm data is received by means of a swarm data receiving device of the assistance system. At least one further motor vehicle in the immediate vicinity of the motor vehicle is detected by means of a detection device of the assistance system. A travel trajectory of the further motor vehicle is determined, in particular on the basis of the detection with the detection device, by means of an electronic computing device of the assistance system. The trajectory generated on the basis of the swarm data is compared with the travel trajectory of the further motor vehicle by means of the electronic computing device. The plausibility of the swarm data is checked by means of the electronic computing device depending on the comparison.

[0013] In particular, this makes it possible to simply yet reliably check the plausibility of the received swarm data on the basis of the recording by the recording device.

[0014] The swarm data primarily consists of information from other motor vehicles that have already traveled in the area, particularly the roadway on which the motor vehicle is located, in the past. This swarm data is then stored historically, for example, in an electronic computing device external to the vehicle, and can then be transmitted from there to the vehicle's swarm data receiving device. The swarm data can include, for example, position data and speed data of the historical vehicles.

[0015] In particular, it is possible to drive through environments with at least partial assistance where no lane markings are detected by the detection device, but at least one object in front has been detected in the direction of travel. This object in front is then compared with the swarm data to verify the plausibility of the swarm data. Thus, the swarm data is compared not with correspondingly detected lanes, but based on the other vehicle.

[0016] In this case, the travel trajectory is understood to mean, in particular, a motion vector of the at least one additional motor vehicle, which can be defined, in particular, by at least two points. These two points are, in particular, the old state of the at least one additional motor vehicle and the new state of the at least one additional motor vehicle. After the motion vector has been generated, the two points can be discarded.

[0017] A drivable trajectory for the motor vehicle is determined based on the trajectory generated on the basis of the swarm data and the driving trajectory, as well as the comparison. In particular, a separate drivable trajectory for the motor vehicle can thus be determined. This can be essentially the same as the trajectory generated on the basis of the swarm data and / or the driving trajectory. Furthermore, however, updates can also occur, for example, based on the comparison, so that the drivable trajectory deviates, at least to some extent, from both the trajectory generated on the basis of the swarm data and the driving trajectory. In particular, however, it must be provided that at least the swarm data has been appropriately validated for plausibility so that it can be accessed.

[0018] Furthermore, it is provided that, to determine the drivable trajectory, interpolation is performed between the trajectory generated based on the swarm data and the driving trajectory. In particular, this allows, for example, intermediate points of the driving trajectory and / or the trajectories generated based on the swarm data to be skipped, thereby generating a smoothed drivable trajectory, which allows for more comfortable operation of the motor vehicle.

[0019] According to an advantageous embodiment, the additional motor vehicle is detected by means of a detection device embodied as a camera and / or a radar sensor and / or a lidar sensor and / or an ultrasonic sensor. Preferably, a camera can be used in particular. Thus, the camera detects, for example, a rear end of the additional motor vehicle and can determine the travel trajectory of the additional motor vehicle. In particular, the camera and / or the radar sensor and / or the lidar sensor and / or the ultrasonic sensor are already standard equipment in at least partially assisted motor vehicles, so that already installed technology can be utilized.

[0020] It is also advantageous if the swarm data is checked for plausibility if the trajectory generated based on the swarm data deviates from the driving trajectory below a specified threshold. In particular, the other vehicle does not have to follow the swarm trajectory exactly; deviations below a specified threshold are permitted. This allows for a very reliable and robust plausibility check.

[0021] In a further advantageous embodiment, a distance threshold between the trajectory and the travel trajectory and / or an angle threshold between the trajectory and the travel trajectory is specified as the threshold. For example, a lateral distance between the trajectory and the travel trajectory can be determined, and in particular, a threshold can be provided for this purpose. If the deviation is sufficiently small, the swarm trajectory can be checked for plausibility. Furthermore, a relative angle between the trajectory and the travel trajectory can also be determined; this can then be used to check the plausibility of the swarm data even if it is below an angle threshold. Alternatively, if the threshold values ​​are exceeded, for example, the swarm data cannot be checked for plausibility.

[0022] It is also advantageous if the additional motor vehicle is detected as a motor vehicle traveling in front of the other motor vehicle. In particular, for example, the rear of the additional motor vehicle can be detected. The additional motor vehicle is located in the same lane or in an adjacent lane to the other motor vehicle and is moving in substantially the same direction as the other motor vehicle. This makes it possible to determine the travel trajectory of the additional motor vehicle and compare it with the swarm trajectory.

[0023] Furthermore, it has proven advantageous if a validity value, which describes the length of a valid drivable trajectory, is determined for the drivable trajectory. For example, depending on the comparison, it can be determined how far the determined drivable trajectory is valid, whereby the drivable trajectory can be reliably followed accordingly. For example, it can be provided that the drivable trajectory is determined as valid for the next 10 m, 20 m, 30 m, 40 m, 50 m, 60 m, 70 m, 80 m, 90 m, 100 m, 150 m or 200 m and a correspondingly high validity value is output. Depending on the validity value, at least partially assisted operation can then be reliably generated according to the length of the drivable trajectory.

[0024] The presented method is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means that cause an electronic computing device, when the program code means are processed by the electronic computing device, to perform a method according to the preceding aspect. A further aspect of the invention also relates to a computer-readable storage medium with a computer program product.

[0025] Furthermore, the invention also relates to an assistance system for verifying the plausibility of a trajectory generated on the basis of swarm data for an at least partially assisted motor vehicle, comprising at least one swarm data receiving device, a detection device, and an electronic computing device. The assistance system is designed to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the assistance system.

[0026] The electronic computing device comprises, for example, processors, electrical circuits, in particular integrated electrical circuits, as well as other electronic components in order to be able to carry out corresponding process steps.

[0027] Yet another aspect of the invention also relates to a motor vehicle with an assistance system according to the preceding aspect. In particular, the motor vehicle is operated with at least partial or full assistance. In a fully assisted motor vehicle, the assistance system can also be considered a support system for fully automated operation.

[0028] The invention also includes further developments of the assistance system according to the invention and of the motor vehicle that have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments of the assistance system according to the invention and of the motor vehicle according to the invention are not described again here.

[0029] The invention also includes combinations of the features of the described embodiments.

[0030] Exemplary embodiments of the invention are described below. Shown are: Fig. 1 a schematic plan view according to an embodiment of a motor vehicle with an embodiment of an assistance system; Fig. 2 a schematic view according to an embodiment of the method; Fig. 3 shows a further schematic view according to an embodiment of the method; Fig. 4 is another schematic view of an embodiment of the method; Fig. 5 a schematic flow diagram according to an embodiment of the method.

[0031] The exemplary embodiments explained below are preferred exemplary embodiments of the invention. In the exemplary embodiments, the described components each represent individual, independently considered features of the invention, which also further develop the invention independently of one another and are thus also to be considered as components of the invention, either individually or in a combination other than that shown. Furthermore, the described exemplary embodiments can also be supplemented by further features of the invention already described.

[0032] In the figures, functionally identical elements are provided with the same reference numerals.

[0033] Fig. 1 shows a schematic plan view of a motor vehicle 1 with an embodiment of an assistance system 2. The motor vehicle 1 is at least partially or fully automated. The assistance system 2 has at least one electronic computing device 3 and a detection device 4, which is designed to detect an environment 5 of the motor vehicle 1. The assistance system 2 further has a swarm data receiving device 6 for receiving swarm data 7, for example from an electronic computing device 8 external to the motor vehicle. In the present exemplary embodiment, it is shown in particular that the motor vehicle 1 is stationary at a traffic light 9, with no lane markings present behind the traffic light 9. It is further shown that a trajectory 10 generated on the basis of the swarm data 7 can be provided or generated from the swarm data 7.

[0034] In particular, it is provided that in the method for checking the plausibility of the trajectory 10 generated on the basis of the swarm data 7, at least the swarm data 7 is received by the swarm data receiving device 6. A further motor vehicle 11 is detected by the detection device 4, wherein a travel trajectory 12 of the further motor vehicle 11 is determined by the electronic computing device 3. The trajectory 10 generated on the basis of the swarm data 7 is compared with the travel trajectory 12 of the further motor vehicle 11 by the electronic computing device, and the plausibility of the swarm data 7 is checked by the electronic computing device 3 depending on the comparison.

[0035] In particular, it is shown that the additional motor vehicle 11 is detected by means of a detection device 4 designed as a camera and / or radar sensor and / or lidar sensor and / or as an ultrasonic sensor. Preferably, the additional motor vehicle 11 can be detected by means of the camera 4. Furthermore, it is shown in particular that the additional motor vehicle 11 is detected as a motor vehicle 11 traveling in front of the motor vehicle 1.

[0036] Fig. Figure 2 shows a schematic diagram according to an embodiment of the method. In particular, Fig. 2 shows how the trajectory 10 generated on the basis of the swarm data 7 is compared with the driving trajectory 12. In particular, different positions are shown. The positions P1, P2, P3, P4, P5, P6 form the support points of the trajectory 10. The positions Z1, Z2 indicate the positions of the further motor vehicle 11. In particular, it is shown here that interpolation can take place between the position P2 and the position P5, whereby a trajectory 13 that can be driven by the motor vehicle 1 can be generated. In particular, it is shown that a distance A1 exists between the position P2 and the position Z1 and a distance A2 exists between the position P5 and the position Z2. For example, if the trajectory 10 between the positions X1 and X2 is plausible, a distance criterion must be present, in particular below a distance threshold for the distances A1 and A2.Furthermore, an angle β must be smaller than a threshold value for the angle to be considered plausible.

[0037] Thus, it is shown in particular that if the trajectory 10 generated on the basis of the swarm data 7 deviates from the travel trajectory 12 below a predetermined threshold value, the swarm data 7 is checked for plausibility. Furthermore, the threshold value can be specified, in particular, as the distance threshold between the trajectory 10 and the travel trajectory 12 and / or an angle threshold between the trajectory 10 and the travel trajectory 12.

[0038] Furthermore, it is shown that the drivable trajectory 13 for the motor vehicle is determined depending on the trajectory 10 generated on the basis of the swarm data 7 and the driving trajectory 12 and the comparison, wherein the drivable trajectory 13 can be interpolated between the trajectory 10 generated on the basis of the swarm data 7 and the driving trajectory 12 to determine the drivable trajectory 13.

[0039] Fig. Figure 3 shows a further schematic view of another embodiment of the method. In particular, Fig. Figure 3 shows a possibility for extending a valid vector. In particular, it is shown here that, for example, the linearly interpolated support points between P2, P5, and P7 are used to generate a new travel vector 14, which is also interpolated again between the interpolated support points. In particular, if, for example, the vector between positions P2 and P5 is valid and the vector between P5 and P7 is valid, then the new travel vector 14 is generated.

[0040] Furthermore, it can also be provided that if the vector between P2 and P5 is already present in the buffer, i.e. in the memory of the electronic computing device 3, and the distance between the position X3 and X2 is less than a threshold value, the vector between P2 and P5 can again be replaced by the travel vector 14.

[0041] Fig. Figure 4 shows a further embodiment of the method. In particular, it shows how gaps 16 between vectors 15, which are already present in the buffer and are smaller than a predetermined threshold, can be skipped, so that an overall vector or the trajectory 10 can be used as plausible. The vectors 15 are only reset if the trajectory 10 changes.

[0042] In particular, it is shown here that, for example, there is a gap 16 between positions X1 and X2, a gap 16 between positions X3 and X4, and a gap 16 between positions X5 and X6. An existing vector or trajectory 10 exists between positions X2 and X3, positions X4 and X5, and between positions X6 and X7. Thus, for example, the trajectory 10 between points X1 to X7 can be considered plausible.

[0043] Fig.5 shows a schematic flow diagram according to one embodiment of the method. In particular, in a first step S1, the swarm data 7 is obtained, and in a second step S2, the additional motor vehicle 11 is detected. This order is purely exemplary and can, for example, occur both simultaneously and in a different order. In a third step S3, the swarm data 7 is compared with the vehicle movement of the additional motor vehicle 11. The position of the additional motor vehicle 11 is detected in all cycles. The comparison between the additional motor vehicle 11 and the trajectory 10 is carried out using a distance and angle criterion. For this purpose, a fourth step S4 can additionally provide validation that it is the same additional motor vehicle 11.In a fifth step S5, a plausible vector is then stored in the buffer, particularly in a memory device, for the next specified meters. If a valid vector is already present in the buffer, a check is carried out to determine whether this vector can be expanded. The buffer is compensated for the inherent motion of motor vehicle 1 in each cycle. If a vector lies behind motor vehicle 1, the vector is deleted from the buffer.

[0044] In a sixth step S6, the buffer is evaluated to determine up to which X-value, i.e., the validity value, the trajectory 10 is plausible. Gaps 16 smaller than a specified size are allowed between the vectors.

[0045] In a seventh step S7, it is then determined whether the validity value is greater than a speed factor. For this purpose, in an eighth step S8, the vehicle's own speed and an applicable factor are fed into the seventh step S7, as are a ninth step S9. A tenth step S10 can decide whether the swarm data 7 or the trajectory 10 can be permitted for control.

Claims

[1] Method for verifying the plausibility of a trajectory (10) generated on the basis of swarm data (7) for an at least partially assisted motor vehicle (1) by means of an assistance system (2), comprising the steps: - receiving the swarm data (7) by means of a swarm data receiving device (6) of the assistance system (2); - detecting at least one further motor vehicle (11) in an immediate vicinity (5) of the motor vehicle (1) by means of a detection device (4) of the assistance system (2); - determining a travel trajectory (12) of the further motor vehicle (11) by means of an electronic computing device (3) of the assistance system (2); - comparing the trajectory (10) generated on the basis of the swarm data (7) with the travel trajectory (12) of the further motor vehicle (11) by means of the electronic computing device (3); and - Plausibility check of the swarm data (7) as a function of the comparison by means of the electronic computing device (3), wherein a drivable trajectory (13) for the motor vehicle (1) is determined as a function of the trajectory (10) generated on the basis of the swarm data (7) and the driving trajectory (12) and the comparison, and wherein, to determine the drivable trajectory (13), interpolation is carried out between the trajectory (10) generated on the basis of the swarm data (7) and the driving trajectory (12). [2] Method according to claim 1, characterized by that the further motor vehicle (11) is detected by means of a detection device (4) designed as a camera and / or as a radar sensor and / or as a lidar sensor and / or as an ultrasonic sensor. [3] Method according to claim 1 or 2, characterized bythat if the trajectory (10) generated on the basis of the swarm data (7) deviates from the driving trajectory (12) below a predetermined threshold value, the swarm data (7) are checked for plausibility. [4] Method according to claim 3, characterized by that a distance threshold value between the trajectory (10) and the travel trajectory (12) and / or an angle threshold value between the trajectory (10) and the travel trajectory (12) are specified as the threshold value. [5] Method according to one of the preceding claims, characterized by that the further motor vehicle (11) is detected as a motor vehicle (11) traveling in front of the motor vehicle (1). [6] Method according to one of the preceding claims, characterized by that a validity value, which describes a length of a valid drivable trajectory (13), is determined for the drivable trajectory (13). [7] Computer program product with program code means which cause an electronic computing device (3) to carry out a method according to one of claims 1 to 6 when the program code means are processed by the electronic computing device (3). [8] Assistance system (2) for checking the plausibility of a trajectory (10) generated on the basis of swarm data (7) for an at least partially assisted motor vehicle (1), with at least one swarm data receiving device (5), with a detection device (4) and with an electronic computing device (3), wherein the assistance system (2) is designed to carry out a method according to one of claims 1 to 6.

Images