Validation of a predicted trajectory of a motor vehicle

EP4743342A1Pending Publication Date: 2026-05-20STELLANTIS EUROPE SPA
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
STELLANTIS EUROPE SPA
Filing Date
2024-07-12
Publication Date
2026-05-20

AI Technical Summary

Technical Problem

Existing solutions for validating predicted motor vehicle trajectories in autonomous and assisted driving systems are not fully effective in ensuring safety and efficiency, particularly in complex scenarios involving environmental factors.

Method used

An automotive control software that processes data from sensors and on-board systems to validate predicted trajectories by determining spatial coordinates of lane boundaries, predicting vehicle trajectories, and using proprietary validation criteria to assess trajectory validity.

Benefits of technology

The software enables quick, real-time validation of motor vehicle trajectories, ensuring safety and efficiency by determining the closeness of trajectory points to lane boundaries and preventing trajectory deviations outside the driving corridor.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IB2024056793_23012025_PF_FP_ABST
    Figure IB2024056793_23012025_PF_FP_ABST
Patent Text Reader

Abstract

Automotive control software storable in, and executable by, electronic automotive processing resources (1) of an electronic automotive control system of the dynamics of a motor vehicle (10) and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to receive automotive quantities provided by an automotive sensory platform (2) designed to measure automotive quantities and determine lane boundaries (8) of a driving corridor (11) of the motor vehicle (10) and at least one predicted trajectory (9) based on the automotive quantities received. Furthermore, the automotive control software is designed to cause, when executed, the electronic automotive processing resources (1) to become configured to determine indicative values of the position of the trajectory (9) with respect to the driving corridor (11) based on the lane boundaries (8) and the predicted trajectory (9) and validate the predicted trajectory (9) based on the indicative values of the position of the trajectory (9) with respect to the driving corridor (11).
Need to check novelty before this filing date? Find Prior Art

Description

[0001] VALIDATION OF A PREDICTED TRAJECTORY OF A MOTOR VEHICLE

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This Patent Application claims priority from Italian Patent Application No. 102023000014778 filed on July 14, 2023, the entire disclosure of which is incorporated herein by reference.

[0004] TECHNICAL FIELD OF THE INVENTION

[0005] The present invention relates in general to the automotive industry, in particular to an electronic automotive control system of the dynamics of a motor vehicle, in particular an assisted or autonomous driving motor vehicle, designed to validate predicted trajectories of the motor vehicle.

[0006] STATE OF THE ART

[0007] AS is known, the prediction of trajectories of motor vehicles is a complex task which involves a collection and analysis of data coming from sensors and other automotive measurement systems. In the automotive industry, the use of automotive systems for validating trajectories, after predicting them, is of fundamental importance in order to guarantee safety and efficiency of autonomous vehicles and vehicles equipped with automotive assisted driving systems.

[0008] In order to validate trajectories in an autonomous manner, it is known to use collision measurement algorithms for identifying potential collisions along the predetermined trajectory that the motor vehicle follows. Furthermore, in order to validate the trajectories of the motor vehicles, simulation instruments are widely utilized, which allow creating virtual scenarios and testing the trajectories in realistic conditions. The simulations can include environmental factors, such as the presence of other vehicles, pedestrians or road obstacles, so as to evaluate the efficacy and the safety of the proposed trajectories.

[0009] OBJECT AND SUMMARY OF THE INVENTION

[0010] The Applicant has been able to observe that the solutions according to the prior art, even if satisfactory with regard to certain aspects, can be improved.

[0011] The object of the present invention is thus to provide a solution which is different with respect to the solutions of the prior art. According to the present invention, an automotive control software is provided as claimed in the appended claims.

[0012] BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 shows a functional block diagram relative to the validation of automotive trajectories in an electronic automotive control system of the dynamics of a motor vehicle according to the present invention.

[0014] Figure 2 schematically shows different road scenarios relative to the validation of automotive trajectories.

[0015] Figures 3 and 4 show time trends of automotive quantities involved in the validation of automotive trajectories.

[0016] DESCRIPTION OF PREFERRED EMBODIMENTS OF THE INVENTION

[0017] The present invention will now be specifically described with reference to the accompanying figures so as to enable a person skilled in the art to manufacture it and utilize it. Various modifications to the described embodiments will be immediately evident to the persons skilled in the art and the general principles described can be applied to other embodiments and applications without thereby departing from the scope of protection of the present invention, as defined in the appended claims. Therefore, the present invention is not to be considered limited to the described and illustrated embodiments, but it is to be given the broadest scope of protection in accordance with the described and claimed characteristics.

[0018] If not otherwise defined, all the technical and scientific terms utilized herein have the same meaning commonly utilized by persons with ordinary skill in the field pertaining to the present invention. In case of conflict, the present description, comprising the provided definitions, will result to be binding. Furthermore, the examples are provided by mere illustrative purpose and as such they are not to be considered limiting.

[0019] In particular, the block diagrams included in the accompanying figures and described in the following are not to be understood as representation of the structural characteristics, namely constructive limitations, but are to be interpreted as representation of functional characteristics, that is intrinsic properties of the devices and defined by the effects obtained, namely functional limitations and which can be implemented in different manners, thus so as to protect the functionalities thereof (possibility to operate). In order to facilitate the understanding of the embodiments described herein, reference will be made to some specific embodiments and a specific language will be utilized for describing them. The terminology utilized in the present document has the aim to describe only particular embodiments, and is not intended to limit the scope of the present invention.

[0020] Figure 1 shows a functional block diagram relative to the validation of automotive trajectories performed by electronic processing resources 1 of an electronic automotive control system of the dynamics of a motor vehicle 10 according to the present invention, said electronic processing resources 1 storing a validation software of the trajectories of the motor vehicle 10 which, when executed, causes the electronic processing resources 1 to become programmed for validating the trajectories travelled by the motor vehicle 10 in the manner described in the following and, should a trajectory 14 not be validated, for generating a flag, namely an indicator of the occurrence of an invalidity condition of the trajectory 14, which can then be utilized for triggering a suitable automotive intervention for example of the autonomous driving system of the motor vehicle 10 so as to cause, for example, the pulling over of the motor vehicle 10 to the roadside or the planning of a different trajectory 14.

[0021] With regard to the control of the dynamics of the motor vehicle 10 in general and the validation of the trajectories of the motor vehicle 10 in particular, it is highlighted that what counts are the operations that must be implemented for producing such functionality and not the hardware and software architectures with which such operations are implemented, to the point that they could be implemented by means of a concentrated architecture, namely by one single electronic automotive control unit 1, or by means of a cooperative distributed architecture, namely distributed among different electronic automotive control units in communication and cooperating with one another according to a proprietary logic architecture which the producer of the motor vehicle 10 will decide to adopt.

[0022] For descriptive convenience, in the following description reference will be made to one single electronic automotive control unit 1, without thereby losing generality.

[0023] The automotive validation software is designed to cause, when executed by the electronic automotive control unit 1, said electronic automotive control unit 1 to become configured to receive, through an automotive on-board communication network (CAN), indicative data of automotive quantities provided by an automotive sensory platform 2 and by other automotive on-board systems and in particular comprising one or more among:

[0024] - position data indicative of the geographical position of the motor vehicle 10 and provided, for example, by an automotive geolocation system;

[0025] - driving speed data indicative of the longitudinal driving speed of the motor vehicle 10 and provided, for example, by the automotive geolocation system or by speed sensors associated with the wheels of the motor vehicle 10;

[0026] - curvature data indicative of a curvature reference kdesfor the trajectory 9 of the motor vehicle 10 and provided, for example, by a higher level control 7; and,

[0027] - boundary data representative of the lane boundaries 8 of the driving lane of the motor vehicle 10 and provided, for example, by an automotive front view system comprising an ADAS camera designed to capture digital images and perform various processing operations simultaneously on the captured digital images for creating various applications, such as the driving lane recognition, so as to provide data representative of elements present in the captured digital images such as, in particular, the right and left lane boundaries 8 of the driving lane that the motor vehicle 10 is travelling, as well as preceding motor vehicles, guardrails, obstacles, vulnerable users of the road, in particular pedestrians, road signs, etc.

[0028] In particular, the electronic control unit 1 is configured to process the received data for: determining the spatial coordinates of lateral lane boundaries 8 (block 3) of a driving corridor 11 of the motor vehicle 10, delimited by said lane boundaries 8, which can be constituted by the driving lane or by a safety corridor in which the motor vehicle 10 is confined to move and calculated, for example, in a known manner and thus not specifically described, based on the dimensions of the motor vehicle 10 and on the width of the driving lane;

[0029] - predicting a trajectory 9 (block 5) of the motor vehicle 10; and

[0030] - validating the predicted trajectory 9 (block 4) based on the spatial coordinates of the lateral lane boundaries 8 of a driving corridor 11 of the motor vehicle 10 and on a proprietary validation criterion described in the following.

[0031] In a preferred embodiment, the predicted trajectory 9 is a geometrical trajectory, namely is a trajectory predicted based on the curvature reference kdesand on the position of the motor vehicle 10, but without keeping into account the longitudinal dynamics, in particular the speed, of the motor vehicle 10.

[0032] Conveniently, the geometrical trajectory is computed based on the following formula: n,, aes 7

[0033] > static 2Awhere x and y are the longitudinal and lateral spatial coordinates, respectively, of the geometrical trajectory expressed in a Cartesian system.

[0034] Furthermore, the electronic automotive control unit 1 is configured (block 3) to determine different coefficients based on the automotive quantities in order to compute the spatial coordinates of the lane boundaries 8 based on a pre-established polynomial, conveniently of the third order of the following type: y = ax3+ bx2+ ex + d where a, A, c and d are determined coefficients and x and y are the longitudinal and lateral spatial coordinates, respectively, of the lane boundaries 8 expressed in a Cartesian system.

[0035] According to a further aspect of the present invention, the electronic automotive control unit 1 is configured (block 3) to compute the spatial coordinates of the lane boundaries 8 based on the formula: b' . k y = —X3+ -x2+ tan( )x + y0o 2 where, the coefficients determined by the electronic automotive processing resources 1 are k’, k, y and y0and inparticular k’ is the derivative of k.

[0036] As mentioned in the foregoing and as is illustrated in Figure 1, the curvature reference kdesis calculated by a higher-level control (block 7) based on a trajectory planned, by a trajectory planner (block 6), as a function of one or more digital road maps and on data provided by the automotive sensory platform 2 and comprising boundary data.

[0037] The electronic automotive control unit 1 is preferably further configured to determine a number of points of the first lane 13 and points of the second lane boundary 12 of the driving corridor 11 so that each point of the trajectory 14 corresponds to and is associated with a point of the first lane 13 and a point of the second lane boundary 12 of the driving corridor 11; in particular, triplets are formed comprising points of the trajectory 14, of the first and of the second lane boundary 8 of the driving corridor 11. In detail, the electronic automotive control unit 1 is configured to form a triplet comprising a point of the trajectory 14, a corresponding (with respect to the point of the trajectory 14) point of the first lane 13 of the driving corridor 11 and a corresponding (with respect to the point of the trajectory 14) point of the second lane boundary 12 of the driving corridor 11; wherein, the triplet is formed to comprise points determined, by the electronic automotive control unit 1, to be aligned with each other along a line, preferably a straight line, with respect to the reference system of vehicle 10.

[0038] The electronic automotive control unit 1 is configured to determine indicative values of the position of the trajectory 9, in particular of a number of points of the trajectory 14, with respect to the driving corridor 11 based on the lane boundaries 8 and on the predicted trajectory 9; in particular to calculate, for each point of a number of points of the trajectory 14, at least one lateral distance between the point of the trajectory 14 and a corresponding point of one of the lane boundaries 8. In particular, the electronic control unit 1 is configured to determine the indicative values of the position of the trajectory 9 with respect to the driving corridor 11, and in particular the indicative values of the position of the number of points of the trajectory 14 with respect to the driving corridor 11, based on the lateral distances calculated. Furthermore, the electronic control unit 1 is configured to validate the trajectory 9 based on the indicative values of the position of a number of points of the trajectory 14 with respect to the driving corridor 11.

[0039] In particular, the electronic automotive control unit 1 is configured to compute, for each point of the number of points of the trajectory 14, a first lateral distance between the point of the trajectory 14 and the point of the first lane boundary 13 associated with it, a second lateral distance between the point of the trajectory 14 and the point of the second lane boundary 12 associated with it and an indicative value of the position of the point of the trajectory 14 with respect to the driving corridor 11 based on said computed lateral distances. In particular, the more the lateral distances are relatively small values, and thus the closer the point of the trajectory 14 is to the associated points of the lane boundaries 12, 13, the more the indicative value of the position of the point of the trajectory 14 with respect to the driving corridor 11 will be relatively and respectively high.

[0040] Furthermore, in particular, the electronic automotive control unit 1 is configured to compare the predicted trajectory 9 with the driving corridor 11 in order to check whether or not the predicted trajectory 9 extends outside the driving corridor 11. If the predicted trajectory 9 is determined to extend outside the driving corridor 11, the electronic control unit 1 is preferably configured to determine the size of a portion of the trajectory 14, in particular a number of points of the trajectory 14, comprised within or extended outside the driving corridor 11 based on the lane boundaries 8 and on the predicted trajectory 9 and to validate the predicted trajectory 9 also based on the size of the portion of the trajectory 14 comprised within or extended outside the driving corridor 11. In particular, the electronic automotive control unit 1 is configured to determine whether a point of the trajectory 14 extends outside the driving corridor 11 if the electronic control unit 1 determines that said point of the trajectory 14 is not comprised between a point of a first lane boundary 13 and between a point of a second lane boundary 14 of the driving corridor 11; in particular, to determine whether the abscissa value of the point of the trajectory 14 is smaller or greater with respect to the abscissa value of a point of a first lane 13 or of a second boundary lane 12 of the road driving corridor 11.

[0041] Furthermore, the electronic automotive control unit 1 is conveniently configured to determine, for each of the points of the trajectory 14, an indicative value of the fact that the point of the trajectory 14 extends or does not extend outside the driving corridor 11; in particular, said value corresponds to 0 if it extends outside and to 1 if it does not extend outside.

[0042] Figure 2 schematically shows a first 17 and a second example 18 of a control performed for validating a trajectory 9.

[0043] In particular, the first example 17 illustrates a situation where the trajectory 9 is valid and the second example 18 a situation where the trajectory 9 is not valid. In particular, the first example 17 has a trajectory 9 with a smaller number of points of a trajectory 14, extending outside the driving corridor 11 with respect to the second example 18; in the second example 18, furthermore, the trajectory 9 increasingly moves away from the driving corridor 11.

[0044] According to an aspect of the present invention, the electronic automotive control unit 1 is configured to determine an indicative value of the position of a number of points of the trajectory 14 with respect to the driving corridor 11 for each point of the number of points of the determined trajectory 14 which do not extend outside the driving corridor 11

[0045] The electronic control unit 1 is preferably configured to compute a score of a trajectory 9 as a function of the indicative values of the position of the trajectory 9 with respect to the driving corridor 11 and / or on the number of points of the trajectory 14 comprised within or extended outside the driving corridor 11 and to validate the traj ectory 9 based on the score of a trajectory 9; in particular, if said score of a trajectory 9 is higher than a pre-established threshold score value, wherein, conveniently, the threshold score value is determined as a function of experiments carried out with the aim to prevent false positives.

[0046] In particular, with the aim to compute the score of a trajectory 9, the electronic control unit 1 is configured to compute a score of a trajectory 9 based on a number of indicative values of the position of the points of the trajectory 14 comprised within or extended outside the driving corridor 11. In particular, the electronic automotive control unit 1 is configured to calculate the score of a trajectory 9 by means of the following formula: wherein:

[0047] - S is the score of a trajectory 9;

[0048] Wi is an indicative value of the position of a number of points of the trajectory 14 with respect to the driving corridor 11; and

[0049] - ytis an indicative value of the fact that said point of the traj ectory 14 extends or does not extend outside the driving corridor 11.

[0050] Figures 3 and 4 show time trends of automotive quantities involved in the validation of automotive trajectories. In particular, the graphs of Figure 3A and Figure 4A respectively show variations of score values 15 of a trajectory 9 and the graphs of Figure 3B and of Figure 4B respectively show variations of validity indexes 16 of the trajectory 9, determined as a function of the score values of the trajectory 9. By way of mere example, in the graphs of Figure 3 and of Figure 4, the threshold score value corresponds to 0.7 and, therefore, a validity index of the trajectory 9 corresponds to a score of a trajectory 9 below said threshold, which is indicative of the non-validity of the determined trajectory 9.

[0051] The present automotive control software for validating trajectories of a motor vehicle 10 has various advantages.

[0052] In particular, the present automotive control software is designed to cause, when executed, electronic automotive processing resources 1 to become configured to determine whether or not a trajectory 9 is valid based on quick controls, in particular adapted to be applied in real time. Furthermore, the present automotive control software is programmed to cause, when executed, the electronic automotive processing resources 1 to become configured to determine whether or not a trajectory 9 is valid based on the closeness of the points of the trajectory 14 with respect to the points of the lane boundaries 12, 13 of the driving corridor 11 on which the motor vehicle 10 is located; this allows determining a score of a trajectory 9 indicative of the skidding of the motor vehicle 10 in case the latter is following the determined trajectory 9.

Claims

CLAIMS1. Automotive control software storable in, and executable by, electronic automotive processing resources (1) of an electronic automotive control system of the dynamics of a motor vehicle (10) and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to: receive automotive quantities provided by an automotive sensory platform (2) designed to measure automotive quantities; determine lane boundaries (8) of a driving corridor (11) of the motor vehicle (10) and at least one predicted trajectory (9) based on the automotive quantities received; determine indicative values of the position of the traj ectory (9) with respect to the driving corridor (11) based on the lane boundaries (8) and the predicted trajectory (9); and validate the predicted trajectory (9) based on the indicative values of the position of the trajectory (9) with respect to the driving corridor (11).

2. The automotive control software to validate trajectories of a motor vehicle (10) according to claim 1 and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to: calculate, for each of a number of points of the trajectory (14), at least one lateral distance between the point of the trajectory (14) and a corresponding point of one of the lane boundaries (8); and determine the indicative values of the position of the trajectory (9) with respect to the driving corridor (11) based on the lateral distances calculated.

3. The automotive control software to validate trajectories of a motor vehicle (10) according to any one of the previous claims and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to: calculate a score of a trajectory (9) based on the indicative values of the position of the trajectory (9) with respect to the driving corridor (11); and validate the trajectory (9) based on said score value for the trajectory (9).

4. The automotive control software to validate trajectories of a motor vehicle (10) according to any one of the previous claims and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to: compare the predicted trajectory (9) with the driving corridor (11) in order to check whether or not the predicted trajectory (9) extends outside the driving corridor (11); if the predicted trajectory (9) is determined to extend outside the driving corridor (11), determine the size of a portion of the trajectory (14) comprised within or extended outside the driving corridor (11); and validate the predicted traj ectory (9) also based on the size of the portion of the trajectory (14) comprised within or extended outside the driving corridor (11).

5. The automotive control software to validate trajectories of a motor vehicle (10) according to claim 4, when dependent upon claim 3, and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to: calculate the score of a trajectory (9) based on a number of indicative values of the position of the points of the trajectory (14) comprised within or extended outside the driving corridor (11).

6. The automotive control software to validate trajectories of a motor vehicle (10) according to claim 5 and designed to cause, when executed, the electronic automotive processing resources (1) to become configured to validate the trajectory (9) in case said score value for the trajectory (9) is higher than a pre-established threshold score value.

7. The automotive control software according to any one of the previous claims, wherein the automotive quantities comprise the driving speed of the motor vehicle (10) and wherein the automotive control software is designed to cause, when executed, the electronic automotive processing resources (1) to become configured to determine the trajectory (9) that the motor vehicle (10) follows based on a pre-determined curvature reference kdes, but not based on the driving speed of the motor vehicle (10).

8. The automotive control software according to any one of the previous claims and designed to cause, when executed, the electronic automotive processing resources(1) to become configured to trigger an automotive intervention when they invalidate a predicted trajectory (9).

9. A control system of the dynamics of a motor vehicle (10) comprising electronic automotive processing resources (1) storing and configured to execute the automotive control software of any one of the previous claims.