Methods, devices, vehicles, and media for determining vehicle parameters

Abstract

This disclosure relates to a method, apparatus, vehicle, and medium for determining vehicle parameters. The method includes: acquiring multiple predicted trajectories of an obstacle vehicle; determining multiple anchor points of multiple parameter curves matching the multiple predicted trajectories, the multiple parameter curves being related to a motion planning target of the vehicle, the motion planning target being used to reflect the motion parameters of the vehicle to be planned; determining shared anchor points and self-use anchor points based on the multiple anchor points, the shared anchor points being anchor points that can be used jointly by the multiple parameter curves, and the self-use anchor points being anchor points that can be used individually by each parameter curve; and determining the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a method, apparatus, vehicle, and medium for determining vehicle parameters. Background Technology

[0002] With the development of autonomous driving technology, obstacle avoidance has become a critical issue in the design of autonomous driving systems. Related technologies can use predicted obstacle trajectories to determine the vehicle's decision-making and planning outcomes, such as determining the vehicle's parameters. However, these technologies can lead to abrupt changes and haptic feedback issues, or overly conservative decisions that do not conform to human driving habits. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, vehicle, and medium for determining vehicle parameters.

[0004] According to a first aspect of the present disclosure, a method for determining vehicle parameters is provided, comprising:

[0005] Obtain multiple predicted trajectories of vehicles obstructing the vehicle;

[0006] Multiple anchor points are determined for multiple parameter curves that match the multiple predicted trajectories. These multiple parameter curves are related to the motion planning target of the vehicle. The motion planning target is used to reflect the motion parameters of the vehicle to be planned.

[0007] Based on the multiple anchor points, shared anchor points and self-use anchor points are determined. The shared anchor points are anchor points that can be used by the multiple parameter curves together, and the self-use anchor points are anchor points that can be used by each parameter curve individually.

[0008] Based on the shared anchor points and the self-use anchor points, the multiple parameter curves of the vehicle are determined.

[0009] Optionally, determining multiple anchor points for multiple parametric curves that match the multiple predicted trajectories includes:

[0010] For each predicted trajectory, in the first coordinate system, taking the position of the vehicle as the starting position, the steps of determining the first coordinate value of the anchor point of the parameter curve matching the predicted trajectory according to a preset interval, determining the second coordinate value of the anchor point according to a cost function, and determining the anchor point according to the first coordinate value and the second coordinate value are repeatedly executed to determine the multiple anchor points of the multiple parameter curves.

[0011] Wherein, the first coordinate value is the coordinate value of the first direction of the first coordinate system, the second coordinate value is the coordinate value of the second direction of the first coordinate system, the cost function is determined at least based on the amount of change between the second coordinate values ​​of adjacent anchor points, and when the anchor point is the first anchor point, the amount of change is the amount of change between the second coordinate value of the starting position and the second coordinate value of the first anchor point.

[0012] Optionally, the cost function is determined based on a first distance between the anchor point and the lane centerline of the vehicle, the change amount, and a second distance between the anchor point and the position of the obstacle vehicle under the predicted trajectory.

[0013] Optionally, the motion planning objective includes path planning, the multiple parameter curves include multiple path curves, and when the multiple parameter curves include multiple path curves, the first coordinate system is a coordinate system composed of an X-axis and a Y-axis, the first direction represents the direction of the X-axis, the second direction represents the direction of the Y-axis, the X-axis is used to reflect the movement of the vehicle in the horizontal direction, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0014] Optionally, the motion planning objective includes speed planning, the multiple parameter curves include multiple speed curves, and when the multiple parameter curves include the multiple speed curves, the first coordinate system is a coordinate system composed of the S-axis and the T-axis, or a coordinate system composed of the Y-axis and the T-axis, the first direction represents the direction of the T-axis, the second direction represents the direction of the S-axis or the Y-axis, the T-axis is used to reflect time, the S-axis is used to reflect the mileage of the vehicle, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0015] Optionally, each anchor point of different parameter curves is aligned in the vertical direction of the vehicle, and the determination of shared anchor points and self-use anchor points based on the plurality of anchor points includes:

[0016] Multiple first weights are determined based on the multiple prediction probabilities of the multiple predicted trajectories;

[0017] Based on the plurality of first weights and the third distance between the plurality of first anchor points, the plurality of first anchor points are moved to determine the target first anchor points whose positions coincide after the movement. The plurality of first anchor points include anchor points aligned in the vertical direction.

[0018] The shared anchor point is determined based on the overlapping position of the target first anchor point, and the anchor points other than the target first anchor point among the plurality of anchor points are determined as the self-use anchor points.

[0019] Optionally, determining the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points includes:

[0020] Based on the shared anchor points and the self-used anchor points, curve smoothing is performed to determine the multiple parameter curves.

[0021] According to a second aspect of the present disclosure, a vehicle parameter determination apparatus is provided, comprising:

[0022] The acquisition module is configured to acquire multiple predicted trajectories of obstacle vehicles from the vehicle itself;

[0023] The first determining module is configured to determine multiple anchor points of multiple parameter curves that match the multiple predicted trajectories, the multiple parameter curves being related to the vehicle's motion planning target, the motion planning target being used to reflect the motion parameters of the vehicle to be planned;

[0024] The second determining module is configured to determine shared anchor points and self-use anchor points based on the plurality of anchor points. The shared anchor points are anchor points that can be used by the plurality of parameter curves together, and the self-use anchor points are anchor points that can be used individually by each parameter curve.

[0025] The third determining module is configured to determine the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points.

[0026] According to a third aspect of the present disclosure, a vehicle is provided, comprising:

[0027] processor;

[0028] Memory used to store processor-executable instructions;

[0029] The processor is configured as follows:

[0030] Obtain multiple predicted trajectories of vehicles obstructing the vehicle;

[0031] Multiple anchor points are determined for multiple parameter curves that match the multiple predicted trajectories. These multiple parameter curves are related to the motion planning target of the vehicle. The motion planning target is used to reflect the motion parameters of the vehicle to be planned.

[0032] Based on the multiple anchor points, shared anchor points and self-use anchor points are determined. The shared anchor points are anchor points that can be used by the multiple parameter curves together, and the self-use anchor points are anchor points that can be used by each parameter curve individually.

[0033] Based on the shared anchor points and the self-use anchor points, the multiple parameter curves of the vehicle are determined.

[0034] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the method for determining vehicle parameters provided in the first aspect of the present disclosure.

[0035] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0036] By identifying shared and self-use anchor points through multiple anchor points of multiple parameter curves that match multiple predicted trajectories, and generating multiple parameter curves based on these shared and self-use anchor points, the system takes into account various prediction results of the future driving trajectory of the obstacle vehicle, thus accommodating multiple obstacle avoidance scenarios. This allows the vehicle to avoid potential risks in advance, ensuring the safety of the vehicle's driving.

[0037] Furthermore, since a vehicle cannot travel along two trajectories simultaneously, by defining shared anchor points, the shared curves formed by the shared anchor points of multiple parameter curves are identical. In this case, the vehicle's execution result is unique, generating deterministic actions for uncertain future scenarios, resulting in more stable vehicle movement. Moreover, the self-use anchor points correspond to the self-use curves in the parameter curves. By simultaneously including shared curves and self-use curves, the vehicle's trajectory can be switched when the predicted trajectory probability of obstacle vehicles changes, avoiding overly conservative decisions by the vehicle. This approach is applicable to all dangerous scenarios involving interaction with dynamic obstacles (e.g., dynamic obstacle vehicles).

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0040] Figure 1 This is a schematic diagram illustrating multiple predicted trajectories according to an exemplary embodiment.

[0041] Figure 2 This is a flowchart illustrating a method for determining vehicle parameters according to an exemplary embodiment.

[0042] Figure 3 This is a schematic diagram illustrating multiple anchor points of multiple path curves according to an exemplary embodiment.

[0043] Figure 4 This is a schematic diagram illustrating multiple anchor points of multiple velocity curves according to an exemplary embodiment.

[0044] Figure 5This is a schematic diagram illustrating shared anchor points and self-use anchor points for multiple path curves according to an exemplary embodiment.

[0045] Figure 6 This is a schematic diagram illustrating multiple path curves according to an exemplary embodiment.

[0046] Figure 7 This is a schematic diagram illustrating multiple velocity curves according to an exemplary embodiment.

[0047] Figure 8 This is a schematic diagram illustrating path control and speed control of a vehicle under multiple predicted trajectories according to an exemplary embodiment.

[0048] Figure 9 This is a flowchart illustrating the determination of multiple anchor points according to an exemplary embodiment.

[0049] Figure 10 This is a flowchart illustrating the determination of shared anchor points and private anchor points according to an exemplary embodiment.

[0050] Figure 11 This is a schematic diagram illustrating the movement of a plurality of first anchor points according to an exemplary embodiment.

[0051] Figure 12 This is a flowchart illustrating trajectory planning according to an exemplary embodiment.

[0052] Figure 13 This is a block diagram illustrating a vehicle parameter determination device according to an exemplary embodiment.

[0053] Figure 14 This is a block diagram illustrating a vehicle according to an exemplary embodiment.

[0054] Figure 15 This is a block diagram illustrating a vehicle parameter determination device according to an exemplary embodiment. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0056] In related technologies, predicted trajectories of obstacles can be used to determine the decision-making and planning outcomes of a vehicle, for example, to determine the vehicle's parameters. For example, see [reference needed]. Figure 1Assume the road has three lanes, L1, L2, and L3. Vehicle C1 is cruising in lane L2 at a set speed V1, while obstacle vehicle C2 is traveling in lane L3 at a speed V2, and is to the right and slightly ahead of vehicle C1. Obstacle vehicle C2 has two predicted trajectories, S1 and S2. Predicted trajectory S1 represents obstacle vehicle C2 changing lanes to the left, while predicted trajectory S2 represents obstacle vehicle C2 continuing to travel straight in lane L3.

[0057] In related technologies, the system can select the most probable outcome based on the predicted trajectory of an obstacle, for example, choosing the trajectory with the highest probability between predicted trajectories S1 and S2, and the vehicle makes decisions and plans accordingly. However, the trajectory with the highest probability can switch, causing abrupt changes in the vehicle's decision-making and planning results, leading to sensory issues such as path jitter and speed jitter. Furthermore, it may overlook potential risks, resulting in sudden braking or collisions.

[0058] Furthermore, the related technology can simultaneously consider all predicted trajectories of obstacles, for example, considering both predicted trajectories S1 and S2 to generate the safest trajectory for the vehicle, ensuring no collision risk under any circumstances. However, this approach ignores the mutual exclusivity of possible obstacle behaviors, failing to allow all obstacles to pass simultaneously, resulting in overly conservative vehicle decision-making. Even if the obstacle remains straight, the vehicle will slow down to avoid it, hesitant to overtake, demonstrating overly conservative decision-making that does not conform to human driving habits.

[0059] Figure 2 This is a flowchart illustrating a method for determining vehicle parameters according to an exemplary embodiment. This method can be applied to voluntary vehicles, such as... Figure 2 As shown, the method includes the following steps 210-240.

[0060] Step 210: Obtain multiple predicted trajectories of the obstacle vehicles of the vehicle.

[0061] In a possible implementation, the autonomous vehicle can acquire multiple predicted trajectories of the obstacle vehicle through an autonomous driving system. For example, in the autonomous driving system, the perception module can acquire real-time data of the obstacle vehicle, which may include, but is not limited to, at least one of the following: position, orientation, length, width, height, speed, and acceleration. Based on the real-time data, the prediction module predicts the future trajectory of the obstacle vehicle, obtaining multiple predicted trajectories. Each predicted trajectories can carry a corresponding prediction probability.

[0062] In some embodiments, multiple predicted trajectories can be predicted trajectories selected from all predicted trajectories, which can be all trajectories predicted by the autonomous driving system of the vehicle. For example, predicted trajectories with a prediction probability greater than a preset probability value can be selected from all predicted trajectories to obtain multiple predicted trajectories. By selecting predicted trajectories with a prediction probability greater than a preset probability value and discarding low-probability trajectories, the embodiments of this disclosure can prevent the vehicle's driving decisions based on the parameter curve from being too conservative.

[0063] Step 220: Determine multiple anchor points of multiple parameter curves that match multiple predicted trajectories. The multiple parameter curves are related to the vehicle's motion planning target, which is used to reflect the motion parameters of the vehicle to be planned.

[0064] Anchor points are used to generate parametric curves. In some embodiments, the motion planning objective may include path planning and / or speed planning, where path planning matches multiple path curves and speed planning matches multiple speed curves. The path planning objective reflects the path of the vehicle to be planned, and the speed planning objective reflects the speed of the vehicle to be planned.

[0065] Each path curve reflects the path change information of the vehicle that can ensure safety under the corresponding predicted trajectory, and each speed curve reflects the speed change information of the vehicle that can ensure safety under the corresponding predicted trajectory.

[0066] In a possible implementation, a pre-defined planning algorithm can be used to determine multiple anchor points for multiple parametric curves that match multiple predicted trajectories. For example, when the multiple parametric curves include multiple path curves, a path planning algorithm can be used to determine multiple anchor points for the multiple path curves; when the multiple parametric curves include multiple velocity curves, a velocity planning algorithm can be used to determine multiple anchor points for the multiple velocity curves. Specific details regarding path planning algorithms and velocity planning algorithms can be found in related technologies and will not be elaborated upon here.

[0067] In another possible implementation, multiple anchor points can be determined based on a preset interval and a cost function. Specific details regarding the determination of these multiple anchor points can be found below. Figure 9 The details and related descriptions will not be repeated here.

[0068] For example, consider the case where multiple parametric curves include multiple path curves. Figure 3 , Figure 3 This is a schematic diagram illustrating multiple anchor points of multiple path curves according to an exemplary embodiment. Figure 3 The road conditions and vehicle traffic conditions are the same as those mentioned above. Figure 1 Same; please see details below. Figure 1The relevant descriptions in [the document] will not be repeated here. For example... Figure 3 As shown, assuming that for the predicted trajectory S1, the vehicle's path decision 1 is that the obstacle vehicle changes lanes to the left, and the vehicle also changes lanes to the left; and for the predicted trajectory S2, the vehicle's path decision 2 is that the obstacle goes straight, and the vehicle goes straight. Therefore, the vehicle's path decision 1 will generate path curve H1, and the vehicle's path decision 2 will generate path curve H2. It can be understood that path curve H1 matches the predicted trajectory S1, and path curve H2 matches the predicted trajectory S2.

[0069] To generate path curves H1 and H2 that match the predicted trajectories S1 and S2 respectively, it is necessary to determine multiple anchor points for each of the two path curves, including multiple anchor points M for path curve H1. S1 and multiple anchor points M of path curve H2. S2 △S represents the distance between adjacent anchor points.

[0070] For example, consider the case where multiple parameter curves include multiple velocity curves. Figure 4 , Figure 4 This is a schematic diagram illustrating multiple anchor points of multiple velocity curves according to an exemplary embodiment, wherein, Figure 4 The slope of the coordinate system represents velocity. For example... Figure 4 As shown in case a, for the predicted trajectory S1, the vehicle's speed decision 1 is to decelerate and avoid the obstacle, as... Figure 4 As shown in case b, for the predicted trajectory S2, the vehicle's speed decision 2 is cruise control. Therefore, the vehicle's speed decision 1 generates speed curve W1, and the vehicle's speed decision 2 generates speed curve W2. It can be understood that speed curve W1 matches the predicted trajectory S1, and speed curve W2 matches the predicted trajectory S2.

[0071] To generate velocity curves W1 and W2 that match the predicted trajectories S1 and S2 respectively, it is necessary to determine multiple anchor points for each of the two velocity curves, including multiple anchor points M for velocity curve W1. W1 Multiple anchor points M of velocity curve W2 W2 .

[0072] Step 230: Determine shared anchor points and self-use anchor points based on multiple anchor points. Shared anchor points are anchor points that can be used by multiple parametric curves, while self-use anchor points are anchor points that can be used individually by each parametric curve.

[0073] In some embodiments, each anchor point of different parameter curves is aligned in the vertical direction of the vehicle. Determining shared anchor points and self-use anchor points based on multiple anchor points may include: determining a predetermined number of anchor points that are aligned in the vertical direction and are arranged in front among the multiple anchor points as shared anchor points, and determining anchor points other than shared anchor points among the multiple anchor points as self-use anchor points.

[0074] The preset number can be determined based on at least one of the following considerations: ensuring that the trajectory segments used by the downstream control nodes are shared segments, and preventing collisions with obstacle vehicles. To ensure that the trajectory segments used by the downstream control nodes are shared segments, the number of shared anchor points cannot be too few; to ensure safety and prevent collisions with obstacle vehicles, the number of shared anchor points cannot be too many. The downstream control nodes can be used to control the vehicle based on multiple parametric curves, for example, controlling the vehicle's throttle and steering wheel.

[0075] For example, the above is still the case. Figure 3 For example, in this scenario, there are two path curves, H1 and H2. Assuming the preset number is 4, the 4 anchor points that are vertically aligned and arranged at the beginning can be identified as shared anchor points, as shown below. Figure 5 M G It is a shared anchor point, M H1 M is an anchor point that can be used independently by path curve H1. H2 It is an anchor point that can be used independently by the path curve H2.

[0076] In some embodiments, each anchor point of different parametric curves is aligned in the vertical direction of the vehicle. Determining shared anchor points and self-use anchor points based on multiple anchor points may include: determining multiple first weights based on multiple prediction probabilities of multiple predicted trajectories; moving the multiple first anchor points based on the multiple first weights and a third distance between the multiple first anchor points to determine target first anchor points whose positions coincide after the movement, wherein the multiple first anchor points include anchor points aligned in the vertical direction; determining shared anchor points based on the coincidence position of the target first anchor points, and determining anchor points other than the target first anchor points among the multiple anchor points as self-use anchor points. Specific details regarding the determination of shared anchor points and self-use anchor points can be found below. Figure 10 This will not be elaborated upon here.

[0077] Step 240: Determine multiple parameter curves for the vehicle based on shared anchor points and self-used anchor points.

[0078] This embodiment of the disclosure determines shared anchor points and self-use anchor points by using multiple anchor points of multiple parameter curves that match multiple predicted trajectories, and generates multiple parameter curves based on the shared anchor points and self-use anchor points. Since multiple parameter curves match multiple predicted trajectories, it takes into account multiple prediction results of the future driving trajectory of the obstacle vehicle, that is, it takes into account multiple obstacle avoidance scenarios, enabling the vehicle to avoid potential risks in advance and ensuring the safety of the vehicle's driving.

[0079] Furthermore, since a vehicle cannot travel along two trajectories simultaneously, by defining shared anchor points, the shared curves formed by the shared anchor points of multiple parameter curves are identical. In this case, the vehicle's execution result is unique, generating deterministic actions for uncertain future scenarios, resulting in more stable vehicle movement. Moreover, the self-use anchor points correspond to the self-use curves in the parameter curves. By simultaneously including shared curves and self-use curves, the vehicle's trajectory can be switched when the predicted trajectory probability of obstacle vehicles changes, avoiding overly conservative decisions by the vehicle. This approach is applicable to all dangerous scenarios involving interaction with dynamic obstacles (e.g., dynamic obstacle vehicles).

[0080] In some embodiments, determining multiple parameter curves of the vehicle based on shared anchor points and self-used anchor points includes: performing curve smoothing processing based on shared anchor points and self-used anchor points to determine multiple parameter curves.

[0081] This embodiment of the disclosure determines multiple parametric curves by performing curve smoothing based on shared anchor points and self-used anchor points. This is equivalent to smoothing the self-used trajectory and shared trajectory among the multiple parametric curves, ensuring the smoothness of the vehicle's driving even if there are jitters in the predicted trajectory and switching of predicted probability values. Furthermore, it achieves both consideration of potential risks and avoidance of conservative decision-making.

[0082] In a possible implementation, curve smoothing is performed based on shared anchor points and self-used anchor points to determine multiple parametric curves. This can include using a quadratic optimization algorithm to smooth the curves of shared anchor points and self-used anchor points, thereby determining multiple parametric curves. A fifth-degree polynomial curve can be obtained using the quadratic optimization algorithm.

[0083] For example, taking multiple path curves, including the aforementioned path curve H1 and path curve H2, as an example, see [link to example]. Figure 6 , Figure 6 Curve H1 (or curve segment) is the curve formed by the anchor points of path curve H1, and curve H2 is the curve formed by the anchor points of path curve H2. 12 It is a curve formed by the shared anchor points of path curves H1 and H2. It can be understood that curve H... 12 Curve H1 and curve H1 form path curve H1, curve H 12 The path curve H2 is formed by curve H2 and curve H2.

[0084] For example, consider multiple velocity curves, including velocity curves N1 and N2. See [link / reference] Figure 7 , Figure 7 Curve N1 (or curve segment) is the curve formed by the self-anchored points of velocity curve N1, and curve N2 is the curve formed by the self-anchored points of velocity curve N2. 12 It is a curve formed by the shared anchor points of velocity curves N1 and N2. It can be understood that curve N...12 Curve N1 forms path curve N1, and curve N 12 The path curve N2 is formed by curve N2.

[0085] To more clearly illustrate the control of the vehicle by the multiple parameter curves disclosed herein, let's take the motion planning objective, which includes path planning and speed planning, as an example. The multiple parameter curves matching the path planning include the aforementioned path curves H1 and H2, and the multiple parameter curves matching the speed planning include the aforementioned second speed curves N1 and N2. Figure 8 The path control and speed control of the vehicle under multiple predicted trajectories are described.

[0086] like Figure 8 As shown, the path traveled by vehicle C1 when overtaking the dynamic obstacle vehicle C2 can be found in [reference needed]. Figure 8 Figure c shows the velocity change; see Figure c for more details. Figure 8 Figure d in the diagram illustrates this. In Figure c, R1 represents the path of the vehicle during overtaking, and in Figure d, R2 represents the speed of the vehicle during overtaking. The coordinate system in Figure d is the VT coordinate system, used to represent the change in speed V over time T. Due to the collision risk of obstacle vehicle C2 changing lanes to the left, the path R1 of vehicle C1 during overtaking deviates to the left from the center line of lane L2, and the speed is lower than the set cruising speed V1. This ensures both safety and smoothness during the vehicle's movement, more closely resembling the driving style of an experienced human driver.

[0087] Figure 9 This is a flowchart illustrating the determination of multiple anchor points according to an exemplary embodiment. See also... Figure 9 The process includes the following steps 910.

[0088] Step 910: For each predicted trajectory, in the first coordinate system, taking the vehicle's position as the starting position, repeatedly execute the steps of determining the first coordinate value of the anchor point of the parametric curve matching the predicted trajectory according to a preset interval, determining the second coordinate value of the anchor point according to a cost function, and determining the anchor point according to the first and second coordinate values, so as to determine multiple anchor points of multiple parametric curves; wherein, the first coordinate value is the coordinate value of the first direction of the first coordinate system, the second coordinate value is the coordinate value of the second direction of the first coordinate system, the cost function is determined at least according to the change between the second coordinate values ​​of adjacent anchor points, and when the anchor point is the first anchor point, the change is the change between the second coordinate value of the starting position and the second coordinate value of the first anchor point.

[0089] The preset interval can be determined according to actual needs; for example, the preset interval could be 1 meter. See the example below. Figure 3 The preset interval can be △S=1m.

[0090] In some embodiments, the motion planning objective includes path planning, the multiple parameter curves include multiple path curves, and in the case where the multiple parameter curves include multiple path curves, the first coordinate system is a coordinate system composed of the X-axis and the Y-axis, the first direction represents the direction of the X-axis, the second direction represents the direction of the Y-axis, the X-axis is used to reflect the movement of the vehicle in the horizontal direction, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0091] Since the first coordinate value of each anchor point is determined according to a preset interval, the change in the horizontal direction of adjacent anchor points is the same, which is the preset interval. In other words, the change in the first coordinate value between adjacent anchor points is fixed, which is the preset interval.

[0092] In some embodiments, the motion planning objective includes speed planning, the multiple parameter curves include multiple speed curves, and when the multiple parameter curves include multiple speed curves, the first coordinate system is a coordinate system composed of the S-axis and the T-axis, or a coordinate system composed of the Y-axis and the T-axis, the first direction represents the direction of the T-axis, the second direction represents the direction of the S-axis or the Y-axis, the T-axis is used to reflect time, the S-axis is used to reflect the mileage of the vehicle, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0093] For example, if the first coordinate system corresponding to the velocity curve is a coordinate system composed of the Y-axis and the T-axis, the anchor points of the path curve and the velocity curve can be determined by the same spatial coordinate system, which can be a spatiotemporal coordinate system including the X-axis, Y-axis and T-axis.

[0094] In possible implementations, the cost function may be a cost function from related technologies. In some embodiments, the cost function may also be determined based on a first distance and a change in distance between the anchor point and the lane centerline of the vehicle, and a second distance between the anchor point and the position of the obstacle vehicle on the predicted trajectory.

[0095] Among them, the change can reflect the vehicle's control over the steering wheel, which affects passenger comfort, while the first and second distances affect vehicle safety.

[0096] In some embodiments, the cost function may be obtained by weighted summation of the first distance, the amount of change, the first derivative of the amount of change, the second derivative of the amount of change, and the second distance.

[0097] In this embodiment, the change in the amount of change determines the control angle of the steering wheel, the first derivative determines the speed of the steering wheel, and the second derivative determines the acceleration of the steering wheel's turning speed. The second derivative can affect passenger comfort; for example, it can determine whether passengers experience a swaying sensation while riding.

[0098] In some embodiments, weighted summation based on a first distance, a change, a first derivative, a second derivative, and a second distance may include: weighted summation based on the first distance, a change, a first derivative, a second derivative, and a second distance according to corresponding second weights. The second weights may be determined based on actual needs, for example, based on the importance of the corresponding parameters.

[0099] In some embodiments, determining the second coordinate value of an anchor point based on a cost function may include: solving the cost function with the objective of minimizing its value, and then determining the second coordinate value of the anchor point. Since the change in the first coordinate values ​​of adjacent anchor points is fixed at a preset interval, the change in the second coordinate values ​​between adjacent anchor points will affect the second coordinate value of the anchor point. This embodiment of the present disclosure determines the cost function based on the change in the second coordinate values ​​of adjacent anchor points, and determines the second coordinate value of the anchor point based on the cost function, thereby determining the coordinate information of the next anchor point based on the coordinate information of the previous anchor point. This achieves local trajectory planning, improves planning efficiency, and the local trajectory planning is more suitable for obstacle avoidance planning of vehicles with dynamic obstacles.

[0100] Figure 10 This is a flowchart illustrating the determination of shared anchor points and private anchor points according to an exemplary embodiment. See also Figure 10 The process includes the following steps 1010-1030.

[0101] Step 1010: Determine multiple first weights based on multiple predicted probabilities of multiple predicted trajectories.

[0102] The predicted probability can be output by the prediction module in the autonomous vehicle's driving system. For specific details regarding the autonomous driving system, please refer to step 210 above and its related description; they will not be repeated here.

[0103] In some embodiments, determining multiple first weights based on multiple predicted probabilities of multiple predicted trajectories may include: normalizing the multiple predicted probabilities to determine multiple first weights. For example, taking two predicted trajectories, S1 and S2 as described above, assuming the predicted probability P1 of predicted trajectory S1 is 0.5 and the predicted probability P2 of predicted trajectory S2 is 0.3, then the first weights q1 = 0.5 / 0.5 + 0.3 = 0.6 and q2 = 0.3 / 0.5 + 0.3 = 0.4.

[0104] Step 1020: Based on multiple first weights and a third distance between multiple first anchor points, move multiple first anchor points to determine target first anchor points whose positions coincide after the movement. The multiple first anchor points include anchor points aligned in the vertical direction.

[0105] In some embodiments, moving the plurality of first anchor points can be moving the plurality of first anchor points toward each other.

[0106] In some embodiments, moving multiple first anchor points according to multiple first weights and a third distance between multiple first anchor points to determine a target first anchor point whose position coincides after the movement includes: determining the movement distance of each of the multiple first anchor points according to multiple first weights and the third distance; moving the multiple first anchor points according to the movement distance to determine the target first anchor point whose position coincides after the movement.

[0107] For example, see Figure 11 Multiple first anchor points are from Figure 3 Taking any set of vertically aligned anchor points selected from the above examples as an example, it can be seen that... Figure 11 The diamond-shaped anchor point (i.e., the top anchor point) is the anchor point in path curve H1, and the circular anchor point (i.e., the bottom anchor point) is the anchor point in path curve H2. Assuming two first weights are determined based on the two predicted trajectories, namely the first weight α and the first weight (1-α), then the movement distance of the diamond-shaped anchor point can be α×L3, where L3 is the third distance between the diamond-shaped anchor point and the circular anchor point, and the movement distance of the circular anchor point can be (1-α)×L3. For example... Figure 11 As shown, after moving these two first anchor points, their positions coincide. Therefore, these two first anchor points are the target first anchor points.

[0108] Step 1030: Determine the shared anchor point based on the overlapping position of the first anchor point of the target, and determine the anchor points other than the first anchor point of the target among the multiple anchor points as self-use anchor points.

[0109] In some embodiments, a preset number of target first anchor points can be selected, and shared anchor points are determined based on the overlapping positions of the preset number of target first anchor points. Specific details regarding the preset number can be found in the relevant descriptions above, and will not be repeated here. For example, taking a preset number of four as an example, the shared anchor points determined based on the four overlapping positions, and the determined self-use anchor points, can be found in [reference needed]. Figure 6 The details and related descriptions will not be repeated here.

[0110] Figure 12 This is a flowchart illustrating trajectory planning according to an exemplary embodiment. For example, such as... Figure 12As shown, trajectory planning can include path planning and velocity planning. Assuming the path planning corresponds to multiple path curves, namely path curves 1 and 2, then for both path curves 1 and 2, dynamic planning of path anchor points, determination of shared and self-used path anchor points, and smoothing of the path curves are performed. Similarly, assuming the velocity planning corresponds to multiple velocity curves, namely velocity curves 1 and 2, then for both velocity curves 1 and 2, dynamic planning of velocity anchor points, determination of shared and self-used velocity anchor points, and smoothing of the velocity curves are performed. Finally, the trajectory is output, which includes both path planning results and velocity planning results.

[0111] like Figure 12 As shown, this disclosure allows for path planning followed by speed planning, but it is worth noting that this disclosure does not impose any restrictions on the order of path planning and speed planning. Furthermore, this disclosure also allows for path planning or speed planning to be performed independently.

[0112] about Figure 12 For details regarding the execution of dynamic programming path anchors and dynamic programming velocity anchors, please refer to step 220 and its related description. For details regarding the determination of shared path anchors and self-use path anchors, as well as the determination of shared velocity anchors and self-use velocity anchors, please refer to step 230 and its related description. For details regarding the smoothing of path curves and velocity curves, please refer to step 240 and its related description. These details will not be repeated here.

[0113] Figure 13 This is a block diagram illustrating a vehicle parameter determining device according to an exemplary embodiment. (Refer to...) Figure 13 The vehicle parameter determining device 1300 includes:

[0114] The acquisition module 1310 is configured to acquire multiple predicted trajectories of obstacle vehicles for the vehicle;

[0115] The first determining module 1320 is configured to determine multiple anchor points of multiple parameter curves that match the multiple predicted trajectories, the multiple parameter curves being related to the vehicle's motion planning target, the motion planning target being used to reflect the motion parameters of the vehicle to be planned;

[0116] The second determining module 1330 is configured to determine shared anchor points and self-use anchor points based on the plurality of anchor points. The shared anchor points are anchor points that can be used by the plurality of parameter curves together, and the self-use anchor points are anchor points that can be used by each parameter curve individually.

[0117] The third determining module 1340 is configured to determine the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points.

[0118] Optionally, the first determining module is further configured to:

[0119] For each predicted trajectory, in the first coordinate system, taking the position of the vehicle as the starting position, the steps of determining the first coordinate value of the anchor point of the parameter curve matching the predicted trajectory according to a preset interval, determining the second coordinate value of the anchor point according to a cost function, and determining the anchor point according to the first coordinate value and the second coordinate value are repeatedly executed to determine the multiple anchor points of the multiple parameter curves.

[0120] Wherein, the first coordinate value is the coordinate value of the first direction of the first coordinate system, the second coordinate value is the coordinate value of the second direction of the first coordinate system, the cost function is determined at least based on the amount of change between the second coordinate values ​​of adjacent anchor points, and when the anchor point is the first anchor point, the amount of change is the amount of change between the second coordinate value of the starting position and the second coordinate value of the first anchor point.

[0121] Optionally, the cost function is determined based on a first distance between the anchor point and the lane centerline of the vehicle, the change amount, and a second distance between the anchor point and the position of the obstacle vehicle under the predicted trajectory.

[0122] Optionally, the motion planning objective includes path planning, the multiple parameter curves include multiple path curves, and when the multiple parameter curves include multiple path curves, the first coordinate system is a coordinate system composed of an X-axis and a Y-axis, the first direction represents the direction of the X-axis, the second direction represents the direction of the Y-axis, the X-axis is used to reflect the movement of the vehicle in the horizontal direction, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0123] Optionally, the motion planning objective includes speed planning, the multiple parameter curves include multiple speed curves, and when the multiple parameter curves include the multiple speed curves, the first coordinate system is a coordinate system composed of the S-axis and the T-axis, or a coordinate system composed of the Y-axis and the T-axis, the first direction represents the direction of the T-axis, the second direction represents the direction of the S-axis or the Y-axis, the T-axis is used to reflect time, the S-axis is used to reflect the mileage of the vehicle, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

[0124] Optionally, each anchor point of the different parameter curves is aligned in the vertical direction of the vehicle, and the second determining module 1330 is further configured to:

[0125] Multiple first weights are determined based on the multiple prediction probabilities of the multiple predicted trajectories;

[0126] Based on the plurality of first weights and the third distance between the plurality of first anchor points, the plurality of first anchor points are moved to determine the target first anchor points whose positions coincide after the movement. The plurality of first anchor points include anchor points aligned in the vertical direction.

[0127] The shared anchor point is determined based on the overlapping position of the target first anchor point, and the anchor points other than the target first anchor point among the plurality of anchor points are determined as the self-use anchor points.

[0128] Optionally, the third determining module 1340 is further configured to:

[0129] Based on the shared anchor points and the self-used anchor points, curve smoothing is performed to determine the multiple parameter curves.

[0130] The device in this embodiment determines shared anchor points and self-use anchor points by using multiple anchor points of multiple parameter curves that match multiple predicted trajectories, and generates multiple parameter curves based on the shared anchor points and self-use anchor points. Since the multiple parameter curves match multiple predicted trajectories, it takes into account multiple prediction results of the future driving trajectory of the obstacle vehicle, that is, it takes into account multiple obstacle avoidance scenarios, enabling the vehicle to avoid potential risks in advance and ensuring the safety of the vehicle's driving.

[0131] Furthermore, since a vehicle cannot travel along two trajectories simultaneously, by defining shared anchor points, the shared curves formed by the shared anchor points of multiple parameter curves are identical. In this case, the vehicle's execution result is unique, generating deterministic actions for uncertain future scenarios, resulting in more stable vehicle movement. Moreover, the self-use anchor points correspond to the self-use curves in the parameter curves. By simultaneously including shared curves and self-use curves, the vehicle's trajectory can be switched when the predicted trajectory probability of obstacle vehicles changes, avoiding overly conservative decisions by the vehicle. This approach is applicable to all dangerous scenarios involving interaction with dynamic obstacles (e.g., dynamic obstacle vehicles).

[0132] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0133] This disclosure also provides a vehicle, including:

[0134] processor;

[0135] Memory used to store processor-executable instructions;

[0136] The processor is configured as follows:

[0137] Obtain multiple predicted trajectories of vehicles obstructing the vehicle;

[0138] Multiple anchor points are determined for multiple parameter curves that match the multiple predicted trajectories. These multiple parameter curves are related to the motion planning target of the vehicle. The motion planning target is used to reflect the motion parameters of the vehicle to be planned.

[0139] Based on the multiple anchor points, shared anchor points and self-use anchor points are determined. The shared anchor points are anchor points that can be used by the multiple parameter curves together, and the self-use anchor points are anchor points that can be used by each parameter curve individually.

[0140] Based on the shared anchor points and the self-use anchor points, the multiple parameter curves of the vehicle are determined.

[0141] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the method for determining vehicle parameters provided in this disclosure.

[0142] Figure 14 This is a block diagram illustrating a vehicle 1400 according to an exemplary embodiment. For example, vehicle 1400 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 1400 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0143] Reference Figure 14 The vehicle 1400 may include various subsystems, such as an infotainment system 1410, a perception system 1420, a decision control system 1430, a drive system 1440, and a computing platform 1450. The vehicle 1400 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 1400 can be interconnected via wired or wireless means.

[0144] In some embodiments, the infotainment system 1410 may include a communication system, an entertainment system, and a navigation system, etc.

[0145] The perception system 1420 may include several sensors for sensing information about the environment surrounding the vehicle 1400. For example, the perception system 1420 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0146] The decision control system 1430 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0147] The drive system 1440 may include components that provide powered motion to the vehicle 1400. In one embodiment, the drive system 1440 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0148] Some or all of the functions of the vehicle 1400 are controlled by a computing platform 1450. The computing platform 1450 may include at least one processor 1451 and a memory 1452, the processor 1451 being able to execute instructions 1453 stored in the memory 1452.

[0149] Processor 1451 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0150] The memory 1452 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0151] In addition to instruction 1453, memory 1452 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 1452 can be used by computing platform 1450.

[0152] In this embodiment of the disclosure, the processor 1451 may execute instructions 1453 to complete all or part of the steps of the above-described method for determining vehicle parameters.

[0153] Figure 15 This is a block diagram illustrating a vehicle parameter determination device 1500 according to an exemplary embodiment. For example, the device 1500 may be provided as a server. (Refer to...) Figure 15The device 1500 includes a processing component 1522, which further includes one or more processors, and memory resources represented by memory 1532 for storing instructions, such as application programs, that can be executed by the processing component 1522. The application programs stored in memory 1532 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1522 is configured to execute instructions to perform the aforementioned method for determining vehicle parameters.

[0154] Device 1500 may also include a power supply component 1526 configured to perform power management of device 1500, a wired or wireless network interface 1550 configured to connect device 1500 to a network, and an input / output interface 1558. Device 1500 can operate on an operating system, such as Windows Server, stored in memory 1532. TM Mac OS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0155] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0156] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0157] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0158] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining vehicle parameters, characterized in that, include: Obtain multiple predicted trajectories of vehicles obstructing the vehicle; Multiple anchor points are determined for multiple parameter curves that match the multiple predicted trajectories. These multiple parameter curves are related to the motion planning target of the vehicle. The motion planning target is used to reflect the motion parameters of the vehicle to be planned. Based on the multiple anchor points, shared anchor points and self-use anchor points are determined. The shared anchor points are anchor points that can be used by the multiple parameter curves together, and the self-use anchor points are anchor points that can be used by each parameter curve individually. Based on the shared anchor points and the self-use anchor points, the multiple parameter curves of the vehicle are determined, wherein each anchor point of different parameter curves is aligned in the vertical direction of the vehicle. The determination of the shared anchor points and self-use anchor points based on the multiple anchor points includes: Multiple first weights are determined based on the multiple prediction probabilities of the multiple predicted trajectories; Based on the plurality of first weights and the third distance between the plurality of first anchor points, the plurality of first anchor points are moved to determine the target first anchor points whose positions coincide after the movement. The plurality of first anchor points include anchor points aligned in the vertical direction. The shared anchor point is determined based on the overlapping position of the target first anchor point, and the anchor points other than the target first anchor point among the plurality of anchor points are determined as the self-use anchor points.

2. The method according to claim 1, wherein determining multiple anchor points of multiple parametric curves matching the multiple predicted trajectories comprises: For each predicted trajectory, in the first coordinate system, taking the position of the vehicle as the starting position, the steps of determining the first coordinate value of the anchor point of the parameter curve matching the predicted trajectory according to a preset interval, determining the second coordinate value of the anchor point according to a cost function, and determining the anchor point according to the first coordinate value and the second coordinate value are repeatedly executed to determine the multiple anchor points of the multiple parameter curves. Wherein, the first coordinate value is the coordinate value of the first direction of the first coordinate system, the second coordinate value is the coordinate value of the second direction of the first coordinate system, the cost function is determined at least based on the amount of change between the second coordinate values ​​of adjacent anchor points, and when the anchor point is the first anchor point, the amount of change is the amount of change between the second coordinate value of the starting position and the second coordinate value of the first anchor point.

3. The method according to claim 2, wherein the cost function is determined based on a first distance between the anchor point and the lane centerline of the vehicle, the change amount, and a second distance between the anchor point and the position of the obstacle vehicle under the predicted trajectory.

4. The method according to claim 2, wherein the motion planning objective includes path planning, the multiple parameter curves include multiple path curves, and when the multiple parameter curves include multiple path curves, the first coordinate system is a coordinate system composed of an X-axis and a Y-axis, the first direction represents the direction of the X-axis, the second direction represents the direction of the Y-axis, the X-axis is used to reflect the movement of the vehicle in the horizontal direction, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

5. The method according to claim 2 or 4, wherein the motion planning target includes speed planning, the multiple parameter curves include multiple speed curves, and when the multiple parameter curves include the multiple speed curves, the first coordinate system is a coordinate system composed of the S-axis and the T-axis, or a coordinate system composed of the Y-axis and the T-axis, the first direction represents the direction of the T-axis, the second direction represents the direction of the S-axis or the Y-axis, the T-axis is used to reflect time, the S-axis is used to reflect the mileage of the vehicle, and the Y-axis is used to reflect the movement of the vehicle in the vertical direction.

6. The method according to claim 1, wherein determining the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points comprises: Based on the shared anchor points and the self-used anchor points, curve smoothing is performed to determine the multiple parameter curves.

7. A device for determining vehicle parameters, characterized in that, include: The acquisition module is configured to acquire multiple predicted trajectories of obstacle vehicles from the vehicle itself; The first determining module is configured to determine multiple anchor points of multiple parameter curves that match the multiple predicted trajectories, the multiple parameter curves being related to the vehicle's motion planning target, the motion planning target being used to reflect the motion parameters of the vehicle to be planned; The second determining module is configured to determine shared anchor points and self-use anchor points based on the plurality of anchor points. The shared anchor points are anchor points that can be used by the plurality of parameter curves together, and the self-use anchor points are anchor points that can be used individually by each parameter curve. The third determining module is configured to determine the multiple parameter curves of the vehicle based on the shared anchor points and the self-use anchor points, wherein each anchor point of the different parameter curves is aligned in the vertical direction of the vehicle. The second determining module is also configured to: Multiple first weights are determined based on the multiple prediction probabilities of the multiple predicted trajectories; Based on the plurality of first weights and the third distance between the plurality of first anchor points, the plurality of first anchor points are moved to determine the target first anchor points whose positions coincide after the movement. The plurality of first anchor points include anchor points aligned in the vertical direction. The shared anchor point is determined based on the overlapping position of the target first anchor point, and the anchor points other than the target first anchor point among the plurality of anchor points are determined as the self-use anchor points.

8. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the method for determining vehicle parameters as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 6.

Images