Methods, devices, electronic equipment, and autonomous vehicles for obtaining super-decision results

Abstract

This disclosure provides a method, apparatus, electronic device, and autonomous vehicle for obtaining yield and overtaking decision results, relating to artificial intelligence fields such as autonomous driving, computer vision, and sensors. The method may include: identifying target obstacles that have spatial intersections with the vehicle to be processed, the spatial intersections including positions that both the vehicle to be processed and the target obstacles will pass through within a predetermined future time period; for each target obstacle, performing the following processing: obtaining the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle, the acceleration being the acceleration of the vehicle to be processed; combining the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle, respectively determining the yield and overtaking decision result corresponding to each target obstacle, the yield and overtaking decision result being either yielding or overtaking. Applying the solution described in this disclosure can reduce implementation complexity and improve the accuracy of decision results.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to methods, devices, electronic devices, and autonomous vehicles for obtaining decision-making results in the fields of autonomous driving, computer vision, and sensors. Background Technology

[0002] In autonomous driving scenarios, the driver's decision-making regarding yielding and overtaking plays a crucial role, directly impacting vehicle safety. For instance, in left-turn scenarios (such as turning left into oncoming traffic), deciding which obstacles to yield to and which to overtake requires considering various factors. Summary of the Invention

[0003] This disclosure provides methods, apparatus, electronic devices, and autonomous vehicles for obtaining decision-making results.

[0004] A method for obtaining super-decision results includes:

[0005] Identify a target obstacle that has a spatial intersection with the vehicle to be processed, wherein the spatial intersection includes: a location point that both the vehicle to be processed and the target obstacle will pass through within a predetermined future time period;

[0006] For each target obstacle, the following processing is performed: the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle are obtained, wherein the acceleration is the acceleration of the vehicle to be processed;

[0007] By combining the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle, the yield and overtaking decision result corresponding to each target obstacle is determined, and the yield and overtaking decision result is either yield or overtake.

[0008] A device for obtaining super-decision results includes: a target determination module, an interval acquisition module, and a result generation module;

[0009] The target determination module is used to determine target obstacles that have spatial intersections with the vehicle to be processed. The spatial intersections include: locations that both the vehicle to be processed and the target obstacle will pass through within a predetermined time period in the future.

[0010] The interval acquisition module is used to perform the following processing for each target obstacle: acquire the safe yield acceleration interval and the safe overtaking acceleration interval of the vehicle to be processed relative to the target obstacle, wherein the acceleration is the acceleration of the vehicle to be processed;

[0011] The result generation module is used to combine the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle to determine the yield and overtaking decision result corresponding to each target obstacle, wherein the yield and overtaking decision result is to yield or overtake.

[0012] An electronic device, comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described above.

[0016] A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0017] A computer program product includes a computer program / instructions that, when executed by a processor, implement the method described above.

[0018] An autonomous vehicle includes the electronic devices described above.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a flowchart of an embodiment of the method for obtaining super-decision results as described in this disclosure;

[0022] Figure 2 Here is an example image of the super-decision boundary function described in this disclosure;

[0023] Figure 3 This is a schematic diagram of the safe yield acceleration range and the safe overtaking acceleration range obtained as described in this disclosure;

[0024] Figure 4 This is a schematic diagram of the interval synthesis modeling method described in this disclosure;

[0025] Figure 5 This is a schematic diagram of the composition structure of Embodiment 500 of the device for obtaining super-decision results as described in this disclosure;

[0026] Figure 6 A schematic block diagram of an electronic device 600 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0027] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] Furthermore, it should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0029] Figure 1 This is a flowchart illustrating an embodiment of the method for obtaining super-decision results as described in this disclosure. Figure 1 As shown, the specific implementation methods are as follows.

[0030] In step 101, a target obstacle that has a spatial intersection with the vehicle to be processed (i.e., the main vehicle) is identified. The spatial intersection includes a location point that both the vehicle to be processed and the target obstacle will pass through within a predetermined time period in the future.

[0031] In step 102, for each target obstacle, the following processing is performed: the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle are obtained, wherein the acceleration is the acceleration of the vehicle to be processed.

[0032] In step 103, by combining the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle, the yield and overtaking decision result corresponding to each target obstacle is determined, and the yield and overtaking decision result is either yield or overtake.

[0033] Traditional super-decision-making methods are typically complex to implement and have poor accuracy.

[0034] Using the scheme described in the above embodiments, the safe yield acceleration range and safe overtaking acceleration range corresponding to each spatial intersection point, i.e., each target obstacle, can be obtained respectively. That is, the main vehicle acceleration range for safe yielding and the main vehicle acceleration range for safe overtaking. Then, by combining the acceleration ranges of all target obstacles, the yield and overtaking decision results corresponding to each target obstacle can be determined. From the perspective of implementation, it is relatively simple and convenient, thereby reducing the implementation complexity. Moreover, it has high accuracy, thereby improving driving safety. In addition, it is applicable to scenarios such as left turns, straight driving, and right turns, and has universal applicability.

[0035] For any target obstacle, yielding means that the vehicle to be handled arrives at the corresponding spatial intersection point after the target obstacle, and overtaking means that the vehicle to be handled arrives at the corresponding spatial intersection point before the target obstacle.

[0036] Preferably, in response to acquiring the latest image, obstacles can be identified from the image, and target obstacles can be determined from the identified obstacles.

[0037] In practical applications, sensors such as radar can be used to acquire images. For each acquired image, obstacles can be identified first, and the identification method is not limited. Then, target obstacles that have spatial intersections with the vehicle to be processed can be determined from the identified obstacles. The spatial intersections include the locations that the vehicle to be processed and the target obstacles will pass through within a predetermined time period in the future.

[0038] The specific value of the predetermined duration can be determined according to actual needs, such as 8 seconds. Assuming six obstacles are identified, namely obstacles 1 to 6, and assuming that obstacle 1 and the vehicle to be processed will both pass the same location point within the next 8 seconds, then obstacle 1 can be identified as a target obstacle. This location point is the spatial intersection of obstacle 1 and the vehicle to be processed. Similarly, assuming obstacles 2 to 4 are also identified as target obstacles, a total of four target obstacles can be obtained. These four target obstacles can then be processed according to the method described in this disclosure.

[0039] The above process allows for the timely identification of target obstacles, laying a solid foundation for subsequent processing.

[0040] For each target obstacle, the safe yield acceleration range and safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle can be obtained respectively, where the acceleration is the acceleration of the vehicle to be processed.

[0041] Preferably, the safe yielding acceleration range and the safe overtaking acceleration range can be determined based on the obtained yielding decision boundary function and the acceleration information of the target obstacle. The safe yielding acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration within the safe yielding acceleration range, and can safely avoid the target obstacle at the spatial intersection point. The safe overtaking acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration within the safe overtaking acceleration range, and can safely overtake the target obstacle at the spatial intersection point.

[0042] How can we obtain a boundary function for the super-decision without restrictions? For example, it can be done as follows.

[0043] First, define the inequality relationship of the yield condition (the vehicle to be processed yields). For a spatial intersection point, we have:

[0044]

[0045] Among them, a adc and a obs Let s be two variables, representing the acceleration of the vehicle to be processed and the acceleration of the target obstacle corresponding to the spatial intersection point, respectively. adc This represents the distance from the vehicle to be processed to the spatial intersection point (the distance traveled to the spatial intersection point according to the planned path), s obs v represents the distance from the target obstacle to the spatial intersection point. adc v represents the current speed of the vehicle to be processed. obs The current velocity of the target obstacle can be obtained using traditional methods. adc s obs v adc and v obs , t buf This indicates the right-of-way information for the vehicle to be processed. For example, in a left-turn scenario, the right-of-way for the vehicle to be processed is relatively low, and it needs to yield to vehicles going straight. Accordingly, the t corresponding to the left-turn scenario can be used. buf For different scenarios, corresponding t can be pre-set. buf Different scenarios correspond to different t buf They can also be different.

[0046] Consider taking a adc Given a fixed value, calculate a under the condition of yielding. obs scope:

[0047]

[0048] Among them, the right side of formula (2) is at a adcWhen fixed, it can be regarded as a constant value, and can be represented by t. adc Accordingly, formula (2) can be simplified to:

[0049]

[0050] By classifying and discussing the positive and negative signs on the right side of formula (3), we can have:

[0051]

[0052] To ensure that the vehicle and the target obstacle (taking the vehicle as an example) do not reverse midway, the following constraints can be added:

[0053]

[0054] Combining the above formulas, we can deduce that for different a... adc Values ​​of 'a' under the condition of yielding obs The feasible interval is:

[0055]

[0056]

[0057] The conditions for overtaking are similar to those for yielding; accordingly, the following conclusions can be drawn, namely, for different a... adc Value of a under overtaking conditions obs The feasible interval is:

[0058]

[0059]

[0060] Accordingly, it is possible to use a adc Within the defined domain, sampling is performed with a precision of 0.01 to obtain the super decision boundary function.

[0061] Figure 2 This is an example image corresponding to the super-decision boundary function described in this disclosure. Figure 2 As shown, the horizontal axis represents the acceleration 'a' of the vehicle to be processed. adc The vertical axis represents the acceleration 'a' of the target obstacle. obs In order from top to bottom, the first line is the yield decision boundary line, the third line is the overtaking decision boundary line, and the second line is the boundary line without considering t. buf The solution described in this disclosure introduces t as the boundary line for the decision-making process. buf Accordingly, the upper part of the first line is the yielding area, and the lower part of the third line is the overtaking area, thus reserving a buffer area to further improve the driving safety of vehicles waiting to be processed.

[0062] Preferably, the method for obtaining the acceleration information of the target obstacle may include: obtaining the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result, and obtaining the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result, and using the interval information (hereinafter referred to as the fuzzy interval) with the first calculation result and the second calculation result as endpoints as the acceleration information of the target obstacle.

[0063] The acceleration of the target obstacle can be fuzzified. In order to improve the robustness of the subsequent super-decision results, the model is based on the uncertainty of the target obstacle's acceleration. The motion model of the target obstacle from its current position to the corresponding spatial intersection point is simplified to "uniform acceleration / deceleration motion with acceleration values ​​in [a_obs_cur-delta_cls, a_obs_cur+delta_cls]", where a_obs_cur represents the current acceleration of the target obstacle and delta_cls represents the perturbation radius of the target obstacle.

[0064] The disturbance radius corresponding to different target obstacle types can be predefined. Target obstacle types can include motor vehicles, pedestrians, bicycles, etc.

[0065] The fuzzy interval [a_obs_cur-delta_cls, a_obs_cur+delta_cls] is taken as... Figure 2 The a shown obs The value of, combined with Figure 2 The yield decision boundary lines and overtaking decision boundary lines shown in the diagram can be used to calculate a in reverse. adc The safe yield acceleration interval and the safe overtaking acceleration interval are determined by the bisection method, specifically, since the function is monotonic.

[0066] Accordingly, Figure 3 This is a schematic diagram illustrating the safe yield acceleration range and the safe overtaking acceleration range obtained as described in this disclosure. Figure 3 As shown, the two horizontal lines represent the first calculation result and the second calculation result, namely a_obs_cur-delta_cls and a_obs_cur+delta_cls, respectively. In addition, the gray rectangle on the left represents the safe yielding area, and the gray rectangle on the right represents the safe overtaking area.

[0067] Through the above processing, the safe yield acceleration range and safe overtaking acceleration range corresponding to each target obstacle can be determined efficiently and accurately by combining the decision boundary function and the acceleration information of the target obstacle.

[0068] The solution process for the acceleration intervals (including the safe yield acceleration interval and the safe overtaking acceleration interval) corresponding to each target obstacle is independent of each other. The obtained acceleration intervals are all defined on the path from the starting point (current position) to the spatial intersection point, ignoring the possibility of other spatial intersection points. Accordingly, since the solution process for the acceleration intervals corresponding to different target obstacles is independent of each other, in order to form a unified decision for all target obstacles, it is necessary to perform interval comprehensive modeling based on the stability of the acceleration of the vehicle to be processed, etc., in order to obtain the final decision solution.

[0069] Specifically, it can include the following two implementation methods.

[0070] 1) Method 1

[0071] Preferably, the endpoints of the safe yield acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle can be obtained respectively. According to the principle of minimizing the difference between the left and right boundaries of the acceleration sequence, two endpoints are selected from the obtained endpoints as the left and right boundaries. The left boundary is the minimum value among the elements in the acceleration sequence, and the right boundary is the maximum value among the elements in the acceleration sequence. The acceleration sequence includes M elements, where M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, which is used to represent the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yield acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection. The order of each element in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection. Further, the yield and overtaking decision result corresponding to each target obstacle can be determined according to the left and right boundaries.

[0072] For example, assuming M is 4, meaning there are 4 spatial intersections (4 target obstacles), and the order in which the vehicle passes through them is spatial intersection 1, spatial intersection 2, spatial intersection 3, and spatial intersection 4, then the acceleration sequence a' adc It can be represented as The following conditions must be met:

[0073]

[0074] Where 1≤i≤4 This represents the safe yield acceleration interval corresponding to the spatial intersection point i. This represents the safe overtaking acceleration range corresponding to the spatial intersection point i.

[0075] Accordingly, a total of 16 endpoints can be obtained. Two endpoints can be selected from these 16 endpoints as the left and right boundaries according to the principle of minimizing the difference between the left and right boundaries of the acceleration sequence.

[0076] The optimization objective can be defined as:

[0077]

[0078] This means minimizing the difference between the left and right boundaries, or in other words, minimizing the sequence diameter.

[0079] In practical applications, the 16 endpoints can be sorted in ascending or descending order. Based on the sorting results, the two endpoints that serve as the left and right boundaries can be found using the two-pointer method by taking advantage of monotonicity.

[0080] Then, the decision-making result for each target obstacle can be determined based on the left and right boundaries.

[0081] Preferably, for any target obstacle, the following processing can be performed respectively: In response to determining that at least one of the left and right boundaries is an endpoint of the safe yield acceleration interval corresponding to the target obstacle, the yield and overtaking decision result corresponding to the target obstacle can be determined as yield; in response to determining that at least one of the left and right boundaries is an endpoint of the safe overtaking acceleration interval corresponding to the target obstacle, the yield and overtaking decision result corresponding to the target obstacle can be determined as overtaking; in response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, and neither are endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and the safe yield acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield and overtaking decision result corresponding to the target obstacle can be determined as yield; in response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, and neither are endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and the safe overtaking acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield and overtaking decision result corresponding to the target obstacle can be determined as overtaking.

[0082] Figure 4 This is a schematic diagram of the interval synthesis modeling method described in this disclosure. For example... Figure 4As shown, the horizontal axis represents the acceleration of the vehicle to be processed, and the vertical axis represents the direction of the vehicle's travel path. The dots on the vertical axis represent spatial intersections, numbered from bottom to top as spatial intersection 1 to spatial intersection 4, corresponding to target obstacles 1 to 4 respectively. For each spatial intersection, there is a safe yield acceleration interval and a safe overtaking acceleration interval. The four rectangles to the right of the vertical axis represent the safe overtaking acceleration intervals corresponding to each spatial intersection, while the remaining rectangles represent the safe yield acceleration intervals. The dots corresponding to 1, 2, 3, and 4 represent the elements in the acceleration sequence, i.e., respectively... and

[0083] Assuming and Assuming the left and right boundaries are defined respectively, it can be seen that for spatial intersection point 1, since the right boundary is the endpoint of the safe overtaking acceleration range corresponding to spatial intersection point 1, the overtaking decision for spatial intersection point 1 can be determined as overtaking. For spatial intersection point 2, since neither the left nor right boundary is the endpoint of the safe yielding acceleration range or the safe overtaking acceleration range corresponding to spatial intersection point 2, but the safe overtaking acceleration range corresponding to spatial intersection point 2 intersects with the range formed by the left and right boundaries, i.e., part of it lies within the range formed by the left and right boundaries, the overtaking decision for spatial intersection point 2 can be determined as overtaking. For spatial intersection point 3, since the left boundary is the endpoint of the safe yielding acceleration range corresponding to spatial intersection point 3, the overtaking decision for spatial intersection point 3 can be determined as yielding. For spatial intersection point 4, since neither the left nor right boundary is the endpoint of the safe yielding acceleration range or the safe overtaking acceleration range corresponding to spatial intersection point 4, but the safe overtaking acceleration range corresponding to spatial intersection 4 intersects with the range formed by the left and right boundaries, the overtaking decision for spatial intersection point 4 can be determined as overtaking. Thus, for spatial intersection 1, spatial intersection 2, spatial intersection 3 and spatial intersection 4, the following overtaking / yielding decision results can be obtained respectively: overtake, overtake, yield, overtake.

[0084] By using the above method, the global acceleration variation range of the vehicle under test can be minimized, that is, the sequence diameter of the acceleration range can be minimized, thereby avoiding large changes in the acceleration of the vehicle under test as much as possible, and thus improving the continuity and stability of the vehicle's driving.

[0085] Preferably, the safe yield acceleration range and safe overtaking acceleration range corresponding to each target obstacle (each spatial intersection point) can be combined with the upper and lower limits of the acceleration of the vehicle to be processed to determine the yield and overtaking decision results corresponding to each target obstacle.

[0086] For example, to better handle acceleration boundaries, the acceleration of the vehicle to be processed can be limited to:

[0087]

[0088] The acceleration in the safe yield acceleration range and the safe overtaking acceleration range are theoretical values ​​calculated / derived. In practical applications, considering the different performance of different vehicles, some vehicles may not be able to achieve too high or too low acceleration. Therefore, the upper and lower limits of vehicle acceleration can be determined by taking into account the average performance of different vehicles, as shown in the above formula (10).

[0089] Accordingly, such as Figure 4 As shown, taking the upper and lower limits as -3 and 3 respectively as examples, the left and right boundaries can be determined under these constraints, and the overtaking decision results corresponding to each target obstacle can be determined based on the left and right boundaries, thereby further improving the safety and stability of vehicle driving.

[0090] 2) Method Two

[0091] Preferably, the overtaking decision for each target obstacle can be determined according to the principle of minimizing the cumulative change of adjacent elements in the acceleration sequence, based on the safe yield acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle. The acceleration sequence includes M elements, where M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, representing the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yield acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection, and the order of each element in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection.

[0092] Still using acceleration sequence For example, considering the changes in adjacent elements, the optimization objective can be defined as:

[0093]

[0094] That is, to minimize the cumulative change of adjacent elements in the acceleration sequence.

[0095] In practical applications, the decision to yield or overtake each target obstacle can be determined using dynamic programming, based on the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle. This is equivalent to finding an optimal acceleration sequence where the cumulative change in adjacent elements is minimized. For each element, its value either falls within the safe yield acceleration range or the safe overtaking acceleration range. Accordingly, it can be determined whether to yield or overtake the target obstacle corresponding to each element.

[0096] By using the above methods, the global acceleration changes of the vehicle under test can be made as smooth as possible, thereby improving the continuity and stability of the vehicle's driving.

[0097] Preferably, the safe yield acceleration range and safe overtaking acceleration range corresponding to each target obstacle (each spatial intersection point) can be combined with the upper and lower limits of the acceleration of the vehicle to be processed to determine the yield and overtaking decision results corresponding to each target obstacle.

[0098] Accordingly, taking the upper and lower limits of -3 and 3 as examples, the decision-making results for each target obstacle can be determined under these constraints.

[0099] Based on the obtained decision-making results, subsequent processing can be carried out in the traditional way, which is not directly related to the solution described in this patent and will not be introduced.

[0100] It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this disclosure. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0101] In summary, the scheme described in the embodiments of this disclosure can reduce implementation complexity and has high accuracy and robustness, thereby improving the stability, rationality and safety of vehicle yielding decisions, and is applicable to different scenarios, thus having universal applicability.

[0102] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0103] Figure 5 This is a schematic diagram of the structural composition of Embodiment 500 of the device for obtaining super-decision results as described in this disclosure. Figure 5 As shown, it includes: target determination module 501, interval acquisition module 502, and result generation module 503.

[0104] The target determination module 501 is used to determine target obstacles that have spatial intersections with the vehicle to be processed. The spatial intersections include: locations that both the vehicle to be processed and the target obstacles will pass through within a predetermined time period in the future.

[0105] The interval acquisition module 502 is used to perform the following processing for each target obstacle: acquire the safe yield acceleration interval and the safe overtaking acceleration interval of the vehicle to be processed relative to the target obstacle, wherein the acceleration is the acceleration of the vehicle to be processed.

[0106] The result generation module 503 is used to combine the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle to determine the yield and overtaking decision result corresponding to each target obstacle, wherein the yield and overtaking decision result is to yield or overtake.

[0107] Using the scheme described in the above-described device embodiment, the safe yield acceleration range and safe overtaking acceleration range corresponding to each spatial intersection point, i.e., each target obstacle, can be obtained respectively. That is, the acceleration range of the main vehicle for safe yielding and the acceleration range of the main vehicle for safe overtaking. Then, by combining the acceleration ranges of all target obstacles, the yield and overtaking decision results corresponding to each target obstacle can be determined. From the perspective of implementation, it is relatively simple and convenient, thereby reducing the implementation complexity. Moreover, it has high accuracy, thereby improving driving safety. In addition, it is applicable to scenarios such as left turns, straight driving, and right turns, and has universal applicability.

[0108] Preferably, in response to acquiring the latest image, the target determination module 501 can identify obstacles from the image and determine the target obstacle from the identified obstacles.

[0109] In practical applications, sensors such as radar can be used to acquire images. For each acquired image, obstacles can be identified first, and the identification method is not limited. Then, target obstacles that have spatial intersections with the vehicle to be processed can be determined from the identified obstacles. The spatial intersections include the locations that the vehicle to be processed and the target obstacles will pass through within a predetermined time period in the future.

[0110] For each target obstacle, the interval acquisition module 502 can acquire the safe yield acceleration interval and the safe overtaking acceleration interval of the vehicle to be processed relative to the target obstacle, respectively, wherein the acceleration is the acceleration of the vehicle to be processed.

[0111] Preferably, the interval acquisition module 502 can determine the safe yield acceleration interval and the safe overtaking acceleration interval based on the acquired yield decision boundary function and the acceleration information of the target obstacle. The safe yield acceleration interval meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle according to the acceleration in the safe yield acceleration interval, and can safely avoid the target obstacle at the spatial intersection point. The safe overtaking acceleration interval meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle according to the acceleration in the safe overtaking acceleration interval, and can safely overtake the target obstacle at the spatial intersection point.

[0112] Preferably, the interval acquisition module 502 may acquire the acceleration information of the target obstacle by: acquiring the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result, and acquiring the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result, and using the interval information with the first calculation result and the second calculation result as endpoints as the acceleration information of the target obstacle.

[0113] Furthermore, the result generation module 503 can combine the safe yield acceleration range and the safe overtaking acceleration range corresponding to each target obstacle to determine the yield and overtaking decision results corresponding to each target obstacle.

[0114] Preferably, the result generation module 503 can obtain the endpoints of the safe yield acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle. According to the principle of minimizing the difference between the left and right boundaries of the acceleration sequence, two endpoints are selected from the obtained endpoints as the left and right boundaries. The left boundary is the minimum value among the elements in the acceleration sequence, and the right boundary is the maximum value among the elements in the acceleration sequence. The acceleration sequence includes M elements, where M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, which is used to represent the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yield acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection. The order of each element in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection. Furthermore, the yield and overtaking decision result corresponding to each target obstacle can be determined according to the left and right boundaries.

[0115] Preferably, the result generation module 503 can perform the following processing for any target obstacle: In response to determining that at least one of the left and right boundaries is an endpoint of the safe yield acceleration interval corresponding to the target obstacle, the yield and overtaking decision result corresponding to the target obstacle can be determined as yield; in response to determining that at least one of the left and right boundaries is an endpoint of the safe overtaking acceleration interval corresponding to the target obstacle, the yield and overtaking decision result corresponding to the target obstacle can be determined as overtaking; in response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, and neither are endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and the safe yield acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield and overtaking decision result corresponding to the target obstacle can be determined as yield; in response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, and neither are endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and the safe overtaking acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield and overtaking decision result corresponding to the target obstacle can be determined as overtaking.

[0116] In addition, preferably, the result generation module 503 can also determine the yielding and overtaking decision results for each target obstacle according to the principle of minimizing the cumulative value of the changes of adjacent elements in the acceleration sequence, based on the safe yielding acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle. The acceleration sequence includes M elements, where the value of M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, used to represent the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yielding acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection, and the order of each element in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection.

[0117] Furthermore, preferably, the result generation module 503 can also combine the safe yield acceleration range and safe overtaking acceleration range corresponding to each target obstacle (each spatial intersection point) and the upper and lower limits of the acceleration of the vehicle to be processed to determine the yield and overtaking decision results corresponding to each target obstacle.

[0118] Figure 5 The specific workflow of the device embodiment shown can be found in the relevant descriptions in the foregoing method embodiments, and will not be repeated here.

[0119] In summary, the solution described in the embodiments of this disclosure can reduce implementation complexity and has high accuracy and robustness, thereby improving the stability, rationality and safety of vehicle yielding decisions, and is applicable to different scenarios, thus having universal applicability.

[0120] The solutions described in this disclosure can be applied to the field of artificial intelligence, particularly in areas such as autonomous driving, computer vision, and sensors. Artificial intelligence is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It involves both hardware and software technologies. Artificial intelligence hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0121] Furthermore, the images and other data in the embodiments described in this disclosure are not targeted at any specific user and do not reflect the personal information of any specific user. The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solutions of this disclosure all comply with relevant laws and regulations and do not violate public order and good morals.

[0122] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product. Accordingly, this disclosure also provides an autonomous driving vehicle, the autonomous driving vehicle including the aforementioned electronic device.

[0123] Figure 6 A schematic block diagram of an electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0124] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0125] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as those described in this disclosure. For example, in some embodiments, the methods described in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the methods described in this disclosure can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the methods described in this disclosure by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0131] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0132] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0133] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0134] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for obtaining super-decision results, comprising: Identify a target obstacle that has a spatial intersection with the vehicle to be processed, wherein the spatial intersection includes: a location point that both the vehicle to be processed and the target obstacle will pass through within a predetermined future time period; For each target obstacle, the following processing is performed: the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle are obtained, wherein the acceleration is the acceleration of the vehicle to be processed; The endpoints of the safe yield acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle are obtained respectively. Following the principle of minimizing the difference between the left and right boundaries of the acceleration sequence, two endpoints are selected from the obtained endpoints as the left and right boundaries. The left boundary is the minimum value among all elements in the acceleration sequence, and the right boundary is the maximum value among all elements in the acceleration sequence. The acceleration sequence includes M elements, where M equals the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, representing the acceleration of the vehicle to be processed when it passes the corresponding spatial intersection. The acceleration is located within the safe yield acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection. The order of the elements in the acceleration sequence is the same as the order in which the vehicle to be processed passes each spatial intersection. Based on the left and right boundaries, the yield / overtaking decision result corresponding to each target obstacle is determined, and the yield / overtaking decision result is either yield or overtaking.

2. The method according to claim 1, wherein, The process of determining the target obstacle that has a spatial intersection with the vehicle to be processed includes: in response to acquiring the latest image, identifying the obstacle from the image, and determining the target obstacle from the identified obstacle.

3. The method according to claim 1, wherein, The step of obtaining the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle includes: Based on the obtained yield decision boundary function and the acceleration information of the target obstacle, the safe yield acceleration range and the safe overtaking acceleration range are determined. The safe yield acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely avoid the target obstacle at the spatial intersection point; The safe overtaking acceleration range meets the following conditions: the vehicle to be processed travels from the current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely overtake the target obstacle at the spatial intersection point.

4. The method according to claim 3, wherein, Obtaining the acceleration information of the target obstacle includes: obtaining the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result; obtaining the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result; and using the interval information with the first calculation result and the second calculation result as endpoints as the acceleration information of the target obstacle.

5. The method according to claim 1, wherein, The step of determining the overtaking decision results for each target obstacle based on the left and right boundaries includes: For any target obstacle, the following actions are taken: In response to determining that at least one of the left and right boundaries is an endpoint of the safe yield acceleration range corresponding to the target obstacle, the yield decision result corresponding to the target obstacle is determined to be yield; In response to determining that at least one of the left and right boundaries is an endpoint of the safe overtaking acceleration range corresponding to the target obstacle, the overtaking decision result corresponding to the target obstacle is determined to be overtaking; In response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, nor are they endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and that the safe yield acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield overtaking decision result corresponding to the target obstacle is determined to be yield. In response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, nor are they endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and that the safe overtaking acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield decision result corresponding to the target obstacle is determined to be overtaking.

6. A method for obtaining super-decision results, comprising: Identify a target obstacle that has a spatial intersection with the vehicle to be processed, wherein the spatial intersection includes: a location point that both the vehicle to be processed and the target obstacle will pass through within a predetermined future time period; For each target obstacle, the following processing is performed: the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle are obtained, wherein the acceleration is the acceleration of the vehicle to be processed; Based on the principle of minimizing the cumulative change of adjacent elements in the acceleration sequence, the yielding / overtaking decision for each target obstacle is determined according to the safe yielding acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle. The yielding / overtaking decision is either to yield or to overtake. The acceleration sequence includes M elements, where M equals the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, representing the acceleration of the vehicle to be processed when it passes the corresponding spatial intersection. The acceleration is located within the safe yielding acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection. The order of the elements in the acceleration sequence is the same as the order in which the vehicle to be processed passes each spatial intersection.

7. The method according to claim 6, wherein, The process of determining the target obstacle that has a spatial intersection with the vehicle to be processed includes: in response to acquiring the latest image, identifying the obstacle from the image, and determining the target obstacle from the identified obstacle.

8. The method according to claim 6, wherein, The step of obtaining the safe yield acceleration range and the safe overtaking acceleration range of the vehicle to be processed relative to the target obstacle includes: Based on the obtained yield decision boundary function and the acceleration information of the target obstacle, the safe yield acceleration range and the safe overtaking acceleration range are determined. The safe yield acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely avoid the target obstacle at the spatial intersection point; The safe overtaking acceleration range meets the following conditions: the vehicle to be processed travels from the current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely overtake the target obstacle at the spatial intersection point.

9. The method according to claim 8, wherein, Obtaining the acceleration information of the target obstacle includes: obtaining the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result; obtaining the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result; and using the interval information with the first calculation result and the second calculation result as endpoints as the acceleration information of the target obstacle.

10. A device for acquiring super-decision results, comprising: The module consists of a target determination module, an interval acquisition module, and a result generation module. The target determination module is used to determine target obstacles that have spatial intersections with the vehicle to be processed. The spatial intersections include: locations that both the vehicle to be processed and the target obstacle will pass through within a predetermined time period in the future. The interval acquisition module is used to perform the following processing for each target obstacle: acquire the safe yield acceleration interval and the safe overtaking acceleration interval of the vehicle to be processed relative to the target obstacle, wherein the acceleration is the acceleration of the vehicle to be processed; The result generation module is used to obtain the endpoints of the safe yield acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle; according to the principle of minimizing the difference between the left and right boundaries of the acceleration sequence, two endpoints are selected from the obtained endpoints as the left and right boundaries, wherein the left boundary is the minimum value among the elements in the acceleration sequence, and the right boundary is the maximum value among the elements in the acceleration sequence. The acceleration sequence includes M elements, where M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, which is used to represent the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yield acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection. The order of the elements in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection. Based on the left and right boundaries, the yield and overtaking decision result corresponding to each target obstacle is determined, and the yield and overtaking decision result is either yield or overtaking.

11. The apparatus according to claim 10, wherein, The target determination module, in response to acquiring the latest image, identifies obstacles from the image and determines the target obstacle from the identified obstacles.

12. The apparatus according to claim 10, wherein, The interval acquisition module determines the safe yield acceleration interval and the safe overtaking acceleration interval based on the acquired yield decision boundary function and the acceleration information of the target obstacle. The safe yield acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely avoid the target obstacle at the spatial intersection point; The safe overtaking acceleration range meets the following conditions: the vehicle to be processed travels from the current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely overtake the target obstacle at the spatial intersection point.

13. The apparatus according to claim 12, wherein, The interval acquisition module obtains the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result, and obtains the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result. The interval information with the first calculation result and the second calculation result as endpoints is used as the acceleration information of the target obstacle.

14. The apparatus according to claim 10, wherein, For any target obstacle, the result generation module performs the following processing: In response to determining that at least one of the left and right boundaries is an endpoint of the safe yield acceleration range corresponding to the target obstacle, the yield decision result corresponding to the target obstacle is determined to be yield; In response to determining that at least one of the left and right boundaries is an endpoint of the safe overtaking acceleration range corresponding to the target obstacle, the overtaking decision result corresponding to the target obstacle is determined to be overtaking; In response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, nor are they endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and that the safe yield acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield overtaking decision result corresponding to the target obstacle is determined to be yield. In response to determining that neither the left nor right boundaries are endpoints of the safe yield acceleration interval corresponding to the target obstacle, nor are they endpoints of the safe overtaking acceleration interval corresponding to the target obstacle, and that the safe overtaking acceleration interval corresponding to the target obstacle intersects with the interval formed by the left and right boundaries, the yield decision result corresponding to the target obstacle is determined to be overtaking.

15. A device for acquiring super-decision results, comprising: The module consists of a target determination module, an interval acquisition module, and a result generation module. The target determination module is used to determine target obstacles that have spatial intersections with the vehicle to be processed. The spatial intersections include: locations that both the vehicle to be processed and the target obstacle will pass through within a predetermined time period in the future. The interval acquisition module is used to perform the following processing for each target obstacle: acquire the safe yield acceleration interval and the safe overtaking acceleration interval of the vehicle to be processed relative to the target obstacle, wherein the acceleration is the acceleration of the vehicle to be processed; The result generation module is used to determine the yielding or overtaking decision for each target obstacle according to the principle of minimizing the cumulative change of adjacent elements in the acceleration sequence, based on the safe yielding acceleration interval and the safe overtaking acceleration interval corresponding to each target obstacle. The yielding or overtaking decision is either to yield or to overtake. The acceleration sequence includes M elements, where M is equal to the number of spatial intersections. Each target obstacle corresponds to its own spatial intersection, and each element corresponds to a different spatial intersection, representing the acceleration of the vehicle to be processed when it passes through the corresponding spatial intersection. The acceleration is located in the safe yielding acceleration interval or the safe overtaking acceleration interval corresponding to the corresponding spatial intersection, and the order of each element in the acceleration sequence is the same as the order in which the vehicle to be processed passes through each spatial intersection.

16. The apparatus according to claim 15, wherein, The target determination module, in response to acquiring the latest image, identifies obstacles from the image and determines the target obstacle from the identified obstacles.

17. The apparatus according to claim 15, wherein, The interval acquisition module determines the safe yield acceleration interval and the safe overtaking acceleration interval based on the acquired yield decision boundary function and the acceleration information of the target obstacle. The safe yield acceleration range meets the following conditions: the vehicle to be processed travels from its current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely avoid the target obstacle at the spatial intersection point; The safe overtaking acceleration range meets the following conditions: the vehicle to be processed travels from the current position to the spatial intersection point corresponding to the target obstacle at the acceleration range, and can safely overtake the target obstacle at the spatial intersection point.

18. The apparatus according to claim 17, wherein, The interval acquisition module obtains the difference between the current acceleration of the target obstacle and the disturbance radius corresponding to the target obstacle to obtain a first calculation result, and obtains the sum of the current acceleration of the target obstacle and the disturbance radius to obtain a second calculation result. The interval information with the first calculation result and the second calculation result as endpoints is used as the acceleration information of the target obstacle.

19. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

21. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the method of any one of claims 1-9.

22. An autonomous vehicle, including the electronic equipment as described in claim 19.

Images