Driving information prediction method, apparatus, electronic device, storage medium, program, and autonomous vehicle

Abstract

The present invention provides a method for predicting driving information, an apparatus, an electronic device, a storage medium, a program, and an autonomous vehicle. [Solution] This disclosure provides a driving information prediction method, apparatus, electronic device, storage medium, program and autonomous vehicle, relating to the field of autonomous driving, more particularly to the field of artificial intelligence, and more particularly to the field of autonomous driving and intelligent transportation technology. The method includes determining a first master-slave relationship between a target vehicle and a first obstacle based on the motion parameters of the target vehicle at the current time, route information of the target vehicle at a first time interval, motion parameters of a first obstacle at the current time, and predicted route information of the first obstacle at a first time interval; obtaining first predicted driving information based on the first master-slave relationship; and determining first optimal driving information based on evaluation results corresponding to the first predicted driving information.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving, particularly to the field of artificial intelligence, and more particularly to the fields of autonomous driving and intelligent transportation technologies.

Background Art

[0002] With the progress of autonomous driving technology, autonomous vehicles are becoming increasingly popular, and the automation of vehicle driving and the intelligence of transportation systems are the main directions of current and future transportation development. Facing a complex traffic environment, autonomous vehicles need to have high intelligence and adaptability to handle emergencies and complex traffic scenarios. Currently, they often rely on real-time data sensed by the vehicle's own sensors to evaluate collision risks and predict the driving information of the vehicle. However, with the increase in traffic participants, the method of evaluating and regenerating the driving information of a vehicle based only on the real-time data from the vehicle's sensors cannot ultimately guarantee the accuracy of the predicted driving information.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The present disclosure provides a driving information prediction method, apparatus, electronic device, storage medium, program, and autonomous vehicle.

Means for Solving the Problems

[0004] According to one aspect of the present disclosure, a driving information prediction method is provided, the method includes: Determining a first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle over a first time period, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle over the first time period; Based on the first master-slave relationship, a first predicted driving information is obtained, wherein the first predicted driving information includes a first predicted motion parameter for a plurality of predicted time points in a first time length of the target vehicle, and a second predicted motion parameter for a plurality of predicted time points in a first time length of the first obstacle. The method involves determining a first optimal driving information based on an evaluation result corresponding to the first predicted driving information, wherein the first optimal driving information includes optimal predicted motion parameters for multiple predicted times in a first time length of the target vehicle, and optimal predicted motion parameters for multiple predicted times in a first time length of the first obstacle.

[0005] According to another aspect of this disclosure, a driving information prediction device is provided, and the device is A master-slave relationship determination module for determining a first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle at a first time interval. A driving information prediction module for obtaining first predicted driving information based on the first master-slave relationship, wherein the first predicted driving information includes first predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and second predicted motion parameters at multiple predicted times in a first time length of the first obstacle, An optimal driving information determination module for determining first optimal driving information based on evaluation results corresponding to the first predicted driving information, wherein the first optimal driving information includes optimal predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and optimal predicted motion parameters at multiple predicted times in a first time length of the first obstacle.

[0006] According to another aspect of this disclosure, an electronic device is provided, which is At least one processor, The system comprises at least one processor and memory that is communicated with, The memory stores instructions that are executable by the at least one processor, and when such instructions are executed by the at least one processor, the at least one processor performs any one of the methods in the embodiments of the present disclosure. Another aspect of the present disclosure provides a non-temporary computer-readable storage medium storing computer instructions for causing a computer to perform any one of the methods of the embodiments of the present disclosure.

[0007] According to another aspect of the present disclosure, a program, when executed by a processor, provides a program for causing any of the embodiments of the present disclosure to perform.

[0008] According to another aspect of this disclosure, an autonomous vehicle including the aforementioned electronic device is provided.

[0009] By adopting the above embodiment, the first master-slave relationship between the target vehicle and the obstacle can be determined in real time by combining the motion parameters of the target vehicle and the obstacle at the current time with the path information of both at the first future time length. Furthermore, first predicted driving information can be obtained based on the first master-slave relationship between the two, and finally, predicted optimal driving information can be determined based on the evaluation result of the first predicted driving information. Since the master-slave relationship of each traffic participant can be analyzed based on the current state and future path of each traffic participant, and driving information can be predicted and evaluated to obtain optimal driving information, the accuracy of the driving information obtained through prediction can be improved.

[0010] It should be understood that the information contained herein is not intended to describe any key points or important features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Further details of other features of this disclosure will be provided in the specification below. [Brief explanation of the drawing]

[0011] The attached drawings are for the purpose of better understanding the solutions of this disclosure and do not constitute a limitation of this disclosure. [Figure 1] This is a schematic flowchart of a driving information prediction method according to one embodiment of the present disclosure. [Figure 2] This is a schematic diagram illustrating a scenario for obtaining priority for the right of way between a target vehicle and a first obstacle over a first time period, according to one embodiment of the present disclosure. [Figure 3] This is a schematic diagram showing a scenario for the process of determining the first optimal driving information according to one embodiment of the present disclosure. [Figure 4] This is a schematic diagram showing a scenario for the process of determining a policy decision command according to one embodiment of the present disclosure. [Figure 5] This is a flowchart of a driving information prediction method according to one embodiment of the present disclosure. [Figure 6] This is a schematic diagram illustrating a traffic scenario according to one embodiment of the present disclosure. [Figure 7] This is a schematic block diagram showing a driving information prediction device according to one embodiment of the present disclosure. [Figure 8] This is a schematic block diagram showing a driving information prediction device according to another embodiment of the present disclosure. [Figure 9] This is a schematic block diagram showing a driving information prediction device according to further embodiments of the present disclosure. [Figure 10] This is a block diagram of an electronic device for realizing an embodiment of the present disclosure. [Modes for carrying out the invention]

[0012] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings. These drawings include various details of the embodiments of the present disclosure to aid understanding, and should be considered as illustrative only. Accordingly, those skilled in the art should understand that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, well-known descriptions of functions and structures are omitted in the following description for clarity and brevity.

[0013] FIG. 1 is a schematic flowchart of a driving information prediction method proposed according to an embodiment of the present disclosure, and includes the following. In S110, based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle in the first time period, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle in the first time period, a first master-slave relationship between the target vehicle and the first obstacle is determined. In S120, based on the first master-slave relationship, first predicted driving information is obtained. The first predicted driving information includes first predicted motion parameters of the target vehicle at a plurality of predicted times in the first time period, and second predicted motion parameters of the first obstacle at a plurality of predicted times in the first time period. In S130, based on the evaluation result corresponding to the first predicted driving information, first optimal driving information is determined. The first optimal driving information includes optimal predicted motion parameters of the target vehicle at a plurality of predicted times in the first time period, and optimal predicted motion parameters of the first obstacle at a plurality of predicted times in the first time period.

[0014] The driving information prediction method according to the embodiment of the present disclosure can be executed by an electronic device. The electronic device may be an in-vehicle terminal installed on the target vehicle, or another terminal device with computing capabilities and communicable with the target vehicle. The above is only an exemplary description of the electronic device. In actual processing, as long as it is an electronic device capable of executing the driving information prediction method according to this embodiment, it belongs to the protection scope of this embodiment and is not limited to the devices described in the above examples. The first obstacle may refer to any one of all obstacles located within the designated range of the target vehicle. The designated range of the target vehicle is a range centered on the target vehicle with a designated length as the radius. This designated length may be configured according to actual situations such as 200 meters, or 500 meters, or more, or less, and is not limited here. The first obstacle can belong to any one type of traffic participant. For example, the type of the first obstacle can be any one of a vehicle, a pedestrian, an animal, etc.

[0015] By adopting the above solutions, combined with the motion parameters of the target vehicle and the obstacle at the current time, and the route information of both in the first future time period, the first master-slave relationship between the target vehicle and the obstacle can be determined in real time. Furthermore, based on the first master-slave relationship between the two, the first predicted driving information can be obtained. Finally, based on the evaluation result of the first predicted driving information, the predicted optimal driving information can be determined. Since the master-slave relationship of each traffic participant can be analyzed based on the current state and future route of each traffic participant, and the driving information can be predicted and evaluated to obtain the optimal driving information, the accuracy of the finally predicted driving information can be improved.

[0016] In some possible embodiments, determining the first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle in the first time period, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle in the first time period includes: determining the priority of the right of way of the target vehicle and the first obstacle in the first time period based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle in the first time period, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle in the first time period; and determining the first master-slave relationship between the target vehicle and the first obstacle based on the priority of the right of way of the target vehicle and the first obstacle in the first time period.

[0017] Determining the priority of the right of way for the target vehicle and the first obstacle at a first time interval, based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle at a first time interval, includes obtaining the driving type of the target vehicle at a first time interval based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at a first time interval, obtaining the driving type of the first obstacle at a first time interval based on the motion parameters of the first obstacle at the current time and the predicted route information of the first obstacle at a first time interval, and obtaining the priority of the right of way for the target vehicle and the first obstacle at a first time interval based on the driving type of the target vehicle at a first time interval and the driving type of the first obstacle at a first time interval.

[0018] Here, the motion parameter is at least one of position, velocity, orientation, and acceleration. Includes. The driving type may also be referred to as a driving mode, and for example, the driving type of the target vehicle during the first hour may be one of several selectable driving types, which include at least one of straight, left turn, right turn, lane change, etc.

[0019] The process of obtaining the driving type of a target vehicle at a first time interval, based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at a first time interval, may involve using high-resolution map information, the position of the target vehicle at the current time, the speed of the target vehicle at the current time, the orientation of the target vehicle at the current time, and the route information of the target vehicle at a first time interval as first input parameters, and calculating the first input parameters using a first calculation function to obtain the driving type of the target vehicle at a first time interval. Here, the first calculation function can be constructed based on actual demand, and is not limited to that in this embodiment.

[0020] Here, the motion parameters of the target vehicle at the current time can be determined in conjunction with high-resolution data and positioning information, and the specific method of determination is not limited in this embodiment.

[0021] The route information for the target vehicle in the first hour can be determined based on high-resolution data, positioning information, and pre-planning information provided by a pre-planning system. The route information for the target vehicle in the first hour can also be simply called the route for the target vehicle in the first hour, or the pre-planned route of the target vehicle, and this embodiment does not limit the method of determination. The route information for the target vehicle in the first hour refers to the route that the target vehicle is scheduled to take within the first hour, the start time of the first hour may be the current time, and the duration of the first hour can be configured according to the actual situation. For example, the duration may be 10 seconds, or 1 minute, or more, or less, and is not limited here.

[0022] For example, calculating the first input parameter using the first calculation function and obtaining the driving type of the target vehicle at the first time duration can be expressed by the following equation.

number

[0023] The process of obtaining the driving type of the first obstacle at a first time interval, based on the motion parameters of the first obstacle at the current time and the predicted path information of the first obstacle at a first time interval, may involve using high-resolution map information, the position of the first obstacle at the current time, the speed of the first obstacle at the current time, the orientation of the first obstacle at the current time, the predicted path information of the first obstacle at a first time interval, the driving type of the target vehicle at a first time interval, and the vehicle flow type of the first obstacle as second input parameters, calculating the second input parameters using a second calculation function, and obtaining the driving type of the first obstacle at a first time interval. Here, the second calculation function may be the same as or different from the first calculation function, and both fall within the scope of protection of this embodiment. The second calculation function can be configured according to actual needs, and is not limited in this embodiment.

[0024] The motion parameters of the first obstacle at the current time and the predicted path information of the first obstacle at the first time length can be determined based on sensing and prediction information, high-resolution data, and positioning information, and this embodiment does not limit the specific sensing method. The predicted path information of the first obstacle at the first time length refers to predicting the path that the first obstacle is expected to take at the first time length.

[0025] The first obstacle's traffic flow type may be one of several selectable traffic flow types. These selectable traffic flow types can be classified by at least one of the following: direction of travel, speed of travel, etc. For example, based on direction of travel, they can be classified by at least one of the following: straight-ahead vehicles, turning vehicles, U-turn vehicles, merging vehicles, diverging vehicles, etc. Or, based on speed, they can be classified by at least one of the following: high-speed traffic, medium-speed traffic, low-speed traffic, etc. Furthermore, for example, these selectable traffic flow types can be classified by both direction of travel and speed. While the above-mentioned classification methods are included, they are not limited to these, and other classification methods for classifying these selectable traffic flow types may also be included; this embodiment does not limit or exhaustively enumerate them. The first obstacle's traffic flow type may be any one of several selectable traffic flow types determined based on a traffic flow classification strategy, and the traffic flow classification strategy may be pre-configured, but this embodiment does not limit the traffic flow classification strategy.

[0026] The calculation of the second input parameter using the second calculation function and obtaining the travel type at the first time length of the first obstacle can be expressed by the following equation.

number

[0027] The priority of the right of way for the target vehicle and the first obstacle at the first time interval may include the relative right of way priority of the target vehicle with respect to the first obstacle at the first time interval, and the relative right of way priority of the first obstacle with respect to the target vehicle at the first time interval. Here, the relative right of way priority can be expressed using a first or second value. For example, if the target vehicle has a first value relative right of way priority with respect to the first obstacle at the first time interval, and the first obstacle has a second value relative right of way priority with respect to the target vehicle at the first time interval, the target vehicle may have a higher right of way priority with respect to the first obstacle at the first time interval, and the first obstacle may have a lower right of way priority with respect to the target vehicle at the first time interval. These first and second values ​​are different and can be constructed according to the actual situation. For example, the first value may be 1 and the second value may be 0, or vice versa. Here, we do not limit or exhaustively enumerate all possible values ​​for the first and second values.

[0028] Obtaining the right of way priority for the target vehicle and the first obstacle during the first time period based on the target vehicle's driving type during the first time period and the first obstacle's driving type during the first time period may include obtaining the right of way priority for the target vehicle and the first obstacle during the first time period based on the target vehicle's driving type during the first time period, initial predicted motion parameters for multiple predicted times during the target vehicle's first time period, the first obstacle's driving type during the first time period, and initial predicted motion parameters for multiple predicted times during the first time period of the first obstacle.

[0029] Here, the initial predicted motion parameters for multiple predicted time points in the first time length of the target vehicle may be determined based on the route information for the first time length of the target vehicle and the motion parameters of the target vehicle at the current time. The specific method for determining the initial predicted motion parameters for multiple predicted time points in the first time length of the target vehicle is not limited in this embodiment. For example, the pre-policy determination module may determine them based on a pre-set strategy, or they may be calculated by a pre-policy determination algorithm in the pre-policy determination module, and this is not limited in this embodiment.

[0030] The initial predicted motion parameters for multiple predicted time points in the first time length of the first obstacle may be determined based on the predicted path information for the first time length of the first obstacle and the motion parameters of the first obstacle at the current time. This embodiment does not limit the specific method for determining the initial predicted motion parameters for multiple predicted time points in the first time length of the first obstacle. In this embodiment, the specific processing method for obtaining the right of passage priority for the target vehicle and the first obstacle during the first time period is not limited, based on the target vehicle's driving type during the first time period, the initial predicted motion parameters at multiple predicted times during the target vehicle's first time period, the driving type of the first obstacle during the first time period, and the initial predicted motion parameters at multiple predicted times during the first time period of the first obstacle.

[0031] Referring to Figure 2, the process of obtaining priority for the right of way between the target vehicle and the first obstacle over the first time period will be explained exemplified. First, the motion parameters of the target vehicle at the current time are determined in combination with high-resolution data and positioning information 201. Furthermore, route information for the target vehicle at a first time interval is determined based on pre-planning information provided by the pre-planning system 202. Both the motion parameters of the target vehicle at the current time and the route information for the target vehicle at a first time interval can be used as target vehicle position and motion tendency information 210. Based on the motion parameters of the target vehicle at the current time and the route information for the target vehicle at a first time interval, the driving type for the target vehicle at a first time interval is obtained.

[0032] Then, using high-resolution data and positioning information 201, and sensing and prediction information 203, the first obstacle position and motion tendency information 211 (i.e., motion parameters of the first obstacle at the present time, and predicted path information for the first time length of the first obstacle in the future (e.g., represented as T, where T is a positive number)) is determined, and the driving type of the first obstacle at the first time length is obtained based on the motion parameters of the first obstacle at the present time, the predicted path information for the first time length of the first obstacle, and the traffic flow strategy 204 (i.e., the traffic flow type of the first obstacle), etc.

[0033] The above processing steps rely not only on static high-resolution data (e.g., high-resolution map information) but also on acquiring real-time sensing, predictive data, and output results of pre-strategy decisions to ensure an accurate understanding of the surrounding environment. This allows for a precise analysis of the target vehicle's and the first obstacle's driving patterns over a first time period. This enables a preliminary understanding of the target vehicle's and the first obstacle's intentions and potential risks. By integrating this information, the system can construct a relatively comprehensive environmental model, laying a solid foundation for subsequent yielding / overtaking interaction simulations, collision risk assessments, and trajectory rationality evaluations.

[0034] Finally, the right-of-way priority 205 for the target vehicle and the first obstacle at the first time interval is determined by deeply analyzing the driving type of the target vehicle and the first obstacle at the first time interval. The determination of the right-of-way priority 205 for the target vehicle and the first obstacle at the first time interval can be based on, but is not limited to, a pre-set right-of-way priority-related strategy or algorithm. After determining the right-of-way priority 205 for the target vehicle and the first obstacle at the first time interval, it is processed using an encoding method to obtain encoded content necessary for subsequent processing, which may include, for example, at least one of the right-of-way priority 205 for the target vehicle and the first obstacle at the first time interval, initial predicted motion parameters for the target vehicle at multiple predicted times at the first time interval, initial predicted motion parameters for the first obstacle at multiple predicted times at the first time interval, and the traffic flow type of the first obstacle.

[0035] In this way, the motion parameters of the target vehicle and the first obstacle at the current time, and the path information of the target vehicle and the first obstacle at the future first time length, can be used to obtain the driving type of the target vehicle and the first obstacle, respectively. Furthermore, based on the driving types of the target vehicle and the first obstacle, the relative right-of-way priority of both can be determined. By determining the driving type in conjunction with the motion parameters of the target vehicle and the first obstacle at the current time, the real-time accuracy and accuracy of the driving types of both obtained through analysis can be guaranteed, as can the real-time accuracy and accuracy of the determined relative right-of-way priority of both.

[0036] The first master-slave relationship between the target vehicle and the first obstacle may include an object in a dominant position and an object in a subordinate position among the target vehicle and the first obstacle at the first time length. Here, the object in a dominant position may be the object among the target vehicle and the first obstacle that passes through the predicted merging area first, and the object in a subordinate position may be the object among the target vehicle and the first obstacle that passes through the predicted merging area later. The first master-slave relationship between the target vehicle and the first obstacle may be determined based on a pre-set related strategy and the priority of right of way between the target vehicle and the first obstacle over a first time period, or the priority of right of way between the target vehicle and the first obstacle over a first time period may be processed using a pre-set master-slave relationship analysis model, which will not be listed here in an exhaustive or limited manner.

[0037] Exemplary, determining a first master-slave relationship between a target vehicle and a first obstacle based on the right-of-way priority of the target vehicle and the first obstacle at a first time interval includes determining a predicted merging area based on initial predicted motion parameters at multiple predicted times for the target vehicle at a first time interval and initial predicted motion parameters at multiple predicted times for the first obstacle at a first time interval, and determining a first master-slave relationship between a target vehicle and a first obstacle based on the right-of-way priority of the target vehicle and the first obstacle at a first time interval, the predicted merging area, and reference information, wherein the reference information includes at least one of the driving type of the target vehicle, the driving type of the first obstacle, the motion parameters of the target vehicle at the current time, the motion parameters of the first obstacle at the current time, initial predicted motion parameters at multiple predicted times for the target vehicle at a first time interval, and initial predicted motion parameters at multiple predicted times for the first obstacle at a first time interval.

[0038] For example, a predicted merging area is determined based on the initial predicted motion parameters at multiple predicted times for the target vehicle at a first time interval, and the initial predicted motion parameters at multiple predicted times for the first obstacle at a first time interval. Based on the priority of right of way for the target vehicle and the first obstacle at a first time interval, the initial predicted motion parameters at multiple predicted times for the target vehicle at a first time interval, and the initial predicted motion parameters at multiple predicted times for the first obstacle at a first time interval are used to determine which of the target vehicle and the first obstacle will pass through the predicted merging area first. The object that passes through the predicted merging area first is designated as the object with a dominant position in the first master-slave relationship, and the other objects are designated as objects with a subordinate position in the first master-slave relationship. The method for determining which of the target vehicle and the first obstacle will pass through the predicted merging area first is not limited here.

[0039] For example, a predicted merging area is determined based on the initial predicted motion parameters of the target vehicle at multiple predicted times in a first time period and the initial predicted motion parameters of the first obstacle at multiple predicted times in a first time period; a first distance between the target vehicle and the predicted merging area and a second distance between the first obstacle and the predicted merging area are determined based on the motion parameters of the target vehicle at the current time and the motion parameters of the first obstacle at the current time; and a first master-slave relationship is determined between the target vehicle and the first obstacle based on the first distance, the second distance, and the priority of right of way for the target vehicle and the first obstacle in a first time period. For example, if the first distance and the second distance are close, that is, the difference between the first distance and the second distance is less than a specified distance threshold, and the specified distance threshold can be configured according to the actual situation, and may be 10 meters, 20 meters, or more or less, in this case the difference between the first distance and the second distance is not large, then, based on the motion parameters of the target vehicle and the first obstacle at the current time, the time length for the target vehicle and the first obstacle to reach the predicted merging area can be predicted, and the time length for both to reach the predicted merging area can be made approximately the same, so that the object with a relatively higher priority for the right of way among the two is determined to be the object that passes through the predicted merging area first, i.e., the object that holds a leading position in the first master-slave relationship, and the other object that holds a subordinate position.

[0040] The above is merely an illustrative explanation; in actual processing, other methods or strategies may be used to determine the first master-slave relationship between the target vehicle and the first obstacle. As an alternative example, a method for determining a first master-slave relationship may be implemented to include: determining a predicted merging area based on initial predicted motion parameters of a target vehicle at multiple predicted times in a first time length and initial predicted motion parameters of a first obstacle at multiple predicted times in a first time length; determining a first distance between the target vehicle and the predicted merging area and a second distance between the first obstacle and the predicted merging area based on the motion parameters of the target vehicle at the current time and the motion parameters of the first obstacle at the current time; and determining a first master-slave relationship between the target vehicle and the first obstacle based on the first distance, the second distance, and at least one of the driving type of the target vehicle, the driving type of the first obstacle, the motion parameters of the target vehicle at the current time, the motion parameters of the first obstacle at the current time, the multiple predicted motion parameters of the target vehicle at multiple predicted times in a first time length and initial predicted motion parameters of the first obstacle at multiple predicted times in a first time length.

[0041] For example, suppose the first distance is much larger than the second distance, for example, the difference between the first distance and the second distance is greater than a specified distance threshold, or the first distance is greater than the second distance multiplied by a specified multiple, where the specified multiple can be constructed according to the actual situation, for example, 2 times, 3 times, or more, and we will not list them here in an exhaustive or limiting manner. In this case, because the first distance is much larger than the second distance, we can determine that the target vehicle is much further away from the merging area than the first obstacle, and we can determine that the first hierarchical relationship is that the first obstacle is in a dominant position and the target vehicle is in a subordinate position.

[0042] Assume that the first distance and the second distance are close, for example, that the difference between the first distance and the second distance is not greater than a specified distance threshold. In this case, since the difference between the first distance and the second distance is not large, the first master-slave relationship can be determined based on the priority of the right of way for the target vehicle and the first obstacle at the first time length, and at least one of the following: the driving type of the target vehicle, the driving type of the first obstacle, the motion parameters of the target vehicle at the current time, the motion parameters of the first obstacle at the current time, the initial predicted motion parameters of the target vehicle at multiple predicted times at the first time length, and the initial predicted motion parameters of the first obstacle at multiple predicted times at the first time length. For example, based on the motion parameters of the target vehicle and the first obstacle at the current time, the time lengths for the target vehicle and the first obstacle to reach the predicted merging area are predicted, and the object with a shorter time length to reach the predicted merging area is designated as the dominant object in the first master-slave relationship, and the object with a longer time length to reach the predicted merging area is designated as the subordinate object in the first master-slave relationship.

[0043] It should be noted that the above are all illustrative explanations, and in actual processing, the first master-slave relationship between the target vehicle and the first obstacle can be determined using other methods or strategies, and this embodiment does not limit or exhaustively list such methods.

[0044] In this way, the relative right-of-way priority of both the target vehicle and the first obstacle can be determined first, and then the first master-slave relationship between them can be determined based on the right-of-way priority of both. In this way, the determination of the first master-slave relationship between the target vehicle and the first obstacle can be made more accurate, and consequently, the accuracy of subsequent predicted driving information can be guaranteed.

[0045] In some possible embodiments, obtaining first predictive driving information based on the first master-slave relationship includes performing a forward simulation based on the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time to obtain first predictive motion parameters for the target vehicle at multiple predicted times in the first time length, and second predictive motion parameters for the first obstacle at multiple predicted times in the first time length, and using the first predictive motion parameters for the target vehicle at multiple predicted times in the first time length, and the second predictive motion parameters for the first obstacle at multiple predicted times in the first time length as the first predictive driving information.

[0046] Here, performing a forward simulation based on the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, and obtaining the first predicted motion parameters for the target vehicle at multiple predicted times in the first time length, and the second predicted motion parameters for the first obstacle at the multiple predicted times in the first time length, may include iterating through the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time multiple times based on a forward simulation method, to obtain the first predicted motion parameters for the target vehicle at multiple predicted times in the first time length, and the second predicted motion parameters for the first obstacle at multiple predicted times in the first time length.

[0047] For example, the process of iterating multiple times based on a forward simulation method to obtain first predicted motion parameters for the target vehicle under multiple predicted times in the first time length, and second predicted motion parameters for the first obstacle under the multiple predicted times in the first time length, may include, during the i-th iteration, using the first master-slave relationship, the motion parameters for the target vehicle under the i-th time, and the motion parameters for the first obstacle under the i-th time as the i-th input parameter, processing the i-th input parameter based on a forward simulation method, and obtaining first predicted motion parameters for the target vehicle under the (i+1)th predicted time, and second predicted motion parameters for the first obstacle under the (i+1)th predicted time; and determining that the multiple iterations are complete when the (i+1)th predicted time is the last predicted time in the first time length, and obtaining first predicted motion parameters for the target vehicle under multiple predicted times in the first time length, and second predicted motion parameters for the first obstacle under the multiple predicted times in the first time length. Here, if i is equal to 1, the i-th time is the current time, and if i is an integer greater than 1, the i-th time is the i-th predicted time.

[0048] Furthermore, if the (i+1)th predicted time is not the last predicted time in the first time length, the process may further include returning to perform the (i+1)th iteration, which is the same as the ith iteration and therefore will not be repeated here. The aforementioned forward simulation methods may include the Stackelberg competition and Monte Carlo tree search methods, and this document does not provide a limited or exhaustive list of all algorithms and methods available for forward simulation.

[0049] The first predicted motion parameters for a plurality of predicted times in the first time length of the target vehicle may include the first predicted motion parameters for each of the prediction times in the plurality of prediction times in the first time length of the target vehicle, and the first predicted driving parameters for any of the prediction times include at least one of a first predicted speed for any of the prediction times, a first predicted position for any of the prediction times, and a first predicted direction for any of the prediction times. The second predicted motion parameters at multiple predicted times in the first time length of the first obstacle may include the second predicted motion parameters at each of the multiple predicted times in the first time length of the first obstacle, and the second predicted motion parameters at any of the predicted times include at least one of the second predicted velocity at any of the predicted times, the second predicted position at any of the predicted times, and the second predicted orientation at any of the predicted times.

[0050] In this way, the current motion parameters of the target vehicle, the current motion parameters of the first obstacle obtained by sensing them in real time, and the first master-slave relationship between the target vehicle and the first obstacle determined in real time are used to jointly perform a forward simulation, predicting the motion parameters of the target vehicle and the first obstacle at multiple predicted time points in the future, thereby ensuring the real-time nature and accuracy of the prediction results.

[0051] In some possible embodiments, determining the first optimal driving information based on the evaluation result corresponding to the first predicted driving information includes one of the following: if the evaluation result corresponding to the first predicted driving information satisfies a first condition, setting the first predicted driving information as the first optimal driving information; if the evaluation result corresponding to the first predicted driving information does not satisfy the first condition, altering the first master-slave relationship to obtain a second master-slave relationship between the target vehicle and the first obstacle, obtaining second predicted driving information based on the second master-slave relationship, and determining the first optimal driving information from the first predicted driving information and the second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information.

[0052] The first condition includes at least one of the following: the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold; and the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the subjective evaluation threshold. The first condition can be used to measure whether the first predicted driving information satisfies the safety requirements and / or subjective requirements. Here, the safety threshold is also called the safety requirement threshold, and the subjective evaluation threshold is also called the subjective requirement threshold, and both the safety threshold and the subjective evaluation threshold can be configured according to the actual situation, and are not limited in this embodiment.

[0053] The method further includes at least one of the following: calculating a first safety evaluation value in the evaluation result corresponding to the first predicted driving information based on a safety evaluation formula, the first master-slave relationship, and the first predicted driving information; calculating a first subjective evaluation value in the evaluation result corresponding to the first predicted driving information based on a subjective evaluation formula, the first master-slave relationship, and the first predicted driving information; calculating a second safety evaluation value in the evaluation result corresponding to the second predicted driving information based on a safety evaluation formula, the second master-slave relationship, and the second predicted driving information; and calculating a second subjective evaluation value in the evaluation result corresponding to the second predicted driving information based on a subjective evaluation formula, the second master-slave relationship, and the second predicted driving information.

[0054] Preferably, the evaluation result corresponding to the first predicted driving information may include a first safety evaluation value and a first subjective evaluation value. In this case, the first condition includes that the first safety evaluation value in the evaluation result corresponding to the first predicted driving information is higher than the safety threshold, and the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information is higher than the subjective evaluation threshold. The first safety evaluation value can be used to indicate the level of collision risk between the target vehicle and the first obstacle corresponding to the first predicted driving information. A higher first safety evaluation value indicates a lower collision risk, while a lower first safety evaluation value indicates a higher collision risk. A method for obtaining a first safety evaluation value in the evaluation results corresponding to the first predicted driving information may include calculating a first safety evaluation value in the evaluation results corresponding to the first predicted driving information based on a safety evaluation formula, the first master-slave relationship, and the first predicted driving information. Here, the safety evaluation formula can be constructed based on actual conditions.

[0055] For example, calculating the first safety evaluation value in the evaluation result corresponding to the first predictive driving information based on the safety evaluation formula, the first master-slave relationship, and the first predictive driving information can be expressed as follows.

number

[0056] The first sensory evaluation value can represent the sensory experience during the interaction process between the target vehicle and the first obstacle, corresponding to the first predicted driving information. Here, "sensation" can refer to the feeling of being pushed in the back by a person due to acceleration during the interaction process between the target vehicle and the first obstacle, and / or the forward leaning state of a person due to deceleration during the interaction process between the target vehicle and the first obstacle, where "person" can include at least one of the driver in the target vehicle, the passenger in the target vehicle, the driver in the first obstacle, or the passenger in the first obstacle. A higher first sensory evaluation value indicates a higher sensory experience during the interaction process between the target vehicle and the first obstacle, while a lower first sensory evaluation value indicates a lower sensory experience during the interaction process between the target vehicle and the first obstacle.

[0057] A method for obtaining a first subjective evaluation value in the evaluation results corresponding to the first predicted driving information may include calculating a first subjective evaluation value in the evaluation results corresponding to the first predicted driving information based on a subjective evaluation formula, the first master-slave relationship, and the first predicted driving information.

[0058] For example, calculating the first subjective evaluation value in the evaluation result corresponding to the first predictive driving information, based on the subjective evaluation formula, the first master-slave relationship, and the first predictive driving information, can be expressed as follows.

number

[0059] Determining whether the evaluation result corresponding to the first predicted driving information satisfies the first condition may involve determining whether the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold, and whether the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the perceived evaluation threshold. Furthermore, if the first safety evaluation value in the evaluation result corresponding to the first predicted driving information is higher than the safety threshold, and the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information is higher than the perceived evaluation threshold, it may be determined that the first condition is satisfied. Alternatively, if the first safety evaluation value in the evaluation result corresponding to the first predicted driving information does not exceed the safety threshold, and / or if the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information does not exceed the perceived evaluation threshold, it may be determined that the first condition is not satisfied.

[0060] Selectively, the evaluation result corresponding to the first predicted driving information may include a first safety evaluation value. The processing method for obtaining the first safety evaluation value in the evaluation result corresponding to the first predicted driving information is the same as in the embodiment described above and will not be repeated here. In this case, the first condition may include the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeding the safety threshold. Specifically, determining whether the evaluation result corresponding to the first predicted driving information satisfies the first condition is the same as determining whether the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold. Furthermore, if the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold, it is determined that the first condition is satisfied, or if the first safety evaluation value in the evaluation result corresponding to the first predicted driving information does not exceed the safety threshold, it is determined that the first condition is not satisfied.

[0061] Selectively, the evaluation result corresponding to the first predicted driving information may include the first perceived evaluation value. The processing method for obtaining the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information is the same as in the example above and will not be repeated here. In this case, the first condition includes the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information exceeding the perceived evaluation threshold. Specifically, determining whether the evaluation result corresponding to the first predicted driving information satisfies the first condition may be done by determining whether the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the perceived evaluation threshold. Furthermore, if the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the perceived evaluation threshold, it is determined that the first condition is satisfied, or if the first perceived evaluation value in the evaluation result corresponding to the first predicted driving information does not exceed the perceived evaluation threshold, it is determined that the first condition is not satisfied.

[0062] In one example, the evaluation result corresponding to the first predicted driving information satisfying the first condition can indicate that the first predicted driving information satisfies the safety requirements and / or the subjective requirements. Therefore, in this example, the first predicted driving information is directly used as the first optimal driving information, that is, the optimal predicted motion parameters under each of the multiple predicted times in the first time length of the target vehicle in the first optimal driving information are the first predicted motion parameters under each predicted time in the first time length of the target vehicle, and the optimal predicted motion parameters under the multiple predicted times in the first time length of the first obstacle in the first optimal driving information are the second predicted motion parameters under each predicted time in the first time length of the first obstacle.

[0063] In one example, if the evaluation result corresponding to the first predicted driving information does not satisfy the first condition, it can indicate that the first predicted driving information does not satisfy the safety requirements and / or the subjective requirements. Therefore, in this example, it is necessary to reverse the first master-slave relationship to obtain a second master-slave relationship between the target vehicle and the first obstacle, obtain second predicted driving information based on the second master-slave relationship, and further perform the process of determining the first optimal driving information from the first and second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information. In this way, through a first condition that can be used to measure whether the driving information meets safety and / or subjective requirements, the first predicted driving information corresponding to the first master-slave relationship can be evaluated, and the safety and / or subjective experience of the ultimately obtained first optimal driving information can be guaranteed.

[0064] Reversing the first master-slave relationship and obtaining a second master-slave relationship between the target vehicle and the first obstacle can refer to reversing the dominant and subordinate roles between the target vehicle and the first obstacle within a first time period in the first master-slave relationship, thereby obtaining a second master-slave relationship between the target vehicle and the first obstacle. For example, in the first master-slave relationship, the target vehicle is the dominant role and the first obstacle is the subordinate role; after reversing the first master-slave relationship, in the resulting second master-slave relationship, the first obstacle is the dominant role and the target vehicle is the subordinate role.

[0065] Obtaining second predictive driving information based on the second master-slave relationship may include performing a forward simulation based on the second master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time to obtain third predictive motion parameters for the target vehicle at multiple predicted times in the first time length, and fourth predictive motion parameters for the first obstacle at multiple predicted times in the first time length, and using the third predictive motion parameters for the target vehicle at multiple predicted times in the first time length, and the fourth predictive motion parameters for the first obstacle at multiple predicted times in the first time length as the second predictive driving information.

[0066] Here, the processing method for obtaining the third predicted motion parameters for the target vehicle at multiple predicted time points in the first time length, and the fourth predicted motion parameters for the first obstacle at multiple predicted time points in the first time length, using forward simulation, is similar to the method used in the above-described embodiment to obtain the first predicted motion parameters for the target vehicle at multiple predicted time points in the first time length, and the second predicted motion parameters for the first obstacle at multiple predicted time points in the first time length, and therefore will not be described again here.

[0067] The third predicted motion parameters for a plurality of predicted times in the first time length of the target vehicle may include the third predicted motion parameters for each of the prediction times in the plurality of prediction times in the first time length of the target vehicle, and the third predicted driving parameter for any of the prediction times includes at least one of the third predicted speed, the third predicted position, and the third predicted orientation for any of the prediction times. The fourth predicted motion parameters at multiple predicted times in the first time length of the first obstacle may include the fourth predicted motion parameters at each of the multiple predicted times in the first time length of the first obstacle, and the fourth predicted motion parameters at any of the predicted times include at least one of the fourth predicted velocity at any of the predicted times, the fourth predicted position at any of the predicted times, and the fourth predicted orientation at any of the predicted times.

[0068] In the process of obtaining the second predicted driving information and the first predicted driving information, the motion parameters of the target vehicle at the current time and the motion parameters of the first obstacle at the current time were used as input in both cases. However, the two have different master-slave relationships. For example, in the first master-slave relationship, the target vehicle is in a dominant position and the first obstacle is in a subordinate position, and in the second master-slave relationship, the target vehicle is in a subordinate position and the first obstacle is in a dominant position. In order to satisfy the need for different objects in the first and second master-slave relationships to pass through the predicted merging area first, the predicted motion parameters of the target vehicle and the first obstacle included in the second predicted driving information and the first predicted driving information at the same predicted time may be different. Specifically, the third predicted motion parameter at the first predicted time in the first time period of the target vehicle and the first predicted motion parameter at the first predicted time in the first time period of the target vehicle may be the same or different. For example, at least one of the third predicted speed, third predicted position, and third predicted direction at the first predicted time in the first time period of the target vehicle may be different from at least one of the first predicted speed, first predicted position, and first predicted direction at the first predicted time in the first time period of the target vehicle. The fourth predicted motion parameter at the first predicted time in the first time period of the first obstacle and the second predicted motion parameter at the first predicted time in the first time period of the first obstacle may be the same or different. For example, at least one of the fourth predicted speed, fourth predicted position, and fourth predicted direction at the first predicted time in the first time period of the first obstacle may be different from at least one of the second predicted speed, second predicted position, and second predicted direction at the first predicted time in the first time period of the first obstacle.

[0069] Preferably, the evaluation result corresponding to the first predictive driving information includes a first safety evaluation value and a first subjective evaluation value. The evaluation result corresponding to the second predictive driving information may also include a second safety evaluation value and a second subjective evaluation value. The explanation regarding the first safety evaluation value and the first perceived evaluation value is the same as in the previously described embodiment and will not be repeated here.

[0070] The second safety evaluation value can be used to indicate the level of collision risk between the target vehicle and the first obstacle, corresponding to the second predicted driving information. A method for obtaining a second safety evaluation value may include calculating a second safety evaluation value in the evaluation result corresponding to the second predictive driving information, based on the safety evaluation formula, the second master-slave relationship, and the second predictive driving information.

[0071] For example, calculating the second master-slave relationship and the second predicted driving information based on the safety evaluation formula, and obtaining a safety evaluation value between the target vehicle and the first obstacle corresponding to the second predicted driving information, can be expressed as follows.

number

[0072] The second subjective evaluation value can be used to represent the subjective experience during the interaction process between the target vehicle and the first obstacle, corresponding to the second predicted driving information. A method for obtaining a second subjective evaluation value may include calculating a second subjective evaluation value in the evaluation result corresponding to the second predictive driving information, based on the subjective evaluation formula, the second master-slave relationship, and the second predictive driving information.

[0073] For example, calculating the second master-slave relationship and the second predicted driving information based on the subjective evaluation formula, and obtaining subjective evaluation values ​​in the interaction process between the target vehicle and the first obstacle corresponding to the second predicted driving information, can be expressed as follows.

number

[0074] In this case, determining the first optimal driving information from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information includes determining a first reference value corresponding to the first predicted driving information based on the evaluation results corresponding to the first predicted driving information, determining a second reference value corresponding to the second predicted driving information based on the evaluation results corresponding to the second predicted driving information, and selecting the first optimal driving information from the first and second predicted driving information based on the maximum value among the first and second reference values.

[0075] Here, determining a first reference value corresponding to the first predicted driving information based on the evaluation results corresponding to the first predicted driving information may include obtaining a first value by multiplying a first safety evaluation value in the evaluation results corresponding to the first predicted driving information by a first factor, obtaining a second value by multiplying a first subjective evaluation value in the evaluation results corresponding to the first predicted driving information by a second factor, and adding the first value and the second value to obtain a first reference value corresponding to the first predicted driving information. Determining a second reference value corresponding to the second predicted driving information based on the evaluation results corresponding to the second predicted driving information may include multiplying the second safety evaluation value in the evaluation results corresponding to the second predicted driving information by a first factor to obtain a third value, multiplying the second subjective evaluation value in the evaluation results corresponding to the second predicted driving information by a second factor to obtain a fourth value, and adding the third value and the fourth value to obtain a second reference value corresponding to the second predicted driving information.

[0076] The first and second factors can be determined based on the equilibrium factor. This equilibrium factor can be constructed based on the actual situation, and the value of the equilibrium factor is greater than 0 and less than 1, for example, the equilibrium factor It is represented as JPEG2026104836000043.jpg85, and the range of the value of the equilibrium factor is It can be represented as JPEG2026104836000044.jpg1021. The first factor is an equilibrium factor (for example, the first factor is The second factor may be equal to (represented as JPEG2026104836000045.jpg85), and the second factor may be equal to subtracting the equilibrium factor from 1, for example the second factor is It can be represented as JPEG2026104836000046.jpg816.

[0077] Selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value among the first and second reference values ​​includes selecting the largest reference value from the first and second reference values, and selecting the predicted driving information corresponding to the maximum reference value from the first predicted driving information and the second predicted driving information to be the first optimal driving information. In this example, the first reference value is calculated together with the first safety evaluation value and the first subjective evaluation value. Therefore, the first reference value may be a numerical value that represents the overall evaluation status of the first predicted driving information, and the magnitude of the first reference value is positively correlated with the quality of the overall evaluation status of the first predicted driving information.

[0078] Since the second reference value is calculated together with the second safety evaluation value and the second subjective evaluation value, the second reference value may also be a numerical value that indicates the overall evaluation status of the second predictive driving information, and the magnitude of the second reference value is positively correlated with the quality of the overall evaluation status of the second predictive driving information.

[0079] Furthermore, since the magnitudes of the first and second reference values ​​correlate with the overall evaluation status of the corresponding predicted driving information, the predicted driving information corresponding to the maximum value of the first and second reference values ​​is the one with the better overall evaluation status. Based on this, in this example, the predicted driving information with the best overall evaluation status can be selected as the first optimal driving information based on the maximum value of the first and second reference values.

[0080] For example, selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value of the first reference value and the second reference value can be expressed using the following formula.

number

[0081] For example, if it is determined from the first and second predicted driving information that the first predicted driving information is the first optimal driving information, then the optimal predicted motion parameters for each of the multiple predicted times in the first time length of the target vehicle in the first optimal driving information are the first predicted motion parameters for each predicted time in the first time length of the target vehicle, and the optimal predicted motion parameters for each of the multiple predicted times in the first time length of the first obstacle in the first optimal driving information are the second predicted motion parameters for each predicted time in the first time length of the first obstacle. Also, for example, if it is determined from the first and second predicted driving information that the second predicted driving information is the first optimal driving information, then the optimal predicted motion parameters for each of the multiple predicted times in the first time length of the target vehicle in the first optimal driving information are the third predicted motion parameters for each predicted time in the first time length of the target vehicle, and the optimal predicted motion parameters for each of the multiple predicted times in the first time length of the first obstacle in the first optimal driving information are the fourth predicted motion parameters for each predicted time in the first time length of the first obstacle.

[0082] Selectively, the evaluation result corresponding to the first predictive driving information may include a first safety evaluation value, and the evaluation result corresponding to the second predictive driving information may include a second safety evaluation value. The explanation of the first safety evaluation value and the second safety evaluation value is the same as in the embodiment described above and will not be repeated here.

[0083] In this case, determining the first optimal driving information from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information includes determining a first reference value corresponding to the first predicted driving information based on a first safety evaluation value in the evaluation results corresponding to the first predicted driving information, determining a second reference value corresponding to the second predicted driving information based on a second safety evaluation value in the evaluation results corresponding to the second predicted driving information, and selecting the first optimal driving information from the first and second predicted driving information based on the maximum value among the first and second reference values.

[0084] Determining a first reference value corresponding to the first predicted driving information based on a first safety evaluation value in the evaluation results corresponding to the first predicted driving information can mean setting the first safety evaluation value in the evaluation results corresponding to the first predicted driving information as the first reference value corresponding to the first predicted driving information. Determining a second reference value corresponding to the second predictive driving information based on a second safety evaluation value in the evaluation results corresponding to the second predictive driving information can mean setting the second safety evaluation value in the evaluation results corresponding to the second predictive driving information as the second reference value corresponding to the second predictive driving information.

[0085] Selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value among the first and second reference values ​​includes selecting the largest reference value from the first and second reference values, and selecting the predicted driving information corresponding to the maximum reference value from the first predicted driving information and the second predicted driving information to be the first optimal driving information.

[0086] In this example, the first reference value is equal to the first safety evaluation value, so the first reference value and the first safety evaluation value have the same meaning. Both are numerical values ​​that indicate the safety evaluation status of the first predicted driving information, and the magnitude of the first reference value is positively correlated with the quality of the safety evaluation status of the first predicted driving information. The second reference value is equal to the second safety evaluation value, so the second reference value and the second safety evaluation value have the same meaning. Both are numerical values ​​that indicate the safety evaluation status of the second predicted driving information, and the magnitude of the second reference value is positively correlated with the quality of the safety evaluation status of the second predicted driving information.

[0087] Furthermore, since the magnitudes of the first and second reference values ​​are positively correlated with the safety evaluation status of the corresponding predicted driving information, the predicted driving information corresponding to the maximum value of the first and second reference values ​​is the one with the better safety evaluation status. Therefore, in this example, the predicted driving information with the best safety evaluation status can be selected as the first optimal driving information based on the maximum value of the first and second reference values.

[0088] For example, selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value of the first reference value and the second reference value can be expressed using the following formula.

number

[0089] Selectively, the evaluation result corresponding to the first predicted driving information may include a first subjective evaluation value, and the evaluation result corresponding to the second predicted driving information may include a second subjective evaluation value. The explanation of the first subjective evaluation value and the second subjective evaluation value is the same as in the embodiment described above and will not be repeated here.

[0090] In this case, determining the first optimal driving information from the first and second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information includes determining a first reference value corresponding to the first predicted driving information based on a first perceived evaluation value in the evaluation result corresponding to the first predicted driving information, determining a second reference value corresponding to the second predicted driving information based on a second perceived evaluation value in the evaluation result corresponding to the second predicted driving information, and selecting the first optimal driving information from the first and second predicted driving information based on the maximum value among the first and second reference values.

[0091] Determining a first reference value corresponding to the first predicted driving information based on a first subjective evaluation value in the evaluation results corresponding to the first predicted driving information can mean setting the first subjective evaluation value in the evaluation results corresponding to the first predicted driving information as the first reference value corresponding to the first predicted driving information. Determining a second reference value corresponding to the second predicted driving information based on the second subjective evaluation value in the evaluation results corresponding to the second predicted driving information can mean setting the second subjective evaluation value in the evaluation results corresponding to the second predicted driving information as the second reference value corresponding to the second predicted driving information.

[0092] Selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value among the first and second reference values ​​may include selecting the largest reference value from the first and second reference values, and selecting the predicted driving information corresponding to the maximum reference value from the first predicted driving information and the second predicted driving information to be the first optimal driving information.

[0093] In this example, the first reference value is equal to the first perceived evaluation value, so the first reference value and the first perceived evaluation value have the same meaning. Both are numerical values ​​that indicate the perceived evaluation status of the first predicted driving information, and the magnitude of the first reference value is positively correlated with the quality of the perceived evaluation status of the first predicted driving information. The second reference value is equal to the second perceived evaluation value, so the second reference value and the second perceived evaluation value have the same meaning. Both are numerical values ​​that indicate the perceived evaluation status of the second predicted driving information, and the magnitude of the second reference value is positively correlated with the quality of the perceived evaluation status of the second predicted driving information.

[0094] Furthermore, since the magnitudes of the first and second reference values ​​are positively correlated with the perceived quality of the corresponding predicted driving information, the predicted driving information corresponding to the maximum value of the first and second reference values ​​is the one with the better perceived quality. Therefore, in this example, the predicted driving information with the best perceived quality can be selected as the first optimal driving information based on the maximum value of the first and second reference values.

[0095] The process for determining the first optimal driving information described above will be illustrated using Figure 3. First, the master-slave relationship 302 is determined based on the right-of-way priority 301 of the target vehicle and the first obstacle at the first time interval, the initial predicted motion parameters of the target vehicle at multiple predicted time points at the first time interval, and the initial predicted motion parameters of the first obstacle at multiple predicted time points at the first time interval. Specifically, the first master-slave relationship 302 between the target vehicle and the first obstacle is determined. For example, the master-slave relationship between the target vehicle and the first obstacle at the first time interval is determined based on the relative position, speed, acceleration of the target vehicle and the first obstacle at multiple predicted time points at the first time interval, the traffic flow type of the first obstacle, and the right-of-way priority of the target vehicle and the first obstacle at the first time interval. Confirm JPEG2026104836000057.jpg77.

[0096] Then, based on existing kinematic models, and in conjunction with forward simulation methods such as the Stackelberg race and Monte Carlo tree search method, a forward simulation 303 of yielding and overtaking interactions is performed based on the first master-slave relationship between the target vehicle and the first obstacle, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, thereby obtaining first predicted driving information.

[0097] Again, based on the first predicted driving information, a collision risk and trajectory rationality evaluation 304 is performed, that is, a safety evaluation value corresponding to the first predicted driving information (collision risk of both) (Used to evaluate JPEG2026104836000058.jpg97) and perceived evaluation value (perceived loss of overtaking and yielding) The value used to evaluate JPEG2026104836000059.jpg86 is calculated, and the specific calculation method is the same as in the example described above, so it will not be repeated here.

[0098] If the evaluation results determined based on the first predicted driving information indicate a high risk of collision and perceived loss for both parties, and a high risk associated with yielding or overtaking due to the decision-making process between one's own vehicle and the other vehicle, then it is necessary to prove that the current rationality of the first predicted driving information is poor, to review the first master-servant relationship, and to make appropriate adjustments. Therefore, a second competition 305 may be further implemented, which may include switching the first master-servant relationship to a second master-servant relationship, allowing both parties to obtain more favorable conditions for decision-making. This adjustment is not only based on risk assessment but also aims to achieve more efficient yielding / overtaking interaction and risk control in uncertain traffic environments. Second master-servant relationship after exchange. Based on JPEG2026104836000060.jpg77, a forward simulation is performed again to obtain second predicted driving information, and then the collision risk and trajectory rationality are evaluated based on the second predicted driving information, that is, safety evaluation values ​​corresponding to the second predicted driving information (collision risk of both) The JPEG2026104836000061.jpg87 image is used to evaluate the subjective evaluation value (used to evaluate the perceived loss of overtaking and yielding), and the specific calculation method is the same as in the example described above, so it will not be repeated here.

[0099] Finally, based on the evaluation results of the two sets of predicted driving information before and after the master-slave relationship exchange, the first optimal driving information is selected, ensuring that both parties can complete the overtaking and yielding interaction in a safe and comfortable manner. In this way, subjective and / or safety evaluations are performed in conjunction with the first master-slave relationship, the target vehicle and the first obstacle included in the first predicted driving information, at each predicted time, thereby ensuring the comprehensiveness and timeliness of the evaluation of the first predicted driving information. Similarly, subjective and / or safety evaluations are performed in conjunction with the second master-slave relationship, the target vehicle and the first obstacle included in the second predicted driving information, at each predicted time, thereby ensuring the comprehensiveness and timeliness of the evaluation of the second predicted driving information.

[0100] Furthermore, by combining the evaluation results of the first and second predicted driving information, the above processing allows for the determination of the first optimal driving information from the two predicted driving information sets. Since the two predicted driving information sets are determined based on two types of hierarchical relationships, it is possible to provide the most comprehensive evaluation results for the various predicted driving information sets available to each traffic participant, and furthermore, the accuracy of the first optimal driving information ultimately determined can be guaranteed.

[0101] By adopting the solution provided by the above embodiments, the first predicted driving information corresponding to the first master-slave relationship can be evaluated through a first condition that can be used to measure whether the predicted driving information satisfies safety requirements and / or perceptual requirements. Furthermore, in conjunction with the evaluation results, it is possible to decide whether to further reverse the master-slave relationship and re-determine the first optimal driving information, or to directly use the first predicted driving information as the first optimal driving information. This ultimately guarantees the accuracy of the evaluation of the predicted driving information and ensures the safety and / or perceptual experience of the final obtained first optimal driving information.

[0102] In some possible embodiments, determining first optimal driving information based on evaluation results corresponding to the first predicted driving information includes altering the first master-slave relationship to obtain a second master-slave relationship between the target vehicle and the first obstacle, obtaining second predicted driving information based on the second master-slave relationship, and determining the first optimal driving information from the first and second predicted driving information based on evaluation results corresponding to the second predicted driving information and evaluation results corresponding to the first predicted driving information. The process of alternating the first master-slave relationship in this embodiment to obtain a second master-slave relationship between the target vehicle and the first obstacle, obtaining second predicted driving information based on the second master-slave relationship, and determining the first optimal driving information from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information, will not be repeated here, as the specific explanations of each of the above processes are the same as in the embodiments described above.

[0103] The difference between this embodiment and the previously described embodiment is that, in this embodiment, it is not necessary to perform an evaluation beforehand to determine whether the evaluation result corresponding to the first predicted driving information satisfies the first condition before switching the first master-slave relationship. Instead, after obtaining the first predicted driving information in the first master-slave relationship, the first master-slave relationship is directly switched to obtain the second master-slave relationship. After obtaining two types of predicted driving information in the two master-slave relationships, the first optimal driving information is selected by combining the evaluation results of the two predicted driving information. The solution provided by this embodiment reduces the process of determining whether the first condition is met, and allows for the direct evaluation of two types of predictive driving information in two master-slave relationships to select the first optimal driving information. This ensures the accuracy of the predictive driving information evaluation and ultimately guarantees the safety and user experience of the first optimal driving information obtained.

[0104] In some possible embodiments, the system may further include determining first optimal driving information based on evaluation results corresponding to the first predicted driving information, and then generating a policy decision command for controlling the target vehicle to perform yielding or overtaking based on the first optimal driving information and evaluation results corresponding to the first optimal driving information. Specifically, the policy decision command may include at least one of the following: the speed planning result for each of the multiple predicted times in the first time period of the target vehicle; the route planning result for the first time period of the target vehicle; and the position, orientation, etc., for each of the multiple predicted times in the first time period of the target vehicle.

[0105] Regarding the target vehicle, the total number of obstacles within the designated area of ​​the target vehicle may be one or more. In one example, for a target vehicle, the total number of obstacles within the designated range of the target vehicle is one; that is, only the first obstacle exists within the designated range of the target vehicle.

[0106] In this example, generating a policy decision command based on the first optimal driving information and the evaluation results corresponding to the first optimal driving information may include generating a policy decision command based on the optimal driving parameters at multiple predicted times in the first time length of the first obstacle included in the first optimal driving information, the optimal motion parameters at multiple predicted times in the first time length of the target vehicle, and the evaluation results corresponding to the first optimal driving information.

[0107] The process of generating a policy decision command based on the optimal motion parameters at multiple predicted times for the first time duration of the first obstacle included in the first optimal driving information, the optimal motion parameters at multiple predicted times for the first time duration of the target vehicle, and the evaluation results corresponding to the first optimal driving information, can be performed based on a pre-set strategy or by a policy decision model, and is not limited to this in this embodiment.

[0108] For example, generating a policy decision command based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length includes: determining whether a merging area exists between the target vehicle and the first obstacle based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length; if it is determined that a merging area exists, determining whether the predicted action of the target vehicle is to overtake or yield based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information; and if the predicted action of the target vehicle is to overtake, determining whether the safety evaluation value between the target vehicle and the first obstacle exceeds a safety threshold based on the evaluation result corresponding to the first optimal driving information, and if it exceeds a safety threshold, generating a policy decision command to control the target vehicle to perform an overtaking process. Here, a safety evaluation value exceeding the safety threshold indicates that the risk of collision between the target vehicle and the first obstacle is low, meaning that the target vehicle can safely pass through the merging area.

[0109] For example, the policy decision command may include a command to control the target vehicle to perform an overtaking operation over a first obstacle, a speed planning result for each of the multiple predicted times in the target vehicle's first time period, and a route planning result for the target vehicle's first time period; or the policy decision command may include only the speed planning result for each of the multiple predicted times in the target vehicle's first time period and the route planning result for the target vehicle's first time period, in order for the target vehicle to achieve overtaking by executing this policy decision command.

[0110] For example, generating a policy decision command based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length includes: determining whether a merging area exists between the target vehicle and the first obstacle based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length; if it is determined that a merging area exists, determining whether the predicted action of the target vehicle is overtaking or yielding based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information; and if the predicted action of the target vehicle is overtaking, determining whether the safety evaluation value between the target vehicle and the first obstacle exceeds a safety threshold based on the evaluation result corresponding to the first optimal driving information, and if it does not, generating a policy decision command to control the target vehicle to execute a yielding process. Here, if the safety assessment value does not exceed the safety threshold, it can indicate a high risk of collision between the target vehicle and the first obstacle, that is, it can indicate that the target vehicle may not be able to safely pass through the merging area based on the predicted motion parameters.

[0111] For example, the policy decision command may include a command to control the target vehicle to perform the action of yielding its lane to a first obstacle, a speed planning result for each of the multiple predicted times in the first time period of the target vehicle, and a path planning result for the target vehicle in the first time period, or the policy decision command may include only the speed planning result for each of the multiple predicted times in the first time period of the target vehicle, and the path planning result for the target vehicle in the first time period, in order to realize that the target vehicle yields its lane by executing this policy decision command.

[0112] For example, generating a policy decision command based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length includes: determining whether a merging area exists between the target vehicle and the first obstacle based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length; if it is determined that a merging area exists, determining that the predicted action of the target vehicle is overtaking or yielding based on the optimal motion parameters of a first obstacle at multiple predicted times in the first time length included in the first optimal driving information; and if the predicted action of the target vehicle is yielding, determining whether the safety evaluation value between the target vehicle and the first obstacle exceeds a safety threshold based on the evaluation result corresponding to the first optimal driving information, and if it exceeds a safety threshold, generating a policy decision command to control the target vehicle to execute a yielding process.

[0113] It should be noted that the above is merely an illustrative explanation, and in actual processing, the above processing can also be carried out using other policy decision commands or pre-trained policy decision models. Therefore, specific methods for generating policy decision commands will not be listed here in an exclusive or exhaustive manner. In one example, for a target vehicle, the total number of obstacles within the designated range of the target vehicle may be multiple; that is, there are multiple obstacles within the designated range of the target vehicle, and the first obstacle is one of these multiple obstacles. In this example, generating a policy decision command based on the first optimal driving information and the evaluation results corresponding to the first optimal driving information may include generating a policy decision command based on the optimal motion parameters at multiple predicted times in the first time length of the obstacle included in each of the multiple optimal driving information, the optimal motion parameters at multiple predicted times in the first time length of the target vehicle included in each of the multiple optimal driving information, and the evaluation results corresponding to each of the multiple optimal driving information, where the multiple optimal driving information includes the first optimal driving information, and different optimal driving trajectories can correspond to different obstacles.

[0114] If the total number of obstacles within the designated range of the target vehicle is three, then these three obstacles include a first obstacle, a second obstacle, and a third obstacle. By processing the target vehicle and the first obstacle using the method of the embodiment described above, first optimal driving information can be obtained, which will not be repeated here. Similarly, by processing the target vehicle and the second obstacle using the embodiment described above, second optimal driving information can be obtained, and this second optimal driving information may include the optimal motion parameters of the second obstacle at multiple predicted times in the first time length, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length. Similarly, by processing the target vehicle and the third obstacle using the embodiment described above, third optimal driving information can be obtained, and this third optimal driving information may include the optimal motion parameters of the third obstacle at multiple predicted times in the first time length, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length.

[0115] All three of the optimal driving information sets described above include optimal driving parameters for multiple predicted times within the first time duration of the target vehicle. However, the optimal driving parameters for multiple predicted times within the first time duration of the target vehicle included in the three optimal driving information sets may be the same or different. This is because the above processing was performed for each of the target vehicle and its corresponding obstacles to generate the optimal driving information for each of the target vehicle and its corresponding obstacles. Therefore, it is necessary to perform further analysis in conjunction with the contents of each optimal driving information set to generate a policy decision command.

[0116] For example, generating a policy decision command based on the optimal motion parameters of obstacles at multiple predicted time points in the first time length included in each of the multiple optimal driving information, the optimal motion parameters of the target vehicle at multiple predicted time points in the first time length included in each of the multiple optimal driving information, and the evaluation results corresponding to each of the multiple optimal driving information means determining the optimal predicted position of each obstacle at each predicted time point based on the optimal motion parameters of obstacles at multiple predicted time points in the first time length included in each of the multiple optimal driving information, and projecting the optimal predicted position of each obstacle at each predicted time point perpendicularly onto the path of the target vehicle at the first time length, and each This may include obtaining one or more projection points on the path of the target vehicle at a first time length corresponding to each obstacle; determining a predicted inflow time when each obstacle enters the path of the target vehicle based on the one or more projection points on the path of the target vehicle at a first time length corresponding to each obstacle; calculating the time difference between the predicted inflow time when each obstacle enters the path of the target vehicle and the current time; and generating a policy decision command based on the corresponding time difference for each obstacle, the optimal motion parameters at multiple predicted times in the first time length of the target vehicle included in each of the optimal driving information, and the evaluation results corresponding to each of the optimal driving information.

[0117] Here, determining the predicted inflow time at which each obstacle enters the target vehicle's path based on one or more projection points on the path of the target vehicle in the first time length corresponding to each obstacle may include determining the corresponding predicted time for each of the one or more projection points on the path of the target vehicle in the first time length corresponding to each obstacle, and setting the earliest predicted time among the corresponding predicted times for each of the projection points on the path of the target vehicle in the first time length corresponding to each obstacle as the predicted inflow time at which each obstacle enters the target vehicle's path.

[0118] Selectively, generating a policy decision command based on the corresponding time difference of each obstacle, the optimal motion parameters of the target vehicle at multiple predicted times in the first time length included in each of the optimal driving information, and the evaluation results corresponding to each of the optimal driving information includes: determining target optimal driving information including the target obstacle if there is a target obstacle whose time difference is less than the time difference threshold among multiple obstacles; determining the yield / overtaking relationship between the target obstacle and the target vehicle based on the evaluation results corresponding to the target optimal driving information, the optimal motion parameters of the target obstacle at multiple predicted times in the first time length included in the target optimal driving information, and the optimal motion parameters of the target vehicle at multiple predicted times in the first time length; and generating a policy decision command based on the yield / overtaking relationship between the target obstacle and the target vehicle, and the optimal motion parameters of the other obstacles excluding the target obstacle at multiple predicted times in the corresponding first time length.

[0119] For example, generating a policy decision command based on the yielding / overtaking relationship between the target obstacle and the target vehicle, and the optimal motion parameters at multiple predicted times in the corresponding first time length for other obstacles excluding the target obstacle, may include: if the yielding / overtaking relationship between the target obstacle and the target vehicle results in the target vehicle overtaking the target obstacle, adjusting the optimal motion parameters at one or more times to be adjusted from the predicted entry time onward among the multiple predicted times in the first time length of the target obstacle to obtain adjusted driving information for the target obstacle; and generating a policy decision command based on the adjusted driving information for the target obstacle and the optimal motion parameters at multiple predicted times in the corresponding first time length for other obstacles excluding the target obstacle.

[0120] Adjusting the optimal motion parameters at one or more adjustment times after the predicted inflow time, among multiple predicted times in the first time length of the target obstacle, and obtaining adjusted running information for the target obstacle, includes: setting the predicted inflow time and each subsequent predicted time in the first time length of the target obstacle as adjustment times, delaying each adjustment time by the first time length, obtaining the corresponding adjusted time for each adjustment time, setting the optimal motion parameters at each adjustment time as the optimal motion parameters at the corresponding adjusted time for each adjustment time, and setting the optimal motion parameters at each adjusted time in the first time length of the target obstacle as the adjusted running information for the target obstacle. Here, the first time length may be greater than or equal to the time difference threshold. If the adjusted time exceeds the first time length range, the adjusted time can be deleted.

[0121] Generating a policy decision command based on the adjusted driving information of the target obstacle and the optimal motion parameters at multiple predicted times in the corresponding first time length for other obstacles excluding the target obstacle may include determining the yield / overtaking relationship between the target vehicle and other obstacles based on the corresponding optimal motion parameters at multiple predicted times in the corresponding first time length for other obstacles excluding the target obstacle, and generating a policy decision command based on the adjusted driving information of the target obstacle and the yield / overtaking relationship between the target vehicle and other obstacles. The specific processing form for generating a policy decision command based on the adjusted driving information of the target obstacle and the yield / overtaking relationship between the target vehicle and other obstacles is not limited to the examples in this implementation. For example, this policy decision command may include commands to control the target vehicle to perform the process of overtaking a target obstacle, commands to control the target vehicle to perform the process of yielding a lane to each other obstacle or overtaking each other obstacle, speed planning results at each of the multiple predicted times in the first time length of the target vehicle, and route planning results in the first time length of the target vehicle, or this policy decision command may include only speed planning results at each of the multiple predicted times in the first time length of the target vehicle, and route planning results in the first time length of the target vehicle, so that the target vehicle performs the process of overtaking a target obstacle, yielding a lane to each other obstacle or overtaking each other obstacle by executing this policy decision command.

[0122] For example, generating a policy decision command based on the yielding / overtaking relationship between the target obstacle and the target vehicle, and the optimal motion parameters under multiple predicted times in the corresponding first time length for each of the other obstacles excluding the target obstacle, may include generating a policy decision command based on the optimal motion parameters under multiple predicted times in the corresponding first time length for the target obstacle, and the optimal motion parameters under multiple predicted times in the corresponding first time length for each of the other obstacles excluding the target obstacle, when the yielding / overtaking relationship between the target obstacle and the target vehicle is such that the target vehicle yields its lane to the target obstacle. In this case, this embodiment does not limit the specific processing form for generating a policy decision command based on the optimal motion parameters under multiple predicted times in the corresponding first time length for the target obstacle and the optimal motion parameters under multiple predicted times in the corresponding first time length for each of the other obstacles excluding the target obstacle. For example, this policy decision command may include commands to control the target vehicle to perform the action of yielding a lane to a target obstacle, commands to control the target vehicle to perform the action of yielding a lane to or overtaking each other obstacle, speed planning results for each of the multiple predicted times in the first time period of the target vehicle, and route planning results for the first time period of the target vehicle. Alternatively, this policy decision command may include only the speed planning results for each of the multiple predicted times in the first time period of the target vehicle, and route planning results for the first time period of the target vehicle, in order for the target vehicle to perform the action of yielding a lane to a target obstacle, yielding a lane to or overtaking each other obstacle by executing this policy decision command.

[0123] Selectively, generating a policy decision command based on the corresponding time difference of each obstacle, the optimal motion parameters at multiple predicted times in the first time length of the target vehicle included in each of the optimal driving information, and the evaluation results corresponding to each of the optimal driving information includes, if there are no target obstacles whose time difference is less than the time difference threshold among the multiple obstacles, determining the yield / overtaking relationship between each obstacle and the target vehicle based on the evaluation results corresponding to each of the optimal driving information, the optimal motion parameters at multiple predicted times in the first time length of the obstacles included in each of the optimal driving information, and the optimal motion parameters at multiple predicted times in the first time length of the target vehicle, and generating a policy decision command based on the yield / overtaking relationship between each obstacle and the target vehicle. For example, this policy decision command may include commands to control the target vehicle to perform lane-yielding or overtaking operations for different obstacles at each obstacle, speed planning results for each of multiple predicted times in the target vehicle's first time interval, and route planning results for the target vehicle's first time interval. Alternatively, this policy decision command may include only speed planning results for each of multiple predicted times in the target vehicle's first time interval and route planning results for the target vehicle's first time interval, in order for the target vehicle to perform lane-yielding or overtaking operations for different obstacles at each obstacle by executing this policy decision command.

[0124] It should be noted that the above is merely an illustrative explanation, and in actual processing, a policy decision command can be obtained by processing based on a pre-defined strategy or policy decision model, and such a command is not listed here in an exhaustive or exhaustive manner.

[0125] Referring to Figure 4, the process of determining the policy decision command will be explained exemplified. First, the planning system 402 acquires input information 401 which may include evaluation information (i.e., evaluation results corresponding to the first optimal driving information) and optimal strategy decision trajectory reference information (i.e., the first optimal driving information). Next, the planning system processes the input information 401 to finally obtain a policy decision command that can include a speed planning result 4021 and a route planning result 4022. In order to achieve efficient transfer of evaluation and policy decision information, it may be understood that the interface between the policy decision module and the planning system in the electronic device needs to be opened so as to ensure that the planning system can implement yielding and overtaking in accordance with the commands of the policy decision module. For example, if overtaking is decided, the overtaking cost (price) of the planning system can be reduced to ensure that the lower logic plans the overtaking trajectory as much as possible, and if yielding is decided, the public interface can be used to increase the corresponding deceleration cost (price) and avoid accelerating the vehicle.

[0126] Finally, the driver of the target vehicle can also intervene in the pre-planning system 402 via the driver input processing system 403. For example, if the driver decides to overtake and acceleration is delayed, the driver can perform accelerator intervention 4031, such as lightly pressing the accelerator pedal to assist in increasing the vehicle's speed. If steering is delayed, the driver can perform steering intervention 4032, such as adjusting the target vehicle's direction of travel. This ensures both driving safety and efficiency while also providing a positive driving experience for the user.

[0127] By adopting the above method, decisions can be generated and executed to control the target vehicle to yield or overtake, in conjunction with the currently determined optimal driving information and its corresponding evaluation results. Since the optimal driving information is selected by evaluating it in conjunction with the predicted behavior of multiple traffic participants, the accuracy of the final generated policy decision command can be guaranteed, and furthermore, the safety of the target vehicle carrying out appropriate actions based on the policy decision command can be guaranteed.

[0128] Referring to Figures 5 and 6, the driving information prediction method provided by the embodiment of the present application will be described exemplarily. In S510, interaction environment analysis and upstream signal extraction are performed. Specifically, as shown in Figure 5, the system can determine the motion parameters of the target vehicle at the current time in combination with high-resolution data and positioning information 511, determine the route information of the target vehicle at a first time interval based on pre-planning system information 512, and obtain the driving type 513 of the target vehicle at a first time interval based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at a first time interval. Using sensing and prediction information 514, the system can determine the motion parameters of the first obstacle at the current time and the predicted route information of the first obstacle at a future first time interval, and obtain the driving type 515 of the first obstacle at a first time interval based on the motion parameters of the first obstacle at the current time and the predicted route information of the first obstacle at a first time interval. This allows for a preliminary understanding of the intentions and potential risks of the target vehicle and the first obstacle. By integrating this information, the system can construct a relatively comprehensive environmental model, providing a solid foundation for subsequent yielding / overtaking interaction simulations, collision risk assessments, and trajectory rationality evaluations.

[0129] Referring to Figure 6, which schematically illustrates several possible merging scenarios between traffic participants, in which vehicle A represents the first obstacle and vehicle B represents the target vehicle, the arrows for each vehicle represent the direction of travel, and the dashed lines extending from the arrows can represent the travel path or predicted position at the first time length. In scenario 601 of Figure 6, vehicle B may travel straight and vehicle A may turn left. In scenario 602 of Figure 6, vehicle B may turn right and vehicle A may travel straight. In scenario 603 of Figure 6, vehicle B may turn left and vehicle A may turn right. In scenario 604 of Figure 6, vehicle B may travel straight and vehicle A may change lanes.

[0130] In S520, the integration of right-of-way information and the establishment of master-slave relationships are performed. Specifically, as shown in Figure 5, this may include obtaining a right-of-way priority 522 for the target vehicle and the first obstacle based on the target vehicle's driving type 513 at the first time duration, the first obstacle's driving type 515 at the first time duration, and the traffic flow strategy 521 (where the traffic flow strategy is the traffic flow type of the first obstacle). In S530, we perform interaction simulations involving yielding and overtaking, as well as secondary competition reasoning.

[0131] Specifically, as shown in Figure 5, the first master-slave relationship is obtained by determining the master-slave relationship 531 based on the priority 522 of the right of passage between the target vehicle and the first obstacle, Based on the first master-slave relationship, a forward simulation 532 is performed to obtain first predicted driving information, for example, the possible collision risk and trajectory change are predicted by the forward simulation, and the first predicted driving information, which is the optimal driving trajectory, is determined by iterative calculation. The system evaluates the first predicted driving information and performs a secondary competition 533. For example, it obtains the evaluation result of the first predicted driving information through the evaluation of the first predicted driving information, and based on the evaluation result, it determines whether it is necessary to exchange master-slave relationships and perform a secondary competition. Finally, it obtains the first optimal driving information, thereby improving the evaluation stability and decision reliability of the vehicle in uncertain environments.

[0132] Taking scenario 601 shown in Figure 6 as an example, although vehicle B has a higher right-of-way priority than vehicle A, when combined with the initial predicted motion parameters of vehicle A and vehicle B, it is found that vehicle A will reach the predicted merging point (i.e., the intersection of the travel paths of vehicle A and vehicle B in the first time length in 601 of Figure 6) earlier than vehicle B, and in the ultimately determined first master-slave relationship, vehicle A is in a dominant position and vehicle B is in a subordinate position. The illustrative explanations of the other scenarios in Figure 6 are the same as for scenario 601 and will not be repeated here.

[0133] In S540, the evaluation results are output and a policy decision command is issued. Specifically, as shown in Figure 5, planning is performed based on the first optimal driving information obtained in the evaluation and secondary competition 533 and the corresponding evaluation results 541, to obtain route planning results and speed planning results 542. In this process, the driver can also input intervention information 543, such as accelerator intervention or steering intervention, to the route planning results and speed planning results. In this process, it can be understood that the information transmitted is not merely yielding / overtaking results and collision probability, but also signals that the planning system can understand and utilize. To achieve this goal, the policy decision and evaluation systems must be well-adapted to the planning module, and information transmission must utilize a dedicated interface and follow a specific format and protocol. This ensures data integrity and timeliness, and ultimately guarantees efficient cooperation between the policy decision and planning systems.

[0134] Figure 7 shows a schematic block diagram of a driving information prediction device provided by one embodiment of the present disclosure. As shown in Figure 7, the device is A master-slave relationship determination module 701 for determining a first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle at a first time interval. A driving information prediction module 702 for obtaining first predicted driving information based on the first master-slave relationship, wherein the first predicted driving information includes first predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and second predicted motion parameters at multiple predicted times in a first time length of the first obstacle, An optimal driving information determination module 703 for determining first optimal driving information based on evaluation results corresponding to the first predicted driving information, wherein the first optimal driving information includes optimal predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and optimal predicted motion parameters at multiple predicted times in a first time length of the first obstacle.

[0135] The driving information prediction module is used to perform one of the following actions: if the evaluation result corresponding to the first predicted driving information satisfies the first condition, set the first predicted driving information as the first optimal driving information; if the evaluation result corresponding to the first predicted driving information does not satisfy the first condition, switch the first master-slave relationship to obtain a second master-slave relationship between the target vehicle and the first obstacle, obtain second predicted driving information based on the second master-slave relationship, and determine the first optimal driving information from the first predicted driving information and the second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information.

[0136] The first condition includes at least one of the following: the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold; and the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the subjective evaluation threshold. The optimal driving information determination module is used to reverse the first master-slave relationship and obtain a second master-slave relationship between the target vehicle and the first obstacle, to obtain second predicted driving information based on the second master-slave relationship, and to determine the first optimal driving information from the first predicted driving information and the second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information. The second predicted driving information includes a third predicted motion parameter for multiple predicted time points in the first time length of the target vehicle, and a fourth predicted motion parameter for multiple predicted time points in the first time length of the first obstacle.

[0137] As shown in Figure 8, the apparatus further comprises a safety evaluation module 801. The safety evaluation module is used to perform at least one of the following: calculating a first safety evaluation value in the evaluation result corresponding to the first predicted driving information based on a safety evaluation formula, the first master-slave relationship, and the first predicted driving information; calculating a first subjective evaluation value in the evaluation result corresponding to the first predicted driving information based on a subjective evaluation formula, the first master-slave relationship, and the first predicted driving information; calculating a second safety evaluation value in the evaluation result corresponding to the second predicted driving information based on a safety evaluation formula, the second master-slave relationship, and the second predicted driving information; and calculating a second subjective evaluation value in the evaluation result corresponding to the second predicted driving information based on a subjective evaluation formula, the second master-slave relationship, and the second predicted driving information.

[0138] The optimal driving information determination module is used to determine a first reference value corresponding to the first predicted driving information based on an evaluation result corresponding to the first predicted driving information, to determine a second reference value corresponding to the second predicted driving information based on an evaluation result corresponding to the second predicted driving information, and to select the first optimal driving information from the first and second predicted driving information based on the maximum value among the first and second reference values.

[0139] The aforementioned driving information prediction module is used to perform a forward simulation based on the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, in order to obtain first predicted motion parameters for the target vehicle at multiple predicted times in a first time length, and second predicted motion parameters for the first obstacle at multiple predicted times in a first time length, and to use the first predicted motion parameters for the target vehicle at multiple predicted times in a first time length, and the second predicted motion parameters for the first obstacle at multiple predicted times in a first time length as the first predicted driving information.

[0140] The aforementioned driving information prediction module is used to perform a forward simulation based on the second master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, in order to obtain a third predicted motion parameter for the target vehicle at multiple predicted times in the first time length, and a fourth predicted motion parameter for the first obstacle at multiple predicted times in the first time length, and to use the third predicted motion parameter for the target vehicle at multiple predicted times in the first time length, and the fourth predicted motion parameter for the first obstacle at multiple predicted times in the first time length as the second predicted driving information.

[0141] The master-slave relationship determination module is used to determine the priority of the right of way for the target vehicle and the first obstacle over a first time period, based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle over a first time period, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle over a first time period, and to determine the first master-slave relationship between the target vehicle and the first obstacle based on the priority of the right of way for the target vehicle and the first obstacle over a first time period.

[0142] The master-slave relationship determination module is used to obtain the driving type of the target vehicle at a first time interval based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at a first time interval; to obtain the driving type of the first obstacle at a first time interval based on the motion parameters of the first obstacle at the current time and the predicted route information of the first obstacle at a first time interval; and to obtain the right of way priority of the target vehicle and the first obstacle at a first time interval based on the driving type of the target vehicle and the driving type of the first obstacle at a first time interval.

[0143] The master-slave relationship determination module is used to determine a predicted merging area based on initial predicted motion parameters at multiple predicted times in a first time period for the target vehicle and initial predicted motion parameters at multiple predicted times in a first time period for the first obstacle, and to determine the first master-slave relationship between the target vehicle and the first obstacle based on the right-of-way priority of the target vehicle and the first obstacle in a first time period, the predicted merging area, and reference information, wherein the reference information includes at least one of the driving type of the target vehicle, the driving type of the first obstacle, motion parameters of the target vehicle at the current time, motion parameters of the first obstacle at the current time, initial predicted motion parameters at multiple predicted times in a first time period for the target vehicle, and initial predicted motion parameters at multiple predicted times in a first time period for the first obstacle.

[0144] As shown in Figure 9, the apparatus further includes a policy decision command generation module 901. The policy decision command generation module is used to generate policy decision commands for controlling the target vehicle to perform yielding or overtaking processing, based on the first optimal driving information and the evaluation results corresponding to the first optimal driving information. The specific functions and illustrative descriptions of each module and submodule of the apparatus according to the embodiments of this disclosure can be found in the relevant descriptions of the corresponding steps in the embodiments of the method described above, and will not be repeated here. The technical solutions disclosed herein ensure that the acquisition, storage, and application of users' personal information comply with applicable laws and regulations and do not violate public order or morality. According to embodiments of the present disclosure, the present disclosure further provides electronic devices, non-temporary computer-readable storage media, and program products.

[0145] Figure 10 shows a schematic block diagram showing how an electronic device 1000 according to an embodiment of the present disclosure can be implemented. An electronic device refers to any form of digital computer, such as a laptop computer, desktop computer, workstation, personal digital assistant, server, blade server, mainframe computer, and other suitable computers. An electronic device further refers to any form of mobile device, such as a personal digital assistant, cellular phone, intelligent phone, wearable device, and other similar computer equipment. The components, their connections, and functions described in this disclosure are illustrative and do not limit the implementation of anything described or specified in this disclosure.

[0146] As shown in Figure 10, device 1000 includes a computing unit 1001 capable of performing various appropriate operations and processes based on computer program instructions stored in read-only memory (ROM) 1002, or computer program instructions loaded from storage unit 1008 into random access memory (RAM) 1003. RAM 1003 can further store various programs and data necessary for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are connected to each other via bus 1004. An input / output (I / O) interface 1005 is also connected to bus 1004.

[0147] Multiple components in device 1000 are connected to an I / O interface 1005, which includes an input unit 1006 such as a keyboard and mouse, an output unit 1007 such as various displays and speakers, a storage unit 1008 such as a magnetic disk or optical disk, and a communication unit 1009 such as a network card, modem, or wireless communication transceiver. The communication unit 1009 allows device 1000 to exchange information / data with other devices via computer networks such as the Internet and / or various carrier networks.

[0148] The computing unit 1001 may be a variety of general-purpose and / or dedicated processing components having processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, a computing unit that executes various machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs each of the methods described above, for example, the driving information prediction method. For example, in some embodiments, the driving information prediction method can be implemented as a computer software program tangibly contained in a machine-readable medium such as a memory unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed into device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the driving information prediction method described above can be performed. In addition, in other embodiments, the computing unit 1001 may be configured to perform the driving information prediction method by any other suitable method (e.g., firmware).

[0149] Various embodiments of the systems or technologies described in this disclosure can be implemented by digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standards (ASSPs), systems-on-a-chip (SOCs), complex-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. Each of these embodiments may be implemented by one or more computer programs that run and / or interpret 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 transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0150] Program code for performing the methods of this disclosure can be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programming data processing device, so that when the program code is executed by the processor or controller, it can perform the functions / operations defined in the flowcharts and / or block diagrams. The program code may run entirely in a mainscan, partially in a mainscan, partially as an independent soft encapsulation and partially in a remote mainscan, or entirely in a remote mainscan or server.

[0151] In this disclosure, machine-readable media may be tangible media containing or storing programs used by or in conjunction with instruction execution systems, devices, or equipment. Machine-readable media may be machine-readable signal media or machine-readable storage media. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any suitable combination of the contents described above. Further specific examples of machine-readable storage media include one or more wired electrical connections, portable computer disk cartridges, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any combination of the contents described above.

[0152] To provide user interaction, a computer may implement the systems and technologies described herein, which may include an annotation device for annotating information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor), a keyboard and pointing device for the user to provide input to the computer (e.g., a mouse or trackball). Other types of devices may also be used to provide user interaction; for example, the feedback provided to the user may be any form of sensor feedback (e.g., visual feedback, auditory feedback, or haptic feedback), and input from the user may be accepted in any form (e.g., acoustic input, voice input, haptic input).

[0153] The systems and technologies described herein can be implemented in computing systems that include background components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include front-end components (e.g., user computers having a graphics user interface or network browser, through which users can interact with embodiments of the systems and technologies described herein), or in any combination of such background components, middleware components, or front-end components. Components of the system can be connected to one another via digital data communication in any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0154] A computer system can include a client and a server. Typically, the client and server are geographically separated and interact via a communication network. The client-server relationship is created by a computer program that operates on the corresponding computer. The server may be a cloud server, a server in a distributed system, or a server incorporating blockchain technology, etc.

[0155] It should be understood that steps can be newly ranked, added, or deleted using the various forms of flows shown above. For example, each step described in this disclosure may be executed in parallel, sequentially, or in a different order. This disclosure is not limited to this, as long as the technical solutions disclosed herein can achieve the desired results.

[0156] 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, subcombinations, and substitutions are possible due to design considerations and other factors. Any changes, equivalent substitutions, and improvements within the gist and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for predicting driving information, Based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle at a first time interval, a first master-slave relationship is determined between the target vehicle and the first obstacle. Based on the first master-slave relationship, a first predicted driving information is obtained, wherein the first predicted driving information includes a first predicted motion parameter at multiple predicted time points in a first time length for the target vehicle, and a second predicted motion parameter at multiple predicted time points in a first time length for the first obstacle. The method includes determining first optimal driving information based on evaluation results corresponding to the first predicted driving information, wherein the first optimal driving information includes optimal predicted motion parameters at multiple predicted times in a first time length for the target vehicle, and optimal predicted motion parameters at multiple predicted times in a first time length for the first obstacle. Method for predicting driving information.

2. Determining the first optimal driving information based on the evaluation results corresponding to the first predicted driving information is: If the evaluation result corresponding to the first predicted driving information satisfies the first condition, the first predicted driving information is designated as the first optimal driving information. If the evaluation result corresponding to the first predicted driving information does not satisfy the first condition, the first master-slave relationship is reversed to obtain a second master-slave relationship between the target vehicle and the first obstacle, second predicted driving information is obtained based on the second master-slave relationship, and first optimal driving information is determined from the first predicted driving information and the second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information. The method for predicting driving information according to claim 1.

3. The first condition includes at least one of the following: the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold; and the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the subjective evaluation threshold. The method for predicting driving information according to claim 2.

4. Determining the first optimal driving information based on the evaluation results corresponding to the first predicted driving information is: The first master-slave relationship is reversed to obtain a second master-slave relationship between the target vehicle and the first obstacle. Based on the aforementioned second master-slave relationship, second predictive driving information is obtained, This includes determining the first optimal driving information from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information, The method for predicting driving information according to claim 1.

5. The second predicted driving information includes a third predicted motion parameter at multiple predicted time points in the first time length of the target vehicle, and a fourth predicted motion parameter at multiple predicted time points in the first time length of the first obstacle. The method for predicting driving information according to claim 2.

6. The aforementioned driving information prediction method further includes: Based on the safety evaluation formula, the first master-slave relationship, and the first predicted driving information, calculate the first safety evaluation value in the evaluation result corresponding to the first predicted driving information. Based on the subjective evaluation formula, the first master-slave relationship, and the first predicted driving information, calculate the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information. Based on the safety evaluation formula, the second master-slave relationship, and the second predicted driving information, calculate the second safety evaluation value in the evaluation result corresponding to the second predicted driving information. This includes at least one of the following: calculating a second subjective evaluation value in the evaluation result corresponding to the second predicted driving information based on the subjective evaluation formula, the second master-slave relationship, and the second predicted driving information. The method for predicting driving information according to claim 2.

7. Determining the first optimal driving information from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information is: Based on the evaluation results corresponding to the first predicted driving information, a first reference value corresponding to the first predicted driving information is determined, Based on the evaluation results corresponding to the second predicted driving information, a second reference value corresponding to the second predicted driving information is determined, This includes selecting the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value of the first and second reference values, The method for predicting driving information according to claim 2.

8. Based on the aforementioned first master-slave relationship, obtaining the first predicted driving information is: Based on the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, a forward simulation is performed to obtain the first predicted motion parameters of the target vehicle at multiple predicted times over a first time period, and the second predicted motion parameters of the first obstacle at the multiple predicted times over a first time period. The first predicted driving information includes first predicted motion parameters of the target vehicle at multiple predicted time points over the first time period, and second predicted motion parameters of the first obstacle at multiple predicted time points over the first time period. The method for predicting driving information according to claim 1.

9. Based on the aforementioned second master-slave relationship, obtaining second predictive driving information is possible. Based on the second master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, a forward simulation is performed to obtain the third predicted motion parameters of the target vehicle at multiple predicted times in the first time length, and the fourth predicted motion parameters of the first obstacle at multiple predicted times in the first time length. The second predicted driving information includes: a third predicted motion parameter for the target vehicle at multiple predicted time points in the first time length, and a fourth predicted motion parameter for the first obstacle at multiple predicted time points in the first time length. The method for predicting driving information according to claim 2.

10. Determining a first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle at a first time interval is: Based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle at the first time interval, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle at the first time interval, the priority of the right of passage for the target vehicle and the first obstacle at the first time interval is determined. This includes determining a first hierarchical relationship between the target vehicle and the first obstacle based on the priority of the right of way during a first time period between the target vehicle and the first obstacle, The method for predicting driving information according to claim 1.

11. Determining the priority of the right of way for the target vehicle and the first obstacle during the first time period based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle at the first time period, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle at the first time period is: Based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at the first time interval, the driving type of the target vehicle at the first time interval is obtained. Based on the motion parameters of the first obstacle at the current time and the predicted path information of the first obstacle at the first time length, the type of movement of the first obstacle at the first time length is obtained. This includes obtaining priority for the right of way for the target vehicle and the first obstacle during the first time period, based on the type of travel of the target vehicle during the first time period and the type of travel of the first obstacle during the first time period. The method for predicting driving information according to claim 10.

12. Determining the first hierarchical relationship between the target vehicle and the first obstacle based on the priority of the right of way during the first time period between the target vehicle and the first obstacle is: The predicted confluence region is determined based on the initial predicted motion parameters at multiple predicted time points during the first time length of the target vehicle, and the initial predicted motion parameters at multiple predicted time points during the first time length of the first obstacle. The first master-slave relationship between the target vehicle and the first obstacle is determined based on the priority of right of way between the target vehicle and the first obstacle at a first time interval, the predicted merging area, and reference information, wherein the reference information includes at least one of the following: the driving type of the target vehicle, the driving type of the first obstacle, the motion parameters of the target vehicle at the current time, the motion parameters of the first obstacle at the current time, the initial predicted motion parameters of the target vehicle at multiple predicted times at a first time interval, and the initial predicted motion parameters of the first obstacle at multiple predicted times at a first time interval. The method for predicting driving information according to claim 10.

13. After determining the first optimal driving information based on the evaluation results corresponding to the first predicted driving information, the driving information prediction method further: This includes generating a policy decision command for controlling the target vehicle to perform a yielding process or an overtaking process based on the first optimal driving information and the evaluation results corresponding to the first optimal driving information, The method for predicting driving information according to claim 1.

14. A driving information prediction device, A master-slave relationship determination module for determining a first master-slave relationship between the target vehicle and the first obstacle based on the motion parameters of the target vehicle at the current time, the path information of the target vehicle at a first time interval, the motion parameters of the first obstacle at the current time, and the predicted path information of the first obstacle at a first time interval. A driving information prediction module for obtaining first predicted driving information based on the first master-slave relationship, wherein the first predicted driving information includes first predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and second predicted motion parameters at multiple predicted times in a first time length of the first obstacle, An optimal driving information determination module for determining first optimal driving information based on evaluation results corresponding to the first predicted driving information, wherein the first optimal driving information includes optimal predicted motion parameters at multiple predicted times in a first time length of the target vehicle, and optimal predicted motion parameters at multiple predicted times in a first time length of the first obstacle. Driving information prediction device.

15. The aforementioned driving information prediction module is If the evaluation result corresponding to the first predicted driving information satisfies the first condition, the first predicted driving information is designated as the first optimal driving information. If the evaluation result corresponding to the first predicted driving information does not satisfy the first condition, the system is used to perform one of the following: alternating the first master-slave relationship to obtain a second master-slave relationship between the target vehicle and the first obstacle; obtaining second predicted driving information based on the second master-slave relationship; and determining the first optimal driving information from the first and second predicted driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information. A driving information prediction device according to claim 14.

16. The first condition includes at least one of the following: the first safety evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the safety threshold; and the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information exceeds the subjective evaluation threshold. The driving information prediction device according to claim 15.

17. The aforementioned optimal driving information determination module is: The first master-slave relationship is reversed to obtain a second master-slave relationship between the target vehicle and the first obstacle. Based on the aforementioned second master-slave relationship, second predictive driving information is obtained, The first optimal driving information is determined from the first and second predicted driving information based on the evaluation results corresponding to the second predicted driving information and the evaluation results corresponding to the first predicted driving information, and is used for this purpose. A driving information prediction device according to claim 14.

18. The second predicted driving information includes a third predicted motion parameter at multiple predicted time points in the first time length of the target vehicle, and a fourth predicted motion parameter at multiple predicted time points in the first time length of the first obstacle. A driving information prediction device according to any one of claims 15 to 17.

19. The aforementioned driving information prediction device further, Based on the safety evaluation formula, the first master-slave relationship, and the first predicted driving information, calculate the first safety evaluation value in the evaluation result corresponding to the first predicted driving information. Based on the subjective evaluation formula, the first master-slave relationship, and the first predicted driving information, calculate the first subjective evaluation value in the evaluation result corresponding to the first predicted driving information. Based on the safety evaluation formula, the second master-slave relationship, and the second predicted driving information, calculate the second safety evaluation value in the evaluation result corresponding to the second predicted driving information. The safety evaluation module includes a function for performing at least one of the following: calculating a second subjective evaluation value in the evaluation result corresponding to the second predictive driving information, based on the subjective evaluation formula, the second master-slave relationship, and the second predictive driving information. A driving information prediction device according to any one of claims 15 to 17.

20. The aforementioned optimal driving information determination module is: Based on the evaluation results corresponding to the first predicted driving information, a first reference value corresponding to the first predicted driving information is determined, Based on the evaluation results corresponding to the second predicted driving information, a second reference value corresponding to the second predicted driving information is determined, Used to select the first optimal driving information from the first predicted driving information and the second predicted driving information based on the maximum value of the first reference value and the second reference value, A driving information prediction device according to any one of claims 15 to 17.

21. The aforementioned driving information prediction module is Based on the first master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, a forward simulation is performed to obtain the first predicted motion parameters of the target vehicle at multiple predicted times over a first time period, and the second predicted motion parameters of the first obstacle at the multiple predicted times over a first time period. The first predicted motion parameters of the target vehicle at multiple predicted time points in the first time length, and the second predicted motion parameters of the first obstacle at multiple predicted time points in the first time length are used as the first predicted driving information. A driving information prediction device according to claim 14.

22. The aforementioned driving information prediction module is Based on the second master-slave relationship, the motion parameters of the target vehicle at the current time, and the motion parameters of the first obstacle at the current time, a forward simulation is performed to obtain the third predicted motion parameters of the target vehicle at multiple predicted times in the first time length, and the fourth predicted motion parameters of the first obstacle at multiple predicted times in the first time length. The second predicted driving information is used to define the third predicted motion parameters of the target vehicle at multiple predicted time points in the first time length, and the fourth predicted motion parameters of the first obstacle at multiple predicted time points in the first time length. A driving information prediction device according to any one of claims 15 to 17.

23. The aforementioned master-slave relationship determination module is: Based on the motion parameters of the target vehicle at the current time, the route information of the target vehicle at the first time interval, the motion parameters of the first obstacle at the current time, and the predicted route information of the first obstacle at the first time interval, the priority of the right of passage for the target vehicle and the first obstacle at the first time interval is determined. A first master-slave relationship between the target vehicle and the first obstacle is determined based on the priority of the right of way during the first time period between the target vehicle and the first obstacle, and is used for this purpose. A driving information prediction device according to claim 14.

24. The aforementioned master-slave relationship determination module is: Based on the motion parameters of the target vehicle at the current time and the route information of the target vehicle at the first time interval, the driving type of the target vehicle at the first time interval is obtained. Based on the motion parameters of the first obstacle at the current time and the predicted path information of the first obstacle at the first time length, the type of movement of the first obstacle at the first time length is obtained. A method used to determine the priority of the right of way for the target vehicle and the first obstacle during the first time period, based on the type of travel of the target vehicle during the first time period and the type of travel of the first obstacle during the first time period. The driving information prediction device according to claim 23.

25. The aforementioned master-slave relationship determination module is: The predicted confluence region is determined based on the initial predicted motion parameters at multiple predicted time points during the first time length of the target vehicle, and the initial predicted motion parameters at multiple predicted time points during the first time length of the first obstacle. The first master-slave relationship between the target vehicle and the first obstacle is determined based on the priority of right of way between the target vehicle and the first obstacle at a first time interval, the predicted merging area, and reference information, wherein the reference information includes at least one of the following: the driving type of the target vehicle, the driving type of the first obstacle, the motion parameters of the target vehicle at the current time, the motion parameters of the first obstacle at the current time, the initial predicted motion parameters of the target vehicle at multiple predicted times at a first time interval, and the initial predicted motion parameters of the first obstacle at multiple predicted times at a first time interval. The driving information prediction device according to claim 23.

26. The aforementioned driving information prediction device further, The system includes a policy decision command generation module for generating a policy decision command for controlling the target vehicle to perform a yielding process or an overtaking process based on the first optimal driving information and the evaluation results corresponding to the first optimal driving information. A driving information prediction device according to claim 14.

27. At least one processor, The system comprises at least one processor and a memory that is communicated with by it, The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor performs the method according to any one of claims 1 to 13. Electronic devices.

28. A non-temporary computer-readable storage medium storing computer instructions that cause a computer to perform the method described in any one of claims 1 to 13.

29. A program for implementing the method described in any one of claims 1 to 13, which is executed by a processor in a computer.

30. An autonomous vehicle comprising the electronic device described in claim 27.

Images