Methods, devices, equipment, and media for sharing driving decisions in autonomous vehicles

Abstract

This application discloses a method, apparatus, device, and medium for sharing driving decisions of autonomous vehicles, relating to the field of autonomous driving technology. The specific implementation involves: determining a driving decision for the current driving segment based on the target vehicle's current route, wherein the data format of the driving decision is a preset universal format recognized by the vehicle system; sending the driving decision to a server, whereby the server, based on real-time information of the road segment where the target vehicle is located at the time of determining the driving decision and pre-stored historical driving data, selects a target driving decision for a specific road segment from the received driving decisions and shares the target driving decision. This application embodiment can improve the efficiency of sharing driving decisions between autonomous vehicles and enhance the ability of different autonomous vehicles to navigate the same or similar road scenarios.

Description

[0001] This application is a divisional application of patent application number 201910860739.2 (the original application was filed on September 11, 2019, and the invention was entitled "Driving Decision Sharing Method, Apparatus, Device and Medium for Autonomous Vehicles"). Technical Field

[0002] This application relates to the field of computer technology, and more particularly to the field of autonomous driving technology, specifically to a method, apparatus, device, and medium for sharing driving decisions for autonomous vehicles. Background Technology

[0003] Human driving skills can be shared among different drivers through training, in-vehicle instruction, verbal instruction, and online research, helping drivers improve their skills. Applying this idea of ​​information sharing to the field of autonomous driving can similarly assist vehicles in acquiring more driving information.

[0004] Existing technologies typically rely on manual statistics of common driving decisions for multiple autonomous vehicles to form a driving experience or decision-making planning database, which is then shared with other vehicles. However, this sharing method is inefficient, and the manually collected information cannot be updated in a timely manner, which prevents the ability of different vehicles to navigate the same road scenarios from being effectively improved. Summary of the Invention

[0005] This invention discloses a method, apparatus, device, and medium for sharing driving decisions among autonomous vehicles, in order to improve the efficiency of sharing driving decisions among autonomous vehicles and enhance the ability of different autonomous vehicles to navigate the same or similar road scenarios.

[0006] In a first aspect, embodiments of this application disclose a method for sharing driving decisions in autonomous vehicles, including:

[0007] Based on the current driving segment of the target vehicle, a driving decision is determined for the current driving segment, wherein the data format of the driving decision is a preset general format recognized by the vehicle system;

[0008] The driving decision is sent to the server, which then selects the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located at the time of the driving decision and the pre-stored historical driving data, and shares the target driving decision.

[0009] One embodiment of the above application has the following advantages or beneficial effects: the driving decision of the target vehicle is determined and actively shared, without relying on manual statistics, which improves the sharing efficiency of driving decisions among autonomous vehicles and enhances the ability of different autonomous vehicles to pass through the same or similar road scenarios; other vehicles selectively apply the received driving decisions according to the verification conditions, ensuring driving safety.

[0010] Optionally, the driving decision includes: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the creator information of the driving decision;

[0011] The creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle.

[0012] Optionally, after determining the driving decision for the current road segment, the method further includes:

[0013] The driving decision is shared with candidate vehicles, which then verify the driving decision based on their route information and historical driving data before applying it to their vehicle control systems.

[0014] One embodiment of the above application has the following advantages or beneficial effects: based on the targeted sharing of driving decisions between vehicles, the trust between vehicles is guaranteed, which helps to improve the reuse rate of driving decisions.

[0015] Optionally, the driving decision is shared with candidate vehicles, including:

[0016] Obtain the location information of the target vehicle when it makes the driving decision;

[0017] Based on the location information, vehicles within the preset area are identified as candidate vehicles;

[0018] The driving decisions are shared with candidate vehicles using vehicle-to-vehicle communication technology.

[0019] One embodiment of the above application has the following advantages or beneficial effects: by determining candidate vehicles based on a preset area, timely sharing of driving decisions can be achieved in a targeted manner, thereby improving the utilization rate of driving decisions.

[0020] Optionally, the driving decisions are shared so that other vehicles can verify them and apply them to their vehicle control systems, including:

[0021] The driving decision is sent to the server, which then selects the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located at the time of the driving decision and the pre-stored historical driving data, and shares the target driving decision.

[0022] One embodiment of the above application has the following advantages or beneficial effects: based on server-based driving decision screening, the recommended sharing of preferred driving decisions further improves road safety.

[0023] Optionally, sending the driving decision to the server includes:

[0024] The driving decision and candidate vehicle identifier are sent to the server so that the server can share the selected driving decision with the candidate vehicles according to the candidate vehicle identifier.

[0025] Optionally, the driving decision includes: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the creator information of the driving decision; the creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle;

[0026] Accordingly, the driving decisions are shared, including:

[0027] If the value assessment result of the driving decision and the safety assessment result of the target vehicle are both greater than or equal to the corresponding preset thresholds, then the driving decision will be shared.

[0028] One embodiment of the above application has the following advantages or beneficial effects: when the driving decision meets the set sharing conditions, it is shared, which ensures that the sharing of driving decisions has practical driving reference value, thereby improving the passability and driving safety of other vehicles in the same or similar road scenarios.

[0029] Optionally, determining the driving decision for the current driving segment based on the target vehicle's current driving segment includes:

[0030] Based on the current travel segment of the target vehicle, obtain the driving data of the target vehicle;

[0031] Based on the driving data, the driving decision is determined using a data processing engine;

[0032] The data processing engine is used to define the conditions for generating the driving decision, the algorithm for processing the driving data, and the content of the driving decision.

[0033] One embodiment of the above application has the following advantages or beneficial effects: using a data processing engine to determine driving decisions makes the generation of driving decisions more flexible and controllable.

[0034] Optionally, based on the driving data, the driving decision is determined using a data processing engine, including:

[0035] The driving data is used as a parameter defined in the data processing engine;

[0036] If at least one parameter satisfies the preset logical conditions in the data processing engine, then the parameters are processed using the processing algorithms defined in the data processing engine corresponding to each parameter.

[0037] The driving decision is generated based on the processing results.

[0038] Optionally, the driving data processing algorithm includes: a threshold adjustment algorithm for the driving data, and a road data processing algorithm corresponding to the driving data.

[0039] Optionally, the method can be applied to autonomous vehicles with fixed work areas, or to vehicles in a fleet of autonomous vehicles with the same vehicle system.

[0040] Secondly, embodiments of this application also disclose a driving decision sharing device for autonomous vehicles, comprising:

[0041] The driving decision generation module is used to determine the driving decision for the current driving segment based on the current driving segment of the target vehicle, wherein the data format of the driving decision is a preset general format recognized by the vehicle system;

[0042] The decision-sharing module is used to send the driving decision to the server, so that the server can select the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located when the driving decision is determined and the pre-stored historical driving data, and share the target driving decision.

[0043] Thirdly, embodiments of this application also disclose an electronic device, including:

[0044] At least one processor; and

[0045] A memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores instructions that can be executed by the at least one processor, which, when executed, enable the at least one processor to perform a driving decision sharing method for an autonomous vehicle as described in any embodiment of this application.

[0047] Fourthly, embodiments of this application also disclose a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the driving decision sharing method for an autonomous vehicle as described in any embodiment of this application.

[0048] According to the technical solution of this application embodiment, the driving decision of the target vehicle for the current driving segment is determined and actively shared, without relying on manual statistics. This improves the efficiency of sharing driving decisions among autonomous vehicles, solves the problem of low efficiency in sharing general driving decisions among autonomous vehicles that rely on manual statistics, and enhances the ability of different autonomous vehicles to navigate the same or similar road scenarios. Simultaneously, other vehicles selectively apply the received driving decisions based on verification conditions, ensuring driving safety. Other effects of the above-mentioned optional method will be described below in conjunction with specific embodiments. Attached Figure Description

[0049] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of this application. Wherein:

[0050] Figure 1 This is a flowchart of a driving decision sharing method for an autonomous vehicle disclosed in an embodiment of this application;

[0051] Figure 2 This is a flowchart of another driving decision sharing method for autonomous vehicles disclosed in the embodiments of this application;

[0052] Figure 3 This is a flowchart of another driving decision sharing method for autonomous vehicles disclosed in the embodiments of this application;

[0053] Figure 4 This is a schematic diagram of the structure of a driving decision sharing device for an autonomous vehicle disclosed in an embodiment of this application;

[0054] Figure 5 This is a block diagram of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0055] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0056] Figure 1This is a flowchart of a driving decision sharing method for an autonomous vehicle according to an embodiment of this application. This embodiment is applicable to situations where driving decisions are generated and shared during the operation of an autonomous vehicle. The method of this embodiment can be executed by a driving decision sharing device for an autonomous vehicle, which can be implemented in software and / or hardware and can be integrated into the vehicle control system or on-board equipment.

[0057] like Figure 1 As shown, the driving decision sharing method for autonomous vehicles disclosed in this embodiment may include:

[0058] S101. Based on the current driving segment of the target vehicle, determine the driving decision for the current driving segment, wherein the data format of the driving decision is a preset general format recognized by the vehicle system.

[0059] In this embodiment, the target vehicle can be one or more unmanned vehicles on the current driving segment. During operation, the target vehicle can use sensors deployed on its vehicle to perceive the current driving environment. Based on this perception information, such as whether the road is congested, whether there are obstacles, or whether there are road accidents, the target vehicle determines its driving decision for the current driving segment. This driving decision differs from the original parameters generated during vehicle operation; it is decision data obtained after processing these original parameters.

[0060] The data formats for driving decisions include, but are not limited to, JSON and Protobuf formats. Based on the universality of the data formats, different vehicles can directly use the driving decisions they acquire without additional data format conversion, thereby improving the efficiency of driving decision reuse and saving other vehicles the time to make decisions and plans in the same or similar road scenarios.

[0061] Optionally, the driving decision includes, but is not limited to: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the creator information of the driving decision; the creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle.

[0062] The main content of driving decision-making includes control information on the current motion state of the target vehicle, such as one or more of the driving data such as position coordinates, driving speed, acceleration, vehicle steering sensitivity, and driving path, as well as the adjustable thresholds and adjustment algorithms corresponding to each driving data.

[0063] The creation time and expiration time of a driving decision are used by other vehicles to determine the time validity of the driving decision after obtaining it. That is, the driving decision can only be reused if it is received before the expiration time. Determining the time validity of a driving decision helps improve the safety of vehicle driving. For example, a target vehicle determines its current driving decision based on the existence of a temporary obstacle on the current road segment. The duration of the temporary obstacle's existence is known. The creation time of the driving decision can be the time when the target vehicle perceives the temporary obstacle, and the expiration time of the driving decision can be the time when the temporary obstacle is removed.

[0064] The value assessment results of driving decisions can be used to measure the quality of driving decisions and the drivability of the target vehicle using the current driving decision on the current road segment. For example, the value assessment result of the current driving decision can be determined by comparing the degree of adjustment of vehicle driving data and the adjustment algorithm between the current driving decision and historical driving decisions used by the target vehicle in the same or similar road scenarios. For instance, if the reliability or applicability of the vehicle driving data adjustment algorithm in the current driving decision is lower than that in historical driving decisions, the corresponding score for the value assessment result of the current driving decision will be lower. The target vehicle safety assessment result can be determined based on factors such as the driving safety and vehicle stability of the target vehicle under the current driving decision. Vehicle stability can be determined based on the passengers' perception.

[0065] The value assessment results of driving decisions and the safety assessment results of the target vehicle are the self-evaluations of the target vehicle under the current driving decision. The assessment of the reliability and safety of the driving decision can be used to determine the timing of driving decision sharing. That is, the target vehicle will only trigger the sharing operation of the driving decision when the value assessment results of the driving decision and the safety assessment results of the target vehicle meet the sharing requirements, so as to ensure that the sharing of driving decisions has practical driving reference value, thereby improving the passability and driving safety of other vehicles in the same or similar road scenarios.

[0066] The creator information of a driving decision is used by other vehicles to determine the source of that driving decision, the credibility of the received driving decision, and whether to apply the driving decision to their control system. The owner ID can refer to the vehicle owner's identity information, and the target vehicle's attribute parameters can include information such as the target vehicle's type, mileage, and license plate.

[0067] The driving decision may also include information such as the road name corresponding to the driving decision and the location coordinates of the target vehicle when the driving decision was made, which is used by other vehicles to confirm the effective location of the received driving decision. The driving decision may also include environmental information perceived by the target vehicle when the driving decision was made, which is used by other vehicles to compare the road scene after receiving the driving decision and to help confirm whether to adopt the driving decision. The driving decision may also include the time of decision sharing, which can also be used by other vehicles to determine the time validity of the driving decision.

[0068] S102. Share driving decisions so that other vehicles can verify and apply the driving decisions to their vehicle control systems.

[0069] After determining its driving decision for the current road segment, the target vehicle can share the decision directly or when the driving decision meets predefined sharing conditions. For example, sharing the driving decision includes: sharing the driving decision if both the value assessment result of the driving decision and the safety assessment result of the target vehicle are greater than or equal to their respective preset thresholds. The thresholds corresponding to the value assessment result and the safety assessment result of the target vehicle can be flexibly determined based on indicators such as vehicle trafficability, vehicle safety, and vehicle stability under the current driving decision; this embodiment does not impose specific limitations.

[0070] The forms of driving decision sharing include, but are not limited to, broadcast, unicast, and / or multicast. Furthermore, decision sharing can be achieved directly through vehicle-to-vehicle communication, or it can be achieved by relaying decisions through servers, cloud platforms, or other third-party communication intermediaries. The specific sharing method can be determined based on actual business needs and other practical circumstances; this embodiment does not impose specific limitations.

[0071] After receiving driving decisions shared by the target vehicle, other vehicles can verify these decisions according to preset verification conditions. Only after successful verification can the decisions be used in the vehicle control system. Selectively applying the received driving decisions based on the verification conditions ensures driving safety. In this embodiment, whether a driving decision is reused is jointly determined by the target vehicle that made the decision and the other vehicles receiving it. There are limitations on the timing of sharing driving decisions and the timing of their reapplication; these dual limitations ensure road safety.

[0072] For example, during the effective period of a driving decision, other vehicles can extract the value assessment results and target vehicle safety assessment results from the received driving decision. If both meet the application requirements, the driving decision can be loaded and applied to the control system after driving to the road segment corresponding to the driving decision.

[0073] For example, other vehicles can evaluate the value of the received driving decisions and their own vehicle safety based on the perception information of the current driving segment. The value evaluation is used to determine the applicability of the driving decisions in the current driving segment. If the evaluation results meet the preset application thresholds, the received driving decisions are applied to the control system; otherwise, they can be rejected. The preset application thresholds are also flexibly determined based on indicators such as vehicle trafficability, vehicle safety, and vehicle stability after the vehicle adopts the received driving decisions.

[0074] Furthermore, the method of this embodiment can be applied to autonomous vehicles with fixed work areas, such as park sprinkler trucks in simple driving environments and with slow driving speeds, or vehicles in an autonomous vehicle fleet with the same vehicle system. When the work area of ​​autonomous vehicles is fixed or they travel in a fleet, the driving environment or road segment of different vehicles is basically the same and will not change significantly. The driving decisions shared by the target vehicles traveling ahead help improve the traffic capacity and efficiency of other vehicles traveling behind, while saving the calculation time for other vehicles to repeatedly execute the driving decision determination on the same road segment.

[0075] According to the technical solution of this application embodiment, the driving decision of the target vehicle for the current driving segment is determined and actively shared, without relying on manual statistics. This improves the efficiency of sharing driving decisions among autonomous vehicles, enhances the ability of different autonomous vehicles to navigate the same or similar road scenarios, and saves the calculation time for other vehicles to repeatedly execute the determination of driving decisions in the same or similar road scenarios. Furthermore, other vehicles selectively apply the received driving decisions according to the verification conditions, ensuring driving safety.

[0076] Figure 2 This is a flowchart of another driving decision sharing method for autonomous vehicles disclosed in the embodiments of this application. It is further optimized and extended based on the above embodiments, and can be combined with various optional technical solutions in the above embodiments. For example... Figure 2 As shown, the method may include:

[0077] S201. Based on the current driving segment of the target vehicle, determine the driving decision for the current driving segment, wherein the data format of the driving decision is a preset general format recognized by the vehicle system.

[0078] S202. Share driving decisions with candidate vehicles so that the candidate vehicles can verify the driving decisions based on their driving route information and historical driving data, and then apply them to the vehicle control system.

[0079] In this context, candidate vehicles refer to autonomous vehicles that receive driving decisions shared by target vehicles. For example, before sharing driving decisions, autonomous vehicles can be managed to establish vehicle-to-vehicle pairing communication, including long-distance and short-distance communication. Vehicles that have established pairing communication can share driving decisions, and the high level of trust between the vehicles helps to improve the reuse rate of driving decisions.

[0080] The candidate vehicle's route information describes its current driving environment. Historical driving data includes, but is not limited to, driving decisions made by the candidate vehicle under different driving environments during its historical driving process, which can reflect the candidate vehicle's historical driving status. For example, the candidate vehicle can compare the received driving decision with historical driving decisions based on the current route information. If a similar decision exists in the historical driving decisions, and it is determined that the candidate vehicle's safety meets driving safety requirements under that received driving decision, then the verification is successful. It should be noted that to ensure timely reuse of the received driving decisions by the candidate vehicle, the candidate vehicle needs to verify the driving decisions beforehand. For example, it can extract the location coordinates carried in the received driving decision, which represent the target vehicle's position when the driving decision was made, i.e., the position where the driving decision took effect. The distance between the extracted location coordinates and the candidate vehicle's current position is calculated. If this distance is less than a preset distance threshold, the verification operation of the received driving decision is triggered. This reduces the latency of the candidate vehicle applying the received driving decisions to the control system. The preset distance threshold can be set according to actual needs.

[0081] Optionally, driving decisions may be shared with candidate vehicles, including:

[0082] Obtain the location information of the target vehicle when it makes a driving decision;

[0083] Based on location information, vehicles within a preset area are identified as candidate vehicles;

[0084] By using vehicle-to-vehicle communication technology, driving decisions are shared with candidate vehicles.

[0085] The location information of the target vehicle can be determined by the positioning device on the vehicle. The size of the preset area can be determined based on the effective distance of the signal transmission between vehicles, which is related to the vehicle-to-vehicle (V2V) communication technology used. This embodiment does not impose a specific limitation. By determining candidate vehicles based on the preset area, timely sharing of driving decisions can be achieved in a targeted manner, improving the utilization rate of driving decisions and increasing vehicle traffic capacity and efficiency.

[0086] S203. The driving decision is sent to the server, so that the server can select the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located when the driving decision is determined and the pre-stored historical driving data, and share the target driving decision.

[0087] By sending driving decisions to a server, the server's storage advantage can be used to store and statistically analyze driving decisions sent by different target vehicles. Then, by leveraging the server's computing power, the preferred target driving decisions for specific road segments can be selected from the stored multiple driving decisions and shared, for example, recommended to candidate vehicles that need them. This can improve the ability of different vehicles to pass through the same or similar road scenarios and enhance road safety.

[0088] For example, when a server receives a driving decision shared by a target vehicle, it can extract the location coordinates or road segment information carried in the driving decision. Based on real-time road information monitoring devices or systems, it can obtain real-time information about the road segment where the target vehicle was located when making the driving decision. Combined with a large amount of historical driving data of vehicles stored in the system, the server can filter and recommend driving decisions for specific road segments. The historical driving data is used to help measure the reuse value of driving decisions shared by different target vehicles. For example, for a certain curve, the server stores driving decisions shared by multiple target vehicles. Based on the real-time road information of the curve and a large amount of historical driving data of vehicles on the curve, the server filters out driving decisions from the stored driving decisions that correspond to higher vehicle passability, higher vehicle safety, and higher vehicle stability during driving. These are then used as target driving decisions and shared for other autonomous vehicles about to enter the curve, thereby improving the safety of autonomous vehicles driving on curves.

[0089] It should be noted that the implementation of server-shared target driving decisions can also include broadcast, unicast, and / or multicast. For unicast or multicast sharing scenarios of target driving decisions, for example, a candidate vehicle can send a driving decision sharing request to the server when it is about to enter a specific road segment, requesting the server to send it available driving decisions. The driving decision sharing request sent by the candidate vehicle can carry the candidate vehicle's location information or information about the specific road segment the candidate vehicle is about to enter, as well as a candidate vehicle identifier, which is used to uniquely identify the candidate vehicle. Based on the vehicle location information or specific road segment information carried in the received driving decision sharing request, the server determines the specific road segment, and then shares the selected target driving decisions with the candidate vehicles according to the candidate vehicle identifier, thereby realizing driving decision recommendation. This improves the communication capabilities of different vehicles for the same or similar road scenarios, enhances road safety, and enriches the implementation methods of driving decision sharing. Targeted driving decision sharing based on the interaction between the server and vehicles, or between vehicles, can also reduce the transmission of useless information in the network.

[0090] During the driving decision sharing process, the above-mentioned operations S202 and S203 can be executed simultaneously. That is, the target vehicle can send driving decisions to candidate vehicles and the server at the same time, or it can choose to execute one of them. This can be set according to the sharing strategy, and this embodiment does not make specific limitations.

[0091] Optionally, sending the driving decision to the server includes sending the driving decision and candidate vehicle identifiers to the server, so that the server can share the selected driving decision with the candidate vehicles according to the candidate vehicle identifiers. That is, when the target vehicle sends the driving decision to the server, it can specify the recipient of the driving decision through the candidate vehicle identifier to achieve targeted sharing of driving decisions.

[0092] According to the technical solution of this application embodiment, the driving decisions determined by the target vehicle for a specific road segment can be shared through vehicle-to-vehicle communication or through server relay, enriching the sharing methods of driving decisions, improving the sharing efficiency of driving decisions among autonomous vehicles, and enhancing the ability of different autonomous vehicles to navigate the same or similar road scenarios; based on the server's driving decision filtering, recommended sharing of preferred driving decisions further improves road safety; and, based on vehicle-to-vehicle interaction or server-vehicle interaction, targeted sharing of driving decisions can also reduce the transmission of useless information in the network.

[0093] Figure 3This is a flowchart of another driving decision sharing method for autonomous vehicles disclosed in the embodiments of this application. It is further optimized and extended based on the above embodiments, and can be combined with various optional technical solutions in the above embodiments. For example... Figure 3 As shown, the method may include:

[0094] S301. Obtain the driving data of the target vehicle based on its current driving route.

[0095] S302. Based on driving data, a data processing engine is used to determine driving decisions. The data processing engine is used to define the conditions for generating driving decisions, the algorithm for processing driving data, and the content of driving decisions.

[0096] The target vehicle's driving data may include one or more of the following: location coordinates, speed, acceleration, vehicle steering sensitivity, driving path, and whether pedestrians are present on the roadside. The driving decision generation condition (Trigger) determines when a driving decision is made and can be set according to different road scenarios or road types, such as curves, straight roads, and slopes; this embodiment does not impose specific limitations. After obtaining the target vehicle's driving data, it is first determined whether data satisfying the driving decision generation condition exists. If so, a processing algorithm corresponding to the driving data satisfying the generation condition is determined based on the current driving segment. The determined algorithm is used to process the driving data (Action), thereby obtaining a driving decision (Event). That is, the process of determining a driving decision can be considered a decision event, which includes the following three fields: the condition that triggers the event (Trigger), the event execution action (Action), and the event description. The event description refers to the content of the driving decision. By utilizing the data processing engine, driving decisions for different driving scenarios and road types can be obtained flexibly and controllably. Multiple different driving decisions determined for the target vehicle can be distinguished by a decision ID.

[0097] Optionally, based on driving data, a data processing engine is used to determine driving decisions, including:

[0098] Use driving data as a parameter defined in the data processing engine;

[0099] If at least one parameter satisfies the preset logical conditions in the data processing engine, then the processing algorithm defined in the data processing engine corresponding to each parameter is used to process each parameter. The logical conditions are used to specifically describe the decision generation conditions satisfied by each parameter. The number of parameters that satisfy the logical conditions is related to the preset driving decision generation conditions.

[0100] Based on the processing results, a driving decision is generated.

[0101] The algorithms for processing driving data may include, but are not limited to: threshold adjustment algorithms for driving data, and road data processing algorithms corresponding to driving data.

[0102] For example, the current driving data includes vehicle position coordinates and vehicle speed. It is pre-defined that when the target vehicle is traveling on a specific road segment, if the vehicle position coordinates (x, y, z) are within a preset circular area, the position coordinates are considered to meet the conditions for generating driving decisions. Based on the current road segment, the maximum threshold for vehicle speed and the safe distance threshold between the vehicle and the road boundary are adjusted. The adjustment operation includes increasing or decreasing, for example, adjusting the maximum threshold for vehicle speed (max_speed) to 3.0 and adjusting the safe distance threshold between the vehicle and the road boundary (road_safe_buffer) to 0.2. The preset circular area can be determined based on the road shape or the distribution of obstacles on the road. For example, a fixed obstacle at a distance of a first preset distance, or a road intersection, can be used as the center of a circle, with a second preset distance as the radius. The first and second preset distances can be flexibly set from the perspective of driving safety.

[0103] For example, current driving data includes vehicle position coordinates, vehicle speed, driving path, and whether pedestrians are present on the roadside. When a target vehicle is detected moving from road segment A into road segment B, the change in vehicle position coordinates satisfies the conditions for generating driving decisions. Based on the current driving road segment B, the current vehicle path planning algorithm is updated to obtain a new driving path, or the current pedestrian classification algorithm is updated to obtain a new pedestrian classification result, or the current speed planning cost function is updated to obtain a new vehicle speed planning result. The specific update targets can be determined based on pre-statistical characteristics of the driving road segments, such as the applicability of the path planning algorithm to a specific road segment, whether pedestrians are concentrated on the road segment, and the speed requirements of the road segment. The road data processing algorithms defined in the data processing engine include, but are not limited to: path planning algorithms, including dynamic programming algorithms, quadratic programming algorithms, polynomial curve fitting programming algorithms, Bézier curve fitting programming algorithms, spline curve fitting programming algorithms, etc.; pedestrian classification algorithms, including decision tree classification algorithms and Bayesian classification algorithms; and speed planning cost functions, including Gaussian functions, quadratic functions, and custom piecewise functions, etc. Furthermore, based on the specific road segment the target vehicle is traveling on, threshold adjustments and road data processing algorithms can be performed simultaneously to obtain driving decisions.

[0104] S303. Share driving decisions so that other vehicles can verify and apply the driving decisions to their vehicle control systems.

[0105] According to the technical solution of this application embodiment, the driving data of the target vehicle on the current driving segment is processed by a data processing engine to obtain driving decisions that can be used by different vehicles, making the generation of driving decisions more flexible and controllable. By sharing driving decisions, the sharing efficiency of driving decisions among autonomous vehicles is improved, the ability of different autonomous vehicles to pass through the same or similar road scenarios is enhanced, and the calculation time for other vehicles to repeatedly execute the determination of driving decisions in the same or similar road scenarios is saved. Furthermore, other vehicles selectively apply the received driving decisions according to the verification conditions, ensuring driving safety.

[0106] Figure 4 This is a schematic diagram of a driving decision sharing device for an autonomous vehicle according to an embodiment of this application. This embodiment is applicable to situations where driving decisions are generated and shared during the operation of an autonomous vehicle. The driving decision sharing device for an autonomous vehicle can be implemented in software and / or hardware and can be integrated into the vehicle control system or onboard equipment.

[0107] like Figure 4 As shown, the driving decision sharing device 400 for autonomous vehicles disclosed in this embodiment may include a driving decision determination module 401 and a decision sharing module 402, wherein:

[0108] The driving decision determination module 401 is used to determine the driving decision for the current driving segment based on the current driving segment of the target vehicle. The data format of the driving decision is a preset general format recognized by the vehicle system.

[0109] The decision-sharing module 402 is used to share driving decisions so that other vehicles can verify the driving decisions and apply them to the vehicle control system.

[0110] Optionally, the driving decision includes: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the information of the creator of the driving decision;

[0111] The creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle.

[0112] Optionally, the decision-sharing module 402 includes a first sharing unit for:

[0113] The driving decisions are shared with candidate vehicles, which then verify the driving decisions based on their route information and historical driving data before applying them to their vehicle control systems.

[0114] Optionally, the first shared unit includes:

[0115] The location information acquisition subunit is used to acquire the location information of the target vehicle when making driving decisions;

[0116] The candidate vehicle determination subunit is used to determine vehicles within a preset area as candidate vehicles based on location information.

[0117] The decision-sharing subunit is used to share driving decisions with candidate vehicles using vehicle-to-vehicle communication technology.

[0118] Optionally, the decision-sharing module 402 includes a second sharing unit for:

[0119] The driving decision is sent to the server, which then selects the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located at the time of the driving decision and the pre-stored historical driving data, and shares the target driving decision.

[0120] Optionally, the second shared unit is specifically used for:

[0121] The driving decision and candidate vehicle identifiers are sent to the server so that the server can share the selected driving decision with the candidate vehicles according to the candidate vehicle identifiers.

[0122] Optionally, the decision-sharing module 402 is specifically used to: share the driving decision if the value assessment result of the driving decision and the safety assessment result of the target vehicle are greater than or equal to the corresponding preset thresholds.

[0123] Optionally, the driving decision determination module 401 includes:

[0124] The driving data acquisition unit is used to acquire the driving data of the target vehicle based on the current driving segment of the target vehicle;

[0125] The driving decision determination unit is used to determine driving decisions based on driving data using a data processing engine.

[0126] The data processing engine is used to define the conditions for generating driving decisions, the algorithms for processing driving data, and the content of driving decisions.

[0127] Optionally, the driving decision-making unit includes:

[0128] The parameter determination subunit is used to treat driving data as parameters defined in the data processing engine;

[0129] The parameter processing subunit is used to process each parameter by using the processing algorithm defined in the data processing engine corresponding to each parameter if at least one parameter satisfies the preset logical conditions in the data processing engine.

[0130] The driving decision generation subunit is used to generate driving decisions based on the processing results.

[0131] Optionally, the driving data processing algorithms include: a threshold adjustment algorithm for driving data, and a road data processing algorithm corresponding to the driving data.

[0132] Optionally, in this embodiment, the driving decision sharing device 400 for autonomous vehicles can be configured in an autonomous vehicle with a fixed work area, or in a fleet of autonomous vehicles with the same vehicle system.

[0133] The driving decision sharing device 400 for autonomous vehicles disclosed in this application can execute any driving decision sharing method for autonomous vehicles disclosed in this application, and has the corresponding functional modules and beneficial effects for executing the method. Content not described in detail in this embodiment can be referred to the description in any method embodiment of this application.

[0134] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0135] like Figure 5 As shown, Figure 5 This is a block diagram of an electronic device for implementing the driving decision sharing method for autonomous vehicles in the embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can represent any in-vehicle device, and can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0136] like Figure 5As shown, the electronic device includes one or more processors 501, a memory 502, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a graphical user interface (GUI) on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations, for example, as a server array, a group of blade servers, or a multiprocessor system. Figure 5 Take a processor 501 as an example.

[0137] The memory 502 is the non-transitory computer-readable storage medium provided in this application. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the driving decision sharing method for autonomous vehicles provided in the embodiments of this application. The non-transitory computer-readable storage medium of this application stores computer instructions for causing a computer to perform the driving decision sharing method for autonomous vehicles provided in the embodiments of this application.

[0138] Memory 502, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the driving decision sharing method for autonomous vehicles in this embodiment of the application, for example, the attached... Figure 4 The driving decision determination module 401 and decision sharing module 402 are shown. The processor 501 executes various functional applications and data processing of the server by running non-transient software programs, instructions, and modules stored in the memory 502, thereby realizing the driving decision sharing method for autonomous vehicles in the above method embodiment.

[0139] The memory 502 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function. The data storage area may store data created based on the use of the electronic device for implementing the driving decision sharing method for autonomous vehicles in the embodiments of this application. Furthermore, the memory 502 may include high-speed random access memory and may also include non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 502 may optionally include memory remotely located relative to the processor 501. These remote memories can be connected via a network to the electronic device for implementing the driving decision sharing method for autonomous vehicles in the embodiments of this application. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0140] The electronic device used to implement the driving decision sharing method for autonomous vehicles in the embodiments of this application may further include: an input device 503 and an output device 504. The processor 501, memory 502, input device 503, and output device 504 may be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0141] Input device 503 can receive input digital or character information, and generate key signal inputs related to user settings and function control of the electronic device used to implement the driving decision sharing method for autonomous vehicles in the embodiments of this application. Examples of input devices include touchscreens, keypads, mice, trackpads, touchpads, joysticks, one or more mouse buttons, trackballs, and joysticks. Output device 504 may include display devices, auxiliary lighting devices, and haptic feedback devices. Auxiliary lighting devices may include, for example, light-emitting diodes (LEDs); haptic feedback devices may include, for example, vibration motors. The display device may include, but is not limited to, liquid crystal displays (LCDs), LED displays, and plasma displays. In some embodiments, the display device may be a touchscreen.

[0142] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] These computational programs, also known as programs, software, software applications, or code, include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus for providing machine instructions and / or data to a programmable processor, such as a disk, optical disk, memory, or programmable logic device (PLD), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or an LCD monitor; and a keyboard and pointing device, such as a mouse or trackball, through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including sound input, voice input, or tactile input.

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components, such as data servers; or in computing systems that include middleware components, such as application servers; or in computing systems that include frontend components, such as user computers with graphical user interfaces or web browsers through which users can interact with the implementations of the systems and technologies described herein; or in computing systems that include any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium, such as communication networks. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0146] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0147] According to the technical solution of this application embodiment, the driving decision of the target vehicle for the current driving segment is determined and actively shared, without relying on manual statistics. This improves the efficiency of driving decision sharing among autonomous vehicles, enhances the ability of different autonomous vehicles to navigate the same or similar road scenarios, and saves the computation time for other vehicles to repeatedly execute the determination of driving decisions in the same or similar road scenarios. Furthermore, other vehicles selectively apply the received driving decisions according to verification conditions, ensuring driving safety. Based on the server's driving decision filtering, recommended sharing of preferred driving decisions further improves road safety. The use of a data processing engine to determine driving decisions that are applicable to different vehicles makes the generation of driving decisions more flexible and controllable.

[0148] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for sharing driving decisions in an autonomous vehicle, characterized in that, include: Based on the current driving segment of the target vehicle, a driving decision is determined for the current driving segment, wherein the data format of the driving decision is a preset general format recognized by the vehicle system; The driving decision is sent to the server, which then selects the target driving decision for the specific road segment from the received driving decisions based on real-time information of the road segment where the target vehicle is located at the time of the driving decision and pre-stored historical driving data, and shares the target driving decision; the real-time information is obtained based on a real-time road information monitoring device; The driving decision includes: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the creator information of the driving decision; the creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle; the main content of the driving decision includes driving data, as well as the adjustable threshold and adjustment algorithm corresponding to the driving data; the value assessment result of the driving decision is determined based on the comparison results of the degree of adjustment of the vehicle driving data and the adjustment algorithm in the current driving decision adopted by the target vehicle under the same or similar road scenarios and the historical driving decisions. Accordingly, the driving decisions are shared, including: If the value assessment result of the driving decision and the safety assessment result of the target vehicle are both greater than or equal to the corresponding preset thresholds, then the driving decision will be shared.

2. The method according to claim 1, characterized in that, After determining the driving decision for the current road segment, the process also includes: The driving decision is shared with candidate vehicles, which then verify the driving decision based on their route information and historical driving data before applying it to their vehicle control systems.

3. The method according to claim 2, characterized in that, Sharing the driving decisions with candidate vehicles includes: Obtain the location information of the target vehicle when it makes the driving decision; Based on the location information, vehicles within the preset area are identified as candidate vehicles; The driving decisions are shared with candidate vehicles using vehicle-to-vehicle communication technology.

4. The method according to claim 1, characterized in that, Sending the driving decision to the server includes: The driving decision and candidate vehicle identifier are sent to the server so that the server can share the selected target driving decision with the candidate vehicle according to the candidate vehicle identifier.

5. The method according to claim 1, characterized in that, The step of determining the driving decision for the current driving segment based on the target vehicle's current driving segment includes: Based on the current travel segment of the target vehicle, obtain the driving data of the target vehicle; The driving data is used as a parameter defined in the data processing engine; If at least one parameter satisfies the preset logical conditions in the data processing engine, then the parameters are processed using the processing algorithms defined in the data processing engine corresponding to each parameter. The driving decision is generated based on the processing results; The data processing engine is used to define the conditions for generating the driving decision, the algorithm for processing the driving data, and the content of the driving decision.

6. The method according to claim 5, characterized in that, The driving data processing algorithm includes: a threshold adjustment algorithm for the driving data, and a road data processing algorithm corresponding to the driving data.

7. The method according to claim 1, characterized in that, The method is applied to autonomous vehicles with fixed work areas, or to vehicles in a fleet of autonomous vehicles with the same vehicle system.

8. A driving decision-sharing device for an autonomous vehicle, characterized in that, include: The driving decision generation module is used to determine the driving decision for the current driving segment based on the current driving segment of the target vehicle, wherein the data format of the driving decision is a preset general format recognized by the vehicle system; The decision-sharing module is used to send the driving decision to the server, so that the server can select the target driving decision for the specific road segment from the received driving decisions based on the real-time information of the road segment where the target vehicle is located at the time of determining the driving decision and the pre-stored historical driving data, and share the target driving decision; the real-time information is obtained based on the real-time road information monitoring device; The driving decision includes: the main content of the driving decision, the creation time and expiration time of the driving decision, the value assessment result of the driving decision, the safety assessment result of the target vehicle, and the creator information of the driving decision; the creator information includes the owner ID of the target vehicle and the attribute parameters of the target vehicle; the main content of the driving decision includes driving data, as well as the adjustable threshold and adjustment algorithm corresponding to the driving data; the value assessment result of the driving decision is determined based on the comparison results of the degree of adjustment of the vehicle driving data and the adjustment algorithm in the current driving decision adopted by the target vehicle under the same or similar road scenarios and the historical driving decisions. Accordingly, the decision-sharing module is specifically used to: share the driving decision if the value assessment result of the driving decision and the safety assessment result of the target vehicle are respectively greater than or equal to the corresponding preset thresholds.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the driving decision sharing method for an autonomous vehicle according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the driving decision sharing method for an autonomous vehicle according to any one of claims 1-7.

Images