A method, device and equipment for recommending vehicle autonomous lane change

Abstract

The application discloses a vehicle autonomous lane changing recommendation method, device and equipment, comprising: when the vehicle speed is less than the expected speed, determining a target vehicle in the target lane that meets the preset condition; in the observation period, calculating the traffic congestion index of the vehicle lane and the target lane every interval preset time period, calculating the average traffic congestion index of the vehicle lane and the average traffic congestion index of the target lane; when the risk assessment result of the target lane is safe, if the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle lane and less than the preset traffic congestion index, the vehicle is recommended to change lanes to the target lane. When the risk assessment result of the target lane is safe, the traffic states of the vehicle lane and the target lane are comprehensively considered, and the traffic state change in a period of time is considered, so that the unreasonable lane changing behavior of the vehicle is reduced, and the accuracy of the autonomous lane changing of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a method, device, and apparatus for recommending autonomous lane changing of a vehicle. Background Art

[0002] With the continuous development of intelligent driving technology, autonomous and assisted lane changes are gradually playing a role in improving traffic efficiency and preventing traffic accidents. Active lane changes by intelligent driving vehicles generally fall into two categories: one is a mandatory active lane change due to a turn at an intersection or a vehicle merging in or out, which necessitates the vehicle moving to the corresponding lane; the other is an autonomous lane change, which involves automatically selecting a faster lane when the vehicle ahead is driving slower or in traffic congestion.

[0003] Currently, autonomous lane change decisions for intelligent vehicles generally involve two steps: first, expressing dissatisfaction with the current lane, and second, conducting a risk assessment of the target lane. Only when both conditions are met can a lane change be executed. However, existing autonomous lane change decisions fail to consider the traffic conditions of the target lane or traffic trends over time. Instead, they only assess the risk of the vehicle's surroundings over a short period of time. Consequently, these autonomous lane change decisions have certain limitations. This can result in the intelligent vehicle detecting congestion in the lane ahead after the lane change, or the traffic flow in the original lane gradually increasing or even surpassing that of the lane ahead. Summary of the Invention

[0004] Embodiments of the present application provide a method, apparatus, and device for recommending autonomous lane changes of a vehicle, so as to improve the accuracy of autonomous lane changes of the vehicle.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending autonomous lane change for a vehicle, the method comprising:

[0006] When the vehicle speed is less than the expected speed, a target vehicle that meets the preset conditions is determined in the target lane;

[0007] During the observation period, the traffic congestion index of the vehicle lane and the traffic congestion index of the target lane are calculated at intervals of a preset time period; wherein the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle;

[0008] Calculating the average traffic congestion index of the own vehicle lane and the average traffic congestion index of the target lane according to the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane calculated during the observation period;

[0009] When the risk assessment result of the target lane is safe, if the current speed of the host vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the host vehicle's lane, and the average traffic congestion index of the target lane is less than a preset traffic congestion index, it is recommended that the host vehicle change lanes to the target lane;

[0010] The target lane is an adjacent lane of the host vehicle lane.

[0011] In one possible implementation, the method further includes:

[0012] When there is no target vehicle meeting the preset conditions in the target lane, if the average traffic congestion index of the target lane is less than a first preset ratio of the preset traffic congestion index, and the average traffic congestion index of the host vehicle's lane is greater than a threshold, it is recommended that the host vehicle change lanes to the target lane; wherein the first preset ratio is less than 1.

[0013] In a possible implementation, when the speed of the host vehicle is less than the expected speed, determining a target vehicle in the target lane that meets a preset condition includes:

[0014] When the speed of the host vehicle is less than a second preset ratio of the expected speed, a target vehicle meeting preset conditions is determined in the target lane; wherein the second preset ratio is less than 1.

[0015] In a possible implementation manner, the target vehicles meeting the preset conditions include:

[0016] a vehicle located in front of the host vehicle and within a first preset distance from the host vehicle;

[0017] A vehicle located behind the host vehicle and within a second preset distance from the host vehicle.

[0018] In a possible implementation, calculating the traffic congestion index of the vehicle's lane includes:

[0019] The host vehicle and the vehicle closest to the host vehicle in the host vehicle lane are taken as target vehicles in the host vehicle lane, the traffic congestion index of the target vehicle in the host vehicle lane is calculated, and then the average traffic congestion index of all target vehicles in the host vehicle lane is calculated.

[0020] In a possible implementation manner, the average traffic congestion index of the target lane is less than the average traffic congestion index of the own vehicle lane, including:

[0021] The average traffic congestion index of the target lane is less than a third preset ratio of the average traffic congestion index of the host vehicle lane; wherein the third preset ratio is less than 1.

[0022] In a possible implementation, the risk assessment result of the target lane being safe includes:

[0023] The lane change space provided by the target lane allows the host vehicle to change lanes.

[0024] In a possible implementation manner, when the target lane includes a left lane of the host vehicle lane and a right lane of the host vehicle lane, the method further includes:

[0025] When the average traffic congestion index of the left lane is less than the average traffic congestion index of the right lane, it is recommended that the vehicle change lanes to the left lane; otherwise, it is recommended that the vehicle change lanes to the right lane.

[0026] In a second aspect, an embodiment of the present application further provides a device for recommending autonomous lane changes for a vehicle, the device comprising a data processing module, a calculation module, and an output module:

[0027] The data processing module is configured to: when the vehicle speed is less than the expected speed, determine a target vehicle in the target lane that meets preset conditions;

[0028] The calculation module is configured to calculate the traffic congestion index of the vehicle lane and the traffic congestion index of the target lane at intervals of a preset time period during an observation period; wherein the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle;

[0029] Calculating the average traffic congestion index of the own vehicle lane and the average traffic congestion index of the target lane according to the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane calculated during the observation period;

[0030] The output module is configured to: when a risk assessment result of the target lane is safe, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, recommend that the vehicle change lanes to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane.

[0031] In a third aspect, an embodiment of the present application further provides a device for recommending autonomous lane change for a vehicle, the device comprising a memory and a processor:

[0032] The memory is used to store relevant program codes;

[0033] The processor is used to call the program code to execute the method for recommending autonomous lane change of a vehicle as described in any one of the embodiments of the first aspect above.

[0034] In the above-mentioned implementation of the embodiment of the present application, when the speed of the vehicle is less than the expected speed, a target vehicle in the target lane that meets the preset conditions is determined; within the observation period, the traffic congestion index of the vehicle's lane and the traffic congestion index of the target lane are calculated at intervals of a preset time period; wherein, the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle; based on the traffic congestion indices of all vehicle lanes and target lanes calculated within the observation period, the average traffic congestion index of the vehicle's lane and the average traffic congestion index of the target lane are calculated; when the risk assessment result of the target lane is safe, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, it is recommended that the vehicle change lanes to the target lane; wherein, the target lane is an adjacent lane to the vehicle's lane. The autonomous lane change recommendation method provided in the embodiment of the present application comprehensively considers the traffic conditions of the vehicle's lane and the target lane, as well as changes in traffic conditions over a period of time, when the risk assessment result of the target lane is safe, thereby reducing unreasonable lane change behavior of the vehicle and improving the accuracy of the vehicle's autonomous lane change. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments provided in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] Figure 1 This is a flowchart of a recommended method for autonomous lane changing of a vehicle in an embodiment of the present application;

[0037] Figure 2 This is a flowchart of another recommended method for autonomous lane changing of a vehicle in an embodiment of the present application;

[0038] Figure 3 This is a flowchart of another recommended method for autonomous lane changing of a vehicle in an embodiment of the present application;

[0039] Figure 4 A flowchart of a recommended method for autonomous lane changing in a practical application scenario;

[0040] Figure 5 A schematic diagram of a recommended device for autonomous lane changing of a vehicle according to an embodiment of the present application;

[0041] Figure 6This is a schematic diagram of a recommended device for autonomous lane changing of a vehicle in an embodiment of the present application. DETAILED DESCRIPTION

[0042] Autonomous lane change decisions for intelligent vehicles typically involve two steps: first, expressing dissatisfaction with the current lane, and second, conducting a risk assessment of the target lane. Lane change is only executed when both conditions are met. However, existing autonomous lane change decisions fail to consider the traffic conditions in the target lane or traffic trends over time. Instead, they only assess the risk of the vehicle's surroundings over a short period of time, potentially leading to frequent and irrational lane changes.

[0043] Most of the methods for monitoring and evaluating traffic state flows in the transportation field conduct detection at fixed locations and fixed time periods. For example, detection equipment is set up at a fixed location (on an overpass) to detect traffic flow states at different time periods within a fixed road section. The traffic flow for intelligent driving lane change needs is the traffic state within a certain range relative to the intelligent driving vehicle over a period of time. The position of an intelligent driving vehicle is constantly changing during driving, and it also changes relative to a certain time and space range relative to the intelligent driving vehicle. Therefore, the surrounding target vehicles detected are dynamically changing within a certain time and space range relative to the intelligent driving vehicle. Therefore, the traffic evaluation of intelligent driving vehicles for autonomous lane change focuses on the dynamically changing target state around the vehicle, which can more conveniently obtain dynamic traffic conditions.

[0044] Based on this, an embodiment of the present application provides a method for recommending autonomous lane changing of a vehicle. When the speed of the vehicle is less than the expected speed, a target vehicle in the target lane that meets the preset conditions is determined; within the observation period, the traffic congestion index of the vehicle's lane and the traffic congestion index of the target lane are calculated at intervals of a preset time period; wherein, the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle; based on the traffic congestion index of the vehicle's lane and the traffic congestion index of the target lane calculated within the observation period, the average traffic congestion index of the vehicle's lane and the average traffic congestion index of the target lane are calculated; when the risk assessment result of the target lane is safe, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, it is recommended that the vehicle change lanes to the target lane; wherein, the target lane is an adjacent lane to the vehicle's lane.

[0045] The autonomous lane change recommendation method provided in the embodiment of the present application does not necessarily recommend the vehicle to change lanes autonomously when the risk assessment result of the target lane is safe. It is necessary to comprehensively consider the traffic conditions of the vehicle's lane and the target lane, as well as changes in traffic conditions over a period of time. When the flow rate in the target lane has no advantage over the vehicle's lane or does not meet the expected speed, autonomous lane changing is not recommended. This can reduce frequent lane changes and unreasonable lane changing behaviors of the vehicle, reduce potential risks caused by lane changes, improve the vehicle's intelligent driving efficiency, and improve the accuracy of the vehicle's autonomous lane changes.

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The described embodiments are only exemplary implementation methods of the present application and are not all implementation methods. Those skilled in the art can combine the embodiments of the present application to obtain other embodiments without creative work, and these embodiments are also within the scope of protection of the present application.

[0047] See also Figure 1 , which is a flowchart of a recommended method for vehicle autonomous lane changing provided in an embodiment of the present application.

[0048] The method specifically comprises the following steps:

[0049] S101: When the vehicle speed is less than the expected speed, a target vehicle meeting the preset conditions is determined in the target lane;

[0050] The vehicle's intention to autonomously change lanes is because the vehicle's current speed is lower than the expected speed due to traffic congestion or other reasons, so the vehicle is considering changing lanes. Before changing lanes, a target lane is first selected for lane change. In this embodiment of the application, the target lane is an adjacent lane to the vehicle's lane. The traffic status of the target lane is evaluated based on the target vehicle in the target lane. When evaluating the traffic status of the target lane, it is not necessary to consider all vehicles in the target lane. For example, vehicles located at a long distance behind the vehicle do not need to be considered. Therefore, it is necessary to first determine the target vehicle that meets the preset conditions.

[0051] S102: Calculating the traffic congestion index of the vehicle's lane and the target lane at predetermined time intervals during the observation period; wherein the target lane's traffic congestion index is calculated based on the target vehicle's traffic congestion index;

[0052] The autonomous lane change recommendation method provided in this embodiment comprehensively considers changes in traffic conditions in both the host vehicle's lane and the target lane over a period of time. Therefore, it requires continuous observation for a period of time, known as an observation period. In this embodiment, lane traffic conditions are assessed by calculating the lane congestion index as a measure of traffic flow in each lane. The target lane's congestion index can only be calculated by calculating the target vehicle's congestion index in the target lane.

[0053] S103: Calculating the average traffic congestion index of the own lane and the average traffic congestion index of the target lane based on the traffic congestion index of the own lane and the traffic congestion index of the target lane calculated during the observation period;

[0054] The traffic congestion index of the own lane and the traffic congestion index of the target lane are calculated at every preset time period. Therefore, during the entire observation period, multiple traffic congestion indices of the own lane and the target lane are calculated. Then, based on all the traffic congestion indices of the own lane and the traffic congestion indices of the target lane calculated during the observation period, the average traffic congestion index of the own lane and the average traffic congestion index of the target lane are calculated.

[0055] S104: When the risk assessment result of the target lane is safe, if the current speed of the vehicle is lower than the expected speed, the average traffic congestion index of the target lane is lower than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is lower than the preset traffic congestion index, it is recommended that the vehicle change lanes to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane.

[0056] When the above four conditions are met, it is recommended that the vehicle change lanes to the target lane, namely:

[0057] (1) The risk assessment result of the target lane is safe.

[0058] A prerequisite for recommending the vehicle to change lanes to the target lane is that the risk assessment result of the target lane is safe.

[0059] (2) The current speed of the vehicle is still lower than the expected speed.

[0060] Because after a period of time, the current speed of the vehicle may meet the expected speed, so there is no need to change lanes.

[0061] (3) The average traffic congestion index of the target lane is less than the average traffic congestion index of the own vehicle lane, that is, the traffic flow state of the target lane is better than the traffic flow state of the own vehicle lane.

[0062] (4) The average traffic congestion index of the target lane is less than the preset traffic congestion index, that is, the traffic flow state of the target lane is relatively smooth compared to the expected traffic flow state, and it is recommended that the vehicle change lanes to the target lane.

[0063] When any of the above four conditions is not met, it is not recommended for the vehicle to change lanes to the target lane.

[0064] The autonomous lane change recommendation method provided in the embodiment of the present application comprehensively considers the traffic conditions of the vehicle's lane and the target lane, as well as changes in traffic conditions over a period of time, when the risk assessment result of the target lane is safe. When the flow rate of the target lane is better than the flow rate of the vehicle's lane and meets the expected vehicle speed, the method recommends that the vehicle autonomously change lanes, thereby improving the accuracy of the vehicle's autonomous lane change.

[0065] To reduce frequent lane changes, this embodiment also provides a preferred implementation where the vehicle only generates a lane change intention and executes the recommended autonomous lane change decision when the vehicle's speed is less than a second predetermined ratio of the preset speed. The second predetermined ratio is less than 1. By further limiting the range within which the vehicle's speed is less than the expected speed, frequent lane changes can be reduced, mitigating the dangers associated with such behavior.

[0066] In step S101, when the host vehicle's speed is less than the expected speed, a lane change intention is generated. The system first determines a target vehicle in the target lane that meets the preset conditions. The target lane is the adjacent lane to the host vehicle's lane. If the host vehicle's lane is the leftmost lane, the only adjacent lane is the right lane, so the right lane is the target lane. Similarly, if the host vehicle's lane is the rightmost lane, the only adjacent lane is the left lane, so the left lane is the target lane. If the host vehicle's lane is in the middle lane, the adjacent lanes are the left and right lanes, so both the left and right lanes are the target lanes.

[0067] When the vehicle's lane is in the middle lane, the target lane includes the left lane and the right lane of the vehicle's lane. If the left lane and the right lane both meet the above four conditions, then the vehicle can change lanes to the left lane or the right lane.

[0068] This embodiment also provides a preferred implementation method. When both the left and right lanes meet the above four conditions, the average traffic congestion index of the left lane is compared with the average traffic congestion index of the right lane. If the average traffic congestion index of the left lane is less than the average traffic congestion index of the right lane, it indicates that the traffic conditions in the left lane are better than those in the right lane, and the vehicle is recommended to change lanes to the left lane. Otherwise, the vehicle is recommended to change lanes to the right lane. By comparing the traffic conditions of the left and right lanes of the vehicle's lane, lane change recommendations can be made more accurately.

[0069] When the vehicle is changing lanes, some vehicles that have little impact on the current lane change of the vehicle do not need to be considered, such as vehicles that are located at a long distance behind the vehicle in the target lane. Therefore, it is only necessary to determine the target vehicles that meet the preset conditions. For example, one possible implementation method is that in the target lane, the vehicle that is located in front of the vehicle and within a first preset distance from the vehicle is the target vehicle that meets the preset conditions. In the target lane, if the vehicle in front of the vehicle is relatively close to the vehicle, it will have an impact on the lane change of the vehicle; similarly, the vehicle that is located behind the vehicle in the target lane and within a second preset distance from the vehicle will also have an impact on the lane change of the vehicle. In this embodiment, the size relationship between the first preset distance and the second preset distance is not limited, that is, the two can be equal, or the first preset distance can be greater than the second preset distance, or the first preset distance can be less than the second preset distance.

[0070] In the above embodiment, the distance between the target vehicle and the host vehicle is within a preset distance. The specific value of the preset distance can be determined based on the actual application scenario. One possible implementation method is to set the preset distance to 150m in this embodiment, with the center of the host vehicle's rear axle as the origin, and vehicles within 150m of the origin. It should be noted that this embodiment does not limit the method for calculating the distance to the host vehicle, that is, it does not limit the method for determining the center origin of the host vehicle. For example, the distance between the host vehicle and other vehicles can also be calculated with the center of the host vehicle's front axle as the origin. Other possible implementation methods are also within the scope of protection of the embodiments of this application.

[0071] If a large number of target vehicles are obtained through the above preset conditions screening, another possible implementation method is to select target vehicles that meet the requirements of being located in front of the vehicle, within a preset distance from the vehicle, and with a speed lower than the vehicle's speed. The target vehicle in front of the vehicle is limited to having a speed lower than the vehicle's speed, so the target vehicle's speed will not exceed the preset distance from the vehicle in a short period of time due to the target vehicle's excessive speed. These vehicles can be selected as target vehicles that meet the preset conditions. Similarly, vehicles located behind the vehicle, within a preset distance from the vehicle, and with a speed higher than the vehicle's speed also fall under the target vehicle's preset conditions. Since the target vehicle is located behind the vehicle and has a speed higher than the vehicle's speed, the target vehicle's speed will not exceed the preset distance from the vehicle in a short period of time due to the target vehicle's excessive speed. These vehicles can be selected as target vehicles that meet the preset conditions.

[0072] In the embodiment of the present application, the traffic congestion index of the lane is calculated as a characterization of the road traffic status. One possible implementation method is to calculate the traffic congestion index CI as a characterization. The traffic congestion index CI is also called the public transportation index CI, which measures the traffic congestion status of a region by the ratio of excess time to the original time. The calculation formula of CI is:

[0073] CI=(T-T0) / T0=T / T0-1=[(L / v) / (L / v0)]-1=(v0 / v)-1=(v0-v) / v;

[0074] Among them, T is the actual time; T0 is the ideal time in free flow, that is, the time taken to travel at the driver's desired speed; L is the length of the road section; v is the actual vehicle speed; v0 is the free flow speed, that is, the ideal vehicle speed.

[0075] In step S102 and step S103, during the observation period, the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane are calculated at every preset time interval; wherein, the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle; based on the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane calculated during the observation period, the average traffic congestion index of the own vehicle lane and the average traffic congestion index of the target lane are calculated.

[0076] When calculating the traffic congestion index CI of the target lane, specifically, at every preset time period, each target vehicle in the target lane is sampled to obtain information such as the speed of the target vehicle, and then the traffic congestion index CI of each target vehicle is calculated. The traffic congestion index CI values ​​of all target vehicles are summed and divided by the number of target vehicles to obtain the average traffic congestion index CI of the target lane at the sampling moment.

[0077] The average traffic congestion index (CI) calculated at each preset time interval represents a single frame of sampled data, i.e., the data at that sampling moment. Over the entire observation period, multiple average traffic congestion indexes (CIs) for the target lane are obtained. The sum of the average CIs for all sampling moments is divided by the number of sampling times to obtain the average CI for the target lane over the entire observation period. The following describes how to calculate the CI for the target lane using a specific scenario.

[0078] Set the observation period to 10s and the preset time period to 100ms. This means that every 100ms, the target vehicles in the target lane are sampled. The traffic congestion index (CI) for each target vehicle at the current moment is calculated. The average traffic congestion index (CI) for all target vehicles is then calculated, resulting in the average traffic congestion index (CI) for the target lane at that moment. The single-frame sampling data for that moment is then stored. The average traffic congestion index (CI) for the target lane is then calculated again every 100ms. Since the observation period is 10s and the preset time period is 100ms, 100 frames of sampling data are obtained, resulting in 100 average traffic congestion indexes (CI) for the target lane at different moments. All these average traffic congestion indexes (CI) are summed and divided by 100 to obtain the average traffic congestion index (CI) for the target lane during the observation period.

[0079] When calculating the traffic congestion index (CI) for the host vehicle's lane, it's also necessary to first calculate the traffic congestion index (CI) for the target vehicle in that lane. One possible approach to determining the target vehicle in the host lane is to select the host vehicle and the vehicle closest to it in front of it as the target vehicles in the host lane. The basic principles for calculating the traffic congestion index (CI) are the same as those for the target lane and will not be further elaborated here.

[0080] It should be noted that in the embodiment of the present application, if there is no target vehicle meeting the preset conditions in the target lane, the traffic congestion index CI of the target lane is assigned a value of 0. In addition, the traffic status representation is not limited to the traffic congestion index CI. There are other possible implementation methods, for example, the road traffic index PSI in local standards can be referred to as a traffic status representation.

[0081] By comparing the average congestion index (CI) of the vehicle's lane and the target lane, a decision is made as to whether to recommend the vehicle changing lanes to the target lane. A prerequisite for changing lanes to the target lane is that the target lane's risk assessment result is safe. One possible implementation of the target lane risk assessment is to determine whether there is suitable space in the target lane and whether the available space allows the vehicle to change lanes. If there is sufficient space for the vehicle to change lanes, the target lane is considered safe.

[0082] If the target lane's risk assessment result is safe, but the vehicle's current speed is still slower than the expected speed, it indicates a lane change is still necessary. At this point, if the target lane's average congestion index (CI) is lower than the vehicle's lane's average congestion index (CI), indicating that the target lane's traffic flow is better than the vehicle's lane's, and if the target lane's average congestion index (CI) is lower than the preset CI (a CI value calibrated based on actual application scenarios and requirements), it indicates that traffic in the target lane is smoother than the expected flow, and a lane change to the target lane is recommended.

[0083] In the above embodiment, when the average traffic congestion index CI of the target lane is less than the average traffic congestion index CI of the host lane, one of the lane change conditions is met. In actual application scenarios, when the traffic conditions of the target lane are better than those of the host lane, but not significantly better than those of the host lane, in order to avoid frequent lane changes, the lane change conditions can be further limited. Figure 2 This paper introduces the recommended method for autonomous lane changing of vehicles.

[0084] See also Figure 2 , this figure is a flowchart of another recommended method for vehicle autonomous lane changing provided in an embodiment of the present application.

[0085] The method specifically comprises the following steps:

[0086] S201: When the speed of the vehicle is less than the expected speed, determining a target vehicle in the target lane that meets the preset conditions;

[0087] S202: Calculating the traffic congestion index CI of the vehicle's lane and the traffic congestion index CI of the target lane at every preset time interval during the observation period; wherein the traffic congestion index CI of the target lane is calculated based on the traffic congestion index CI of the target vehicle;

[0088] S203: Calculating the average traffic congestion index CI of the vehicle lane and the average traffic congestion index CI of the target lane based on the traffic congestion index CI of the vehicle lane and the traffic congestion index CI of the target lane calculated during the observation period;

[0089] The traffic congestion index CI of the own vehicle lane and the traffic congestion index CI of the target lane are calculated at every preset time period. Therefore, during the entire observation period, multiple traffic congestion indices CI of the own vehicle lane and the target lane are calculated. Then, based on all the traffic congestion indices CI of the own vehicle lane and the traffic congestion indices CI of the target lane calculated during the observation period, the average traffic congestion index CI of the own vehicle lane and the average traffic congestion index CI of the target lane are calculated.

[0090] S204: When the lane-changing space provided by the target lane allows the vehicle to change lanes, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index CI of the target lane is less than a third preset ratio of the average traffic congestion index CI of the vehicle's lane, and the average traffic congestion index CI of the target lane is less than the preset traffic congestion index CI, it is recommended that the vehicle change lanes to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane; and the third preset ratio is less than 1.

[0091] The autonomous lane change recommendation method provided in the embodiment of the present application comprehensively considers the traffic conditions of the vehicle's lane and the target lane, as well as changes in traffic conditions over a period of time, when the lane change space provided by the target lane allows the vehicle to change lanes. When the flow rate in the target lane is significantly better than the flow rate in the vehicle's lane and meets the expected vehicle speed, the method recommends that the vehicle autonomously change lanes, thereby reducing frequent and unreasonable lane change behaviors of the vehicle and improving the accuracy of the vehicle's autonomous lane changes.

[0092] In actual application scenarios, if the current speed of the host vehicle meets the expected speed, the vehicle autonomous lane change recommendation method provided in the above embodiment will not recommend the host vehicle to change lanes. This embodiment also provides another possible implementation method. If there is no target vehicle meeting the preset conditions in the target lane at this time, and the average traffic congestion index of the target lane is less than a first preset ratio of the preset traffic congestion index, and the first preset ratio is less than 1, that is, the traffic conditions in the target lane are significantly better than the expected traffic conditions, and the average traffic congestion index of the host vehicle's lane is greater than a threshold, that is, the traffic conditions in the host vehicle's lane do not meet the requirements of relatively smooth traffic conditions. This threshold can be experimentally calibrated based on the application scenario. In this case, the host vehicle can be recommended to change lanes to the target lane.

[0093] Based on this, the embodiment of the present application also provides a method for recommending a vehicle to change lanes autonomously, see Figure 3 , the method specifically comprises the following steps:

[0094] S301: When the speed of the vehicle is less than the expected speed, determining a target vehicle in the target lane that meets the preset conditions;

[0095] S302: Calculating the traffic congestion index of the vehicle's lane and the target lane at predetermined intervals during the observation period; wherein the target lane's traffic congestion index is calculated based on the target vehicle's traffic congestion index;

[0096] S303: Calculating the average traffic congestion index of the own lane and the average traffic congestion index of the target lane based on the traffic congestion index of the own lane and the traffic congestion index of the target lane calculated during the observation period;

[0097] S304: When the target lane provides lane change space that allows the vehicle to change lanes, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than a third preset ratio of the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, it is recommended that the vehicle change lanes to the target lane.

[0098] S305: When there is no target vehicle that meets the preset conditions in the target lane, if the average traffic congestion index of the target lane is less than a first preset ratio of the preset traffic congestion index, and the average traffic congestion index of the vehicle's lane is greater than a threshold, it is recommended that the vehicle change lanes to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane.

[0099] When the vehicle's lane is in the middle lane, the target lane includes the left lane and the right lane of the vehicle's lane. If both the left lane and the right lane meet the conditions of step S305, the vehicle can change lanes to the left lane or the right lane.

[0100] Another possible implementation method is to compare the average traffic congestion index of the left lane and the average traffic congestion index of the right lane when both the left lane and the right lane meet the conditions. When the average traffic congestion index of the left lane is less than the average traffic congestion index of the right lane, it means that the traffic condition of the left lane is better than the traffic condition of the right lane, and it is recommended that the vehicle change lanes to the left lane; otherwise, it is recommended that the vehicle change lanes to the right lane.

[0101] The autonomous lane change recommendation method provided in the embodiment of the present application recommends that the vehicle autonomously change lanes when there is no target vehicle in the target lane and if the traffic conditions in the target lane are significantly better than the expected traffic conditions, thereby making the vehicle autonomous lane change more intelligent and improving the accuracy of the vehicle autonomous lane change.

[0102] The following will introduce the working principle of recommending vehicle autonomous lane change with a specific application scenario.

[0103] In this application scenario, the vehicle is assumed to be in the middle lane of the highway. Therefore, the target lanes (i.e., the adjacent lanes) are the left and right lanes of the vehicle. In these two target lanes, target vehicles meeting the preset conditions are set to be within 150 meters of the center of the vehicle's rear axle.

[0104] See also Figure 4 ,This figure is a flow chart of the recommended method for vehicle autonomous lane changing in combination with specific application scenarios.

[0105] The method specifically comprises the following steps:

[0106] S401: When the vehicle speed is less than 50 km / h, a target vehicle meeting the preset conditions is determined in the target lane;

[0107] In this application scenario, the expected speed of the vehicle is set to 50 km / h. Therefore, when the speed of the vehicle is less than 50 km / h, the vehicle will have a lane change intention. It should be noted that the embodiment of the present application does not limit the specific value of the expected speed. The expected speed of 50 km / h is only an example.

[0108] S402: Calculate the traffic congestion index CI of the vehicle's lane and the traffic congestion index CI of the target lane at 100ms intervals within 10s; the traffic congestion index CI of the target lane is calculated based on the traffic congestion index CI of the target vehicle;

[0109] S403: Calculate the average traffic congestion index CI of the vehicle lane and the average traffic congestion index CI of the target lane based on the traffic congestion index CI of the vehicle lane and the traffic congestion index CI of the target lane calculated in 10 seconds;

[0110] Set the observation period to 10 seconds and the preset time period to 100 milliseconds, meaning that the target vehicle in the target lane is sampled every 100 milliseconds. Because there are two target lanes in this application scenario—the left lane and the right lane of the vehicle—the average traffic congestion index (CI) for the left lane and the right lane needs to be calculated separately.

[0111] Taking the left lane as an example, calculate the traffic congestion index CI of each target vehicle in the left lane at the current moment, and then calculate the average traffic congestion index CI of all target vehicles, that is, obtain the average traffic congestion index CI of the left lane at that moment, and store the single-frame sampling data at that moment. Then, after an interval of 100ms, calculate the average traffic congestion index CI of the left lane at that moment, and so on. Since the observation period is 10s and the preset time period of the interval is 100ms, 100 frames of sampling data will be obtained, that is, 100 average traffic congestion indexes CI of the left lane at different moments. Sum all the average traffic congestion indexes CI and then divide them by 100 to obtain the average traffic congestion index CI of the left lane within 10s. The principle of calculating the average traffic congestion index CI of the right lane is the same as that of the left lane, and will not be repeated here.

[0112] S404: When the risk assessment of the target lane is safe, if the current vehicle speed is less than 50 km / h, the average traffic congestion index CI of the target lane is less than the average traffic congestion index CI of the vehicle's lane, and the average traffic congestion index CI of the target lane is less than the preset traffic congestion index CI, it is recommended that the vehicle change lanes to the target lane;

[0113] S405: When the average traffic congestion index CI of the left lane is less than the average traffic congestion index CI of the right lane, it is recommended that the vehicle change lanes to the left lane; otherwise, it is recommended that the vehicle change lanes to the right lane.

[0114] The following describes how to assign specific identifiers to the average traffic congestion indexes of the vehicle's lane and the target lane, and specifically introduces the principle of recommending lane changes for the vehicle.

[0115] The average traffic congestion index for the left lane is ts_l, the average traffic congestion index for the right lane is ts_r, and the average traffic congestion index for the vehicle's lane is ts_f. The traffic state identifiers b_left_better and b_right_better for the left and right lanes are both assigned the default value of false, indicating that lane changes to the left or right lanes are not recommended.

[0116] When the vehicle's speed is lower than the expected speed, the average traffic congestion index ts_f corresponding to the vehicle's lane is greater than f_least_CI, and the vehicle has the intention to change lanes.

[0117] When the average traffic congestion index ts_l of the left lane is less than the average traffic congestion index ts_f of the vehicle's lane, and the average traffic congestion index ts_l of the left lane is less than the preset traffic congestion index f_top_CI, it is recommended that the vehicle change lanes to the left lane, that is, the traffic state identifier b_left_better of the left lane outputs true; when the average traffic congestion index ts_r of the right lane is less than the average traffic congestion index ts_f of the vehicle's lane, and the average traffic congestion index ts_r of the right lane is less than the preset traffic congestion index f_top_CI, it is recommended that the vehicle change lanes to the right lane, that is, the traffic state identifier b_right_better of the right lane outputs true.

[0118] Based on the method for recommending autonomous lane changing of a vehicle provided in the above embodiment, an embodiment of the present application further provides a device for recommending autonomous lane changing of a vehicle, which will be described in detail below with reference to the accompanying drawings.

[0119] join Figure 5 , this figure is a schematic diagram of a recommended device for vehicle autonomous lane changing provided in an embodiment of the present application.

[0120] The device 500 includes: a data processing module 501, a calculation module 502 and an output module 503, wherein:

[0121] The data processing module 501 is used to: when the speed of the vehicle is less than the expected speed, determine the target vehicle in the target lane that meets the preset conditions;

[0122] The data processing module can process the input signal according to the data structure required by the actual situation. The input signal includes a set of target vehicles that meet the preset conditions detected by the sensor. Each target vehicle is accompanied by attribute signals, such as speed, acceleration, position, etc. Assuming that the target lane is the left lane of the vehicle, the target lane and the target vehicles that meet the preset conditions can be represented as O L ={o1,o2…}, where O L represents the left lane, o1 represents the first target vehicle, and o2 represents the second target vehicle.

[0123] The calculation module 502 is configured to calculate the traffic congestion index of the vehicle lane and the traffic congestion index of the target lane at predetermined time intervals during the observation period; wherein the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle;

[0124] Calculate the average traffic congestion index of the own lane and the average traffic congestion index of the target lane based on the traffic congestion index of the own lane and the traffic congestion index of the target lane calculated during the observation period;

[0125] Output module 503 is used to: when the risk assessment result of the target lane is safe, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, recommend that the vehicle change lane to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane.

[0126] In addition, the present application also provides a recommended device for autonomous lane change of a vehicle, see Figure 6 , a schematic diagram of the recommended equipment for autonomous lane changing of vehicles.

[0127] The device 600 includes a memory 601 and a processor 602, wherein:

[0128] Memory 601, used to store relevant program codes;

[0129] The processor 602 is configured to call the program code to execute the method for recommending autonomous lane change for a vehicle as described in the above method embodiment.

[0130] It should be noted that the terms "first" and "second" used in this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this application are interchangeable under appropriate circumstances. This is merely a way of distinguishing objects with the same attributes when describing them in the embodiments of this application.

[0131] Each embodiment in this specification is described in a progressive manner. Similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units, and some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0132] The above description is merely an exemplary embodiment of the present application and does not limit the present application in any form. Any equivalent changes or modifications made to the above embodiments fall within the scope of protection of the present application.

Claims

1. A method for recommending autonomous lane change for a vehicle, characterized in that: The method comprises: When the vehicle speed is less than the expected speed, a target vehicle that meets the preset conditions is determined in the target lane; During the observation period, the traffic congestion index of the vehicle lane and the traffic congestion index of the target lane are calculated at intervals of a preset time period; wherein the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle; Calculating the average traffic congestion index of the own vehicle lane and the average traffic congestion index of the target lane according to the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane calculated during the observation period; When the risk assessment result of the target lane is safe, if the current speed of the host vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the host vehicle's lane, and the average traffic congestion index of the target lane is less than a preset traffic congestion index, it is recommended that the host vehicle change lanes to the target lane; The target lane is an adjacent lane of the host vehicle lane.

2. The method according to claim 1, characterized in that The method further comprises: When there is no target vehicle meeting the preset conditions in the target lane, if the average traffic congestion index of the target lane is less than a first preset ratio of the preset traffic congestion index, and the average traffic congestion index of the host vehicle's lane is greater than a threshold, it is recommended that the host vehicle change lanes to the target lane; wherein the first preset ratio is less than 1.

3. The method according to claim 1, characterized in that When the speed of the host vehicle is less than the expected speed, determining a target vehicle in the target lane that meets the preset conditions includes: When the speed of the host vehicle is less than a second preset ratio of the expected speed, a target vehicle meeting preset conditions is determined in the target lane; wherein the second preset ratio is less than 1.

4. The method according to claim 1, wherein The target vehicles meeting the preset conditions include: a vehicle located in front of the host vehicle and within a first preset distance from the host vehicle; A vehicle located behind the host vehicle and within a second preset distance from the host vehicle.

5. The method according to claim 1, wherein The calculation of the traffic congestion index of the vehicle lane includes: The host vehicle and the vehicle closest to the host vehicle in the host vehicle lane are taken as target vehicles in the host vehicle lane, the traffic congestion index of the target vehicle in the host vehicle lane is calculated, and then the average traffic congestion index of all target vehicles in the host vehicle lane is calculated.

6. The method according to claim 1, characterized in that The average traffic congestion index of the target lane is less than the average traffic congestion index of the host lane, which includes: The average traffic congestion index of the target lane is less than a third preset ratio of the average traffic congestion index of the host vehicle lane; wherein the third preset ratio is less than 1.

7. The method according to claim 1, characterized in that The risk assessment result of the target lane being safe includes: The lane change space provided by the target lane allows the host vehicle to change lanes.

8. The method according to any one of claims 1 to 7, characterized in that When the target lane includes a left lane of the host vehicle lane and a right lane of the host vehicle lane, the method further includes: When the average traffic congestion index of the left lane is less than the average traffic congestion index of the right lane, it is recommended that the vehicle change lanes to the left lane; otherwise, it is recommended that the vehicle change lanes to the right lane.

9. A vehicle autonomous lane change recommendation device, characterized in that: The device includes a data processing module, a calculation module and an output module: The data processing module is configured to: when the vehicle speed is less than the expected speed, determine a target vehicle in the target lane that meets preset conditions; The calculation module is configured to calculate the traffic congestion index of the vehicle lane and the traffic congestion index of the target lane at intervals of a preset time period during an observation period; wherein the traffic congestion index of the target lane is calculated based on the traffic congestion index of the target vehicle; Calculating the average traffic congestion index of the own vehicle lane and the average traffic congestion index of the target lane according to the traffic congestion index of the own vehicle lane and the traffic congestion index of the target lane calculated during the observation period; The output module is configured to: when a risk assessment result of the target lane is safe, if the current speed of the vehicle is less than the expected speed, the average traffic congestion index of the target lane is less than the average traffic congestion index of the vehicle's lane, and the average traffic congestion index of the target lane is less than the preset traffic congestion index, recommend that the vehicle change lanes to the target lane; wherein the target lane is an adjacent lane to the vehicle's lane.

10. A recommended device for autonomous lane change of a vehicle, characterized in that: The device includes a memory and a processor: The memory is used to store relevant program codes; The processor is configured to call the program code and execute the method according to any one of claims 1 to 8.

Images