A control method and device for an autonomous vehicle to cut into a lane and a vehicle-mounted terminal

Abstract

This application relates to the field of autonomous driving technology, and proposes a control method, device, vehicle terminal, and computer program product for autonomous vehicles entering lanes. The method includes: acquiring first vehicle information of the autonomous vehicle, and acquiring second vehicle information of all other vehicles existing in the target lane to which the autonomous vehicle is to enter; calculating the cost value corresponding to each gap between vehicles in the target lane based on the first and second vehicle information; wherein the cost value is used to measure the safety and efficiency of the autonomous vehicle entering the corresponding gap; selecting a target gap from the gaps where the cost value meets a set condition; and controlling the autonomous vehicle to enter the target lane through the target gap. This method, by selecting gaps where the cost value meets the condition for entry, can improve the safety and efficiency of autonomous vehicles entering lanes.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a control method, device, vehicle terminal and computer program product for an autonomous vehicle to enter a lane. Background Technology

[0002] Autonomous vehicles, also known as driverless vehicles, use lidar, cameras, and artificial intelligence algorithms to perceive their environment, make decisions, and control their movement. When autonomous vehicles are driving on the road, they sometimes need to merge into lanes with heavy traffic. In such situations, how to control the autonomous vehicle to merge into lanes safely and efficiently becomes a technical problem that needs to be considered by those skilled in the art. Summary of the Invention

[0003] In view of this, embodiments of this application provide a control method, device, vehicle terminal, and computer program product for autonomous vehicles entering lanes, which can improve the safety and efficiency of autonomous vehicles entering lanes.

[0004] The first aspect of this application provides a method for controlling an autonomous vehicle to enter a lane, including:

[0005] Obtain first vehicle information of the autonomous vehicle, and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter.

[0006] Based on the first vehicle information and the second vehicle information, the cost value corresponding to each vehicle gap existing in the target lane is calculated respectively; wherein, the cost value is used to measure the safety and efficiency of the autonomous vehicle cutting into the corresponding vehicle gap.

[0007] Select the target vehicle gap from the various vehicle gaps whose cost meets the set conditions;

[0008] Control the autonomous vehicle to cut into the target lane by passing between target vehicles.

[0009] In the technical solution of this application embodiment, after determining the target lane to be entered, the autonomous vehicle first obtains its own first vehicle information and the second vehicle information of all other vehicles existing in the target lane. Then, based on the first and second vehicle information, it calculates the cost value corresponding to each gap between vehicles in the target lane. Next, it selects the target vehicle gap whose cost value meets a set condition from among the gaps and controls the autonomous vehicle to enter the target lane through the target vehicle gap. Since the cost value calculated in the above process can be used to measure the safety and efficiency of the autonomous vehicle entering the corresponding vehicle gap, selecting vehicle gaps with satisfactory cost values ​​for entry can improve the safety and efficiency of the autonomous vehicle entering the lane.

[0010] In one implementation of this application, obtaining first vehicle information of the autonomous vehicle and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter includes:

[0011] Acquire first vehicle perception data provided by the autonomous vehicle, and acquire second vehicle perception data provided by the roadside unit;

[0012] The first vehicle perception data and the second vehicle perception data are fused together to obtain the target vehicle perception data.

[0013] From the target vehicle perception data, the information of the first vehicle and the information of the second vehicle are filtered out.

[0014] In one implementation of this application, the cost value corresponding to each vehicle gap existing in the target lane is calculated based on the first vehicle information and the second vehicle information, including:

[0015] For each vehicle gap, determine the first rear vehicle corresponding to that gap, obtain the third vehicle information of the first rear vehicle from the second vehicle information, and calculate the cost value corresponding to that vehicle gap based on the first vehicle information and the third vehicle information.

[0016] In one implementation of this application, the first vehicle information includes the first vehicle position and first vehicle speed of the autonomous vehicle, and the third vehicle information includes the second vehicle position, second vehicle speed, vehicle type, distance relative to the preceding vehicle, and speed relative to the preceding vehicle of the first rear vehicle; based on the first vehicle information and the third vehicle information, the cost corresponding to the vehicle gap is calculated, including:

[0017] The first-generation value is calculated based on the position of the first vehicle, the position of the second vehicle, the speed of the first vehicle, the speed of the second vehicle, and the vehicle category. The closer the positions of the first and second vehicles are, the closer the speeds of the first and second vehicles are, and the vehicle category is not a specified category, the smaller the first-generation value.

[0018] The second-generation value is calculated based on the relative distance to the vehicle in front and the relative speed to the vehicle in front; where the greater the relative distance to the vehicle in front and the smaller the relative speed to the vehicle in front, the smaller the second-generation value.

[0019] Calculate the generation value corresponding to the vehicle gap based on the first-generation value and the second-generation value.

[0020] In one implementation of this application, calculating the generation value corresponding to the vehicle gap based on the first generation value and the second generation value includes:

[0021] The value of the third generation is calculated based on the first and third vehicle information at multiple predicted future time points.

[0022] The value of the first generation, the value of the second generation, and the value of the third generation are calculated to obtain the generation value corresponding to the gap of the vehicle.

[0023] In one implementation of this application, selecting a target vehicle gap whose cost satisfies a set condition from among the various vehicle gaps includes:

[0024] From all the vehicle gaps, select the gap with the lowest corresponding cost as the target vehicle gap.

[0025] In one implementation of this application, controlling an autonomous vehicle to cut into a target lane through gaps between target vehicles includes:

[0026] Determine the vehicles in front and behind the target vehicles corresponding to the gap between them.

[0027] Based on the distance between the vehicle in front and the autonomous vehicle, the distance between the second rear vehicle and the autonomous vehicle, the speed of the autonomous vehicle, the speed of the vehicle in front, and the speed of the second rear vehicle, plan the target trajectory and target speed for the autonomous vehicle to enter the target lane.

[0028] Control the autonomous vehicle to cut into the gap between target vehicles in the target lane at the target speed and along the target trajectory.

[0029] A second aspect of this application provides a control device for an autonomous vehicle to enter a lane, comprising:

[0030] The vehicle information acquisition module is used to acquire the first vehicle information of the autonomous vehicle and the second vehicle information of each other vehicle present in the target lane that the autonomous vehicle is about to enter.

[0031] The cost value calculation module is used to calculate the cost value of each vehicle gap existing in the target lane based on the first vehicle information and the second vehicle information; wherein, the cost value is used to measure the safety and efficiency of the autonomous vehicle cutting into the corresponding vehicle gap.

[0032] The vehicle gap selection module is used to select the target vehicle gap whose cost meets the set conditions from the various vehicle gaps.

[0033] The lane entry control module is used to control the autonomous vehicle to enter the target lane by passing through gaps between target vehicles.

[0034] A third aspect of this application provides an in-vehicle terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the control method for an autonomous vehicle to enter a lane as provided in the first aspect of this application.

[0035] A fourth aspect of this application provides a computer program product that, when run on an in-vehicle terminal, causes the in-vehicle terminal to execute the lane-changing control method for an autonomous vehicle provided in the first aspect of this application.

[0036] The fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the lane-changing control method for an autonomous vehicle as provided in the first aspect of this application.

[0037] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0038] Figure 1 This is a flowchart of a control method for an autonomous vehicle to enter a lane, provided in an embodiment of this application;

[0039] Figure 2 This is an operational schematic diagram of an autonomous vehicle selecting the optimal vehicle gap to enter the lane based on the cost value, according to an embodiment of this application.

[0040] Figure 3 This is a schematic diagram of the structure of a control device for an autonomous vehicle to enter a lane, provided in an embodiment of this application;

[0041] Figure 4 This is a schematic diagram of an in-vehicle terminal provided in an embodiment of this application. Detailed Implementation

[0042] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail. Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0043] With the development of autonomous driving technology, the application of autonomous vehicles is becoming increasingly widespread. When autonomous vehicles are driving on the road, they sometimes need to merge into lanes with high traffic volume. Existing vehicle control algorithms struggle to balance the safety and efficiency of autonomous vehicles merging into high-traffic lanes. Therefore, this application provides a control method, device, vehicle terminal, and computer program product for autonomous vehicles merging into lanes. By selecting vehicle gaps that meet certain cost conditions for merging, the safety and efficiency of autonomous vehicles merging into lanes can be improved. For more specific technical implementation details of this application's embodiments, please refer to the method embodiments described below.

[0044] Please see Figure 1 This application illustrates a control method for an autonomous vehicle to enter a lane, comprising:

[0045] 101. Obtain the first vehicle information of the autonomous vehicle, and obtain the second vehicle information of each other vehicle present in the target lane that the autonomous vehicle is about to enter.

[0046] It should be understood that the implementing entity of the various method embodiments of this application can be the on-board terminal of an autonomous vehicle. Autonomous vehicles, using devices such as lidar and cameras, can perceive vehicle information of various vehicles in the surrounding environment, such as the position, speed, type, distance, and speed of each surrounding vehicle and the autonomous vehicle itself.

[0047] When an autonomous vehicle needs to change lanes, it determines the target lane to enter. From the perceived information of surrounding vehicles, it selects the vehicle's information (referred to as first vehicle information) and the information of all other vehicles in the target lane (referred to as second vehicle information). Considering the target lane may be long and the autonomous vehicle needs to enter the nearest available lane, it can obtain the vehicle information of a portion of the vehicles within a certain distance in front of and behind the autonomous vehicle as second vehicle information to reduce unnecessary computation in subsequent processes. For example, suppose the autonomous vehicle needs to enter lane 1, and there are currently 50 vehicles in lane 1, but only 10 of them are within 100 meters of the autonomous vehicle. In this case, only the vehicle information of these 10 vehicles needs to be obtained as second vehicle information for subsequent calculations.

[0048] Because the perception range of autonomous vehicles is relatively limited, and there may be obstructions between vehicles in the target lane, the vehicle information obtained through autonomous vehicle perception may contain certain errors. This can lead to deviations in the subsequent calculation of the vehicle gap value. To address the issue of errors in the perception data of autonomous vehicles, perception data from roadside units can be introduced for data fusion. By utilizing vehicle-road cooperative data, a wider range and higher accuracy of vehicle information in the target lane can be obtained. The specific operation method is described below.

[0049] In one implementation of this application, obtaining first vehicle information of the autonomous vehicle and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter includes:

[0050] (1) Acquire first vehicle perception data provided by the autonomous vehicle and acquire second vehicle perception data provided by the roadside unit;

[0051] (2) Perform data fusion processing on the first vehicle perception data and the second vehicle perception data to obtain the target vehicle perception data;

[0052] (3) Filter out the first vehicle information and the second vehicle information from the target vehicle perception data.

[0053] Autonomous vehicles can perceive and acquire data such as the position, speed, and type of various vehicles in their surrounding environment; this data is denoted as the first vehicle perception data. Similarly, roadside units can also perceive and acquire data such as the position, speed, and type of various vehicles in the surrounding environment; this data is denoted as the second vehicle perception data. The roadside units can transmit the second vehicle perception data to the autonomous vehicle's onboard terminal via communication technologies such as V2X. After receiving the second vehicle perception data, the onboard terminal performs data fusion processing on the first and second vehicle perception data to obtain the target vehicle perception data. During data fusion, the first and second vehicle perception data are first mapped to the same coordinate system, and then the vehicle information in the two sets of perception data is matched and fused using matching algorithms such as overlap. Finally, the first and second vehicle information are filtered out from the target vehicle perception data. The target vehicle perception data contains vehicle information of all vehicles in the surrounding environment of the autonomous vehicle; the vehicle information of the autonomous vehicle itself needs to be filtered out as the first vehicle information, and the vehicle information of a portion of vehicles within a certain distance in front of and behind the autonomous vehicle in the target lane needs to be filtered out as the second vehicle information. As a result of vehicle-road cooperative perception, target vehicle perception data enables more accurate perception, localization, and behavior prediction of vehicles within the target lane, thereby effectively improving the accuracy of subsequent calculations of vehicle gap cost values. Furthermore, after obtaining target vehicle perception data, the onboard terminal can utilize deep learning models combined with high-precision maps to predict the behavioral trajectories of each vehicle based on the target vehicle perception data. This yields vehicle information for multiple future time points, which can be considered in subsequent calculations of vehicle gap cost values. For details, please refer to the following text.

[0054] 102. Based on the first vehicle information and the second vehicle information, calculate the cost value corresponding to each vehicle gap existing in the target lane;

[0055] After obtaining the first and second vehicle information, the onboard terminal calculates the cost value of each gap in the target lane based on the first and second vehicle information. This cost value measures the safety and efficiency of the autonomous vehicle navigating the corresponding gap. Generally, a lower cost value indicates better safety and efficiency for the autonomous vehicle to enter that gap, and vice versa. Specifically, by analyzing the second vehicle information, it's possible to determine which gaps exist in the target lane and the corresponding information about the vehicles ahead and behind each gap. The first vehicle information provides information such as the autonomous vehicle's position and speed. Combining this with the position and speed information of the vehicles ahead and behind each gap allows for an assessment of the safety and efficiency of the autonomous vehicle entering each gap, thus calculating the cost value for each gap. For example, if the speed of the vehicle behind a gap A is similar to that of the autonomous vehicle, then entering gap A is relatively safe and convenient, and therefore the calculated cost value for gap A is low. For example, suppose the speed of the vehicle behind a gap B differs significantly from that of the autonomous vehicle. In this case, it would be difficult and unsafe for the autonomous vehicle to cut into gap B, thus resulting in a higher calculated cost for gap B. This principle can be applied to other gaps as well. Alternatively, gaps where the position of the vehicle behind the autonomous vehicle is closer to its position can be prioritized. These gaps can have a lower cost in the calculation, but the cost needs to be calculated considering various factors, and the closest gap may not necessarily have the lowest cost. In practice, a cost calculation model (cost) can be set up. The vehicle information of the autonomous vehicle and the vehicle information of the vehicles behind the corresponding gaps can be substituted into this model, and the cost corresponding to the gap can be calculated using the model's pre-defined calculation method.

[0056] In one implementation of this application, the cost value corresponding to each vehicle gap existing in the target lane is calculated based on the first vehicle information and the second vehicle information, including:

[0057] For each vehicle gap, determine the first rear vehicle corresponding to that gap, obtain the third vehicle information of the first rear vehicle from the second vehicle information, and calculate the cost value corresponding to that vehicle gap based on the first vehicle information and the third vehicle information.

[0058] When assessing whether a gap between vehicles is convenient for an autonomous vehicle to enter, it is generally necessary to consider the relevant vehicle information of the vehicles behind that gap. Therefore, when calculating the cost of a gap, the corresponding vehicles behind are first identified, denoted as the first rear vehicle, and the vehicle information of the first rear vehicle is found from the second vehicle information, denoted as the third vehicle information. Then, the position and speed information of the autonomous vehicle are obtained through the first vehicle information, and combined with the position and speed information of the first rear vehicle contained in the third vehicle information, the cost of the gap can be calculated. For example, the first and third vehicle information can be substituted into the aforementioned cost calculation model (cost), and the cost of the gap can be calculated according to the algorithm set in the model.

[0059] In one implementation of this application, the first vehicle information includes the first vehicle position and first vehicle speed of the autonomous vehicle, and the third vehicle information includes the second vehicle position, second vehicle speed, vehicle type, distance relative to the preceding vehicle, and speed relative to the preceding vehicle of the first rear vehicle; based on the first vehicle information and the third vehicle information, the cost corresponding to the vehicle gap is calculated, including:

[0060] (1) Calculate the first generation value based on the position of the first vehicle, the position of the second vehicle, the speed of the first vehicle, the speed of the second vehicle, and the vehicle category; wherein, the closer the positions of the first and second vehicles are, the closer the speeds of the first and second vehicles are, and the vehicle category is not a specified category, the smaller the first generation value is.

[0061] (2) Calculate the second-generation value based on the relative distance to the vehicle in front and the relative speed to the vehicle in front; where the greater the relative distance to the vehicle in front and the smaller the relative speed to the vehicle in front, the smaller the second-generation value.

[0062] (3) Calculate the generation value corresponding to the vehicle gap based on the first generation value and the second generation value.

[0063] When calculating the cost of a vehicle gap, the vehicle information considered can include the first vehicle position and first vehicle speed of the autonomous vehicle, and the second vehicle position, second vehicle speed, vehicle type, distance from the vehicle in front, and speed of the vehicle behind. The first-generation value can be calculated based on the vehicle position, vehicle speed, and vehicle type, while the second-generation value can be calculated based on the distance from and speed of the vehicle in front. The cost of the vehicle gap can be obtained by calculating both the first-generation and second-generation values; for example, it can be a weighted sum of the first-generation value and the second-generation cost value.

[0064] The first-generation value can be represented by I(s,v,c), where s represents the position of the following vehicle relative to the autonomous vehicle, calculated from the positions of the first and second vehicles; v represents the speed of the following vehicle relative to the autonomous vehicle, calculated from the speeds of the first and second vehicles; and c represents the vehicle category of the following vehicle, such as a small car, a large truck, a bus, or an ambulance. If the positions and speeds of the first and second vehicles are close, and the following vehicle is not a designated category like a large truck, bus, or ambulance (which should not compete for road space), then the autonomous vehicle can safely and efficiently wedge into the gap, resulting in a smaller first-generation value. Conversely, if the positions and speeds of the first and second vehicles are far apart, or the following vehicle is a designated category like a large truck, bus, or ambulance, then the autonomous vehicle will have difficulty safely and quickly wedging into the gap, resulting in a larger first-generation value.

[0065] The second-generation value can be represented by I(ds,dv), where ds represents the distance between the following vehicle and the vehicle in front, i.e., the distance between the following vehicle and the vehicle in front, and dv represents the speed of the following vehicle relative to the vehicle in front, i.e., the speed difference between the two vehicles. If the relative distance ds is larger and the relative speed dv is smaller, it means that the corresponding vehicle gap will maintain a large cut-in space for a longer period of time. In this case, the autonomous vehicle can safely and efficiently cut into the gap, and therefore the calculated second-generation value is smaller. Conversely, if the relative distance ds is smaller or the relative speed dv is larger, it means that the corresponding vehicle gap has a smaller cut-in space or a shorter duration of cut-in space. In this case, it is difficult for the autonomous vehicle to safely and efficiently cut into the gap, and therefore the calculated second-generation value is larger.

[0066] The cost corresponding to the vehicle gap can be the weighted sum of the first generation value and the second cost value. For example, we can let cost = Q(s,v,c,ds,dv) = I(s,v,c) + J(ds,dv).

[0067] In one implementation of this application, calculating the generation value corresponding to the vehicle gap based on the first generation value and the second generation value includes:

[0068] (1) Calculate the value of the third generation based on the first and third vehicle information at multiple future time points predicted;

[0069] (2) Calculate the sum of the first generation value, the second generation value and the third generation value to obtain the generation value corresponding to the vehicle gap.

[0070] Referring to the preceding description, the vehicle-mounted terminal can predict the behavioral trajectories of each vehicle based on the target vehicle's perception data, thereby obtaining vehicle information for each vehicle at multiple future time points. This predicted vehicle information can serve as a supplementary factor in calculating the cost of vehicle gaps, further improving the accuracy of the calculation. When calculating the cost of a particular vehicle gap, in addition to calculating the first and second generation values ​​described above, a third generation value can be calculated based on the predicted vehicle information. Then, the sum of the first, second, and third generation values ​​is calculated as the cost of that vehicle gap.

[0071] The third-generation value can be represented by H(t), where t represents the information of the first and third vehicles at multiple future time points. For example, assuming data for 100 future time points is predicted, then t includes the position and speed of the autonomous vehicle at those 100 time points, as well as information such as the position and speed, vehicle category, relative distance to the vehicle in front, and relative speed to the vehicle gap at those 100 time points. The essence of the third-generation cost value is to supplement the first and second-generation values ​​based on the future prediction results of the vehicle information, thereby improving the accuracy of calculating the cost corresponding to the vehicle gap. Similarly, if at multiple future time points, the closer the position and speed of the vehicle behind is to the autonomous vehicle, the less likely the vehicle behind is a specific category vehicle, the greater the distance between the vehicle behind and the vehicle in front, and the smaller the speed difference between the vehicle behind and the vehicle in front, the smaller the calculated third-generation value; conversely, the larger the calculated third-generation value, the more likely it is to be.

[0072] The cost corresponding to the vehicle gap can be the sum of the first-generation value, the second-generation value, and the third-generation value. For example, it can be set as cost = Q(s,v,c,ds,dv,t) = I(s,v,c) + J(ds,dv) + H(t). There are many specific formulas for calculating I(s,v,c), J(ds,dv), and H(t). It is sufficient to design a calculation formula that satisfies the above-mentioned calculation rules for the magnitude of the cost. This application does not impose any limitations on the specific calculation formula used.

[0073] 103. Select the target vehicle gap from the various vehicle gaps whose corresponding cost value meets the set conditions;

[0074] Following the method described in step 102, the cost value corresponding to each vehicle gap existing in the target lane can be calculated. Then, from these vehicle gaps, the vehicle gap whose cost value meets the set conditions can be selected as the target vehicle gap. For example, the vehicle gaps can be sorted in ascending order of cost value, and a vehicle gap with the lowest cost value can be selected as the target vehicle gap.

[0075] In one implementation of this application, selecting a target vehicle gap whose cost satisfies a set condition from among the various vehicle gaps includes:

[0076] From all the vehicle gaps, select the gap with the lowest corresponding cost as the target vehicle gap.

[0077] Generally speaking, the smaller the cost value of a certain vehicle gap, the better the safety and efficiency of an autonomous vehicle entering that gap. Therefore, the vehicle gap with the smallest cost value among all vehicle gaps can be regarded as the optimal vehicle gap, that is, the target vehicle gap.

[0078] 104. Control the autonomous vehicle to cut into the target lane by passing through the gaps between target vehicles.

[0079] After determining the gap between the target vehicles, the autonomous vehicle is controlled to cut into the target lane through the gap. The onboard terminal can automatically plan a safe trajectory to cut into the gap based on information such as the position and speed of the vehicles in front and behind the target vehicle gap, and the position and speed of the autonomous vehicle. Then, the autonomous vehicle can be controlled to cut into the gap of the target vehicle in the target lane along the safe trajectory.

[0080] In one implementation of this application, controlling an autonomous vehicle to cut into a target lane through gaps between target vehicles includes:

[0081] (1) Determine the vehicles in front and behind the target vehicles corresponding to the gap between them;

[0082] (2) Based on the distance between the vehicle in front and the autonomous vehicle, the distance between the second rear vehicle and the autonomous vehicle, the speed of the autonomous vehicle, the speed of the vehicle in front and the speed of the second rear vehicle, plan the target trajectory and target speed for the autonomous vehicle to enter the target lane.

[0083] (3) Control the autonomous vehicle to cut into the gap between target vehicles in the target lane at the target speed and along the target trajectory.

[0084] First, the vehicles in front and behind the target vehicle gap are identified. To distinguish them from the first rear vehicle described earlier, the vehicles behind the target vehicle gap are designated as the second rear vehicle. Then, based on information such as the distance between the vehicle in front and the autonomous vehicle, the distance between the second rear vehicle and the autonomous vehicle, the speed of the autonomous vehicle, the speed of the vehicle in front, and the speed of the second rear vehicle, the target trajectory and target speed for the autonomous vehicle to enter the target lane are planned. Specifically, based on the distances between the vehicle in front and the autonomous vehicle, and the distances between the second rear vehicle and the autonomous vehicle, the location for generating the curve to enter the target lane can be planned, thus obtaining the target trajectory. Based on the speeds of the autonomous vehicle, the vehicle in front, and the second rear vehicle, a corresponding speed value can be assigned to each trajectory point in the generated target trajectory, thus obtaining the target speed during the journey along the target trajectory. Finally, the autonomous vehicle is controlled to travel at the target speed along the target trajectory, enabling it to reach the planned target position at the planned speed, thereby safely and efficiently completing the lane-entry operation.

[0085] As an example, Figure 2 This is a schematic diagram illustrating an operation of an autonomous vehicle selecting the optimal vehicle gap to enter the lane based on cost, according to an embodiment of this application. Figure 2 In this scenario, an autonomous vehicle is traveling in lane 2 and needs to merge into lane 1. Within the defined area of ​​lane 1, there are, in order from front to back, a car 1, a truck 2, a car 3, and an ambulance 4. Correspondingly, there are vehicle gaps: gap 1 (car 1 in front, truck 2 behind), gap 2 (truck 2 in front, car 3 behind), and gap 3 (car 3 in front, ambulance 4 behind). The autonomous vehicle first acquires its own vehicle information, such as its position and speed, and also acquires the vehicle information of car 1, truck 2, car 3, and ambulance 4, including their positions, speeds, vehicle types, distances from the vehicle in front, and speeds relative to the vehicle in front. This vehicle information can include information from the current time point and predicted information from multiple future time points. Then, based on the acquired vehicle information, the cost of each vehicle gap is calculated using the method described above. For example, the cost of vehicle gap 1 can be calculated using the vehicle information of the autonomous vehicle and the truck 2, using the calculation model cost = Q(s,v,c,ds,dv,t) described above, and so on. Next, the vehicle gap with the lowest cost is selected as the optimal vehicle gap. Figure 2In the process, since vehicle gap 2 is closest to the position of the autonomous vehicle, and the position and speed of the vehicle behind vehicle gap 2, namely car 3, are also close to those of the autonomous vehicle, and car 3 is not a designated type of vehicle such as a truck or ambulance, while truck 2 is farther away from car 3 and their speeds are very close, vehicle gap 2 has the lowest cost and is therefore determined as the optimal vehicle gap. Finally, based on the positions and speeds of truck 2 and car 3, as well as the position and speed of the autonomous vehicle, the target trajectory and target speed for the autonomous vehicle to enter vehicle gap 2 are planned, and the autonomous vehicle is controlled to enter vehicle gap 2 at the target speed and along the target trajectory, thus completing the operation of entering lane 1.

[0086] In the technical solution of this application embodiment, after determining the target lane to be entered, the autonomous vehicle first obtains its own first vehicle information and the second vehicle information of all other vehicles existing in the target lane. Then, based on the first and second vehicle information, it calculates the cost value corresponding to each gap between vehicles in the target lane. Next, it selects the target vehicle gap whose cost value meets a set condition from among the gaps and controls the autonomous vehicle to enter the target lane through the target vehicle gap. Since the cost value calculated in the above process can be used to measure the safety and efficiency of the autonomous vehicle entering the corresponding gap, selecting the target vehicle gap that meets the cost value condition for entry can improve the safety and efficiency of the autonomous vehicle entering the lane.

[0087] In summary, this application proposes a control method for autonomous vehicles to enter lanes. It utilizes vehicle-road cooperative data to provide autonomous vehicles with a wider range and higher accuracy of lane perception information, calculates the optimal vehicle gap on the target lane based on an internal model, and plans the optimal vehicle speed and entry trajectory to ensure accurate entry into the optimal vehicle gap at the corresponding position, thereby improving the safety and efficiency of autonomous vehicles entering lanes.

[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0089] The above mainly describes a control method for an autonomous vehicle to enter a lane. The following will describe a control device for an autonomous vehicle to enter a lane.

[0090] Please see Figure 3 One embodiment of a control device for an autonomous vehicle to enter a lane, as described in this application, includes:

[0091] The vehicle information acquisition module 301 is used to acquire first vehicle information of the autonomous vehicle and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter.

[0092] The cost value calculation module 302 is used to calculate the cost value corresponding to each vehicle gap existing in the target lane based on the first vehicle information and the second vehicle information; wherein, the cost value is used to measure the safety and efficiency of the corresponding vehicle gap being cut into by an autonomous vehicle.

[0093] The vehicle gap selection module 303 is used to select the target vehicle gap whose cost meets the set conditions from each vehicle gap.

[0094] Lane entry control module 304 is used to control the autonomous vehicle to enter the target lane by passing through the gap between the target vehicles.

[0095] In one implementation of this application, the vehicle information acquisition module includes:

[0096] The perception data acquisition unit is used to acquire first vehicle perception data provided by the autonomous vehicle and second vehicle perception data provided by the roadside unit.

[0097] The data fusion unit is used to perform data fusion processing on the first vehicle perception data and the second vehicle perception data to obtain the target vehicle perception data.

[0098] The vehicle information filtering unit is used to filter out the first vehicle information and the second vehicle information from the target vehicle perception data.

[0099] In one implementation of this application, the cost calculation module includes:

[0100] The cost value calculation unit is used to determine the first rear vehicle corresponding to each vehicle gap in each vehicle gap, obtain the third vehicle information of the first rear vehicle from the second vehicle information, and calculate the cost value corresponding to the vehicle gap based on the first vehicle information and the third vehicle information.

[0101] In one implementation of this application, the first vehicle information includes the first vehicle position and first vehicle speed of the autonomous vehicle; the third vehicle information includes the second vehicle position, second vehicle speed, vehicle type, distance relative to the preceding vehicle, and speed relative to the preceding vehicle of the first rear vehicle; the cost calculation unit includes:

[0102] The first-generation value calculation subunit is used to calculate the first-generation value based on the first vehicle position, the second vehicle position, the first vehicle speed, the second vehicle speed, and the vehicle category; wherein, if the first vehicle position and the second vehicle position are closer, the first vehicle speed and the second vehicle speed are closer, and the vehicle category is not a specified category, the first-generation value is smaller.

[0103] The second-generation value calculation subunit is used to calculate the second-generation value based on the relative distance to the vehicle in front and the relative speed to the vehicle in front; wherein, the larger the relative distance to the vehicle in front and the smaller the relative speed to the vehicle in front, the smaller the second-generation value.

[0104] The total value calculation subunit is used to calculate the value corresponding to the vehicle gap based on the first-generation value and the second-generation value.

[0105] In one implementation of this application, the total agency value calculation subunit includes:

[0106] The third-generation value calculation subunit is used to calculate the third-generation value based on the first vehicle information and the third vehicle information at multiple predicted future time points.

[0107] The value summation subunit is used to calculate the sum of the first-generation value, the second-generation value, and the third-generation value to obtain the value corresponding to the vehicle gap.

[0108] In one implementation of this application, the vehicle clearance selection module includes:

[0109] The vehicle gap selection unit is used to select the vehicle gap with the lowest cost from all vehicle gaps as the target vehicle gap.

[0110] In one implementation of this application, the lane cut-in control module includes:

[0111] The vehicle determination unit is used to determine the vehicle in front and the vehicle behind the target vehicle corresponding to the gap between them.

[0112] The planning unit is used to plan the target trajectory and target speed for the autonomous vehicle to enter the target lane based on the distance between the vehicle in front and the autonomous vehicle, the distance between the second rear vehicle and the autonomous vehicle, the speed of the autonomous vehicle, the speed of the vehicle in front, and the speed of the second rear vehicle.

[0113] The cut-in control unit is used to control the autonomous vehicle to cut into the gap between target vehicles in the target lane at the target speed and along the target trajectory.

[0114] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a control method for an autonomous vehicle to enter a lane as described in any of the above embodiments.

[0115] This application also provides a computer program product that, when run on an in-vehicle terminal, causes the in-vehicle terminal to execute the control method for an autonomous vehicle to enter a lane as described in any of the above embodiments.

[0116] Figure 4 This is a schematic diagram of an in-vehicle terminal provided in one embodiment of this application. For example... Figure 4 As shown, the vehicle terminal 4 in this embodiment includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps in the embodiments of the control methods for autonomous vehicles entering lanes described above, for example... Figure 1 Steps 101 to 104 are shown. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of modules 301 to 304 are shown.

[0117] The computer program 42 can be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 42 in the vehicle terminal 4.

[0118] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0119] The memory 41 can be an internal storage unit of the vehicle terminal 4, such as a hard drive or memory of the vehicle terminal 4. The memory 41 can also be an external storage device of the vehicle terminal 4, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the vehicle terminal 4. Furthermore, the memory 41 can include both internal storage units and external storage devices of the vehicle terminal 4. The memory 41 is used to store the computer program and other programs and data required by the vehicle terminal. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0120] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0121] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0122] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0123] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0126] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0127] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0128] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A control method for an autonomous vehicle to enter a lane, characterized in that, include: Obtain first vehicle information of the autonomous vehicle, and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter; Based on the first vehicle information and the second vehicle information, the cost value corresponding to each vehicle gap existing in the target lane is calculated respectively; wherein, the cost value is used to measure the safety and efficiency of the autonomous vehicle cutting into the corresponding vehicle gap; Select the target vehicle gap whose cost value meets the set conditions from the various vehicle gaps; The autonomous vehicle is controlled to cut into the target lane by passing through the gaps between the target vehicles.

2. The method as described in claim 1, characterized in that, The acquisition of first vehicle information of the autonomous vehicle and second vehicle information of each other vehicle present in the target lane to which the autonomous vehicle is to enter include: Acquire first vehicle perception data provided by the autonomous vehicle, and acquire second vehicle perception data provided by the roadside unit; The first vehicle perception data and the second vehicle perception data are fused together to obtain the target vehicle perception data. The first vehicle information and the second vehicle information are filtered out from the target vehicle perception data.

3. The method as described in claim 1, characterized in that, The step of calculating the cost value corresponding to each vehicle gap existing in the target lane based on the first vehicle information and the second vehicle information includes: For each of the vehicle gaps, determine the first rear vehicle corresponding to the vehicle gap, obtain the third vehicle information of the first rear vehicle from the second vehicle information, and calculate the cost value corresponding to the vehicle gap based on the first vehicle information and the third vehicle information.

4. The method as described in claim 3, characterized in that, The first vehicle information includes the first vehicle position and the first vehicle speed of the autonomous vehicle, and the third vehicle information includes the second vehicle position, the second vehicle speed, the vehicle type, the distance to the vehicle in front, and the speed to the vehicle in front of the first vehicle behind. The step of calculating the cost value corresponding to the vehicle gap based on the first vehicle information and the third vehicle information includes: A first-generation value is calculated based on the first vehicle's position, the second vehicle's position, the first vehicle's speed, the second vehicle's speed, and the vehicle's category; wherein, the closer the first vehicle's position and the second vehicle's position and speed are, and the vehicle's category is not a specified category, the smaller the first-generation value is. The second-generation value is calculated based on the relative distance to the vehicle in front and the relative speed to the vehicle in front; wherein, the larger the relative distance to the vehicle in front and the smaller the relative speed to the vehicle in front, the smaller the second-generation value. The generation value corresponding to the vehicle gap is calculated based on the first generation value and the second generation value.

5. The method as described in claim 4, characterized in that, The step of calculating the generation value corresponding to the vehicle gap based on the first generation value and the second generation value includes: The third-generation value is calculated based on the first vehicle information and the third vehicle information at multiple predicted future time points. The value of the first generation, the value of the second generation, and the value of the third generation are calculated to obtain the generation value corresponding to the vehicle gap.

6. The method as described in claim 5, characterized in that, Selecting the target vehicle gap whose cost value meets the set conditions from the various vehicle gaps includes: From the various vehicle gaps, select the vehicle gap with the lowest corresponding cost value as the target vehicle gap.

7. The method according to any one of claims 1 to 6, characterized in that, The control of the autonomous vehicle to cut into the target lane through the gaps between the target vehicles includes: Determine the vehicle in front and the vehicle behind the target vehicle corresponding to the gap between them. Based on the distance between the vehicle in front and the autonomous vehicle, the distance between the second vehicle behind and the autonomous vehicle, the speed of the autonomous vehicle, the speed of the vehicle in front, and the speed of the second vehicle behind, the target trajectory and target speed of the autonomous vehicle entering the target lane are planned. The autonomous vehicle is controlled to enter the gap between target vehicles in the target lane at the target speed and along the target trajectory.

8. A control device for an autonomous vehicle to enter a lane, characterized in that, include: The vehicle information acquisition module is used to acquire first vehicle information of the autonomous vehicle and second vehicle information of each other vehicle present in the target lane into which the autonomous vehicle is to enter. The cost value calculation module is used to calculate the cost value corresponding to each vehicle gap existing in the target lane based on the first vehicle information and the second vehicle information; wherein, the cost value is used to measure the safety and efficiency of the autonomous vehicle cutting into the corresponding vehicle gap; The vehicle gap selection module is used to select the target vehicle gap whose cost value meets the set conditions from the various vehicle gaps. The lane entry control module is used to control the autonomous vehicle to enter the target lane by passing through the gaps between the target vehicles.

9. A vehicle-mounted terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the control method for an autonomous vehicle to enter a lane as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, When the computer program product is run on the vehicle terminal, the vehicle terminal performs the control method for an autonomous vehicle to enter a lane as described in any one of claims 1 to 7.

Images