Autonomous vehicles and their control methods and devices

Abstract

This invention discloses an autonomous vehicle and its control method and device. The method includes: acquiring driving parameters and distance parameters of the autonomous vehicle; determining lane-changing parameters of the autonomous vehicle based on the driving parameters; determining a lane-changing result based on the distance parameters and lane-changing parameters; and controlling the lane-changing behavior of the autonomous vehicle based on the lane-changing result. This invention solves the technical problem of low accuracy in lane-changing decisions of autonomous driving systems in related technologies.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicles, and more specifically, to an autonomous driving vehicle and its control method and control device. Background Technology

[0002] Currently, the installation rate of autonomous driving functions in new vehicles is increasing, and the functionality of these functions is becoming more comprehensive. Lane change decision-making is a crucial step in using autonomous driving functions. The process involves analyzing the user's driving behavior to determine their lane change intentions, thus supporting the vehicle's lane change decision. However, the accuracy of lane change intention determination in related technologies is not high, leading to errors in lane change decisions and potentially posing safety hazards when users engage with autonomous driving functions.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides an autonomous vehicle and its control method and device to at least solve the technical problem of low accuracy in lane-changing decisions of autonomous driving systems in related technologies.

[0005] According to one aspect of the present invention, a control method for an autonomous vehicle is provided, comprising: acquiring driving parameters and distance parameters of the autonomous vehicle, wherein the distance parameters are used to represent the distance between the autonomous vehicle and a first vehicle, the first vehicle being a vehicle traveling in the current lane and / or an adjacent lane of the current lane where the autonomous vehicle is located; determining lane-changing parameters of the autonomous vehicle based on the driving parameters, wherein the lane-changing parameters are used to represent the degree of need for the autonomous vehicle to change lanes; determining a lane-changing result based on the distance parameters and the lane-changing parameters, wherein the lane-changing result is used to indicate whether to control the autonomous vehicle to change lanes; and controlling the lane-changing behavior of the autonomous vehicle based on the lane-changing result.

[0006] Optionally, determining the lane-changing result based on the distance parameter and the lane-changing parameter includes: determining the distance ambiguity corresponding to the distance parameter according to a first preset relationship, wherein the first preset relationship is used to represent the correspondence between the distance parameter and the distance ambiguity; determining the lane-changing ambiguity corresponding to the lane-changing parameter according to a second preset relationship, wherein the second preset relationship is used to represent the correspondence between the lane-changing parameter and the lane-changing ambiguity; and processing the distance ambiguity and the lane-changing ambiguity based on preset ambiguity rules to obtain the lane-changing result, wherein the preset ambiguity rules are used to represent the correspondence between the distance ambiguity, the lane-changing ambiguity, and the lane-changing result.

[0007] Optionally, the method further includes: simulating a driving scenario of an autonomous vehicle in a simulation scenario; setting preset driving parameters and preset distance parameters for the autonomous vehicle in the driving scenario; generating a simulated driving scenario of the autonomous vehicle based on the preset driving parameters and preset distance parameters; determining preset lane-changing behavior corresponding to the simulated driving scenario; and generating preset fuzzy rules based on the preset driving parameters, preset distance parameters, and preset lane-changing behavior.

[0008] Optionally, determining lane-changing parameters for the autonomous vehicle based on driving parameters includes: obtaining the expected speed of the autonomous vehicle, wherein the expected speed represents the speed that the autonomous vehicle is expected to reach at the current time; determining the current speed, the number of acceleration commands, and the number of deceleration commands of the autonomous vehicle based on the driving parameters, wherein the current speed is the speed that the autonomous vehicle reaches at the current time, the number of acceleration commands represents the number of times the autonomous vehicle accelerates within a preset time period, and the number of deceleration commands represents the number of times the autonomous vehicle decelerates within a preset time period; and determining the lane-changing parameters based on the expected speed, the current speed, the number of acceleration commands, and the number of deceleration commands.

[0009] Optionally, determining the lane-changing parameters based on the expected speed, current speed, number of acceleration commands, and number of deceleration commands includes: determining speed parameters based on the expected speed and current speed; obtaining a first product of the speed parameters and a first weighting coefficient; determining acceleration parameters based on the number of acceleration commands and the number of deceleration commands; obtaining a second product of the acceleration parameters and a second weighting coefficient, wherein the sum of the second weighting coefficient and the first weighting coefficient is a preset value; and determining the sum of the first product and the second product as the lane-changing parameters.

[0010] Optionally, determining the speed parameter based on the expected speed and the current speed includes: obtaining a first difference between the expected speed and the current speed; obtaining a first ratio between the first difference and the expected speed; and determining the product of the first ratio and the sampling period as the speed parameter, wherein the sampling period is a pre-set period for sampling the driving parameters of the autonomous vehicle.

[0011] Optionally, the acceleration parameter is determined based on the number of acceleration commands and the number of deceleration commands, including: obtaining a first sum of the number of acceleration commands and the number of deceleration commands; and determining the ratio of the number of deceleration commands to the first sum as the acceleration parameter.

[0012] Optionally, the method further includes: when the autonomous vehicle is driven by a human, acquiring the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior of the autonomous vehicle; and adjusting them according to the ratio of the first weight coefficient and the second weight system of the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior.

[0013] According to another aspect of the present invention, a control device for an autonomous vehicle is also provided, comprising: an acquisition module, configured to acquire driving parameters and distance parameters of the autonomous vehicle, wherein the distance parameters represent the distance between the autonomous vehicle and a first vehicle, the first vehicle being a vehicle in the current lane and / or the lane to be changed by the autonomous vehicle; a first determination module, configured to determine lane-changing parameters of the autonomous vehicle based on the driving parameters, wherein the lane-changing parameters represent the degree of dissatisfaction with the autonomous vehicle changing lanes; a second determination module, configured to determine a lane-changing result based on the distance parameters and the lane-changing parameters, wherein the lane-changing result represents whether to control the autonomous vehicle to change lanes; and a control module, configured to control the lane-changing behavior of the autonomous vehicle based on the lane-changing result.

[0014] According to another aspect of the present invention, an autonomous vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the control method of the autonomous vehicle according to any one of the above embodiments.

[0015] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute any of the vehicle control methods in the above embodiments.

[0016] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the vehicle control method of any one of the above embodiments.

[0017] In this embodiment of the invention, after acquiring the driving parameters and distance parameters of the autonomous vehicle, lane-changing parameters of the autonomous vehicle are further determined based on the driving parameters, and the lane-changing result is further determined based on the distance parameters and lane-changing parameters. The lane-changing behavior of the autonomous vehicle is then controlled based on the lane-changing result. It is readily apparent that by acquiring the driving parameters and distance parameters of the autonomous vehicle, determining the lane-changing parameters based on the driving parameters, and further determining the lane-changing result based on the distance parameters and lane-changing parameters, the lane-changing behavior of the autonomous vehicle is controlled based on the lane-changing result. This allows for the use of virtual driving test analysis parameters and the analysis of lane-changing fuzzy inference rules to build a model. This achieves the technical effect of making the lane-changing behavior of the autonomous driving system closer to driver behavior and enabling real-time acquisition of data from manual driving to adjust weights. This solves the technical problem of low accuracy in lane-changing decisions of autonomous driving systems in related technologies. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 This is a flowchart of a control method for an autonomous vehicle according to an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of the membership function of optional distance parameters Gfa / Gpa / Gpb according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of the membership function of an optional dissatisfaction parameter Rdis according to an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of an optional lane-changing intention model according to an embodiment of the present invention;

[0023] Figure 5 This is a flowchart of an optional overall design according to an embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram of a control device for an autonomous vehicle according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] According to an embodiment of the present invention, an embodiment of a control method for an autonomous vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] Figure 1 This is a flowchart of a control method for an autonomous vehicle according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0030] Step S102: Obtain the driving parameters and distance parameters of the autonomous vehicle. The distance parameters are used to represent the distance between the autonomous vehicle and the first vehicle, which is a vehicle traveling in the current lane and / or the adjacent lane of the current lane where the autonomous vehicle is located.

[0031] The aforementioned autonomous vehicle can be an intelligent car that achieves driverless operation through a computer system. This includes, but is not limited to, fully autonomous vehicles and driver-assisted vehicles. The autonomous vehicle operates in a traffic environment where autonomous driving and driver-driven traffic are mixed, and possesses V2X (vehicle-to-everything) communication and control functions, as well as single-vehicle intelligent control functions. Driving parameters may include, but are not limited to, the autonomous vehicle's expected speed, current speed, number of acceleration commands, and number of deceleration commands. Distance parameters can be the distance between the autonomous vehicle and a first vehicle; that is, this distance can be the longitudinal distance between the vehicle and the nearest vehicle in its lane, the longitudinal distance between the vehicle and the nearest vehicle in the adjacent lane, and the longitudinal distance between the vehicle and the nearest vehicle behind in the adjacent lane, all within the Frenet coordinate system. The Frenet coordinate system uses the centerline of the road as a reference line, establishing the coordinate system using the tangent and normal vectors of the reference line, with the vehicle itself as the origin, and the coordinate axes perpendicular to each other. It is highly practical for lane keeping and lane changing at high speeds. The first vehicle can be any vehicle that affects the lane change of the autonomous vehicle, including but not limited to the nearest vehicle in front of the vehicle in the current lane, the nearest vehicle behind the vehicle in the adjacent lane, and the nearest vehicle in front of the vehicle in the adjacent lane.

[0032] In one optional embodiment, the vehicle sensors in the autonomous vehicle perceive the traffic environment around the vehicle in real time (360°) and upload the recorded expected speed Vdes, current speed Vfa, number of acceleration commands NAacc, number of deceleration commands NAdec, and longitudinal distances between the vehicle and the nearest vehicle in front of it in the current lane, the nearest vehicle in front of it in the adjacent lane, and the nearest vehicle behind it in the adjacent lane in the Frenet coordinate system to the onboard system.

[0033] Step S104: Determine the lane-changing parameters of the autonomous vehicle based on the driving parameters, wherein the lane-changing parameters are used to represent the degree of need for the autonomous vehicle to change lanes.

[0034] The aforementioned level of demand can be the degree to which autonomous vehicles need to change lanes based on the current vehicle conditions. For example, the current level of demand for lane changing by autonomous vehicles can be divided into {small, medium, large}.

[0035] In one optional embodiment, the difference between the expected speed Vdes of the autonomous vehicle and the current speed Vfa is a first difference value, i.e. The ratio of the first difference to the expected velocity Vdes determines the first ratio, i.e. The speed parameter is determined by multiplying the first ratio by the sampling period. The velocity parameter is multiplied by the first weighting coefficient to determine the first product, i.e. The sum of the number of acceleration commands (NAacc) and the number of deceleration commands (NAdec) is the first sum, i.e., NAacc + NAdec. The ratio of the number of deceleration commands to the first sum is the acceleration parameter. The product of the acceleration parameter and the second weighting coefficient determines the second product, i.e. Then, the lane-changing parameters are determined based on the sum of the first and second products.

[0036] It should be noted that the driving parameters of this invention include the expected speed Vdes of the autonomous vehicle, the current speed Vfa, the number of acceleration commands NAacc, and the number of deceleration commands NAdec. The speed parameter is represented by all expected and current speeds within a period. A larger speed parameter indicates that the vehicle speed is too fast or too slow, inconsistent with the expected speed, resulting in a high risk of lane changing and a low demand for lane changing. When the expected speed and the current speed are relatively close, the risk of lane changing is low, resulting in a high demand for lane changing. The acceleration parameter is represented by the number of acceleration and deceleration commands. This indicates that frequent acceleration or deceleration within a certain period results in a low demand for lane changing and a high level of dissatisfaction. By comprehensively considering the speed and acceleration parameters, a more accurate demand for lane changing can be calculated.

[0037] Step S106: Determine the lane-changing result based on the distance parameter and the lane-changing parameter, wherein the lane-changing result is used to indicate whether to control the autonomous vehicle to change lanes.

[0038] In one optional embodiment, for the distance parameters Gfa / Gpa / Gpb, the fuzzy variables are set to {small, medium, large, relatively large}, and the basic universe of discourse for the distance parameters is [0, 50] meters; for the dissatisfaction parameter Rdis, the fuzzy variables are set to {small, medium, large}, and the basic universe of discourse is [0, 1]; the fuzzy variables corresponding to the output parameters are {lane change, no lane change}, and the basic universe of discourse is [0, 1]; a virtual cockpit test device is used to simulate driving scenarios in a simulation scene, multiple sets of simulation scenarios are designed, and multiple drivers are selected to conduct multiple rounds of tests; based on the virtual cockpit test data, the fuzzification, fuzzy rules, and defuzzification of the above model input variables are designed to obtain the driving scenario of the autonomous vehicle in the simulation scene, and the preset driving parameters and preset distance parameters of the autonomous vehicle are set, the preset lane-changing behavior corresponding to the simulation driving scenario is determined, and the corresponding preset fuzzy rules are generated; based on the preset fuzzy rules, the distance fuzziness and lane-changing fuzziness are processed to obtain the lane-changing result.

[0039] It should be noted that the input distance parameter and lane change parameter are fuzzified to obtain the corresponding distance fuzzy value and lane change fuzzy value. Then, according to the pre-set fuzzy rules, the corresponding fuzzy values ​​are input, and the lane change result is obtained by comprehensively judging the distance fuzzy value and the lane change fuzzy value, that is, the corresponding fuzzy variable {lane change, no lane change} is output.

[0040] In addition, whether or not a lane change is determined is based on the current road conditions after a lane change has been confirmed. For example, if a lane change is confirmed, but the left lane does not meet the lane change requirement while the right lane does, then the lane change result is determined to be a lane change to the right lane.

[0041] Step S108 controls the lane-changing behavior of the autonomous vehicle based on the lane-changing result.

[0042] The lane-changing behavior mentioned above can be a lane-changing behavior where the autonomous vehicle changes lanes to the left or right, or a lane-changing behavior where the autonomous vehicle continues to travel in the current lane without changing lanes.

[0043] In one optional embodiment, when the lane change result is a lane change, the obtained lane change result is sent to the vehicle control system. The vehicle control system sends a lane change command and then analyzes the road conditions on both sides of the current autonomous vehicle to select the lane to change to. If the left lane meets the lane change requirement, a command is sent to control the steering wheel to drive to the left, thereby controlling the lane change behavior of the autonomous vehicle. When the lane change result is no lane change, the result of no lane change is sent to the vehicle control system, and the autonomous vehicle continues to drive along the current lane.

[0044] Through the above steps, it is possible to acquire the driving parameters and distance parameters of the autonomous vehicle, further determine the lane-changing parameters based on the driving parameters, further determine the lane-changing result based on the distance and lane-changing parameters, and further control the lane-changing behavior of the autonomous vehicle based on the lane-changing result. It is noteworthy that by acquiring the driving and distance parameters of the autonomous vehicle, determining the lane-changing parameters based on the driving parameters, further determining the lane-changing result based on the distance and lane-changing parameters, and then controlling the lane-changing behavior of the autonomous vehicle based on the lane-changing result, it is possible to utilize virtual driving test analysis parameters and analyze lane-changing fuzzy inference rules to build a model. This achieves the technical effect of making the lane-changing behavior of the autonomous driving system closer to driver behavior and being able to obtain real-time data from human driving to adjust weights, thereby solving the technical problem of low accuracy in lane-changing decisions of autonomous driving systems in related technologies.

[0045] In the above embodiments of the present invention, determining the lane-changing result based on the distance parameter and the lane-changing parameter includes: determining the distance ambiguity corresponding to the distance parameter according to a first preset relationship, wherein the first preset relationship is used to represent the correspondence between the distance parameter and the distance ambiguity; determining the lane-changing ambiguity corresponding to the lane-changing parameter according to a second preset relationship, wherein the second preset relationship is used to represent the correspondence between the lane-changing parameter and the lane-changing ambiguity; and processing the distance ambiguity and the lane-changing ambiguity based on a preset ambiguity rule to obtain the lane-changing result, wherein the preset ambiguity rule is used to represent the correspondence between the distance ambiguity, the lane-changing ambiguity, and the lane-changing result.

[0046] The first preset relationship mentioned above can be a distance fuzzy quantity used to describe the correspondence between distance parameters and distance fuzzy quantities; the distance fuzzy quantity can be a fuzzy variable after the distance parameters are fuzzed; the second preset relationship can be a correspondence between lane-changing parameters and lane-changing fuzzy quantities; the lane-changing fuzzy quantity can be a fuzzy variable after the lane-changing parameters are fuzzed.

[0047] Specifically, the distance parameters are the longitudinal distances in the Frenet coordinate system, namely the distance Gfa between the vehicle and the nearest vehicle in front of it in the current lane, the distance Gpa between the vehicle and the nearest vehicle in front of it in the adjacent lane, and the distance Gpb between the vehicle and the nearest vehicle behind it in the adjacent lane. For the distance parameters Gfa, Gpa, and Gpb, the fuzzy variables are set to {small, medium, large, relatively large}, and the basic universe of discourse for the distance parameters is [0, 50] meters. The dissatisfaction parameter Rdis is mainly related to the vehicle's expected speed Vdes, the speed Vfa of Car_fa, the vehicle's acceleration Aacc, and the vehicle's speed Vfa. The deceleration Adec of the vehicle is related to the dissatisfaction parameter Rdis. For this parameter, the fuzzy variables are set to {small, medium, large}, with a basic universe of discourse [0,1]. The fuzzy variables corresponding to the output parameters are {lane change, no lane change}, with a basic universe of discourse [0,1]. The lane change result is obtained by processing the distance fuzziness and lane change fuzziness according to preset fuzzy rules. In this invention, defuzzification uses the centroid method, taking the centroid of the area enclosed by the membership curve and the horizontal axis as the final output value of the fuzzy inference. In this embodiment, the membership functions of the distance parameters Gfa / Gpa / Gpb are as follows: Figure 2 As shown, the fundamental universe of discourse for the membership function of the distance parameter is [0, 50], and the membership function for the dissatisfaction parameter Rdis is as follows. Figure 3 As shown, the fundamental domain of the membership function of the dissatisfaction parameter Rdis is in [0,1].

[0048] Furthermore, the method also includes: simulating a driving scenario of an autonomous vehicle in a simulation scenario; setting preset driving parameters and preset distance parameters for the autonomous vehicle in the driving scenario; generating a simulated driving scenario of the autonomous vehicle based on the preset driving parameters and preset distance parameters; determining preset lane-changing behavior corresponding to the simulated driving scenario; and generating preset fuzzy rules based on the preset driving parameters, preset distance parameters, and preset lane-changing behavior.

[0049] The simulation scenarios described above can be computer-generated scenarios using 3D or 2D technology. The driving scenario can be a scenario where a vehicle is driving on a road. The preset driving parameters can be vehicle driving parameters pre-set in the simulated driving scenario. The preset distance parameters can be distance parameters for simulated road conditions pre-set in the simulated driving scenario. The preset lane-changing behavior can be a lane-changing behavior pre-determined in the simulated driving scenario based on the preset distance parameters and preset driving parameters. The preset fuzzy rules can be fuzzy rules pre-generated in the simulated driving scenario based on the preset distance parameters, preset driving parameters, and preset lane-changing behavior.

[0050] Specifically, in this embodiment of the invention, a schematic diagram of the lane-changing intention model is shown below. Figure 4As shown, the autonomous vehicle is represented by Car_ego, the vehicle in front of it in its lane is represented by Car_fa, the obstacle vehicle in front of it in the adjacent lane is represented by Car_pa, and the obstacle vehicle behind it in the adjacent lane is represented by Car_pb; for example... Figure 4 The scenario described is a situation where a vehicle intends to change lanes to the left. This invention's lane-change intention model can be applied to situations where there is an adjacent lane to the right of the vehicle or adjacent lanes on both the left and right. The lane-change intention model can be a control model that simulates the driver's lane-change intention. This invention's lane-change intention model uses the Mamdani fuzzy system for fuzzy inference. The Mamdani fuzzy system consists of three parts: a fuzzification operator, a fuzzy inference mechanism, and a non-fuzzification operator. It allows setting vehicle driving parameters and distance parameters in the current scenario within the driving scenario. Multiple simulation scenarios are designed based on these parameters, and the corresponding lane-change behaviors are obtained. Multiple drivers are selected for multiple rounds of testing. Based on the virtual cockpit experimental data, fuzzy rules are generated, and an accurate identification system is established.

[0051] Optionally, determining lane-changing parameters for the autonomous vehicle based on driving parameters includes: obtaining the expected speed of the autonomous vehicle, wherein the expected speed represents the speed that the autonomous vehicle is expected to reach at the current time; determining the current speed, the number of acceleration commands, and the number of deceleration commands of the autonomous vehicle based on the driving parameters, wherein the current speed is the speed that the autonomous vehicle reaches at the current time, the number of acceleration commands represents the number of times the autonomous vehicle accelerates within a preset time period, and the number of deceleration commands represents the number of times the autonomous vehicle decelerates within a preset time period; and determining the lane-changing parameters based on the expected speed, the current speed, the number of acceleration commands, and the number of deceleration commands.

[0052] The aforementioned current speed could be the speed of the autonomous vehicle at the current point in time.

[0053] Specifically, the expected speed of the vehicle is Vdes, the current speed is Vfa, the vehicle acceleration is Aacc, and the vehicle deceleration is Adec. NAacc and NAdec represent the number of accelerations and decelerations of the vehicle over a given period of time, which is set to 1 minute. The lane-changing parameter Rdis is determined based on the expected speed Vdes, the current speed Vfa, the number of acceleration commands NAacc, and the number of deceleration commands NAdec.

[0054]

[0055] Further, determining lane-changing parameters based on the expected speed, current speed, number of acceleration commands, and number of deceleration commands includes: determining speed parameters based on the expected speed and current speed; obtaining a first product of the speed parameters and a first weighting coefficient; determining acceleration parameters based on the number of acceleration commands and the number of deceleration commands; obtaining a second product of the acceleration parameters and a second weighting coefficient, wherein the sum of the second weighting coefficient and the first weighting coefficient is a preset value; and determining the sum of the first product and the second product as the lane-changing parameters.

[0056] The first weighting coefficient mentioned above can be used to represent the importance of the velocity parameter in the indicator system, or it can represent the impact of the change of this indicator on the result when other indicators remain unchanged; the second weighting coefficient can represent the importance of the acceleration parameter in the indicator system; the first product can be the product of the first weighting coefficient and the velocity parameter; the second product can be the product of the acceleration parameter and the second weighting coefficient; the preset value can be a pre-set value.

[0057] Specifically, the product of the first weighting coefficient p and the velocity parameter is the first product, i.e. The product of the second weighting coefficient q and the acceleration parameter is the second product, i.e. The first product plus the second product determines the lane-changing parameters, i.e. Wherein, the first weight coefficient and the second weight coefficient are greater than or equal to 0, and the sum of the first weight coefficient and the second weight coefficient is a preset value of 1, and the equation satisfies When the driver is manually driving the vehicle, the driver's driving behavior data is recorded in real time. The lane-changing conditions of the driver during the driving process are analyzed. The dissatisfaction function of multiple lane-changing situations is analyzed. The first term is the degree of dissatisfaction with the speed of the vehicle in front, and the second term is the degree of dissatisfaction with the acceleration of the vehicle itself. By using the ratio of these two terms, the first weight coefficient p or the second weight coefficient q can be appropriately increased to realize the online adjustment of the lane-changing intention model.

[0058] Further, determining the speed parameter based on the expected speed and the current speed includes: obtaining a first difference between the expected speed and the current speed; obtaining a first ratio between the first difference and the expected speed; and determining the product of the first ratio and the sampling period as the speed parameter, wherein the sampling period is a pre-set period for sampling the driving parameters of the autonomous vehicle.

[0059] The first difference mentioned above can be the difference between the expected speed Vdes and the current speed Vfa; the first ratio can be the ratio of the first difference to its speed Vdes; the sampling period can be the period during which relevant data is collected in the periodic measurement process; and the speed parameter can be a parameter value used to describe the relationship between the expected speed and the current speed.

[0060] Specifically, the difference between all expected velocities Vdes collected during the period and the current velocity Vfa is calculated, then the ratio of this difference to the expected velocity Vdes is calculated, and finally multiplied by the sampling period to obtain the velocity parameter. The sampling period is 10 milliseconds, and n is the sampling stage value. In this invention, n is 100.

[0061] It should be noted that when the speed of the autonomous vehicle is too high and differs significantly from the expected speed, it indicates a high risk of lane changing, resulting in a low demand for lane changing. Conversely, when the current speed of the autonomous vehicle is close to the expected speed, it indicates a low risk of lane changing, resulting in a high demand for lane changing.

[0062] Optionally, the acceleration parameter is determined based on the number of acceleration commands and the number of deceleration commands, including: obtaining a first sum of the number of acceleration commands and the number of deceleration commands; and determining the ratio of the number of deceleration commands to the first sum as the acceleration parameter.

[0063] The first sum mentioned above can be the sum of the number of acceleration commands and the number of deceleration commands; the acceleration parameter can be the ratio of the number of deceleration commands to the first sum.

[0064] Specifically, the acceleration parameters are obtained by dividing the number of deceleration commands by the sum of the number of acceleration commands and the number of deceleration commands. The larger the acceleration command parameter and deceleration parameter, the more frequently the autonomous vehicle accelerates or decelerates within a certain period of time, resulting in a lower demand for lane changing and a higher level of dissatisfaction.

[0065] Optionally, the method further includes: when the autonomous vehicle is driven by a human, acquiring the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior of the autonomous vehicle; and adjusting them according to the ratio of the first weighting coefficient and the second weighting system of the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior.

[0066] The aforementioned real-time driving parameters can be the real-time driving parameters of the autonomous vehicle; the real-time distance parameters can be the distance parameters between the autonomous vehicle's lane and the lanes on the left and right sides; and the real-time lane-changing behavior can be the lane-changing behavior determined based on the real-time distance parameters and the real-time lane-changing behavior.

[0067] Specifically, when a driver is manually driving an autonomous vehicle, the autonomous driving system runs in the background, recording the driver's driving behavior data in real time. For lane-changing situations during the driver's operation, the system analyzes the degree of dissatisfaction with the speed of the vehicle in front and the degree of dissatisfaction with the vehicle's acceleration in multiple lane-changing situations. Based on the ratio of these two items, the weight coefficient of the item with the higher ratio is appropriately increased.

[0068] The following is combined with Figure 5A preferred embodiment of the present invention will be described in detail, such as... Figure 5 As shown, the method includes: acquiring relevant parameters of the lane-changing intention model; acquiring distance and driving parameters through radar, artificial intelligence, and other devices in the autonomous driving system; determining speed parameters based on distance and driving parameters; determining acceleration parameters based on the number of acceleration and deceleration commands; determining lane-changing parameters based on the number of acceleration and deceleration commands; determining lane-changing results based on lane-changing and distance parameters; simulating driving scenarios in a virtual cockpit test device; designing multiple sets of simulation scenarios for multiple rounds of testing; performing fuzzy processing on the model; and finally establishing an accurate identification system model. When the driver is manually driving, the data is recorded and analyzed in real time, and the weight coefficient ratio is adjusted appropriately.

[0069] Example 2

[0070] According to embodiments of the present invention, a control device for an autonomous vehicle is also provided. This device can execute the control method for the autonomous vehicle described in the above embodiments, and its specific implementation and preferred application scenarios are the same as those described in the above embodiments, and will not be repeated here.

[0071] Figure 6 This is a schematic diagram of the structure of a control device for an autonomous vehicle according to an embodiment of the present invention, such as... Figure 6 As shown, the device includes the following components: an acquisition module 60, a first determination module 62, a second determination module 64, and a control module 66.

[0072] The acquisition module 60 is used to acquire the driving parameters and distance parameters of the autonomous vehicle. The distance parameters are used to represent the distance between the autonomous vehicle and the first vehicle, which is a vehicle traveling in the current lane and / or the adjacent lane of the current lane where the autonomous vehicle is located.

[0073] The first determining module 62 is used to determine the lane-changing parameters of the autonomous vehicle based on the driving parameters, wherein the lane-changing parameters are used to indicate the degree of need for the autonomous vehicle to change lanes.

[0074] The second determining module 64 is used to determine the lane-changing result based on the distance parameter and the lane-changing parameter, wherein the lane-changing result is used to indicate whether to control the autonomous vehicle to perform a lane change;

[0075] Control module 66 is used to control the lane-changing behavior of autonomous vehicles based on lane-changing results.

[0076] Optionally, the second determining module includes: a first determining unit, configured to determine the distance ambiguity corresponding to the distance parameter according to a first preset relationship, wherein the first preset relationship represents the correspondence between the distance parameter and the distance ambiguity; a second determining unit, configured to determine the lane change ambiguity corresponding to the lane change parameter according to a second preset relationship, wherein the second preset relationship represents the correspondence between the lane change parameter and the lane change ambiguity; and a processing unit, configured to process the distance ambiguity and the lane change ambiguity based on preset ambiguity rules to obtain a lane change result, wherein the preset ambiguity rules represent the correspondence between the distance ambiguity, the lane change ambiguity, and the lane change result.

[0077] Optionally, the second determining module further includes: a simulation unit for simulating the driving scenario of an autonomous vehicle in a simulation scenario; a parameter setting unit for setting preset driving parameters and preset distance parameters of the autonomous vehicle in the driving scenario; a scenario generation unit for generating a simulated driving scenario of the autonomous vehicle based on the preset driving parameters and preset distance parameters; a third determining unit for determining the preset lane-changing behavior corresponding to the simulated driving scenario; and a rule generation unit for generating preset fuzzy rules based on the preset driving parameters, preset distance parameters, and preset lane-changing behavior.

[0078] Optionally, the first determining module includes: a first acquiring unit, used to acquire the expected speed of the autonomous vehicle, wherein the expected speed represents the speed that the autonomous vehicle is expected to reach at the current time; a fourth determining unit, used to determine the current speed, the number of acceleration commands, and the number of deceleration commands of the autonomous vehicle based on driving parameters, wherein the current speed is the speed that the autonomous vehicle reaches at the current time, the number of acceleration commands represents the number of times the autonomous vehicle accelerates within a preset time period, and the number of deceleration commands represents the number of times the autonomous vehicle decelerates within a preset time period; and a fifth determining unit, used to determine lane-changing parameters based on the expected speed, the current speed, the number of acceleration commands, and the number of deceleration commands.

[0079] Optionally, the fifth determining unit includes: a first determining subunit, used to determine speed parameters based on the expected speed and the current speed; a first acquiring subunit, used to acquire a first product of the speed parameters and a first weighting coefficient; a second determining subunit, used to determine acceleration parameters based on the number of acceleration commands and the number of deceleration commands; a second acquiring subunit, used to acquire a second product of the acceleration parameters and a second weighting coefficient, wherein the sum of the second weighting coefficient and the first weighting coefficient is a preset value; and the sum of the first product and the second product is determined to be a lane-changing parameter.

[0080] Optionally, the first determining subunit is further configured to obtain a first difference between the expected speed and the current speed; obtain a first ratio between the first difference and the expected speed; and determine the product of the first ratio and the sampling period as a speed parameter, wherein the sampling period is a preset period for sampling the driving parameters of the autonomous vehicle.

[0081] Optionally, the second determining subunit is further configured to obtain a first sum of the number of acceleration commands and the number of deceleration commands; and determine the ratio of the number of deceleration commands to the first sum as an acceleration parameter.

[0082] Optionally, the fifth determining unit is further configured to acquire real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior of the autonomous vehicle when the autonomous vehicle is driven by a human; and to adjust the parameters according to the ratio of the first weighting coefficient and the second weighting system of the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior.

[0083] Example 3

[0084] According to an embodiment of the present invention, an autonomous vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to execute the control method of the autonomous vehicle according to any one of the above embodiments.

[0085] Example 4

[0086] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute any of the vehicle control methods in the above embodiments.

[0087] Example 5

[0088] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes any of the vehicle control methods described above.

[0089] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0090] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0092] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Furthermore, the functional units in the various embodiments of the present invention 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.

[0094] 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, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0095] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for an autonomous vehicle, characterized in that, include: The driving parameters and distance parameters of the autonomous vehicle are obtained, wherein the distance parameters are used to represent the distance between the autonomous vehicle and a first vehicle, and the first vehicle is a vehicle traveling in the current lane where the autonomous vehicle is located and / or in the adjacent lane of the current lane. The lane-changing parameters of the autonomous vehicle are determined based on the driving parameters, wherein the lane-changing parameters are used to indicate the degree of need for the autonomous vehicle to change lanes. The lane-changing result is determined based on the distance parameter and the lane-changing parameter, wherein the lane-changing result is used to indicate whether to control the autonomous vehicle to change lanes; The lane-changing behavior of the autonomous vehicle is controlled based on the lane-changing results; Determining the lane-changing result based on the distance parameter and the lane-changing parameter includes: The distance ambiguity value corresponding to the distance parameter is determined according to a first preset relationship, wherein the first preset relationship is used to represent the correspondence between the distance parameter and the distance ambiguity value; The lane change ambiguity value corresponding to the lane change parameter is determined according to the second preset relationship, wherein the second preset relationship is used to represent the correspondence between the lane change parameter and the lane change ambiguity value; The distance fuzzy amount and the lane change fuzzy amount are processed based on preset fuzzy rules to obtain a lane change result. The preset fuzzy rules are used to represent the correspondence between the distance fuzzy amount, the lane change fuzzy amount and the lane change result. Determining the lane-changing parameters of the autonomous vehicle based on the driving parameters includes: Speed ​​parameters are determined based on the expected speed and current speed of the autonomous vehicle, wherein the current speed is determined based on the driving parameters; Obtain the first product of the velocity parameter and the first weighting coefficient; The acceleration parameters are determined based on the number of acceleration commands and the number of deceleration commands, wherein the number of acceleration commands and the number of deceleration commands are determined based on the driving parameters; Obtain the second product of the acceleration parameter and the second weighting coefficient, wherein the sum of the second weighting coefficient and the first weighting coefficient is a preset value; The sum of the first product and the second product is determined to be the lane-changing parameter; The method further includes: When the autonomous vehicle is driven by a human, the real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior of the autonomous vehicle are obtained. The ratio of the first weighting coefficient and the second weighting coefficient is adjusted based on the real-time driving parameters, the real-time distance parameters, and the real-time lane-changing behavior.

2. The method according to claim 1, characterized in that, The method further includes: Simulate the driving scenario of the autonomous vehicle in a simulation environment; In the driving scenario, preset driving parameters and preset distance parameters are set for the autonomous vehicle; The simulated driving scenario of the autonomous vehicle is generated based on the preset driving parameters and the preset distance parameters; Determine the preset lane-changing behavior corresponding to the simulated driving scenario; The preset fuzzy rules are generated based on the preset driving parameters, the preset distance parameters, and the preset lane-changing behavior.

3. The method according to claim 1, characterized in that, Determining speed parameters based on the expected speed and the current speed includes: Obtain a first difference between the expected speed and the current speed; Obtain a first ratio between the first difference and the expected speed; The product of the first ratio and the sampling period is determined as the speed parameter, wherein the sampling period is a preset period for sampling the driving parameters of the autonomous vehicle.

4. The method according to claim 1, characterized in that, Determining acceleration parameters based on the number of acceleration commands and the number of deceleration commands includes: Obtain the first sum of the number of acceleration commands and the number of deceleration commands; The ratio of the number of deceleration commands to the first sum value is determined as the acceleration parameter.

5. A control device for an autonomous vehicle, characterized in that, include: The acquisition module is used to acquire the driving parameters and distance parameters of the autonomous vehicle, wherein the distance parameters are used to represent the distance between the autonomous vehicle and a first vehicle, and the first vehicle is a vehicle in the current lane and / or the lane to be changed by the autonomous vehicle. The first determining module is used to determine the lane-changing parameters of the autonomous vehicle based on the driving parameters, wherein the lane-changing parameters are used to indicate the degree of dissatisfaction with the lane-changing of the autonomous vehicle. The second determining module is used to determine the lane-changing result based on the distance parameter and the lane-changing parameter, wherein the lane-changing result is used to indicate whether to control the autonomous vehicle to perform a lane change; A control module is used to control the lane-changing behavior of the autonomous vehicle based on the lane-changing result; The device is further configured to: determine a distance ambiguity corresponding to the distance parameter according to a first preset relationship, wherein the first preset relationship represents the correspondence between the distance parameter and the distance ambiguity; determine a lane change ambiguity corresponding to the lane change parameter according to a second preset relationship, wherein the second preset relationship represents the correspondence between the lane change parameter and the lane change ambiguity; and process the distance ambiguity and the lane change ambiguity based on a preset ambiguity rule to obtain a lane change result, wherein the preset ambiguity rule represents the correspondence between the distance ambiguity, the lane change ambiguity, and the lane change result. The device is further configured to: determine speed parameters based on the expected speed and current speed of the autonomous vehicle, wherein the current speed is determined based on the driving parameters; obtain a first product of the speed parameters and a first weighting coefficient; determine acceleration parameters based on the number of acceleration commands and the number of deceleration commands, wherein the number of acceleration commands and the number of deceleration commands are determined based on the driving parameters; obtain a second product of the acceleration parameters and a second weighting coefficient, wherein the sum of the second weighting coefficient and the first weighting coefficient is a preset value; and determine the sum of the first product and the second product as the lane-changing parameter. The device is also used to acquire real-time driving parameters, real-time distance parameters, and real-time lane-changing behavior of the autonomous vehicle when the autonomous vehicle is driven by a human; and to adjust the ratio of the first weighting coefficient and the second weighting coefficient according to the real-time driving parameters, the real-time distance parameters, and the real-time lane-changing behavior.

6. An autonomous vehicle, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the control method for an autonomous vehicle according to any one of claims 1 to 4.

Images