CN111532285B

CN111532285B - Vehicle control method and device

Info

Publication number: CN111532285B
Application number: CN202010251432.5A
Authority: CN
Inventors: 颜诗涛; 白钰; 赵博林; 许笑寒; �田润; 王志超; 陈鸿帅; 任冬淳
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-04-01
Filing date: 2020-04-01
Publication date: 2021-09-07
Anticipated expiration: 2040-04-01
Also published as: CN111532285A

Abstract

The specification discloses a vehicle control method and device. The embodiment of the specification predicts the running track of the vehicle under the condition of the input of the control quantity according to the control quantity of the vehicle to be input. And determining the difference between the reference track and the running track according to the preset reference track of the vehicle and the predicted running track of the vehicle under the control quantity input condition as a track difference characteristic. The running characteristic is determined based on at least one of the control amount, the change in the control amount, and the environmental information around the vehicle. And determining target characteristics according to the track difference characteristics and the driving characteristics, adjusting the control quantity by taking the minimum target characteristics as an optimization target, and controlling the vehicle to drive according to the adjusted control quantity. When the given reference track is not reasonable, the vehicle can adjust the control quantity to be input to the vehicle by integrating the influence of each characteristic, so that the vehicle can run according to the adjusted control quantity.

Description

Vehicle control method and device

Technical Field

The specification relates to the technical field of intelligent driving, in particular to a vehicle control method and device.

Background

Currently, in the field of intelligent driving technology, a reference track may be provided for a vehicle (e.g., an unmanned vehicle) in advance, so that the vehicle performs track planning according to the reference track, thereby implementing automatic driving of the vehicle.

Specifically, the future travel locus of the vehicle at the control amount may be predicted based on the current state information of the vehicle and the control amount to be input to the vehicle, and the control amount to be input may be adjusted so that the predicted future travel locus coincides with the reference locus, so that the vehicle can travel along the reference locus. The control quantity can comprise: the front wheel angle of the vehicle, the longitudinal acceleration of the vehicle, etc. The front wheel rotating angle of the vehicle can be determined by adjusting the rotating angle of a steering wheel of the vehicle, and the longitudinal acceleration of the vehicle can be determined by adjusting the opening degrees of an accelerator and a brake.

In the automatic driving process of the vehicle, when a given reference track is unreasonable (such as a reference track jumps), if the vehicle is only consistent with the reference track, phenomena such as sharp turning and jolting may occur, which affect the safety and comfort of the vehicle.

Disclosure of Invention

The embodiment of the specification provides a vehicle control method and a vehicle control device, which are used for partially solving the problems in the prior art.

The embodiment of the specification adopts the following technical scheme:

a vehicle control method provided by this specification includes:

predicting a running track of a vehicle under the control quantity input condition according to the control quantity of the vehicle to be input;

determining the difference between a reference track and a predicted running track of the vehicle under the control quantity input condition according to the preset reference track of the vehicle and the predicted running track of the vehicle, wherein the difference is used as a track difference characteristic;

determining a driving characteristic according to at least one of the control quantity, the change of the control quantity and the environmental information around the vehicle, wherein the smaller the driving characteristic is, the higher the driving quality of the vehicle is represented;

determining target characteristics according to the track difference characteristics and the driving characteristics;

adjusting the control quantity by taking the minimum target characteristic as an optimization target;

and controlling the vehicle to run according to the adjusted control quantity.

Optionally, the running characteristic includes a control amount characteristic; determining the control quantity characteristics specifically comprises the following steps:

and determining the controlled quantity characteristic according to the controlled quantity and the weight corresponding to the controlled quantity.

Optionally, the driving characteristics include a variation characteristic; determining the change characteristics specifically comprises the following steps: and determining the change characteristics according to the change rate of the longitudinal acceleration of the vehicle, the change rate of the lateral acceleration of the vehicle and the weight corresponding to the change characteristics.

Optionally, the driving feature comprises an obstacle feature; determining obstacle characteristics, specifically comprising: determining each obstacle in the specified neighborhood of the vehicle according to the environmental information around the vehicle; and determining the obstacle characteristics according to the distance between the vehicle and each obstacle in the specified neighborhood and the weight corresponding to the obstacle characteristics.

Optionally, the method further includes: acquiring a plurality of expert data based on the preset reference track of the vehicle; determining a mean value of the plurality of expert data according to the target characteristics; determining a probability distribution, wherein the expected value of the probability distribution is the mean value of the plurality of expert data, and the probability distribution is related to the function corresponding to the target feature; and determining each weight in the target feature by adopting a maximum likelihood method according to the determined probability distribution.

Optionally, determining a target feature according to the track difference feature and the driving feature specifically includes: identifying the lane type of a lane in which the vehicle is located; and determining the target characteristics under the lane type condition according to the track difference characteristics, the driving characteristics and the lane type of the lane where the vehicle is located.

Optionally, the adjusting the controlled variable with the minimum target characteristic as an optimization target specifically includes: and adjusting the controlled variable by taking the minimum target characteristic as an optimization target and taking the running track not exceeding the neighborhood range of the reference track and the controlled variable not exceeding the preset controlled variable range as limiting conditions.

A vehicle control device provided in this specification includes:

the prediction module is used for predicting the running track of the vehicle under the control quantity input condition according to the control quantity of the vehicle to be input;

the track difference characteristic determining module is used for determining the difference between a reference track and a driving track of the predicted vehicle under the control quantity input condition according to the preset reference track of the vehicle and the driving track, and the difference serves as a track difference characteristic;

the driving characteristic determining module is used for determining driving characteristics according to at least one of the control quantity, the change of the control quantity and the environmental information around the vehicle, wherein the smaller the driving characteristics is, the higher the driving quality of the vehicle is represented;

the target characteristic determining module is used for determining target characteristics according to the track difference characteristics and the driving characteristics;

the adjusting module is used for adjusting the control quantity by taking the minimum target characteristic as an optimization target;

and the control module is used for controlling the vehicle to run according to the adjusted control quantity.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described vehicle control method.

The electronic device provided by the specification comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the vehicle control method.

The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:

in the embodiment of the specification, when the vehicle is controlled, not only the vehicle is uniformly kept consistent with the given reference track, but also factors such as the vehicle control quantity, the change of the vehicle control quantity, the influence of the vehicle surrounding environment information and the like are considered. That is, the scheme not only considers that the vehicle runs according to the reference track, but also considers the influence of factors such as energy consumption, safety and stability of the vehicle on the running of the vehicle. When the given reference track is unreasonable, for example, the reference track jumps, the vehicle can also adjust the control quantity to be input to the vehicle by integrating the influences of the factors, so that the vehicle can run according to the adjusted control quantity. The scheme fully considers the safety and the comfort of the vehicle running, and the vehicle cannot make sharp turning, jolting and the like.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

fig. 1 is a schematic flowchart of a vehicle control method provided in an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of a vehicle control device provided in an embodiment of the present specification;

fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of this specification.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

As shown in fig. 1, fig. 1 is a schematic flowchart of a vehicle control method provided in this specification, where the schematic flowchart includes:

s100: and predicting the running track of the vehicle under the control quantity input condition according to the control quantity of the vehicle to be input.

In order to realize automatic running of the vehicle, a reference track can be provided for the vehicle in advance, so that the vehicle can carry out track planning according to the reference track. Specifically, the future travel locus of the vehicle can be predicted based on the control amount to be input to the vehicle at the control amount. The vehicle can be an unmanned vehicle or a vehicle with a driving assisting function. The control quantity may be: the front wheel angle of the vehicle, the longitudinal acceleration of the vehicle, the lateral acceleration of the vehicle, etc. The front wheel rotation angle of the vehicle can be determined by adjusting the steering wheel rotation angle of the vehicle; and determining the longitudinal acceleration of the vehicle and the like by adjusting the opening degree of an accelerator and a brake.

S102: and determining the difference between the reference track and the driving track according to the preset reference track of the vehicle and the predicted driving track of the vehicle under the control quantity input condition as a track difference characteristic.

The track is a time-space sequence and can be composed of a plurality of track point connecting lines. For example, the vehicle may be driven from one position coordinate (x) by going from the first second to the second₁，y₁) Move to another position coordinate (x)₂，y₂) Is characterized by the connection line of (a). The difference between the reference trajectory and the travel trajectory can be characterized by a lateral position error, a lateral position error change rate, a longitudinal position error change rate, a yaw angle error change rate, and the like between the reference trajectory and the travel trajectory of the vehicle from the time K to the time K +1, whereby the trajectory difference feature J can be determined_error(u). Of course, the trajectory difference feature J_errorThe determination of (u) may also take into account other factors, which are not intended to be limiting by the embodiments of the present specification. Further, the track difference characteristic J can be determined according to the difference between the reference track and the driving track and the weight w1 corresponding to the track difference characteristic_error(u). That is, a basic trajectory difference characteristic is determined from the difference between the reference trajectory and the travel trajectory, and then a final trajectory difference characteristic J is determined from the product of the basic trajectory difference characteristic and the weight w1_error(u). The determination formula of the track difference characteristic is as follows: j. the design is a square_error(u)＝w1*J_error(f)＝w1*(y_r-y_p). Wherein, J_error(u) represents a track variance feature, w1 represents a weight corresponding to the track variance feature, J_error(f) Representing the basic trajectory difference feature, y_rRepresents a reference track, y_pRepresenting the predicted travel trajectory.

S104: and determining the running characteristic according to at least one of the control quantity, the change of the control quantity and the environmental information around the vehicle, wherein the smaller the running characteristic is, the higher the running quality of the vehicle is represented.

Specifically, the running characteristic may be determined based on at least one of the control amount, a change in the control amount, and environmental information around the vehicle. The smaller the control amount is or the smaller the change of the control amount is, the smaller the energy consumption of the vehicle is and the higher the stability is in this state. In addition, if there is no obstacle in the environmental information around the vehicle, or the distance between the vehicle and each obstacle is longer, the safety of the representative vehicle is higher. In the embodiments of the present specification, the smaller the running characteristic, the higher the running quality of the vehicle is represented.

S106: and determining target characteristics according to the track difference characteristics and the driving characteristics.

Continuing with the above example, the trajectory difference feature J is determined_error(u) and after the driving feature, the trajectory difference feature J can be used_error(u) and the driving characteristics to determine the target characteristics j (u). In particular, the track difference characteristic J can be passed_error(u) and the sum of the running characteristics to obtain a target characteristic J (u).

S108: and adjusting the control quantity by taking the minimum target characteristic as an optimization target.

After the target feature j (u) is determined in the above manner, the control amount may be adjusted with the minimum target feature j (u) as the optimization target. I.e. make the trajectory differ by a feature J_errorAnd (u) adjusting the control quantity by using the minimum sum of the driving characteristics as an optimization target.

S110: and controlling the vehicle to run according to the adjusted control quantity.

After the control amount is adjusted in the above manner, the vehicle can be controlled to run according to the adjusted control amount. The embodiments herein take into account the influence of other factors (such as the control amount, the change in the control amount, the environmental information around the vehicle, and the like) in addition to the influence of the difference between the preset reference trajectory of the vehicle and the predicted travel trajectory of the vehicle when controlling the travel of the vehicle. That is, the embodiments of the present disclosure not only enable the vehicle to keep consistent with the reference trajectory of the vehicle during the driving process, but also consider the energy consumption of the vehicle, the driving stability of the vehicle, the safety of the vehicle, and other factors. Then, when the preset reference track of the vehicle is not reasonable (for example, the reference track jumps), the vehicle does not make sharp turns, jolts and the like.

In S104 illustrated in fig. 1, the running characteristic may include a control amount characteristic J_u(u). Control quantity characteristic J_uThe determination method of (u) may specifically include: determining a controlled variable characteristic J according to the controlled variable and the weight w2 corresponding to the controlled variable_u(u). That is, the basic control amount characteristic may be determined by the control amount, and then the control amount characteristic J may be determined based on the product of the basic control amount characteristic and the weight w2_u(u). The determination formula of the control quantity characteristic is as follows: j. the design is a square_u(u)＝w2*J_u(f) W2 × u. Wherein, J_u(u) represents a controlled variable characteristic, w2 represents a weight corresponding to the controlled variable characteristic, and J_u(f) Represents the basic controlled variable characteristic, and u represents the controlled variable. Therefore, the smaller the control quantity u is, the smaller the energy consumption of the vehicle is, and the higher the stability is.

In S104 illustrated in fig. 1, the running characteristic may include a variation characteristic J_comfort(u). Variation characteristic J_comfortThe determination method of (u) may specifically include: determining the change characteristic J according to the change rate of the longitudinal acceleration of the vehicle, the change rate of the lateral acceleration of the vehicle and the weight w3 corresponding to the change characteristic_comfort(u). That is, the basic change characteristic may be determined by the rate of change of the vehicle longitudinal acceleration and the rate of change of the vehicle lateral acceleration, and then the change characteristic J may be obtained from the product of the basic change characteristic and the weight w3_comfort(u). The determination formula of the variation characteristics is as follows: j. the design is a square_comfort(u)＝w3*J_comfort(f)＝w3*(a_xi+a_yi). Wherein, J_comfort(u) represents a change characteristic, w3 represents a weight corresponding to the change characteristic, J_comfort(f) Represents a basic variation characteristic of_xiRepresenting the rate of change of the longitudinal acceleration of the vehicle, a_yiRepresenting lateral acceleration of the vehicleThe rate of change of the degree. It follows that a smaller rate of change of the longitudinal acceleration of the vehicle and/or of the lateral acceleration of the vehicle represents a higher comfort of the vehicle. Of course, the variation characteristic J of the vehicle_comfortThe obtaining of (u) may also take into account other factors, such as the rate of change of the control quantity u (continued derivation), and the like, which is not limited by the embodiments of the present specification.

In S104 illustrated in fig. 1, the driving feature may include an obstacle feature J_safty(u). Feature of obstacle J_saftyThe determination method of (u) may specifically include: determining each obstacle in a specified neighborhood of the vehicle according to the environmental information around the vehicle; determining an obstacle characteristic J according to the distance between the vehicle and each obstacle in the designated neighborhood and the weight w4 corresponding to the obstacle characteristic_safty(u). That is, the basic obstacle feature may be determined based on the distance between the vehicle and each obstacle in the specified vicinity, and then the obstacle feature J may be determined based on the product of the basic obstacle feature and the weight w4_safty(u). Note that the obstacle feature J_safty(u) is inversely related to the distance between the vehicle and the obstacle.

The determination formula of the obstacle feature is as follows:

wherein, J_safty(u) represents an obstacle feature, w4 represents a weight corresponding to the obstacle feature, J_safty(f) Representing a basic obstacle character, N_obsRepresenting the number of obstacles, dis, in a given neighborhood of the vehicle_jRepresenting the distance between the vehicle and each obstacle in the designated neighborhood. It follows that the greater the distance between the vehicle and each obstacle in a given vicinity of the vehicle, the greater the obstacle feature J_saftyThe smaller the value (u) corresponds to, the worse the safety of the vehicle. Conversely, if there are no obstacles in the environment around the vehicle, or the distance between the vehicle and each obstacle in a specified vicinity of the vehicle is smaller, the obstacle feature J_saftyThe larger the value (u) corresponds to, the better the safety of the vehicle. Wherein the specified neighborhood may be: the radius of the vehicle is within 30 meters. Of courseThe designated neighborhood may also be characterized in other ways, which is not limited by the embodiments of the present specification.

As described above, the target feature J (u) ═ J_error(u)+J_u(u)+J_comfort(u)+J_safty(u)＝w1*J_error(f)+w2**J_u(f)+w3*J_comfort(f)+w4*J_safty(f) In that respect The representative meanings of the components in the formula are consistent with the foregoing contents, and the description is omitted here. Determining the basic track difference characteristics J in the target characteristics J (u)_error(f) Basic control quantity characteristic J_u(f) Basic change feature J_comfort(f) Basic obstacle feature J_safty(f) Subsequently, the weight w1 corresponding to the track difference characteristic, the weight w2 corresponding to the controlled variable characteristic, the weight w3 corresponding to the change characteristic, and the weight w4 corresponding to the obstacle characteristic are determined. The method for obtaining each weight in the target features j (u) may be: acquiring a plurality of expert data based on a preset reference track of the vehicle; determining the mean value of a plurality of expert data according to the target characteristics; determining probability distribution, wherein the expected value of the probability distribution can be the average value of a plurality of expert data, and the probability distribution is related to the function corresponding to the target characteristic; and determining each weight in the target feature by adopting a maximum likelihood method according to the determined probability distribution.

The expert data may be, among others: and the human beings drive each driving track of the vehicle according to the preset reference track of the vehicle. The determination of the mean of several expert data may be determined by the target feature. Specifically, the basic trajectory difference feature J may be determined by the difference between the reference trajectory and the travel trajectory of the vehicle_error(f) Determining the basic control quantity characteristic J from the control quantity_u(f) The basic change characteristic J is determined by the change rate of the longitudinal acceleration of the vehicle and the change rate of the lateral acceleration of the vehicle_comfort(f) Determining basic obstacle characteristics J by the distance between the vehicle and each obstacle in the specified vicinity_safty(f) Based on the sum of these four basic features, the basic target feature J (f) J can be determined_error(f)+J_u(f)+J_comfort(f)+J_safty(f) In that respect Wherein J (f) represents a basic target featureThe other components of the formula have the same meanings as described above, and are not described herein again. Then, the average value of a plurality of expert data is determined through the basic target characteristics J (f) in each expert data. That is, the determination of the mean of several expert data does not take into account the influence of the weights w1, w2, w3, w 4. Having determined the mean of the expert data in the above-described manner, it is possible to determine the probability distribution of the mean of the expert data with the expectation value of the basic target feature j (f) (i.e. the feature not comprising the weights w1, w2, w3, w 4) as: the determined probability distribution is variable with respect to a function corresponding to the target feature. It should be noted that the function corresponding to the target feature is a function obtained by extracting a negative sign from the target feature, that is, the probability distribution takes a function determined by extracting a negative sign from the target feature as a variable. It should be further noted that the probability distribution in the embodiment of the present specification is a probability distribution with the largest solution uncertainty based on the maximum entropy principle. Wherein the determined probability distribution may be in the form of:

in the probability distribution, wherein

Representing coefficients, J (u) representing target characteristics, J_error(u) represents a trajectory difference feature, J_u(u) represents a controlled variable characteristic, J_comfort(u) represents a change character, J_safty(u) represents an obstacle feature. It can be seen that the probability distribution at this time is equal to J (u) ═ J_error(u)+J_u(u)+J_comfort(u)+J_safty(u)＝w1*J_error(f)+w2**J_u(f)+w3*J_comfort(f)+w4*J_safty(f) In this case, the influence of the weights w1, w2, w3, and w4 is included.

The embodiment of the specification is a probability distribution determined by that the expected value of the basic target feature J (f) on the probability distribution is the mean value of a plurality of expert data. Of course, the expected value of the probability distribution may also be determined by other ways, which is not limited by the embodiment of the present specification.

After the probability distribution has been determined, the maximum likelihood method can be used, with the following log-likelihood function

By obtaining the maximum value, the weights w1, w2, w3 and w4 for the trajectory difference feature, the controlled variable feature and the obstacle feature can be determined in the target feature j (u). In the log-likelihood function, where N represents the number of expert data and P (τ) represents the aforementioned probability distribution.

For different scenes, the indexes of attention of the vehicle during driving are different. For example, when the vehicle is closer to an obstacle, the vehicle may pay more attention to safety than stability. Therefore, if the target characteristics of the vehicle are consistent for different scenes, it is obviously unreasonable. The lane type of a lane where the vehicle is located can be identified; and determining the target characteristics under the condition of the lane type according to the track difference characteristics, the driving characteristics and the lane type of the lane where the vehicle is located. That is, the current scene of the vehicle can be determined according to the preset curvature radius of the reference track of the vehicle, the lane type of the lane where the vehicle is located and the like obtained according to the environmental information around the vehicle, for example, the straight lane has an obstacle, the straight lane has no obstacle, the curve has an obstacle, the curve has no obstacle and the like. And then, adaptively adjusting the target characteristics according to the current scene of the vehicle, and controlling the vehicle.

The above method may be used to determine the weights corresponding to each of the target features as a set of common weights. Aiming at different scenes, the universal weight can be adaptively adjusted, and the accuracy, comfort and safety of vehicle running are further improved. For example, in a lane change scene close to an obstacle, if the weight w4 corresponding to the obstacle feature is appropriately increased and the weight w3 corresponding to the change feature is appropriately decreased, that is, if safety is emphasized more than comfort, the driving state of the vehicle at that time is more suitable.

In addition, the embodiments of the present specification may also determine different weights for different scenarios. The manner of obtaining each weight in different scenes may be: firstly, acquiring a plurality of expert data under different scenes, and then determining the weights under different scenes by adopting the above method based on the plurality of expert data under different scenes, wherein the method for determining the weights is not repeated. In the running process of the vehicle, each weight in the target characteristics can be adjusted according to the current scene of the vehicle, and the vehicle is controlled.

The control amount may be adjusted with the target characteristic minimum as the optimization target. The method specifically comprises the following steps: and adjusting the controlled variable by taking the minimum target characteristic as an optimization target and taking the driving track not exceeding the neighborhood range of the reference track and the controlled variable not exceeding the preset controlled variable range as limiting conditions. The preset reference track of the vehicle has a neighborhood range, and the vehicle can meet the condition when running in the neighborhood range, wherein the neighborhood range can be that the reference track of the vehicle deviates 1.5 meters leftwards and deviates 1.5 meters rightwards, namely, the allowable track width is adjusted to be 3 meters wide. Of course, other ways may also be used to determine the neighborhood range of the reference trajectory of the vehicle, which is not limited in this description embodiment. In addition, the control amount of the vehicle also has a range, and may be a physical limit value of the control amount or the like, such as a turning angle of the vehicle which cannot exceed 60 ° or the like, which are known data. Only when the control quantity is adjusted within the control quantity range, the safety, stability and other performances of the vehicle can be ensured. After the control amount is adjusted in this way, the vehicle can be controlled to run according to the adjusted control amount.

The embodiment of the specification predicts a running track of a vehicle under a control quantity input condition according to a control quantity of the vehicle to be input, and then determines a difference between a reference track and the running track according to a preset reference track and the predicted running track as a basic track difference characteristic. In addition, the basic controlled variable characteristic, the basic change characteristic and the basic obstacle characteristic are respectively determined according to the controlled variable, the change of the controlled variable and the distance between the vehicle and each obstacle in the specified neighborhood range of the vehicle. And determining a target feature J (u) according to the weight w1 corresponding to the basic track difference feature and the track difference feature, the weight w2 corresponding to the basic control quantity feature and the control quantity feature, the weight w3 corresponding to the basic change feature and the change feature, and the weight w4 corresponding to the basic obstacle feature and the obstacle feature. And (5) taking the target characteristic minimization minJ (u) as an optimization target, adjusting the control quantity u, and controlling the vehicle to run according to the adjusted control quantity. In the embodiment of the specification, when the vehicle is controlled, not only the vehicle is uniformly kept consistent with the given reference track, but also factors such as the vehicle control quantity, the change of the vehicle control quantity, the distance between the vehicle and an obstacle in the surrounding environment information and the like are considered. Namely, the scheme considers the influence of factors such as energy consumption, safety and stability of the vehicle on the running of the vehicle. Therefore, when the given reference track is unreasonable, for example, the reference track jumps, the vehicle can also adjust the control quantity to be input to the vehicle by integrating the influence of various factors, so that the vehicle runs according to the adjusted control quantity.

The vehicle control method provided by the embodiment of the specification can enable the vehicle to run safely when the given reference track is unreasonable. The embodiment of the specification adjusts the control quantity to be input and controls the vehicle by comprehensively referring to the difference between the track and the driving track, the control quantity, the change of the control quantity, the distance between the vehicle and the obstacle and other factors.

The vehicle control method provided by the specification can be particularly applied to trajectory planning for unmanned vehicles. The unmanned vehicle can be an unmanned distribution vehicle, and the unmanned distribution vehicle can be applied to the field of distribution by using the unmanned distribution vehicle, such as the distribution scene of express delivery, takeaway and the like by using the unmanned distribution vehicle. Specifically, in the above-described scenario, delivery may be performed using an autonomous vehicle fleet configured with a plurality of unmanned delivery vehicles.

Based on the same idea, the present specification further provides a corresponding apparatus, a storage medium, and an electronic device.

Fig. 2 is a schematic structural diagram of a vehicle control device provided in an embodiment of the present specification, where the device includes:

the prediction module 200 is used for predicting the running track of the vehicle under the control quantity input condition according to the control quantity of the vehicle to be input;

a track difference characteristic determination module 202, configured to determine, according to a preset reference track of the vehicle and a predicted driving track of the vehicle under the control quantity input condition, a difference between the reference track and the driving track as a track difference characteristic;

a driving characteristic determination module 204, configured to determine a driving characteristic according to at least one of the control amount, the change of the control amount, and environmental information around the vehicle, where a smaller driving characteristic indicates a higher driving quality of the vehicle;

a target feature determination module 206, configured to determine a target feature according to the track difference feature and the driving feature;

an adjusting module 208, configured to adjust the control amount with the target feature minimum as an optimization target;

and the control module 210 is used for controlling the vehicle to run according to the adjusted control quantity.

Optionally, the driving characteristics include controlled variable characteristics, and the driving characteristic determining module 204 is specifically configured to determine the controlled variable characteristics according to the controlled variable and the weight corresponding to the controlled variable.

Optionally, the driving characteristics include change characteristics, and the driving characteristic determining module 204 is specifically configured to determine the change characteristics according to a change rate of a longitudinal acceleration of the vehicle, a change rate of a lateral acceleration of the vehicle, and a weight corresponding to the change characteristics.

Optionally, the driving characteristics include characteristics of obstacles, and the driving characteristic determining module 204 is specifically configured to determine, according to environmental information around the vehicle, each obstacle in a specified proximity of the vehicle; and determining the obstacle characteristics according to the distance between the vehicle and each obstacle in the specified neighborhood and the weight corresponding to the obstacle characteristics.

Optionally, the apparatus further includes a weight determining module 212, where the weight determining module 212 is specifically configured to: acquiring a plurality of expert data based on the preset reference track of the vehicle; determining a mean value of the plurality of expert data according to the target characteristics; determining a probability distribution, wherein the expected value of the probability distribution is the mean value of the plurality of expert data, and the probability distribution is related to the function corresponding to the target feature; and determining each weight in the target feature by adopting a maximum likelihood method according to the determined probability distribution.

Optionally, the target feature determining module 206 is specifically configured to identify a lane type of a lane in which the vehicle is located; and determining the target characteristics under the lane type condition according to the track difference characteristics, the driving characteristics and the lane type of the lane where the vehicle is located.

Optionally, the adjusting module 208 is specifically configured to adjust the controlled variable by taking the minimum target feature as an optimization target and taking the traveling track not exceeding the neighborhood range of the reference track and the controlled variable not exceeding a preset controlled variable range as limiting conditions.

The present specification also provides a computer readable storage medium storing a computer program which, when executed by a processor, is operable to perform a vehicle control method as provided in fig. 1 above.

Based on the vehicle control method shown in fig. 1, the embodiment of the present specification further provides a schematic structural diagram of the electronic device shown in fig. 3. As shown in fig. 3, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, but may also include hardware required for other services. The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to implement the vehicle control method described above with reference to fig. 1.

Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A vehicle control method characterized by comprising:

determining a driving characteristic according to at least one of the control quantity, the change of the control quantity and the environmental information around the vehicle, wherein the driving characteristic comprises at least one of a control quantity characteristic representing the stability of the vehicle, a change characteristic representing the comfort of the vehicle and an obstacle characteristic representing the safety of the vehicle, and the smaller the driving characteristic is, the higher the driving quality of the vehicle is represented;

and controlling the vehicle to run according to the adjusted control quantity.

2. The method of claim 1, wherein the travel characteristic comprises a control quantity characteristic;

determining the control quantity characteristics specifically comprises the following steps:

3. The method of claim 1, wherein the driving characteristics include a change characteristic;

determining the change characteristics specifically comprises the following steps:

and determining the change characteristics according to the change rate of the longitudinal acceleration of the vehicle, the change rate of the lateral acceleration of the vehicle and the weight corresponding to the change characteristics.

4. The method of claim 1, wherein the driving characteristics include obstacle characteristics;

determining obstacle characteristics, specifically comprising:

determining each obstacle in the specified neighborhood of the vehicle according to the environmental information around the vehicle;

and determining the obstacle characteristics according to the distance between the vehicle and each obstacle in the specified neighborhood and the weight corresponding to the obstacle characteristics.

5. The method of any of claims 2-4, wherein the method further comprises:

acquiring a plurality of expert data based on the preset reference track of the vehicle;

determining a mean value of the plurality of expert data according to the target characteristics;

determining a probability distribution, wherein the expected value of the probability distribution is the mean value of the plurality of expert data, and the probability distribution is related to the function corresponding to the target feature;

and determining each weight in the target feature by adopting a maximum likelihood method according to the determined probability distribution.

6. The method according to claim 1, wherein determining the target feature according to the trajectory difference feature and the driving feature specifically comprises:

identifying the lane type of a lane in which the vehicle is located;

and determining the target characteristics under the lane type condition according to the track difference characteristics, the driving characteristics and the lane type of the lane where the vehicle is located.

7. The method of claim 1, wherein adjusting the controlled variable with the target characteristic minimum as an optimization target comprises:

and adjusting the controlled variable by taking the minimum target characteristic as an optimization target and taking the running track not exceeding the neighborhood range of the reference track and the controlled variable not exceeding the preset controlled variable range as limiting conditions.

8. A vehicle control apparatus characterized by comprising:

the track difference characteristic determining module is used for determining the difference between a reference track and a predicted running track of the vehicle under the control quantity input condition according to the preset reference track of the vehicle and the predicted running track of the vehicle, and the difference is used as a track difference characteristic;

a driving characteristic determination module, configured to determine a driving characteristic according to at least one of the control quantity, the change of the control quantity, and environmental information around the vehicle, where the driving characteristic includes at least one of a control quantity characteristic representing vehicle stability, a change characteristic representing vehicle comfort, and an obstacle characteristic representing vehicle safety, and a smaller driving characteristic represents a higher driving quality of the vehicle;

9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-7 when executing the program.