CN117922615A

CN117922615A - Method and device for reducing adverse reactions of passengers in automatic driving public transportation risk avoidance scene

Info

Publication number: CN117922615A
Application number: CN202410331259.8A
Authority: CN
Inventors: 田建; 李志强; 姜一洲; 李彦霖; 周京; 彭建华; 姜瑶; 冯雯雯; 闫磊; 孟琳; 牟凯; 席建锋; 郑黎黎
Original assignee: China Academy of Transportation Sciences
Current assignee: China Academy of Transportation Sciences
Priority date: 2024-03-22
Filing date: 2024-03-22
Publication date: 2024-04-26

Abstract

The application relates to the technical field of automatic driving, and discloses a method for reducing adverse reactions of passengers in an automatic driving bus danger avoiding scene. The method comprises the following steps: for each of a plurality of planned travel schemes, obtaining the uncomfortable probability and the falling probability of each passenger under the planned travel scheme; determining a first probability threshold of the negative correlation according to the discomfort probability, and determining a second probability threshold of the negative correlation according to the falling probability; counting the first total number of the adverse reactions of the passengers under the planning driving scheme; the passenger status of adverse reactions include: the uncomfortable probability is larger than or equal to the second probability threshold value, and the falling probability is larger than or equal to the first probability threshold value; and taking the planned driving scheme corresponding to the minimum first total number as a selected driving scheme, and controlling the bus. By adopting the method, adverse reactions of passengers caused by emergency actions of the automatic driving buses can be reduced. The application also discloses a device for reducing adverse reactions of passengers in the automatic driving public transportation risk avoiding scene.

Description

Method and device for reducing adverse reactions of passengers in automatic driving public transportation risk avoidance scene

Technical Field

The application relates to the technical field of automatic driving, in particular to a method and a device for reducing adverse reactions of passengers in an automatic driving bus danger avoiding scene.

Background

At present, the automatic driving technology has an accurate risk early warning system and quick and stable decision capability, and has great potential in the bus industry facing heavy driving tasks and complex road environments due to the characteristics of automatic driving. For example, an automated driving bus can plan a driving scheme including a driving track, a driving speed, and the like based on real-time road conditions, and realize automated operation.

In the process of implementing the embodiment of the application, the related art is found to have at least the following problems:

Passengers in the bus are more generally, the bus driven automatically has sensitive reaction capability, and the sensitive reaction capability easily causes uncomfortable and falling adverse reactions of the passengers in the bus under the danger avoiding scene.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the application and thus may include information that does not form the prior art that is already known to those of ordinary skill in the art.

Disclosure of Invention

The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview, and is intended to neither identify key/critical elements nor delineate the scope of such embodiments, but is intended as a prelude to the more detailed description that follows.

The embodiment of the application provides a method and a device for reducing adverse reactions of passengers in an automatic driving bus danger avoiding scene, so as to reduce the adverse reactions of the passengers caused by emergency actions of the automatic driving bus.

In some embodiments, a method for reducing adverse reactions of passengers in an automatic driving bus danger avoidance scene comprises:

After obtaining a plurality of planning driving schemes, obtaining the uncomfortable probability of each passenger under the planning driving scheme and the falling probability of each passenger under the planning driving scheme for each planning driving scheme;

Determining a first probability threshold corresponding to the passenger according to the uncomfortable probability of each passenger, and determining a second probability threshold corresponding to the passenger according to the falling probability of each passenger; wherein the first probability threshold is inversely related to the discomfort probability and the second probability threshold is inversely related to the fall probability;

According to the magnitude relation between the uncomfortable probability and the second probability threshold value and the magnitude relation between the falling probability and the first probability threshold value, counting a first total number of the passengers in the planned driving scheme, wherein the passengers are in adverse reactions; wherein, for any passenger, the passenger status of the adverse reaction comprises: the discomfort probability is greater than or equal to the second probability threshold, and the fall probability is greater than or equal to the first probability threshold;

and regarding the planning running schemes, taking the planning running scheme corresponding to the minimum first total number as a selected running scheme, and controlling the bus according to the selected running scheme.

Optionally, determining a first probability threshold corresponding to each passenger according to the discomfort probability of each passenger includes:

；

wherein, For the first probability threshold,/>Is the maximum value of the first probability threshold value,/>Is the minimum value of the first probability threshold value,/>The discomfort probability corresponding to any passenger.

Optionally, determining a second probability threshold corresponding to each passenger according to the falling probability of each passenger includes:

；

wherein, For the second probability threshold,/>Is the maximum value of the second probability threshold value,/>Is the minimum value of the second probability threshold value,/>The probability of falling corresponding to any passenger.

Optionally, obtaining the probability of falling of each passenger under the planned driving scheme includes:

Acquiring the handrail state of each passenger under the planned driving scheme; wherein the armrest state is one of an armless state, a suspended armrest state and a fixed armrest state;

When the handrail state is the suspended handrail state, the falling probability of any passenger under the planned driving scheme is calculated by the following mode:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the probability of fall under the present planned driving scenario,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the height of the armrest relative to the floor in the vehicle,/>For the discomfort probability,/>Representing a correction function corresponding to the discomfort probability,/>For passenger sex,/>For the age of the passenger,/>Representation of passenger gender/>Age of passengerCorresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the height of the passenger,/>Is the first correction coefficient;

And/or the number of the groups of groups,

When the handrail state is the fixed handrail state, the falling probability of any passenger under the planned driving scheme is calculated by the following mode:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the probability of fall under the nth planned driving scenario,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the discomfort probability,/>Representing a correction function corresponding to the discomfort probability,/>For passenger sex,/>For the age of the passenger,/>Representation of passenger gender/>Passenger age/>Corresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the bus acceleration direction under the planning driving scheme in the nth step,/>For the connection line direction of the mass center of the passenger and the handrail in the state that the passenger does not fallIs an included angle function of two directions and is used for correcting the standard maintenance stable grip strength/>, of a passenger in a gripping mode，/>Is the second correction coefficient;

And/or the number of the groups of groups,

When the handrail state is the armless state, the falling probability of any passenger under the planned driving scheme is calculated by the following method:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For planning the probability of fall under the driving scheme in the nth, v >In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the height of the passenger,/>、/>And/>Is a regression coefficient.

Optionally, the uncomfortable probability of each passenger under the planned driving scheme is obtained through the following structural equation model:

；

wherein, For the discomfort probability,/>For the endophytic latent variable matrix,/>Is exogenous latent variable matrix,/>Is an interference coefficient matrix,/>For the endophytic latent variable matrix/>Probability of discomfort/>First influence coefficient matrix,/>For the exogenous latent variable matrix/>Probability of discomfort/>A second influence coefficient matrix,/>Is an exogenous variable matrix,/>For the exogenous matrix/>At the exogenous latent variable matrix/>First load matrix,/>For the exogenous matrix/>First measurement error matrix,/>For the endogenous variable matrix,/>For the matrix/>Within the endophytic latent variable matrix/>Second load matrix on,/>For the endogenous variable matrix/>Is a second measurement error matrix of (a).

Optionally, the endogenous variable matrixAnd/or the exogenous matrix/>The elements of (2) are divided into two classes, one class being sequential arguments and the other class being classification arguments.

Optionally, the obtaining manner of the sequence display variable includes: mapping the obtained original variable value into a preset numerical value interval;

the obtaining mode of the classification explicit variable comprises the following steps: and presetting more than two thresholds in a preset numerical value interval, and mapping the obtained original variable value into one of the more than two thresholds.

Optionally, the endogenous variable matrixThe elements of (1) include: one or more of an in-vehicle environmental parameter, a passenger physiological parameter; the in-vehicle environmental parameters include one or more of passenger loading rate, in-vehicle temperature, in-vehicle humidity, in-vehicle noise, in-vehicle carbon dioxide content.

Optionally, the exogenous variable matrixThe elements of (1) include: natural environment, handrail parameters, driving parameters, passenger-specific information, and journey attributes.

Optionally, obtaining a plurality of planned driving schemes includes: under the danger avoiding scene, acquiring a first kinematic parameter of the bus and a second kinematic parameter of a risk vehicle; and taking the bus and the risk vehicle as targets for avoiding collision, and obtaining a plurality of planning driving schemes of the bus according to the first kinematic parameters and the second kinematic parameters.

Optionally, the method for reducing adverse reactions of passengers in the automatic driving bus danger avoiding scene further comprises the following steps: obtaining the total time period from the beginning to the end of the planning driving scheme; dividing the total time period into a plurality of step sizes according to a preset time interval; in each step, the passenger status is counted as a second total number of adverse reactions.

Optionally, counting the first total number of adverse reactions of the passenger state under the planned driving scheme includes: and taking the sum of the second total number obtained in all step sizes of the planning driving scheme as the first total number.

Optionally, after taking the planned driving scheme corresponding to the minimum first total number as the selected driving scheme, the method for reducing adverse reactions of passengers in the automatic driving bus danger avoidance scene further comprises: taking the passenger corresponding to the adverse reaction of the passenger state in the selected driving scheme as a target passenger; and reminding the target passenger to remind the target passenger to finish preparation for coping.

In some embodiments, an apparatus for reducing adverse effects of passengers in an autopilot bus risk avoidance scenario includes a processor and a memory storing program instructions, the processor being configured, when executing the program instructions, to perform the method for reducing adverse effects of passengers in an autopilot bus risk avoidance scenario provided in the foregoing embodiments.

The automatic driving bus danger avoiding scene provided by the embodiment of the application is less, and the following technical effects can be realized:

In the danger avoiding scene of the automatic driving bus, the bus can plan a plurality of planning driving schemes, and the reaction states (namely, the passenger states) of passengers in the bus are different in each planning driving scheme, wherein the passenger states comprise benign reactions and adverse reactions; the comfort level of the passenger in the passenger perception and whether the passenger falls down are two dimensions, so that whether the passenger state belongs to benign reaction or adverse reaction is determined. In one dimension, taking the passenger state with the discomfort probability being greater than or equal to the second probability threshold as the passenger state of the adverse reaction; in another dimension, the passenger status with a probability of falling greater than or equal to the first probability threshold is taken as the passenger status for the adverse reaction.

In the confirmation process, a cross confirmation method is adopted: a comfort dimension in the perception of the passenger, the threshold for determining an adverse reaction being a second probability threshold that is positively correlated with the probability of a fall of the passenger; in the dimension of whether a fall phenomenon occurs, the threshold value for determining an adverse reaction is a first probability threshold value, which is positively correlated with the uncomfortable probability of the passenger.

By adopting the technical scheme, for any passenger, under the condition that the falling probability is unchanged, if the uncomfortable probability of the passenger is larger, the first probability threshold value is smaller, and in the dimension of whether the falling phenomenon occurs, the passenger state is more easily judged as adverse reaction; correspondingly, in the case where the probability of discomfort is unchanged, if the probability of fall of the passenger is relatively large, the second probability threshold is small, and the passenger state is more easily determined as an adverse reaction in the dimension of comfort in the passenger perception.

In another aspect, for any passenger, in the case that the discomfort probability is relatively high, the high discomfort probability is more likely to be greater than or equal to the second probability threshold, that is, the comfort dimension in passenger perception is more likely to be the determination result of the passenger state as an adverse reaction, and at the same time, the first probability threshold is smaller, so that the determination result of the passenger state as an adverse reaction is also more likely to be the determination result of whether the falling phenomenon occurs in the dimension of whether the falling phenomenon occurs; for any passenger, in the case that the falling probability is relatively large, the large falling probability is more likely to be larger than or equal to the first probability threshold, that is, in the dimension of whether the falling phenomenon occurs, the determination result that the passenger state is an adverse reaction is more likely to occur, and at the same time, the second probability threshold is smaller, so in the comfort dimension in the passenger perception, the determination result that the passenger state is an adverse reaction is also more likely to occur.

By adopting the cross-validation method, whether the passenger state is an adverse reaction or not can be judged more accurately as a whole.

The present application relates to a method for determining the state of passengers, and more particularly to a method for determining the state of passengers in buses, which comprises the steps of selecting a selected driving scheme from a plurality of planning driving schemes capable of achieving the purpose (such as realizing risk avoidance) based on the prediction result of the state of passengers in the buses, wherein the selected driving scheme is a driving state which does not occur currently, and the method can be used for determining whether the state of the passengers is an adverse reaction more accurately in the whole.

The bus is controlled based on the selected driving scheme, so that adverse reaction of passengers on the whole can be reduced in the danger avoiding scene of the bus.

The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.

Drawings

One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which:

Fig. 1 is a schematic flow chart of a method for reducing adverse reactions of passengers in an automatic driving bus danger avoidance scene provided by an embodiment of the application;

FIG. 2 is a schematic illustration of a process for obtaining a probability of each passenger falling under the planned driving schedule according to an embodiment of the present application;

Fig. 3 is a schematic diagram of a process of obtaining adverse reactions of passengers under the planned driving scenario according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a process for obtaining multiple planning schemes according to an embodiment of the application;

FIG. 5 is a schematic diagram of a reminding process according to an embodiment of the application;

Fig. 6 is a schematic diagram of a device for reducing adverse reactions of passengers in an automatic driving bus danger avoiding scene provided by an embodiment of the application;

fig. 7 is a schematic diagram of an autopilot bus according to an embodiment of the present application.

Detailed Description

For a more complete understanding of the nature and the technical content of the embodiments of the present application, reference should be made to the following detailed description of embodiments of the application, taken in conjunction with the accompanying drawings, which are meant to be illustrative only and not limiting of the embodiments of the application. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawing.

The terms first and second and the like in the description and in the claims of embodiments of the application and in the above-described figures are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe embodiments of the application herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.

The term "plurality" means two or more, unless otherwise indicated.

In the embodiment of the application, the character "/" indicates that the front object and the rear object are in an OR relationship. For example, A/B represents: a or B.

The term "and/or" is an associative relationship that describes an object, meaning that there may be three relationships. For example, a and/or B, represent: a or B, or, A and B.

In the embodiment of the application, the passenger state with the uncomfortable probability larger than or equal to the second probability threshold is taken as the passenger state of the adverse reaction, the passenger state with the falling probability larger than or equal to the first probability threshold is taken as the passenger state of the adverse reaction, and the cross confirmation mode is adopted, so that the influence of the uncomfortable probability and the falling probability on the whole passenger is fully represented for any passenger, and whether the passenger state is the adverse reaction can be judged more accurately on the whole. Based on the accurate judgment result, determining a selected driving scheme in a plurality of planning driving schemes, and controlling the bus according to the selected driving scheme so as to achieve the following technical effects: the phenomenon that passengers react adversely on the whole is reduced in the danger avoiding scene of the bus.

Fig. 1 is a schematic flow chart of a method for reducing adverse reactions of passengers in an automatic driving bus danger avoidance scene provided by an embodiment of the application. The method can be performed in a controller of the autonomous bus or in a cloud platform in case the autonomous bus is already connected to the cloud platform.

Referring to fig. 1, the method for reducing adverse reactions of passengers in the automatic driving bus danger avoiding scene includes:

s101, after a plurality of planning driving schemes are obtained, for each planning driving scheme, obtaining the uncomfortable probability of each passenger under the planning driving scheme and obtaining the falling probability of each passenger under the planning driving scheme.

The specific methods for obtaining the plurality of planned driving schemes may be determined empirically by those skilled in the art, including but not limited to: collision avoidance methods (e.g., field potential based methods, fuzzy logic based methods, machine learning based methods, trajectory planning based methods, agent system based methods, model predictive control based methods, etc.), artificial intelligence planning methods, and the like.

The present planning scheme in the above steps refers to any one of a plurality of planning driving schemes.

Of course, the embodiment of the application is based on the danger avoiding scene, and the proposed method for reducing adverse reactions of passengers in the danger avoiding scene of the automatic driving bus is generally used for avoiding collision and collision of two automobiles and avoiding pedestrians in the automatic driving bus; the risk avoidance scenario can also be interpreted broadly as: the motion state of the bus has abrupt change, such as a scene of turning at an intersection, a parking scene of meeting a red light at the intersection, a bus starting scene, a bus arrival parking scene and the like.

The person skilled in the art can empirically obtain the probability of discomfort for each passenger under the present planned driving schedule, e.g. the greater the instantaneous acceleration in the planned driving schedule, the greater the probability of discomfort for each passenger.

The person skilled in the art can empirically obtain the probability of falling for each passenger under the present planned driving schedule, e.g., the greater the instantaneous acceleration in the planned driving schedule, the greater the probability of falling for each passenger.

In the embodiment of the application, the discomfort probability can also be used for the discomfort degree of the passengers, wherein the greater the discomfort probability is, the higher the discomfort degree of the passengers is.

S102, determining a first probability threshold corresponding to the passenger according to the uncomfortable probability of each passenger, and determining a second probability threshold corresponding to the passenger according to the falling probability of each passenger.

Wherein the first probability threshold is inversely related to the discomfort probability and the second probability threshold is inversely related to the fall probability.

Optionally, determining the first probability threshold corresponding to the passenger according to the uncomfortable probability of each passenger includes:

for any passenger:

Obtaining a first probability range corresponding to the uncomfortable probability of any passenger in a plurality of preset probability ranges; and determining a first probability threshold corresponding to the first probability range according to the corresponding relation between the first probability range and the first probability threshold.

The correspondence between the first probability range and the first probability threshold may be stored in a one-to-one correspondence data table, and after the first probability range corresponding to the uncomfortable probability of any passenger is obtained, the first probability threshold corresponding to the first probability range may be obtained by querying the data table.

Or determining a first probability threshold corresponding to the passenger according to the uncomfortable probability of each passenger can comprise:

for any passenger:

Determining a first probability threshold corresponding to the uncomfortable probability of any passenger according to the functional relation between the uncomfortable probability and the first probability threshold;

the functional relationship between the discomfort probability and the first probability threshold is a pre-established functional relationship, and the functional relationship can be a linear functional relationship. For example:

；

wherein, For the first probability threshold,/>Is the maximum value of the first probability threshold value,/>Is the minimum value of the first probability threshold value,/>A probability of discomfort for any passenger.

Alternatively, the foregoing functional relationship may be an exponential functional relationship, that is, in the process of determining the first probability threshold corresponding to each passenger according to the uncomfortable probability of the passenger, the method may include:

；

Thus, for any passenger, the first probability threshold is reduced more and more rapidly as the probability of discomfort increases linearly, that is, as the probability of discomfort increases linearly, the probability of occurrence of a determination result that the passenger state is an adverse reaction will increase exponentially in the dimension of whether a fall phenomenon occurs. This is advantageous in that the determination result of whether the passenger state is an adverse reaction can be obtained more accurately as a whole.

Optionally, determining the second probability threshold corresponding to the passenger according to the falling probability of each passenger includes:

for any passenger:

Acquiring a second probability range corresponding to the falling probability of any passenger in a plurality of preset probability ranges; and determining a second probability threshold corresponding to the second probability range according to the corresponding relation between the second probability range and the second probability threshold.

The correspondence between the second probability range and the second probability threshold value can be stored in a one-to-one correspondence data table, and after the second probability range corresponding to the falling probability of any passenger is obtained, the second probability threshold value corresponding to the second probability range can be obtained by querying the data table.

Or determining a second probability threshold corresponding to the passenger according to the falling probability of each passenger can comprise:

for any passenger:

determining a second probability threshold corresponding to the falling probability of any passenger according to the functional relation between the falling probability and the second probability threshold;

The functional relationship between the falling probability and the second probability threshold is a pre-established functional relationship, and the functional relationship can be a linear functional relationship. For example:

；

wherein, Is a second probability threshold,/>Is the maximum value of the second probability threshold value,/>Is the minimum value of the second probability threshold value,/>Is the corresponding falling probability of any passenger.

；

As such, for any passenger, the second probability threshold is reduced faster and faster as the linearity of the probability of a fall increases, i.e., the probability of occurrence of a determination result that the passenger state is an adverse reaction will exhibit an exponential increase as the linearity of the probability of a fall increases, which is the comfort dimension in the passenger perception. This is advantageous in that the determination result of whether the passenger state is an adverse reaction can be obtained more accurately as a whole.

In the above embodiment, three ways of determining the first probability threshold and three ways of determining the second probability threshold are listed, and it should be noted that the specific way of determining the first probability threshold may be different from the specific way of determining the second probability threshold, that is, the first probability threshold may be determined by any of the three ways, or the second probability threshold may be determined by any of the three ways.

The maximum value and the minimum value of the first probability threshold can be obtained through a test mode, and under the condition that the falling probability is the minimum value of the first probability threshold, the passenger state has the risk of falling, but is not easy to fall too easily; in the case where the probability of falling is the maximum value of the first probability threshold, the passenger state is liable to fall, but the falling event at this time should not be a large probability event in the probability concept. The person skilled in the art can determine that the passenger state is at risk of falling according to his own experience and actual requirements, but the passenger state is not too easy to fall, and the falling event should not be a concrete scene of a large probability event in the probability concept.

The maximum and minimum values of the second probability threshold may also be obtained experimentally. In case the discomfort probability is the minimum of the second probability threshold, the passenger should be able to feel the discomfort to a low degree; in case the discomfort probability is the maximum value of the second probability threshold, the passenger should be able to feel the discomfort higher. Those skilled in the art can determine the specific passenger states corresponding to the above-mentioned "the passenger can feel discomfort to a low degree" and "the passenger can feel discomfort to a high degree" according to their own experiences and actual demands.

S103, counting the first total number of the passengers in the planned driving scheme as adverse reactions according to the magnitude relation between the uncomfortable probability and the second probability threshold value and the magnitude relation between the falling probability and the first probability threshold value.

Wherein, for any passenger, the passenger status of the adverse reaction includes: the discomfort probability is greater than or equal to the second probability threshold and the fall probability is greater than or equal to the first probability threshold.

Specifically, the passenger status of the adverse reaction includes the following three cases: the uncomfortable probability is greater than or equal to a first preset probability threshold, the falling probability is greater than or equal to a second preset probability threshold, the uncomfortable probability is greater than or equal to the first preset probability threshold, and the falling probability is greater than or equal to the second preset probability threshold.

In some application scenarios, if the discomfort probability corresponding to a passenger state is greater than or equal to a first preset probability threshold value, and the fall probability is less than a second preset probability threshold value, determining the passenger state as a bad state; if the discomfort probability corresponding to the passenger is smaller than the first preset probability threshold value and the falling probability is larger than or equal to the second preset probability threshold value, determining the passenger state as a bad state; and if the discomfort probability corresponding to the passenger is greater than or equal to the first preset probability threshold value and the falling probability is greater than or equal to the second preset probability threshold value, determining the passenger state as a bad state.

After all the passenger states under the planning driving scheme are judged for one time according to the magnitude relation between the uncomfortable probability and the second probability threshold value and the magnitude relation between the falling probability and the first probability threshold value, all the passenger states under the planning driving scheme can be obtained, and therefore the first total number of the passenger states under the planning driving scheme as adverse reactions can be counted.

And S104, regarding the planning driving schemes, taking the planning driving scheme corresponding to the minimum first total number as a selected driving scheme, and controlling the bus according to the selected driving scheme.

After the confirmation and statistics processes in S101 to S103 are performed on each planned driving scheme, a first total number corresponding to each planned driving scheme may be obtained. And selecting the minimum first total number from the plurality of first total numbers, and taking the planning running scheme corresponding to the minimum first total number as the selected running scheme.

One skilled in the art can determine, based on experience, the specific process of controlling a bus according to a selected driving scheme.

The following exemplifies the procedure of obtaining the uncomfortable probability for each passenger under the present planned travel scenario in S101.

；

wherein, Is uncomfortable probability,/>For the endophytic latent variable matrix,/>Is exogenous latent variable matrix,/>Is an interference coefficient matrix,/>For endogenous latent variable matrix/>Probability of discomfort/>First influence coefficient matrix,/>For exogenous latent variable matrix/>Probability of discomfort/>A second influence coefficient matrix of (a); first influence coefficient matrix/>Second influence coefficient matrix/>Interference coefficient matrix/>All obtained through experiments; /(I)Is an exogenous variable matrix,/>For exogenous variable matrix/>In exogenous latent variable matrix/>First load matrix on, first load matrix/>Can be obtained by experiment,/>For exogenous variable matrix/>Is a first measurement error matrix of (a); /(I)For the endogenous variable matrix,/>For the endogenous variable matrix/>In-growth latent variable matrix/>A second load matrix on the first and second load matrices/>Can be obtained by experiment,/>For the endogenous variable matrix/>Is a second measurement error matrix of (a).

In some application scenarios, an endogenous variable matrixThe elements in (a) include in-vehicle environment parameters including one or more of passenger loading rate, in-vehicle temperature, in-vehicle humidity, in-vehicle noise, in-vehicle carbon dioxide content, in-vehicle ground friction coefficient, and the like. The above-mentioned in-vehicle friction coefficient is usually a static friction coefficient.

The passenger load rate can be obtained through detection of the image recognition device, the temperature in the vehicle can be obtained through the temperature sensor, the noise in the vehicle can be obtained through the noise sensor, the carbon dioxide content in the vehicle can be obtained through the carbon dioxide sensor, and the ground friction coefficient in the vehicle can be obtained through the friction coefficient detection device. The passenger load rate, the temperature in the vehicle, the humidity in the vehicle, the noise in the vehicle and the carbon dioxide content in the vehicle can be obtained in real time, and the ground friction coefficient in the vehicle can be obtained at one time or can be obtained periodically (such as one month, half year and one year).

In other application scenarios, an endogenous variable matrixIncluding passenger physiological parameters such as one or more of passenger heart rate, passenger blood pressure, respiratory rate.

The endogenous variable matrixMay be in the form of M ₁ X1, or may also be in the form of 1X M ₁, M ₁ being the total number of endogenous display variables obtained.

For ease of computation, the endogenous variable matrix is typically madeThe obtained original variable value can be mapped into a preset value interval, and/or more than two thresholds are preset in the preset value interval, and the obtained original variable value is mapped into one of the more than two thresholds.

For convenience of the following description, the variables mapped to the preset numerical intervals may be referred to as sequential display variables; the above-described variables mapped to one of the two or more thresholds may be referred to as classification variables.

Typically, the above-mentioned preset value range is [0,1], i.e., normalization processing. Of course, in some special scenarios, the person skilled in the art may also set the above-mentioned preset value range empirically, so as to facilitate calculation.

Typically, two thresholds are set within a preset value interval, e.g., 0 and 1 in a preset value range [0,1] are taken as thresholds. This situation belongs to a two-class process, a more common class approach. Of course, in some special scenarios, one skilled in the art may also empirically determine more than two thresholds in a preset value interval to facilitate accurate calculation.

In-growth variable matrixIn the case where the variables in (a) comprise both classification variables, the probability of discomfort/>, for the final calculated occupant, of the classification variable can be better measuredIs a non-linear influence of (c).

The passenger load rate, the temperature in the vehicle, the humidity in the vehicle, the noise in the vehicle, the carbon dioxide content in the vehicle and the ground friction coefficient in the vehicle can be used as sequence display variables.

Of course, in-vehicle noise may also be used as a classification argument, e.g., no noise: 0, noisy: 1.

The content is to an endogenous variable matrixExemplary descriptions are made below, in the same manner, for the matrix/>, of exogenous variablesAn exemplary description is made.

In some application scenarios, the exogenous variable matrixIncluding one or more of natural environment parameters, handrail parameters, driving parameters, passenger-specific information, and journey attributes. Wherein the natural environment parameters include one or more of lighting conditions and weather conditions; the handrail parameters include one or more of handrail category, handrail height; the driving parameters include one or more of speed, acceleration, steering angle and turning radius; the passenger inherent information includes one or more of age, sex, height and weight; the travel attributes include one or more of a current travel duration, a current standing travel duration, a riding status, and a handset use case.

Wherein the natural environment parameter affects an in-vehicle environment parameter.

The age, height and weight can be estimated by means of image recognition. Age may be expressed in terms of age groups.

The exogenous variable matrixMay be in the dimension M ₂ X1, or may also be in the dimension 1X M ₂, M ₂ being the total number of exogenous variables obtained.

For ease of computation, the exogenous variables are typically matrixThe obtained original variable value can be mapped into a preset value interval, and/or more than two thresholds are preset in the preset value interval, and the obtained original variable value is mapped into one of the more than two thresholds.

Also, the above-described variables mapped into the preset numerical intervals may be referred to as sequential display variables; the above-described variables mapped to one of the two or more thresholds may be referred to as classification variables.

Externally generated variable matrixIn the case where the variables in (a) comprise both classification variables, the probability of discomfort/>, for the final calculated occupant, of the classification variable can be better measuredIs a non-linear influence of (c).

Further, the armrest height, speed, acceleration, steering angle, turning radius, age, height, weight, current travel duration, and current standing travel duration are all used as sequence variables.

The above-mentioned lighting conditions (sufficient lighting: 0, darkness: 1), weather conditions (sunny: 0, others: 1), handrail category (hanging handrail: 0, others: 1), sex (female: 0, male: 1), riding status (having seat riding: 0, standing riding: 1), mobile phone use condition (not using mobile phone: 0, using mobile phone: 1) can be used as classification display variables.

In the previous embodiment, it was mentioned several times that a certain parameter was obtained by means of a test, during which the probability of discomfortCan be represented as 0 or 1 as a classification argument.

Of course, in the case where three or more thresholds are set in the preset numerical range [0,1], the passenger uncomfortable probabilityCan be any of {0,0.2,0.4,0.6,0.8,1 }. In this case, during the test, 6 discomfort levels can be set in the questionnaire to obtain the discomfort probability/>, in each case。/>

Although during the course of the test, the probability of discomfortThe method is embodied in the form of classified apparent variables, and the actual application state and each detection parameter involved in the test process are necessarily different to a certain extent, and in this case, the finally calculated discomfort probability is usually embodied in the form of sequential apparent variables.

The following is an exemplary description of the procedure for obtaining the uncomfortable probability of each passenger under the planned driving plan through the structural equation model, with one possible overall plan.

；

The parameters in the structural equation model are described in detail in the foregoing, and will not be described in detail here.

The exogenous variable matrix can be set with reference to Table 1Exogenous latent variable matrix/>Endogenous variable matrix/>Endogenous latent variable matrix/>。

Table 1 partitioning of variables look-up table:

in combination with Table 2, the apparent variables are mapped into a range of values of [0,1 ].

Table 2 variable map table

Display variable	Code assignment
		Event category	Normal: 0. discomfort: 1
Passenger load rate	Normalized encoding by value size
		In-vehicle temperature	Normalized encoding by value size
Humidity in vehicle	Normalized encoding by value size
		Noise in vehicle	Normalized encoding by value size
Coefficient of friction of the ground in a vehicle	Normalized encoding by value size
		Illumination conditions	The illumination is sufficient: 0. dark: 1
Weather conditions	Sunny days: 0. other: 1
		Armrest category	Hanging handrail: 0. other: 1
Height of armrest	Normalized encoding by value size
		Speed of speed	Normalized encoding by value size
Acceleration of	Normalized encoding by value size
		Steering angle	Normalized encoding by value size
Radius of turning	Normalized encoding by value size
		Age of	Normalized encoding by value size
Sex (sex)	Female: 0. male: 1
		Height of body	Normalized encoding by value size
Weight of body	Normalized encoding by value size
		Current length of travel	Normalized encoding by value size
Current length of standing travel	Normalized encoding by value size
		Riding state	Riding with seats: 0. standing riding: 1
Mobile phone service condition	Unused cell phone: 0. using a mobile phone: 1

Firstly, obtaining uncomfortable probability of passengers at one moment by a random sampling methodMatrix of endogenous display variablesExogenous apparent variable matrix/>The uncomfortable probability/>, of passengers getting off at one momentEndogenous variable matrix/>Exogenous apparent variable matrix/>As one set of data, a plurality of sets of data are thus obtained. The number of data sets is required to be able to calculate the first influence coefficient matrix/>Second influence coefficient matrix/>Interference coefficient matrix/>First load matrix/>First measurement error matrix/>Second load matrix/>Second measurement error matrix/>。

Fig. 2 is a schematic diagram of a process for obtaining a probability of falling for each passenger under the planned driving scenario according to an embodiment of the present application.

As shown in fig. 2, obtaining the probability of falling of each passenger under the planned driving scenario includes:

S201, the handrail state of each passenger under the planned driving scheme is obtained.

The handrail status in the embodiment of the present application is different from the handrail type in the previous embodiment, and the handrail status in the embodiment of the present application is used to indicate the action relationship between the passenger and the handrail.

The armrest state is one of an armless state, a suspended armrest state and a fixed armrest state.

The armless state means that the passengers are in a standing state without protective measures, or no armrests are arranged in the vehicle, or armrests are arranged in the vehicle, but the passengers are not supported;

The suspended handrail state indicates a standing state in which the passenger holds the suspended handrail;

the stationary armrest state indicates that the occupant has held a stationary support, such as the occupant having held a stationary armrest, or the occupant has held a seat back.

The armrest status of the passenger may be determined by means of image recognition.

S202, determining a calculation mode according to the handrail state, and calculating the falling probability of each passenger under the planned driving scheme.

The following is classified into three cases according to the handrail state, and a specific manner of calculating the probability of falling of each passenger under the present planned travel plan in each case is exemplified.

Under the condition that the handrail state is the armless state, the falling probability of each passenger under the planning driving scheme is obtained by the following mode:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For planning the probability of falling under the driving scheme in the nth, the method comprises the following steps ofIn order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the height of the passenger,、/>And/>Is a regression coefficient.

Under the condition that the handrail state is the fixed handrail state, the falling probability of any passenger under the planning driving scheme is calculated by the following mode:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the falling probability under the planning driving scheme,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the height of the armrest relative to the floor in the vehicle,/>Is uncomfortable probability,/>Representing a correction function corresponding to the discomfort probability,/>For the sex of the passenger,For the age of the passenger,/>Representation of passenger gender/>Passenger age/>Corresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the height of the passenger,/>Is the first correction coefficient.

The correction functionMaintaining stable grip strength for correction criteria/>Correction function/>And discomfort probability/>And (5) negative correlation.

Thus, the probability of falling for each passenger under the present planned travel scenario is defined as: and determining the falling probability of each passenger according to the uncomfortable probability of each passenger under the planning driving scheme.

This enables a relatively accurate probability of fall to be obtained, and further a relatively accurate passenger status, and thus a relatively accurate selected travel plan to be selected.

When the handrail state is the suspended handrail state, the falling probability of any passenger under the planned driving scheme is calculated by the following method:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the probability of falling under the nth planning driving scheme,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>In order to be a probability of discomfort, the user,Representing a correction function corresponding to the discomfort probability,/>For passenger sex,/>For the age of the passenger,/>Representation of passenger gender/>Passenger age/>Corresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the bus acceleration direction under the planning driving scheme in the nth step,/>For the connection line direction of the mass center of the passenger and the handrail in the state that the passenger does not fallIs an included angle function of two directions and is used for correcting the standard maintenance stable grip strength/>, of a passenger in a gripping mode，/>Is the second correction coefficient.

Thus, the probability of falling for each passenger under the present planned travel scenario is defined as: and determining the falling probability of the passenger according to the uncomfortable probability of each passenger under the planning driving scheme.

The standard maintains stable grip strengthFor example, the standard holding power for an adult man may be 450N.

The correction functionCan be obtained by experimental means. The correction function/>Maintaining stable grip strength for correction criteria/>Thus,/>The standard that can be used to represent passengers of different genders, different age groups maintains a stable grip, or the limit maintains a stable grip (maximum grip of passengers in an emergency).

The correction functionCan be obtained by experimental means. The correction function/>Also used for correcting standard to maintain stable grip strength/>Thus,/>The standard that can be used to indicate a passenger in different comfort conditions maintains a stable grip, or the extreme maintains a stable grip.

The above-mentioned angle functionMay be a cosine function.

In the foregoing embodiment, the probability of discomfort and the probability of fall are calculated for each passenger of each planned travel plan.

The internal and external variable matrices involved in calculating the discomfort probability may be represented by average values of the variables measured during a period from the start time to the end time of the travel plan, or by the worst values of the variables measured during a period from the start time to the end time of the travel plan, the worst values representing the worst values that are likely to cause discomfort to the passengers.

The mean or maximum value of the inertial forces involved in calculating the probability of a fall can be obtained by planning the time period from the start to the end of the driving scheme.

In a specific scenario, each planned driving scenario may last for a period of time during which each moment may cause the passenger to feel discomfort or to fall. For this case, as shown in connection with fig. 3, the process of obtaining the passenger adverse reaction under the planned travel plan includes:

S301, obtaining the total time period from the beginning to the end of the planned driving scheme.

S302, dividing the total time period into a plurality of step sizes according to a preset time interval.

S303, counting the second total number of the adverse reactions of the passenger state in each step.

That is, in each step, the following steps are performed: obtaining the uncomfortable probability of each passenger under the planning driving scheme, obtaining the falling probability of each passenger under the planning driving scheme, determining a first probability threshold corresponding to the passenger according to the uncomfortable probability of each passenger, determining a second probability threshold corresponding to the passenger according to the falling probability of each passenger, and counting the second total number of adverse reactions of the passenger states under the planning driving scheme in the step length according to the magnitude relation between the uncomfortable probability and the second probability threshold and the magnitude relation between the falling probability and the first probability threshold.

The way of dividing the step length and calculating the adverse reaction of the passengers in each step length can calculate the adverse reaction of the passengers more accurately.

On this basis, the step S103 counts the first total number of adverse reactions of the passenger status under the present planned driving scenario, including: and taking the sum of the second total number obtained in all step sizes of the planning driving scheme as the first total number.

In this technical solution, the number of the second total number is the same as the number of the steps divided by one planned driving scheme (such as the present planned driving scheme), and if the lengths of the time periods from the starting time to the ending time of the driving scheme are different for different planned driving schemes, the number of the second total number corresponding to the planned driving scheme is also different.

The required growth probabilities of the different planning driving schemes are different, and then the number of the second total numbers corresponding to the different planning driving schemes is also different in probability.

Under the condition that the number of passengers in the bus is unchanged, the difference of the first total number is easy to cause the difference of the first total number, however, in the process of determining the selected running scheme in the planning running schemes, the change of the number of the second total number is not involved, the maximum value is still determined in the first total numbers, and the planning running scheme corresponding to the minimum first total number is used as the selected running scheme.

This can result in: when the time consumption of the planning driving scheme is long, the number of the second total number corresponding to the planning driving scheme is large, and the numerical value of the first total number is easy to be large; when the time consumption of the planning driving scheme is shorter, the number of the second total number corresponding to the planning driving scheme is smaller, which easily results in the smaller value of the first total number. Namely, the selected driving scheme is more prone to be completed in a short time, the duration of tension (an uncomfortable state) generated by the process of avoiding passengers is reduced, danger avoidance is easy to complete in time, and traffic jam is reduced; and once the long-time-consuming planning driving scheme is determined as the selected driving scheme, the uncomfortable phenomenon (or uncomfortable phenomenon and falling phenomenon) of passengers generated by each step in the planning driving scheme is very little, which is more beneficial to reducing the adverse reaction of passengers in the vehicle.

In the case of dividing the step length for each planned driving scheme, the vehicle is subjected to inertia force in the case of braking and/or turningCan be obtained by the following means:

；

wherein, For planning the starting time of the driving scheme,/>For planning the end time of the driving scheme,/>From the start time/>, as step size numberAny time/>Number of time steps passed,/>As a rounding function,/>For standing passengers at time t, the inertia force of the standing passengers due to acceleration and deceleration of the bus is/(are)For the weight of the passenger,/>For the acceleration of the bus at the moment t,/>For the moment t, the inertia force of standing passengers caused by the steering of buses,/>For planning the speed of the bus at the beginning of the driving scheme,/>For the turning radius of the bus turning at the moment t,/>The inertia force (resultant force) of the standing passenger at the moment t.

Fig. 4 is a schematic diagram of a process for obtaining multiple planning schemes according to an embodiment of the present application.

As shown in connection with fig. 4, a plurality of planned travel scenarios are obtained, including:

S401, acquiring a first kinematic parameter of the bus and a second kinematic parameter of a risk vehicle in the risk avoidance scene.

The first kinematic parameters include: a first position, a first speed, and a first acceleration; the second kinematic parameters include a second position, a second speed, and a second acceleration.

In the embodiment of the present application, the term "present" in the term "present bus" is used to distinguish between vehicles at risk. The risk vehicles are of any vehicle type and the number of risk vehicles is any number.

The method for reducing adverse reactions of passengers in the automatic driving bus danger avoiding scene can further comprise the following steps before the plurality of planning driving schemes are obtained: predicting the driving risk through traffic environment information, and under the condition that the formed risk is greater than or equal to the critical accident risk amount, predicting a conflict vehicle (risk vehicle), a conflict position and a conflict occurrence time, starting to enter a risk avoidance scene, and obtaining a first kinematic parameter of the bus and a second kinematic parameter of the risk vehicle.

S402, taking the bus and the risk vehicle as targets for avoiding collision, and obtaining a plurality of planning driving schemes of the bus according to the first kinematic parameters and the second kinematic parameters.

In some specific application scenarios, a conflict position and a conflict occurrence time are also required in the process of obtaining a plurality of planning driving schemes of the bus.

Each planned driving scheme comprises the track and the acceleration of the bus.

Correspondingly, obtaining the exogenous variable matrix corresponding to the planned driving scheme comprises the following steps: obtaining the track, the speed and the acceleration of the bus corresponding to the planned driving scheme; the track of the bus can represent the turning radius and the turning angle of the bus.

Taking the division step length of the planning driving scheme as an example, further explaining the contents contained in the planning driving scheme, and further defining the acquisition mode of partial elements in the exogenous variable matrix.

In some application scenarios, the firstThe seed plan driving scheme may be expressed as/>Wherein, the method comprises the steps of, wherein,Represents the/>End time of seed planning driving scheme,/>Represents the/>The planned driving scenario is from the start time/>, of the nth planned version scenarioTo the end time/>The total number of steps passed (e.g. each step may be set to 0.5 seconds),/>Represents the firstAcceleration sequence set of seed planning driving scheme,/>Represents the/>Steering angle sequence set of seed planning driving scheme,/>Represents the/>A set of turn radius sequences for a planned driving scenario. /(I)、/>And/>The specific expression of (2) is as follows:

；

wherein, Represents the/>The seed planning driving scheme is at the/>Planned bus acceleration in time steps,/>Represents the/>The seed planning driving scheme is at the/>Planned bus steering angle in time step,/>Represents the/>The seed planning driving scheme is at the/>Planned turning radii in time steps.

In the process of obtaining the exogenous variable matrix, the exogenous variable matrix can be obtained by、/>And/>Obtaining partial exogenous variables. /(I)

In the foregoing embodiment, the process of determining the selected driving scheme is described, and finally, the process of reminding is described as an example.

Fig. 5 is a schematic diagram of a reminding procedure provided by an embodiment of the present application, where the procedure is performed after the planned driving scheme corresponding to the minimum first total number is used as the selected driving scheme in S104.

As shown in connection with fig. 5, the alert process includes:

s501, taking the passenger corresponding to the adverse reaction of the passenger state in the selected driving scheme as a target passenger.

The passenger status that would have adverse effects is determined for each planned travel scenario, and when one planned travel scenario is selected as the selected travel scenario, the target passenger is obtained by retrospectively querying the determined passenger status.

S502, reminding the target passengers to remind the target passengers to prepare for coping.

For the passenger state of the adverse reaction that the uncomfortable probability is larger than or equal to the first preset probability threshold value, the target passenger can be reminded of rest;

For passenger conditions with a probability of falling greater than or equal to a second predetermined probability threshold, which is an adverse reaction, the target passenger may be alerted to grasp an armrest or other in-vehicle fixture (e.g., a seat back).

The reminding mode can comprise one or more of sound reminding, indicator light reminding and display screen reminding.

In some application scenarios, it is easier to alert target passengers targeted if each passenger wears an intelligent personal terminal corresponding to an autonomous bus.

In some embodiments, an apparatus for reducing adverse effects of passengers in an autopilot bus risk avoidance scenario includes a processor and a memory storing program instructions, the processor being configured to execute the method for reducing adverse effects of passengers in an autopilot bus risk avoidance scenario provided in the foregoing embodiments when the program instructions are executed.

Fig. 6 is a schematic diagram of a device for reducing adverse reactions of passengers in an automatic driving bus danger avoidance scene provided by an embodiment of the application. Referring to fig. 6, an apparatus 60 for reducing adverse reactions of passengers in an automatic driving bus danger avoidance scenario includes:

A processor (processor) 61 and a memory (memory) 62, and may also include a communication interface (Communication Interface) 63 and a bus 64. The processor 61, the communication interface 63, and the memory 62 may communicate with each other via the bus 64. The communication interface 63 may be used for information transfer. The processor 61 may call the logic instructions in the memory 62 to execute the method for reducing adverse reactions of passengers in the case of the automatic driving bus danger avoidance scenario provided in the foregoing embodiment.

Further, the logic instructions in the memory 62 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product.

The memory 62 is a computer readable storage medium that can be used to store a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present application. The processor 61 executes functional applications and data processing by running software programs, instructions and modules stored in the memory 62, i.e. implements the methods of the method embodiments described above.

Memory 62 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. In addition, memory 62 may include high-speed random access memory, and may also include non-volatile memory.

As shown in connection with fig. 7, the automated guided bus 70 includes: the bus body 71 and the device 60 for reducing adverse reactions of passengers in the automatic driving bus danger avoidance scene. The device 60 for reducing adverse reactions of passengers in the automatic driving bus danger avoidance scene is arranged on a bus body 71. The mounting relationships described herein are not limited to being placed within the bus body 71, but include mounting connections with other components of the autopilot bus 70, including but not limited to physical, electrical, or signaling connections, etc. It will be appreciated by those skilled in the art that the device 60 for reducing adverse passenger reactions in the case of an automated driving bus evacuation scenario may be adapted to a viable bus body 71, thereby implementing other viable embodiments.

The embodiment of the application provides a computer readable storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to:

According to the magnitude relation between the uncomfortable probability and the second probability threshold value and the magnitude relation between the falling probability and the first probability threshold value, counting the first total number of the passengers in the planned driving scheme as adverse reactions; wherein, for any passenger, the passenger status of the adverse reaction includes: the uncomfortable probability is larger than or equal to the second probability threshold value, and the falling probability is larger than or equal to the first probability threshold value;

and regarding the planning driving schemes, taking the planning driving scheme corresponding to the minimum first total number as a selected driving scheme, and controlling the bus according to the selected driving scheme.

The computer readable storage medium described above may be a transitory computer readable storage medium.

The technical solution of the embodiment of the present application may be embodied in the form of a software product, where the software product is stored in a storage medium, and includes one or more instructions to cause a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method in the embodiment of the present application. And the aforementioned storage medium may be a non-transitory storage medium including: a plurality of media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or a transitory storage medium.

The above description and the drawings illustrate embodiments of the application sufficiently to enable those skilled in the art to practice them. Other embodiments may involve structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in, or substituted for, those of others. Moreover, the terminology used in the present application is for the purpose of describing embodiments only and is not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a," "an," and "the" (the) are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, when used in the present disclosure, the terms "comprises," "comprising," and/or variations thereof, mean that the recited features, integers, steps, operations, elements, and/or components are present, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus that includes such elements. In this context, each embodiment may be described with emphasis on the differences from the other embodiments, and the same similar parts between the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method sections disclosed in the embodiments, the description of the method sections may be referred to for relevance.

Those of skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. The skilled person may use different methods for each particular application to achieve the described functionality, but such implementation is not to be considered as beyond the scope of the embodiments of the application. It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.

In the embodiments disclosed herein, the disclosed methods, articles of manufacture (including but not limited to devices, apparatuses, etc.) may be practiced in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements may be merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form. The elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physically located, or may be distributed over a plurality of network elements. Some or all of the units may be selected according to actual needs to implement the present embodiment. In addition, each functional unit in the embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Claims

1. A method for reducing adverse reactions of passengers in an automatic driving bus danger avoiding scene, comprising the following steps:

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

Determining a first probability threshold corresponding to each passenger according to the discomfort probability of each passenger, wherein the first probability threshold comprises:

；

wherein, For the first probability threshold,/>Is the maximum value of the first probability threshold value,/>Is the minimum value of the first probability threshold value,/>The discomfort probability corresponding to any passenger;

And/or the number of the groups of groups,

Determining a second probability threshold corresponding to each passenger according to the falling probability of each passenger, including:

；

3. The method of claim 1, wherein obtaining the probability of fall for each passenger under the planned travel plan comprises:

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the probability of fall under the present planned driving scenario,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the height of the armrest relative to the floor in the vehicle,/>For the discomfort probability,/>Representing a correction function corresponding to said discomfort probability,For passenger sex,/>For the age of the passenger,/>Representation of passenger gender/>Passenger age/>Corresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the height of the passenger,/>Is the first correction coefficient;

And/or the number of the groups of groups,

；

wherein n is the serial number of the planning running scheme in all the planning running schemes, For the probability of fall under the nth planned driving scenario,/>In order to apply inertial force to passengers in a vehicle in a braking and/or turning scene of the vehicle,/>Is the friction coefficient between the ground in the car and the foot bottom surface of the passenger,/>For the weight of the passenger,/>Gravitational acceleration,/>For the discomfort probability,/>Representing a correction function corresponding to the discomfort probability,/>For passenger sex,/>For the age of the passenger,Representation of passenger gender/>Passenger age/>Corresponding correction function,/>Maintaining stable grip for a standard in standing condition of a passenger,/>For the bus acceleration direction under the planning driving scheme in the nth step,/>For the connection line direction of the mass center of the passenger and the handrail in the state that the passenger does not fallIs an included angle function of two directions and is used for correcting the standard maintenance stable grip strength/>, of a passenger in a gripping mode，/>Is the second correction coefficient;

And/or the number of the groups of groups,

；

4. The method according to claim 1, wherein the discomfort probability for each passenger under the present planned driving scenario is obtained by means of the following structural equation model:

；

wherein, For the discomfort probability,/>For the endophytic latent variable matrix,/>Is exogenous latent variable matrix,/>Is an interference coefficient matrix,/>For the endophytic latent variable matrix/>Probability of discomfort/>First influence coefficient matrix,/>For the exogenous latent variable matrix/>Probability of discomfort/>A second influence coefficient matrix,/>Is an exogenous variable matrix,/>For the exogenous matrix/>At the exogenous latent variable matrix/>First load matrix,/>For the exogenous matrix/>First measurement error matrix,/>For the endogenous variable matrix,/>For the matrix/>Within the endogenous latent variable matrixSecond load matrix on,/>For the endogenous variable matrix/>Is a second measurement error matrix of (a).

5. The method of claim 4, wherein the matrix of endogenous variablesAnd/or the exogenous matrix/>The elements in the model are divided into two classes, one class is a sequential display variable, and the other class is a classification display variable;

the obtaining mode of the sequence display variable comprises the following steps: mapping the obtained original variable value into a preset numerical value interval;

6. The method of claim 4, wherein the step of determining the position of the first electrode is performed,

The endogenous variable matrixThe elements of (1) include: one or more of an in-vehicle environmental parameter, a passenger physiological parameter; the in-vehicle environmental parameters include one or more of passenger load rate, in-vehicle temperature, in-vehicle humidity, in-vehicle noise, in-vehicle carbon dioxide content;

the exogenous variable matrix The elements of (1) include: natural environment, handrail parameters, driving parameters, passenger-specific information, and journey attributes.

7. The method according to any one of claims 1 to 6, wherein obtaining a plurality of planned driving scenarios comprises:

under the danger avoiding scene, acquiring a first kinematic parameter of the bus and a second kinematic parameter of a risk vehicle;

And taking the bus and the risk vehicle as targets for avoiding collision, and obtaining a plurality of planning driving schemes of the bus according to the first kinematic parameters and the second kinematic parameters.

8. The method according to any one of claims 1 to 6, further comprising:

Obtaining the total time period from the beginning to the end of the planning driving scheme;

Dividing the total time period into a plurality of step sizes according to a preset time interval;

Counting the passenger states as a second total number of adverse reactions in each step;

Counting the first total number of the passengers in the planned driving scheme as adverse reactions, wherein the first total number comprises the following steps:

and taking the sum of the second total number obtained in all step sizes of the planning driving scheme as the first total number.

9. The method according to any one of claims 1 to 6, further comprising, after taking as the selected travel plan the planned travel plan corresponding to the minimum first total number:

taking the passenger corresponding to the adverse reaction of the passenger state in the selected driving scheme as a target passenger;

and reminding the target passenger to remind the target passenger to finish preparation for coping.

10. An apparatus for reducing adverse effects of passengers in an autopilot bus shelter scenario, comprising a processor and a memory storing program instructions, wherein the processor is configured to execute the method for reducing adverse effects of passengers in an autopilot bus shelter scenario as claimed in any one of claims 1 to 9 when executing the program instructions.