CN117141473B

CN117141473B - Intelligent obstacle avoidance method and device for vehicle

Info

Publication number: CN117141473B
Application number: CN202311423184.8A
Authority: CN
Inventors: 程斯荣; 潘俊芳; 陈秋钿; 冼国文
Original assignee: Guangzhou Desai Xiwei Intelligent Transportation Technology Co ltd
Current assignee: Guangzhou Desai Xiwei Intelligent Transportation Technology Co ltd
Priority date: 2023-10-31
Filing date: 2023-10-31
Publication date: 2024-01-19
Anticipated expiration: 2043-10-31
Also published as: CN117141473A

Abstract

The invention discloses an intelligent obstacle avoidance method and device for a vehicle, comprising the following steps: acquiring target real-time information of a target vehicle; analyzing the real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle; for each passenger of the target vehicle, determining a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model; analyzing real-time information of a road where a target vehicle is located to obtain a road analysis result; and generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle. Therefore, the intelligent obstacle avoidance device can be used for realizing intelligent obstacle avoidance on the vehicle by combining the riding condition of the passengers in the vehicle, is beneficial to improving the intelligence of the obstacle avoidance of the vehicle, is beneficial to improving the accuracy of the obstacle avoidance of the vehicle, and is beneficial to improving the comfort and the safety of the passengers riding the vehicle.

Description

Intelligent obstacle avoidance method and device for vehicle

Technical Field

The invention relates to the technical field of intelligent safe driving, in particular to an intelligent obstacle avoidance method and device for a vehicle.

Background

With the rapid development of internet technology and economic level, vehicles have become an important transportation means in people's daily lives. Driving safety has been the focus of attention, and along with the development of science and technology, driving intelligentization has also become a hotspot in the vehicle driving process.

Currently, in terms of driving safety of a vehicle, it is generally determined whether to perform an obstacle avoidance operation by determining a distance between the vehicle and an obstacle, and a current manner of the obstacle avoidance operation is often fixed, which does not take into consideration a specific situation of a passenger in the vehicle. Therefore, if the vehicle encounters an obstacle during driving and performs an obstacle avoidance operation, there is a possibility that the obstacle avoidance operation is too intense to reduce the comfort of the passenger and even the safety of the passenger in the vehicle. Therefore, it is important to provide a new obstacle avoidance method for vehicles to improve comfort and safety of passengers during obstacle avoidance of vehicles.

Disclosure of Invention

The technical problem to be solved by the invention is to provide the intelligent obstacle avoidance method and the intelligent obstacle avoidance device for the vehicle, which can realize intelligent obstacle avoidance for the vehicle by combining the riding condition of passengers in the vehicle, are beneficial to improving the intelligence of the obstacle avoidance of the vehicle, are beneficial to improving the accuracy of the obstacle avoidance of the vehicle, and are further beneficial to improving the comfort and the safety of the passengers riding the vehicle.

In order to solve the technical problems, a first aspect of the present invention discloses an intelligent obstacle avoidance method for a vehicle, the method comprising:

acquiring target real-time information of a target vehicle, wherein the target real-time information comprises vehicle real-time information of the target vehicle, passenger real-time information of each passenger included in the target vehicle and road real-time information of a road where the target vehicle is located;

analyzing the passenger real-time information of each passenger included in the target vehicle to obtain passenger posture information of each passenger included in the target vehicle, wherein the passenger posture information comprises one or more of body inclination angle information of each passenger and body distortion degree information of each passenger;

for each passenger of the target vehicle, determining a riding comfort parameter of the passenger according to passenger posture information of the passenger and a pre-determined comfort evaluation model;

analyzing the real-time road information of the road where the target vehicle is located to obtain a road analysis result, wherein the road analysis result comprises obstacle information of obstacles of the road where the target vehicle is located;

And generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle.

As an optional implementation manner, in the first aspect of the present invention, the generating the obstacle avoidance control parameter of the target vehicle according to the riding comfort parameters of all the passengers and the road analysis result, and the vehicle real-time information of the target vehicle includes:

generating an obstacle influence relation between the target vehicle and the obstacle according to the road analysis result and the real-time vehicle information of the target vehicle;

and generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers and the obstacle influence relation.

As an optional implementation manner, in the first aspect of the present invention, before the determining, for each of the passengers of the target vehicle, the passenger comfort parameter of the passenger according to the passenger posture information of the passenger and the predetermined comfort evaluation model, the method further includes:

acquiring a plurality of pieces of training sample information, wherein the training sample information comprises driving parameter values;

For each piece of training sample information, calculating the individual fitness of the training sample information;

screening at least one target training sample information with the individual fitness being greater than or equal to a preset fitness threshold from all the training sample information according to the individual fitness of all the training sample information;

and executing model training operation on the pre-determined standby comfort evaluation model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information so as to generate a comfort evaluation model trained to be converged.

As an optional implementation manner, in the first aspect of the present invention, the analyzing the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle includes:

acquiring multi-modal information of each passenger included in the target vehicle, wherein the multi-modal information comprises one or more of expression information, voice information and action information;

for each passenger seated on the target vehicle, performing multi-mode fitting operation on the multi-mode information of the passenger and the passenger posture information of the passenger to obtain a posture fitting result of the passenger;

And for each passenger on the target vehicle, determining passenger posture information of the passenger according to the posture fitting result of the passenger.

As an optional implementation manner, in the first aspect of the present invention, before the generating the obstacle avoidance control parameter of the target vehicle according to the riding comfort parameters of all the passengers and the road analysis result and the vehicle real-time information of the target vehicle, the method further includes:

acquiring passenger attribute information of each passenger of the target vehicle, and generating obstacle avoidance priority of each passenger according to the passenger attribute information of each passenger;

generating a passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all the passengers and the riding comfort parameters of all the passengers, wherein the obstacle avoidance priorities of the passengers arranged earlier in the passenger obstacle avoidance sequence are higher;

wherein the generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all the passengers and the obstacle influence relation comprises the following steps:

and generating obstacle avoidance control parameters of the target vehicle according to the passenger obstacle avoidance sequence and the obstacle influence relation.

As an optional implementation manner, in a first aspect of the present invention, the generating, according to the passenger obstacle avoidance sequence and the obstacle influencing relationship, an obstacle avoidance control parameter of the target vehicle includes:

generating at least one obstacle avoidance reference scheme of the target vehicle according to an obstacle influence relation, wherein each obstacle avoidance reference scheme comprises an obstacle avoidance reference speed control parameter, an obstacle avoidance reference acceleration control parameter and an obstacle avoidance reference camber control parameter;

determining a target passenger from all passengers included in the target vehicle according to the passenger obstacle avoidance sequence, wherein the obstacle avoidance priority corresponding to the target passenger is the highest obstacle avoidance priority;

and determining a target obstacle avoidance reference scheme from all the obstacle avoidance reference schemes based on the riding comfort parameters of the target passengers, and generating obstacle avoidance control parameters of the target vehicle according to the target obstacle avoidance reference scheme.

As an optional implementation manner, in the first aspect of the present invention, the determining, based on the riding comfort parameter of the target passenger, a target obstacle avoidance reference scheme from all the obstacle avoidance reference schemes includes:

for each obstacle avoidance reference scheme, calculating the matching degree between the target passenger and the obstacle avoidance reference scheme according to the riding comfort parameter of the target passenger;

According to the matching degree between the target passenger and each obstacle avoidance reference scheme, determining the highest matching degree from all the matching degrees, and determining the obstacle avoidance reference scheme corresponding to the highest matching degree as a target obstacle avoidance reference scheme; or,

for each obstacle avoidance reference plan, determining a plan keyword of the obstacle avoidance reference plan, and determining a comfort keyword of the target passenger according to the riding comfort parameter of the target passenger;

for each obstacle avoidance reference scheme, calculating the keyword matching degree between the scheme keywords of the obstacle avoidance reference scheme and the comfort keywords of the target passengers;

and determining the highest keyword matching degree from all the keyword matching degrees, and determining an obstacle avoidance reference scheme corresponding to the keyword matching degree as a target obstacle avoidance reference scheme.

The second aspect of the invention discloses an intelligent obstacle avoidance apparatus for a vehicle, the apparatus comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring target real-time information of a target vehicle, wherein the target real-time information comprises vehicle real-time information of the target vehicle, passenger real-time information of each passenger included in the target vehicle and road real-time information of a road where the target vehicle is located;

The analysis module is used for analyzing the real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle, wherein the passenger posture information comprises one or more of body inclination angle information of each passenger and body distortion degree information of each passenger;

a determining module, configured to determine, for each of the passengers of the target vehicle, a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model;

the analysis module is further used for analyzing the real-time road information of the road where the target vehicle is located to obtain a road analysis result, wherein the road analysis result comprises obstacle information of an obstacle of the road where the target vehicle is located;

and the generation module is used for generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the vehicle real-time information of the target vehicle.

In a second aspect of the present invention, as an optional implementation manner, the generating module generates the obstacle avoidance control parameter of the target vehicle according to the riding comfort parameters of all the passengers, the road analysis result, and the real-time vehicle information of the target vehicle, where a specific manner includes:

As an optional implementation manner, in the second aspect of the present invention, the obtaining module is further configured to obtain, before the determining module determines, for each of the passengers of the target vehicle, a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model, a plurality of training sample information, where the training sample information includes a driving parameter value;

the apparatus further comprises:

the calculation module is used for calculating the individual fitness of the training sample information for each piece of training sample information;

the screening module is used for screening at least one target training sample information with the individual fitness being greater than or equal to a preset fitness threshold value from all the training sample information according to the individual fitness of all the training sample information;

and the training module is used for executing model training operation on the pre-determined standby comfort evaluation model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information so as to generate a comfort evaluation model trained to be converged.

In a second aspect of the present invention, the specific manner in which the analysis module analyzes the passenger real-time information of each of the passengers included in the target vehicle to obtain the passenger posture information of each of the passengers included in the target vehicle includes:

As an optional implementation manner, in the second aspect of the present invention, the obtaining module is further configured to obtain passenger attribute information of each passenger of the target vehicle before the generating module generates the obstacle avoidance control parameter of the target vehicle according to the riding comfort parameters of all the passengers and the road analysis result, and the vehicle real-time information of the target vehicle;

The generation module is further used for generating obstacle avoidance priority of each passenger according to the passenger attribute information of each passenger; generating a passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all the passengers and the riding comfort parameters of all the passengers, wherein the obstacle avoidance priorities of the passengers arranged earlier in the passenger obstacle avoidance sequence are higher;

the specific mode of generating the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers and the obstacle influence relation by the generation module comprises the following steps:

In a second aspect of the present invention, as an optional implementation manner, the generating module generates the obstacle avoidance control parameter of the target vehicle according to the passenger obstacle avoidance sequence and the obstacle influence relationship, where a specific manner includes:

In a second aspect of the present invention, as an optional implementation manner, the generating module determines, based on the riding comfort parameter of the target passenger, a specific manner of determining the target obstacle avoidance reference scheme from all the obstacle avoidance reference schemes includes:

In a third aspect, the invention discloses an intelligent obstacle avoidance apparatus for a vehicle, the apparatus comprising:

a memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program codes stored in the memory to execute the intelligent obstacle avoidance method of the vehicle disclosed in the first aspect of the invention.

A fourth aspect of the invention discloses a computer storage medium storing computer instructions that, when invoked, are used to perform the intelligent obstacle avoidance method of the vehicle disclosed in the first aspect of the invention.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, the target real-time information of the target vehicle is acquired; analyzing the real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle; for each passenger of the target vehicle, determining a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model; analyzing real-time information of a road where a target vehicle is located to obtain a road analysis result; and generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle. Therefore, the intelligent obstacle avoidance device can be used for realizing intelligent obstacle avoidance on the vehicle by combining the riding condition of the passengers in the vehicle, is beneficial to improving the intelligence of the obstacle avoidance of the vehicle, is beneficial to improving the accuracy of the obstacle avoidance of the vehicle, and is beneficial to improving the comfort and the safety of the passengers riding the vehicle.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of an intelligent obstacle avoidance method for a vehicle according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another intelligent obstacle avoidance method for a vehicle according to an embodiment of the present invention;

FIG. 3 is a schematic structural view of an intelligent obstacle avoidance apparatus for a vehicle according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of an intelligent obstacle avoidance apparatus for another vehicle in accordance with an embodiment of the present invention;

fig. 5 is a schematic structural view of an intelligent obstacle avoidance apparatus for a vehicle according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or article.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

The invention discloses an intelligent obstacle avoidance method and device for a vehicle, which can realize intelligent obstacle avoidance for the vehicle by combining the riding condition of passengers in the vehicle, are beneficial to improving the intelligent performance of the obstacle avoidance of the vehicle, are beneficial to improving the accuracy of the obstacle avoidance of the vehicle, and are further beneficial to improving the comfort and safety of the passengers riding the vehicle. The following will describe in detail.

Example 1

Referring to fig. 1, fig. 1 is a schematic flow chart of an intelligent obstacle avoidance method for a vehicle according to an embodiment of the invention. The intelligent obstacle avoidance method of the vehicle described in fig. 1 may be applied to an intelligent obstacle avoidance device of the vehicle, or may be applied to a cloud server or a local server of the intelligent obstacle avoidance device of the vehicle, or may be applied to the vehicle itself, which is not limited by the embodiment of the present invention. As shown in fig. 1, the intelligent obstacle avoidance method of the vehicle may include the following operations:

101. and acquiring target real-time information of the target vehicle.

In the embodiment of the invention, the target real-time information comprises vehicle real-time information of a target vehicle, passenger real-time information of each passenger included in the target vehicle and road real-time information of a road on which the target vehicle is located.

In the embodiment of the present invention, optionally, the target real-time information of the target vehicle may be obtained in real time, or may be obtained when it is detected that the target vehicle needs to perform the obstacle avoidance operation, or may be obtained at regular time according to a preset time period, and the embodiment of the present invention is not specifically limited.

In the embodiment of the present invention, optionally, the target vehicle may be a vehicle for driving teaching, and each passenger included in the target vehicle may be a learner for learning driving; further, the number of students included in the target vehicle may be one or more, and the embodiment of the present invention is not particularly limited.

In the embodiment of the invention, optionally, the target real-time information of the target vehicle can be acquired through one or more of an ultrasonic sensor, a visual sensor, an infrared sensor and a vehicle-mounted sensor; the vehicle-mounted sensor is mainly used for acquiring one or more target real-time information of speed, acceleration, direction and distance information around a target vehicle.

102. And analyzing the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle.

In the embodiment of the invention, the passenger posture information comprises one or more of body inclination angle information of each passenger and body distortion degree information of each passenger.

In the embodiment of the invention, the passenger real-time information of each passenger comprises the position information of each passenger.

103. For each passenger of the target vehicle, a passenger comfort parameter of the passenger is determined according to passenger posture information of the passenger and a predetermined comfort evaluation model.

In an embodiment of the present invention, optionally, the passenger comfort parameter of each passenger includes one or more of a passenger comfort speed parameter of each passenger, a passenger comfort acceleration parameter of each passenger, a passenger comfort turning speed parameter of each passenger, and a passenger comfort turning acceleration parameter of each passenger.

104. And analyzing the real-time information of the road where the target vehicle is located to obtain a road analysis result.

In the embodiment of the invention, the road analysis result comprises obstacle information of the obstacle of the road where the target vehicle is located.

In the embodiment of the present invention, optionally, the obstacle information of the obstacle on the road where the target vehicle is located includes one or more of position information of the obstacle, volume information of the obstacle, distance relation information between the obstacle and the target vehicle, attribute information of the obstacle, hardness information of the obstacle, and category information of the obstacle.

105. And generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle.

In an embodiment of the present invention, optionally, the obstacle avoidance control parameter of the target vehicle includes one or more of an obstacle avoidance speed control parameter of the target vehicle, an obstacle avoidance acceleration control parameter of the target vehicle, an obstacle avoidance camber control parameter of the target vehicle, and an obstacle avoidance camber acceleration control parameter of the target vehicle.

Therefore, the intelligent obstacle avoidance method of the vehicle described in fig. 1 can acquire the target real-time information of the target vehicle, analyze the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle, determine the riding comfort parameter of each passenger according to the passenger posture information obtained by each passenger and the comfort evaluation model, analyze the road real-time information of the road where the target vehicle is located to obtain the road analysis result, and generate the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all the passengers, the road analysis result and the vehicle real-time information of the target vehicle, so that the intelligent obstacle avoidance of the vehicle can be realized by combining the riding conditions of the passengers in the vehicle, the intelligent performance of the obstacle avoidance of the vehicle can be improved, the accuracy of the obstacle avoidance of the vehicle can be improved, and the comfort and the safety of the riding vehicle of the passenger can be improved.

Example two

Referring to fig. 2, fig. 2 is a flow chart of an intelligent obstacle avoidance method of another vehicle according to an embodiment of the invention. The intelligent obstacle avoidance method of the vehicle described in fig. 2 may be applied to an intelligent obstacle avoidance device of the vehicle, or may be applied to a cloud server or a local server of the intelligent obstacle avoidance device of the vehicle, or may be applied to the vehicle itself, which is not limited by the embodiment of the present invention. As shown in fig. 2, the intelligent obstacle avoidance method of the vehicle may include the following operations:

201. and acquiring target real-time information of the target vehicle.

202. And analyzing the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle.

203. For each passenger of the target vehicle, a passenger comfort parameter of the passenger is determined according to passenger posture information of the passenger and a predetermined comfort evaluation model.

204. And analyzing the real-time information of the road where the target vehicle is located to obtain a road analysis result.

In the embodiment of the present invention, for the detailed description of step 201 to step 204, please refer to other descriptions of step 101 to step 104 in the first embodiment, and the detailed description of the embodiment of the present invention is omitted.

205. And generating an obstacle influence relation between the target vehicle and the obstacle according to the road analysis result and the real-time information of the target vehicle.

In an embodiment of the present invention, optionally, the obstacle influence relationship between the target vehicle and the obstacle includes one or more of an influence relationship of a distance value between the target vehicle and the obstacle, and an influence relationship of an angle between the target vehicle and the obstacle.

206. And generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters and the obstacle influence relation of all passengers.

In the embodiment of the invention, optionally, the obstacle avoidance control parameter of the target vehicle is matched with the riding comfort parameter and the obstacle influence relation of each passenger.

Therefore, the intelligent obstacle avoidance method of the vehicle described in fig. 2 can generate an obstacle influence relation between the target vehicle and the obstacle according to the road analysis result and the real-time information of the target vehicle, generate obstacle avoidance control parameters of the target vehicle according to riding comfort parameters and the obstacle influence relation of all passengers, generate accuracy and instantaneity of the obstacle influence relation by combining the real-time information of the target vehicle, comprehensively generate accuracy and reliability of the obstacle influence relation by combining various parameters, and is beneficial to realizing intelligent obstacle avoidance of the vehicle, improving the accuracy of obstacle avoidance of the vehicle and further improving the comfort and safety of the riding vehicle of the passengers.

In an alternative embodiment, for each passenger of the target vehicle, before determining the passenger comfort parameters of the passenger according to the passenger posture information of the passenger and the predetermined comfort evaluation model, the method further comprises:

for each piece of training sample information, calculating individual fitness of the training sample information;

screening at least one target training sample information with the individual fitness being greater than or equal to a preset fitness threshold from all training sample information according to the individual fitness of all training sample information;

and performing model training operation on the pre-determined standby comfort assessment model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information so as to generate a comfort assessment model trained to be converged.

In this optional embodiment, optionally, the driving parameter value includes one or more of a driving speed value, a driving acceleration value, a steering angle value, a steering speed value, a steering acceleration value; further, each of the training sample information includes a driving parameter value, and driving parameter values included in different training sample information may be different.

In this alternative embodiment, optionally, the individual fitness of each training sample information is used to represent the fitness of the training sample information for each driving parameter.

In this optional embodiment, optionally, performing a model training operation on the pre-determined standby comfort assessment model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information to generate a comfort assessment model trained to converge may include:

inputting the driving parameter value of each target training sample information and the individual fitness of each target training sample information into a pre-determined standby comfort evaluation model, calculating the model loss parameter of the standby comfort evaluation model, and judging whether the model loss parameter is smaller than or equal to a preset loss threshold value;

when the model loss parameter is less than or equal to a preset loss threshold value, determining a standby comfort evaluation model corresponding to the model loss parameter less than or equal to the preset loss threshold value as a comfort evaluation model trained to be converged;

when the model loss parameter is judged to be larger than the preset loss threshold value, the operation of inputting the driving parameter value of each target training sample information and the individual fitness of each target training sample information into the pre-determined standby comfort evaluation model, calculating the model loss parameter of the standby comfort evaluation model and judging whether the model loss parameter is smaller than or equal to the preset loss threshold value is triggered again.

In this alternative embodiment, the comfort assessment model trained to converge may optionally be obtained, for example, by: the method comprises the steps of generating a group of random individuals containing values of driving parameters, calculating fitness of each individual through a preset function, carrying out selection operation according to the fitness value of each individual, determining the individual with the fitness value higher than a preset threshold value as a target individual, randomly selecting two individuals from all the individuals to carry out crossover operation, generating new individuals through crossover operation, randomly changing the values of the driving parameters of the individuals for all the individuals to increase diversity of the population, replacing the newly generated individuals with the population corresponding to the original individuals to form a new population, carrying out fitness calculation operation on each individual again based on the new population, finally determining the driving parameters corresponding to the target individual from all the individuals to be determined as optimal driving parameters, and carrying out model training operation on a standby comfort evaluation model determined in advance based on the optimal driving parameters to generate a comfort evaluation model trained to be converged.

It can be seen that, implementing this optional embodiment can obtain a plurality of training sample information, and calculate the individual fitness of every training sample information, according to the individual fitness of all training sample information, at least one target training sample information is selected from all training sample information, according to the driving parameter value of every target training sample information and the individual fitness of every target training sample information, carry out model training operation to the reserve comfort evaluation model, so as to generate a training to convergent comfort evaluation model, can train the reserve comfort evaluation model based on the driving parameter value of training sample information and the individual fitness that is calculated, can make the efficiency and the intelligence that train reserve comfort evaluation model through a plurality of training sample information, and be favorable to improving accuracy and reliability that train reserve comfort evaluation model, thereby be favorable to improving efficiency and timeliness that obtain the training to convergent comfort evaluation model, and be favorable to improving accuracy and reliability that obtain the training to convergent comfort evaluation model, and then be favorable to confirm that each passenger's accurate and intelligent obstacle and each passenger's comfort and the comfort of taking the vehicle are favorable to the improvement in the safety and comfort process of combining the intelligent obstacle and the comfort of passengers.

In another alternative embodiment, analyzing the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle includes:

for each passenger on the target vehicle, performing multi-mode fitting operation on the multi-mode information of the passenger and the passenger posture information of the passenger to obtain a posture fitting result of the passenger;

for each passenger seated on the target vehicle, passenger posture information of the passenger is determined according to the posture fitting result of the passenger.

In this optional embodiment, optionally, the multi-mode information of each passenger included in the target vehicle may be acquired in real time, or may be acquired at regular time according to a preset time period, or may be acquired when the vehicle needs to avoid an obstacle, which is not specifically limited in the embodiment of the present invention.

In this alternative embodiment, alternatively, the acquisition of the multimodal information of each passenger included in the target vehicle may be acquired by one or more of a visual sensor, an infrared sensor, and an acoustic sensor.

In this optional embodiment, optionally, for each passenger on the target vehicle, performing a multi-modal fitting operation on the multi-modal information of the passenger and the passenger posture information of the passenger to obtain a posture fitting result of the passenger, including:

for each passenger seated on a target vehicle, extracting first target information of multi-modal information of the passenger and second target information of passenger posture information of the passenger, wherein the first target information comprises characteristic information corresponding to the multi-modal information of the passenger, and the second target information comprises characteristic information corresponding to the passenger posture information of the passenger;

and for each passenger on the target vehicle, carrying out information fitting operation according to the first target information of the passenger and the second target information of the passenger to obtain a posture fitting result of the passenger.

In this alternative embodiment, optionally, the pose fitting result of each passenger includes one or more of body pose information, expression pose information, language pose information of the passenger.

Therefore, the implementation of the optional embodiment can acquire the multi-modal information of each passenger included in the target vehicle, perform multi-modal fitting operation on the multi-modal information of each passenger and the passenger posture information of each passenger to obtain the posture fitting result of each passenger, determine the passenger posture information of each passenger according to the posture fitting result of each passenger, combine the multi-modal information of each passenger and perform multi-modal fitting operation to obtain the posture fitting result, and be beneficial to improving the accuracy and reliability of the obtained posture fitting result of each passenger and the intelligence and efficiency of the obtained posture fitting result of each passenger, thereby being beneficial to improving the accuracy and intelligence of determining the riding comfort parameters of each passenger, and further being beneficial to improving the matching degree between the obstacle avoidance control parameters of the generated target vehicle and the riding comfort parameters of each passenger, and further being beneficial to improving the comfort and safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, before generating the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle, the method further comprises:

generating a passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all passengers and the riding comfort parameters of all passengers, wherein the obstacle avoidance priority of the passenger arranged earlier in the passenger obstacle avoidance sequence is higher;

wherein, according to the riding comfort parameters and the obstacle influence relation of all passengers, generating obstacle avoidance control parameters of the target vehicle, comprising:

and generating obstacle avoidance control parameters of the target vehicle according to the obstacle avoidance sequence of the passengers and the obstacle influence relation.

In this optional embodiment, optionally, the passenger attribute information of each passenger includes one or more of age information, sex information, physical health information, weight information, height information, and physical constitution information of the passenger.

In this alternative embodiment, the obstacle avoidance priority of an older passenger is optionally higher than that of a younger passenger, for example; the obstacle avoidance priority of the passengers with abnormal constitutions is higher than that of the passengers with normal constitutions, for example, the obstacle avoidance priority of pregnant women is higher than that of young people.

In this optional embodiment, optionally, generating the passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all passengers and the riding comfort parameters of all passengers includes:

for each passenger, calculating a passenger riding safety evaluation parameter according to the obstacle avoidance priority of the passenger and the passenger riding comfort parameter;

and according to the riding safety evaluation parameters of each passenger, arranging the riding safety evaluation parameters of all the passengers in a high-to-low mode to obtain the obstacle avoidance sequence of the passengers.

Therefore, the implementation of the optional embodiment can acquire the passenger attribute information of each passenger of the target vehicle, generate the passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all the passengers and the riding comfort parameters of all the passengers, generate the obstacle avoidance control parameters of the target vehicle according to the passenger obstacle avoidance sequence and the obstacle influence relation, combine the riding comfort parameters of each passenger and the obstacle avoidance priorities to generate the passenger obstacle avoidance sequence, determine the obstacle avoidance priorities of each passenger, be beneficial to improving the intelligence of the obstacle avoidance of the vehicle, further generate the intelligence of the obstacle avoidance control parameters of the target vehicle according to the passenger obstacle avoidance sequence according to the obstacle influence relation, be beneficial to improving the matching degree between the obstacle avoidance control parameters of the target vehicle and the riding comfort parameters of each passenger, and be further beneficial to improving the comfort and safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, generating obstacle avoidance control parameters of the target vehicle according to the passenger obstacle avoidance sequence and the obstacle influencing relationship includes:

generating at least one obstacle avoidance reference scheme of the target vehicle according to the obstacle influence relation, wherein each obstacle avoidance reference scheme comprises an obstacle avoidance reference speed control parameter, an obstacle avoidance reference acceleration control parameter and an obstacle avoidance reference camber control parameter;

according to the obstacle avoidance sequence of the passengers, determining a target passenger from all passengers included in the target vehicle, wherein the obstacle avoidance priority corresponding to the target passenger is the highest obstacle avoidance priority;

and determining a target obstacle avoidance reference scheme from all the obstacle avoidance reference schemes based on riding comfort parameters of target passengers, and generating obstacle avoidance control parameters of the target vehicle according to the target obstacle avoidance reference scheme.

In this optional embodiment, optionally, each obstacle avoidance reference scheme is used to control the target vehicle to avoid an obstacle on the road on which the target vehicle is located; further, the obstacle avoidance reference speed control parameter, the obstacle avoidance reference acceleration control parameter and the obstacle avoidance reference camber control parameter included in each obstacle avoidance reference scheme are different.

In this optional embodiment, optionally, generating, according to a target obstacle avoidance reference scheme, an obstacle avoidance control parameter of the target vehicle includes:

At least one obstacle avoidance reference parameter in the target obstacle avoidance reference scheme is extracted, and obstacle avoidance control parameters of the target vehicle are generated based on all the obstacle avoidance reference parameters.

Therefore, the implementation of the optional embodiment can generate at least one obstacle avoidance reference scheme of the target vehicle according to the obstacle influence relation, determine the target passenger corresponding to the highest obstacle avoidance priority according to the passenger obstacle avoidance sequence, determine the target obstacle avoidance reference scheme in all the obstacle avoidance reference schemes so as to generate obstacle avoidance control parameters, determine the obstacle avoidance control parameters of the target vehicle based on the generated obstacle avoidance reference scheme and the passenger obstacle avoidance sequence, and be beneficial to improving the efficiency and the intelligence of determining the obstacle avoidance control parameters of the target vehicle, and determine the highest obstacle avoidance priority according to the passenger obstacle avoidance sequence, thereby being beneficial to pertinently performing intelligent obstacle avoidance, being beneficial to improving the obstacle avoidance safety of the passenger, reducing the damage degree of the passenger, and being beneficial to improving the matching degree between the obstacle avoidance control parameters of the target vehicle and the riding comfort parameters of each passenger, and further being beneficial to improving the comfort and the safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, determining a target obstacle avoidance reference scheme from all obstacle avoidance reference schemes based on the ride comfort parameters of the target passenger includes:

for each obstacle avoidance reference scheme, determining scheme keywords of the obstacle avoidance reference scheme, and determining comfort keywords of the target passenger according to riding comfort parameters of the target passenger;

In this optional embodiment, optionally, for each obstacle avoidance reference scheme, calculating, according to the riding comfort parameter of the target passenger, a matching degree between the target passenger and the obstacle avoidance reference scheme includes:

For each obstacle avoidance reference scheme, determining an obstacle avoidance comfort parameter of the obstacle avoidance reference scheme;

and for each obstacle avoidance reference scheme, calculating the matching degree between the obstacle avoidance comfort parameters of the obstacle avoidance reference scheme and the riding comfort parameters of the target passengers to obtain the matching degree between the target passengers and the obstacle avoidance reference scheme.

In this alternative embodiment, optionally, for example, if the solution keyword of the obstacle avoidance reference solution a is fast turning obstacle avoidance, the solution keyword of the obstacle avoidance reference solution B is slow turning obstacle avoidance, and the target passenger comfort keyword is slow turning, the obstacle avoidance reference solution B is determined as the target obstacle avoidance reference solution.

Therefore, the implementation of the optional embodiment can calculate the matching degree between the target passenger and each obstacle avoidance reference scheme according to the riding comfort parameter of the target passenger, and determine the obstacle avoidance reference scheme corresponding to the highest matching degree as the target obstacle avoidance reference scheme, or determine the scheme keyword of each obstacle avoidance reference scheme and the comfort keyword of the target passenger, calculate the keyword matching degree between the scheme keyword of the obstacle avoidance reference scheme and the comfort keyword of the target passenger, determine the obstacle avoidance reference scheme corresponding to the highest keyword matching degree as the target obstacle avoidance reference scheme, calculate the matching degree between the target passenger and each obstacle avoidance reference scheme or the keyword matching degree between the scheme keyword of the obstacle avoidance reference scheme and the comfort keyword of the target passenger according to the riding comfort parameter of the target passenger, thereby being beneficial to improving the intelligence and the efficiency of determining the target obstacle avoidance reference scheme, further being beneficial to improving the accuracy and the reliability of determining the target obstacle avoidance reference scheme, further being beneficial to improving the obstacle avoidance control parameter of the target vehicle according to the target obstacle avoidance reference scheme, and being beneficial to the realization of the intelligent vehicle, and improving the riding comfort of the intelligent vehicle.

Example III

Referring to fig. 3, fig. 3 is a schematic structural diagram of an intelligent obstacle avoidance apparatus for a vehicle according to an embodiment of the invention. As shown in fig. 3, the intelligent obstacle avoidance apparatus of the vehicle may include:

an acquiring module 301, configured to acquire target real-time information of a target vehicle, where the target real-time information includes vehicle real-time information of the target vehicle, passenger real-time information of each passenger included in the target vehicle, and road real-time information of a road on which the target vehicle is located;

the analysis module 302 is configured to analyze the real-time information of each passenger included in the target vehicle to obtain passenger posture information of each passenger included in the target vehicle, where the passenger posture information includes one or more of body inclination angle information of each passenger and body distortion degree information of each passenger;

a determining module 303, configured to determine, for each passenger of the target vehicle, a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model;

the analysis module 302 is further configured to analyze real-time road information of a road where the target vehicle is located, so as to obtain a road analysis result, where the road analysis result includes obstacle information of an obstacle of the road where the target vehicle is located;

The generating module 304 is configured to generate obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result, and the real-time vehicle information of the target vehicle.

Therefore, the device described in fig. 3 can acquire the target real-time information of the target vehicle, analyze the passenger real-time information of each passenger included in the target vehicle to obtain the passenger posture information of each passenger included in the target vehicle, determine the riding comfort parameter of each passenger according to the passenger posture information and the comfort evaluation model, analyze the road real-time information of the road where the target vehicle is located to obtain the road analysis result, and generate the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all the passengers, the road analysis result and the vehicle real-time information of the target vehicle, so that the intelligent obstacle avoidance can be realized for the vehicle in combination with the riding conditions of the passengers in the vehicle, the intelligent performance of the obstacle avoidance of the vehicle is improved, the accuracy of the obstacle avoidance of the vehicle is improved, and the comfort and the safety of the riding of the passenger are improved.

The specific ways of generating the obstacle avoidance control parameters of the target vehicle by the generating module 304 according to the riding comfort parameters of all passengers, the road analysis result and the real-time information of the target vehicle include:

Generating an obstacle influence relation between the target vehicle and the obstacle according to the road analysis result and the real-time information of the vehicle of the target vehicle;

and generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters and the obstacle influence relation of all passengers.

Therefore, the device described in fig. 3 can generate the obstacle influence relation between the target vehicle and the obstacle according to the road analysis result and the real-time information of the target vehicle, generate the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters and the obstacle influence relation of all passengers, generate the accuracy and the instantaneity of the obstacle influence relation by combining the real-time information of the target vehicle, comprehensively generate the accuracy and the reliability of the obstacle influence relation by combining various parameters, and is beneficial to realizing intelligent obstacle avoidance of the vehicle, improving the intelligent obstacle avoidance of the vehicle and the accuracy of obstacle avoidance of the vehicle, and further improving the comfort and the safety of the riding vehicle of the passengers.

In an alternative embodiment, as shown in fig. 4, the obtaining module 301 is further configured to obtain, before the determining module 303 determines, for each passenger of the target vehicle, a riding comfort parameter of the passenger according to passenger posture information of the passenger and a predetermined comfort evaluation model, a plurality of training sample information, where the training sample information includes a driving parameter value;

The apparatus further comprises:

a calculation module 305 that calculates, for each training sample information, an individual fitness of the training sample information;

the screening module 306 is configured to screen at least one target training sample information with an individual fitness greater than or equal to a preset fitness threshold from all training sample information according to the individual fitness of all training sample information;

the training module 307 is configured to perform a model training operation on the pre-determined standby comfort assessment model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information, so as to generate a comfort assessment model trained to converge.

As can be seen, implementing the apparatus described in fig. 4 can obtain a plurality of training sample information, and calculate the individual fitness of each training sample information, and screen at least one target training sample information from all training sample information according to the individual fitness of all training sample information, and execute model training operation on the standby comfort assessment model according to the driving parameter value of each target training sample information and the individual fitness of each target training sample information, so as to generate a training-to-convergence comfort assessment model, train the standby comfort assessment model based on the driving parameter value of the training sample information and the calculated individual fitness, and enable the standby comfort assessment model to be trained through a plurality of training sample information, thereby being beneficial to improving the efficiency and the intelligence of training the standby comfort assessment model, improving the accuracy and the reliability of training the standby comfort assessment model, and further being beneficial to improving the accuracy and the reliability of obtaining the training-to-convergence comfort assessment model, further being beneficial to improving the accuracy and the reliability of the training-to-convergence comfort assessment model, and further being beneficial to improving the accuracy and the comfort of each passenger comfort assessment model, and the comfort of each passenger comfort barrier being beneficial to being well as the safety and the comfort of the passenger being carried by the intelligent vehicle.

In another alternative embodiment, as shown in fig. 4, the analysis module 302 analyzes the passenger real-time information of each passenger included in the target vehicle, and the specific manner of obtaining the passenger posture information of each passenger included in the target vehicle includes:

As can be seen, implementing the apparatus described in fig. 4 can obtain multi-modal information of each passenger included in the target vehicle, and perform multi-modal fitting operation on the multi-modal information of each passenger and the passenger posture information of each passenger to obtain a posture fitting result of each passenger, determine the passenger posture information of each passenger according to the posture fitting result of each passenger, and perform multi-modal fitting operation in combination with the multi-modal information of each passenger to obtain a posture fitting result, so as to facilitate improving the accuracy and reliability of obtaining the posture fitting result of each passenger, and the intelligence and efficiency of obtaining the posture fitting result of each passenger, thereby facilitating improving the accuracy and intelligence of determining the riding comfort parameter of each passenger, and further facilitating improving the matching degree between the obstacle avoidance control parameter of the target vehicle and the riding comfort parameter of each passenger, and further facilitating improving the comfort and safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, as shown in fig. 4, the obtaining module 301 is further configured to obtain passenger attribute information of each passenger of the target vehicle before the generating module 304 generates the obstacle avoidance control parameter of the target vehicle according to the riding comfort parameters of all the passengers and the road analysis result, and the real-time information of the vehicle of the target vehicle;

the generating module 304 is further configured to generate an obstacle avoidance priority of each passenger according to passenger attribute information of each passenger; generating a passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all passengers and the riding comfort parameters of all passengers, wherein the obstacle avoidance priority of the passenger arranged earlier in the passenger obstacle avoidance sequence is higher;

the specific ways of generating the obstacle avoidance control parameters of the target vehicle by the generating module 304 according to the riding comfort parameters and the obstacle influencing relation of all passengers include:

Therefore, the device described in fig. 4 can acquire the passenger attribute information of each passenger of the target vehicle, generate the passenger obstacle avoidance sequence based on the obstacle avoidance priorities of all the passengers and the riding comfort parameters of all the passengers, generate the obstacle avoidance control parameters of the target vehicle according to the passenger obstacle avoidance sequence and the obstacle influence relation, combine the riding comfort parameters of each passenger and the obstacle avoidance priorities to generate the passenger obstacle avoidance sequence, determine the obstacle avoidance priorities of each passenger, facilitate the improvement of the intelligence of the obstacle avoidance of the vehicle, and further facilitate the improvement of the matching degree between the obstacle avoidance control parameters of the target vehicle and the riding comfort parameters of each passenger according to the obstacle avoidance sequence, thereby further facilitating the improvement of the comfort and safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, as shown in fig. 4, the specific manner of generating the obstacle avoidance control parameters of the target vehicle by the generating module 304 according to the passenger obstacle avoidance sequence and the obstacle influencing relationship includes:

Therefore, the device described in fig. 4 can generate at least one obstacle avoidance reference scheme of the target vehicle according to the obstacle influence relation, determine the target passenger corresponding to the highest obstacle avoidance priority according to the obstacle avoidance sequence of the passengers, determine the target obstacle avoidance reference scheme in all the obstacle avoidance reference schemes so as to generate obstacle avoidance control parameters, determine the obstacle avoidance control parameters of the target vehicle based on the generated obstacle avoidance reference scheme and the passenger obstacle avoidance sequence, and be beneficial to improving the efficiency and the intelligence of determining the obstacle avoidance control parameters of the target vehicle, and determine the highest obstacle avoidance priority according to the passenger obstacle avoidance sequence, thereby being beneficial to carrying out intelligent obstacle avoidance for the passengers with higher obstacle avoidance priority, being beneficial to improving the obstacle avoidance safety of the passengers, reducing the damage degree of the passengers, and being beneficial to improving the matching degree between the obstacle avoidance control parameters of the target vehicle and the riding comfort parameters of each passenger in the obstacle avoidance process, and further being beneficial to improving the comfort and the safety of each passenger in the obstacle avoidance process.

In yet another alternative embodiment, as shown in fig. 4, the generating module 304 determines, based on the riding comfort parameters of the target passenger, the specific manner of determining the target obstacle avoidance reference scheme from all the obstacle avoidance reference schemes includes:

As can be seen, implementing the device described in fig. 4 can calculate the matching degree between the target passenger and each obstacle avoidance reference scheme according to the riding comfort parameter of the target passenger, and determine the obstacle avoidance reference scheme corresponding to the highest matching degree as the target obstacle avoidance reference scheme, or determine the scheme keyword of each obstacle avoidance reference scheme and the comfort keyword of the target passenger, calculate the keyword matching degree between the scheme keyword of the obstacle avoidance reference scheme and the comfort keyword of the target passenger, and determine the obstacle avoidance reference scheme corresponding to the highest keyword matching degree as the target obstacle avoidance reference scheme, and calculate the matching degree between the target passenger and each obstacle avoidance reference scheme or the keyword matching degree between the scheme keyword of the obstacle avoidance reference scheme and the comfort keyword of the target passenger according to the riding comfort parameter of the target passenger, thereby being beneficial to improving the intelligence and efficiency of determining the target obstacle avoidance reference scheme, further being beneficial to improving the accuracy and reliability of determining the target obstacle avoidance reference scheme, further being beneficial to improving the safety of the vehicle, being beneficial to the intelligent and improving the safety of the vehicle, and being beneficial to improving the riding comfort of the intelligent vehicle.

Example IV

Referring to fig. 5, fig. 5 is a schematic structural diagram of an intelligent obstacle avoidance apparatus for a vehicle according to another embodiment of the present invention. As shown in fig. 5, the intelligent obstacle avoidance apparatus of the vehicle may include:

a memory 401 storing executable program codes;

a processor 402 coupled with the memory 401;

the processor 402 invokes executable program codes stored in the memory 401 to perform the steps in the intelligent obstacle avoidance method of the vehicle described in the first or second embodiment of the present invention.

Example five

The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing the steps in the intelligent obstacle avoidance method of the vehicle described in the first or second embodiment of the invention when the computer instructions are called.

Example six

An embodiment of the present invention discloses a computer program product comprising a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the intelligent obstacle avoidance method of a vehicle described in embodiment one or embodiment two.

The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.

Finally, it should be noted that: the disclosed intelligent obstacle avoidance method and device of the vehicle are only the preferred embodiments of the present invention, and are only used for illustrating the technical scheme of the present invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. An intelligent obstacle avoidance method for a vehicle, the method comprising:

generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the real-time vehicle information of the target vehicle;

generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all the passengers, the road analysis result and the real-time vehicle information of the target vehicle, wherein the obstacle avoidance control parameters comprise:

generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers and the obstacle influence relation;

and before generating the obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all the passengers, the road analysis result and the vehicle real-time information of the target vehicle, the method further comprises:

2. The intelligent obstacle avoidance method of the vehicle of claim 1 wherein, for each of the occupants of the subject vehicle, prior to determining the occupant comfort parameter for that occupant based on the occupant pose information for that occupant and the predetermined comfort assessment model, the method further comprises:

3. The intelligent obstacle avoidance method of the vehicle of claim 1 wherein said analyzing the passenger real-time information for each of said passengers included in said target vehicle to obtain the passenger pose information for each of said passengers included in said target vehicle comprises:

4. The intelligent obstacle avoidance method of the vehicle of claim 3 wherein said generating obstacle avoidance control parameters for the target vehicle based on the passenger obstacle avoidance sequence and the obstacle influencing relationship comprises:

5. The intelligent obstacle avoidance method of the vehicle of claim 4 wherein said determining a target obstacle avoidance reference scenario from all of said obstacle avoidance reference scenarios based on ride comfort parameters of said target occupant comprises:

6. An intelligent obstacle avoidance apparatus for a vehicle, the apparatus comprising:

the generation module is used for generating obstacle avoidance control parameters of the target vehicle according to the riding comfort parameters of all passengers, the road analysis result and the vehicle real-time information of the target vehicle;

the specific mode of generating the obstacle avoidance control parameters of the target vehicle by the generation module according to the riding comfort parameters of all passengers, the road analysis result and the vehicle real-time information of the target vehicle comprises the following steps:

the acquisition module is further used for acquiring passenger attribute information of each passenger of the target vehicle before the generation module generates obstacle avoidance control parameters of the target vehicle according to riding comfort parameters of all the passengers, the road analysis result and the vehicle real-time information of the target vehicle;

7. An intelligent obstacle avoidance apparatus for a vehicle, the apparatus comprising:

a memory storing executable program code;

a processor coupled to the memory;

the processor invokes the executable program code stored in the memory to perform the intelligent obstacle avoidance method of the vehicle as set forth in any one of claims 1-5.

8. A computer storage medium storing computer instructions which, when invoked, are adapted to perform the intelligent obstacle avoidance method of a vehicle as claimed in any one of claims 1 to 5.