CN112644481B

CN112644481B - Emergency danger avoiding method and device for automatic driving

Info

Publication number: CN112644481B
Application number: CN201910959757.6A
Authority: CN
Inventors: 李柏
Original assignee: Beijing Jingdong Qianshi Technology Co Ltd
Current assignee: Beijing Jingdong Qianshi Technology Co Ltd
Priority date: 2019-10-10
Filing date: 2019-10-10
Publication date: 2023-05-30
Anticipated expiration: 2039-10-10
Also published as: CN112644481A

Abstract

The invention discloses an automatic driving emergency risk avoiding method and device, and relates to the technical field of machine control. One embodiment of the method comprises the following steps: acquiring a real-time distance between a vehicle and surrounding inductions in an automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks; and controlling the automatic driving of the vehicle according to the operation mode so as to realize the emergency risk avoidance of the automatic driving. The implementation mode achieves the technical effect of quickly finding out a reasonable emergency risk avoiding method from a database so as to realize automatic driving treatment of sudden emergency and dangerous conditions.

Description

Emergency danger avoiding method and device for automatic driving

Technical Field

The invention relates to the technical field of machine control, in particular to an automatic driving emergency risk avoiding method and device.

Background

The automatic driving is used as a high-level form for starting the intelligent and networking development, is a typical representation of the deep fusion of the artificial intelligence and the entity economy, has positive effects on road traffic safety, future travel and novel industry ecology, and has important significance for promoting the construction of the manufacturing of strong countries and science and technology and the realization of the high-quality development of automobiles and related industries.

In the field of autopilot, how to apply different motion planning and control techniques makes it important to realize autopilot in complex environments. The existing motion planning technology mainly adopts graph searching, sampling method, numerical optimization and learning method thereof.

In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:

in the face of emergency and dangerous situations which are sudden in a short time, automatic driving is difficult to timely plan a reasonable operation mode to realize emergency danger avoidance.

Disclosure of Invention

In view of this, the embodiments of the present invention provide a method and apparatus for automatically driving emergency avoidance, which can quickly find a reasonable emergency avoidance method from a database to cope with sudden emergency and dangerous situations.

To achieve the above object, according to a first aspect of the embodiments of the present invention, there is provided an emergency risk avoidance method for automatic driving, including:

acquiring a real-time distance between a vehicle and surrounding inductions in an automatic driving process;

determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks;

And controlling the automatic driving of the vehicle according to the operation mode so as to realize the emergency risk avoidance of the automatic driving.

Further, before the step of acquiring the real-time distance between the vehicle and the surrounding sensor, the emergency risk avoiding method for automatic driving further comprises: and simulating the operation mode of the vehicle according to the boundary state information of the vehicle, the preset distance between the vehicle and the surrounding inductors and the road information, acquiring the running track corresponding to the operation mode, and constructing a database, wherein the preset distance is smaller than the threshold distance.

Further, the boundary state information of the vehicle includes a real-time centroid speed of the vehicle and one or more of the following information: real-time barycenter acceleration of the vehicle, real-time rotation angle acceleration of the vehicle and real-time tire pressure information of the vehicle.

Further, the step of determining the operation mode of the vehicle through the database includes: and determining a corresponding operation mode by searching a database according to the boundary state information, the real-time distance and the road information of the real-time driving path of the vehicle.

Further, the step of searching the database comprises: searching running tracks corresponding to different operation modes in the database, and determining the operation mode corresponding to the corresponding running track under the condition that the running track in the database can avoid danger.

Further, the threshold distance is determined based on the relative travel speed of the vehicle and its surrounding inductions and the road information of the real-time travel path.

Further, the emergency risk avoiding method for automatic driving further comprises the following steps: and controlling the actual running track of the automatic driving of the vehicle according to the operation mode, and correcting the database.

According to a second aspect of an embodiment of the present invention, there is provided an emergency risk avoidance device for automatic driving, including:

the real-time distance acquisition module is used for acquiring the real-time distance between the vehicle and the surrounding inductors in the automatic driving process;

the operation mode determining module is used for determining the operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates the operation mode combination of the steering wheel, the accelerator pedal and the brake pedal and the corresponding running track thereof;

and the control module is used for controlling the automatic driving of the vehicle according to the operation mode so as to realize the emergency risk avoidance of the automatic driving.

According to a third aspect of an embodiment of the present invention, there is provided a terminal including:

one or more processors; storage means for storing one or more programs,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement an emergency evacuation method for autopilot as described above.

According to a fourth aspect of embodiments of the present invention, there is provided a computer readable medium having stored thereon a computer program which when executed by a processor implements an emergency evacuation method of any of the above described autopilots.

One embodiment of the above invention has the following advantages or benefits: because the real-time distance between the vehicle and the surrounding sensing objects is acquired in the automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks; according to the technical means of controlling the automatic driving of the vehicle to realize the emergency risk avoidance of the automatic driving, the technical problem that the automatic driving is difficult to timely plan a reasonable operation mode to realize the emergency risk avoidance in the short time aiming at the emergency and dangerous situation in the prior art is solved, and the reasonable emergency risk avoidance method is quickly found from the database so as to realize the technical effect of automatic driving treatment of the emergency and dangerous situation in the emergency.

Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic diagram of a main flow of an emergency evacuation method for autopilot according to a first embodiment of the present invention;

fig. 2a is a schematic diagram of a main flow of an emergency evacuation method for autopilot according to a second embodiment of the present invention;

FIG. 2b is a simulated driving track corresponding to a simulated operation mode when a database is constructed according to the emergency risk avoidance method shown in FIG. 2 a;

fig. 3 is a schematic diagram of main modules of an autonomous emergency risk avoidance device according to an embodiment of the present invention;

FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

fig. 5 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic diagram of a main flow of an emergency evacuation method for autopilot according to a first embodiment of the present invention; as shown in fig. 1, the emergency risk avoiding method for automatic driving provided by the embodiment of the invention includes:

step S101, acquiring a real-time distance between the vehicle and surrounding sensing objects during automatic driving.

Specifically, the distance between the sensor around the vehicle and the vehicle is obtained in real time through the vehicle-mounted sensors (radar sensor, vision sensor and the like) arranged around the vehicle body, and whether the vehicle is in a dangerous state or not is pre-judged through the real-time distance, so that the follow-up local motion planning is facilitated, and the emergency risk avoidance is realized.

Emergency risk avoidance: refers to the act of protecting the larger legal equity by having to resort to the legal benefit of the less damaging party in order to protect the public benefit, the person of the principal or others and other rights from the ongoing hazard. In the field of autopilot, emergency situations are also specified which are to be handled in extreme time periods, so that public interests, personal and other rights of the person or others are as far as possible protected from or less impaired.

Further, according to an embodiment of the present invention, before the step of acquiring the real-time distance between the vehicle and the surrounding sensor, the method for avoiding danger in automatic driving further includes: and planning a path of automatic driving of the vehicle and acquiring road information of the path.

In particular, the route from the current location of the vehicle to the requested destination may be planned according to the vehicle decision system of the autonomous vehicle, and any existing path planning algorithm may be employed for path planning of the autonomous vehicle, such as planning a path of minimum cost. Meanwhile, road information on the planned path is acquired, so that the realization of subsequent emergency danger avoidance is facilitated.

Further, according to an embodiment of the present invention, before the step of obtaining the road information of the path, the method for planning the movement of the autopilot further includes: according to boundary state information of a vehicle, a preset distance between the vehicle and an inductor around the vehicle and road information, combining a vehicle dynamics model, simulating an operation mode of the vehicle, acquiring a running track corresponding to the operation mode, and constructing a database, wherein the preset distance is smaller than a threshold distance.

Specifically, according to a specific implementation of the embodiment of the present invention, the boundary state information of the vehicle includes one or more of the following information and a real-time mass center speed of the vehicle: real-time barycenter acceleration of the vehicle, real-time rotation angle acceleration of the vehicle and real-time tire pressure information of the vehicle.

Specifically, the vehicle motion mode is simulated by data, namely, the boundary state information of the preset vehicle (mainly the current mass center speed of the vehicle), the preset distance between the preset vehicle and the surrounding sensor (for example, the situation that pedestrians suddenly appear in front of a driving route is assumed), and the road information (mainly the width of a road, the flat condition, the influence of weather on the road condition and the like), and the vehicle dynamics model is combined, so that the optimal vehicle operation mode combination is continuously simulated, and the emergency risk avoidance is realized. By continuously enumerating various possible emergency conditions, the corresponding operation modes (different operation amplitudes, operation sequences and combinations of operation durations of a steering wheel, an accelerator pedal and a brake pedal) of the automatic driving vehicle are simulated, specifically, the operation amplitudes of the steering wheel are rotation angles of the steering wheel, the operation amplitudes of the accelerator pedal and the brake pedal refer to the tightness amplitudes of the pressing pedal), the running tracks corresponding to the different operation modes of the vehicle are obtained, and the establishment of a database is completed. It should be noted that when the real-time distance is very small (i.e. the distance between the vehicle and the inductor is very close), it is not possible to ensure absolute safety of both the vehicle and the inductor at any rate, at this time, the scheme with the lowest cost may be selected to determine the corresponding vehicle operation mode, and the cost may refer to bearing a certain damage to the vehicle body. Further, the influence of weather factors on road conditions, such as raining, snowing, etc., may also be considered in constructing the database.

Step S102, determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the operation mode combination of the steering wheel, the accelerator pedal and the brake pedal and the corresponding running track are indicated in the database.

Since the real-time distance is the distance between the vehicle and the surrounding sensor, the threshold distance corresponding to the real-time distance between the vehicle and the sensor in different directions is not completely consistent. According to a specific implementation of the embodiment of the present invention, the threshold distance corresponding to the real-time distance between the vehicle and the sensor in front of the vehicle is generally greater than the threshold distance corresponding to the real-time distance between the vehicle and the sensor on the right side of the vehicle; according to another embodiment, the threshold distance corresponding to the real-time distance of the vehicle to the front thereof is equal to the threshold distance corresponding to the real-time distance of the vehicle to the left thereof. It should be noted that the above scenario is only one case of the embodiment of the present invention, and is not limited to the actual setting of the threshold distance, and the specific setting of the threshold distance may be set correspondingly according to the actual situation.

Specifically, according to an embodiment of the present invention, the step of determining, by the database, an operation mode of the vehicle includes: according to the real-time motion state information, the real-time distance and the road information of the current running path of the vehicle, the motion modes (namely the boundary state information, the preset distance, the road information and the like of the vehicle in the simulated automatic driving process) in the database are matched, whether each running track can avoid sudden danger or not is inquired one by inquiring the running tracks corresponding to different operation modes in the database, and if so, the operation mode corresponding to the running track is determined as the vehicle operation mode to control the vehicle to avoid the emergency danger. According to the real-time condition of the emergency encountered by the vehicle, different operation modes and corresponding running tracks in the offline database are inquired, and the corresponding operation mode of the automatic driving vehicle is determined, so that the problems of temporary local path planning, poor emergency risk avoiding effect and the like according to the real-time condition are avoided, the planning time for obtaining the optimal operation mode is further shortened, and the optimal emergency risk avoiding effect can be achieved.

The combination of the operation modes of the steering wheel, the accelerator pedal and the brake pedal refers to the steering wheel deflection angle, the tightness degree of the accelerator/brake pedal, the operation sequence and the operation duration of the combination of the operation modes and the like which are controlled by the automatic driving vehicle in face of the current emergency.

Further, according to an embodiment of the present invention, the emergency risk avoidance method for autopilot further includes: the threshold distance is determined based on the relative travel speed of the vehicle and its surrounding sensed objects (i.e., the current relative travel speed) and the road information of the current travel path. By adopting the relative running speed as one of the determination conditions of the threshold distance, when the right side (or other directions) of the vehicle is a parallel vehicle, the relative running speed between the two vehicles is small, so that the set threshold distance is also small, and the situation that the vehicle (sensor) parallel to the current vehicle is misjudged as a dangerous condition is avoided through the arrangement; when the sensor on the right side (or other directions) of the vehicle is about to strike the vehicle, the relative running speed is high, so that the set threshold distance is large, and enough time is reserved for realizing emergency danger avoidance. The safe distance (i.e., threshold distance) between the autonomous vehicle and the sensed object is different relative to the real-time speed of the autonomous vehicle; the safety distance (i.e. threshold distance) from the sensor is also different for different road conditions, such as rainy, snowy, foggy, etc.

In addition, as the conditions in the real driving process are various, the road conditions are complex and changeable, when the sudden conditions are met and the operation modes are determined through the database, if the sudden conditions cannot be completely matched, the vehicle operation modes corresponding to the closest simulation data can be determined. For example, the vehicle speed is 9.98m/s when the vehicle actually runs, and pedestrians suddenly appear in front of 3.08 m; the off-line database only simulates a specific operation mode of the vehicle corresponding to the pedestrian suddenly appearing in front of the position 3m with the speed of 10m/s, and at the moment, the operation mode of the vehicle corresponding to the simulation data closest to the real-time condition can be selected to realize the emergency risk avoidance of the vehicle.

Further, according to an embodiment of the present invention, in an automatic driving process, a vehicle continuously performs local motion planning according to real-time road information, and the emergency risk avoiding method for automatic driving further includes: in case of failure of the local motion planning in a certain planning period, the operation mode of the vehicle is determined by the database. Specifically, the failure of local motion planning refers to that a reasonable path is not planned in a specific time, or the planned path cannot complete normal running on an actual road (for example, a road model in the planned path is not updated in time, so that the planned path does not conform to the actual road), and at this time, the operation mode of the vehicle is also quickly determined through a database, so as to avoid unnecessary danger.

Step S103, controlling the automatic driving of the vehicle according to the operation mode so as to realize the emergency risk avoidance of the automatic driving.

Specifically, according to an embodiment of the present invention, the emergency risk avoidance method for autopilot further includes: and controlling the actual running track of the automatic driving of the vehicle according to the operation mode, and correcting the database. Through the arrangement, the database is further improved, so that the emergency risk avoiding effect is further optimized.

According to the technical scheme of the embodiment of the invention, as the route for planning the automatic driving of the vehicle is adopted, the road information of the route is obtained; acquiring a real-time distance between a vehicle and surrounding inductions in an automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks; according to the technical means of controlling the automatic driving of the vehicle to realize the emergency risk avoidance of the automatic driving, the technical problem that the automatic driving is difficult to timely plan a reasonable movement track in the face of emergency and dangerous conditions in a short time in the prior art is solved, and the technical effect of quickly searching a reasonable emergency risk avoidance method from a database to realize the automatic driving treatment of the emergency and dangerous conditions in the burst is further achieved.

Fig. 2a is a schematic diagram of a main flow of an emergency evacuation method for autopilot according to a second embodiment of the present invention; as shown in fig. 2a, the emergency risk avoiding method for automatic driving provided by the embodiment of the invention includes:

step S201, a database is constructed, wherein different operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks are indicated in the database.

Specifically, according to boundary state information of a vehicle, preset distance between the vehicle and an inductor around the vehicle and road information, and combining a vehicle dynamics model, simulating operation modes of the vehicle, acquiring running tracks corresponding to different operation modes, and constructing a database, wherein the preset distance is smaller than a threshold distance.

The embodiment of the invention simulates the possible emergency in the enumeration reality scene, thereby determining the optimal operation mode combination of automatic driving of the vehicle. In the construction process of the database, the database can be constructed by sampling every certain step length (distance) for various conditions in the range. The database contains the simulated vehicle running track corresponding to different operation mode control under different vehicle boundary state information and road information. Wherein the vehicle boundary state information includes a vehicle real-time centroid speed (real-time travel speed) and one or more of the following information: real-time barycenter acceleration of the vehicle, real-time rotation angle acceleration of the vehicle and real-time tire pressure information of the vehicle. That is, the boundary state is regarded as information at the initial time t=0.

Then, the control operation (comprising different operation modes of steering wheel, accelerator pedal and brake pedal) is carried out on the vehicle within a period of time delta T, and the running track of the vehicle at each moment within the time T epsilon [0, [ delta ] T is deduced from a certain boundary state through simulation of simulation according to the vehicle dynamics model. Then, the "boundary state information and the different operation modes" are taken as inputs, the "vehicle travel track within the time T e [0, [ delta ] T ] is taken as an output, and the optimal operation mode is determined by analyzing the output result. By enumerating all boundary state information according to a certain precision and enumerating all possible operation mode combinations, a huge number of inputs can be corresponded, simulation can be carried out on the inputs one by one to obtain corresponding outputs, an offline data table is built according to input data and output data and the finally determined optimal operation mode, and the data table is stored in a database.

Specifically, according to an embodiment of the present invention, as shown in fig. 2b, a pedestrian suddenly appears in front of the vehicle running is preset, different operation modes (a combination of different operation amplitudes, operation sequences and operation durations of a simulated steering wheel, an accelerator pedal and a brake pedal, specifically, the operation amplitude of the steering wheel is a rotation angle of the steering wheel, and the operation amplitude of the accelerator/brake pedal is a tightness amplitude of a pressing pedal) are simulated at this time, and a simulated running track of the vehicle combined according to the corresponding simulated operation modes is obtained, so as to realize emergency risk avoidance. And constructing a data table according to the simulation operation mode and the driving track, and storing the data table into a database. So as to be beneficial to searching corresponding emergency risk avoidance schemes (different operation modes and running tracks) through a database after encountering emergency conditions in the actual running process of the vehicle.

The operation modes of the steering wheel, the accelerator pedal and the brake pedal are combined to rotate the reverse wheel, step on the brake and step on the accelerator. There are many possibilities of turning the steering wheel, the degree of tightness of the brake pedal and the accelerator pedal, and the length of control over a fixed period of time, and the steering wheel, the accelerator pedal, and the brake pedal are operated independently, so there are very many combinations. In the process of constructing the database, a huge number of input samples are required to be simulated, but because the process is an off-line processing process, only a corresponding operation mode is required to be inquired in the database in the actual emergency risk avoiding process, so that the time consumption of emergency risk avoiding required by an emergency is greatly shortened.

Step S202, planning a path of automatic driving of the vehicle and acquiring road information of the path.

In step S203, the real-time distance between the vehicle and the surrounding sensor during the automatic driving process is obtained.

Specifically, a distance between an inductor around the vehicle and the vehicle is acquired in real time through an on-board sensor (radar sensor, vision sensor, etc.) mounted on the vehicle body, and whether the vehicle is in a dangerous state or not is pre-judged through the real-time distance, so that the follow-up local motion planning is facilitated to realize emergency risk avoidance.

In step S204, if the real-time distance is smaller than the threshold distance, the operation mode of the vehicle is determined by the database.

Specifically, according to an embodiment of the present invention, the step of determining, by the database, an operation mode of the vehicle includes: and according to the real-time motion state information, the real-time distance and the road information of the current driving path of the vehicle, matching the motion modes (namely, the boundary state information, the preset distance, the road information and the like of the vehicle in the simulated automatic driving process) in the database, and determining the operation mode indicated by the motion modes. According to the real-time condition of the emergency encountered by the vehicle at present, the off-line database is queried, and the optimal operation mode of the vehicle is determined according to different operation modes and corresponding running tracks indicated in the database, so that the problems of temporary local path planning, poor emergency risk avoidance effect and the like according to the real-time condition are avoided, the planning time for obtaining the optimal operation mode is further shortened, and the optimal emergency risk avoidance effect can be achieved.

Further, according to an embodiment of the present invention, the emergency risk avoidance method for autopilot further includes: the threshold distance is determined based on the relative travel speed of the vehicle and its surrounding inductions (i.e., the current real-time travel speed) and the road information of the current travel path. The safe distance (i.e., threshold distance) between the autonomous vehicle and the sensed object is different relative to the real-time speed of the autonomous vehicle; the safety distance (i.e. threshold distance) from the sensor is also different for different road conditions, such as rainy, snowy, foggy, etc.

In addition, as the conditions in the real driving process are various, the road conditions are complex and changeable, when the sudden conditions are met and the operation modes are determined through the database, if the sudden conditions cannot be completely matched, the vehicle operation modes corresponding to the closest simulation data can be determined. For example, the vehicle speed is 9.98m/s when the vehicle actually runs, and pedestrians suddenly appear in front of 3.08 m; the off-line database only simulates a specific vehicle operation mode corresponding to the sudden appearance of pedestrians at the position 3m in front of the vehicle with the speed of 10m/s, and at the moment, the vehicle operation mode corresponding to the simulation data closest to the real-time condition can be selected to realize the emergency risk avoidance of the vehicle.

Step S205, controlling the automatic driving of the vehicle according to the operation mode so as to realize the emergency avoidance of the automatic driving.

And S206, correcting the database according to the actual running track of the emergency risk avoiding process. Through the arrangement, the database is further improved, so that the emergency risk avoiding effect is further improved.

Fig. 3 is a schematic diagram of main modules of an autonomous emergency risk avoidance device according to an embodiment of the present invention; as shown in fig. 3, an emergency risk avoiding device 300 for automatic driving according to an embodiment of the present invention includes:

the real-time distance acquisition module 301 is configured to acquire a real-time distance between the vehicle and an inductor around the vehicle during an automatic driving process.

Further, according to an embodiment of the present invention, the automatic driving emergency risk avoidance device 300 further includes a path planning module, configured to plan a path of the automatic driving of the vehicle, and acquire road information of the path.

According to an embodiment of the present invention, the automatic driving emergency risk avoidance device 300 further includes a database construction module, configured to simulate operation modes of a vehicle according to boundary state information of the vehicle, a preset distance between the vehicle and surrounding sensors, and a road condition, and to acquire driving tracks corresponding to different operation modes in combination with a vehicle dynamics model, so as to construct a database, wherein the preset distance is smaller than a threshold distance.

Namely, through data simulation, boundary state information (mainly the current running speed of the vehicle), preset distance (such as the assumption that pedestrians and the like suddenly appear around a running route) of a preset vehicle and surrounding inductions of the preset vehicle, road conditions (mainly the width of the road, the flat condition, the influence of weather on the road conditions and the like), and a vehicle dynamics model are combined to continuously simulate to obtain an optimal vehicle combination so as to realize emergency avoidance, and through continuously enumerating various possible emergent conditions, the corresponding operation modes (combination of different operation amplitudes, operation sequences and operation duration of a steering wheel, an accelerator pedal and a brake pedal) of the automatic driving vehicle are obtained, specifically, the operation amplitude of the steering wheel is the rotation angle of the steering wheel, the operation amplitude of the accelerator/brake pedal is the tightness amplitude of a pressing pedal, and the corresponding running track of the pressing pedal are obtained, so that the establishment of a database is completed. It should be noted that when the real-time distance is very small (i.e. the distance between the vehicle and the inductor is very close), it is not possible to ensure absolute safety of both the vehicle and the inductor at any rate, at this time, the scheme with the lowest cost may be selected to determine the corresponding vehicle operation mode, and the cost may refer to bearing a certain damage to the vehicle body. Further, the influence of weather factors on road conditions, such as raining, snowing, etc., may also be considered in constructing the database.

The operation mode determining module 302 is configured to determine an operation mode of the vehicle through a database, where the database indicates a combination of operation modes of the steering wheel, the accelerator pedal, and the brake pedal and a corresponding driving track thereof, when the real-time distance is less than the threshold distance.

Specifically, according to an embodiment of the present invention, the operation mode determining module 302 is further configured to: and according to the real-time motion state information, the real-time distance and the road information of the current driving path of the vehicle, matching the motion modes (namely, the boundary state information, the preset distance, the road information and the like of the vehicle in the simulated automatic driving process) in the database, and determining the operation mode indicated by the motion modes. According to the real-time condition of the emergency encountered by the vehicle, different operation modes and corresponding running tracks in the offline database are inquired, and the corresponding operation mode of the automatic driving vehicle is determined, so that the problems of temporary local path planning, poor emergency risk avoiding effect and the like according to the real-time condition are avoided, the planning time for obtaining the optimal operation mode is further shortened, and the optimal emergency risk avoiding effect can be achieved.

The combination of the operation modes of the steering wheel, the accelerator pedal and the brake pedal refers to the steering wheel deflection angle, the tightness degree of the accelerator/brake pedal, the operation sequence and the operation duration of the operation combination and the like which are controlled by the automatic driving vehicle in face of the current emergency.

Further, according to an embodiment of the present invention, the automatic driving emergency risk avoidance device 300 further includes a threshold distance determining module for determining a threshold distance according to a relative driving speed (referred to as a current relative driving speed) of the vehicle and surrounding inductances thereof and road information of the current driving path. The safe distance (i.e., threshold distance) between the autonomous vehicle and the sensed object is different relative to the real-time speed of the autonomous vehicle; the safety distance (i.e. threshold distance) from the sensor is also different for different road conditions, such as rainy, snowy, foggy, etc.

The emergency risk avoiding module 303 is configured to control automatic driving of the vehicle according to an operation mode, so as to realize emergency risk avoidance of automatic driving.

Specifically, according to an embodiment of the present invention, the automatic driving emergency risk avoidance device 300 further includes a correction module, configured to control an actual driving track of the automatic driving of the vehicle according to the operation mode, and correct the database. Through the arrangement, the database is further improved, and better emergency risk avoidance is achieved.

According to the technical scheme of the embodiment of the invention, the real-time distance between the vehicle and the surrounding inductor is acquired in the automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks; according to the technical means of controlling the automatic driving of the vehicle to realize the emergency risk avoidance of the automatic driving, the technical problem that the automatic driving is difficult to timely plan a reasonable movement track in the face of emergency and dangerous conditions in a short time in the prior art is solved, and the technical effect of quickly searching a reasonable emergency risk avoidance method from a database to realize the automatic driving treatment of the emergency and dangerous conditions in the burst is further achieved.

It can be understood that, since the method embodiment and the apparatus embodiment are in different presentation forms of the same technical concept, the content of the method embodiment portion in the present application should be adapted to the apparatus embodiment portion synchronously, which is not described herein.

Fig. 4 illustrates an exemplary system architecture 400 to which an autonomous emergency evacuation method or an emergency evacuation device of an embodiment of the present invention may be applied.

As shown in fig. 4, the system architecture 400 may include

terminal devices

401, 402, 403, a network 404, and a server 405. The network 404 is used as a medium to provide communication links between the

terminal devices

401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

A user may interact with the server 405 via the network 404 using the

terminal devices

401, 402, 403 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the

terminal devices

401, 402, 403.

The

terminal devices

401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 405 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the

terminal devices

401, 402, 403. The background management server may analyze the received road information of the path, real-time distance, and other data, and may feed back the processing result (e.g., the operation mode of the vehicle) to the terminal device.

It should be noted that, the method for avoiding danger in automatic driving according to the embodiment of the present invention is generally executed by the server 405, and accordingly, the device for avoiding danger in automatic driving is generally disposed in the server 405.

It should be understood that the number of terminal devices, networks and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.

As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 501.

The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

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 various embodiments of the present invention. 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). It should also be noted that, 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. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams 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.

The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor comprises a real-time distance acquisition module, an operation mode determination module and a control module. The names of these modules do not in any way limit the module itself, and for example, the real-time distance acquisition module may also be described as "a module that acquires a real-time distance of a vehicle from its surroundings during automatic driving".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: acquiring a real-time distance between a vehicle and surrounding inductions in an automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein different operation combinations of a steering wheel, an accelerator and a brake pedal and corresponding running tracks are indicated in the database; according to the technical means of controlling the automatic driving of the vehicle according to the operation mode to realize the emergency risk avoidance of the automatic driving, the method overcomes the defect that in the prior art, the automatic driving is difficult to timely plan a reasonable operation mode to realize the emergency risk avoidance in face of emergency and dangerous conditions in short time.

According to the technical scheme of the embodiment of the invention, the real-time distance between the vehicle and the surrounding inductor is acquired in the automatic driving process; determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than the threshold distance, wherein different operation combinations of a steering wheel, an accelerator and a brake pedal and corresponding running tracks are indicated in the database; according to the technical means of controlling the automatic driving of the vehicle to realize the emergency risk avoidance of the automatic driving, the technical problem that the automatic driving is difficult to timely plan a reasonable movement track in the face of emergency and dangerous conditions in a short time in the prior art is solved, and the technical effect of quickly searching a reasonable emergency risk avoidance method from a database to realize the automatic driving treatment of the emergency and dangerous conditions in the burst is further achieved.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. An emergency risk avoidance method for automatic driving, comprising:

acquiring the real-time distance between the vehicle and the surrounding inductions through vehicle-mounted sensors arranged around the vehicle body in the automatic driving process;

determining an operation mode of the vehicle through a database under the condition that the real-time distance is smaller than a threshold distance, wherein the database indicates operation mode combinations of a steering wheel, an accelerator pedal and a brake pedal and corresponding running tracks; wherein the step of determining the operation mode of the vehicle through the database comprises the following steps: determining a corresponding operation mode by searching the database according to the boundary state information of the vehicle, the real-time distance and the road information of the real-time driving path; the database is constructed by simulating the operation mode of the vehicle according to boundary state information of the vehicle, the preset distance between the vehicle and the surrounding inductors and road information and combining a vehicle dynamics model, and acquiring a running track corresponding to the operation mode, wherein the preset distance is smaller than the threshold distance;

2. The automated driving emergency risk avoidance method of claim 1 wherein the boundary state information of the vehicle comprises one or more of a vehicle real-time centroid speed and: real-time barycenter acceleration of the vehicle, real-time rotation angle acceleration of the vehicle and real-time tire pressure information of the vehicle.

3. The method of claim 1, wherein the step of searching a database comprises: searching running tracks corresponding to different operation modes in the database, and determining the operation mode corresponding to the corresponding running track under the condition that the running track in the database can avoid danger.

4. The automatic driving emergency risk avoidance method of claim 1 wherein the threshold distance is determined from the relative travel speed of the vehicle and its surrounding inductions and road information of the real-time travel path.

5. The automatic emergency evacuation method of claim 1, further comprising: and controlling the actual running track of the automatic driving of the vehicle according to the operation mode, and correcting the database.

6. An automatic driving emergency risk avoidance device, comprising:

the real-time distance acquisition module is used for acquiring the real-time distance between the vehicle and the surrounding inductions through vehicle-mounted sensors arranged on the periphery of the vehicle body in the automatic driving process;

the operation mode determining module is used for determining the operation mode of the vehicle through a database when the real-time distance is smaller than a threshold distance, wherein the database indicates the operation mode combination of a steering wheel, an accelerator pedal and a brake pedal and the corresponding running track; wherein, the operation mode determining module is further used for: determining a corresponding operation mode by searching the database according to the boundary state information of the vehicle, the real-time distance and the road information of the real-time driving path; the database is constructed by simulating the operation mode of the vehicle according to boundary state information of the vehicle, the preset distance between the vehicle and the surrounding inductors and road information and combining a vehicle dynamics model, and acquiring a running track corresponding to the operation mode, wherein the preset distance is smaller than the threshold distance;

7. A terminal, comprising:

one or more processors; storage means for storing one or more programs,

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-5.

8. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-5.