CN112046503A

CN112046503A - Vehicle control method based on artificial intelligence, related device and storage medium

Info

Publication number: CN112046503A
Application number: CN202010979532.XA
Authority: CN
Inventors: 由长喜
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-09-17
Filing date: 2020-09-17
Publication date: 2020-12-08
Anticipated expiration: 2040-09-17
Also published as: CN112046503B

Abstract

The application discloses vehicle control method based on artificial intelligence is applied to the autopilot field, and this application includes: acquiring initial acceleration, initial speed, target acceleration and target speed corresponding to a target vehicle; determining the type of a target scene according to the initial acceleration, the initial speed and the target acceleration; acquiring N groups of adjusting parameters according to the type of the target scene; determining a speed curve path corresponding to the target vehicle through N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed; and controlling the target vehicle to run according to the speed curve path. The embodiment of the application also provides a related device and a storage medium. The corresponding adjusting parameters can be obtained according to the current scene type, and different adjusting parameters are used as the constraint and the index for defining the speed curve path, so that the problem of single planning of the speed curve path can be solved, and a better car following effect is achieved.

Description

Vehicle control method based on artificial intelligence, related device and storage medium

Technical Field

The present application relates to the field of automatic driving, and in particular, to a vehicle control method based on artificial intelligence, a related apparatus, and a storage medium.

Background

With the rapid development of the vehicle industry and the continuous improvement of the living standard of people, the proportion of automobiles in daily life of people is gradually increased, and in order to relieve the driving intensity of drivers, automatic driving automobiles are produced, and the automatic driving automobiles are also called unmanned automobiles and are called self-automobiles for short, and the self-automobiles are vehicles which realize unmanned driving through a computer system.

In the stable car following process, the behavior of the guided car is an important reference for the behavior of the self-car. From the motion state of the lead vehicle, a target acceleration or a target speed of the own vehicle can be generally calculated. In view of this, some companies have developed automatic Driving support systems, such as an automatic Pilot (Autopilot) of Tesla (Tesla), an Advanced Driving support System (ADAS) of CT6 of kadilac, and an automatic auxiliary Driving System (NIO Pilot).

In the process before the self-vehicle reaches the target state, a speed curve path (speed profile) defined in time and space needs to be planned, and the quality of the speed profile directly influences the comfort and the safety in the vehicle following process. However, the existing automatic driving assistance system is mainly oriented to a high-speed closed scene, so the design of speed profile is single, and in the actual driving process, multiple scenes often exist, and therefore, the single speed profile design can cause poor car following effect.

Disclosure of Invention

The embodiment of the application provides a vehicle control method based on artificial intelligence, a related device and a storage medium, corresponding adjusting parameters can be obtained according to the current scene type, different adjusting parameters are used as constraints and indexes for defining a speed curve path, the problem of single planning of the speed curve path can be solved, and therefore a better vehicle following effect is achieved.

In view of the above, one aspect of the present application provides an artificial intelligence based vehicle control method, including:

acquiring initial acceleration, initial speed, target acceleration and target speed corresponding to a target vehicle;

determining a target scene type according to the initial acceleration, the initial speed and the target acceleration, wherein the target scene type is included in a scene type set, the scene type set comprises at least two scene types, each scene type corresponds to at least one group of adjusting parameters, the target scene type corresponds to N groups of adjusting parameters, and N is an integer greater than or equal to 1;

acquiring N groups of adjusting parameters according to the type of a target scene, wherein each group of adjusting parameters is used for representing the change condition of the vehicle on the jerk, and the jerk is the time change rate of the acceleration;

determining a speed curve path corresponding to the target vehicle through N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed;

and controlling the target vehicle to run according to the speed curve path.

Another aspect of the present application provides a vehicle control apparatus including:

the acquisition module is used for acquiring initial acceleration, initial speed, target acceleration and target speed corresponding to the target vehicle;

the device comprises a determining module, a processing module and a processing module, wherein the determining module is used for determining a target scene type according to an initial acceleration, an initial speed and a target acceleration, the target scene type is contained in a scene type set, the scene type set comprises at least two scene types, each scene type corresponds to at least one group of adjusting parameters, the target scene type corresponds to N groups of adjusting parameters, and N is an integer greater than or equal to 1;

the acquisition module is further used for acquiring N groups of adjusting parameters according to the type of the target scene, wherein each group of adjusting parameters is used for representing the change condition of the vehicle on the jerk, and the jerk is the time change rate of the acceleration;

the determining module is further used for determining a speed curve path corresponding to the target vehicle through the N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed;

and the control module is used for controlling the target vehicle to run according to the speed curve path.

In one possible design, in another implementation of another aspect of an embodiment of the present application,

the acquisition module is specifically used for acquiring positioning information of the target vehicle;

determining an initial acceleration and an initial speed according to the positioning information of the target vehicle;

acquiring environmental information and vehicle state information of a target vehicle;

and determining the target acceleration and the target speed according to the environment information and the vehicle state information.

the determining module is specifically used for determining N task types according to the initial acceleration, the initial speed and the target acceleration, wherein each task type corresponds to one group of adjusting parameters;

and determining a target scene type corresponding to the target vehicle from the scene type set according to the N task types.

the determining module is specifically used for determining that the N task types comprise a conventional driving task if the initial speed is greater than the static value, the initial acceleration is within a first acceleration interval, and the target acceleration is within a second acceleration interval;

and according to the conventional driving task, determining the target scene type corresponding to the target vehicle from the scene type set as a conventional following scene.

the determining module is specifically used for acquiring adjusting parameters corresponding to the conventional driving task according to the conventional car following scene;

calculating to obtain speeds corresponding to different moments in a target time period according to the adjusting parameters, the initial acceleration, the initial speed, the target acceleration and the target speed corresponding to the conventional running task;

and generating a speed curve path corresponding to the target vehicle according to the speeds corresponding to different moments in the target time period.

the determining module is specifically configured to determine that the N task types include a task of releasing an accelerator pedal if the initial speed is greater than the static value, the initial acceleration is greater than a first threshold, and the target acceleration is less than or equal to 0 within a first time period;

in a second time period, if the initial speed is greater than the static value and the target acceleration is less than a second threshold, determining that the N task types further comprise a rapid deceleration task, wherein the second threshold is less than 0, and the second time period is the next time period adjacent to the first time period;

and determining the target scene type corresponding to the target vehicle as a rapid deceleration scene from the scene type set according to the task of releasing the accelerator pedal and the rapid deceleration task.

the determining module is specifically used for acquiring adjusting parameters corresponding to a task of releasing the accelerator pedal according to a rapid deceleration scene;

acquiring an adjusting parameter corresponding to the rapid deceleration task according to the rapid deceleration scene;

based on the initial acceleration, the initial speed, the target acceleration and the target speed, determining the speeds of the target vehicle at different moments in a first time period and the speeds of the target vehicle at different moments in a second time period by releasing the adjusting parameters corresponding to the accelerator pedal task and the adjusting parameters corresponding to the rapid deceleration task;

and generating a speed curve path corresponding to the target vehicle according to the speeds corresponding to different moments in the first time period and the speeds corresponding to different moments in the second time period.

the determining module is specifically configured to determine that the N task types include a task of releasing a brake pedal if the initial speed is greater than the static value, the initial acceleration is less than a third threshold, and the target acceleration is greater than or equal to 0 in a first time period;

in a second time period, if the initial speed is greater than the static value, the initial acceleration is in a first acceleration interval, and the target acceleration is in a second acceleration interval, determining that the N task types comprise a conventional driving task, wherein the second time period is the next time period adjacent to the first time period;

in a third time period, if the initial speed is greater than the static value, the initial acceleration is greater than the first threshold value, and the target acceleration is less than or equal to 0, determining that the N task types comprise tasks of releasing an accelerator pedal, wherein the third time period is the next time period adjacent to the second time period;

and determining the target scene type corresponding to the target vehicle as an acceleration and deceleration switching scene from the scene type set according to the task of releasing the brake pedal, the task of conventional driving and the task of releasing the accelerator pedal.

the determining module is specifically used for acquiring adjusting parameters corresponding to a task of releasing the brake pedal according to an acceleration and deceleration switching scene;

acquiring adjusting parameters corresponding to a conventional driving task according to an acceleration and deceleration switching scene;

acquiring an adjusting parameter corresponding to a task of releasing an accelerator pedal according to an acceleration and deceleration switching scene;

based on the initial acceleration, the initial speed, the target acceleration and the target speed, determining the speeds of the target vehicle at different moments in a first time period, the speeds of the target vehicle at different moments in a second time period and the speeds of the target vehicle at different moments in a third time period by releasing the adjusting parameters corresponding to the brake pedal task, the adjusting parameters corresponding to the conventional running task and the adjusting parameters corresponding to the accelerator pedal releasing task;

and generating a speed curve path corresponding to the target vehicle according to the speeds corresponding to different moments in the first time period, the speeds corresponding to different moments in the second time period and the speeds corresponding to different moments in the third time period.

the determining module is specifically configured to determine that the N task types include a stationary vehicle starting task if the initial acceleration and the initial speed are equal to static values and the target acceleration is greater than 0;

and according to the static vehicle starting task, determining the target scene type corresponding to the target vehicle as a vehicle following starting scene from the scene type set.

the determining module is specifically used for acquiring adjusting parameters corresponding to the static vehicle starting task according to the vehicle following starting scene;

calculating to obtain speeds corresponding to different moments in a target time period according to the adjusting parameters, the initial acceleration, the initial speed, the target acceleration and the target speed corresponding to the static vehicle starting task;

Another aspect of the present application provides a computer device, comprising: a memory, a transceiver, a processor, and a bus system;

wherein, the memory is used for storing programs;

a processor for executing the program in the memory, the processor for executing the vehicle control method of the above aspects according to the instructions in the program code;

the bus system is used for connecting the memory and the processor so as to enable the memory and the processor to communicate.

Another aspect of the present application provides a vehicle for executing the vehicle control method of the above-described aspects.

Another aspect of the present application provides a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute the vehicle control method of the above-described aspects.

In another aspect of the application, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the vehicle control method provided by the aspects described above.

According to the technical scheme, the embodiment of the application has the following advantages:

the embodiment of the application provides a vehicle control method based on artificial intelligence, which comprises the steps of firstly obtaining initial acceleration, initial speed, target acceleration and target speed corresponding to a target vehicle, then determining a target scene type according to the initial acceleration, the initial speed and the target acceleration, obtaining N groups of adjusting parameters according to the target scene type, then determining a speed curve path corresponding to the target vehicle through the N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed, and finally controlling the target vehicle to run according to the speed curve path. By the mode, the current scene type is determined based on the predefined scene type set, different scene types have different adjusting parameters, the corresponding adjusting parameters can be obtained according to the current scene type, the different adjusting parameters are used as the constraint and the index for defining the speed curve path, and the problem of single speed curve path planning can be solved, so that a better car following effect is achieved, and the safety and the comfort are improved in the driving process of the car.

Drawings

FIG. 1 is a schematic diagram of an application environment of a vehicle control system according to an embodiment of the present application;

FIG. 2 is a block diagram of an exemplary unmanned system;

FIG. 3 is a schematic diagram of continuity curves corresponding to different levels in an embodiment of the present application;

FIG. 4 is a schematic diagram of an embodiment of an artificial intelligence based vehicle control method according to an embodiment of the present application;

FIG. 5 is a schematic view of a navigation interface in an autonomous driving state according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an application scenario of a conventional car following scenario in an embodiment of the present application;

FIG. 7 is a schematic diagram of an application scenario of a rapid deceleration scenario in an embodiment of the present application;

FIG. 8 is a schematic view of the velocity profile path during deceleration in an embodiment of the present application;

fig. 9 is a schematic view of an application scenario of an acceleration/deceleration switching scenario in the embodiment of the present application;

fig. 10 is a schematic view of an application scenario of a following start scenario in the embodiment of the present application;

FIG. 11 is a schematic view of the velocity curve path during acceleration in an embodiment of the present application;

FIG. 12 is a graph illustrating an acceleration-based process according to an embodiment of the present application;

FIG. 13 is a graph illustrating a deceleration process according to an embodiment of the present application;

fig. 14 is a schematic diagram of an embodiment of a vehicle control apparatus according to an embodiment of the present application;

fig. 15 is a schematic structural diagram of a vehicle-mounted computer according to an embodiment of the present application.

Detailed Description

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "corresponding" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like. By combining the artificial intelligence technology and the car networking technology, more and more high-tech functions are used for the car, and the automatic driving is the development trend of the future car, and the era of the automatic driving comes. Based on this, the artificial intelligence technique and the automatic driving technique will be described first.

Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The automatic driving technology generally comprises technologies such as high-precision maps, environment perception, behavior decision, path planning, motion control and the like, and the self-determined driving technology has wide application prospect,

the application provides a vehicle control method based on artificial intelligence, which comprises the steps of obtaining a target speed and a target acceleration which are required to be reached by a target vehicle in a future period of time by judging the current environment, the state of a guided vehicle, traffic information and the like, judging the scene type of the target vehicle by combining the current speed and the current acceleration, and calculating the speed curve path of the target vehicle according to adjusting parameters corresponding to the scene type, so that the target vehicle can be controlled to run on a road according to the speed curve path. With reference to fig. 1, fig. 1 is a schematic view of an application environment of a vehicle control system in an embodiment of the present application, and as shown in the figure, the vehicle control system includes a terminal device, a vehicle, a command center, and a road video monitor, where the terminal device may report positioning and receive related traffic information, the vehicle may receive the positioning information and implement automatic control, the command center may process based on the acquired traffic information, and the road video monitor is used for shooting and uploading a road traffic condition in real time. The terminal device can construct an intelligent visual vehicle networking by using a Wireless broadband technology, such as a Wireless Fidelity (WiFi) hotspot of a Wireless city, a 3rd-Generation (3G) technology, a fourth Generation mobile communication technology (4G) or a fifth Generation mobile communication technology (5G), in combination with a video monitoring point established on the vehicle and on the road side, so as to realize visual management of a license plate, an accident site, an event, a disaster and the like. The vehicle control system can monitor people, vehicles, objects, roads and environments in a specific urban area in real time, record visual information of various urban objects in real time through cloud videos, and carry out labeling, coding and recording.

Further, referring to fig. 2, fig. 2 is a schematic block diagram of an architecture of an unmanned system according to an embodiment of the present application, and specifically, the unmanned system includes two parts, one part is implemented by hardware, and the other part is implemented by software. The hardware implementation part mainly comprises a sensor (sensor), a vehicle-to-vehicle (V2V) and an actuator (activator). The sensor is a detection device which can sense the measured information and convert the sensed information into an electric signal or other information in a required form according to a certain rule to be output so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like. The V2V communication technology is a communication technology that is not limited to fixed base stations, and provides direct end-to-end wireless communication for moving vehicles. That is, through the V2V communication technology, the vehicle terminals directly exchange wireless information with each other without being forwarded through the base station. Actuators, as output devices or transducers in control systems, can convert electricity, hydraulic pressure, air pressure, capacity, etc. into mechanical action.

The software implementation includes a perception (perception) module, a prediction (prediction) module, and a Localization (Localization) module. The Perception refers to the ability of the unmanned system to collect information from the environment and extract relevant knowledge from the information, and the Environmental Perception (Environmental awareness) refers specifically to the scene understanding ability of the environment, such as the location of obstacles, the detection of road signs, and the classification of data such as the detection of pedestrians and vehicles. The sensing module is responsible for detecting and calculating the objects and the attributes of the surrounding environment from the data transmitted by the sensors. The object information is calculated by the prediction module to generate a predicted track, and the predicted track is transmitted to the behavior decision module and the action planning module.

The prediction module is used for predicting the behavior of the object detected by the sensing module and transmitting the predicted result into a track with a time-space dimension to the downstream module.

Generally, the object information output by the sensing module includes position, speed, orientation, and object classification (such as vehicle, pedestrian, and bicycle), etc., and these sensing calculated output object attributes are biased toward objective physical attributes. By using these output attributes, in combination with objective physics laws, an "instantaneous prediction" of the object can be made in a very short time.

The Positioning module can estimate the current position of the vehicle, And a common unmanned vehicle Positioning method includes a Global Positioning System (GPS) And an Inertial Navigation System (Inertial Navigation System), And may further combine with a map-aided Positioning algorithm, for example, synchronous Positioning And map construction (SLAM), where the target of the SLAM is to construct a map And simultaneously use the map for Positioning, And the SLAM determines the current position of the vehicle by using the observed environmental characteristics.

The output result of the routing is not used by an actual driver, but is input to a downstream module for behavior decision, action planning and the like, and the level of the path planning is deeper to the lane level of a high-precision map used by the unmanned vehicle. The output of the route searching module strictly depends on the drawing of an unmanned vehicle high-precision map, and under certain strategy definition, the route searching module needs to solve the problem of calculating an optimal road running sequence from a starting point to an end point

Behavioral Decision (Behavioral Decision) accepts the results of routing, as well as perceptual prediction and map information. By integrating the input information, the behavior decision module macroscopically decides how the unmanned vehicle runs. The decision at the macro level includes normal car following on the road, waiting for avoidance when encountering traffic lights and pedestrians, and interactive passing between intersections and other vehicles.

Motion Planning (Motion Planning) can be split into two problems, trajectory Planning and velocity Planning respectively. The trajectory planning solves the problem of defining an optimized trajectory on a two-dimensional plane according to behavior decisions and comprehensive map information. The speed planning problem is to solve the problem of what speed to use for driving after one or several tracks are selected.

The task of Feedback Control is to implement the planned action, so the evaluation index of the Feedback Control module is the Control accuracy. There may be measurements within the control system, the controller outputs control actions by comparing the measurements of the vehicle with expected conditions,

to facilitate an understanding of the present application, definitions of some terms referred to herein will be described below.

1. A target vehicle: also referred to as "egocar" or unmanned vehicle, the target vehicle in this application may be an electric vehicle or a fuel vehicle.

2. Lead car (lead car): also referred to as "preceding vehicle", in the present application, the nearest surrounding vehicle appearing in the target lane ahead of the own vehicle is taken as the lead vehicle during the travel of the vehicle.

3. Time To Collision (TTC): indicating the time when the own vehicle will hit the preceding vehicle.

4. Secondary car (blocking car): indicating a recent environmental vehicle that has a hindrance to the movement of the vehicle in the next few seconds, except for the lead vehicle.

5. Vehicle Automatic Cruise Control (ACC): the automatic control system is used for automatically controlling the distance between the vehicles and the speed of the vehicles according to the condition of the vehicles ahead, thereby reducing the operation of a driver on an accelerator and a brake and improving the comfort.

6. Vehicle Emergency Braking system (AEB): the distance between the automobile and a front automobile or an obstacle is measured by adopting a radar, then the measured distance is compared with an alarm distance and a safety distance by utilizing a data analysis module, an alarm prompt is carried out when the measured distance is less than the alarm distance, and the AEB system is started when the measured distance is less than the safety distance even if a driver does not have time to step on a brake pedal, so that the automobile is automatically braked, and the safe trip is guaranteed.

7. G2 continuous curvature (G2 continuous): is a continuous grading of curves or curved surfaces, G2 continuous means that the curvature is continuous and that curves and curved surfaces have a high degree of smoothness. For easy understanding, please refer to fig. 3, fig. 3 is a schematic diagram of continuity curves corresponding to different levels in the embodiment of the present application, and as shown in the drawing, S1 is used to indicate a discontinuous curve, S2 is used to indicate a G0 curve with continuous points, and a G0 curve refers to a curved surface or a curve with continuous points. The curve has no break point, and the joint of the curved surfaces has no crack. S3 is used to indicate a G1 curve that is tangent-continuous, and a G1 curve refers to a curve that is continuous with curve points, and all connected line segments and curve pieces are in tangent relation. The S4 is used for indicating a G2 curve with continuous curvature, the G2 curve refers to a G2 curve with a curved surface or a continuous curve point, the curvature analysis result is continuous change, and the speed curve path generated by the application is close to a G2 curve. S5 is used for indicating a G3 curve with curvature tangency continuity, a G3 curve refers to a curve or curve point continuity, and the curvature curve or curvature curve analysis result is tangency continuity.

8. Jerk (jerk): representing the time rate of change of acceleration.

9. Jerk (snap): representing the time rate of change of jerk.

10. Jerk (crack): representing the time rate of change of snap.

11. Jerk (pop): representing the time rate of change of crack.

12. Automatic driving level: currently, automatic driving classified into levels L0 to L5 is common. Where the level L0 indicates that without automation technology, the vehicle is driven completely by the driver's manual operation without any automatic driving function. The L1 level indicates assist driving such as a vehicle equipped with constant-speed cruising, lane keeping, automatic parking, and the like. The level L2 indicates semi-automatic driving, and the level L2 automatic driving has many rudimentary functions of automatic driving vehicles, such as full-speed automatic assisted driving, automatic assisted driving in congestion, automatic hazard prediction braking, etc., but more times, the driver still needs to lead the vehicle to run, and only in a specific situation, the driver can temporarily leave the steering wheel by both hands. The level L3 indicates conditional autopilot, and at the level L3, the vehicle can realize autopilot of most road conditions, taking over a large part of the driving functions of the vehicle, but the driver still needs to keep attention at all times in order to take over the vehicle in time when an emergency occurs. The level L4 represents a high degree of autopilot, at the level L4 the automation system in the vehicle is already very sophisticated and the vehicle can take over the work of the driver to the level of autopilot, but can still take over if the driver wants to drive in person. L5 indicates full autopilot, i.e. the driver can completely ignore the driving situation.

The artificial intelligence-based vehicle control method is mainly applied to unmanned automobiles of L3 level and L4 level, and can also be applied to unmanned automobiles of other levels in practical application.

With reference to fig. 4, an embodiment of a vehicle control method according to the present application includes:

101. acquiring initial acceleration, initial speed, target acceleration and target speed corresponding to a target vehicle;

in the present embodiment, the vehicle control device acquires the current initial acceleration (a) of the target vehicle₀) Initial velocity (V)₀) Target acceleration (a)_T) And a target speed (V)_T) Wherein the initial acceleration (a)₀) Indicates the acceleration, initial velocity (V) corresponding to the current time of the target vehicle₀) Indicating the speed, target acceleration (a) corresponding to the current time of the target vehicle_T) Represents the acceleration, target speed (V) that the target vehicle needs to reach in the future T seconds_T) Indicating the speed that the target vehicle needs to reach in the future T seconds.

The vehicle control device according to the present application is disposed in a vehicle, and may also be disposed in a terminal device, and a command for controlling the vehicle is sent to the vehicle through the terminal device, so that the vehicle is controlled by a control system of the vehicle.

102. Determining a target scene type according to the initial acceleration, the initial speed and the target acceleration, wherein the target scene type is included in a scene type set, the scene type set comprises at least two scene types, each scene type corresponds to at least one group of adjusting parameters, the target scene type corresponds to N groups of adjusting parameters, and N is an integer greater than or equal to 1;

in the present embodiment, the vehicle control device is based on the initial speed (V)₀) It is possible to determine whether the target vehicle is currently in a stationary state, for example, an initial speed (V)₀) And equals 0 meters per second (m/s), indicating that the target vehicle is stationary. According to the initial speed (V)₀) It is also possible to determine whether the target vehicle is currently in a low-speed traveling state, for example, an initial speed (V)₀) When the speed is less than 12m/s, the target vehicle is in a low-speed running state. The vehicle control means may also incorporate an initial acceleration (a)₀) And a target acceleration (a)_T) And judging the scene type of the target vehicle. For example, whether a rapid deceleration is required, or whether the brake pedal needs to be released, etc.

Specifically, the vehicle control device needs to determine the target scene type where the target vehicle is located from at least two scene types, and since one scene type generally consists of at least one task type, each task type corresponds to one set of adjustment parameters, N sets of corresponding adjustment parameters can be obtained according to N task types included in the target scene type, and each set of adjustment parameters corresponds to one task type.

103. Acquiring N groups of adjusting parameters according to the type of a target scene, wherein each group of adjusting parameters is used for representing the change condition of the vehicle on the jerk, and the jerk is the time change rate of the acceleration;

in this embodiment, the vehicle control device may obtain N sets of adjustment parameters based on the target scene type. For example, the target scene type is a "following starting scene", and the "following starting scene" only includes a "static starting task", so that the vehicle control device needs to acquire the adjustment parameter corresponding to the "static starting task", where N is equal to 1, that is, a group of adjustment parameters is acquired. For another example, the target scene type is a "rapid deceleration scene", and the "rapid deceleration task" includes a "task of releasing an accelerator pedal" and a "rapid deceleration task", and therefore, the vehicle control device needs to acquire the adjustment parameter of the "task of releasing an accelerator pedal" and the adjustment parameter of the "rapid deceleration task", where N is equal to 2, that is, two sets of adjustment parameters are acquired.

It should be noted that each set of adjustment parameters is used to represent the variation of the vehicle on jerk, and specifically includes a jerk maximum value, a jerk minimum value, a jerk increasing rate, and a jerk decreasing rate.

104. Determining a speed curve path corresponding to the target vehicle through N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed;

in this embodiment, the vehicle control device uses N sets of adjustment parameters to adjust the initial acceleration (a) that has been acquired₀) Initial velocity (V)₀) Target acceleration (a)_T) And a target speed (V)_T) The calculation results in a speed profile path (speed profile), which may be a G2 continuous speed profile, representing the relationship between time and speed. Alternatively, the speed profile path can also be designed as a continuous speed profile of G3.

105. And controlling the target vehicle to run according to the speed curve path.

In this embodiment, the vehicle control device is favorable to improving the comfort of automatic driving because the G2 curve has high continuity and smoothness according to the calculated speed curve path, which satisfies the design of the G2 curve. Specifically, the vehicle Control apparatus may execute algorithms to implement Control of the target vehicle, and for example, the running of the target vehicle can be controlled based on the speed curve path using either an integral to Model Predictive Control (MPC) or a Linear Quadratic Regulator (LQR).

For ease of understanding, please refer to fig. 5, fig. 5 is a schematic view of a navigation interface in an automatic driving state in the embodiment of the present application, and as shown, the example is the level L3, at which the vehicle control device can control the target vehicle to travel on the road according to the calculated speed curve path without the participation of the driver. An automatic driving level, a current scene type (i.e., a target scene type), a current speed (i.e., an initial speed), and a projected speed (i.e., a target speed) may be presented on the navigation interface. If the driver operation needs to be switched, clicking 'switching to manual driving' is enough.

Optionally, on the basis of the embodiment corresponding to fig. 4, in another optional embodiment provided in the embodiment of the present application, the obtaining of the initial acceleration, the initial speed, the target acceleration, and the target speed corresponding to the target vehicle specifically includes the following steps:

acquiring positioning information of a target vehicle;

In the present embodiment, a method for acquiring an initial acceleration, an initial velocity, a target acceleration, and a target velocity is described. The vehicle control device can determine the initial acceleration and the initial speed of the target vehicle based on the positioning information, namely the initial acceleration and the initial speed of the speed curve path. The vehicle control apparatus also needs to determine a target acceleration and a target speed of the target vehicle based on the environmental information.

Specifically, the positioning system estimates the speed and acceleration of the target vehicle at the current moment to obtain an initial acceleration and an initial speed. The positioning system comprises but not limited to a GPS, an inertial navigation system, a speedometer, a camera, a laser radar and other sensors, and the position, the course and other information of the target vehicle can be acquired through the positioning system. The positioning technology can be divided into absolute positioning, relative positioning and combined positioning according to the positioning mode. The absolute positioning is realized by a GPS, and the absolute position and the course information of the vehicle on the earth are obtained by a satellite by adopting double antennas. The relative positioning means that acceleration and angular acceleration are obtained through an inertial navigation system or a sensor such as a milemeter and the like according to the initial pose of the vehicle, and the acceleration and the angular acceleration are integrated with time to obtain the current pose information relative to the initial pose. The combined positioning refers to combining absolute positioning and relative positioning to make up for the deficiency of a single positioning mode.

The map and sensing module provides environment information, namely the surrounding environment information and the vehicle state information are sensed through various sensors such as a camera, a laser radar, a millimeter wave radar, an ultrasonic radar, a gyroscope, an accelerometer and the like. The environmental information includes, but is not limited to, the shape, direction, curvature, gradient, lane, traffic sign, signal light, position, size, heading direction, speed, etc. of the road. The vehicle state information is not limited to the forward speed, acceleration, steering angle, vehicle body position and posture, and the like of the vehicle. The decision module can output the target acceleration and the target speed of the target vehicle within the future T seconds according to the environment information and the vehicle state information, the value of T can be 2-5 seconds, and the value can also be taken according to the actual situation, which is not limited here.

Secondly, in the embodiment of the application, a method for acquiring the initial acceleration, the initial speed, the target acceleration and the target speed is provided, through the above manner, the initial acceleration and the initial speed of the target vehicle can be accurately inferred by using the positioning information, and the target acceleration and the target speed can be accurately inferred by using the environmental information and the vehicle state information, so that important information is provided for planning a speed curve path, and the feasibility and the operability of a scheme are improved.

Optionally, on the basis of the embodiment corresponding to fig. 4, in another optional embodiment provided in the embodiment of the present application, the determining the target scene type according to the initial acceleration, the initial velocity, and the target acceleration specifically includes the following steps:

determining N task types according to the initial acceleration, the initial speed and the target acceleration, wherein each task type corresponds to one group of adjusting parameters;

In this embodiment, a method for determining a target scene type is introduced. Firstly, a plurality of scene types are required to be designed, each scene type corresponds to at least one task type, and different task types have different adjusting parameters. The vehicle control device may determine the corresponding task type based on the initial acceleration, the initial speed, and the target acceleration, and then determine the corresponding target scene type based on at least one task type, where the target scene type may be displayed on the vehicle navigation, or may not be displayed, and is not limited herein. Specifically, the method and the device are introduced by taking the example that the scene type set comprises four scene types, and in actual design, other scene types can be added. These four scenarios will be described separately below.

The first scenario is a conventional car following scenario, in which the design of the speed curve path is mainly based on comfort.

The second scenario is a rapid deceleration scenario, in which the vehicle is often required to reach the target speed as soon as possible, and therefore, the design of the speed curve path is mainly based on safety or acceleration experience.

The third scenario is an acceleration/deceleration switching scenario in which continuous acceleration or deceleration is required, and the influence of the response speed of the system on the comfort is greater than the influence of jerk on the comfort, so that it is necessary for the vehicle to leave the acceleration state speed as soon as possible and immediately start decelerating, or leave the deceleration state speed as soon as possible and immediately start accelerating. The design of the speed profile path allows for the use of larger jerk.

The fourth scene is a following vehicle starting scene, and in the following vehicle starting scene, the design of the speed curve path mainly takes comfort as a main factor.

Based on the above scene types, each scene type is composed of at least one task type, and the adjustment parameters corresponding to each task type will be described below with reference to table 1.

TABLE 1

As can be seen from table 1, it is,

the maximum value of the jerk is represented,jdenotes the jerk minimum value, s⁺Denotes the growth rate of jerk, s^-Indicating the rate of drop of jerk. It should be noted that the numerical values shown in table 1 are merely illustrative and should not be construed as limiting the present application. The above five task types are described separately below, and it is first necessary to define a current state and a target state, wherein the current state includes an initial speed (V)₀) And initial acceleration (a)₀) The target state includes a target speed (V)_T) And a target acceleration (a)_T) T denotes the target speed (V) reached within T seconds_T) Specifically:

the first type of task is a rapid deceleration task, e.g. to reach a_T＜-3.0m/s²In the case of (2), the rapid deceleration task is satisfied.

The second type of task is the release of the brake pedal task, e.g. to reach a₀＜-1.0m/s²And a is a_T≥0m/s²The task of releasing the brake pedal is fulfilled, at which time the target vehicle is restored from braking to a uniform speed or acceleration.

A third task type is the release of the accelerator pedal task, for example, to reach a₀＞1.0m/s²And a is a_T≤0m/s²The task of releasing the brake pedal is fulfilled, at which time the target vehicle is restored from acceleration to uniform velocity or braking.

A fourth type of task is a stationary start task, e.g. reaching V₀≈0m/s，a₀≈0m/s²，a_T＞0m/s²The stationary start task is satisfied, and at this time, the target vehicle is accelerated from a stopped state to a certain state.

The fifth task type is a normal driving task, and specifically includes acceleration to constant speed, deceleration to constant speed, acceleration to constant speed, and deceleration to constant speed.

The velocity profile path may be generated in various ways, such as a Dynamic Programming (DP) algorithm based on sampling, a rapid expansion random tree (RRT) algorithm, a Particle Filtering (PF) algorithm, an optimized Nonlinear Model Predictive Control (NMPC) algorithm, an Iterative Linear Quadratic Regulator (ILQR), and the like. The key link of the design of the method is the design and optimization of cost (cost) functions aiming at different scenes.

Secondly, in the embodiment of the present application, a method for determining a target scene type is provided, and by the above manner, in combination with a relationship between an initial acceleration, an initial velocity, and a target acceleration, a task type to be executed can be determined, and the one or more task types are suitable for a specific target scene type. Based on the above, it is easy to see that the combination relationship among the task types is considered when defining the scene types, so that a plurality of scene types are constructed, and the problem of rough scene type division in the existing scheme is solved. Meanwhile, the problem of slow response of the fuel vehicle is considered, the design of a speed curve path can be optimized by using multiple scene types, and therefore the applicability of the fuel vehicle on an algorithm is improved.

Optionally, on the basis of the embodiment corresponding to fig. 4, in another optional embodiment provided by the embodiment of the present application, the determining N task types according to the initial acceleration, the initial velocity, and the target acceleration specifically includes the following steps:

if the initial speed is greater than the static value, the initial acceleration is within a first acceleration interval, and the target acceleration is within a second acceleration interval, determining that the N task types comprise a conventional driving task;

determining a target scene type corresponding to the target vehicle from the scene type set according to the N task types, and specifically comprising the following steps:

In the embodiment, a method for determining a conventional car following scene is described. Assume initial velocity (V)₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Within a first acceleration interval, and a target acceleration (a)_T) In the second acceleration interval, it is determined that the N task types include a regular driving task, and the regular driving task may be specifically from acceleration to constant speed, from deceleration to constant speed, from constant speed to acceleration, or from constant speed to deceleration. For example, the first acceleration interval may be greater than or equal to-1.0 m/s²And is less than or equal to 1.0m/s²The second acceleration interval may be greater than or equal to 3m/s². It will be appreciated that the ranges of the first and second acceleration intervals are illustrative and should not be construed as limiting the application. The static value may be 0m/s, or 0 + -0.1 m/s, etc., and is not limited herein.

For easy understanding, please refer to fig. 6, and fig. 6 is a schematic view of an application scenario of a conventional following scenario in an embodiment of the present application, as shown in the drawing, a target vehicle is indicated by a1, a lead vehicle is indicated by a2, during a stable following process, a behavior of the lead vehicle is an important reference of a behavior of the target vehicle, and a target acceleration or a target speed of the target vehicle can be obtained through some decision-making algorithms and planning algorithms according to a position, a speed, acceleration information, lane speed limit information, and a motion state of a surrounding obstacle of the lead vehicle.

In the embodiment of the application, the conventional car following scene can be determined based on the initial acceleration, the initial speed and the target acceleration, so that the conventional car following is realized on an unmanned automobile, and the safety and the comfort of the unmanned system for following the automobile are guaranteed to a great extent.

Optionally, on the basis of the embodiment corresponding to fig. 4, in another optional embodiment provided in the embodiment of the present application, the obtaining N sets of adjustment parameters according to the target scene type specifically includes the following steps:

acquiring adjusting parameters corresponding to a conventional driving task according to a conventional vehicle following scene;

determining a speed curve path corresponding to the target vehicle through N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed, and specifically comprising the following steps:

In this embodiment, a method for generating a speed curve path in a conventional car following scene is introduced, and with reference to the contents shown in table 1 in the foregoing embodiment, based on the conventional car following scene, an adjustment parameter corresponding to a conventional driving task, that is, a jerk maximum value (e.g., 1.5 m/s) corresponding to the conventional driving task may be obtained³) Jerk minimum (e.g., -3 m/s)³) The growth rate of jerk (e.g., 2 m/s)⁴) The rate of descent of jerk (e.g., -5m/s⁴). Based on the above parameters, the initial velocity (V) that has been acquired is adopted₀) Initially addingSpeed (a)₀) Target speed (V)_T) And a target acceleration (a)_T) Namely, the speed at different moments in the target time period (i.e. the T time period) can be calculated.

Further, in the embodiment of the application, a method for generating a speed curve path in a conventional car following scene is provided, and in the manner, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a task corresponding to the conventional car following scene, so that comfort and safety in a process of driving a car to a heel can be achieved, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that flexibility and feasibility of a scheme are improved.

in a first time period, if the initial speed is greater than a static value, the initial acceleration is greater than a first threshold value, and the target acceleration is less than or equal to 0, determining that the N task types comprise tasks of releasing an accelerator pedal;

according to the N task types, determining a target scene type corresponding to the target vehicle from the scene type set, which may specifically include the following steps:

In this embodiment, a method for determining a sudden deceleration scenario is introduced. One case is, if the initial speed (V) is set during the first period of time, assuming that the target vehicle is in an accelerating state₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Greater than a first threshold and a target acceleration (a)_T) Less than or equal to 0, then the determination of the N task types includes releasing the accelerator pedal task. For example, the first threshold may be 1.0m/s². It is to be understood that the first threshold is merely illustrative and should not be construed as limiting the present application. The target vehicle stops accelerating, and within a second time period, if the initial speed (V)₀) Still greater than the static value (approximately equal to 0m/s), and the target acceleration (a)_T) And if the number of the tasks is less than the second threshold value, determining the N task types further comprises releasing the rapid deceleration task. For example, the second threshold may be-3.0 m/s². It is to be understood that the second threshold is merely illustrative and should not be construed as limiting the present application. The sum of the first period and the second period is a target period (i.e., T period).

Alternatively, if the initial speed (V) is assumed to be in a non-accelerating state of the target vehicle₀) Greater than a static value (approximately equal to 0m/s), and a target acceleration (a)_T) And if the N task types are smaller than the second threshold value, determining that the N task types comprise rapid deceleration tasks.

For easy understanding, please refer to fig. 7, fig. 7 is a schematic diagram of an application scenario of a rapid deceleration scenario in an embodiment of the present application, and as shown in the drawing, B1 indicates a target vehicle, and when a red light is encountered, a target acceleration or a target speed of the target vehicle can be obtained through some decision-making algorithms and planning algorithms. In addition, a rapid deceleration scene may occur in a scene such as an emergency cut-in or a rear-end collision.

In the embodiment of the application, the method for determining the rapid deceleration scene is provided, and the rapid deceleration scene can be determined based on the initial acceleration, the initial speed and the target acceleration through the mode, so that the rapid deceleration is realized on the unmanned automobile, and the safety and the comfort of the unmanned system following the automobile are guaranteed to a great extent.

Optionally, on the basis of the embodiment corresponding to fig. 4, in another optional embodiment provided in the embodiment of the present application, the obtaining N sets of adjustment parameters according to the target scene type may specifically include the following steps:

acquiring an adjusting parameter corresponding to a task of releasing an accelerator pedal according to a rapid deceleration scene;

based on the initial acceleration, the initial speed, the target acceleration and the target speed, determining a speed curve path corresponding to the target vehicle through the N groups of adjusting parameters, which may specifically include the following steps:

In this embodiment, a method for generating a speed curve path in a rapid deceleration scenario is described. In one case, with reference to the contents shown in table 1 in the foregoing embodiment, based on the rapid deceleration scenario, the adjustment parameter corresponding to the task of releasing the accelerator pedal and the adjustment parameter corresponding to the rapid deceleration task may be obtained. Namely, the maximum value of jerk (such as 0m/s) corresponding to the task of releasing the accelerator pedal is obtained³) Jerk minimum (e.g., -10 m/s)³) The growth rate of jerk (e.g., 10 m/s)⁴) The rate of descent of jerk (e.g., -10 m/s)⁴) And obtaining the maximal value of jerk (such as 0m/s) corresponding to the rapid deceleration task³) Jerk minimum (e.g., -10 m/s)³) The growth rate of jerk (e.g., 10 m/s)⁴) The rate of descent of jerk (e.g., -10 m/s)⁴). Based on the adjustment parameter corresponding to the accelerator pedal task and the adjustment parameter corresponding to the rapid deceleration task, the acquired initial speed (V) is adopted₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) I.e. the speed at different moments in the target time period, i.e. the T period, can be calculated. Wherein the target time period comprisesThe first time period is a time period corresponding to the task of releasing the accelerator pedal, and the second time period is a time period corresponding to the task of rapidly decelerating.

In another case, in combination with the contents shown in table 1 in the foregoing embodiment, based on the rapid deceleration scenario, only the jerk maximum value (e.g. 0m/s) corresponding to the rapid deceleration task may be obtained³) Jerk minimum (e.g., -10 m/s)³) The growth rate of jerk (e.g., 10 m/s)⁴) The rate of descent of jerk (e.g., -10 m/s)⁴). Based on the adjusting parameter corresponding to the rapid deceleration task, the obtained initial speed (V) is adopted₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) I.e. the speed at different moments in the target time period, i.e. the T period, can be calculated.

For ease of understanding, referring to fig. 8, fig. 8 is a schematic diagram of a speed curve path during deceleration in an embodiment of the present application, and as shown, for improved comfort, the speed curve path needs to achieve a continuity of curvature of G2 to ensure a sufficient degree of smoothness of the target vehicle longitudinal speed variation. To meet this design requirement, at least the design is required from the snap curve, and it is understood that higher order crackles and pops, etc. can also be used in the actual design. And then, a jerk curve, an acceleration curve and a speed curve are obtained in sequence through integration, and a displacement curve can also be obtained. FIG. 8 shows the path of the velocity profile during deceleration, where 0 to t1 indicate the establishment of the target acceleration (a)_T) T1 to tII represent the period of time of the uniform acceleration, and tII to tIII represent the period of time in which the acceleration gradually decreases to 0.

Since the initial velocity (V) is known₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) Therefore, it is necessary to design a connection initial velocity (V)₀) And target speed (V)_T) G2 continuous curve. Based on the adjustment parameters corresponding to each task type in table 1, the snap curve can be determined according to the corresponding time points (i.e. t1, t2, tI, tII, t3, t4 and tII) of the 6 acceleration phases shown in fig. 3, and finally, integration is sequentially performedA jerk curve, an acceleration curve and a velocity curve can be obtained. The 6 time parameters of the speed curve path are calculated as follows:

1. it is determined that t1, that is,

2. it is determined that t2, that is,

wherein Δ a ═ a_T-a₀)；

3. It is determined that the t, i.e.,

4. determining tII, i.e., tII ═ t1+ [ V (tII) -V (tI)]/a_TWherein, in the step (A),

5. it is determined that t3, that is,

6. determining t4, i.e. t4 ═ t₃+Δt1；

7. The time period tIII is determined, i.e., tIII ═ T, where T is a predefined target time period.

Further, in the embodiment of the application, a method for generating a speed curve path in a rapid deceleration scene is provided, and in the above manner, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task in the rapid deceleration scene, so that comfort and safety in a process of full heel of the vehicle can be realized on one hand, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that flexibility and feasibility of a scheme are improved.

in a first time period, if the initial speed is greater than the static value, the initial acceleration is less than a third threshold value, and the target acceleration is greater than or equal to 0, determining that the N task types comprise a task of releasing a brake pedal;

In this embodiment, a method for determining an acceleration/deceleration switching scenario is described. In one case, it is assumed that the target vehicle is in a braking state, during a first period of time, if the initial speed (V)₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Less than a third threshold and a target acceleration (a)_T) Less than or equal to 0, then determining that the N task types includes releasing the brake pedal task. For example, the third threshold may be-1.0 m/s². It is to be understood that the third threshold is merely an illustration and should not be construed as a limitation of the present application. If the initial speed (V) is set in the second time period in the state where the target vehicle starts moving₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Within a first acceleration interval, and a target acceleration (a)_T) In the second acceleration interval, it is determined that the N task types further include a regular driving task, and the regular driving task may be specifically from acceleration to constant speed, from deceleration to constant speed, from constant speed to acceleration, or from constant speed to deceleration. For example, the first acceleration interval may be greater than or equal to-1.0 m/s²And is less than or equal to 1.0m/s²The second acceleration interval may be greater than or equal to 3m/s². It will be appreciated that the ranges of the first and second acceleration intervals are illustrative and should not be construed as limiting the application. The static value may be 0m/s, or 0 + -0.1 m/s, etc., and is not limited herein. The target vehicle is in the normal following state, in the third time period, if the initial speed (V)₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Greater than a first threshold and a target acceleration (a)_T) Less than or equal to 0, then determining the N task types further includes releasing the accelerator pedal task. For example, the first threshold may be 1.0m/s². It is understood that the first threshold is only an illustration and should not be construed as a limitation of the present application, and the sum of the first time period, the second time period, and the third time period is the target time period (i.e., T time period).

In another case, it is assumed that the target vehicle is in a braking state, during a first period of time, if the initial speed (V) is₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Less than a third threshold and a target acceleration (a)_T) Less than or equal to 0, then determining that the N task types includes releasing the brake pedal task. If the initial speed (V) is set in the state where the target vehicle starts moving₀) Still greater than the static value (approximately equal to 0m/s), and the target acceleration (a)_T) And if the number of the tasks is less than the second threshold value, determining the N task types further comprises releasing the rapid deceleration task. For example, the second threshold may be-3.0 m/s². It is to be understood that the second threshold is merely illustrative and should not be construed as limiting the present application.

In another case, it is assumed that the target vehicle is in a normal following state for a first period of timeIf the initial velocity (V)₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Within a first acceleration interval, and a target acceleration (a)_T) Within the second acceleration interval, it is then determined that the N task types further comprise a regular driving task. The target vehicle is in the normal following state, in the second time period, if the initial speed (V)₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Greater than a first threshold and a target acceleration (a)_T) Less than or equal to 0, then determining the N task types further includes releasing the accelerator pedal task. In a third period of time with the target vehicle at rest, the initial speed (V)₀) Equal to a static value (equal to about 0m/s), an initial acceleration (a)₀) Also equal to a static value (equal to about 0m/s)²) And the target acceleration (a)_T) And if the number of the task types is more than 0, determining that the N task types also comprise a static vehicle starting task.

In another case, it is assumed that the target vehicle is in a normal following state, during the first period, if the initial speed (V) is₀) Greater than a static value (approximately equal to 0m/s), an initial acceleration (a)₀) Less than a third threshold and a target acceleration (a)_T) Less than or equal to 0, then determining that the N task types includes releasing the brake pedal task. The target vehicle is in the normal following state if the initial speed (V)₀) Still greater than the static value (approximately equal to 0m/s), and the target acceleration (a)_T) And if the number of the tasks is less than the second threshold value, determining the N task types further comprises releasing the rapid deceleration task.

It should be noted that the above cases all belong to acceleration/deceleration switching scenarios, and in practical cases, there are many cases that satisfy the acceleration/deceleration switching scenarios, which are not all exhaustive here.

For convenience of understanding, please refer to fig. 9, and fig. 9 is a schematic view of an application scenario of an acceleration/deceleration switching scenario in an embodiment of the present application, as shown in the drawing, C1 indicates a target vehicle, C2 and C3 indicate other vehicles on a lane, which often require frequent start and stop of the vehicle at a low speed in a congestion situation, and may also require sudden braking when a red light is encountered, based on which, a target acceleration or a target speed of the target vehicle may be obtained through some decision-making algorithms and planning algorithms.

For low-speed congestion scenarios, especially for fuel-oil vehicles, when acceleration and deceleration switching of the vehicle is subject to non-negligible and difficult-to-regulate response delay, it is necessary to design and optimize specifically for this particular problem. And the comfort of the target vehicle is not the primary consideration factor of the speed planning under all conditions, and the comfort can be reduced when necessary, and the response speed is obtained by increasing the design of jerk, so that the driving experience is improved.

In the embodiment of the application, a method for determining an acceleration and deceleration switching scene is provided, and the acceleration and deceleration switching scene can be determined based on the initial acceleration, the initial speed and the target acceleration, so that acceleration and deceleration switching is realized on an unmanned automobile, and the safety and the comfort of an unmanned system following the automobile are guaranteed to a great extent.

acquiring an adjusting parameter corresponding to a task of releasing a brake pedal according to an acceleration and deceleration switching scene;

In this embodiment, a method for generating a speed curve path in an acceleration/deceleration switching scenario is introduced, and in one case, in combination with the contents shown in table 1 in the foregoing embodiment, based on the acceleration/deceleration switching scenario, an adjustment parameter corresponding to a task of releasing a brake pedal, an adjustment parameter corresponding to a task of regular traveling, and an adjustment parameter corresponding to a task of releasing an accelerator pedal may be obtained. Namely, the maximum value of jerk (such as 10 m/s) corresponding to the task of releasing the brake pedal is obtained³) Jerk minimum (e.g., 0m/s)³) The growth rate of jerk (e.g., 10 m/s)⁴) The rate of descent of jerk (e.g., -10 m/s)⁴). And obtaining a jerk maximum value (such as 1.5 m/s) corresponding to the routine driving task³) Jerk minimum (e.g., -3 m/s)³) The growth rate of jerk (e.g., 2 m/s)⁴) The rate of descent of jerk (e.g., -5m/s⁴). And acquiring a jerk maximum value (such as 0m/s) corresponding to the task of releasing the accelerator pedal³) Jerk minimum (e.g., -10 m/s)³) The growth rate of jerk (e.g., 10 m/s)⁴) The rate of descent of jerk (e.g., -10 m/s)⁴)。

Based on the adjustment parameter corresponding to the task of releasing the brake pedal, the adjustment parameter corresponding to the task of regular driving, and the adjustment parameter corresponding to the task of releasing the accelerator pedal, the initial speed (V) that has been acquired is adopted₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) I.e. the speed at different moments in the target time period, i.e. the T period, can be calculated. The target time period comprises a first time period, a second time period and a third time period, wherein the first time period is a time period corresponding to a task of releasing the brake pedal, the second time period is a time period corresponding to a task of regular driving, and the third time period is a time period corresponding to a task of releasing the accelerator pedal.

It should be noted that, in an actual situation, the corresponding adjustment parameter needs to be obtained in combination with a specific task type in an acceleration and deceleration switching scenario, where the above example is described by taking an acceleration and deceleration switching scenario including a task of releasing a brake pedal, a task of normal driving, and a task of releasing an accelerator pedal as an example, but it is understood that, as described in the foregoing embodiment, the specific task type in the acceleration and deceleration switching scenario may further include a task of releasing a brake pedal and a task of releasing a rapid deceleration, or the specific task type in the acceleration and deceleration switching scenario may further include a task of normal driving, a task of releasing an accelerator pedal, a task of starting a stationary vehicle, and the like, which is not necessarily exhaustive.

Further, in the embodiment of the application, a method for generating a speed curve path in an acceleration and deceleration switching scene is provided, and in the manner, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task in the acceleration and deceleration switching scene, so that comfort and safety in a heel vehicle process can be achieved on one hand, and on the other hand, a corresponding speed curve path can be calculated in a targeted manner according to scene requirements, so that flexibility and feasibility of a scheme are improved.

if the initial acceleration and the initial speed are equal to static values and the target acceleration is greater than 0, determining that the N task types comprise a static vehicle starting task;

In this embodiment, a method for determining a following start scene is introduced, assuming an initial speed (V)₀) Equal to a static value (equal to about 0m/s), firstInitial acceleration (a)₀) Also equal to a static value (equal to about 0m/s)²) And the target acceleration (a)_T) If the value is greater than 0, it is determined that the N task types include a stationary vehicle starting task, and the static value may be 0m/s, and it is understood that the static value may be 0 ± 0.1m/s, which is not limited herein.

For convenience of understanding, please refer to fig. 10, fig. 10 is a schematic view of an application scenario of a following vehicle starting scenario in the embodiment of the present application, as shown in the drawing, D1 indicates a target vehicle, when the following vehicle starts, the target vehicle accelerates from a stationary state, in general, a lead vehicle may exist in front of the target vehicle, the lead vehicle behavior is an important reference of the target vehicle behavior, and according to the position, speed, acceleration information, lane speed limit information, and a motion state of a surrounding obstacle of the lead vehicle, a target acceleration or a target speed of the target vehicle may be obtained through some decision-making algorithms and planning algorithms. If there is no lead vehicle in front of the target vehicle, the target acceleration or target speed of the target vehicle can be determined according to the road surface condition, the lane speed limit information, the motion state of surrounding obstacles, and the like.

In the embodiment of the application, the method for determining the following starting scene is provided, and the following starting scene can be determined based on the initial acceleration, the initial speed and the target acceleration through the mode, so that the following starting is realized on an unmanned automobile, and the following safety and comfort of an unmanned system are guaranteed to a great extent.

acquiring an adjusting parameter corresponding to a static vehicle starting task according to a vehicle following starting scene;

In this embodiment, a method for generating a speed curve path in a following starting scene is introduced, and based on the following starting scene, an adjustment parameter corresponding to a static vehicle starting task, that is, a jerk maximum value (e.g., 2 m/s) corresponding to the static vehicle starting task may be obtained³) Jerk minimum (e.g., 0m/s)³) The growth rate of jerk (e.g., 2 m/s)⁴) The rate of descent of jerk (e.g., -2m/s⁴). Based on the above parameters, the initial velocity (V) that has been acquired is adopted₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) Namely, the speed at different moments in the target time period (i.e. the T time period) can be calculated.

For ease of understanding, referring to fig. 11, fig. 11 is a schematic diagram of a speed curve path during acceleration in the present embodiment, and as shown, for improved comfort, the speed curve path needs to achieve a continuity of curvature of G2 to ensure a sufficient smoothness of the target vehicle longitudinal speed variation. To meet this design requirement, at least the design is required from the snap curve, and it is understood that higher order crackles and pops, etc. can also be used in the actual design. And then, a jerk curve, an acceleration curve and a speed curve are obtained in sequence through integration, and a displacement curve can also be obtained. FIG. 11 is a graph showing a path of a speed curve during deceleration, wherein 0 to t1 indicate establishment of a target acceleration (a)_T) T1 to tII, and tII to tIII, respectively, indicate that the acceleration gradually reaches the target acceleration (a)_T) And (3) a stage of (a).

Since the initial velocity (V) is known₀) Initial acceleration (a)₀) Target speed (V)_T) And a target acceleration (a)_T) Therefore, it is necessary to design a connection initial velocity (V)₀) And target speed (V)_T) G2 continuous curve.Based on the adjustment parameters corresponding to each task type in table 1, the snap curve can be determined according to the corresponding time points (i.e., t1, t2, tI, tII, t3, t4, and tII) of the 6 acceleration phases shown in fig. 3, and finally, the jerk curve, the acceleration curve, and the velocity curve can be obtained by sequentially performing integration. The calculation method of the 6 time parameters of the speed curve path is similar to the foregoing embodiment, and is not described herein again.

Further, in the embodiment of the application, a method for generating a speed curve path in a car following starting scene is provided, and in the above manner, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task in the car following starting scene, so that comfort and safety in a car heel process can be achieved on one hand, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that flexibility and feasibility of a scheme are improved.

The present application combines the experimental results to verify the performance of the speed curve path, please refer to fig. 12, fig. 12 is a graph diagram based on the acceleration process in the embodiment of the present application, as shown, the planned curve is indicated by E1, and the speed obtained based on the acceleration simulation is indicated by E2, during the acceleration process, the speed curve and the acceleration curve from 10m/s to 14m/s have smooth effect at the corners.

Referring to fig. 13, fig. 13 is a graph illustrating a deceleration process according to an embodiment of the present invention, where F1 is a planned curve, and F2 is a velocity obtained based on an acceleration simulation, and both the velocity curve and the acceleration curve from 20m/s to 17m/s have a smooth effect at the corners during the deceleration process.

Therefore, the safety of releasing acceleration, reducing the speed of a brake pedal (namely shortening the acceleration and deceleration switching time of a target vehicle) and emergency braking can be considered in addition to ensuring the comfort of conventional vehicle following on unmanned vehicles at the level of L3 and the level of L4 and on traditional fuel vehicles for realizing the automatic driving function by means of an ACC system, and the safety and the comfort of the vehicle following scene of a common unmanned system are ensured to a great extent.

Referring to fig. 14, fig. 14 is a schematic view of an embodiment of a vehicle control device in an embodiment of the present application, and a vehicle control device 20 includes:

an obtaining module 201, configured to obtain an initial acceleration, an initial speed, a target acceleration, and a target speed corresponding to a target vehicle;

a determining module 202, configured to determine a target scene type according to an initial acceleration, an initial velocity, and a target acceleration, where the target scene type is included in a scene type set, the scene type set includes at least two scene types, each scene type corresponds to at least one set of adjustment parameters, the target scene type corresponds to N sets of adjustment parameters, and N is an integer greater than or equal to 1;

the obtaining module 201 is further configured to obtain N sets of adjusting parameters according to the type of the target scene, where each set of adjusting parameters is used to indicate a change condition of the vehicle in jerk, and the jerk is a time change rate of the acceleration;

the determining module 202 is further configured to determine a speed curve path corresponding to the target vehicle through the N sets of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration, and the target speed;

and the control module 203 is used for controlling the target vehicle to run according to the speed curve path.

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, the current scene type is determined based on a predefined scene type set, different scene types have different adjusting parameters, the corresponding adjusting parameters can be obtained aiming at the current scene type, and the different adjusting parameters are used as the constraint and index for defining the speed curve path, so that the problem of single speed curve path planning can be solved, a better vehicle following effect is achieved, and the safety and the comfort are improved in the vehicle driving process.

Alternatively, on the basis of the embodiment corresponding to fig. 14, in another embodiment of the vehicle control device 20 provided in the embodiment of the present application,

an obtaining module 201, specifically configured to obtain positioning information of a target vehicle;

In the embodiment of the application, the vehicle control device is provided, and by adopting the device, the initial acceleration and the initial speed of the target vehicle can be accurately deduced by utilizing the positioning information, and the target acceleration and the target speed can be accurately deduced by utilizing the environmental information and the vehicle state information, so that important information is provided for planning a speed curve path, and the feasibility and the operability of a scheme are improved.

a determining module 202, configured to determine N task types according to an initial acceleration, an initial speed, and a target acceleration, where each task type corresponds to a group of adjustment parameters;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, the type of the task to be executed can be determined by combining the relation among the initial acceleration, the initial speed and the target acceleration, and one or more task types are suitable for a specific target scene type. Based on the above, it is easy to see that the combination relationship among the task types is considered when defining the scene types, so that a plurality of scene types are constructed, and the problem of rough scene type division in the existing scheme is solved. Meanwhile, the problem of slow response of the fuel vehicle is considered, the design of a speed curve path can be optimized by using multiple scene types, and therefore the applicability of the fuel vehicle on an algorithm is improved.

the determining module 202 is specifically configured to determine that the N task types include a conventional driving task if the initial speed is greater than the static value, the initial acceleration is within a first acceleration interval, and the target acceleration is within a second acceleration interval;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, a conventional vehicle following scene can be determined based on initial acceleration, initial speed and target acceleration, so that the conventional vehicle following is realized on an unmanned vehicle, and the safety and comfort of the unmanned system vehicle following are ensured to a great extent.

the determining module 202 is specifically configured to obtain an adjusting parameter corresponding to a conventional driving task according to a conventional following scene;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a task corresponding to a conventional vehicle following scene, so that comfort and safety in a vehicle heel filling process can be achieved, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that flexibility and feasibility of a scheme are improved.

the determining module 202 is specifically configured to determine, in a first time period, that the N task types include a task of releasing an accelerator pedal if the initial speed is greater than the static value, the initial acceleration is greater than a first threshold, and the target acceleration is less than or equal to 0;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, a rapid deceleration scene can be determined based on initial acceleration, initial speed and target acceleration, so that rapid deceleration is realized on an unmanned automobile, and safety and comfort of an unmanned system following the automobile are guaranteed to a great extent.

the determining module 202 is specifically configured to obtain an adjusting parameter corresponding to a task of releasing an accelerator pedal according to a rapid deceleration scene;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task in a rapid deceleration scene, so that comfort and safety in the process of driving a heel can be achieved, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that the flexibility and the feasibility of a scheme are improved.

the determining module 202 is specifically configured to determine, in a first time period, if the initial speed is greater than the static value, the initial acceleration is less than a third threshold, and the target acceleration is greater than or equal to 0, that the N task types include a task of releasing a brake pedal;

In the embodiment of the application, the vehicle control device is provided, and by adopting the device, an acceleration and deceleration switching scene can be determined based on the initial acceleration, the initial speed and the target acceleration, so that acceleration and deceleration switching is realized on an unmanned automobile, and the safety and the comfort of an unmanned system following the automobile are ensured to a great extent.

the determining module 202 is specifically configured to obtain an adjusting parameter corresponding to a task of releasing a brake pedal according to an acceleration/deceleration switching scenario;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task under an acceleration and deceleration switching scene, so that comfort and safety in the process of driving the vehicle to a heel can be achieved, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, so that the flexibility and feasibility of a scheme are improved.

the determining module 202 is specifically configured to determine that the N task types include a stationary vehicle starting task if the initial acceleration and the initial speed are equal to static values and the target acceleration is greater than 0;

In the embodiment of the application, a vehicle control device is provided, adopt above-mentioned device, can follow the car scene of starting based on initial acceleration, initial velocity and target acceleration to realize starting with the car on unmanned car, to a great extent has ensured unmanned system and has followed security and travelling comfort of car.

the determining module 202 is specifically configured to obtain an adjusting parameter corresponding to a static vehicle starting task according to a vehicle following starting scene;

In the embodiment of the application, a vehicle control device is provided, and by adopting the device, before a target vehicle reaches a target state, a corresponding speed curve path is generated based on a corresponding task in a vehicle following starting scene, so that comfort and safety in a vehicle heel filling process can be achieved on the one hand, and on the other hand, a corresponding speed curve path can be calculated according to scene requirements in a targeted manner, and therefore the flexibility and the feasibility of a scheme are improved.

The embodiment of the present application further provides another vehicle control apparatus, where the vehicle control apparatus is disposed in a computer device, and the computer device may be a server or a terminal device, and the following description will take the computer device as the terminal device as an example. As shown in fig. 15, for convenience of explanation, only the portions related to the embodiments of the present application are shown, and details of the technology are not disclosed, please refer to the method portion of the embodiments of the present application. The terminal device may be any terminal device (or computer device) including a vehicle-mounted computer, a tablet computer, a Personal Digital Assistant (PDA), a point of sale (POS), a vehicle-mounted computer, and so on, taking the terminal device as the vehicle-mounted computer as an example:

fig. 15 is a block diagram showing a partial structure of an in-vehicle computer related to a terminal device according to an embodiment of the present application. Referring to fig. 15, the in-vehicle computer includes: radio Frequency (RF) circuit 310, memory 320, input unit 330, display unit 340, sensor 350, audio circuit 360, wireless fidelity (WiFi) module 370, processor 380, and power supply 390. Those skilled in the art will appreciate that the in-vehicle computer configuration shown in FIG. 15 is not intended to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The following specifically describes each component of the in-vehicle computer with reference to fig. 15:

the RF circuit 310 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 380; in addition, the data for designing uplink is transmitted to the base station. In general, the RF circuit 310 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuit 310 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to global system for mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Message Service (SMS), etc.

The memory 320 may be used to store software programs and modules, and the processor 380 executes various functional applications and data processing of the in-vehicle computer by operating the software programs and modules stored in the memory 320. The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phone book, etc.) created according to the use of the in-vehicle computer, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 330 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the in-vehicle computer. Specifically, the input unit 330 may include a touch panel 331 and other input devices 332. The touch panel 331, also referred to as a touch screen, can collect touch operations of a user (e.g., operations of the user on the touch panel 331 or near the touch panel 331 using any suitable object or accessory such as a finger, a stylus, etc.) on or near the touch panel 331, and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 331 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 380, and can receive and execute commands sent by the processor 380. In addition, the touch panel 331 may be implemented in various types, such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. The input unit 330 may include other input devices 332 in addition to the touch panel 331. In particular, other input devices 332 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 340 may be used to display information input by the user or information provided to the user and various menus of the in-vehicle computer. The display unit 340 may include a display panel 341, and optionally, the display panel 341 may be configured in the form of a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 331 can cover the display panel 341, and when the touch panel 331 detects a touch operation on or near the touch panel 331, the touch panel is transmitted to the processor 380 to determine the type of the touch event, and then the processor 380 provides a corresponding visual output on the display panel 341 according to the type of the touch event. Although the touch panel 331 and the display panel 341 are shown in fig. 15 as two separate components to implement the input and output functions of the in-vehicle computer, in some embodiments, the touch panel 331 and the display panel 341 may be integrated to implement the input and output functions of the in-vehicle computer.

The in-vehicle computer may also include at least one sensor 350, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display panel 341 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 341 and/or the backlight when the in-vehicle computer moves to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of the vehicle-mounted computer (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping) and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer and an infrared sensor which can be configured on the vehicle-mounted computer, the detailed description is omitted.

Audio circuitry 360, speaker 361, and microphone 362 may provide an audio interface between the user and the vehicle computer. The audio circuit 360 may transmit the electrical signal converted from the received audio data to the speaker 361, and the audio signal is converted by the speaker 361 and output; on the other hand, the microphone 362 converts the collected sound signals into electrical signals, which are received by the audio circuit 360 and converted into audio data, which are then processed by the audio data output processor 380 and then transmitted to, for example, another vehicle-mounted computer via the RF circuit 310, or output to the memory 320 for further processing.

WiFi belongs to short-distance wireless transmission technology, and the vehicle-mounted computer can help a user to receive and send e-mails, browse webpages, access streaming media and the like through the WiFi module 370, and provides wireless broadband internet access for the user. Although fig. 15 shows the WiFi module 370, it is understood that it does not belong to the essential constitution of the in-vehicle computer, and may be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 380 is a control center of the vehicle-mounted computer, connects various parts of the entire vehicle-mounted computer by using various interfaces and lines, and performs various functions and processes data of the vehicle-mounted computer by operating or executing software programs and/or modules stored in the memory 320 and calling data stored in the memory 320, thereby performing overall monitoring of the vehicle-mounted computer. Optionally, processor 380 may include one or more processing units; optionally, processor 380 may integrate an application processor, which primarily handles operating systems, user interfaces, application programs, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 380.

The vehicle computer also includes a power supply 390 (e.g., a battery) for supplying power to various components, and optionally, the power supply may be logically connected to the processor 380 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system.

Although not shown, the vehicle-mounted computer may further include a camera, a bluetooth module, and the like, which are not described herein.

In this embodiment, the processor 380 included in the terminal device further has the following functions:

and controlling the target vehicle to run according to the speed curve path.

It should be noted that the processor 380 included in the terminal device is further configured to execute the corresponding steps in each embodiment corresponding to fig. 4, which is not described herein again.

Also provided in an embodiment of the present application is a computer-readable storage medium having stored therein a computer program, which when run on a computer, causes the computer to execute the artificial intelligence based vehicle control method as described in the foregoing embodiments.

Embodiments of the present application also provide a computer program product comprising a program, which when run on a computer, causes the computer to execute the artificial intelligence based vehicle control method described in the foregoing embodiments.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A vehicle control method based on artificial intelligence, characterized by comprising:

determining a target scene type according to the initial acceleration, the initial speed and the target acceleration, wherein the target scene type is included in a scene type set, the scene type set comprises at least two scene types, each scene type corresponds to at least one set of adjusting parameters, the target scene type corresponds to N sets of adjusting parameters, and N is an integer greater than or equal to 1;

acquiring N groups of adjusting parameters according to the target scene type, wherein each group of adjusting parameters is used for representing the change condition of the vehicle on the jerk, and the jerk is the time change rate of the acceleration;

determining a speed curve path corresponding to the target vehicle through the N groups of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration and the target speed;

and controlling the target vehicle to run according to the speed curve path.

2. The vehicle control method according to claim 1, wherein the obtaining of the initial acceleration, the initial speed, the target acceleration, and the target speed corresponding to the target vehicle includes:

acquiring positioning information of the target vehicle;

determining the initial acceleration and the initial speed according to the positioning information of the target vehicle;

acquiring environmental information and vehicle state information of the target vehicle;

3. The vehicle control method of claim 1, wherein said determining a target scene type from the initial acceleration, the initial velocity, and the target acceleration comprises:

determining N task types according to the initial acceleration, the initial speed and the target acceleration, wherein each task type corresponds to a group of adjusting parameters;

4. The vehicle control method according to claim 3, wherein the determining N task types based on the initial acceleration, the initial speed, and the target acceleration includes:

if the initial speed is greater than a static value, the initial acceleration is within a first acceleration interval, and the target acceleration is within a second acceleration interval, determining that the N task types comprise a conventional driving task;

the determining, according to the N task types, a target scene type corresponding to the target vehicle from the scene type set includes:

and according to the conventional driving task, determining that the target scene type corresponding to the target vehicle is a conventional following scene from the scene type set.

5. The vehicle control method according to claim 4, wherein the obtaining N sets of adjustment parameters according to the target scene type includes:

acquiring an adjusting parameter corresponding to the conventional driving task according to the conventional car following scene;

the determining, by the N sets of adjustment parameters, a speed curve path corresponding to the target vehicle based on the initial acceleration, the initial speed, the target acceleration, and the target speed includes:

calculating to obtain speeds corresponding to different moments in a target time period according to the adjusting parameters corresponding to the conventional running task, the initial acceleration, the initial speed, the target acceleration and the target speed;

6. The vehicle control method according to claim 3, wherein the determining N task types based on the initial acceleration, the initial speed, and the target acceleration includes:

in a first time period, if the initial speed is greater than a static value, the initial acceleration is greater than a first threshold value, and the target acceleration is less than or equal to 0, determining that the N task types comprise a task of releasing an accelerator pedal;

in a second time period, if the initial speed is greater than a static value and the target acceleration is less than a second threshold, determining that the N task types further include a rapid deceleration task, where the second threshold is less than 0, and the second time period is a next time period adjacent to the first time period;

7. The vehicle control method according to claim 6, wherein the obtaining N sets of adjustment parameters according to the target scene type includes:

acquiring an adjusting parameter corresponding to the task of releasing the accelerator pedal according to the rapid deceleration scene;

determining the speeds of the target vehicle at different moments in the first time period and the speeds of the target vehicle at different moments in the second time period according to the adjusting parameters corresponding to the task of releasing the accelerator pedal and the adjusting parameters corresponding to the task of rapidly decelerating based on the initial acceleration, the initial speed, the target acceleration and the target speed;

8. The vehicle control method according to claim 3, wherein the determining N task types based on the initial acceleration, the initial speed, and the target acceleration includes:

in a first time period, if the initial speed is greater than a static value, the initial acceleration is less than a third threshold value, and the target acceleration is greater than or equal to 0, determining that the N task types comprise a task of releasing a brake pedal;

determining that the N task types comprise a regular driving task if the initial speed is greater than a static value, the initial acceleration is within a first acceleration interval, and the target acceleration is within a second acceleration interval within a second time period, wherein the second time period is the next time period adjacent to the first time period;

in a third time period, if the initial speed is greater than a static value, the initial acceleration is greater than a first threshold value, and the target acceleration is less than or equal to 0, determining that the N task types include a task of releasing an accelerator pedal, wherein the third time period is the next time period adjacent to the second time period;

and determining the target scene type corresponding to the target vehicle as an acceleration and deceleration switching scene from the scene type set according to the task of releasing the brake pedal, the task of normally driving and the task of releasing the accelerator pedal.

9. The vehicle control method according to claim 8, wherein the obtaining N sets of adjustment parameters according to the target scene type includes:

acquiring an adjusting parameter corresponding to the task of releasing the brake pedal according to the acceleration and deceleration switching scene;

acquiring an adjusting parameter corresponding to the conventional driving task according to the acceleration and deceleration switching scene;

acquiring an adjusting parameter corresponding to the task of releasing the accelerator pedal according to the acceleration and deceleration switching scene;

determining the speed of the target vehicle at different moments in the first time period, the speed of the target vehicle at different moments in the second time period and the speed of the target vehicle at different moments in the third time period based on the initial acceleration, the initial speed, the target acceleration and the target speed through the adjusting parameters corresponding to the task of releasing the brake pedal, the adjusting parameters corresponding to the task of normally running and the adjusting parameters corresponding to the task of releasing the accelerator pedal;

10. The vehicle control method according to claim 3, wherein the determining N task types based on the initial acceleration, the initial speed, and the target acceleration includes:

if the initial acceleration and the initial speed are equal to static values, and the target acceleration is greater than 0, determining that the N task types comprise a static vehicle starting task;

11. The vehicle control method of claim 10, wherein the obtaining N sets of tuning parameters according to the target scene type comprises:

acquiring an adjusting parameter corresponding to the static vehicle starting task according to the vehicle following starting scene;

calculating to obtain speeds corresponding to different moments in a target time period according to the adjusting parameters corresponding to the static vehicle starting task, the initial acceleration, the initial speed, the target acceleration and the target speed;

12. A vehicle control apparatus characterized by comprising:

a determining module, configured to determine a target scene type according to the initial acceleration, the initial velocity, and the target acceleration, where the target scene type is included in a scene type set, the scene type set includes at least two scene types, each scene type corresponds to at least one set of adjustment parameters, the target scene type corresponds to N sets of adjustment parameters, and N is an integer greater than or equal to 1;

the acquisition module is further configured to acquire N groups of adjustment parameters according to the target scene type, where each group of adjustment parameters is used to indicate a change condition of a vehicle in jerk, and the jerk is a time change rate of an acceleration;

the determining module is further configured to determine a speed curve path corresponding to the target vehicle through the N sets of adjusting parameters based on the initial acceleration, the initial speed, the target acceleration, and the target speed;

13. A computer device, comprising: a memory, a transceiver, a processor, and a bus system;

wherein the memory is used for storing programs;

a processor for executing a program in the memory, the processor being configured to perform the vehicle control method of any of claims 1 to 11 in accordance with instructions in the program code;

14. A vehicle characterized by comprising means for executing the vehicle control method according to any one of claims 1 to 11.

15. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the vehicle control method according to any one of claims 1 to 11.