CN111824157B - Automatic driving method and device - Google Patents

Automatic driving method and device Download PDF

Info

Publication number
CN111824157B
CN111824157B CN202010676750.6A CN202010676750A CN111824157B CN 111824157 B CN111824157 B CN 111824157B CN 202010676750 A CN202010676750 A CN 202010676750A CN 111824157 B CN111824157 B CN 111824157B
Authority
CN
China
Prior art keywords
target
information
moment
vehicle
driving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010676750.6A
Other languages
Chinese (zh)
Other versions
CN111824157A (en
Inventor
罗阳阳
赵季楠
赖健明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Xiaopeng Motors Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiaopeng Autopilot Technology Co Ltd filed Critical Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority to CN202010676750.6A priority Critical patent/CN111824157B/en
Publication of CN111824157A publication Critical patent/CN111824157A/en
Application granted granted Critical
Publication of CN111824157B publication Critical patent/CN111824157B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles

Abstract

The embodiment of the invention provides an automatic driving method and device, wherein the method comprises the following steps: acquiring running related information of a vehicle during automatic driving of the vehicle by a target user; predicting target track information according to the driving correlation information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user; controlling the vehicle to run according to the target track information; and then can realize that the control vehicle traveles according to user's driving habit, improves user experience.

Description

Automatic driving method and device
Technical Field
The invention relates to the technical field of automobiles, in particular to an automatic driving method and device.
Background
With the development of artificial intelligence, artificial intelligence is also widely applied to various fields, such as the field of vehicles. Vehicles employ artificial intelligence in many ways, such as voice assistance, autonomous driving (also known as unmanned driving), and the like. Automatic driving combines sensor, machine and artificial intelligence, realizes controlling vehicle and drives to promote the safety and the efficiency of whole driving action.
At present, in the automatic driving process, in the same scene, the same track is generated for different users; however, under various working conditions/scenarios (such as passing/following/winding driving, etc.), driving habits of different users are different. For example, starting to steer from how far away from the leading vehicle or obstacle; the transverse distance between the car and the target is kept during passing and obstacle detouring; in the lane changing process, the steering wheel is continuously changed until the lane changing is finished, or the steering wheel is firstly turned, held and turned back, and the like. Therefore, the track generated by the existing automatic driving cannot meet the driving habits of different users, and the automatic driving experience is poor.
Disclosure of Invention
The embodiment of the invention provides an automatic driving method for controlling vehicle driving based on a track conforming to driving habits of a user.
The embodiment of the invention also provides an automatic driving device to ensure the implementation of the method.
In order to solve the above problems, the present invention discloses an automatic driving method, comprising: acquiring running related information of a vehicle during automatic driving of the vehicle by a target user; predicting target track information according to the driving correlation information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user; and controlling the vehicle to run according to the target track information.
Optionally, the controlling the vehicle to run according to the target track information includes: determining target running associated information corresponding to the target track information according to the target track information and the track model; and controlling the vehicle to run according to the running related information, the target track information and the target running related information.
Optionally, the predicting target trajectory information according to the driving related information and a pre-generated trajectory model includes: inputting the running related information into a pre-generated working condition model to obtain a target running working condition output by the working condition model; and calling the track model to predict target track information based on the running associated information and the target running condition.
Optionally, the controlling the vehicle to run according to the running related information, the target trajectory information, and the target running related information includes: correcting the target track information according to the driving correlation information and the target driving correlation information to obtain corrected target track information; and controlling the vehicle to run according to the corrected target track information.
Optionally, the driving related information includes driving state information, and the corrected target trajectory information includes driving state information at a plurality of times; the controlling the vehicle to run according to the corrected target track information comprises the following steps: fitting the fitted track information between the corresponding position at the current moment and the corresponding position at the first moment according to the driving state information at the current moment of the vehicle and the driving state information at the first moment in the corrected target track information; controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information; and controlling the vehicle to run from a position corresponding to the first moment to a position corresponding to the last moment in the corrected target track information according to the corrected target track information.
Optionally, the target trajectory information includes driving state information at a plurality of moments, and the driving state information includes a speed; the travel related information includes a current speed of the target object, and the target travel related information includes a historical speed of the target object; the correcting the target track information according to the driving correlation information and the target driving correlation information to obtain the corrected target track information includes: determining speed compensation information according to the current speed and the historical speed of the target object; respectively determining the target speed of each moment according to the speed compensation information and the speed of each moment; and generating corrected target track information according to the target speed at each moment.
Optionally, the driving state information further includes: course angle, position information, acceleration, and curvature; the generating of the corrected target track information according to the target speed at each moment includes: aiming at a moment in the target track information, determining a target course angle at the moment according to a target speed at the moment, a curvature at the moment and a target course angle at the last moment; determining the target position information of the moment according to the target speed of the moment, the target course angle of the moment, the curvature of the moment and the position information of the previous moment; determining the target acceleration at the moment according to the target speed at the moment and the target speed at the last moment of the moment; and generating corrected target track information according to the target speed, the target position information, the target course angle, the target acceleration and the curvature at each moment.
An embodiment of the present invention further provides an automatic driving apparatus, including: the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring the driving related information of a vehicle in the automatic driving process of the vehicle of a target user; the prediction module is used for predicting target track information according to the driving correlation information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user; and the control module is used for controlling the vehicle to run according to the target track information.
Optionally, the control module includes: the information determining submodule is used for determining target running associated information corresponding to the target track information according to the target track information and the track model; and the vehicle control submodule is used for controlling the vehicle to run according to the running related information, the target track information and the target running related information.
Optionally, the prediction module is configured to input the driving related information into a pre-generated working condition model to obtain a target operating condition output by the working condition model; and calling the track model to predict target track information based on the running associated information and the target running condition.
Optionally, the vehicle control sub-module comprises: the correction unit is used for correcting the target track information according to the driving related information and the target driving related information to obtain corrected target track information; and the vehicle running control unit is used for controlling the vehicle to run according to the corrected target track information.
Optionally, the driving related information includes driving state information, and the corrected target trajectory information includes driving state information at a plurality of times; the vehicle running control unit is used for fitting the fitting track information between the corresponding position at the current moment and the corresponding position at the first moment according to the driving state information at the current moment of the vehicle and the driving state information at the first moment in the corrected target track information; controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information; and controlling the vehicle to run from a position corresponding to the first moment to a position corresponding to the last moment in the corrected target track information according to the corrected target track information.
Optionally, the target trajectory information includes driving state information at a plurality of moments, and the driving state information includes a speed; the travel related information includes a current speed of the target object, and the target travel related information includes a historical speed of the target object; the correction unit is used for determining speed compensation information according to the current speed and the historical speed of the target object; respectively determining the target speed of each moment according to the speed compensation information and the speed of each moment; and generating corrected target track information according to the target speed at each moment.
Optionally, the driving state information further includes: course angle, position information, acceleration, and curvature; the correction unit is used for determining a target course angle at a moment according to a target speed at the moment, the curvature of the moment and a target course angle at the previous moment aiming at the moment in the target track information; determining the target position information of the moment according to the target speed of the moment, the target course angle of the moment, the curvature of the moment and the position information of the previous moment; determining the target acceleration at the moment according to the target speed at the moment and the target speed at the last moment of the moment; and generating corrected target track information according to the target speed, the target position information, the target course angle, the target acceleration and the curvature at each moment.
Embodiments of the present invention further provide a readable storage medium, where instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform any one of the automatic driving methods according to the embodiments of the present invention.
Compared with the prior art, the embodiment of the invention has the following advantages:
in the embodiment of the invention, in the automatic driving process of the target user vehicle, the driving related information of the vehicle can be acquired; then, predicting target track information which accords with the driving habits of the target user according to the driving related information and a track model which is generated in advance based on the driving habits of the user; and controlling the vehicle to run according to the target track information, so that the vehicle is controlled to run according to the driving habits of the user, and the user experience is improved.
Drawings
FIG. 1 is a flow chart of the steps of an embodiment of an autopilot method of the present invention;
FIG. 2 is a flow chart of the steps of an alternative embodiment of an autopilot method of the present invention;
FIG. 3 is a flow chart of the steps of an alternative embodiment of an autopilot method of the present invention;
FIG. 4 is a flow chart of steps of a trajectory modification method embodiment of the present invention;
FIG. 5 is a flow chart of steps in an alternative embodiment of a trajectory modification method of the present invention;
FIG. 6 is a block diagram of an embodiment of an autopilot device of the present invention;
fig. 7 is a block diagram of an alternative embodiment of an autopilot device of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
According to the automatic driving method provided by the embodiment of the invention, the track conforming to the driving habit of the user can be generated in the automatic driving process, and then the vehicle is controlled to run based on the track conforming to the driving habit of the user, so that the user experience is improved.
Referring to FIG. 1, a flow chart of the steps of an embodiment of an autopilot method of the present invention is shown.
And 102, acquiring the running related information of the vehicle in the automatic driving process of the vehicle of the target user.
In the embodiment of the invention, the target user can select the automatic driving mode in the process of driving the vehicle; and then the automatic driving system controls the vehicle to realize the automatic driving of the vehicle. In the process of automatically driving the target user vehicle, the driving related information of the vehicle can be acquired; trajectory information is then generated based on the travel-related information to control the vehicle to travel based on the trajectory information.
The driving related information may include all information related to the driving of the target user vehicle, such as driving state information, driving environment information, and the like, which is not limited in this embodiment of the present invention.
And step 104, predicting target track information according to the driving related information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user.
And 106, controlling the vehicle to run according to the target track information.
In the embodiment of the invention, a track model can be generated in advance based on the driving habits of a target user; then, predicting target track information which accords with the driving habits of the target user in the current automatic driving process by adopting a track model generated in advance; the vehicle is then controlled based on the target trajectory information.
Wherein, the corresponding historical driving related information can be collected in advance during the driving process of the target user; the historical driving related information refers to information related to the driving of the target user vehicle in the process that the target user drives the vehicle before the current moment; then generating a track model based on historical driving related information; the specific method of generating the trajectory model will be described later.
After the driving related information of the vehicle is acquired, a track model generated in advance can be adopted, and target track information which accords with the driving habits of the target user in the current automatic driving process can be predicted based on the currently acquired driving related information. Wherein the target track information may include: driving state information of the vehicle at a plurality of times after the current time; one representation of the target trajectory information may be:
{t＝0：(x0,y0),θ0,kappa0,v0,a0；
t＝1：(x1,y1),θ1,kappa1,v1,a1；
t＝2：(x2,y2),θ2,kappa2,v2,a2；
......
t＝n：(xn,yn),θn,kappan,vn,an}
where t is the time after the current time, and t is the time after the current time0, may refer to a subsequent time after the current time. (x)0,y0)、(x1,y1)、(x2,y2) And (x)n,yn) May refer to location information of the target user's vehicle at each time. Theta0，θ1，θ2And thetanMay refer to the heading angle of the target user vehicle at each time. kappa type0，kappa1，kappa2And kappanAnd may refer to the curvature of the target user vehicle at each instant. v. of0、v1、v2And vnMay refer to the speed of the target user vehicle at each time. a is0、a1、a2And anMay refer to the acceleration of the target user vehicle at each instant.
In addition, in the automatic driving process, at a plurality of moments after the current moment, the vehicle can be controlled to run according to the driving state information at each moment in the target track information.
In summary, in the embodiment of the present invention, in the process of automatically driving the vehicle by the target user, the driving related information of the vehicle may be acquired; then, predicting target track information which accords with the driving habits of the target user according to the driving related information and a track model which is generated in advance based on the driving habits of the user; and controlling the vehicle to run according to the target track information, so that the vehicle can be controlled to run according to the driving habits of the user, and the user experience is improved.
How to generate the trajectory model will be described below.
In the embodiment of the invention, the operation conditions of the vehicle can be classified in advance; the operating condition may refer to an operating state of the vehicle under conditions directly related to its motion. Wherein, the classification mode to the operating condition can set up as required, for example according to the vehicle environment of traveling divides, and the operating condition of vehicle can include: working, going off duty, going out of country, going on business, etc. According to the vehicle driving road condition division, the operation condition of the vehicle may include: congestion, unobstructed, etc.; the operating conditions of the vehicle may include, according to the vehicle travel distance: long distance, short distance, etc., and the present invention is not limited in this regard.
As one example of the present invention, the operating conditions of the vehicle may be classified into at least the following categories: obstacle detouring working conditions, overtaking working conditions, following working conditions, detouring driving working conditions and lane changing working conditions.
According to the embodiment of the invention, the historical driving related information of the target user vehicle under each operation condition can be obtained when the target user drives the vehicle under the operation condition. The historical travel related information may include information related to the travel of the target user vehicle in a case where the target user drives the vehicle before the current time, and may include: historical vehicle information of the target user vehicle, historical driving environment information of the target user vehicle, historical distance information of the target user vehicle from a preceding target object, and historical driving state information of the target object. The historical vehicle information may include historical driving state information of the target user vehicle and other information, and the other information may refer to other information than the historical driving state information of the target user vehicle in the historical vehicle information, such as state information of vehicle devices, such as air conditioner temperature, seat angle, opening and closing of wipers, and the like. The target object may be a vehicle in front of the target user vehicle, or may be an obstacle in front of the target user vehicle, which is not limited in this embodiment of the present invention. The historical driving state information may include: position information, heading angle, curvature, speed, acceleration, and the like, which are not limited in this embodiment of the present invention.
In the embodiment of the invention, the operating condition model can be trained by adopting the operating condition and historical driving related information. The historical driving related information can be input into the working condition model, the working condition model carries out forward calculation on the historical driving related information, and the probability of various operating working conditions is output. Then, the probability of the historical driving associated information corresponding to the real operating condition can be searched from the probabilities of various operating conditions output by the operating condition model; and then carrying out reverse training on the working condition model by aiming at the maximum probability of the historical driving associated information output by the working condition model corresponding to the real operating working condition.
According to the embodiment of the invention, the track model can be generated according to the running condition and the historical running related information. The method comprises the steps that all historical driving related information under each operation condition can be classified according to each operation condition, and multiple types of historical driving related information are obtained; and then, for each type of historical driving associated information, fitting the historical driving state information of the target user vehicle in the type of historical driving associated information to obtain the historical track information corresponding to the type of historical driving associated information. The historical track information may be used to represent a track of the target user driving the vehicle during the process from the beginning to the end of the operating condition, and may include historical driving state information of the target user vehicle at a plurality of moments.
Further, according to the mode, historical track information of various historical driving related information corresponding to various operating conditions can be generated; and then generating a track model based on various running conditions, various historical running associated information corresponding to the various running conditions and historical track information of the various historical running associated information under the various running conditions.
In an optional embodiment of the present invention, the historical driving related information for generating the trajectory model may include: historical distance information of the target user vehicle from a preceding target object and historical driving state information of the target object.
In an optional embodiment of the present invention, the operating condition model may be a neural network; the trajectory model may be an expert system.
And then in the automatic driving process of the vehicle of the target user, target track information which accords with the habit of the target user can be predicted based on the trained working condition model and the generated track model.
Referring to FIG. 2, a flow chart of the steps of an alternative embodiment of an autonomous driving method of the present invention is shown.
Step 202, acquiring running related information of the vehicle in the automatic driving process of the vehicle of the target user.
In the embodiment of the invention, various information acquisition devices in the target user vehicle can acquire data in real time in the automatic driving process of the target user vehicle. For example, the image acquisition device can acquire an internal environment image of a target user vehicle and an external environment image of the vehicle; for another example, various sensors may collect status information of vehicle devices of the target user vehicle, such as pressure information, angle information, vehicle travel speed information, and the like of the seat. And then, the data acquired by the information acquisition equipment can be acquired, and the driving related information of the target user vehicle is generated. The driving related information of the target user vehicle may refer to information related to driving of the target user vehicle at the current time, and may include: vehicle information of the target user vehicle, traveling environment information of the target user vehicle, distance information of the target user vehicle from a preceding target object, and driving state information of the target object. The vehicle information may include driving state information of the target user vehicle and other information. The driving state information may include: position information, heading angle, curvature, speed, acceleration, and the like, which are not limited in this embodiment of the present invention.
And 204, inputting the running related information into a pre-generated working condition model to obtain a target running working condition output by the working condition model.
The current operating condition of the target user vehicle may then be determined based on the travel related information.
In an optional embodiment of the present invention, the driving related information may be input into the trained operating condition model, and the operating condition model performs forward calculation based on the driving related information to determine the probability of various operating conditions; and outputting the operation condition with the maximum probability. And then the operating condition output by the operating condition model can be determined as the current operating condition of the target user vehicle. For convenience of description, the current operating condition of the target user vehicle may be referred to as a target operating condition.
And step 206, calling the track model to predict target track information based on the running relevant information and the target running condition.
And then determining target track information by combining the running related information and the target running condition output by the condition model. The operation condition matched with the target operation condition can be found from the track model; and then searching the historical driving associated information with the highest matching degree with the driving associated information from various types of historical driving associated information corresponding to the operation condition matched with the target operation condition. And determining the historical track information corresponding to the type of historical driving related information with the highest matching degree with the driving related information as target track information. And then, the track information which is most matched with the current driving associated information and accords with the driving habits of the user is searched through the track model.
In an optional embodiment of the present invention, when the historical travel related information used to generate the trajectory model includes: when the historical distance information between the target user vehicle and the front target object and the historical driving state information of the target object are obtained, the driving related information for searching the target track information from the track model may also include: distance information of the target user vehicle from the preceding target object and driving state information of the target object.
And 208, determining target running related information corresponding to the target track information according to the target track information and the track model.
And step 210, controlling the vehicle to run according to the running related information, the target track information and the target running related information.
Since the target trajectory information is trajectory information that is driven under the condition of the target travel related information during the target user's historical driving of the vehicle, the target travel related information (i.e., the historical travel related information) is distinguished from the currently acquired travel related information; therefore, the target trajectory information output by the trajectory model may be different from the trajectory information of the target user actually driving the vehicle under the condition of the current driving related information. Therefore, after the target track information is determined, the historical driving related information corresponding to the target track information can be determined based on the track model. The type of historical travel related information corresponding to the target track information may be searched from the track model, and the historical related information may be determined as the target travel related information (i.e., the type of historical travel related information that has the highest degree of matching with the travel related information). Then, the vehicle is controlled by combining the driving related information, the target track information and the target driving related information; and then can be according to the current environment of traveling, the control vehicle traveles according to user's driving habit, further improves user experience.
Wherein, the step 210 may include the following sub-steps:
and a substep S2 of correcting the target trajectory information according to the driving related information and the target driving related information to obtain corrected target trajectory information.
And a substep S4 of controlling the vehicle to run according to the corrected target track information.
The driving related information and the target driving related information can be compared, and the target track information is corrected according to the comparison result so as to correct the target driving information into track information which is more in line with the driving habits of the user in the current driving environment; and then controlling the vehicle based on the corrected target track information.
In summary, in the process of controlling the vehicle to run according to the target track information, the target running related information corresponding to the target track information may be determined according to the target track information and the track model; then controlling the vehicle to run according to the running related information, the target track information and the target running related information; since the target trajectory information is trajectory information that is driven under the condition of the target travel related information during the target user's historical driving of the vehicle, the target travel related information (i.e., the historical travel related information) is distinguished from the currently acquired travel related information; further controlling the vehicle by combining the driving related information, the target track information and the target driving related information; and then can be according to current driving environment, the vehicle is driven according to user's driving habit to the control, further improves user experience.
How to control the vehicle based on the corrected target trajectory information will be described below.
Referring to FIG. 3, a flow chart of steps of an alternative embodiment of an autonomous driving method of the present invention is shown.
Step 302, in the automatic driving process of the target user vehicle, obtaining the driving related information of the vehicle.
And 304, inputting the running related information into a pre-generated working condition model to obtain a target running working condition output by the working condition model.
And step 306, calling the track model to predict target track information based on the running relevant information and the target running condition.
And 308, correcting the target track information according to the driving related information and the target driving related information to obtain corrected target track information.
Step 302 to step 308 are similar to step 202 to step 208, and are not described herein again.
Wherein, the vehicle is controlled to run according to the corrected target track information, and the following steps 310 to 314 may be referred to:
and 310, fitting the fitted track information between the position corresponding to the current moment and the position corresponding to the first moment according to the driving state information of the vehicle at the current moment and the driving state information of the first moment in the corrected target track information.
And step 312, controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information.
And step 314, controlling the vehicle to run from a position corresponding to the first moment to a position corresponding to the last moment in the corrected target track information according to the corrected target track information.
In the embodiment of the invention, the target track information comprises the driving state information of the vehicle at a plurality of moments after the current moment; and the position corresponding to the current moment has a certain distance with the position corresponding to the first moment in the target track information. Therefore, the embodiment of the invention can firstly determine the track information of the position corresponding to the target user vehicle from the current moment and the position corresponding to the first moment in the target track information; and then controlling the vehicle to run according to the target track information after controlling the vehicle to run to the position corresponding to the first moment of the target track information according to the track information. And the position corresponding to each moment in the target track information, namely the track point corresponding to each moment.
According to the driving state information of the vehicle at the current moment and the driving state information of the first moment in the corrected target track information, fitting track information between the corresponding position at the current moment and the corresponding position at the first moment can be fitted in multiple modes. For example, a fifth-order polynomial is used for fitting, and for example, a spline curve such as a B-spline, a 3-order spline, etc. is used for fitting, which is not limited in this embodiment of the present invention. The fitting track information may include driving state information at a plurality of times between the current time and the first time of the target track time.
And controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the driving state information at each moment in the fitted track information, such as position information, course angle, curvature, speed, acceleration and the like. And controlling the vehicle to travel from the position corresponding to the first moment to the position corresponding to the last moment in the corrected target track information according to the driving state information, such as position information, course angle, curvature, speed, acceleration and the like, of each moment in the corrected target track information.
In summary, in the embodiment of the present invention, in the process of controlling the vehicle according to the corrected target track information, the fitting track information between the position corresponding to the current time and the position corresponding to the first time may be fitted according to the driving state information of the vehicle at the current time and the driving state information of the first time in the corrected target track information; then controlling the vehicle to drive from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information, and controlling the vehicle to drive from the position corresponding to the first moment to the position corresponding to the last moment in the corrected target track information according to the corrected target track information; therefore, the vehicle can be controlled according to the target track information after the vehicle is controlled to run from the current position to the position corresponding to the first time of the target track information in the actual driving process.
How the target trajectory information is corrected will be described below.
Referring to FIG. 4, a flowchart illustrating steps of an embodiment of a trajectory modification method of the present invention is shown.
Step 402, determining speed compensation information according to the current speed and the historical speed of the target object.
And step 404, respectively determining the target speed at each moment according to the speed compensation information and the speed at each moment.
And step 406, generating corrected target track information according to the target speed at each moment.
In the embodiment of the invention, the target track information can be corrected based on the speed of the target object in front of the target user vehicle. The driving related information comprises the current speed of the target object, and the target driving related information comprises the historical speed of the target object corresponding to the target track information; the current speed of the target object can be compared with the historical speed of the target object, and the target track information can be corrected.
In an alternative embodiment of the present invention, a difference between the current velocity and the historical velocity of the target object may be calculated, and the difference may be used as the velocity compensation information. Then, based on the speed compensation information, the speed corresponding to each moment in the target track information is compensated, and the target speed corresponding to each moment is determined; and generating the corrected target track information based on the target speed at each moment. The driving state information at multiple times included in the target trajectory information includes other state information besides the speed, and the other state information may include: heading angle, position information, acceleration, and curvature. Therefore, the other state information at each time can be corrected based on the target speed at each time, and the corrected target trajectory information can be obtained.
In an optional embodiment of the present invention, if the speed compensation information is a difference between a historical speed and a current speed of the target object; for each time, the sum of the velocity at that time and the velocity compensation information may be calculated to obtain the target velocity at that time. If the speed compensation information is the difference value between the current speed and the historical speed of the target object; for each time, the difference between the speed at the time and the speed step information can be calculated to obtain the target speed at the time.
The following describes how to generate corrected target trajectory information based on the target velocity at each time.
The course angle, the position information and the acceleration of each moment in the target track information can be corrected according to the target speed of each moment, and corrected target track information is generated. The curvature in the target track information does not need to be corrected, that is, the curvature in the corrected target track information is the same as the curvature in the target track information.
Referring to FIG. 5, a flowchart illustrating steps of an alternative embodiment of a trajectory modification method of the present invention is shown.
Step 502, aiming at a moment in the target track information, determining a target course angle at the moment according to the target speed at the moment, the curvature at the moment and the target course angle at the previous moment.
Step 504, determining the target position information of the moment according to the target speed of the moment, the target course angle of the moment, the curvature of the moment and the position information of the previous moment.
Step 506, determining the target acceleration at the moment according to the target speed at the moment and the target speed at the previous moment.
Now, the following description will be given taking an example of correcting a heading angle, position information, and acceleration at a time in target trajectory information.
In the embodiment of the invention, the course angle compensation information at the moment can be calculated according to the target speed and the curvature at the moment. And then, determining the target course angle at the moment according to the course angle corresponding to the last moment of the moment and the corresponding course angle compensation information.
One implementation way of calculating the course angle compensation information may refer to the following formula:
Figure BDA0002584332340000141
wherein d θiIs course angle compensation information v 'of the ith moment'iTarget speed at the i-th time, RiThe curvature radius of the ith moment is shown, the reciprocal of the curvature radius is the curvature, and delta t is the time difference between two adjacent moments.
One implementation of calculating the target course angle at that time may refer to the following equation:
θ′i＝θ′i-1+dθi
θ′itarget course angle, theta, at the ith timei-1Is the target course angle at the i-1 th moment.
In the embodiment of the invention, the position compensation information of the moment can be determined according to the target speed of the moment, the time difference between two adjacent moments and the curvature of the moment; and then determining the target position information of the moment according to the position compensation information of the moment, the position information corresponding to the last moment of the moment and the target course angle of the moment.
One implementation manner of determining the position compensation information at this time may refer to the following formula:
dxi＝dt*v′i
Figure BDA0002584332340000142
wherein the position compensation information is (dx)i，dyi)。
One implementation of determining the target location information at this time may refer to the following equation:
pose′i＝pose′i-1·dposei
dposei＝(dxi,dyi,dθi)
pose′iis the target position information of the ith time'i-1Is the target position information of the (i-1) th moment. Wherein, the pos'iAnd fuse'i-1Dot product, i.e. matrix transformation.
In the embodiment of the present invention, the target acceleration at the time may be determined according to the target speed at the time and the target speed at the previous time. Reference may be made to the following equation:
a′i＝(v′i-v′i-1)/Δt
a′iis the acceleration at the ith moment, v'i-1Is the target speed at the i-1 st moment.
Where i can be a positive integer greater than or equal to 1. When i is 0, that is, the 0 th time, the target position information pos 'of the time'0Heading angle theta'0And acceleration a'0Position information (position) at the 0 th time in the target track information0Heading angle theta0And acceleration a0。
And step 508, generating corrected target track information according to the target speed, the target position information, the target course angle, the target acceleration and the curvature at each moment.
In one example of the present invention, the corrected target track information may be expressed as:
{t＝0：pose0θ0,kappa0,v′0,a0；
t＝1：pose′1,θ′1,kappa1,v′1,a′1；
t＝2：pose′2,θ′2,kappa2,v′2,a′2；
......
t＝n：pose′n,θ′n,kappan,v′n,a′n}
it should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 6, a block diagram of an embodiment of an automatic driving apparatus according to the present invention is shown, and may specifically include the following modules:
an obtaining module 602, configured to obtain driving related information of a target user vehicle during automatic driving of the vehicle;
a prediction module 604, configured to predict target trajectory information according to the driving related information and a pre-generated trajectory model, where the trajectory model is generated based on driving habits of the target user;
and the control module 606 is used for controlling the vehicle to run according to the target track information.
Referring to fig. 7, a block diagram of an alternative embodiment of an autopilot device of the present invention is shown.
In an optional embodiment of the present invention, the control module 606 includes:
an information determining submodule 6062, configured to determine, according to the target trajectory information and the trajectory model, target driving related information corresponding to the target trajectory information;
and a vehicle control sub-module 6064 configured to control the vehicle to run according to the running related information, the target trajectory information, and the target running related information.
In an optional embodiment of the present invention, the predicting module 604 is configured to input the driving related information into a pre-generated working condition model, so as to obtain a target operating condition output by the working condition model; and calling the track model to predict target track information based on the running associated information and the target running condition.
In an alternative embodiment of the present invention, the vehicle control sub-module 6064 includes:
a correcting unit 60642, configured to correct the target trajectory information according to the driving related information and the target driving related information, so as to obtain corrected target trajectory information;
and a vehicle running control unit 60644 configured to control the vehicle to run according to the corrected target trajectory information.
In an optional embodiment of the present invention, the driving related information includes driving state information, and the modified target trajectory information includes driving state information at a plurality of times; the vehicle running control unit 60644 is configured to fit the fitted track information between the position corresponding to the current time and the position corresponding to the first time according to the driving state information of the vehicle at the current time and the driving state information of the first time in the corrected target track information; controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information; and controlling the vehicle to run from a position corresponding to the first moment to a position corresponding to the last moment in the corrected target track information according to the corrected target track information.
In an optional embodiment of the present invention, the target trajectory information includes driving state information at a plurality of times, and the driving state information includes a speed; the travel related information includes a current speed of the target object, and the target travel related information includes a historical speed of the target object; the correcting unit 60642 is configured to determine speed compensation information according to the current speed and the historical speed of the target object; respectively determining the target speed of each moment according to the speed compensation information and the speed of each moment; and generating corrected target track information according to the target speed at each moment.
In an optional embodiment of the present invention, the driving state information further includes: course angle, position information, acceleration, and curvature; the correcting unit 60642 is configured to determine, for a moment in the target trajectory information, a target heading angle at the moment according to the target speed at the moment, the curvature at the moment, and the target heading angle at the previous moment; determining the target position information of the moment according to the target speed of the moment, the target course angle of the moment, the curvature of the moment and the position information of the previous moment; determining the target acceleration at the moment according to the target speed at the moment and the target speed at the last moment of the moment; and generating corrected target track information according to the target speed, the target position information, the target course angle, the target acceleration and the curvature at each moment.
In summary, in the embodiment of the present invention, in the automatic driving process of the target user vehicle, the driving related information of the vehicle may be acquired; then, predicting target track information which accords with the driving habits of the target user according to the driving related information and a track model which is generated in advance based on the driving habits of the user; and controlling the vehicle to run according to the target track information, so that the vehicle is controlled to run according to the driving habits of the user, and the user experience is improved.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
Embodiments of the present invention further provide a readable storage medium, where instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform any one of the automatic driving methods according to the embodiments of the present invention.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The present invention provides an automatic driving method and an automatic driving device, which are described in detail above, and the principle and the implementation of the present invention are explained in the present document by applying specific examples, and the description of the above examples is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (10)

1. An automated driving method, comprising:
acquiring running related information of a vehicle during automatic driving of the vehicle by a target user;
predicting target track information which accords with the driving habits of a target user in the current automatic driving process according to the driving correlation information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user;
and controlling the vehicle to run according to the target track information.
2. The method of claim 1, wherein said controlling said vehicle to travel in accordance with said target trajectory information comprises:
determining target running associated information corresponding to the target track information according to the target track information and the track model;
and controlling the vehicle to run according to the running related information, the target track information and the target running related information.
3. The method of claim 1, wherein predicting target trajectory information based on the travel related information and a pre-generated trajectory model comprises:
inputting the running related information into a pre-generated working condition model to obtain a target running working condition output by the working condition model;
and calling the track model to predict target track information based on the running associated information and the target running condition.
4. The method according to claim 2, wherein the controlling the vehicle to travel in accordance with the travel related information, the target trajectory information, and the target travel related information includes:
correcting the target track information according to the driving correlation information and the target driving correlation information to obtain corrected target track information;
and controlling the vehicle to run according to the corrected target track information.
5. The method according to claim 4, wherein the travel related information includes driving state information, and the corrected target trajectory information includes driving state information at a plurality of times;
the controlling the vehicle to run according to the corrected target track information comprises the following steps:
fitting the fitted track information between the corresponding position at the current moment and the corresponding position at the first moment according to the driving state information at the current moment of the vehicle and the driving state information at the first moment in the corrected target track information;
controlling the vehicle to run from the position corresponding to the current moment to the position corresponding to the first moment according to the fitted track information;
and controlling the vehicle to run from a position corresponding to the first moment to a position corresponding to the last moment in the corrected target track information according to the corrected target track information.
6. The method of claim 4, wherein the target trajectory information includes driving state information at a plurality of times, the driving state information including speed; the travel related information includes a current speed of the target object, and the target travel related information includes a historical speed of the target object;
the correcting the target track information according to the driving correlation information and the target driving correlation information to obtain the corrected target track information includes:
determining speed compensation information according to the current speed and the historical speed of the target object;
respectively determining the target speed of each moment according to the speed compensation information and the speed of each moment;
and generating corrected target track information according to the target speed at each moment.
7. The method of claim 6, wherein the driving state information further comprises: course angle, position information, acceleration, and curvature;
the generating of the corrected target track information according to the target speed at each moment includes:
aiming at a moment in the target track information, determining a target course angle at the moment according to a target speed at the moment, a curvature at the moment and a target course angle at the last moment;
determining the target position information of the moment according to the target speed of the moment, the target course angle of the moment, the curvature of the moment and the position information of the previous moment;
determining the target acceleration at the moment according to the target speed at the moment and the target speed at the last moment;
and generating corrected target track information according to the target speed, the target position information, the target course angle, the target acceleration and the curvature at each moment.
8. An autopilot device, the device comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring the driving related information of a vehicle in the automatic driving process of the vehicle of a target user;
the prediction module is used for predicting target track information which accords with the driving habits of a target user in the current automatic driving process according to the driving correlation information and a pre-generated track model, wherein the track model is generated based on the driving habits of the target user;
and the control module is used for controlling the vehicle to run according to the target track information.
9. The apparatus of claim 8, wherein the control module comprises:
the information determining submodule is used for determining target running associated information corresponding to the target track information according to the target track information and the track model;
and the vehicle control submodule is used for controlling the vehicle to run according to the running related information, the target track information and the target running related information.
10. A readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the autopilot method of any of method claims 1-7.
CN202010676750.6A 2020-07-14 2020-07-14 Automatic driving method and device Active CN111824157B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010676750.6A CN111824157B (en) 2020-07-14 2020-07-14 Automatic driving method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010676750.6A CN111824157B (en) 2020-07-14 2020-07-14 Automatic driving method and device

Publications (2)

Publication Number Publication Date
CN111824157A CN111824157A (en) 2020-10-27
CN111824157B true CN111824157B (en) 2021-10-08

Family

ID=72924182

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010676750.6A Active CN111824157B (en) 2020-07-14 2020-07-14 Automatic driving method and device

Country Status (1)

Country Link
CN (1) CN111824157B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112428991B (en) * 2020-11-30 2022-10-04 北京车和家信息技术有限公司 Vehicle control method, device, medium, equipment and vehicle
CN113665589B (en) * 2021-09-18 2023-04-07 广州小鹏自动驾驶科技有限公司 Vehicle longitudinal control method and device, vehicle-mounted terminal and storage medium
CN115107786B (en) * 2022-07-04 2023-06-16 广州市恒众车联网科技股份有限公司 Driving behavior correction system and method for intelligent automobile

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108820042A (en) * 2018-05-25 2018-11-16 东软集团股份有限公司 A kind of automatic Pilot method and device
CN110654372A (en) * 2018-06-29 2020-01-07 比亚迪股份有限公司 Vehicle driving control method and device, vehicle and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5959569A (en) * 1997-10-09 1999-09-28 Eaton Vorad Technologies, L.L.C. Method and apparatus for in path target determination for an automotive vehicle using a gyroscopic device
DE602006021188D1 (en) * 2005-07-26 2011-05-19 Macdonald Dettwiler & Associates Inc CAR
CN106114507B (en) * 2016-06-21 2018-04-03 百度在线网络技术（北京）有限公司 Local path planning method and device for intelligent vehicle
CN110400490B (en) * 2019-08-08 2022-02-25 腾讯科技（深圳）有限公司 Trajectory prediction method and apparatus
CN110758403B (en) * 2019-10-30 2022-03-01 北京百度网讯科技有限公司 Control method, device, equipment and storage medium for automatic driving vehicle

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108820042A (en) * 2018-05-25 2018-11-16 东软集团股份有限公司 A kind of automatic Pilot method and device
CN110654372A (en) * 2018-06-29 2020-01-07 比亚迪股份有限公司 Vehicle driving control method and device, vehicle and storage medium

Also Published As

Publication number Publication date
CN111824157A (en) 2020-10-27

Similar Documents

Publication Publication Date Title
CN111824157B (en) Automatic driving method and device
EP3219564B1 (en) Driving prediction with a deep neural network
JP6970117B2 (en) Control data creation method for driver rule-based support
US10183679B2 (en) Apparatus, system and method for personalized settings for driver assistance systems
US20200363800A1 (en) Decision Making Methods and Systems for Automated Vehicle
US9915948B2 (en) System and method for controlling motion of vehicle
CN112840350A (en) Autonomous vehicle planning and prediction
CN110406530B (en) Automatic driving method, device, equipment and vehicle
CN110850861A (en) Attention-based hierarchical lane change depth reinforcement learning
US20160325743A1 (en) Method for improving performance of a method for computationally predicting a future state of a target object, driver assistance system, vehicle including such driver assistance system and respective program storage medium and program
CN111845766A (en) Method for automatically controlling automobile
US11400942B2 (en) Vehicle lane trajectory probability prediction utilizing kalman filtering with neural network derived noise
JP2021026720A5 (en)
US11358612B2 (en) Method for controlling an automated or autonomous locomotive device, and evaluation unit
US11934957B2 (en) Methods, systems, and apparatuses for user-understandable explainable learning models
CN113661106A (en) Model-based predictive control to determine input variables for vehicle actuators
Do et al. Lane change–intention inference and trajectory prediction of surrounding vehicles on highways
US20210213977A1 (en) Nearby Driver Intent Determining Autonomous Driving System
Okuda et al. Model predictive driver assistance control for cooperative cruise based on hybrid system driver model
KR102427366B1 (en) Lane estimation method and apparatus using deep neural network
Misawa et al. Prediction of driving behavior based on sequence to sequence model with parametric bias
CN115092181A (en) Vehicle control method and device, storage medium and processor
Arbabi et al. Lane-change initiation and planning approach for highly automated driving on freeways
KR20220108823A (en) Systems and methods for predicting the trajectory of a vehicle
Gutiérrez-Moreno et al. Hybrid decision making for autonomous driving in complex urban scenarios

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: Room 46, room 406, No.1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou City, Guangdong Province 510000

Applicant after: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd.

Address before: Room 46, room 406, No.1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou City, Guangdong Province 510000

Applicant before: Guangzhou Xiaopeng Internet of vehicles Technology Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20201027

Assignee: GUANGZHOU XIAOPENG MOTORS TECHNOLOGY Co.,Ltd.

Assignor: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd.

Contract record no.: X2021440000219

Denomination of invention: An automatic driving method and device

Granted publication date: 20211008

License type: Common License

Record date: 20211220

EE01 Entry into force of recordation of patent licensing contract
TR01 Transfer of patent right

Effective date of registration: 20240226

Address after: 510000 No.8 Songgang street, Cencun, Tianhe District, Guangzhou City, Guangdong Province

Patentee after: GUANGZHOU XIAOPENG MOTORS TECHNOLOGY Co.,Ltd.

Guo jiahuodiqu after: Zhong Guo

Address before: Room 46, room 406, No.1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou City, Guangdong Province 510000

Patentee before: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd.

Guo jiahuodiqu before: Zhong Guo

TR01 Transfer of patent right