CN117734692A - Method, device, equipment and storage medium for determining lane change result of vehicle - Google Patents
Method, device, equipment and storage medium for determining lane change result of vehicle Download PDFInfo
- Publication number
- CN117734692A CN117734692A CN202311558615.1A CN202311558615A CN117734692A CN 117734692 A CN117734692 A CN 117734692A CN 202311558615 A CN202311558615 A CN 202311558615A CN 117734692 A CN117734692 A CN 117734692A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane change
- hidden state
- determining
- related information
- 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.)
- Pending
Links
- 230000008859 change Effects 0.000 title claims abstract description 157
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000013528 artificial neural network Methods 0.000 claims abstract description 34
- 230000006870 function Effects 0.000 claims description 79
- 230000001133 acceleration Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000004913 activation Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 7
- 125000004122 cyclic group Chemical group 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for determining a lane change result of a vehicle. Comprising the following steps: acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information; constructing a door function model, and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information; and determining a vehicle lane change result according to the hidden state and the candidate hidden state. The method has the advantages that the gate function model comprising the cyclic neural network structure is constructed, the acquired vehicle related information of the current vehicle is input into the model in a time sequence form, so that the hidden state and the candidate hidden state of the current vehicle are determined, the vehicle lane change result is acquired, the importance degree of different vehicles on the lane change decision of the vehicle can be distinguished, the problems that the number of parameters is large and the calculation time is long in the lane change decision model based on data driving are solved, and the lane change decision efficiency of the vehicle is improved.
Description
Technical Field
The present invention relates to the field of vehicle control technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining a lane change result of a vehicle.
Background
The life style of people can be changed in the future of automatic driving, the utilization rate and the traffic capacity of automobiles can be improved, the mobility of people with inconvenient actions is enhanced, the fatigue of drivers is relieved, and traffic accidents caused by the error of the drivers are reduced. Autopilot is a critical problem in the automotive field, and research on lane changing of vehicles is an important component thereof.
The existing lane change model is mainly based on a safe distance model, fuzzy control and a data driving method, the former two methods are poor in robustness, cannot be suitable for various scenes, and have certain limitation. In addition, the existing model based on data driving has more parameters and long calculation time, and the relation between the vehicle and the surrounding environment vehicle cannot be fully considered.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for determining a lane change result of a vehicle so as to realize lane change behavior decision aiming at an unmanned vehicle.
According to an aspect of the present invention, there is provided a vehicle lane change result determining method, the method including:
acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information;
constructing a door function model, and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information;
and determining a vehicle lane change result according to the hidden state and the candidate hidden state.
Optionally, acquiring vehicle related information of the current vehicle includes: taking the transverse speed, the longitudinal speed, the transverse acceleration and the longitudinal acceleration of the current vehicle acquired according to the appointed time as current vehicle information; taking the lateral speed, the longitudinal speed, the lateral acceleration, the longitudinal acceleration, the lateral distance from the current vehicle and the longitudinal distance from the current vehicle of the surrounding vehicles acquired according to the designated time as surrounding vehicle information; taking the transverse speed, the longitudinal speed, the transverse acceleration, the longitudinal acceleration, the transverse distance from the current vehicle and the longitudinal distance from the current vehicle of the left and right lane vehicles acquired according to the appointed time as left and right lane vehicle information; the current vehicle information, surrounding vehicle information, and left and right lane vehicle information are taken as vehicle-related information.
Optionally, constructing the gate function model includes: building a circulating neural network structure; acquiring history related information of the current vehicle according to the appointed time interval, and determining acquisition time corresponding to each history related information; grouping each history related information according to the acquisition time to generate a sample time sequence, wherein the sample time sequence comprises a specified number of history related information; and generating a gate function model according to the sample time sequence and the circulating neural network structure.
Optionally, generating a gate function model according to the sample time sequence and the recurrent neural network structure includes: training the circulating neural network structure according to the sample time sequence, and determining a training loss function; and when the training loss function converges, taking the corresponding target neural network structure as a gate function model.
Optionally, determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information includes: inputting the related information of each vehicle into a door function model to determine candidate hidden states; and acquiring an update door, and substituting the update door and the candidate hidden state into a specified algorithm to determine the hidden state, wherein the candidate hidden state and the hidden state are vehicle running state information.
Optionally, determining the lane change result of the vehicle according to the hidden state and the candidate hidden state includes: splicing the hidden state and the candidate hidden state to generate a splicing result; inputting the splicing result into a preset full-connection layer to generate a lane change intention value, wherein the full-connection layer comprises a designated activation function; and determining a vehicle lane change result according to the lane change intention value.
Optionally, determining the lane change result of the vehicle according to the lane change intention value includes: when the lane change intention value is larger than or equal to a first preset threshold value and smaller than a second preset threshold value, determining that the lane change result of the vehicle is a left lane change; when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, determining that the lane change result of the vehicle is not lane change; and when the lane change intention value is larger than the third preset threshold value and smaller than or equal to the fourth preset threshold value, determining that the lane change result of the vehicle is right lane change.
According to another aspect of the present invention, there is provided a vehicle lane change result determination apparatus including:
the vehicle related information acquisition module is used for acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information;
the model construction and state determination module is used for constructing a door function model and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information;
and the vehicle lane change result determining module is used for determining a vehicle lane change result according to the hidden state and the candidate hidden state.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a vehicle lane change result determination method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement a method for determining a lane change result of a vehicle according to any one of the embodiments of the present invention when executed.
According to the technical scheme provided by the embodiment of the invention, the door function model comprising the cyclic neural network structure is constructed, and the acquired vehicle related information of the current vehicle is input into the model in a time sequence form, so that the hidden state and the candidate hidden state of the current vehicle are determined, the vehicle lane change result is further acquired, the importance degree of influence of different vehicles on the lane change decision of the own vehicle can be distinguished, the problems of multiple parameters and long calculation time of the lane change decision model based on data driving are solved, and the lane change decision efficiency of the vehicle is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for determining a lane change result of a vehicle according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a gate function model according to a first embodiment of the present invention;
FIG. 3 is a flowchart of another vehicle lane change result determination method according to a first embodiment of the present invention;
FIG. 4 is a flowchart of another vehicle lane change result determination method according to the second embodiment of the present invention;
fig. 5 is a schematic structural diagram of a lane change result determining apparatus for a vehicle according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device for implementing a method for determining a lane change result of a vehicle according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," 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.
Example 1
Fig. 1 is a flowchart of a method for determining a lane change result of a vehicle according to an embodiment of the present invention, where the method may be performed by a lane change result determining device of a vehicle, and the lane change result determining device of the vehicle may be implemented in hardware and/or software, and the lane change result determining device of the vehicle may be configured in the vehicle. As shown in fig. 1, the method includes:
s110, acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information.
The vehicle lane change result refers to a reference result of a lane change behavior decision of the current vehicle in an automatic driving process, and because the actual traffic scene application of the automatic driving vehicle is subjected to a complex driving environment with high uncertainty and dynamic interaction, various vehicle related information such as current vehicle information, surrounding vehicle information and vehicle information on left and right lanes need to be referred to when the vehicle lane change behavior decision is performed.
S120, constructing a door function model, and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information.
Optionally, constructing the gate function model includes: building a circulating neural network structure; acquiring history related information of the current vehicle according to the appointed time interval, and determining acquisition time corresponding to each history related information; grouping each history related information according to the acquisition time to generate a sample time sequence, wherein the sample time sequence comprises a specified number of history related information; and generating a gate function model according to the sample time sequence and the circulating neural network structure.
Specifically, the recurrent neural network refers to a time series neural network (Gate Recurrent Unit, GRU), which is a neural network capable of processing sequence data, which can use history information to predict the current state. In the lane change decision, the GRU can judge whether lane change is needed or not and the direction and the time of lane change according to the movement track of the vehicle and the change of the surrounding environment. The output of the gate function model is the lane change intention value, the lane change intention recognition problem can be defined as (X, Y), X is the input, X= { X 1 ,X 2 ,…，X t (wherein X is t ＝{S t Eft, ot }, where S t Representing current vehicle information, S t ∈R n ,n＝4,Ef t Indicating surrounding vehicle information Ef t ∈R m ，m＝6，O t Indicating the vehicle information of the lanes on the left side and the right side, O t ∈R u×m U=4, that is, indicates that the left lane is closest to the vehicle and the right lane is closest to the vehicle. Y is the output, Y= { y| -1. Ltoreq.y.ltoreq.1 }.
Specifically, the gate function model is trained through a sample time sequence, and a user can specify a time interval, for example, 1s, at this time, the controller groups each history related information according to the collection time to generate a sample time sequence, and when the user groups the sample time sequence, for example, when the number is 7, each group includes 7 sample time sequences of adjacent collection times.
Optionally, generating a gate function model according to the sample time sequence and the recurrent neural network structure includes: training the circulating neural network structure according to the sample time sequence, and determining a training loss function; and when the training loss function converges, taking the corresponding target neural network structure as a gate function model.
Specifically, the cyclic neural network structure comprises an encoder, the encoder is composed of two-way O-GRUs, the O-GRUs are gating units based on surrounding target vehicles, the cyclic neural network structure can be trained according to a sample time sequence, a training loss function in the training process is determined, and when the training loss function converges, the training of a gate function model is completed.
Optionally, determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information includes: inputting the related information of each vehicle into a door function model to determine candidate hidden states; and acquiring an update door, and substituting the update door and the candidate hidden state into a specified algorithm to determine the hidden state, wherein the candidate hidden state and the hidden state are vehicle running state information.
Specifically, at time step t, the hidden state is represented by the following formula (1):
wherein z is t Is the update gate, +.，Is a candidate hidden state expressed by the following formula (2):
wherein x is t As input, a t For the information gate control of the cycle, o t For gating vehicles on lanes on both sides, E t For controlling the front door of a bicycle lane, r t For forgetting gating, W is an optimization parameter, t is a time step, h t-1 To be in the last hidden state Ef t Representing surrounding vehicle information, H (S) t ) Is a linear transformation of the input vehicle information.
Specifically, H (S t ) The calculation process of (2) is represented by the following formula (3):
wherein a is t For the information gate control of the cycle, o t For gating vehicles on lanes on both sides, E t For controlling the front door of a bicycle lane, r t For forgetting gating, W is an optimization parameter, t is a time step, h t-1 To be in the last hidden state Ef t Representing surrounding vehicle information, H (S) t ) Is a linear transformation of input vehicle information, S t Representing current vehicle information, O t Indicating left and right lane vehicle information.
The specific embodiment is as follows: fig. 2 is a schematic diagram of a gate function model according to an embodiment of the present invention, in which in fig. 2, the gate function model is input as a time sequence X, x= { X 1 ,X 2 ,…，X t (wherein X is t ＝{S t Eft, ot }, where S t Representing current vehicle information, ef t Representing surrounding vehicle information, O t Indicating left and right lane vehicle information. The input is passed through an encoder consisting of a bi-directional O-GRU, O-GRU is a gating unit based on surrounding target vehicles, a controller can splice outputs of the bidirectional O-GRUs together, finally outputs a spliced result to a full-connection layer, obtains a final output result Y through a tanh activation function, and the Y represents a lane change intention value, wherein Y= { y|1 is less than or equal to Y1 }.
S130, determining a vehicle lane change result according to the hidden state and the candidate hidden state.
Fig. 3 is a flowchart of a method for determining a lane change result of a vehicle according to an embodiment of the present invention, and step S130 mainly includes steps S131 to S133 as follows:
s131, splicing the hidden state and the candidate hidden state to generate a splicing result.
S132, inputting the splicing result into a preset full-connection layer to generate a lane change intention value, wherein the full-connection layer comprises a designated activation function.
Specifically, the controller may splice the hidden state and the candidate hidden state to generate a spliced result, and then output the spliced result to the full-connection layer, where the full-connection layer includes a specified activation function, and the specified activation function may be a tanh activation function, that is, a final lane change intention value is obtained through the tanh activation function.
S133, determining a vehicle lane change result according to the lane change intention value.
Optionally, determining the lane change result of the vehicle according to the lane change intention value includes: when the lane change intention value is larger than or equal to a first preset threshold value and smaller than a second preset threshold value, determining that the lane change result of the vehicle is a left lane change; when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, determining that the lane change result of the vehicle is not lane change; and when the lane change intention value is larger than the third preset threshold value and smaller than or equal to the fourth preset threshold value, determining that the lane change result of the vehicle is right lane change.
Specifically, the preset threshold value is set by the user according to the driving situation of the vehicle, and for example, the first preset threshold value may be-1, the second preset threshold value may be-0.3, the third preset threshold value may be 0.3, the fourth preset threshold value may be 1, and when the lane change intention value is greater than or equal to the first preset threshold value and less than the second preset threshold value, that is, -1 is less than or equal to Y < -0.3, the lane change result of the vehicle is determined to be left lane change. And when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, namely Y is larger than or equal to-0.3 and smaller than or equal to 0.3, determining that the lane change result of the vehicle is not lane change. When the lane change intention value is larger than the third preset threshold value and smaller than or equal to the fourth preset threshold value, namely, Y is more than 0.3 and less than or equal to 1, determining that the lane change result of the vehicle is right lane change.
According to the technical scheme provided by the embodiment of the invention, the door function model comprising the cyclic neural network structure is constructed, and the acquired vehicle related information of the current vehicle is input into the model in a time sequence form, so that the hidden state and the candidate hidden state of the current vehicle are determined, the vehicle lane change result is further acquired, the importance degree of influence of different vehicles on the lane change decision of the own vehicle can be distinguished, the problems of multiple parameters and long calculation time of the lane change decision model based on data driving are solved, and the lane change decision efficiency of the vehicle is improved.
Example two
Fig. 4 is a flowchart of a method for determining a lane change result of a vehicle according to a second embodiment of the present invention, where a specific process for obtaining vehicle-related information of a current vehicle is added on the basis of the first embodiment. The specific contents of steps S250-S260 are substantially the same as steps S120-S130 in the first embodiment, so that a detailed description is omitted in this embodiment. As shown in fig. 4, the method includes:
and S210, taking the transverse speed, the longitudinal speed, the transverse acceleration and the longitudinal acceleration of the current vehicle acquired according to the designated time as current vehicle information.
And S220, taking the lateral speed, the longitudinal speed, the lateral acceleration, the longitudinal acceleration, the lateral distance from the current vehicle and the longitudinal distance from the current vehicle of the surrounding vehicles acquired according to the designated time as surrounding vehicle information.
S230, taking the transverse speed, the longitudinal speed, the transverse acceleration, the longitudinal acceleration, the transverse distance from the current vehicle and the longitudinal distance from the current vehicle of the left and right lane vehicles acquired according to the appointed time as left and right lane vehicle information.
And S240, taking the current vehicle information, surrounding vehicle information and left and right lane vehicle information as vehicle related information.
Specifically, the gate function model is input as a time series X, x= { X 1 ,X 2 ,…，X t (wherein X is t ＝{S t Eft, ot }, where S t Representing current vehicle information, ef t Representing surrounding vehicle information, O t Indicating left and right lane vehicle information. The current vehicle information includes a lateral speed, a longitudinal speed, a lateral acceleration, and a longitudinal acceleration of the current vehicle. The surrounding vehicle information includes a lateral speed, a longitudinal speed, a lateral acceleration, a longitudinal acceleration, a lateral distance from the current vehicle, and a longitudinal distance from the current vehicle of the surrounding vehicle. The left and right lane vehicle information includes a lateral speed, a longitudinal speed, a lateral acceleration, a longitudinal acceleration, a lateral distance from the current vehicle, and a longitudinal distance from the current vehicle of the left and right lane vehicles.
S250, constructing a door function model, and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information.
Optionally, constructing the gate function model includes: building a circulating neural network structure; acquiring history related information of the current vehicle according to the appointed time interval, and determining acquisition time corresponding to each history related information; grouping each history related information according to the acquisition time to generate a sample time sequence, wherein the sample time sequence comprises a specified number of history related information; and generating a gate function model according to the sample time sequence and the circulating neural network structure.
Optionally, generating a gate function model according to the sample time sequence and the recurrent neural network structure includes: training the circulating neural network structure according to the sample time sequence, and determining a training loss function; and when the training loss function converges, taking the corresponding target neural network structure as a gate function model.
Optionally, determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information includes: inputting the related information of each vehicle into a door function model to determine candidate hidden states; and acquiring an update door, and substituting the update door and the candidate hidden state into a specified algorithm to determine the hidden state, wherein the candidate hidden state and the hidden state are vehicle running state information.
S260, determining a vehicle lane change result according to the hidden state and the candidate hidden state.
Optionally, determining the lane change result of the vehicle according to the hidden state and the candidate hidden state includes: splicing the hidden state and the candidate hidden state to generate a splicing result; inputting the splicing result into a preset full-connection layer to generate a lane change intention value, wherein the full-connection layer comprises a designated activation function; and determining a vehicle lane change result according to the lane change intention value.
Optionally, determining the lane change result of the vehicle according to the lane change intention value includes: when the lane change intention value is larger than or equal to a first preset threshold value and smaller than a second preset threshold value, determining that the lane change result of the vehicle is a left lane change; when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, determining that the lane change result of the vehicle is not lane change; and when the lane change intention value is larger than the third preset threshold value and smaller than or equal to the fourth preset threshold value, determining that the lane change result of the vehicle is right lane change.
According to the technical scheme provided by the embodiment of the invention, the door function model comprising the cyclic neural network structure is constructed, and the acquired vehicle related information of the current vehicle is input into the model in a time sequence form, so that the hidden state and the candidate hidden state of the current vehicle are determined, the vehicle lane change result is further acquired, the importance degree of influence of different vehicles on the lane change decision of the own vehicle can be distinguished, the problems of multiple parameters and long calculation time of the lane change decision model based on data driving are solved, and the lane change decision efficiency of the vehicle is improved.
Example III
Fig. 5 is a schematic structural diagram of a vehicle lane change result determining apparatus according to a third embodiment of the present invention. As shown in fig. 5, the apparatus includes: a vehicle-related information acquiring module 310, configured to acquire vehicle-related information of a current vehicle, where the vehicle-related information includes current vehicle information, surrounding vehicle information, and left and right lane vehicle information;
the model construction and state determination module 320 is configured to construct a door function model, and determine a hidden state and a candidate hidden state of the current vehicle according to the door function model and the vehicle related information;
the vehicle lane change result determining module 330 is configured to determine a vehicle lane change result according to the hidden state and the candidate hidden state.
Optionally, the vehicle related information obtaining module 310 is specifically configured to: taking the transverse speed, the longitudinal speed, the transverse acceleration and the longitudinal acceleration of the current vehicle acquired according to the appointed time as current vehicle information; taking the lateral speed, the longitudinal speed, the lateral acceleration, the longitudinal acceleration, the lateral distance from the current vehicle and the longitudinal distance from the current vehicle of the surrounding vehicles acquired according to the designated time as surrounding vehicle information; taking the transverse speed, the longitudinal speed, the transverse acceleration, the longitudinal acceleration, the transverse distance from the current vehicle and the longitudinal distance from the current vehicle of the left and right lane vehicles acquired according to the appointed time as left and right lane vehicle information; the current vehicle information, surrounding vehicle information, and left and right lane vehicle information are taken as vehicle-related information.
Optionally, the model building and status determining module 320 specifically includes: the gate function model building unit is used for: building a circulating neural network structure; acquiring history related information of the current vehicle according to the appointed time interval, and determining acquisition time corresponding to each history related information; grouping each history related information according to the acquisition time to generate a sample time sequence, wherein the sample time sequence comprises a specified number of history related information; and generating a gate function model according to the sample time sequence and the circulating neural network structure.
Optionally, the gate function model building unit specifically includes: a gate function model generation subunit configured to: training the circulating neural network structure according to the sample time sequence, and determining a training loss function; and when the training loss function converges, taking the corresponding target neural network structure as a gate function model.
Optionally, the model building and status determining module 320 specifically includes: a state determining unit configured to: inputting the related information of each vehicle into a door function model to determine candidate hidden states; and acquiring an update door, and substituting the update door and the candidate hidden state into a specified algorithm to determine the hidden state, wherein the candidate hidden state and the hidden state are vehicle running state information.
Optionally, the vehicle lane change result determining module 330 specifically includes: a splicing result generating unit, configured to: splicing the hidden state and the candidate hidden state to generate a splicing result; the lane change intention value generating unit is used for: inputting the splicing result into a preset full-connection layer to generate a lane change intention value, wherein the full-connection layer comprises a designated activation function; the vehicle lane change result determining unit is used for: and determining a vehicle lane change result according to the lane change intention value.
Optionally, the vehicle lane change result determining unit is specifically configured to: when the lane change intention value is larger than or equal to a first preset threshold value and smaller than a second preset threshold value, determining that the lane change result of the vehicle is a left lane change; when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, determining that the lane change result of the vehicle is not lane change; and when the lane change intention value is larger than the third preset threshold value and smaller than or equal to the fourth preset threshold value, determining that the lane change result of the vehicle is right lane change.
According to the technical scheme provided by the embodiment of the invention, the door function model comprising the cyclic neural network structure is constructed, and the acquired vehicle related information of the current vehicle is input into the model in a time sequence form, so that the hidden state and the candidate hidden state of the current vehicle are determined, the vehicle lane change result is further acquired, the importance degree of influence of different vehicles on the lane change decision of the own vehicle can be distinguished, the problems of multiple parameters and long calculation time of the lane change decision model based on data driving are solved, and the lane change decision efficiency of the vehicle is improved.
The vehicle lane change result determining device provided by the embodiment of the invention can execute the vehicle lane change result determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example IV
Fig. 6 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a vehicle lane change result determination method.
In some embodiments, a vehicle lane change result determination method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of a vehicle lane change result determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform a vehicle lane change result determination method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A vehicle lane change result determining method, characterized by comprising:
acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information;
constructing a door function model, and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information;
and determining a vehicle lane change result according to the hidden state and the candidate hidden state.
2. The method of claim 1, wherein the obtaining vehicle-related information for the current vehicle comprises:
taking the transverse speed, the longitudinal speed, the transverse acceleration and the longitudinal acceleration of the current vehicle acquired according to the appointed time as the current vehicle information;
taking the lateral speed, the longitudinal speed, the lateral acceleration, the longitudinal acceleration, the lateral distance from the current vehicle and the longitudinal distance from the current vehicle of the surrounding vehicles acquired according to the designated time as the surrounding vehicle information;
taking the transverse speed, the longitudinal speed, the transverse acceleration, the longitudinal acceleration, the transverse distance from the current vehicle and the longitudinal distance from the current vehicle of the left and right lane vehicles acquired according to the appointed time as the left and right lane vehicle information;
and taking the current vehicle information, the surrounding vehicle information and the left and right lane vehicle information as the vehicle related information.
3. The method of claim 1, wherein said constructing a gate function model comprises:
building a circulating neural network structure;
acquiring history related information of a current vehicle according to a specified time interval, and determining acquisition time corresponding to each history related information;
grouping each of the history related information according to the acquisition time to generate a sample time sequence, wherein the sample time sequence comprises a specified number of history related information;
and generating the gate function model according to the sample time sequence and the circulating neural network structure.
4. A method according to claim 3, wherein said generating said gate function model from said time series of samples and said recurrent neural network structure comprises:
training the circulating neural network structure according to the sample time sequence, and determining a training loss function;
and when the training loss function converges, taking the corresponding target neural network structure as the gate function model.
5. The method of claim 1, wherein the determining the hidden state and the candidate hidden state of the current vehicle from the door function model and the vehicle-related information comprises:
inputting each of the vehicle-related information into the door function model to determine the candidate hidden state;
and acquiring an update door, and substituting the update door and the candidate hidden state into a specified algorithm to determine the hidden state, wherein the candidate hidden state and the hidden state are vehicle running state information.
6. The method of claim 1, wherein the determining a vehicle lane change result from the hidden state and the candidate hidden state comprises:
splicing the hidden state and the candidate hidden state to generate a splicing result;
inputting the splicing result into a preset full-connection layer to generate a lane change intention value, wherein the full-connection layer comprises a designated activation function;
and determining a vehicle lane change result according to the lane change intention value.
7. The method of claim 6, wherein the determining a vehicle lane change result from the lane change intention value comprises:
when the lane change intention value is larger than or equal to a first preset threshold value and smaller than a second preset threshold value, determining that the lane change result of the vehicle is a left lane change;
when the lane change intention value is larger than or equal to a second preset threshold value and smaller than or equal to a third preset threshold value, determining that the lane change result of the vehicle is no lane change;
and when the lane change intention value is larger than a third preset threshold value and smaller than or equal to a fourth preset threshold value, determining that the lane change result of the vehicle is a right lane change.
8. A lane change result determining apparatus for a vehicle, comprising:
the vehicle related information acquisition module is used for acquiring vehicle related information of a current vehicle, wherein the vehicle related information comprises current vehicle information, surrounding vehicle information and left and right lane vehicle information;
the model construction and state determination module is used for constructing a door function model and determining the hidden state and the candidate hidden state of the current vehicle according to the door function model and the vehicle related information;
and the vehicle lane change result determining module is used for determining a vehicle lane change result according to the hidden state and the candidate hidden state.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A computer storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311558615.1A CN117734692A (en) | 2023-11-21 | 2023-11-21 | Method, device, equipment and storage medium for determining lane change result of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311558615.1A CN117734692A (en) | 2023-11-21 | 2023-11-21 | Method, device, equipment and storage medium for determining lane change result of vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117734692A true CN117734692A (en) | 2024-03-22 |
Family
ID=90251675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311558615.1A Pending CN117734692A (en) | 2023-11-21 | 2023-11-21 | Method, device, equipment and storage medium for determining lane change result of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117734692A (en) |
-
2023
- 2023-11-21 CN CN202311558615.1A patent/CN117734692A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220105961A1 (en) | Method for automatic control of vehicle and method for training lane change intention prediction network | |
| Choi et al. | Uncertainty-based object detector for autonomous driving embedded platforms | |
| CN114771572A (en) | Automatic driving track prediction method, device, equipment and storage medium | |
| JP2022078310A (en) | Image classification model generation method, device, electronic apparatus, storage medium, computer program, roadside device and cloud control platform | |
| CN114987546A (en) | Training method, device and equipment of trajectory prediction model and storage medium | |
| CN113408711A (en) | Ship motion extremely-short-term forecasting method and system based on LSTM neural network | |
| CN116092055A (en) | Training method, acquisition method, device, equipment and automatic driving vehicle | |
| CN115829058A (en) | Training sample processing method, cross-modal matching method, device, equipment and medium | |
| CN115860102A (en) | Pre-training method, device, equipment and medium for automatic driving perception model | |
| CN114386599A (en) | Method and device for training trajectory prediction model and trajectory planning | |
| CN114639233B (en) | Congestion state prediction method and device, electronic equipment and storage medium | |
| CN116499487B (en) | Vehicle path planning method, device, equipment and medium | |
| CN116311893A (en) | Traffic jam time prediction method and device, electronic equipment and storage medium | |
| CN117734692A (en) | Method, device, equipment and storage medium for determining lane change result of vehicle | |
| CN115447617A (en) | Vehicle control method, device, equipment and medium | |
| CN116842392B (en) | Track prediction method and training method, device, equipment and medium of model thereof | |
| CN113791564B (en) | Remote control method, device, equipment, cloud server and control system | |
| CN116721536A (en) | Unmanned decision result determining method, device, equipment and medium | |
| CN117669686A (en) | Model processing method and device and electronic equipment | |
| CN117494043A (en) | Target motion trail prediction method and device, electronic equipment and medium | |
| CN115476882A (en) | Behavior decision model optimization method, behavior decision device, behavior decision equipment and behavior decision medium | |
| CN116700065A (en) | Control method and device of unmanned equipment, electronic equipment and storage medium | |
| CN117853757A (en) | Obstacle tracking and tracking model training method, device, equipment and storage medium | |
| CN115600318A (en) | Steering decision model optimization method, steering decision method, device, equipment and medium | |
| CN116884215A (en) | Traffic state prediction and model generation methods, devices, equipment and media |
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 |