CN117912238A - Vehicle augmented situation awareness method and system - Google Patents
Vehicle augmented situation awareness method and system Download PDFInfo
- Publication number
- CN117912238A CN117912238A CN202311802896.0A CN202311802896A CN117912238A CN 117912238 A CN117912238 A CN 117912238A CN 202311802896 A CN202311802896 A CN 202311802896A CN 117912238 A CN117912238 A CN 117912238A
- Authority
- CN
- China
- Prior art keywords
- information
- augmented
- vehicle
- real
- amplified
- 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
- 230000003190 augmentative effect Effects 0.000 title claims abstract description 137
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000007726 management method Methods 0.000 claims abstract description 101
- 230000007175 bidirectional communication Effects 0.000 claims abstract description 31
- 230000005540 biological transmission Effects 0.000 claims abstract description 23
- 230000000306 recurrent effect Effects 0.000 claims description 55
- 238000005070 sampling Methods 0.000 claims description 52
- 230000006870 function Effects 0.000 claims description 44
- 230000006854 communication Effects 0.000 claims description 40
- 238000004891 communication Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 32
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000003062 neural network model Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 14
- 230000003416 augmentation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000002457 bidirectional effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 8
- 230000007787 long-term memory Effects 0.000 claims 1
- 230000006403 short-term memory Effects 0.000 claims 1
- 108091006146 Channels Proteins 0.000 description 69
- 210000004027 cell Anatomy 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 6
- 239000013598 vector Substances 0.000 description 6
- 239000000969 carrier Substances 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006386 memory function Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle augmented situation awareness method and a system, wherein the method comprises the following steps: establishing an augmented task based on a background management system; sending the redundancy information to a plurality of vehicle control systems based on the redundancy task, and determining a plurality of redundancy vehicles; planning a corresponding optimized augmented path by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented location; each of the amplified vehicles runs based on a corresponding optimized amplified path, and in the running process of the amplified vehicles, a vehicle control system of the amplified vehicles transmits real-time positioning information and real-time speed information to a background management system based on a bidirectional communication link channel; the background management system utilizes real-time traffic prediction information to perform augmented situation awareness based on the real-time positioning information and the real-time speed information. The invention not only improves the timeliness of information transmission in the augmented situation awareness, but also ensures that the reliability of the augmented situation awareness can be maintained under various traffic conditions.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a vehicle augmented situation awareness method and system.
Background
For an augmented task, the situation awareness of a vehicle is a key technology, and aims to perceive the running situation of the augmented vehicle and track the situation of the augmented vehicle from a scene, the existing vehicle situation awareness technology integrates technologies such as a sensor and machine learning, and the like, the driving distance of the augmented vehicle can be acquired according to the acquired vehicle driving information, and the situation awareness of the vehicle is carried out through the driving distance.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a vehicle augmented situation sensing method and a system, which not only improve the timeliness of information transmission in the augmented situation sensing, but also ensure that the reliability of the augmented situation sensing can be maintained under various traffic conditions.
In order to solve the technical problems, the invention provides a vehicle augmented situation awareness method, which comprises the following steps:
Establishing an augmented task based on a background management system;
Transmitting the redundancy information to a vehicle control system of a plurality of vehicles based on the redundancy task, and determining a plurality of redundancy vehicles based on the redundancy information;
planning an optimized augmented path corresponding to each augmented vehicle by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented place;
Each of the amplified vehicles runs based on a corresponding optimized amplified path, and in the running process of the amplified vehicles, a vehicle control system of the amplified vehicles transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel;
The background management system utilizes real-time traffic prediction information to conduct augmented situation awareness based on the real-time positioning information and the real-time speed information, the real-time traffic prediction information is information obtained by performing prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recurrent neural network model for training.
Optionally, the establishing an augmentation task based on the background management system includes:
The background management system receives an enhancement request sent by personnel at an enhancement site, wherein the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of the enhancement vehicles, and an enhancement task is established based on the enhancement request.
Optionally, the sending the augmentation information to the vehicle control system of the plurality of vehicles based on the augmentation task, determining the plurality of augmentation vehicles based on the augmentation information, includes:
After each vehicle control system receives the augmented information, the vehicle control system sends the corresponding duty state to the background management system;
The background management system acquires idle vehicle information based on the duty state of each vehicle, and determines a plurality of spare vehicles based on the number of spare vehicles and the types of spare vehicles in the spare vehicles.
Optionally, the planning, by using a trajectory planning algorithm, the optimized augmented path corresponding to each augmented vehicle based on the current location information of each augmented vehicle and the location information of the augmented location includes:
establishing a state sampling space based on the current position information of each of the augmented vehicles and the position information of the augmented places;
space-time grid sampling processing is carried out based on the state sampling space, and a plurality of track points are obtained;
generating a plurality of initial augmented paths based on the plurality of track points, the current position information of the augmented vehicle and the position information of the augmented location;
And evaluating a plurality of initial amplified paths based on the track evaluation function to obtain the evaluation weight corresponding to each initial amplified path, and selecting the path with the largest evaluation weight as the optimized amplified path corresponding to each amplified vehicle.
Optionally, the performing space-time grid sampling processing based on the state sampling space to obtain a plurality of track points includes:
Constructing a first coordinate system based on the current position information of the state sampling space to the augmented vehicle, and constructing a second coordinate system based on the position information of the state sampling space to the augmented place;
equidistant sampling is carried out based on the first coordinate system, and a plurality of grid points are obtained;
And carrying out equidistant sampling processing by utilizing a plurality of grid points based on the second coordinate system to obtain a plurality of track points.
Optionally, the vehicle control system of the augmented vehicle transmits the real-time positioning information and the real-time speed information to the background management system based on a bidirectional communication link channel, and the method comprises the following steps:
the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol;
The vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, and the background management system updates the running information of the augmented vehicle based on the real-time positioning information and the real-time speed information.
Optionally, the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol, including:
the vehicle control system establishes a forward WebScoket communication link with the background management system based on a TCP protocol;
establishing a forward link channel using a Walsh function based on the forward WebScoket communication link;
The background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol;
establishing a reverse link channel using a Walsh function based on the reverse WebScoket communication link;
A bi-directional communication link channel is established based on the forward link channel and the reverse link channel.
Optionally, the deep recurrent neural network model comprises a plurality of recurrent neurons, each recurrent neuron comprises an input layer, a plurality of recurrent layers and an input layer, and the recurrent layers comprise an embedded layer, a bidirectional long-short-time memory network layer, a recurrent unit layer, a flat layer and a full-connection layer.
Optionally, the background management system performs augmented situation awareness by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information, and includes:
continuously measuring and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information;
When the amplified vehicle arrives at the amplified site, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on the start tag icon is received, and the amplified start event is sent to a background management system.
In addition, the invention also provides a vehicle augmented situation awareness system, which comprises:
the task building module is used for building an augmented task based on the background management system;
The vehicle-to-be-amplified determining module is used for sending the to-be-amplified information to the vehicle control systems of the vehicles based on the to-be-amplified tasks and determining the vehicles based on the to-be-amplified information;
The system comprises an amplifying path planning module, a power supply module and a power supply module, wherein the amplifying path planning module is used for planning an optimized amplifying path corresponding to each amplifying vehicle by utilizing a track planning algorithm based on the current position information of each amplifying vehicle and the position information of an amplifying place;
the information transmission module is used for each amplified vehicle to travel based on the corresponding optimized amplified path, and in the process of the amplified vehicle traveling, the vehicle control system of the amplified vehicle transmits real-time positioning information and real-time speed information to the background management system based on the bidirectional communication link channel;
The back-end management system is used for carrying out back-end situation sensing by utilizing real-time traffic prediction information based on the real-time positioning information and the real-time speed information, wherein the real-time traffic prediction information is information obtained by carrying out prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recursion neural network model for training.
In the embodiment of the invention, the optimized and enhanced path corresponding to each enhanced vehicle is accurately and rapidly planned by utilizing a track planning algorithm according to the current position information of each enhanced vehicle and the position information of the enhanced place, the optimized and enhanced path can be driven in shorter time and better path, in the driving process of the enhanced vehicle, related driving information is transmitted through a bidirectional communication link channel, the delay of information transmission can be effectively reduced through the bidirectional communication link channel, meanwhile, the safety and reliability of information transmission can be improved, the real-time traffic prediction information obtained by the prediction processing of a traffic prediction model is introduced in the enhancement situation awareness, the traffic road condition information at the moment is predicted, the accuracy of the enhancement situation awareness can be further improved by combining the real-time traffic prediction information, and the situation awareness reliability can be maintained even if complex traffic conditions are met.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a vehicle augmented situation awareness method in an embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a vehicle augmented situation awareness system according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a vehicle augmented situation awareness method according to an embodiment of the invention.
As shown in fig. 1, a vehicle augmented situation awareness method includes:
s11: establishing an augmented task based on a background management system;
in the implementation process of the invention, the background management system-based building of the rescue task comprises the following steps: the background management system receives an enhancement request sent by personnel at an enhancement site, wherein the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of the enhancement vehicles, and an enhancement task is established based on the enhancement request.
Specifically, the background management system receives an enhancement request sent by personnel at an enhancement site, the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of enhancement vehicles, and all information contained in the enhancement request is input into a construction list of enhancement tasks to establish corresponding enhancement tasks.
S12: transmitting the redundancy information to a vehicle control system of a plurality of vehicles based on the redundancy task, and determining a plurality of redundancy vehicles based on the redundancy information;
In the implementation process of the invention, the method for transmitting the amplified information to the vehicle control systems of the vehicles based on the amplified tasks, and determining the amplified vehicles based on the amplified information comprises the following steps: after each vehicle control system receives the augmented information, the vehicle control system sends the corresponding duty state to the background management system; the background management system acquires idle vehicle information based on the duty state of each vehicle, and determines a plurality of spare vehicles based on the number of spare vehicles and the types of spare vehicles in the spare vehicles.
Specifically, according to the rescue task, rescue information is sent to a vehicle control system of each vehicle, and after the vehicle control system receives the rescue information, the corresponding duty state is sent to a background management system; the background management system can know specific idle vehicles according to the duty state of each vehicle, acquire idle vehicle information, and determine a plurality of needed amplified vehicles from the idle vehicles according to the type and the number of the amplified vehicles in the amplified information, so that the needed amplified vehicles can be accurately arranged.
S13: planning an optimized augmented path corresponding to each augmented vehicle by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented place;
In the implementation process of the invention, the method for planning the optimized augmented path corresponding to each augmented vehicle by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented place comprises the following steps: establishing a state sampling space based on the current position information of each of the augmented vehicles and the position information of the augmented places; space-time grid sampling processing is carried out based on the state sampling space, and a plurality of track points are obtained; generating a plurality of initial augmented paths based on the plurality of track points, the current position information of the augmented vehicle and the position information of the augmented location; and evaluating a plurality of initial amplified paths based on the track evaluation function to obtain the evaluation weight corresponding to each initial amplified path, and selecting the path with the largest evaluation weight as the optimized amplified path corresponding to each amplified vehicle.
Further, the performing space-time grid sampling processing based on the state sampling space to obtain a plurality of track points includes: constructing a first coordinate system based on the current position information of the state sampling space to the augmented vehicle, and constructing a second coordinate system based on the position information of the state sampling space to the augmented place; equidistant sampling is carried out based on the first coordinate system, and a plurality of grid points are obtained; and carrying out equidistant sampling processing by utilizing a plurality of grid points based on the second coordinate system to obtain a plurality of track points.
Specifically, a state sampling space is established based on the current position information of each of the vehicles and the position information of the place of the augmentation, wherein the state sampling space is defined as a two-dimensional plane space formed by an x axis and a y axis of the vehicle, the current position information of the vehicle is used as a starting point, and the position information of the place of the augmentation is used as an end point; constructing a first coordinate system according to the starting point, constructing a second coordinate system according to the ending point, and respectively constructing coordinate systems between the track starting point and the track for the subsequent sampling processing, wherein the coordinate axes of the two coordinate systems have the same direction; equidistant sampling is carried out according to the first coordinate system and the second coordinate system, equidistant sampling is carried out along the transverse axis and the longitudinal axis of the first coordinate system, a plurality of grid points are obtained, equidistant sampling is carried out according to the lateral range of each grid point along the normal direction of the grid points, and a plurality of grid points are obtained; equidistant sampling is carried out along the transverse axis and the longitudinal axis of the second coordinate system to obtain a plurality of mileage points, equidistant sampling is carried out according to the lateral range of each mileage point along the normal direction of the mileage points, and the state vectors of the obtained grid points are combined to obtain a plurality of track points; connecting lines are carried out according to the current position information of the amplified vehicle, the track points and the position information of the amplified points, and a plurality of initial amplified paths are generated; the method comprises the steps of evaluating a plurality of initial amplified paths based on a track evaluation function, constructing a judgment matrix for the plurality of initial amplified paths according to an hierarchical structure, calculating the relative weight of each initial amplified path according to the judgment matrix by using a preset judgment criterion, sequencing the initial amplified paths according to the relative weight from high to low, calculating the comprehensive evaluation degree of each initial amplified path relative to the whole according to the sequencing order, calculating the relative weight and the comprehensive evaluation degree to obtain the evaluation weight corresponding to each track, comparing the plurality of initial amplified paths according to the evaluation weight, selecting the track with the largest evaluation weight as an optimized amplified path, accurately and rapidly planning the optimized amplified path corresponding to each amplified vehicle by using a track planning algorithm, finding a safer and more effective path in a more complex environment, and enabling the amplified vehicle to run in a shorter time and a better path at the current position and the target amplified point.
S14: each of the amplified vehicles runs based on a corresponding optimized amplified path, and in the running process of the amplified vehicles, a vehicle control system of the amplified vehicles transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel;
In the implementation process of the invention, the vehicle control system of the augmented vehicle transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel, and the method comprises the following steps: the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol; the vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, and the background management system updates the running information of the augmented vehicle based on the real-time positioning information and the real-time speed information.
Further, the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol, and the method includes: the vehicle control system establishes a forward WebScoket communication link with the background management system based on a TCP protocol; establishing a forward link channel using a Walsh function based on the forward WebScoket communication link; the background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol; establishing a reverse link channel using a Walsh function based on the reverse WebScoket communication link; a bi-directional communication link channel is established based on the forward link channel and the reverse link channel.
Specifically, the vehicle control system establishes a forward WebScoket communication link with the background management system based on a transmission control protocol (Transmission Control Protocol, TCP), wherein the TCP is a connection-oriented, reliable and byte stream-based transport layer protocol, the establishment of the communication link through the TCP can ensure that transmission data can be timely transmitted to a target system and can accommodate more information, the vehicle control system sends a WebScoket request message to the background management system, the WebScoket request message contains a domain name of the vehicle control system, the background management system analyzes a root domain part of the request message according to the domain name after receiving the request message, and returns root domain name information in the analyzed root domain part to the vehicle control system to establish the forward WebScoket communication link; based on the forward WebScoket communication link, a forward link channel is established by utilizing a Walsh function, the Walsh function is a function for dividing the channel, the channel divided by the Walsh function can enhance the anti-interference performance and improve the transmission efficiency, the sequence channel is divided by the Walsh function, the quadrature modulation is carried out on the sequence channel, and the information is encoded on sine and cosine carriers, so that a forward link channel of related logic is established; the background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol, the background management system sends WebScoket request message to the vehicle control system, webScoket request message contains the domain name of the background management system, the vehicle control system analyzes the root domain part of the request message according to the domain name after receiving the request message, and returns the root domain name information in the analyzed root domain part to the background system to establish a reverse WebScoket communication link; establishing a backward link channel by utilizing a Walsh function based on the reverse WebScoket communication link, dividing a sequence channel by the Walsh function, modulating the sequence channel, and encoding information onto sine and cosine carriers, thereby establishing a backward link channel of related logic; establishing a bi-directional communication link channel based on the forward link channel and the reverse link channel; the vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, the background management system updates the driving information of the augmented vehicle based on the real-time positioning information and the real-time speed information, the two-way communication link channel can timely transmit the related positioning information and the related speed information, the situation that the augmented situation cannot be timely perceived is avoided, the information transmission delay can be effectively reduced through the two-way communication link channel, and meanwhile, the safety and the reliability of the information transmission can be improved.
S15: the background management system utilizes real-time traffic prediction information to conduct augmented situation awareness based on the real-time positioning information and the real-time speed information, the real-time traffic prediction information is information obtained by performing prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recurrent neural network model for training.
In the implementation process of the invention, the deep recurrent neural network model comprises a plurality of recurrent neurons, each recurrent neuron comprises an input layer, a plurality of recurrent layers and an input layer, and the recurrent layers comprise a bidirectional long-short-time memory network layer, a recurrent unit layer, a flat layer and a full-connection layer.
Further, the background management system performs augmented situation awareness by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information, and includes: continuously measuring and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information; when the amplified vehicle arrives at the amplified site, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on the start tag icon is received, and the amplified start event is sent to a background management system.
Specifically, a deep recurrent neural network model is constructed as an initial traffic prediction model, the deep recurrent neural network model comprises a plurality of recurrent neurons, each recurrent neuron is a core building block of the deep recurrent neural network, each recurrent neuron comprises an input layer, a plurality of recurrent layers and an input layer, the input layer is responsible for inputting data, the recurrent layers are used for carrying out prediction processing on the input data, the input layer outputs a prediction result, the recurrent layers comprise an embedded layer, a bidirectional long and short time memory network layer, a recurrent unit layer, a flat layer and a full connection layer, the embedded layer is used for converting texts into numerical vectors and converting road section traffic flow information into embedded vectors, the bidirectional long and short time memory network layer is a variant of the deep recurrent neural network, the deep recurrent neural network shares network weights, the output of the current step of the deep recurrent neural network is not only dependent on the input of the current step, also depending on the output of the previous step, a two-way long and short memory network layer is designed, which comprises an input gate, a forgetting gate, an output gate and a cell state, the cell state providing the memory function of the model, the network information of the front and rear layers can still be transferred when the model structure is deepened, the input gate decides which new information is added to the cell state, i.e. updates the cell state, the current input is transferred to an activation function, the updated information is decided by the activation function, the importance of the updated information is evaluated, the unimportant information is removed, the current input is simultaneously transferred to a tanh function for processing, the tanh function is a hyperbolic tangent function for adjusting the model, and the updating of the cell state is decided by combining the processing value of the tanh function and the output of the activation function, the method comprises the steps that a forgetting gate determines which information is needed to be discarded in a cell state, after the forgetting gate splices input information from the current moment and input information from the last moment, weighting calculation processing is carried out on spliced information, whether the information needs to be reserved or not is judged according to a weighting calculation result, an output gate determines output state characteristics, output judging conditions can be obtained through the output gate, reserved data information can be used for obtaining output information of a network layer through a tanh function according to the judging conditions, a two-way long-short-time memory network layer is used for outputting the reserved data information, the circulation unit layer comprises a reset gate and an update gate, the reset gate is used for further removing unnecessary past information, the update gate is used for further deleting the information needed to be discarded and adding new information, the flat layer is a connecting bridge of the circulation unit layer and the full-connection layer, input of the circulation unit layer is connected to the subsequent full-connection layer, and the full-connection layer maps processed data of the previous layers to a final prediction result; inputting the road section traffic flow data set into a deep recurrent neural network model for training to obtain a trained traffic prediction model, and predicting real-time traffic based on the trained traffic prediction model to obtain real-time traffic prediction information; continuously calculating and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information, calculating the distance from the augmented place according to the real-time positioning information, calculating the preliminary time by using the real-time speed information according to the calculated distance, and judging the change of speed and time by combining the real-time traffic prediction information to obtain the estimated arrival time; when an amplified vehicle arrives at an amplified place, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on a start tag icon is received, the amplified start event is sent to a background management system, similarly, when an amplified task is finished, an amplified end event is triggered according to an end icon, and the amplified end event is sent to the background management system, so that the background management system can learn about specific conditions, real-time traffic prediction information obtained by prediction processing by using a traffic prediction model is introduced in the amplified situation sensing, the traffic condition information at the moment is predicted, the accuracy of the amplified situation sensing can be further improved by combining the real-time traffic prediction information, and the reliability of situation sensing can be maintained even if complex traffic conditions are met.
In the embodiment of the invention, the optimized and enhanced path corresponding to each enhanced vehicle is accurately and rapidly planned by utilizing a track planning algorithm according to the current position information of each enhanced vehicle and the position information of the enhanced place, the optimized and enhanced path can be driven in shorter time and better path, in the driving process of the enhanced vehicle, related driving information is transmitted through a bidirectional communication link channel, the delay of information transmission can be effectively reduced through the bidirectional communication link channel, meanwhile, the safety and reliability of information transmission can be improved, the real-time traffic prediction information obtained by the prediction processing of a traffic prediction model is introduced in the enhancement situation awareness, the traffic road condition information at the moment is predicted, the accuracy of the enhancement situation awareness can be further improved by combining the real-time traffic prediction information, and the situation awareness reliability can be maintained even if complex traffic conditions are met.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a vehicle augmented situation awareness system according to an embodiment of the invention.
As shown in fig. 2, a vehicle augmented situation awareness system, the system comprising:
task creation module 21: the method is used for establishing an augmented task based on a background management system;
in the implementation process of the invention, the background management system-based building of the rescue task comprises the following steps: the background management system receives an enhancement request sent by personnel at an enhancement site, wherein the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of the enhancement vehicles, and an enhancement task is established based on the enhancement request.
Specifically, the background management system receives an enhancement request sent by personnel at an enhancement site, the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of enhancement vehicles, and all information contained in the enhancement request is input into a construction list of enhancement tasks to establish corresponding enhancement tasks.
The redundant vehicle determination module 22: the vehicle control system is used for sending the redundancy information to the vehicle control systems of the vehicles based on the redundancy tasks, and determining the vehicles based on the redundancy information;
In the implementation process of the invention, the method for transmitting the amplified information to the vehicle control systems of the vehicles based on the amplified tasks, and determining the amplified vehicles based on the amplified information comprises the following steps: after each vehicle control system receives the augmented information, the vehicle control system sends the corresponding duty state to the background management system; the background management system acquires idle vehicle information based on the duty state of each vehicle, and determines a plurality of spare vehicles based on the number of spare vehicles and the types of spare vehicles in the spare vehicles.
Specifically, according to the rescue task, rescue information is sent to a vehicle control system of each vehicle, and after the vehicle control system receives the rescue information, the corresponding duty state is sent to a background management system; the background management system can know specific idle vehicles according to the duty state of each vehicle, acquire idle vehicle information, and determine a plurality of needed amplified vehicles from the idle vehicles according to the type and the number of the amplified vehicles in the amplified information, so that the needed amplified vehicles can be accurately arranged.
The redundant path planning module 23: the method comprises the steps of using a track planning algorithm to plan an optimized augmented path corresponding to each augmented vehicle based on current position information of each augmented vehicle and position information of an augmented place;
In the implementation process of the invention, the method for planning the optimized augmented path corresponding to each augmented vehicle by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented place comprises the following steps: establishing a state sampling space based on the current position information of each of the augmented vehicles and the position information of the augmented places; space-time grid sampling processing is carried out based on the state sampling space, and a plurality of track points are obtained; generating a plurality of initial augmented paths based on the plurality of track points, the current position information of the augmented vehicle and the position information of the augmented location; and evaluating a plurality of initial amplified paths based on the track evaluation function to obtain the evaluation weight corresponding to each initial amplified path, and selecting the path with the largest evaluation weight as the optimized amplified path corresponding to each amplified vehicle.
Further, the performing space-time grid sampling processing based on the state sampling space to obtain a plurality of track points includes: constructing a first coordinate system based on the current position information of the state sampling space to the augmented vehicle, and constructing a second coordinate system based on the position information of the state sampling space to the augmented place; equidistant sampling is carried out based on the first coordinate system, and a plurality of grid points are obtained; and carrying out equidistant sampling processing by utilizing a plurality of grid points based on the second coordinate system to obtain a plurality of track points.
Specifically, a state sampling space is established based on the current position information of each of the vehicles and the position information of the place of the augmentation, wherein the state sampling space is defined as a two-dimensional plane space formed by an x axis and a y axis of the vehicle, the current position information of the vehicle is used as a starting point, and the position information of the place of the augmentation is used as an end point; constructing a first coordinate system according to the starting point, constructing a second coordinate system according to the ending point, and respectively constructing coordinate systems between the track starting point and the track for the subsequent sampling processing, wherein the coordinate axes of the two coordinate systems have the same direction; equidistant sampling is carried out according to the first coordinate system and the second coordinate system, equidistant sampling is carried out along the transverse axis and the longitudinal axis of the first coordinate system, a plurality of grid points are obtained, equidistant sampling is carried out according to the lateral range of each grid point along the normal direction of the grid points, and a plurality of grid points are obtained; equidistant sampling is carried out along the transverse axis and the longitudinal axis of the second coordinate system to obtain a plurality of mileage points, equidistant sampling is carried out according to the lateral range of each mileage point along the normal direction of the mileage points, and the state vectors of the obtained grid points are combined to obtain a plurality of track points; connecting lines are carried out according to the current position information of the amplified vehicle, the track points and the position information of the amplified points, and a plurality of initial amplified paths are generated; the method comprises the steps of evaluating a plurality of initial amplified paths based on a track evaluation function, constructing a judgment matrix for the plurality of initial amplified paths according to an hierarchical structure, calculating the relative weight of each initial amplified path according to the judgment matrix by using a preset judgment criterion, sequencing the initial amplified paths according to the relative weight from high to low, calculating the comprehensive evaluation degree of each initial amplified path relative to the whole according to the sequencing order, calculating the relative weight and the comprehensive evaluation degree to obtain the evaluation weight corresponding to each track, comparing the plurality of initial amplified paths according to the evaluation weight, selecting the track with the largest evaluation weight as an optimized amplified path, accurately and rapidly planning the optimized amplified path corresponding to each amplified vehicle by using a track planning algorithm, finding a safer and more effective path in a more complex environment, and enabling the amplified vehicle to run in a shorter time and a better path at the current position and the target amplified point.
Information transmission module 24: the vehicle control system of the enhanced vehicle transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel in the running process of the enhanced vehicle;
In the implementation process of the invention, the vehicle control system of the augmented vehicle transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel, and the method comprises the following steps: the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol; the vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, and the background management system updates the running information of the augmented vehicle based on the real-time positioning information and the real-time speed information.
Further, the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol, and the method includes: the vehicle control system establishes a forward WebScoket communication link with the background management system based on a TCP protocol; establishing a forward link channel using a Walsh function based on the forward WebScoket communication link; the background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol; establishing a reverse link channel using a Walsh function based on the reverse WebScoket communication link; a bi-directional communication link channel is established based on the forward link channel and the reverse link channel.
Specifically, the vehicle control system establishes a forward WebScoket communication link with the background management system based on a transmission control protocol (Transmission Control Protocol, TCP), wherein the TCP is a connection-oriented, reliable and byte stream-based transport layer protocol, the establishment of the communication link through the TCP can ensure that transmission data can be timely transmitted to a target system and can accommodate more information, the vehicle control system sends a WebScoket request message to the background management system, the WebScoket request message contains a domain name of the vehicle control system, the background management system analyzes a root domain part of the request message according to the domain name after receiving the request message, and returns root domain name information in the analyzed root domain part to the vehicle control system to establish the forward WebScoket communication link; based on the forward WebScoket communication link, a forward link channel is established by utilizing a Walsh function, the Walsh function is a function for dividing the channel, the channel divided by the Walsh function can enhance the anti-interference performance and improve the transmission efficiency, the sequence channel is divided by the Walsh function, the quadrature modulation is carried out on the sequence channel, and the information is encoded on sine and cosine carriers, so that a forward link channel of related logic is established; the background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol, the background management system sends WebScoket request message to the vehicle control system, webScoket request message contains the domain name of the background management system, the vehicle control system analyzes the root domain part of the request message according to the domain name after receiving the request message, and returns the root domain name information in the analyzed root domain part to the background system to establish a reverse WebScoket communication link; establishing a backward link channel by utilizing a Walsh function based on the reverse WebScoket communication link, dividing a sequence channel by the Walsh function, modulating the sequence channel, and encoding information onto sine and cosine carriers, thereby establishing a backward link channel of related logic; establishing a bi-directional communication link channel based on the forward link channel and the reverse link channel; the vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, the background management system updates the driving information of the augmented vehicle based on the real-time positioning information and the real-time speed information, the two-way communication link channel can timely transmit the related positioning information and the related speed information, the situation that the augmented situation cannot be timely perceived is avoided, the information transmission delay can be effectively reduced through the two-way communication link channel, and meanwhile, the safety and the reliability of the information transmission can be improved.
The augmented situation awareness module 25: the background management system is used for performing augmented situation awareness by utilizing real-time traffic prediction information based on the real-time positioning information and the real-time speed information, the real-time traffic prediction information is information obtained by performing prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recursion neural network model for training.
In the implementation process of the invention, the deep recurrent neural network model comprises a plurality of recurrent neurons, each recurrent neuron comprises an input layer, a plurality of recurrent layers and an input layer, and the recurrent layers comprise a bidirectional long-short-time memory network layer, a recurrent unit layer, a flat layer and a full-connection layer.
Further, the background management system performs augmented situation awareness by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information, and includes: continuously measuring and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information; when the amplified vehicle arrives at the amplified site, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on the start tag icon is received, and the amplified start event is sent to a background management system.
Specifically, a deep recurrent neural network model is constructed as an initial traffic prediction model, the deep recurrent neural network model comprises a plurality of recurrent neurons, each recurrent neuron is a core building block of the deep recurrent neural network, each recurrent neuron comprises an input layer, a plurality of recurrent layers and an input layer, the input layer is responsible for inputting data, the recurrent layers are used for carrying out prediction processing on the input data, the input layer outputs a prediction result, the recurrent layers comprise an embedded layer, a bidirectional long and short time memory network layer, a recurrent unit layer, a flat layer and a full connection layer, the embedded layer is used for converting texts into numerical vectors and converting road section traffic flow information into embedded vectors, the bidirectional long and short time memory network layer is a variant of the deep recurrent neural network, the deep recurrent neural network shares network weights, the output of the current step of the deep recurrent neural network is not only dependent on the input of the current step, also depending on the output of the previous step, a two-way long and short memory network layer is designed, which comprises an input gate, a forgetting gate, an output gate and a cell state, the cell state providing the memory function of the model, the network information of the front and rear layers can still be transferred when the model structure is deepened, the input gate decides which new information is added to the cell state, i.e. updates the cell state, the current input is transferred to an activation function, the updated information is decided by the activation function, the importance of the updated information is evaluated, the unimportant information is removed, the current input is simultaneously transferred to a tanh function for processing, the tanh function is a hyperbolic tangent function for adjusting the model, and the updating of the cell state is decided by combining the processing value of the tanh function and the output of the activation function, the method comprises the steps that a forgetting gate determines which information is needed to be discarded in a cell state, after the forgetting gate splices input information from the current moment and input information from the last moment, weighting calculation processing is carried out on spliced information, whether the information needs to be reserved or not is judged according to a weighting calculation result, an output gate determines output state characteristics, output judging conditions can be obtained through the output gate, reserved data information can be used for obtaining output information of a network layer through a tanh function according to the judging conditions, a two-way long-short-time memory network layer is used for outputting the reserved data information, the circulation unit layer comprises a reset gate and an update gate, the reset gate is used for further removing unnecessary past information, the update gate is used for further deleting the information needed to be discarded and adding new information, the flat layer is a connecting bridge of the circulation unit layer and the full-connection layer, input of the circulation unit layer is connected to the subsequent full-connection layer, and the full-connection layer maps processed data of the previous layers to a final prediction result; inputting the road section traffic flow data set into a deep recurrent neural network model for training to obtain a trained traffic prediction model, and predicting real-time traffic based on the trained traffic prediction model to obtain real-time traffic prediction information; continuously calculating and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information, calculating the distance from the augmented place according to the real-time positioning information, calculating the preliminary time by using the real-time speed information according to the calculated distance, and judging the change of speed and time by combining the real-time traffic prediction information to obtain the estimated arrival time; when an amplified vehicle arrives at an amplified place, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on a start tag icon is received, the amplified start event is sent to a background management system, similarly, when an amplified task is finished, an amplified end event is triggered according to an end icon, and the amplified end event is sent to the background management system, so that the background management system can learn about specific conditions, real-time traffic prediction information obtained by prediction processing by using a traffic prediction model is introduced in the amplified situation sensing, the traffic condition information at the moment is predicted, the accuracy of the amplified situation sensing can be further improved by combining the real-time traffic prediction information, and the reliability of situation sensing can be maintained even if complex traffic conditions are met.
In the embodiment of the invention, the optimized and enhanced path corresponding to each enhanced vehicle is accurately and rapidly planned by utilizing a track planning algorithm according to the current position information of each enhanced vehicle and the position information of the enhanced place, the optimized and enhanced path can be driven in shorter time and better path, in the driving process of the enhanced vehicle, related driving information is transmitted through a bidirectional communication link channel, the delay of information transmission can be effectively reduced through the bidirectional communication link channel, meanwhile, the safety and reliability of information transmission can be improved, the real-time traffic prediction information obtained by the prediction processing of a traffic prediction model is introduced in the enhancement situation awareness, the traffic road condition information at the moment is predicted, the accuracy of the enhancement situation awareness can be further improved by combining the real-time traffic prediction information, and the situation awareness reliability can be maintained even if complex traffic conditions are met.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access memory (RAM, random Access Memory), magnetic or optical disk, and the like.
In addition, the foregoing describes in detail a vehicle augmented situation awareness method and system provided by the embodiments of the present invention, and specific examples should be adopted herein to illustrate the principles and embodiments of the present invention, where the foregoing examples are only for helping to understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method for vehicle augmented situation awareness, the method comprising:
Establishing an augmented task based on a background management system;
Transmitting the redundancy information to a vehicle control system of a plurality of vehicles based on the redundancy task, and determining a plurality of redundancy vehicles based on the redundancy information;
planning an optimized augmented path corresponding to each augmented vehicle by using a track planning algorithm based on the current position information of each augmented vehicle and the position information of the augmented place;
Each of the amplified vehicles runs based on a corresponding optimized amplified path, and in the running process of the amplified vehicles, a vehicle control system of the amplified vehicles transmits real-time positioning information and real-time speed information to the background management system based on a bidirectional communication link channel;
The background management system utilizes real-time traffic prediction information to conduct augmented situation awareness based on the real-time positioning information and the real-time speed information, the real-time traffic prediction information is information obtained by performing prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recurrent neural network model for training.
2. The vehicle augmented situation awareness method according to claim 1, wherein the background-based management system establishes an augmented task comprising:
The background management system receives an enhancement request sent by personnel at an enhancement site, wherein the enhancement request comprises position information of the enhancement site, the number of enhancement vehicles and the types of the enhancement vehicles, and an enhancement task is established based on the enhancement request.
3. The vehicle situation awareness method according to claim 1, wherein the sending of the augmentation information to the vehicle control systems of the plurality of vehicles based on the augmentation task, determining the plurality of augmented vehicles based on the augmentation information, comprises:
After each vehicle control system receives the augmented information, the vehicle control system sends the corresponding duty state to the background management system;
The background management system acquires idle vehicle information based on the duty state of each vehicle, and determines a plurality of spare vehicles based on the number of spare vehicles and the types of spare vehicles in the spare vehicles.
4. The vehicle augmented situation awareness method according to claim 1, wherein the planning the optimized augmented path corresponding to each augmented vehicle using a trajectory planning algorithm based on the current location information of each augmented vehicle and the location information of the augmented location comprises:
establishing a state sampling space based on the current position information of each of the augmented vehicles and the position information of the augmented places;
space-time grid sampling processing is carried out based on the state sampling space, and a plurality of track points are obtained;
generating a plurality of initial augmented paths based on the plurality of track points, the current position information of the augmented vehicle and the position information of the augmented location;
And evaluating a plurality of initial amplified paths based on the track evaluation function to obtain the evaluation weight corresponding to each initial amplified path, and selecting the path with the largest evaluation weight as the optimized amplified path corresponding to each amplified vehicle.
5. The vehicle augmented situation awareness method according to claim 4, wherein the performing space-time grid sampling based on the state sampling space to obtain a plurality of track points includes:
Constructing a first coordinate system based on the current position information of the state sampling space to the augmented vehicle, and constructing a second coordinate system based on the position information of the state sampling space to the augmented place;
equidistant sampling is carried out based on the first coordinate system, and a plurality of grid points are obtained;
And carrying out equidistant sampling processing by utilizing a plurality of grid points based on the second coordinate system to obtain a plurality of track points.
6. The vehicle augmented situation awareness method according to claim 1, wherein the vehicle control system of the augmented vehicle transmits real-time positioning information and real-time speed information to the background management system based on a bi-directional communication link channel, comprising:
the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol;
The vehicle control system controls the positioning device and the data acquisition device to acquire real-time positioning information and real-time speed information, and transmits the real-time positioning information and the real-time speed information to the background management system based on the two-way communication link channel, and the background management system updates the running information of the augmented vehicle based on the real-time positioning information and the real-time speed information.
7. The vehicle augmented situation awareness method according to claim 6, wherein the vehicle control system and the background management system establish a bidirectional communication link channel based on a TCP protocol, comprising:
the vehicle control system establishes a forward WebScoket communication link with the background management system based on a TCP protocol;
establishing a forward link channel using a Walsh function based on the forward WebScoket communication link;
The background management system establishes a reverse WebScoket communication link with the vehicle control system based on a TCP protocol;
establishing a reverse link channel using a Walsh function based on the reverse WebScoket communication link;
A bi-directional communication link channel is established based on the forward link channel and the reverse link channel.
8. The vehicle augmented situation awareness method of claim 1, wherein the deep recurrent neural network model comprises a number of recurrent neurons, each recurrent neuron comprising an input layer, a number of recurrent layers, and an input layer, the recurrent layers comprising an embedded layer, a bidirectional long and short term memory network layer, a recurrent unit layer, a flat layer, and a fully connected layer.
9. The vehicle augmented situation awareness method according to claim 1, wherein the background management system performs augmented situation awareness using real-time traffic prediction information based on the real-time positioning information and real-time speed information, comprising:
continuously measuring and updating the estimated arrival time of each augmented vehicle by using real-time traffic prediction information based on the real-time positioning information and the real-time speed information;
When the amplified vehicle arrives at the amplified site, the calculation and updating of the estimated arrival time of the amplified vehicle are stopped, an amplified start event triggered based on the start tag icon is received, and the amplified start event is sent to a background management system.
10. A vehicle augmented situation awareness system, the system comprising:
the task building module is used for building an augmented task based on the background management system;
The vehicle-to-be-amplified determining module is used for sending the to-be-amplified information to the vehicle control systems of the vehicles based on the to-be-amplified tasks and determining the vehicles based on the to-be-amplified information;
The system comprises an amplifying path planning module, a power supply module and a power supply module, wherein the amplifying path planning module is used for planning an optimized amplifying path corresponding to each amplifying vehicle by utilizing a track planning algorithm based on the current position information of each amplifying vehicle and the position information of an amplifying place;
the information transmission module is used for each amplified vehicle to travel based on the corresponding optimized amplified path, and in the process of the amplified vehicle traveling, the vehicle control system of the amplified vehicle transmits real-time positioning information and real-time speed information to the background management system based on the bidirectional communication link channel;
The back-end management system is used for carrying out back-end situation sensing by utilizing real-time traffic prediction information based on the real-time positioning information and the real-time speed information, wherein the real-time traffic prediction information is information obtained by carrying out prediction processing based on a traffic prediction model, and the traffic prediction model is a convergence model obtained by inputting a road section traffic flow data set into a deep recursion neural network model for training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311802896.0A CN117912238A (en) | 2023-12-25 | 2023-12-25 | Vehicle augmented situation awareness method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311802896.0A CN117912238A (en) | 2023-12-25 | 2023-12-25 | Vehicle augmented situation awareness method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117912238A true CN117912238A (en) | 2024-04-19 |
Family
ID=90691284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311802896.0A Pending CN117912238A (en) | 2023-12-25 | 2023-12-25 | Vehicle augmented situation awareness method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117912238A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551234A (en) * | 2015-12-25 | 2016-05-04 | 天维尔信息科技股份有限公司 | Alarm condition rescue method and apparatus thereof |
| CN110119839A (en) * | 2019-04-24 | 2019-08-13 | 华南理工大学 | A kind of Urban Road Traffic Accidents emergency management and rescue paths planning method |
| CN112071060A (en) * | 2020-08-27 | 2020-12-11 | 华南理工大学 | Emergency rescue path planning method based on urban road network traffic environment change |
| CN112183862A (en) * | 2020-09-29 | 2021-01-05 | 长春理工大学 | Traffic flow prediction method and system for urban road network |
| CN116046008A (en) * | 2023-02-01 | 2023-05-02 | 深圳市唯特视科技有限公司 | Situation awareness-based route planning method, system and efficiency evaluation device |
| CN116798233A (en) * | 2023-08-25 | 2023-09-22 | 湖南天宇汽车制造有限公司 | Ambulance rapid passing guiding system |
| CN117095547A (en) * | 2023-07-31 | 2023-11-21 | 智慧互通科技股份有限公司 | Intelligent traffic early warning method and system based on multi-mode visual tracking |
-
2023
- 2023-12-25 CN CN202311802896.0A patent/CN117912238A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551234A (en) * | 2015-12-25 | 2016-05-04 | 天维尔信息科技股份有限公司 | Alarm condition rescue method and apparatus thereof |
| CN110119839A (en) * | 2019-04-24 | 2019-08-13 | 华南理工大学 | A kind of Urban Road Traffic Accidents emergency management and rescue paths planning method |
| CN112071060A (en) * | 2020-08-27 | 2020-12-11 | 华南理工大学 | Emergency rescue path planning method based on urban road network traffic environment change |
| CN112183862A (en) * | 2020-09-29 | 2021-01-05 | 长春理工大学 | Traffic flow prediction method and system for urban road network |
| CN116046008A (en) * | 2023-02-01 | 2023-05-02 | 深圳市唯特视科技有限公司 | Situation awareness-based route planning method, system and efficiency evaluation device |
| CN117095547A (en) * | 2023-07-31 | 2023-11-21 | 智慧互通科技股份有限公司 | Intelligent traffic early warning method and system based on multi-mode visual tracking |
| CN116798233A (en) * | 2023-08-25 | 2023-09-22 | 湖南天宇汽车制造有限公司 | Ambulance rapid passing guiding system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | The cognitive internet of vehicles for autonomous driving | |
| Yu et al. | Deep learning-based traffic safety solution for a mixture of autonomous and manual vehicles in a 5G-enabled intelligent transportation system | |
| CN110244701B (en) | Method and apparatus for reinforcement learning of autonomous vehicles based on automatically generated course sequences | |
| EP3759563B1 (en) | Centralized shared autonomous vehicle operational management | |
| RU2756439C1 (en) | Determination of localisation for operation of a vehicle | |
| CN111845754B (en) | Decision prediction method of automatic driving vehicle based on edge calculation and crowd-sourcing algorithm | |
| CN110796856A (en) | Vehicle lane change intention prediction method and training method of lane change intention prediction network | |
| US20080033630A1 (en) | System and method of predicting traffic speed based on speed of neighboring link | |
| CN109472884A (en) | Unmanned vehicle date storage method, device, equipment and storage medium | |
| US11874120B2 (en) | Shared autonomous vehicle operational management | |
| US10836405B2 (en) | Continual planning and metareasoning for controlling an autonomous vehicle | |
| CN108694841A (en) | A kind of intelligent vehicle passage crossroads traffic light method based on V2X technologies | |
| Fu et al. | Hybrid autonomous driving guidance strategy combining deep reinforcement learning and expert system | |
| US11899454B2 (en) | Objective-based reasoning in autonomous vehicle decision-making | |
| CN111806466B (en) | Intelligent driving system and working process thereof | |
| US20220297732A1 (en) | Train dispatching control method, platform, and system, intelligent carriage, and medium | |
| CN113159403A (en) | Method and device for predicting pedestrian track at intersection | |
| US11613269B2 (en) | Learning safety and human-centered constraints in autonomous vehicles | |
| CN117912238A (en) | Vehicle augmented situation awareness method and system | |
| CN116911480A (en) | Path prediction method and system based on trust sharing mechanism in Internet of vehicles scene | |
| CN114459495B (en) | Displacement information generation method, device and computer readable storage medium | |
| CN116972860A (en) | Yaw recognition method and device, electronic equipment and storage medium | |
| CN114895676A (en) | Method for realizing high-speed running of ground automatic driving vehicle based on space intelligent system | |
| US20230264578A1 (en) | Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system for new energy vehicle | |
| CN112783133B (en) | AGV running state prediction method |
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 |