CN116901981A - Online self-learning Markov vehicle speed prediction method - Google Patents

Online self-learning Markov vehicle speed prediction method Download PDF

Info

Publication number
CN116901981A
CN116901981A CN202311107609.4A CN202311107609A CN116901981A CN 116901981 A CN116901981 A CN 116901981A CN 202311107609 A CN202311107609 A CN 202311107609A CN 116901981 A CN116901981 A CN 116901981A
Authority
CN
China
Prior art keywords
acceleration
matrix
state transition
prediction
speed
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
Application number
CN202311107609.4A
Other languages
Chinese (zh)
Inventor
鞠飞
周鑫源
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Forestry University
Original Assignee
Nanjing Forestry University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Forestry University filed Critical Nanjing Forestry University
Priority to CN202311107609.4A priority Critical patent/CN116901981A/en
Publication of CN116901981A publication Critical patent/CN116901981A/en
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/105—Speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/107—Longitudinal acceleration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an online self-learning Markov vehicle speed prediction method, which comprises the following steps: (10) constructing an offline database: and selecting standard working conditions, and integrating and forming an off-line database of the vehicle running speed. (20) offline training of a state transition probability matrix: defining the acceleration of the vehicle as a Markov state, determining a prediction range, counting state transition events, and calculating a transition probability matrix. (30) designing a state transition matrix real-time updating algorithm: and deducing a recursive form of the state transition matrix, defining a self-learning factor, and utilizing vehicle acceleration historical information to realize online updating of the state transition matrix. (40) on-line prediction: and acquiring acceleration historical data of the vehicle, updating a transition probability matrix, and predicting the speed of the vehicle. The online self-learning Markov prediction method provided by the invention can improve the accuracy of speed prediction and the calculation timeliness; meanwhile, the method is simple and easy to realize, has strong working condition self-adaption and has good engineering application prospect.

Description

Online self-learning Markov vehicle speed prediction method
Technical Field
The invention belongs to the field of automatic driving, and particularly relates to an online self-learning Markov vehicle speed prediction method.
Background
With the development of vehicle-road-network technology, ground vehicles can acquire surrounding traffic information for designing predictive motion control, and advanced auxiliary driving functions and even high-level unmanned technologies are realized. The vehicle speed prediction is a precondition for predicting a plurality of functions such as energy management, self-adaptive cruising, automatic lane changing and the like, and the prediction accuracy directly influences the safety and the fuel economy of vehicle control. Therefore, the accurate vehicle speed prediction method has important significance for realizing safe and efficient intelligent driving.
At present, vehicle speed prediction techniques have been widely studied, including polynomial fitting methods, conventional Markov chains, and a class of deep learning methods based on neural networks. However, the method has the problems of poor prediction precision, poor working condition adaptability, offline training resource waste and low online calculation timeliness. The existing vehicle speed prediction method cannot achieve high accuracy, self-adaptability and high real-time performance, and needs to be further improved.
Disclosure of Invention
Aiming at the problem that the existing speed prediction method cannot achieve high precision, self-adaption and high real-time performance, the invention provides an online self-learning type Markov vehicle speed prediction method, which effectively improves the prediction precision and ensures the real-time performance.
The technical solution for realizing the purpose of the invention is as follows:
an online self-learning Markov vehicle speed prediction method comprises the following steps:
(10) And (3) offline database construction: and selecting a standard working condition, integrating the data of the standard working condition, and constructing a vehicle running speed off-line database.
(20) Offline training of state transition probability matrix: and taking the acceleration of the vehicle as a state in the Markov event, defining a state grid of the vehicle, determining a prediction range, acquiring acceleration data according to the offline database, counting a state transition event, establishing a state transition matrix, and calculating and storing a transition probability matrix.
(30) Designing a state transition matrix real-time updating algorithm: and deducing a recursive form of the state transition matrix, defining a self-learning factor, and utilizing vehicle historical acceleration transition information and combining the offline state transition matrix to realize online updating of the state transition matrix.
(40) On-line prediction: and acquiring acceleration historical data of the vehicle at the current moment, identifying a state transition event by referring to the acceleration state grid, updating a transition probability matrix on line, predicting the acceleration of the vehicle, and further acquiring the predicted speed of the vehicle.
Compared with the prior art, the invention has the remarkable advantages that:
1. the calculation efficiency is high: based on the training of the offline state transition matrix, the online self-learning speed prediction method only needs to replace and update offline data in real time, and does not need a complicated online algorithm, so that the online calculation timeliness is greatly improved, and the method can be more quickly adapted to new environments and changes.
2. The adaptability is strong: the traditional speed prediction method collects a large amount of data through an offline training model to perform offline training, and predicts by using the offline data, which often has the defect of low hysteresis and precision.
Drawings
FIG. 1 is a flow chart of an online self-learning Markov vehicle speed prediction method of the present invention.
FIG. 2 is an off-line operating mode combining diagram.
Fig. 3 is a transition probability matrix offline training flowchart.
Fig. 4 is a graph of a multi-step markov transition probability matrix.
Fig. 4 (a) is a graph of acceleration transition probability matrix after 1 second at the present time.
Fig. 4 (b) is a graph of acceleration transition probability matrix after 3 seconds at the present time.
Fig. 4 (c) is a graph of acceleration transition probability matrix 7 seconds after the current time.
Fig. 4 (d) is a graph of acceleration transition probability matrix after 10 seconds at the present time.
Fig. 5 is a flow chart of transition probability matrix real-time update.
Fig. 6 is a graph of the velocity prediction trace and root mean square error of a conventional markov model.
Fig. 6 (a) is a graph of the velocity prediction trajectory error of a conventional markov model.
Fig. 6 (b) is a root mean square error plot of velocity prediction data for a conventional markov model.
Fig. 7 is a graph of the on-line self-learning velocity prediction trajectory and root mean square error.
Fig. 7 (a) is an online self-learning type velocity prediction trajectory error.
Fig. 7 (b) is a root mean square error diagram of the online self-learning type velocity prediction data.
Table 1 shows the performance of the present invention in comparison to the two prior art methods.
Detailed Description
The present invention will be described in conjunction with the accompanying drawings so that those skilled in the art can better understand the present invention from the description.
FIG. 1 shows a flow chart of an online self-learning Markov speed prediction method of the present invention.
In this embodiment, as shown in fig. 1, a markov speed prediction method of online self-learning type includes the steps of:
(10) And (3) offline database construction: and selecting a standard working condition, integrating the data of the standard working condition, and constructing a vehicle running speed off-line database.
In order to more comprehensively cover various typical road sections and enable the prediction result to be more accurate, the embodiment integrates several typical working conditions and obtains offline data from the same.
FIG. 2 shows an offline operating mode combining diagram.
(20) Offline training of state transition probability matrix: and taking the acceleration of the vehicle as a state in the Markov event, defining a state grid of the vehicle, determining a prediction range, acquiring acceleration data according to the offline database, counting a state transition event, establishing a state transition matrix, and calculating and storing a transition probability matrix.
FIG. 3 shows that the (20) state transition probability matrix offline training step includes:
(21) State grid definition: with vehicle acceleration as the state in a markov event, i.e., the acceleration state space can be defined as x= { a 1 ，a 2 ，......，a p }，a 1 And a p The minimum acceleration and the maximum acceleration are respectively represented, and p is the size of the state space. Defining acceleration state grid, acceleration a (-4 a is less than or equal to 4) m/s 2 With a mesh size of 0.1m/s 2 The variables are divided.
(22) Prediction time step size determination: the predicted time range was taken to be 10 seconds.
(23) Counting state transition events: and traversing the value in each acceleration state grid at each prediction time step, and according to the offline acceleration track. Statistics of each current acceleration value a i Transition to its corresponding next time acceleration value a j Is recorded as the number of samples ofp is the state space size, k is the index of future instants, k e {1,2,.. The. Q is the acceleration curve test length. Statistics of the sum a in the offline track i The number of samples of equal value, noted +.>
(24) Calculating a state transition matrix: the number of samples counted according to the state eventThe state transition matrix at a certain time k in the future can be calculated as:
the (24) state transition matrix calculating step includes:
(241) And (3) establishing a state transition matrix: initializing transition probability matricesThe size is (Nacc, nacc, 10), nacc is the acceleration grid length, initialize +.>Matrix for counting acceleration a for each time step i The number of occurrences, initialize->And the matrix is used for counting the transfer times from one acceleration value to another acceleration value.
(242) And (3) establishing a frequency matrix: according to the number of samplesThe ratio of the two to the test length Q of the acceleration curve respectively represents the frequency of occurrence of two events in the curve, namely:
establishing a frequency matrix
(243) And (3) establishing a state transition matrix formula: according to the event frequencyThe state transition matrix at a future time may also be calculated as:
(244) And (5) storing a transition probability matrix: according to the acceleration a i ，a j And recording the position indexes i and j of the acceleration state grid, and storing the data in the corresponding positions of the state transition matrix.
FIG. 4 shows a preliminary multi-step Markov transition probability matrix diagram, P in the diagram, based on the (20) state transition probability matrix offline training ij Indicating acceleration from the current time a i Transition to the next time a j Is a probability of (2).
Fig. 4 (a) is a graph of acceleration transition probability matrix after 1 second at the present time.
Fig. 4 (b) is a graph of acceleration transition probability matrix after 3 seconds at the present time.
Fig. 4 (c) is a graph of acceleration transition probability matrix 7 seconds after the current time.
Fig. 4 (d) is a graph of acceleration transition probability matrix after 10 seconds at the present time.
In order to better embody the invention and adapt to more road conditions than the traditional method, the embodiment selects to perform experiments under the working condition of US06 which is not integrated into an offline database.
(30) Designing a state transition matrix real-time updating algorithm: and deducing a recursive form of the state transition matrix, defining a self-learning factor, and utilizing vehicle historical acceleration transition information and combining the offline state transition matrix to realize online updating of the state transition matrix.
FIG. 5 shows that the (30) design state transition matrix real-time update algorithm steps include:
(31) Defining a self-learning factor: according to the event frequencyDeriving its recursive form, one can obtain:
wherein the method comprises the steps ofRepresenting acceleration from a after time k in offline data i Transfer to acceleration value a j Is used for the number of samples of (a), similarly available->
According to the recursive form of the two equations, the state transition matrix at a certain time can be calculated as:
if no corresponding acceleration value a exists in the offline acceleration track i ThenNamely:
wherein eta is an introduced Markov learning coefficient, and can be freely adjusted in practical application to realize a better prediction effect.
(32) On-line updating of the state transition matrix: for each time step, acquiring the latest series of acceleration data, determining position indexes j and i in an acceleration state grid according to the current acceleration value and the acceleration values of the first k time steps, updating the corresponding frequency matrix, and finally calculating a transition probability matrix.
(40) On-line prediction: and acquiring acceleration historical data of the vehicle at the current moment, identifying a state transition event by referring to the acceleration state grid, updating a transition probability matrix on line, predicting the acceleration of the vehicle, and further acquiring the predicted speed of the vehicle.
The (40) online prediction step includes:
(41) Acceleration value and speed value acquisition: acquiring a speed value and an acceleration value at the current moment, and finding the nearest index a in an acceleration grid by performing approximate processing on the current acceleration value i 。
(42) Initializing acceleration and speed prediction vectors: two zero matrices are created to store acceleration and velocity predictions for k time steps in the future, respectively.
(43) Calculating a prediction result: according to the transition probability matrix, acquiring a transition probability vector corresponding to the ith row and the kth column, and using the transition probability vectorMultiplying the elements of the acceleration grid one by one and summing to obtain an acceleration prediction value +.>Namely:
the velocity predictions in the next k time steps are then obtained by adding the first k predicted acceleration values and the current velocity value vNamely:
if any one of the speed predictions is less than 0, it is set to 0 to ensure that the speed value is non-negative.
(44) Calculating a prediction error: by taking the root mean square error for the predicted speed value and the true speed value and storing it at the corresponding time in the improved prediction error vector. And drawing a prediction result.
To clarify the quantization speed prediction error, a Root Mean Square Error (RMSE) was introduced as a performance evaluation index: the smaller the root mean square error, the higher the prediction accuracy.
Fig. 6 shows a graph of the velocity prediction trace and root mean square error of a conventional markov model.
Fig. 6 (a) shows a graph of the velocity prediction trajectory error of a conventional markov model.
Fig. 6 (b) shows a root mean square error plot of the velocity prediction data of a conventional markov model.
Fig. 7 shows an on-line self-learning speed prediction trajectory and root mean square error plot.
Fig. 7 (a) shows an online self-learning type velocity prediction trajectory error.
Fig. 7 (b) shows a root mean square error map of the velocity prediction data of the online self-learning type.
The red lines in fig. 6 (a) and 7 (a) represent the track trend of the speed predicted by the method at each moment, the thick lines represent the actual running speed curve of the vehicle, and it can be seen from the graph that the speed prediction track drawn by the speed prediction method of the invention has higher coincidence degree with the actual vehicle speed track, and the areas of the green shaded portions in fig. 6 (b) and 7 (b) represent the root mean square error at each moment, so that the speed prediction of the invention has higher accuracy than the traditional markov model in the embodiment.
To further verify the advantages of the present invention, a more advanced Long Short-Term Memory (LSTM) network was also used in this example to compare with the predicted results of the present invention, and table 1 is a comparison table of three methods:
TABLE 1
Table 1 shows a comparison list of the present invention with the conventional Markov and long-short term memory network speed prediction method in terms of root mean square error and calculation time, from Table 1 we can obtain that the root mean square error of the conventional Markov prediction method is 2.16m/s, the root mean square error of the conventional Markov prediction method and the speed prediction method of the long-short term memory network and the self-learning type are respectively 1.86m/s and 1.82m/s, the prediction precision is improved by 13.9% and 15.7% respectively compared with the conventional Markov speed prediction method, and the prediction precision of the present invention is superior to the two existing prediction technologies, from which we can also obtain that the calculation time of the present invention is 0.6ms when the precision is higher than the conventional Markov prediction method, and the calculation time of the long-short term memory network prediction method is 24ms, the calculation time of the prediction result of the present invention is far less than the calculation efficiency of the long-short term memory network prediction method. Embodying the advantages of the present invention.

Claims (6)

1. An online self-learning Markov vehicle speed prediction method is characterized by comprising the following steps:
(10) And (3) offline database construction: and selecting a standard working condition, integrating the data of the standard working condition, and constructing a vehicle running speed off-line database.
(20) Offline training of state transition probability matrix: and taking the acceleration of the vehicle as a state in the Markov event, defining a state grid of the vehicle, determining a prediction range, acquiring acceleration data according to the offline database, counting a state transition event, establishing a state transition matrix, and calculating and storing a transition probability matrix.
(30) Designing a state transition matrix real-time updating algorithm: and deducing a recursive form of the state transition matrix, defining a self-learning factor, and utilizing vehicle historical acceleration transition information and combining the offline state transition matrix to realize online updating of the state transition matrix.
(40) On-line prediction: and acquiring acceleration historical data of the vehicle at the current moment, identifying a state transition event by referring to the acceleration state grid, updating a transition probability matrix on line, predicting the acceleration of the vehicle, and further acquiring the predicted speed of the vehicle.
2. The speed prediction method according to claim 1, wherein the (10) offline database construction step includes:
(11) Standard working condition integration: and integrating experimental data of several working conditions according to the urban working condition FUDS, the comprehensive working condition NEDC, the high-speed working condition HWFET, the urban working condition NYCC and the comprehensive working condition WLTP.
(12) Offline data acquisition: and according to the integration of the experimental data of the working conditions, acquiring a speed-time curve and an acceleration-time curve.
3. The speed prediction method according to claim 1, wherein the (20) state transition probability matrix offline training step comprises:
(21) State grid definition: the acceleration of the vehicle is used as the state in the Markov event, an acceleration state grid is defined, and the acceleration (-4 a is less than or equal to 4) m/s 2 With a mesh size of 0.1m/s 2 The variables are divided.
(22) Prediction range determination: the predicted time range was taken to be 10 seconds.
(23) Counting state transition events: traversing the values in each acceleration state grid under each predicted time step, and counting each current acceleration value a according to the offline acceleration track i Transition to its corresponding next time acceleration value a j Is recorded as the number of samples ofi, j e {1, 2....p }, p is the state space size, k is an index of future instants, k e {1,2,.. The. Q is the acceleration curve test length. Statistics of the sum a in the offline track i The number of samples of equal value, noted +.>
(24) Calculating a state transition matrix: based on the number of samples of state transition event, the transition probability matrix at a future time can be calculated from the number of samplesAnd->The ratio of the two is obtained.
4. A speed prediction method according to claim 3, wherein the (24) state transition matrix calculation step comprises:
(241) And (3) establishing a state transition matrix: initializing state transition matricesInitializing matrix->For counting acceleration a per time step i The number of occurrences, initialize the matrix->For counting the number of transitions from one acceleration value to another.
(242) And (3) establishing a frequency matrix: according to the number of samplesThe ratio of the two to the test length Q of the acceleration curve respectively represents the frequency of occurrence of two events in the curve, which is marked as +.>Establishing a frequency matrix->
(243) And (3) establishing a state transition matrix formula: according to the event frequencyThe state transition matrix at a future time can be defined by +.>The ratio of the two is obtained.
(244) And (5) storing a transition probability matrix: according to the acceleration a i 、a j And recording the position indexes i and j of the acceleration state grid, and storing the data in the corresponding positions of the state transition matrix.
5. The method of speed prediction according to claim 1, wherein the step of (30) designing a state transition matrix real-time update algorithm comprises:
(31) Defining a self-learning factor: according to the state transition matrixDeriving the state transition matrix recursion form, and obtaining:
wherein the method comprises the steps ofRepresenting the current acceleration from a in the offline data i Acceleration value a after transition to its corresponding k time j Sample number of>Wherein eta is an introduced Markov learning coefficient, and can be freely adjusted in practical application to realize a better prediction effect.
(32) On-line updating of the state transition matrix: and for each time step, acquiring the latest series of acceleration data, determining a position index in an acceleration state grid according to the current acceleration value and the acceleration value of the next predicted moment, updating a corresponding frequency matrix, and finally calculating a transition probability matrix.
6. The speed prediction method according to claim 1, wherein the (40) online prediction step includes:
(41) Acceleration value and speed value acquisition: and acquiring a speed value and an acceleration value at the current moment, and finding the closest index in the acceleration grid by performing approximate processing on the current acceleration value.
(42) Initializing acceleration and speed prediction vectors: two zero matrices are created for storing the acceleration and velocity predictions, respectively, over a future prediction time horizon.
(43) Calculating a prediction result: according to the state transition matrix, a corresponding transition probability vector is obtained, the probability vector is multiplied with elements of the acceleration grid one by one and summed to obtain an acceleration predicted value, then the velocity predicted value in the next k time steps is obtained by adding the previous predicted acceleration values and adding the current velocity value, and if any velocity predicted value is smaller than 0, the velocity predicted value is set to 0 to ensure that the velocity value is non-negative.
(44) Calculating a prediction error: and drawing a prediction result by solving root mean square error of the predicted speed value and the real speed value and storing the root mean square error in the improved prediction error vector at the corresponding moment.
CN202311107609.4A 2023-08-30 2023-08-30 Online self-learning Markov vehicle speed prediction method Pending CN116901981A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311107609.4A CN116901981A (en) 2023-08-30 2023-08-30 Online self-learning Markov vehicle speed prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311107609.4A CN116901981A (en) 2023-08-30 2023-08-30 Online self-learning Markov vehicle speed prediction method

Publications (1)

Publication Number Publication Date
CN116901981A true CN116901981A (en) 2023-10-20

Family

ID=88354954

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311107609.4A Pending CN116901981A (en) 2023-08-30 2023-08-30 Online self-learning Markov vehicle speed prediction method

Country Status (1)

Country Link
CN (1) CN116901981A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117325875A (en) * 2023-12-01 2024-01-02 北京航空航天大学 Vehicle long-term speed prediction method based on individual driving characteristics

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117325875A (en) * 2023-12-01 2024-01-02 北京航空航天大学 Vehicle long-term speed prediction method based on individual driving characteristics
CN117325875B (en) * 2023-12-01 2024-02-02 北京航空航天大学 Vehicle long-term speed prediction method based on individual driving characteristics

Similar Documents

Publication Publication Date Title
CN112265546B (en) Networked automobile speed prediction method based on time-space sequence information
CN107909179B (en) Method for constructing prediction model of running condition of plug-in hybrid vehicle and vehicle energy management method
CN110775065B (en) Hybrid electric vehicle battery life prediction method based on working condition recognition
CN111696370B (en) Traffic light control method based on heuristic deep Q network
CN110648014B (en) Regional wind power prediction method and system based on space-time quantile regression
CN113538910B (en) Self-adaptive full-chain urban area network signal control optimization method
CN109920248B (en) Bus arrival time prediction method based on GRU neural network
CN111339712A (en) Method for predicting residual life of proton exchange membrane fuel cell
CN112101684B (en) Plug-in hybrid electric vehicle real-time energy management method and system
CN108986453A (en) A kind of traffic movement prediction method based on contextual information, system and device
CN116901981A (en) Online self-learning Markov vehicle speed prediction method
CN113449919B (en) Power consumption prediction method and system based on feature and trend perception
CN115409256A (en) Route recommendation method for congestion area avoidance based on travel time prediction
CN116244647A (en) Unmanned aerial vehicle cluster running state estimation method
CN113298318A (en) Novel overload prediction method for distribution transformer
CN113788007A (en) Layered real-time energy management method and system
CN115238789A (en) Financial industry special data prediction method and system based on improved GRU
CN113537620A (en) Vehicle speed prediction method based on Markov model optimization and working condition recognition
CN112734111A (en) AGV dynamic time estimation method for horizontal transportation task
CN117901724B (en) Control method, system and equipment for thermal management system of pure electric vehicle
CN118116200B (en) Traffic flow prediction method and system based on CNN-LSTM-At
CN117874472B (en) System and method for analyzing trusted time of wave recording file based on width learning network
CN114707417B (en) Method, system and equipment for predicting vehicle running track in real time
CN112734030B (en) Unmanned platform decision learning method for empirical playback sampling by using state similarity
CN118194708A (en) Self-adaptive quality prediction modeling method based on industrial Internet of things and cloud edge cooperation

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