CN108021028B - It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt - Google Patents
It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt Download PDFInfo
- Publication number
- CN108021028B CN108021028B CN201711407168.4A CN201711407168A CN108021028B CN 108021028 B CN108021028 B CN 108021028B CN 201711407168 A CN201711407168 A CN 201711407168A CN 108021028 B CN108021028 B CN 108021028B
- Authority
- CN
- China
- Prior art keywords
- control
- state
- model
- network
- pomdp model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention relates to a kind of various dimensions intelligence caravan cooperative control methods converted based on relevant redundancy with enhancing study, belong to internet of things field.This method is around intelligent business Sojourn house car Unified Device connection protocol, shared device interface, the autonomous Collaborative Control demand for improving level of integrated system, utilize the autonomous control boot policy based on POMDP model and depth enhancing study, input of the state of a control obtained using various dimensions Intelligent Fusion as computer control system, POMDP model is established to perceive, adapt to, the variation of tracing equipment state of a control, optimizing behavior strategy is selected using based on the policy optimization method of depth enhancing study, realizes the autonomous Collaborative Control of commercial Sojourn house car.The present invention not only contributes to the validity and real-time of final decision, while improving the accuracy of interaction feedback and the study degree of optimization of strategy, promotes user experience.
Description
Technical field
The invention belongs to internet of things field, are related to a kind of convert based on relevant redundancy and cooperate with control with the various dimensions of enhancing study
Method processed.
Background technique
Product of the intelligent caravan as intelligent network connection automobile and smart home depth integration, utilizes multi-sensor data collection
With the car borne gateway communication technology, intelligentized control method is carried out to mobile unit, meets space experience and intelligence of the people for caravan
The demand of life.The real-time and accuracy executed as the intelligent control technology of one of intelligent caravan core, control strategy
Directly decide the superiority and inferiority of intelligent caravan, but for the existing intelligent caravan of existing market, single, control that there is control modes
The problems such as strategy generating intelligence processed is short of, Executing Cost is excessively high.For this purpose, this patent using multi-source heterogeneous information characteristics it is unified with
Fusion, integrates Multiple Source Sensor data, lays the foundation for the control under multi-modal complex environment, and uses POMDP mould
State of a control boot policy method under type is combined with state of a control boot policy optimization the two of depth enhancing study, makes to control
Decision more accurately with intelligence, while using the bottom control based on bus, is greatly reduced sensor cost of access, improves entire
The reliability of aware platform saves a large amount of calculation resources.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of converted based on relevant redundancy to assist with the various dimensions for enhancing study
Same control method,
In order to achieve the above objectives, the invention provides the following technical scheme:
It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt, comprising the following steps:
S1: multi-source heterogeneous information characteristics are unified and are merged；
S2: using the state of a control strategy guidance based on POMDP model；
S3: using the state of a control boot policy optimization based on depth enhancing study；
S4: the distributed bottom control based on bus is used.
Further, the step S1 specifically: under multiple-sensor network environment, multisensor Heterogeneous Information passes through classics
Correlation analysis algorithm CCA and isomorphism relevant redundancy convert (Isomorphic Relevant Redundant
Transformation, IRRT) algorithm analysis, multiple Heterogeneous Informations are mapped to unified, the computable space of dimension,
Information is merged after carrying out unified representation to characteristic information.
Further, the step S2 specifically: the commercial Sojourn house car obtained using multi-source heterogeneous integration technology is all kinds of to be set
Standby state of a control establishes POMDP model to perceive, adapt to, the variation of tracing equipment state of a control；Pass through POMDP model
Internal action device is acted to equipment state of a control application, to cause equipment state of a control to change, and obtains certain return；Root
A possibility that a series of performed strategies are measured according to the accumulative return of acquisition, and then the control of the equipment of commercial Sojourn house car is asked
Topic is converted into policy selection problem；Specifically, POMDP model is described as<S, A, T, O, Q, and β>, integrated environment state is in POMDP
Confidence state in model probability distribution is expressed as B={ bt, the probability distribution of t moment is bt={ bt(s1) ..., bt
(sm)}；Wherein, bt(si) expression t moment ambient condition be siProbability；By controlling current time the observation of environment and moving
The selection of work, POMDP model inference go out the value of the confidence of subsequent time state of a control；Assuming that the confidence state of initial time is b0,
Execution acts a and observation o, obtains subsequent time confidence state b1；When in state of a control S1, what model obtained is viewed as O1, mould
Type internal state is i1；By calculating, corresponding movement a is selected according to state of a control boot policy1, cause ambient condition from S1
It is transferred to S2, model, which obtains, returns r1With observation O2, model internal state is from i at this time1(b1) it is transferred to i2(b2), then model according to
This is continued to run；
Specifically, the boot policy estimation function of Construct question realizes dialogue state tracking, which isWherein,It is corresponding
The value of the movement vector state s of node n；Developed by state of a control strategy, obtains subsequent timeState of a control boot policy function, whereinIndicate optimal plan
Slightly,Indicate the strategic function of last moment.
Further, the step S3 specifically: drawing for commercial Sojourn house car equipment state of a control is obtained according to POMDP model
Strategy is led, selects optimizing behavior strategy using the policy optimization method of study DQN is enhanced based on depth；Specifically, using Q-
Network (Q (s, a；Behavioral strategy θ)) is defined, target Q- network (Q (s, a are utilized；θ-)) target Q value that DQN loses item is generated, with
And memory POMDP model is used to train the stochastical sampling state value of Q network again；Learn to define POMDP model by enhancing
It is expected that Total ReturnWherein, r is returnedtIt is converted by the factor gamma ∈ [0,1] of each time step, T is to terminate step
Suddenly；Using movement value function Qπ(s, a) observation state stAdaptive expectations, and utilize neural network Q (s, a)=(Q (s, a；θ))
Approximation movement value function；For based on the boot policy π, optimal movement value function Q under movement aπ(s, a)=E [Rt|st=a, a1
=a, π] pass through strategyIt realizes；Construct the Bellman equation containing action value aIt is solved by adjusting Bellman target component of the Q-network to iteration；
Firstly, DQN using memory reconstruct, in each time step t of POMDP model, will remember tuple et=(st,
at, rt, st+1) it is stored in mnemonic Dt={ e1..., etIn；
Secondly, DQN maintains two independent Q network (Q (s, a respectively；θ)) and (Q (s, a；θ-))；Parameter current 6 is every
It is repeatedly updated in a time step, and is copied to old parameter θ after n iterations-In；When updating iteration, in order to
It minimizes relative to old parameter θ-Side Bellman error, pass through optimization loss functionTo update parameter current 6；For updating i every time, from memory
Individually sampling obtains memory tuple (s, a, r, s ')~U (D) in memory D；For each sample, calculated by stochastic gradient descent
Method updates parameter current 6；The gradient g of declineiBy 6 relative to θ-Loss sample gradientIt acquires；
Finally, selecting in each time step t relative to current Q- network (Q (s, a；Preference behavior act θ))；
Q network (Q (s, a are safeguarded using Center Parameter server；θ-)) distributed indicate；Meanwhile the parameter server receives by force
The gradient information that chemistry is practised, and under the driving of asynchronous stochastic gradient descent algorithm, ginseng is modified using these gradient informations
Number vector θ-。
Further, the step S4 specifically: the addressing mode for the data channel that design is mapped based on memory, synthesis are examined
Consider triggering mode, timing and load capacity problem, cooperates with variable connector and sampling holder, realize being total to for Data interface channels
It enjoys；The self-control system with redundancy structure is designed, intelligently parsing merges decision control instruction obtained, it is defeated to take into account power supply
Fluctuation, electromagnetic radiation and distributed capacitor inductive interferences factor out, complete the autonomous control of mobile unit.
The beneficial effects of the present invention are: the present invention is a kind of various dimensions intelligence converted based on relevant redundancy with enhancing study
It can caravan cooperative control method.Equipment working condition is monitored, drive environmental classes people perception, characteristics of human body identification, user be intended to push away
Reason, resource information interaction, vehicle device autonomous control etc., compared with other methods, this patent surrounds intelligent business Sojourn house car
Unified Device connection protocol, shared device interface, the autonomous Collaborative Control demand for improving level of integrated system, using based on POMDP
The autonomous control boot policy of model and depth enhancing study, the state of a control obtained using various dimensions Intelligent Fusion is as calculating
The input of machine control system establishes POMDP model to perceive, adapt to, the variation of tracing equipment state of a control, using being based on depth
Enhancing learns the policy optimization method of (DQN) to select optimizing behavior strategy, realizes the autonomous Collaborative Control of commercial Sojourn house car.
POMDP model and depth are enhanced in conjunction with two methods of study, formed under multi-modal mode with the intelligent caravan under complex environment
Optimal Control decision, not only contributes to the validity and real-time of final decision, at the same improve the accuracy of interaction feedback with
The study degree of optimization of strategy promotes user experience.
Detailed description of the invention
In order to keep the purpose of the present invention, technical scheme and beneficial effects clearer, the present invention provides following attached drawing and carries out
Illustrate:
Fig. 1 be multi-source heterogeneous feature unified representation with merge scheme；
Fig. 2 is in the state of a control boot policy figure of POMDP model；
Fig. 3 is the state of a control strategy optimization model of depth enhancing study.
Specific embodiment
Below in conjunction with attached drawing, a preferred embodiment of the present invention will be described in detail.
As shown in Figure 1, 2, 3, each section specific implementation details of the present invention are as follows:
1, multi-source heterogeneous information characteristics are unified and are merged.The process includes following 5 steps:
(1) multi-modal data acquires；
(2) multi-modal feature extraction；
(3) feature association；
(4) multi-modal feature unified representation；
(5) multi-source heterogeneous information characteristics fusion.
2, the state of a control boot policy design based on POMDP model.The process includes following 4 steps:
(1) POMDP model perception, adaptation, the variation of tracing equipment state of a control are established；
(2) affector is acted to equipment state of a control application, obtains certain return；
(3) a possibility that a series of performed strategies are measured according to the accumulative return of acquisition,
(4) gained policy selection is carried out；
3, the state of a control boot policy optimization based on depth enhancing study.The process includes following 3 steps:
(1) Q- net definitions behavioral strategy；
(2) target Q value that DQN loses item is generated；
(3) the stochastical sampling state value that POMDP model is used to train Q network is remembered again.
4, the distributed bottom control based on bus.Using CAN bus based intelligent caravan gateway centralized control scheme,
Intelligent caravan interface unit module is introduced, the effective diversity that controlled device is isolated reduces the complexity of system；Pass through keyboard
Control, remote control mode improve the reliability of intelligent caravan gateway from intelligent caravan gateway separation；Intelligent room vehicle internal network is selected
CAN bus reduces the cost of system, meets the scalability of system, and according to more principal characteristics of CAN bus, realizes controlled pair
The plug-and-play feature of elephant.
Finally, it is stated that preferred embodiment above is only used to illustrate the technical scheme of the present invention and not to limit it, although logical
It crosses above preferred embodiment the present invention is described in detail, however, those skilled in the art should understand that, can be
Various changes are made to it in form and in details, without departing from claims of the present invention limited range.
Claims (3)
1. a kind of converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt, it is characterised in that: this method packet
Include following steps:
S1: multi-source heterogeneous information characteristics are unified and are merged；
S2: using the state of a control strategy guidance based on POMDP model；
S3: using the state of a control boot policy optimization based on depth enhancing study；
S4: the distributed bottom control based on bus is used；
The step S2 specifically: using the control shape for the commercial Sojourn house car various kinds of equipment that multi-source heterogeneous integration technology obtains
State establishes POMDP model to perceive, adapt to, the variation of tracing equipment state of a control；Pass through the internal action device of POMDP model
It is acted to equipment state of a control application, to cause equipment state of a control to change, and obtains certain return；According to the tired of acquisition
Meter returns a possibility that measure a series of performed strategies, and then the equipment control problem of commercial Sojourn house car is converted into plan
Slightly select permeability；Specifically, POMDP model is described as { S, A, T, O, Q, β }, and integrated environment state is in POMDP model probability point
Confidence state in cloth is expressed as B={ bt, the probability distribution of t moment is bt={ bt(s1),...,bt(Sm)}；Wherein, bt
(si) expression t moment ambient condition be SiProbability；By controlling current time the selection of the observation and movement of environment, POMDP
Model inference goes out the value of the confidence of subsequent time state of a control；Assuming that the confidence state of initial time is b0, execution act a and observation
O obtains subsequent time confidence state b1；When in state of a control S1, what model obtained is viewed as O1, model internal state is i1；
By calculating, corresponding movement a is selected according to state of a control boot policy1, cause ambient condition from S1It is transferred to S2, model obtains
R must be returned1With observation O2, model internal state is from i at this time1(b1) it is transferred to i2(b2), then model continues to run according to this；
Specifically, the boot policy estimation function of Construct question realizes dialogue state tracking, which isWherein,It is corresponding
The value of the movement vector state s of node n；Developed by state of a control strategy, obtains subsequent timeState of a control boot policy function, whereinIndicate optimal plan
Slightly, Vt* the strategic function of last moment is indicated；
The step S3 specifically: the boot policy of commercial Sojourn house car equipment state of a control is obtained according to POMDP model, is used
Enhance the policy optimization method of study DQN based on depth to select optimizing behavior strategy；Specifically, using Q- network (Q (s, a；
Behavioral strategy θ)) is defined, target Q- network (Q (s, a are utilized；θ-)) target Q value of DQN loss item is generated, and remember again
POMDP model is used to train the stochastical sampling state value of Q network；Learn the expection Total Return of definition POMDP model by enhancingWherein, r is returnedtIt is converted by factor gamma=[0,1] of each time step, T is to terminate step；Using movement
Value function Qπ(s, a) observation state StAdaptive expectations, and utilize neural network Q (s, a)=(Q (s, a；θ-)) approximation action value
Function；For based on the boot policy π, optimal movement value function Q under movement aπ(s, a)=E [Rt|st=a, a1=a, π] pass through
StrategyIt realizes；Construct the Bellman equation containing action value aIt is solved by adjusting Bellman target component of the Q-network to iteration；
Firstly, DQN using memory reconstruct, in each time step t of POMDP model, will remember tuple et=(st,at,rt,
st+1) it is stored in mnemonic Dt={ e1,...,etIn；
Secondly, DQN maintains two independent Q network (Q (s, a respectively；θ)) and (Q (s, a；θ-))；Parameter current θ is in each time
It is repeatedly updated in step-length, and is copied to old parameter θ after n iterations-In；When updating iteration, in order to minimize
Relative to old parameter θ-Side Bellman error, pass through optimization loss functionTo update parameter current θ；For updating i every time, from memory
Individually sampling obtains memory tuple (s, a, r, s`)~U (D) in memory D；For each sample, calculated by stochastic gradient descent
Method updates parameter current δ；The gradient g of declineiBy θ relative to θ-Loss sample gradientIt acquires；
Finally, selecting in each time step t relative to current Q- network (Q (s, a；Preference behavior act θ))；It uses
Center Parameter server safeguards Q network (Q (s, a；θ-)) distributed indicate；Meanwhile the parameter server receives extensive chemical
The gradient information practised, and under the driving of asynchronous stochastic gradient descent algorithm, modified using these gradient informations parameter to
Measure θ-。
2. a kind of various dimensions cooperative control method converted based on relevant redundancy with enhancing study according to claim 1,
It is characterized by: the step S1 specifically: under multiple-sensor network environment, multisensor Heterogeneous Information passes through classical related
Parser CCA and isomorphism relevant redundancy transformation (IsomorphicRelevantRedundantTransformation, IRRT)
Multiple Heterogeneous Informations are mapped to unified, the computable space of dimension by algorithm analysis, carry out unified table to characteristic information
Information is merged after showing.
3. a kind of various dimensions cooperative control method converted based on relevant redundancy with enhancing study according to claim 1,
It is characterized by: the step S4 specifically: the addressing mode for the data channel that design is mapped based on memory comprehensively considers touching
Originating party formula, timing and load capacity problem cooperate with variable connector and sampling holder, realize the shared of Data interface channels；If
The self-control system with redundancy structure is counted, intelligently parsing merges decision control instruction obtained, takes into account power supply output wave
Dynamic, electromagnetic radiation and distributed capacitor inductive interferences factor, complete the autonomous control of mobile unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711407168.4A CN108021028B (en) | 2017-12-22 | 2017-12-22 | It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711407168.4A CN108021028B (en) | 2017-12-22 | 2017-12-22 | It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108021028A CN108021028A (en) | 2018-05-11 |
| CN108021028B true CN108021028B (en) | 2019-04-09 |
Family
ID=62074474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711407168.4A Active CN108021028B (en) | 2017-12-22 | 2017-12-22 | It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108021028B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108777872B (en) * | 2018-05-22 | 2020-01-24 | 中国人民解放军陆军工程大学 | Intelligent anti-interference method and intelligent anti-interference system based on deep Q neural network anti-interference model |
| CN110533054B (en) * | 2018-05-25 | 2024-02-06 | 中国电力科学研究院有限公司 | Multi-mode self-adaptive machine learning method and device |
| CN110989602B (en) * | 2019-12-12 | 2023-12-26 | 齐鲁工业大学 | Autonomous guided vehicle path planning method and system in medical pathology inspection laboratory |
| CN113126498A (en) * | 2021-04-17 | 2021-07-16 | 西北工业大学 | Optimization control system and control method based on distributed reinforcement learning |
| CN113727420B (en) * | 2021-09-03 | 2023-05-23 | 重庆邮电大学 | Multimode access network selection device and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101083656A (en) * | 2007-07-05 | 2007-12-05 | 上海交通大学 | Data stream technique based multi-source heterogeneous data integrated system |
| CN101094173A (en) * | 2007-06-28 | 2007-12-26 | 上海交通大学 | Integrated system of data interchange under distributed isomerical environment |
| CN101213111A (en) * | 2005-06-03 | 2008-07-02 | 埃伦贝格尔及珀恩斯根有限公司 | Multiplexing-system for controlling loads in boots or recreational vehicles |
| CN101222524A (en) * | 2008-01-09 | 2008-07-16 | 华南理工大学 | Distributed multi-sensor cooperated measuring method and system |
| CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
| CN102207928A (en) * | 2011-06-02 | 2011-10-05 | 河海大学常州校区 | Reinforcement learning-based multi-Agent sewage treatment decision support system |
| CN106228314A (en) * | 2016-08-11 | 2016-12-14 | 电子科技大学 | The workflow schedule method of study is strengthened based on the degree of depth |
-
2017
- 2017-12-22 CN CN201711407168.4A patent/CN108021028B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101213111A (en) * | 2005-06-03 | 2008-07-02 | 埃伦贝格尔及珀恩斯根有限公司 | Multiplexing-system for controlling loads in boots or recreational vehicles |
| CN101094173A (en) * | 2007-06-28 | 2007-12-26 | 上海交通大学 | Integrated system of data interchange under distributed isomerical environment |
| CN101083656A (en) * | 2007-07-05 | 2007-12-05 | 上海交通大学 | Data stream technique based multi-source heterogeneous data integrated system |
| CN101222524A (en) * | 2008-01-09 | 2008-07-16 | 华南理工大学 | Distributed multi-sensor cooperated measuring method and system |
| CN101466111A (en) * | 2009-01-13 | 2009-06-24 | 中国人民解放军理工大学通信工程学院 | Dynamic spectrum access method based on policy planning constrain Q study |
| CN102207928A (en) * | 2011-06-02 | 2011-10-05 | 河海大学常州校区 | Reinforcement learning-based multi-Agent sewage treatment decision support system |
| CN106228314A (en) * | 2016-08-11 | 2016-12-14 | 电子科技大学 | The workflow schedule method of study is strengthened based on the degree of depth |
Non-Patent Citations (2)
| Title |
|---|
| Deep Reinforcement Learning with POMDPs;Maxim Egorov;《IEEE》;20151211;正文第1-5页 |
| Mining Semantically Consistent Patterns for Cross-View Data;Lei Zhang, etc;《IEEE Transactions on Knowledge and Data Engineering》;20141231;正文第1-4页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108021028A (en) | 2018-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108021028B (en) | It is a kind of to be converted based on relevant redundancy and enhance the various dimensions cooperative control method learnt | |
| Ye et al. | Machine learning for vehicular networks: Recent advances and application examples | |
| Sunhare et al. | Internet of things and data mining: An application oriented survey | |
| Xu et al. | Scalable learning paradigms for data-driven wireless communication | |
| CN110481536B (en) | Control method and device applied to hybrid electric vehicle | |
| CN101222524B (en) | Distributed multi-sensor cooperated measuring system | |
| CN102200787B (en) | Robot behaviour multi-level integrated learning method and robot behaviour multi-level integrated learning system | |
| CN114237041B (en) | Space-ground cooperative fixed time fault tolerance control method based on preset performance | |
| CN108153259B (en) | Multi-controller optimal state estimation control strategy design method based on Kalman filtering | |
| WO2018120963A1 (en) | Feedback-based self-adaptive subjective and objective weight context awareness system and working method thereof | |
| CN110501917A (en) | The system and method for realizing internet of things intelligent household information management using cloud computing | |
| CN112949472A (en) | Cooperative sensing method based on multi-sensor information fusion | |
| CN113538162A (en) | Planting strategy generation method and device, electronic equipment and storage medium | |
| Shahriari et al. | Generic online learning for partial visible dynamic environment with delayed feedback: Online learning for 5G C-RAN load-balancer | |
| CN117475518B (en) | Synchronous human motion recognition and prediction method and system | |
| CN108182476A (en) | A kind of policy learning method controlled in intensified learning by wish | |
| CN112965381B (en) | Method for establishing cooperative intelligent self-adaptive decision model | |
| Sun et al. | Optimal tracking control of switched systems applied in grid-connected hybrid generation using reinforcement learning | |
| CN113276114A (en) | Reconfigurable mechanical arm cooperative force/motion control system and method based on terminal task assignment | |
| Shang et al. | [Retracted] Human‐Computer Interaction of Networked Vehicles Based on Big Data and Hybrid Intelligent Algorithm | |
| Mou et al. | Biologically inspired machine learning-based trajectory analysis in intelligent dispatching energy storage system | |
| CN117077511A (en) | Multi-element load prediction method, device and storage medium based on improved firefly algorithm and SVR | |
| Ge et al. | An AFD-based ILC dynamics adaptive matching method in frequency domain for distributed consensus control of unknown multiagent systems | |
| Chen et al. | FUNOff: Offloading applications at function granularity for mobile edge computing | |
| CN117220287B (en) | Generating capacity 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |