CN112003891B - Multi-sensing data fusion method for intelligent networked vehicle controller - Google Patents
Multi-sensing data fusion method for intelligent networked vehicle controller Download PDFInfo
- Publication number
- CN112003891B CN112003891B CN202010683438.XA CN202010683438A CN112003891B CN 112003891 B CN112003891 B CN 112003891B CN 202010683438 A CN202010683438 A CN 202010683438A CN 112003891 B CN112003891 B CN 112003891B
- Authority
- CN
- China
- Prior art keywords
- data
- sensor
- sensors
- weight
- fusion
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 abstract description 6
- 230000008447 perception Effects 0.000 abstract description 5
- 238000012216 screening Methods 0.000 abstract description 4
- 238000007499 fusion processing Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
- Small-Scale Networks (AREA)
- Traffic Control Systems (AREA)
Abstract
The method comprises the steps of presetting the basic weight of a sensor and carrying out filtering correction on sensor data acquired by all the sensors; screening data by determining an effective data fusion set of the sensors, further obtaining dynamic weight values through similarity measurement, finally calculating comprehensive weights according to the basic weights and the dynamic weights, and performing weighted fusion calculation on different sensor data according to the comprehensive weights to obtain fusion data of a plurality of sensors. According to the method, the accuracy of the input data is ensured by filtering and correcting the acquired data, and further the later-period calculated amount is reduced by screening the effective data; the data fusion method adopted by the invention can adjust the data fusion weights of different sensors in time under different perception scenes by setting the dynamic weights, so as to obtain more accurate perception data.
Description
Technical Field
The invention relates to the field of unmanned vehicle control, in particular to a multi-sensing data fusion method for an intelligent network vehicle controller.
Background
The intelligent networked vehicle acquires environmental information through various sensors, and performs fusion processing through a vehicle controller after receiving sensor data to finally form environmental perception data so as to provide decision basis for ensuring safe driving of the vehicle. The intelligent networked vehicle needs to work through cooperation of multiple sensors in the environment sensing process, data fusion among different sensors is always a research hotspot of the networked vehicle, in the existing data fusion process, the use weight of data acquired by the sensors in the fusion process is mostly determined according to the grades of the sensors, and the division of the sensor grades is preset in advance according to the categories of the sensors, so that the corresponding sensor grades are fixed all the time, the use weight of the sensor data cannot change in various scenes, and in some scenes, inaccurate data fusion easily occurs, the phenomenon of deviation of the environment sensing occurs, and the decision correctness of a controller is finally influenced.
Disclosure of Invention
In order to solve the technical problem, the invention provides a multi-sensing data fusion method for an intelligent networked vehicle controller, which can adjust the weight of data according to the environment and determine an optimal fusion data set.
The invention is realized by the following method: the multi-sensing data fusion method for the intelligent networked vehicle controller comprises the following steps:
s1: presetting the basic weight of the sensor;
comparing each sensor with other sensors respectively according to an AHP analysis method, judging the grade of the sensor, wherein the comparison factors mainly comprise the following steps: the sensor precision, detection range and the like are assigned according to the importance level of the data acquired by a certain sensor relative to the data of other sensors.
According to the grade empowerment comparison, the kth sensor is compared with other sensors such as k +1, k +2 and the like one by one to obtain a weight matrix U consisting of a plurality of empowerments 1 。
By calculating a weight matrix U 1 The maximum characteristic root of the sensor is obtained to obtain a corresponding characteristic vector which is the basic weight e of the sensor 1 。
S2: filtering and correcting the sensor data acquired by all the sensors;
the specific steps of filtering and correcting comprise:
s201: collecting a data set;
assuming that the number of vehicle sensors capable of monitoring the same target is n, the measurement frequency of each sensor is m, wherein k is more than or equal to 1 and is less than or equal to n, i is more than or equal to 1 and is less than or equal to m, the ith measurement data of the kth sensor is recorded as f (k, i), and a data set is utilizeda k Represents all data acquired by the kth sensor, a k ＝{f(k,1),f(k,2),f(k,3)……f(k,i)……f(k,m)}。
S202: computing a data set a k The probability P of occurrence of each data f (k, i) ki ；
According to the probability density function, the raw data f (k, i) and the mean value of the ith and the ith previous s measurement data of the kth sensor
The following relationships exist:
in the above formula, γ represents a standard deviation of measurement noise, and measurement noise of different sensors is different, and it is determined according to comparison between various actual parameters of a known target and parameters obtained by the sensors and statistical analysis of data. The initial determination may be empirically estimated and later revised step by step with increasing collected comparison data. The initial estimate may be based on the following equation:
further calculating the i-th and i-th previous s measurement data of the kth sensor in the data set a k The probability of occurrence of (c).
S203: based on the raw measurement data f (k, i) and its data at a k Probability of occurrence of P ki Correcting the data to obtain corrected data f 0 (k,i)。
When a plurality of data are collected, correcting the data to obtain corrected data:
s3: determining a valid data fusion set of sensors;
and selecting an effective data set by judging the effectiveness of the data corrected by the sensor.
Specifically, the measured data of the same target object obtained by the same sensor k is corrected to obtain a 0k Wherein a is 0k Containing a plurality of measurement data, a 0k ＝{f 0 (k,1),f 0 (k,2),f 0 (k,3)……f 0 (k,i)}，
Calculating the acquisition data a in the sensor k 0k Each measured data in a 0k Of the absolute value Δ l of the difference between the other measurement data ki And further calculates Δ l ki Mean value of k Δl ki A 1 is mixing E k Δl ki Referred to as the mean value of the error of the corrected data for sensor k.
Calculating the error mean values of the correction data of different sensors, further averaging to obtain a data fusion base number lambda after obtaining the error mean values of the correction data of a plurality of sensors,
the data fusion cardinality λ is a standard constant that determines efficient data fusion. The radix λ calculation method is as follows:
according to the above, correcting the data error mean value E k Δl ki <Or when the data of the sensor is determined to be valid data which can be merged.
S4: obtaining a dynamic weight value through similarity measurement;
s401: calculating the Jacard similarity coefficient of the sensor;
in this step, the jaccard similarity coefficient is calculated from the jaccard distance, and a variable weight value is obtained.
Obtaining Jacard similarity of a kth sensor to a (k + 1) th sensorCoefficient R 1 。
In the above formula, G 1 、G 2 、G 3 Representing the number of elements, wherein the number of elements is confirmed according to the following method:
will matrix U 2 Element(s) in (b) and comparison matrix U 3 Corresponding element values are compared, G 1 Indicates the number of elements, G, whose corresponding elements are all 1 2 Representation matrix U 2 The middle element is 1 and the matrix U 3 The corresponding element in (1) is the number of elements of 0, G 3 Representation matrix U 2 The middle element is 0 and the matrix U 3 The corresponding element in (1) is the number of elements.
Similarly, according to the method, the Jacard similarity coefficient R of the kth sensor relative to the (k + 2) th sensor is obtained 2 。
S402: obtaining dynamic weight of the sensor through the Jacard similarity coefficient;
obtaining n-1 relative Jacard similarity coefficients of the kth sensor and calculating an average value to obtain a dynamic weight e of the kth sensor 2 . Since the effective data fusion set of the sensor is determined in the previous step, and the data set exceeding the standard constant of the effective data fusion is screened and excluded, the data discreteness in the step is weak, the standard deviation is small, and the average value of the Jacard similarity coefficient can be used as the dynamic weight e 2 。
S5: calculating a comprehensive weight e for fusing sensor data, and performing weighted fusion on the multi-sensor data according to the comprehensive weight to obtain final fusion data;
calculating the comprehensive weight e:
e＝c*e 1 +(1-c)e 2
wherein c represents a basic weight adjustment coefficient, which is determined according to the particularity and importance degree of the sensor, and generally takes a value of 0.5, the more important the sensor data type is, the larger the value is, and e 1 Represents the basis weight, e 2 Representing a variable weight.
Has the advantages that: according to the method, the accuracy of the input data is ensured by filtering and correcting the acquired data, and the later-period calculated amount is reduced by screening the effective data; according to the data fusion method adopted by the invention, the data weight comprises a basic weight and a dynamic weight, the data fusion weights of different sensors are timely adjusted under different sensing scenes to obtain more accurate sensing data, and the data fusion defect of adopting a fixed fusion weight in the prior art is overcome.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The method of the invention will now be described more fully with reference to the examples, but it is understood that all variations that can be obtained by a person skilled in the art without inventive step based on the method of the invention fall within the scope of protection of the invention.
The multi-sensing data fusion method for the intelligent networked vehicle controller comprises the following steps:
s1: presetting the basic weight of the sensor;
specifically, the method comprises the following steps:
s101: comparing each sensor with other sensors respectively according to an AHP analysis method, and judging the grade of the sensor, wherein the comparison factors mainly comprise the following steps: the sensor precision, detection range and the like are assigned according to the importance level of the data acquired by a certain sensor relative to the data of other sensors.
Assuming that the kth sensor is compared with the (k + 1) th sensor, the importance levels are classified and weighted as follows:
in the above-mentioned assignment table, 1<b 1 <b 2 <b 3 <b 4 <b 5 ，0<b 9 <b 8 <b 7 <b 6 <1
According to the grade empowerment comparison, the kth sensor is compared with other sensors such as k +1, k +2 and the like one by one to obtain a weight matrix U consisting of a plurality of empowerments 1 。
S102: calculating a basic weight;
by calculating a weight matrix U 1 The maximum feature root of the sensor to obtain a corresponding feature vector, which is the basic weight e of the sensor 1 。
S2: filtering and correcting the sensor data acquired by all the sensors;
the specific steps of filtering and correcting comprise:
s201: collecting a data set;
assuming that the number of vehicle sensors capable of monitoring the same target is n, the measurement frequency of each sensor is m, wherein k is more than or equal to 1 and is less than or equal to n, i is more than or equal to 1 and is less than or equal to m, the ith measurement data of the kth sensor is recorded as f (k, i), and a data set a is utilized k Representing all data acquired by the kth sensor, a k (f (k,1), f (k,2), f (k,3) … … f (k, i) … … f (k, m) }. In addition, in a k Several of the same measurement data may appear in (1), such as: f (k,1) ═ f (k, 2).
S202: computing a data set a k The probability P of occurrence of each data f (k, i) in ki ；
According to the probability density function, the raw data f (k, i) and the mean value of the ith and the ith previous s measurement data of the kth sensor
Exist as followsThe relation is as follows:
in the above formula, γ represents a standard deviation of measurement noise, and measurement noise of different sensors is different, and it is determined according to comparison between various actual parameters of a known target and parameters obtained by the sensors and statistical analysis of data. The initial determination can be estimated empirically and later corrected progressively as the collected comparison data increases. The initial estimate may be based on the following equation:
in the above-mentioned formula, the compound of formula,
the mean value of s measurement data of the ith sensor and the ith sensor before the ith sensor is calculated according to a maximum likelihood estimation algorithm, and the calculation method comprises the following steps:
further calculating the i-th and i-th previous s measurement data of the kth sensor in the data set a k The probability of occurrence of (a).
S203: from the raw measurement data f (k, i) and its data at a k Probability of occurrence of P ki Correcting the data to obtain corrected data f 0 (k,i)；
When a plurality of data are collected, correcting the data to obtain corrected data:
s3: determining a valid data fusion set of sensors;
and selecting an effective data set by judging the effectiveness of the data corrected by the sensor.
Specifically, a is obtained by correcting the measurement data of the same target object obtained by the same sensor k 0k Wherein a is 0k Containing a plurality of measurement data, a 0k ＝{f 0 (k,1),f 0 (k,2),f 0 (k,3)……f 0 (k,i)}，
Calculating the acquisition data a in the sensor k 0k Each measured data in a 0k Of the difference between the other measurement data ki And further calculates Δ l ki Mean value of k Δl ki A 1 is mixing E k Δl ki Referred to as the mean value of the error of the corrected data for sensor k.
Calculating the error mean values of the correction data of different sensors, further averaging to obtain a data fusion base number lambda after obtaining the error mean values of the correction data of a plurality of sensors,
the data fusion cardinality λ is a standard constant that determines efficient data fusion. The radix λ calculation method is as follows:
error mean value E of corrected data when k sensor measured data k Δl ki Above λ, the sensor data exceeds the standard constant for valid data fusion and therefore does not belong to fusible data.
According to the above, the data error mean value E is corrected k Δl ki <Or λ, the data of the sensor is determined as valid data which can be fused.
S4: obtaining a dynamic weight value through similarity measurement;
s401: calculating the Jacard similarity coefficient of the sensor;
in this step, the jaccard similarity coefficient is calculated from the jaccard distance, and a variable weight value is obtained.
The jaccard distance measures the discrimination between two sets by the ratio of different elements in the two sets to all elements. Specifically, data (data within a standard constant of valid data fusion) acquired by each sensor at each time is compared with data (data within a standard constant of valid data fusion) acquired by other sensors at the time, comparison results are respectively represented by 1 and 0, wherein 1 represents the same, 0 represents different, for example, a k-th sensor is compared with a k + 1-th sensor and a k + 2-th sensor, and if each sensor performs 3 measurements in total, 3 measurement data are obtained and corrected according to the steps, and a measurement data set acquired by the k-th sensor is corrected to be a i ＝{a 1 ,a 2 ,a 3 And b is obtained after the measurement data set obtained by the (k + 1) th sensor is corrected i ＝{b 1 ,b 2 ,b 3 D is obtained by correcting a measurement data set obtained by the (k + 2) th sensor i ＝{d 1 ,d 2 ,d 3 In turn, the data (corrected) a obtained for the first time by the kth sensor 1 Are each independently of b 1 、d 1 Comparing, and obtaining data a (after correction) for the second time by the kth sensor 2 Are each independently of b 2 、d 2 Making a comparison of 3 Respectively with b 3 、d 3 Comparing, and outputting the comparison result through a number 1 or 0 to obtain a comparison matrix U of the kth sensor 2 The comparison matrix includes the comparison result of the kth sensor and all the measurement data of all the other sensors, and similarly, the comparison matrix U of the kth +1 th sensor can be obtained 3 Comparison matrix U of (k + 2) th sensor 4 。
Acquiring the Jacard similarity coefficient R of the kth sensor relative to the (k + 1) th sensor 1 。
In the above formula, G 1 、G 2 、G 3 Representing the number of elements, wherein the number of elements is confirmed according to the following method:
will matrix U 2 Element(s) in (b) and comparison matrix U 3 Corresponding element values are compared, G 1 Indicates the number of elements whose corresponding elements are all 1, G 2 Representation matrix U 2 The middle element is 1 and the matrix U 3 The corresponding element in (1) is the number of elements of 0, G 3 Representation matrix U 2 The middle element is 0 and the matrix U 3 The corresponding element in (1) is the number of elements.
Similarly, according to the method, the Jacard similarity coefficient R of the kth sensor relative to the (k + 2) th sensor is obtained 2 。
Further, in the comparison method of this step, the partial data appearing in step S3, that is, the data exceeding the standard constant for effective data fusion, is all represented by 0 during comparison.
S402: obtaining dynamic weight of the sensor through the Jacard similarity coefficient;
obtaining n-1 relative Jacobs's similarity coefficients of the kth sensor and calculating an average value to obtain a dynamic weight e of the kth sensor 2 . Since the effective data fusion set of the sensor is determined in the previous step, and the data set exceeding the standard constant of the effective data fusion is screened and excluded, the data discreteness in the step is weak, the standard deviation is small, and the average value of the Jacard similarity coefficient can be used as the dynamic weight e 2 ，
Further, if necessary, the Jacard similarity coefficient of the sensor may be normalized first, and then the dynamic weight may be obtained through mean value calculation.
S5: calculating a sensor fusion comprehensive weight e, and performing weighted fusion calculation on different sensor data according to the comprehensive weight to obtain fusion data of a plurality of sensors;
calculating the comprehensive weight e:
e＝c*e 1 +(1-c)e 2
wherein c represents a basic weight adjustment coefficient, which is determined according to the particularity and the importance degree of the sensor, generally, the value is 0.5, the more important the sensor data type is, the larger the value is, and e 1 Represents the basis weight, e 2 Representing a variable weight. And performing weighted fusion calculation on different sensor data according to the comprehensive weight of each sensor to finally obtain fusion data.
According to the method, the accuracy of the input data is ensured by filtering and correcting the acquired data, and further the later-period calculated amount is reduced by screening the effective data; according to the data fusion method adopted by the invention, the data weight comprises a basic weight and a dynamic weight, and under different perception scenes, the data fusion weights of different sensors are timely adjusted to obtain more accurate perception data.
Claims (1)
1. The multi-sensing data fusion method for the intelligent networked vehicle controller is characterized by comprising the following steps of:
s1: presetting the basic weight of the sensor; the presetting of the basic weight of the sensor in S1 includes:
s101: comparing each sensor with other sensors respectively according to an AHP analysis method, judging the grade of the sensor, and assigning values to the data obtained by a certain sensor according to the importance grade of the data relative to the data of other sensors to obtain a weight matrix U 1 ；
S102: by calculating a weight matrix U 1 The maximum characteristic root of the sensor is obtained to obtain a corresponding characteristic vector which is the basic weight e of the sensor 1 ；
S2: filtering and correcting the sensor data acquired by all the sensors;
s3: determining a valid data fusion set of sensors;
s4: obtaining a dynamic weight value through similarity measurement; the method specifically comprises the following steps:
s401: calculating the Jacard similarity coefficient of the sensor;
the step S401 includes: comparing the data acquired by each sensor with the data acquired by other sensors at the time to obtain multiple comparison matrixes, comparing the corresponding elements in the comparison matrixes to obtain Jacard similarity coefficients,
s402: obtaining dynamic weight of the sensor through the Jacard similarity coefficient;
the S402 includes: obtaining n-1 relative Jacard similarity coefficients of the kth sensor and calculating an average value to obtain a dynamic weight e of the kth sensor 2 Wherein n is the total number of sensors;
s5: calculating a comprehensive weight e, and performing weighted fusion calculation on different sensor data according to the comprehensive weight to obtain fusion data of a plurality of sensors; the calculation method of the comprehensive weight e in the step S5 is as follows:
e＝c*e 1 +(1-c)e 2
wherein c represents a basic weight adjustment coefficient determined according to the specificity and importance of the sensor, e 1 Represents the basis weight, e 2 Representing dynamic weights.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683438.XA CN112003891B (en) | 2020-07-16 | 2020-07-16 | Multi-sensing data fusion method for intelligent networked vehicle controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010683438.XA CN112003891B (en) | 2020-07-16 | 2020-07-16 | Multi-sensing data fusion method for intelligent networked vehicle controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112003891A CN112003891A (en) | 2020-11-27 |
| CN112003891B true CN112003891B (en) | 2022-09-06 |
Family
ID=73467344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010683438.XA Active CN112003891B (en) | 2020-07-16 | 2020-07-16 | Multi-sensing data fusion method for intelligent networked vehicle controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112003891B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022115993A1 (en) * | 2020-12-01 | 2022-06-09 | Robert Bosch Gmbh | Method and apparatus for tuning sensor fusion weights |
| CN113447671B (en) * | 2021-07-15 | 2022-09-23 | 中煤科工集团重庆研究院有限公司 | Roadway section wind speed detection method based on high-frequency and low-frequency ultrasonic waves |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3013834B1 (en) * | 2013-11-28 | 2015-12-25 | Airbus Operations Sas | METHOD FOR MERGING SENSOR DATA USING A COHERENCE CRITERION |
| CN103926564B (en) * | 2014-03-21 | 2016-08-24 | 成都民航空管科技发展有限公司 | A kind of multi-source monitors fusion method and the device of data |
| CN105136264B (en) * | 2015-09-29 | 2017-09-22 | 北京万集科技股份有限公司 | It is a kind of to combine the weight acquisition methods and device, weighing system weighed based on multi-site |
| CN106408983B (en) * | 2016-10-10 | 2019-01-04 | 上海宏英智能科技有限公司 | A kind of Vehicular automatic driving system |
| CN110020394B (en) * | 2017-08-01 | 2023-07-18 | 广州极飞科技股份有限公司 | Data processing method and device |
| CN108573270B (en) * | 2017-12-15 | 2020-04-28 | 上海蔚来汽车有限公司 | Method and apparatus for synchronizing multi-sensor target information fusion and multi-sensor sensing, computer device, and recording medium |
| CN108960334B (en) * | 2018-07-12 | 2021-09-14 | 中国人民解放军陆军炮兵防空兵学院郑州校区 | Multi-sensor data weighting fusion method |
| CN109784664A (en) * | 2018-12-20 | 2019-05-21 | 广东广业开元科技有限公司 | A kind of external dependence degree calculation method, system and device based on changeable weight |
| CN109766958B (en) * | 2019-04-12 | 2019-07-05 | 江苏量动信息科技有限公司 | A kind of data preprocessing method and device for data fusion |
| CN110135952B (en) * | 2019-05-16 | 2022-07-19 | 深圳市梦网视讯有限公司 | Commodity recommendation method and system based on class similarity |
| CN110389971A (en) * | 2019-06-28 | 2019-10-29 | 长春工程学院 | A kind of multi-Sensor Information Fusion Approach based on cloud computing |
| CN110324336B (en) * | 2019-07-02 | 2021-07-30 | 成都信息工程大学 | Internet of vehicles data situation sensing method and device based on network security |
-
2020
- 2020-07-16 CN CN202010683438.XA patent/CN112003891B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112003891A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112003891B (en) | Multi-sensing data fusion method for intelligent networked vehicle controller | |
| CN109131342B (en) | Method and device for measuring speed by fusing acceleration sensor and wheel axle speed sensor | |
| CN117278643B (en) | Vehicle-mounted cloud calibration data transmission system based on cloud edge cooperation | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN107111800B (en) | Part manufacturing method based on analysis of weighted statistical indicators | |
| CN111951430B (en) | Vehicle drivability evaluation method and system | |
| CN116600104B (en) | Phase acquisition quality analysis method and system for IPC network camera | |
| CN110287537B (en) | Wild value resistant self-adaptive Kalman filtering method for frequency standard output jump detection | |
| CN112734858B (en) | Binocular calibration precision online detection method and device | |
| CN111967717A (en) | Data quality evaluation method based on information entropy | |
| CN117349683A (en) | Auto-parts application colour difference anomaly detection system based on spectral data | |
| CN113935535A (en) | Principal component analysis method for medium-and-long-term prediction model | |
| CN109669849B (en) | Complex system health state assessment method based on uncertain depth theory | |
| CN117313020B (en) | Data processing method of bearing type tension sensor | |
| CN110852906A (en) | Method and system for identifying electricity stealing suspicion based on high-dimensional random matrix | |
| US20230214660A1 (en) | Hybrid training method for self-learining algorithms | |
| CN115526276A (en) | Wind tunnel balance calibration load prediction method with robustness | |
| CN113712245B (en) | Cigarette circumference accurate control method | |
| CN107274036B (en) | Crop yield prediction method and system | |
| CN112747773B (en) | Method for improving precision of gyroscope based on Allan variance and random polynomial | |
| CN114897772A (en) | Method for regulating and controlling positive vulcanization of rubber based on machine vision | |
| JP3035089B2 (en) | Process characteristic estimation method and apparatus, process monitoring method and process control method using the estimation method | |
| CN114330553A (en) | Digital acquisition system calibration method based on supervised learning | |
| CN116208152B (en) | High-precision analog quantity acquisition device and method | |
| CN111415715A (en) | Intelligent correction method, system and device based on multivariate spectral data |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220705 Address after: 1406-1, floor 14, building a7-5, Hanyu Golden Valley, No. 7000, Jingshi Road, Jinan area, China (Shandong) pilot Free Trade Zone, Jinan, Shandong Province, 250101 Applicant after: SHANDONG PROMOTE ELECTROMECHANICAL TECHNOLOGY CO.,LTD. Applicant after: Shandong netlink Intelligent Vehicle Industry Technology Research Institute Co.,Ltd. Address before: 250100 No. 1406, 14th floor, Xinlian science and technology building, building a7-5, Hanyu Golden Valley, No. 7000, Jingshi Road, Jinan area, China (Shandong) pilot Free Trade Zone, Jinan, Shandong Province Applicant before: Shandong netlink Intelligent Vehicle Industry Technology Research Institute Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A multi-sensor data fusion method for intelligent networked vehicle controllers Effective date of registration: 20231019 Granted publication date: 20220906 Pledgee: Jinan Branch of Qingdao Bank Co.,Ltd. Pledgor: SHANDONG PROMOTE ELECTROMECHANICAL TECHNOLOGY CO.,LTD. Registration number: Y2023370000116 |