CN108828980A - A kind of mistake is bent away from the prediction technique and system of mental and physical efforts - Google Patents
A kind of mistake is bent away from the prediction technique and system of mental and physical efforts Download PDFInfo
- Publication number
- CN108828980A CN108828980A CN201810460791.4A CN201810460791A CN108828980A CN 108828980 A CN108828980 A CN 108828980A CN 201810460791 A CN201810460791 A CN 201810460791A CN 108828980 A CN108828980 A CN 108828980A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- centrifugal force
- data
- mental
- prediction
- 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.)
- Granted
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
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Tires In General (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The invention discloses a kind of mistakes to be bent away from mental and physical efforts prediction technique and system, belongs to transporting equipment field.A kind of mistake is bent away from the prediction technique of mental and physical efforts, includes the following steps：1, integrate the real-time tire pressure data of vehicle, acceleration information, speed data and torque data；2, integrated data are generated to the feature vector for having timing；3, according to feature vector, the prediction model of training centrifugal force；4, after obtaining prediction model, feature vector is input to prediction model, the predicted value of the centrifugal force of the vehicle of a period of time after acquisition.The present invention passes through the driving sensing data of magnanimity, and data modeling is carried out using a kind of deep neural network of machine learning, the correlativity of current time tire pressure, acceleration, speed and torque with centrifugal force suffered by the vehicle at moment backward is found out, therefrom to achieve the purpose that predict centrifugal force suffered by vehicle.
Description
Technical field
The invention belongs to technical field of vehicle control, more particularly to a kind of mistake is bent away from the prediction technique and system of mental and physical efforts.
Background technique
With the growth of China's container port throughput, the handling efficiency of container is increasingly by harbour operation management person's
Pay attention to.Shortening handling time, while improving the average speed of transporting container vehicle, since tractor and planker are soft company
It connects, planker is loaded with cargo and when excessively curved, and the posture of vehicle vertical direction has a degree of inclination, in order to guarantee vehicle
It will not turn on one's side because of excessive velocities when excessively curved, need velocity and acceleration control when will be excessively curved in the reasonable scope.Therefore
Predicting suffered lateral centrifugal force of carrying vehicle during excessively curved becomes that judge whether vehicle can be stablized excessively curved safely
Important indicator.
Summary of the invention
The invention proposes a kind of mistakes to be bent away from mental and physical efforts prediction technique and system, predicts institute of carrying vehicle during excessively curved
The lateral centrifugal force received.
The present invention can be achieved through the following technical solutions：
A kind of mistake is bent away from the prediction technique of mental and physical efforts, it is characterised in that：Include the following steps：
Step 1：The integrated real-time tire pressure data of vehicle, acceleration information, speed data and torque data；
Step 2：Integrated data are generated to the feature vector for having timing；
Step 3：According to feature vector, the prediction model of training centrifugal force；
Step 4：After obtaining prediction model, feature vector is input to prediction model, the vehicle of a period of time after acquisition
Centrifugal force predicted value.
Further, in step 1 system real-time detection obtain vehicle tire pressure data, acceleration information, speed data and torsion
Square data, and guarantee the markers alignment of each data, step 2 is output to according to the sequencing of timing.
Further, the tire pressure for calculating left and right sides tire in step 2 according to the input data is poor, is laterally centrifuged suffered by vehicle
Power, vehicle load, vehicle acceleration-deceleration, t+1 seconds feature vectors, t+2 seconds feature vectors are combined into, until t+n seconds
Feature vector is output to step 3.
Further, after step 3 inputs feature vector t+1 seconds as the training data of model respectively, after t+2 seconds ..., t+
In the training process of centrifugal force prediction model after n seconds, whether every primary prediction error for training then judgment models of completion restrains,
If a determination be made that not restraining, then continue waiting for next group feature vector, if convergence if by model be output to vehicle from
In mental and physical efforts emulator, emulator is output to step 4.
Further, in the training process of centrifugal force prediction model, model uses the structure of deep neural network, passes through mistake
The value of each parameter in the training method computation model of poor back transfer, the model is by feature input layer, hidden layer and output
Layer composition, feature vector enter from feature input layer, after the kernel function operation of the hidden layer of multilayer, are output to output layer,
Wherein the kernel function of hidden layer is nonlinear continuous derivatived functions.
Further, feature vector is input in vehicle centrifugal force emulator by step 4, passes through latter section of emulator prediction
The centrifugation force value of time is saved at target centrifugal force premeasuring when band, to indicate vehicle t+1 moment suffered by vehicle when excessively curved
The predicted value of centrifugal force, the predicted value of the centrifugal force at t+2 moment, the predicted value of the centrifugal force at t+3 moment ..., the t+n moment
The predicted value of centrifugal force.
A kind of system for the prediction technique being bent away from mental and physical efforts using above-mentioned mistake, it is characterised in that：Including master controller, tire pressure
Sensor, acceleration transducer, velocity sensor and torque sensor, it is the tyre pressure sensor, the velocity sensor, described
Acceleration transducer and the torque sensor are connected with the master controller respectively, and master controller receives each sensor signal,
According to real-time tire pressure, acceleration, speed and torque data, training centrifugal force prediction model is predicted using obtained centrifugal force
Model, the mistake of the vehicle of a period of time is bent away from mental and physical efforts after prediction.
Further, the tyre pressure sensor be arranged in front left, front right, rear left, on the tire in rear right bit.
Further, the acceleration transducer include the traveling acceleration transducer for being parallel to vehicle heading, it is vertical
In vehicle heading and it is parallel to the lateral acceleration sensor on ground, the traveling acceleration transducer laterally accelerates
Degree sensor is connected with master controller respectively.
Beneficial effect
Technical solution of the present invention passes through the driving sensing data of magnanimity, and utilizes a kind of depth of machine learning nerve
Network carries out data modeling, therefrom find out current time tire pressure, acceleration, speed and torque and moment backward vehicle it is suffered from
The correlativity of mental and physical efforts achievees the purpose that predict centrifugal force suffered by vehicle；The present invention is predicted by the way of deep learning modeling
Centrifugal force suffered by vehicle changes the existing control lag being modified based on measurement data, can be to the centrifugal force of vehicle
It is predicted, the safety of vehicle driving turning process can not only be improved, and can control driving procedure and auxiliary is provided.
Detailed description of the invention
Fig. 1 is the flow chart that centrifugal force of the invention is predicted；
Fig. 2 is the flow chart of prediction model training of the invention；
Fig. 3 is the schematic diagram of deep neural network of the invention；
Fig. 4 is the flow chart of centrifugal force predictor calculation of the invention；
Fig. 5 is crossed for vehicle of the invention and is bent through the schematic diagram that journey corresponds to centrifugal force predicted value；
Fig. 6 is system structure diagram of the invention.
Specific embodiment
The present invention can be more clearly understood according to following detailed description in conjunction with attached drawing.
This system is generated, centrifugal force prediction model based on the data that vehicle control platform acquires by feature vector
After centrifugal force prediction, the predicted value of the lateral direction of car centrifugal force of a period of time is obtained.
System includes master controller 5, tyre pressure sensor 6, acceleration transducer 7, velocity sensor 8 and torque sensor 9,
The tyre pressure sensor 6, the velocity sensor 8, the acceleration transducer 7 and the torque sensor 9 respectively with it is described
Master controller 5 is connected, and 5 receiving sensor signal of master controller obtains real-time tire pressure, acceleration, speed and torque data.Add
Velocity sensor 7 includes the traveling acceleration transducer for being parallel to vehicle heading, perpendicular to vehicle heading and parallel
Lateral acceleration sensor in ground, the traveling acceleration transducer, lateral acceleration sensor respectively with main control
Device 5 is connected.
Master controller in this programme uses the platform architecture processor of X86, runs linux operating system, and can load
Run toy data base software and other required middleware softwares.
Mainly connected by the way of the agreement of CANBUS2.0 between this programme and external sensor and controller
It connects.
Tyre pressure sensor 6 be separately mounted to tractor it is left front, left back, right before, it is right after tire in or tractor and
Planker it is left front, left back, right before, it is right after tire in, acquire real-time tire pressure data and be returned to controller.
Tire pressure data in this programme are directly to carry out wheel nausea using the pressure sensor for being mounted on each wheel tyre cavity
The measurement of pressure, and Vehicle Controller tire pressure detection unit is sent from inside tires for pressure information by wireless transmitter
(TPMS) it realizes, is then passed through in CANUSB2.0 bus transfer to master controller by tie pressure detection module.
Tire pressure data in this programme need to include front left, front right, rear left, the pressure data of the tire in rear right bit.
Lateral acceleration sensor is mounted on the chassis of tractor or planker, acquires real-time vehicle lateral acceleration data
It is returned to controller, controller centrifugal force according to suffered by lateral acceleration data calculating trailer.
Traveling acceleration transducer is mounted on traction chassis, and velocity sensor is mounted on trailer wheel, and acquisition is real-time
Vehicle heading acceleration and speed data be returned to controller, controller calculates vehicle according to acceleration and speed data
Load-carrying.
In order to obtain accurate acceleration signal and angular velocity data in real time, the present embodiment has imported inertial measuring unit
(IMU) unit (acceleration transducer 7).Master controller acquires inertia in real time and surveys by being directly connected to inertial measuring unit
Measure the traveling acceleration information fed back in device, the related angular velocity data on lateral acceleration data and all directions.
Communication between master controller 5 and inertial measuring unit (acceleration transducer 7) uses CANBUS2.0 agreement.
Velocity sensor 8 is the device for detecting vehicle speed, and the output signal of vehicle speed sensor can be magneto-electric
AC signal, be also possible to Hall-type digital signal either photo-electric digital signal.
Speed signal in this programme arises directly from any one of above-mentioned signal, and master controller passes through rectification acquisition side
Wave signal, then square wave quantity in calculating cycle obtains instantaneous car speed again.
Torque sensor 9 is mounted on the outlet side of electric engine or driving motor, acquires real-time torque data and passes control back
Device processed, controller calculate the acceleration-deceleration of vehicle.
Engine torque (torque sensor 9) in this programme, after obtaining relevant data by vehicle control platform, and
Actual torque data is obtained by calculating.
Torque data is by vehicle control platform, by CANBUS2.0 bus real-time Transmission to master controller 5.Vehicle control
The concerned brake subsystem or vehicle control platform of platform itself is indicated with main reducing gear 10.
System after obtaining tire pressure data, acceleration information, speed data, torque data using above-mentioned apparatus, work as by calculating
The tire pressure of the left and right sides tire at preceding moment is poor, the acceleration-deceleration of transverse direction centrifugal force suffered by vehicle, vehicle load, vehicle.From history
The tire pressure for obtaining past tire pressure data, acceleration information, speed data, torque data and left and right sides tire in library is poor, vehicle
The data such as acceleration-deceleration of transverse direction centrifugal force, vehicle load, vehicle suffered by are combined into t+1 seconds feature vectors, t+2 seconds spies
Vector is levied, until t+n seconds feature vectors.
After being separately input to t+1 seconds according to marking when feature vector, after t+2 seconds ..., the prediction of centrifugal force after t+n seconds
The feature input layer of model is output to output layer by the non-linear conversion of hidden layer 1 to n, wherein non-linear turn of hidden layer
Change kernel function completion, kernel function is using non-linear and continuous guidable function, in non-linear conversion process, the parameter of kernel function
Use last round of updated parameter.
In training process, the output valve of output layer is the predicted value of centrifugal force suffered by vehicle, by predicted value and measured value
Error successively updates the parameter of kernel function by way of error back propagation since hidden layer n, until hidden layer 1.
After completing a wheel training, judge whether the Parameters variation for updating the hidden layer kernel function of front and back restrains, if do not received
It holds back, continues waiting for next group feature vector, the parameter of the kernel function of each model is output to vehicle centrifugation if having restrained
In power emulator.
After having obtained parameter convergent prediction model, input parameter is input to the input layer of vehicle centrifugal force emulator,
The output valve of output layer is obtained after hidden layer non-linear conversion, the parameter of kernel function used in conversion process is using
Convergent model parameter, output valve be vehicle t+1 moment to the t+n moment centrifugal force predicted value, the calculating process of emulator with
The difference of the training process of prediction model is that the calculating process of emulator updates core letter without using the method for error back propagation
Several parameter, to realize transverse direction centrifugal force suffered by the excessively curved vehicle at multiple moment in the process of prediction vehicle.
Embodiment 1
Master controller 5 after vehicle speed data, calculates current obtaining tire pressure data, acceleration information, torque data in real time
The tire pressure of the left and right sides tire of t moment is poor, the acceleration-deceleration of transverse direction centrifugal force suffered by vehicle, vehicle load, vehicle, and numerical value is returned
One changes to being written to Redis database after 0.2~0.6.
T moment is obtained from Redis database to the tire pressure at t-10 moment, acceleration, torque, speed, left and right sides tire
Tire pressure is poor, difference, the 2 power values, 3 of transverse direction centrifugal force suffered by vehicle, vehicle load, the acceleration-deceleration of vehicle and this tittle
Power value is input to the feature input layer of prediction model as input feature value, and hidden layer uses sigmoid function as core
Function, as a result the predicted value of centrifugal force was output to the output layer of prediction model by the conversion of hidden layer, as t+1 seconds vehicles
The predicted value of transverse direction centrifugal force suffered by.
It is laterally centrifuged suffered by vehicle after calculating transverse direction centrifugal force suffered by the vehicle for obtaining t+1 seconds as t+1 seconds
Power measured value is updated in prediction model using the error backpropagation algorithm that Rumelhart was proposed in 1986 and is owned
The parameter of sigmoid function judges that parameter has restrained after the absolute value of the variable quantity of parameter is less than 1E-10, it is believed that mould
Trained completion is output in vehicle centrifugal force emulator type.
When carrying out actual prediction using the model that training is completed, equally by real-time tire pressure data, acceleration information, torque number
According to after vehicle speed data, the tire pressure for calculating the left and right sides tire of current t moment is poor, transverse direction centrifugal force suffered by vehicle, vehicle carry
The acceleration-deceleration of weight, vehicle, is written to Redis database, obtains from Redis database after numerical value is normalized to 0.2~0.6
Take t moment to the tire pressure at t-10 moment, acceleration, torque, speed, the tire pressure of left and right sides tire are poor, are laterally centrifuged suffered by vehicle
Power, vehicle load, difference, 2 power values, the 3 power values of the acceleration-deceleration of vehicle and this tittle are defeated as input feature value
Enter the feature input layer to prediction model, hidden layer uses sigmoid function as kernel function, and the as a result conversion of hidden layer will be from
The predicted value of mental and physical efforts is output to the output layer of prediction model, as the predicted value of transverse direction centrifugal force suffered by t+1 seconds vehicles
And it is recorded in Redis database.
Technical solution of the present invention passes through the driving sensing data of magnanimity, and utilizes a kind of depth of machine learning nerve
Network carries out data modeling, therefrom find out current time tire pressure, acceleration, speed and torque and moment backward vehicle it is suffered from
The correlativity of mental and physical efforts achievees the purpose that predict centrifugal force suffered by vehicle；The present invention is predicted by the way of deep learning modeling
Centrifugal force suffered by vehicle changes the existing control lag being modified based on measurement data, can be to the centrifugal force of vehicle
It is predicted, the safety of vehicle driving turning process can not only be improved, and can control driving procedure and auxiliary is provided.
According to the disclosure and teachings of the above specification, this patent those skilled in the art can also be to above-mentioned embodiment party
Formula is changed and is modified.Therefore, the invention is not limited to above-mentioned specific embodiment, all those skilled in the art exist
Made any conspicuous improvement, replacement or modification all belong to the scope of protection of the present invention on the basis of the present invention.
In addition, these terms are merely for convenience of description although using some specific terms in this specification, and
Any restrictions are not constituted to this patent.
Claims (9)
1. the prediction technique that a kind of mistake is bent away from mental and physical efforts, it is characterised in that：Include the following steps：
Step 1：The integrated real-time tire pressure data of vehicle, acceleration information, speed data and torque data；
Step 2：Integrated data are generated to the feature vector for having timing；
Step 3：According to feature vector, the prediction model of training centrifugal force；
Step 4：Obtain prediction model after, feature vector is input to prediction model, after acquisition the vehicle of a period of time from
The predicted value of mental and physical efforts.
2. the prediction technique that mistake as described in claim 1 is bent away from mental and physical efforts, it is characterised in that：System real-time detection obtains in step 1
Tire pressure data, acceleration information, speed data and the torque data of vehicle are obtained, and guarantees the markers alignment of each data, according to
The sequencing of timing is output to step 2.
3. the prediction technique that mistake as described in claim 1 is bent away from mental and physical efforts, it is characterised in that：In step 2 according to the input data
Calculate left and right sides tire tire pressure is poor, the acceleration-deceleration of transverse direction centrifugal force suffered by vehicle, vehicle load, vehicle, be combined into t+1 seconds
Feature vector, t+2 seconds feature vectors, the feature vector until t+n seconds is output to step 3.
4. the prediction technique that mistake as claimed in claim 3 is bent away from mental and physical efforts, it is characterised in that：Step 3 is using feature vector as mould
The training data (31) of type input t+1 seconds respectively after, after t+2 seconds ..., the training process of centrifugal force prediction model after t+n seconds
In (32), then whether judgment models restrain (33) for every primary training of completion, i.e. whether the prediction error of model restrains, if it is determined that
The result is that not restraining, then next group feature vector is continued waiting for, model is output to the emulation of vehicle centrifugal force if convergence
In device (34), emulator is output to step 4.
5. the prediction technique that mistake as claimed in claim 4 is bent away from mental and physical efforts, it is characterised in that：In the training of centrifugal force prediction model
(32) in the process, model use the structure of deep neural network, by each in the training method computation model of Feedback error
The value of a parameter, the model are made of feature input layer (321), hidden layer (322) and output layer (323), feature vector from
Feature input layer (321) enters, and after the kernel function operation of the hidden layer of multilayer, output layer (323) is output to, wherein hiding
The kernel function of layer is nonlinear continuous derivatived functions.
6. the prediction technique that mistake as claimed in claim 4 is bent away from mental and physical efforts, it is characterised in that：Step 4 input feature value first
(41) into vehicle centrifugal force emulator (42), the centrifugation force value of a period of time after being predicted by emulator, when saving into band
Target centrifugal force premeasuring (43), to indicate vehicle predicted value of the centrifugal force at t+1 moment, t+2 suffered by vehicle when excessively curved
The predicted value of the centrifugal force at moment, the predicted value of the centrifugal force at t+3 moment ..., the predicted value of the centrifugal force at t+n moment.
7. a kind of system for the prediction technique for applying mistake as described in claim 1 to be bent away from mental and physical efforts, it is characterised in that：Including master control
Device (5), tyre pressure sensor (6), acceleration transducer (7), velocity sensor (8) and torque sensor (9) processed, the tire pressure pass
Sensor (6), the velocity sensor (8), the acceleration transducer (7) and the torque sensor (9) respectively with the master
Controller (5) is connected, and master controller (5) receives each sensor signal, according to real-time tire pressure, acceleration, speed and torque number
According to training centrifugal force prediction model, using obtained centrifugal force prediction model, the mistake of the vehicle of a period of time is bent away from the heart after prediction
Power.
8. system as claimed in claim 7, it is characterised in that：The tyre pressure sensor (6) setting front left, front right, rear left,
Afterwards on the tire in right bit.
9. system as claimed in claim 7, it is characterised in that：The acceleration transducer (7) includes being parallel to vehicle driving
The traveling acceleration transducer in direction perpendicular to vehicle heading and is parallel to the lateral acceleration sensor on ground, described
Traveling acceleration transducer, lateral acceleration sensor is connected with master controller (5) respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810460791.4A CN108828980B (en) | 2018-05-15 | 2018-05-15 | Method and system for predicting over-bending centrifugal force |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810460791.4A CN108828980B (en) | 2018-05-15 | 2018-05-15 | Method and system for predicting over-bending centrifugal force |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108828980A true CN108828980A (en) | 2018-11-16 |
| CN108828980B CN108828980B (en) | 2021-06-11 |
Family
ID=64148731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810460791.4A Active CN108828980B (en) | 2018-05-15 | 2018-05-15 | Method and system for predicting over-bending centrifugal force |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108828980B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111547044A (en) * | 2020-03-31 | 2020-08-18 | 桂林电子科技大学 | Truck curve automatic driving training method and system |
| CN114234972A (en) * | 2022-03-01 | 2022-03-25 | 长沙金维信息技术有限公司 | Inertial navigation method for inertial navigation system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1749722A1 (en) * | 2005-08-01 | 2007-02-07 | Delphi Technologies, Inc. | Rollover warning and detection method for transport vehicles |
| CN101027961A (en) * | 2006-03-01 | 2007-09-05 | 株式会社久保田 | Detecting device and controlling device for working vehicle postures |
| JP4244453B2 (en) * | 1999-07-21 | 2009-03-25 | 株式会社デンソー | Body slip angle estimation method and apparatus |
| CN102556160A (en) * | 2010-12-29 | 2012-07-11 | 天津市友达机电液成套设备有限公司 | Turning radius display and vehicle speed alarm method for wheeled vehicle and device thereof |
| CN102923024A (en) * | 2011-08-08 | 2013-02-13 | 林其禹 | Fully autonomous seat system for automobile and execution method for fully autonomous seat system for automobile |
| CN105117524A (en) * | 2015-07-30 | 2015-12-02 | 西安航空制动科技有限公司 | Dynamic simulation method of using differential braking to control aircraft turning process |
| CN106494406A (en) * | 2015-09-08 | 2017-03-15 | 星克跃尔株式会社 | Bend guidance method, bend guider, electronic installation and program |
| CN107972672A (en) * | 2016-10-21 | 2018-05-01 | 奥迪股份公司 | Drive assist system and driving assistance method |
-
2018
- 2018-05-15 CN CN201810460791.4A patent/CN108828980B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4244453B2 (en) * | 1999-07-21 | 2009-03-25 | 株式会社デンソー | Body slip angle estimation method and apparatus |
| EP1749722A1 (en) * | 2005-08-01 | 2007-02-07 | Delphi Technologies, Inc. | Rollover warning and detection method for transport vehicles |
| CN101027961A (en) * | 2006-03-01 | 2007-09-05 | 株式会社久保田 | Detecting device and controlling device for working vehicle postures |
| CN102556160A (en) * | 2010-12-29 | 2012-07-11 | 天津市友达机电液成套设备有限公司 | Turning radius display and vehicle speed alarm method for wheeled vehicle and device thereof |
| CN102923024A (en) * | 2011-08-08 | 2013-02-13 | 林其禹 | Fully autonomous seat system for automobile and execution method for fully autonomous seat system for automobile |
| CN105117524A (en) * | 2015-07-30 | 2015-12-02 | 西安航空制动科技有限公司 | Dynamic simulation method of using differential braking to control aircraft turning process |
| CN106494406A (en) * | 2015-09-08 | 2017-03-15 | 星克跃尔株式会社 | Bend guidance method, bend guider, electronic installation and program |
| CN107972672A (en) * | 2016-10-21 | 2018-05-01 | 奥迪股份公司 | Drive assist system and driving assistance method |
Non-Patent Citations (1)
| Title |
|---|
| 未显示: "数学建模神经网络预测模型及程序", 《百度文库》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111547044A (en) * | 2020-03-31 | 2020-08-18 | 桂林电子科技大学 | Truck curve automatic driving training method and system |
| CN111547044B (en) * | 2020-03-31 | 2022-01-28 | 桂林电子科技大学 | Truck curve automatic driving training method and system |
| CN114234972A (en) * | 2022-03-01 | 2022-03-25 | 长沙金维信息技术有限公司 | Inertial navigation method for inertial navigation system |
| CN114234972B (en) * | 2022-03-01 | 2022-05-24 | 长沙金维信息技术有限公司 | Inertial navigation method for inertial navigation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108828980B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2882232B2 (en) | Vehicle weight center slip angle measuring device | |
| CN111152795B (en) | Model and parameter dynamic adjustment based adaptive vehicle state prediction system and prediction method | |
| CN109606378A (en) | Vehicle running state estimation method towards non-Gaussian noise environment | |
| CN103661393B (en) | Kinematic road gradient is estimated | |
| US20090177346A1 (en) | Dynamic estimation of vehicle inertial parameters and tire forces from tire sensors | |
| Doumiati et al. | A method to estimate the lateral tire force and the sideslip angle of a vehicle: Experimental validation | |
| CN104742888B (en) | Drive full a reference speed real-time detection method | |
| CN111547059A (en) | Distributed driving electric automobile inertia parameter estimation method | |
| CN106394561A (en) | Estimation method and device for longitudinal vehicle speed of vehicle | |
| CN107585207B (en) | A kind of vehicle line traffic control four-wheel steering system and its control method | |
| CN110884499B (en) | Method and system for determining vehicle mass center slip angle | |
| CN108828980A (en) | A kind of mistake is bent away from the prediction technique and system of mental and physical efforts | |
| CN104864949B (en) | A kind of dynamic weighting method for vehicle and device | |
| CN101378935A (en) | Roll over judgment device | |
| CN115798078A (en) | Vehicle accurate fault diagnosis method and device | |
| CN104773190A (en) | Auxiliary traction control system for train | |
| CN110687907A (en) | Intelligent automobile decoupling prediction controller based on model dynamic reconstruction and control method thereof | |
| CN110435564A (en) | Determine vehicle drive behavior | |
| CN109204318A (en) | A kind of method and terminal device of the rapidly lane change of judgement vehicle | |
| CN115432009A (en) | Automatic driving vehicle trajectory tracking control system | |
| EP4166410A1 (en) | Vehicle control method and apparatus, computer-readable storage medium, and electronic device | |
| CN105059285A (en) | Distributed driving automobile integrated control system and method based on multiple intelligent agents | |
| CN109693653A (en) | A kind of anti-skidding protection control method of locomotive axle | |
| CN108426673A (en) | A kind of emergency management and rescue vehicle centroid position measures and method of adjustment | |
| CN108973847A (en) | A kind of haulage vehicle Anti-side-turning device and its application 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220907 Address after: Room 643, 999 Changning Road, Changning District, Shanghai 200050 Patentee after: SHANGHAI WISDOM INFORMATION TECHNOLOGY CO.,LTD. Address before: No.163 Haibin Middle Road, Haiyang City, Yantai City, Shandong Province Patentee before: MACHINERY TECHNOLOGY (SHAN DONG) HEAVY INDUSTRY Co.,Ltd. Patentee before: SHANGHAI WISDOM INFORMATION TECHNOLOGY CO.,LTD. |