CN104932505A - Automatic navigation system based on camera detection, control method of system and vertical balance car - Google Patents
Automatic navigation system based on camera detection, control method of system and vertical balance car Download PDFInfo
- Publication number
- CN104932505A CN104932505A CN201510308759.0A CN201510308759A CN104932505A CN 104932505 A CN104932505 A CN 104932505A CN 201510308759 A CN201510308759 A CN 201510308759A CN 104932505 A CN104932505 A CN 104932505A
- Authority
- CN
- China
- Prior art keywords
- data
- embedded computer
- runway
- camera
- navigation system
- 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
Landscapes
- Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an automatic navigation system based on camera detection, a control method of the system and a vertical balance car. The system comprises a vertical balance data collection module, a camera data collection module and a signal processing and control module, wherein the vertical balance data collection module and the camera data collection module are connected with the signal processing and control module, the vertical balance data collection data obtains present attitude angle data of the vertical balance car, the camera data collection module collects gray-level image data of a runway, and the signal processing and control module collects, stores and processes the gray-level image data of the runway, the present attitude angle data of the vertical balance car, and present speed and differential speed data of the vertical balance car, and controls the balance of the vertical balance car according to the present attitude angle data of the vertical balance car. Thus, the road condition in front can be effective predicted, prediction can be controlled more effectively, and the control precision is improved.
Description
Technical field
The present invention relates to a kind of automated navigation system, especially a kind of automated navigation system, control method and vertical balanced car detected based on camera, belongs to the technical fields such as infotech, automatic technology, automatic navigation technology, self-equilibrating technology.
Background technology
Automatic navigation technology is one of focus of studying of people always, the many employings 1 of automatic navigation technology system traditional at present) gps system navigation 2) photoelectric sensor 3) electromagnetic sensor; Adopt the system of GPS navigation, due to civilian GPS positioning precision and the restriction of data sample rates, often there is the phenomenon of " drift ", cause that control hysteresis, control accuracy are low, the consequence of poor real; Photoelectric sensor and electromagnetic sensor is adopted to carry out the system of navigating, although its sampling rate is higher, good measuring accuracy, but photoelectric sensor and electromagnetic sensor are " line " " point " formulas to be measured, namely " one-dimensional " is measured, can not measure the global feature of road pavement, cause system can only measure current road state and be difficult to obtain following pavement state.
Tradition Self-Balancing vehicle adopts 8 single-chip microcomputers of 8MHz, and operational precision is low, arithmetic speed is slow, sampling rate is slow.Meanwhile, current automated navigation system is applied on brougham more, and brougham, by the characteristic of its four-wheel, determines it and moves un-skill, to turn to inconvenience feature.
Along with the development of Self-Balancing vehicle technology, Self-Balancing vehicle plays the part of important role by many occasions, but the Self-Balancing vehicle technology using camera to carry out self-navigation still belongs to blank.In addition, the single-axis attitude algorithm that traditional Self-Balancing vehicle adopts is slightly inadequate in security compared with three-axis attitude algorithm.
Summary of the invention
First object of the present invention is the defect in order to solve above-mentioned prior art, and provide a kind of automated navigation system detected based on camera, this system can effectively predict front road conditions, carries out more effective PREDICTIVE CONTROL, improves control accuracy.
Second object of the present invention is the control method providing a kind of above-mentioned automated navigation system.
3rd object of the present invention is to provide a kind of vertical balanced car.
First object of the present invention can reach by taking following technical scheme:
Based on the automated navigation system that camera detects, described system comprises vertical balanced data acquisition module, camera data acquisition module and signal transacting and control module, and described vertical balanced data acquisition module, camera data acquisition module are connected with signal transacting and control module respectively; Wherein:
Described vertical balanced data acquisition module, for the current pose angular data of data acquisition vertical balanced car gathered by IMU sensor;
Described camera data acquisition module, for gathering the greyscale image data of runway by camera sensing device;
Described signal transacting and control module, for being collected by embedded computer, the greyscale image data of Storage and Processing runway, the current pose angular data of vertical balanced car, the current vehicle speed of vertical balanced car and differential data, and according to the current pose angular data of vertical balanced car, balance is carried out to vertical balanced car and controls.
As a kind of preferred version, described signal transacting and control module comprise:
Balance control module, for according to the current pose angular data obtained, carries out balance to vertical balanced car and controls;
Graphics processing unit, for carrying out computing to the runway greyscale image data gathered.
As a kind of preferred version, described IMU sensor is made up of L3G4200 gyroscope and MMA8451 accelerometer, and described gyroscope is connected with embedded computer by iic bus with accelerometer.
As a kind of preferred version, described camera sensing device adopts imageing sensor OV7620, and is connected with embedded computer by DMA passage.
As a kind of preferred version, described embedded computer adopts Freescale company Kinetis MK60DN512 Series MCU to form.
Second object of the present invention can reach by taking following technical scheme:
Based on the control method of above-mentioned automated navigation system, described method comprises:
In S1, IMU sensor, the data of gyroscope and accelerometer input embedded computer by iic bus, embedded computer is by the inverse trigonometric function computing to accelerometer data, in conjunction with the integration data of gyro data, carry out first-order low-pass ripple, obtain working as previous belief, calculate the current pose angular data of vertical balanced car; Meanwhile, the data input embedded computer of camera sensing device, obtains the greyscale image data of runway;
S2, in embedded computer, the attitude angle data that calculated by embedded computer of balance control module substitutes into PID controller, and the balance that the motor rotation controlling vertical balanced car realizes vertical balanced car controls; Simultaneously, graphics processing unit carries out Dynamic Binarization process to the runway greyscale image data that embedded computer obtains, identify that specifically to use with black line be the runway at edge, by carrying out edge feature calculating to the border of runway, obtain the road conditions of runway, and send differential signal to the motor of vertical balanced car by embedded computer, thus real-time follow-up track.
As a kind of preferred version, embedded computer resolving attitude angle data described in step S1, specific as follows:
Static attitude angle is resolved by following formulae discovery, and the attitude angle calculated is roll angle, the angle of pitch two attitudes:
Wherein, a
x, a
y, a
zfor orthogonal 3-axis acceleration data,
for the static angle of pitch, ρ
ofor static roll angle, a is set
yorthogonal with motor shaft, then effectively static attitude angular data is
angle;
Add gyro data ω and do dynamic data combining, get ω
xparallel with motor shaft, then the dynamic angle of pitch after merging is:
Wherein, Confidence
gyrofor gyrostatic degree of confidence, Confidence
accefor the degree of confidence of accelerometer.
As a kind of preferred version, PID controller described in step S2 is by following formulae discovery:
Wherein, K
pfor controller proportional gain factor, K
ifor controller integral coefficient, K
dfor controller differential coefficient, e is error;
Use during Embedded computer system and make discretize:
Wherein, e is the numerical value that attitude angle departs from balance angle, and u is the dutycycle directly outputting to motor, e
kand e
k-1represent the deviation in k and k-1 moment respectively.
As a kind of preferred version, Dynamic Binarization described in step S2 adopts Bernsen algorithm, and this Bernsen arthmetic statement is as follows:
Wherein, f (i, j) is for image is at the gray-scale value at pixel (i, j) place, and T (i, j) is the binary-state threshold of each pixel (i, j) in image;
Carry out binaryzation to pixel (i, j) each in image with b (i, the j) pointwise of binaryzation function, b (i, j) function is as follows:
Image after binaryzation, its runway edge, by having a strong rising edge, namely identifies runway edge by the saltus step of this rising edge of embedded computer identification.
3rd object of the present invention can reach by taking following technical scheme:
Vertical balanced car, comprises car body, left wheel, right wheel and motor, and described left wheel and right wheel are arranged on the both sides, bottom of car body, and described driven by motor left wheel and right wheel movement, also comprise above-mentioned automated navigation system; Wherein, described IMU sensor and embedded computer are arranged in car body, and described camera sensing device is arranged on car body top, and described embedded computer is connected with motor.
The present invention has following beneficial effect relative to prior art:
1, automated navigation system of the present invention adopts camera to carry out the navigation of plane formula, can effectively predict front road conditions, carries out more effective PREDICTIVE CONTROL, improves control accuracy; In addition, have benefited from the sampling rate of IMU sensor and the processing speed of embedded computer, control accuracy also significantly improves.
2, automated navigation system of the present invention can carry out Dynamic Binarization process to the runway greyscale image data obtained, identify that specifically to use with black line be the runway at edge, by the feature calculation to runway, the road conditions such as the steering characteristic that must go off the course, linear feature, cross characteristics, and send differential signal by embedded computer to the motor of vertical balanced car, real-time detecting and tracking can be carried out to given runway.
3, automated navigation system of the present invention can be applied on vertical balanced car, compared with traditional brougham, lighter, dexterous, and in energy consumption, and due to the own characteristic of vertical balanced car, its energy consumption is also low than brougham comparatively speaking.
4, light, the safety of vertical balanced car of the present invention, environmental protection, owing to applying automated navigation system, runway can be detected in real time, there is the advantage that recognition effect is good, tracking velocity is high and real-time, and adopt the upright algorithm of balance and image processing algorithm is efficiently convenient, practicability and effectiveness.
Accompanying drawing explanation
Fig. 1 is the automated navigation system structured flowchart of the embodiment of the present invention 1.
Fig. 2 is the inclination angle fusion results figure of the embodiment of the present invention 1.
Fig. 3 is the inverted pendulum model figure of the embodiment of the present invention 1.
Fig. 4 is the medium filtering process flow diagram of the embodiment of the present invention 1.
Fig. 5 is the Bernsen algorithm flow chart of the embodiment of the present invention 1.
The former figure of runway image that Fig. 6 obtains for the embodiment of the present invention 1.
Fig. 7 is the runway image of the embodiment of the present invention 1 after Bernsen algorithm process.
Fig. 8 is the vertical balanced bassinet structure schematic diagram of the embodiment of the present invention 2.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited thereto.
Embodiment 1:
As shown in Figure 1, the automated navigation system of the present embodiment comprises vertical balanced data acquisition module, camera data acquisition module and signal transacting and control module, and described vertical balanced data acquisition module, camera data acquisition module are connected with signal transacting and control module respectively;
Described vertical balanced data acquisition module, for the current pose angular data of data acquisition vertical balanced car gathered by IMU sensor;
Described camera data acquisition module, for gathering the greyscale image data of runway by camera sensing device;
Described signal transacting and control module, for being collected by embedded computer, the greyscale image data of Storage and Processing runway, the current pose angular data of vertical balanced car, the current vehicle speed of vertical balanced car and differential data, and according to the current pose angular data of vertical balanced car, balance is carried out to vertical balanced car and controls; It can comprise:
Balance control module, for according to the current pose angular data obtained, carries out balance to vertical balanced car and controls;
Graphics processing unit, for carrying out computing to the runway greyscale image data gathered.
Described embedded computer adopts Freescale company Kinetis MK60DN512 Series MCU to form; Above-mentioned IMU sensor is made up of L3G4200 gyroscope and MMA8451 accelerometer, and described gyroscope is connected with embedded computer by iic bus with accelerometer; Described camera sensing device adopts imageing sensor OV7620.
The control procedure of the automated navigation system of the present embodiment is as follows:
In S1, IMU sensor, the data of gyroscope and accelerometer input embedded computer by iic bus, embedded computer is by the inverse trigonometric function computing to accelerometer data, in conjunction with the integration data of gyro data, carry out first-order low-pass ripple, obtain working as previous belief, calculate the current pose angular data of vertical balanced car; Meanwhile, the data input embedded computer of camera sensing device, obtains the greyscale image data of runway;
S11, embedded computer resolving attitude angle data, specific as follows:
1) static attitude angle is resolved by following formulae discovery, and the attitude angle calculated is roll angle, the angle of pitch two attitudes:
Wherein, a
x, a
y, a
zfor orthogonal 3-axis acceleration data,
for the static angle of pitch, ρ
ofor static roll angle, a is set
yorthogonal with motor shaft, then effectively static attitude angular data is
angle;
2) static attitude angular data is comparatively large at dynamic time-harmonic wave noise, should add gyro data ω thus and do dynamic data combining; Get ω
xparallel with motor shaft, then the dynamic angle of pitch after merging is:
Wherein, Confidence
gyrofor gyrostatic degree of confidence, Confidence
accefor the degree of confidence of accelerometer, the degree of confidence of usually getting accelerometer is 5%, and gyroscope degree of confidence is 95%, and degree of confidence refers to the credibility of the measured value of measured parameter;
As shown in Figure 2, input signal is the data waveform obtained as stated above+angular signal of-90 °, can see, can obtain reasonable effect according to the method described above from waveform.
S2, in embedded computer, the attitude angle data that calculated by embedded computer of balance control module substitutes into PID controller, and the balance that the motor rotation controlling vertical balanced car realizes vertical balanced car controls; Simultaneously, graphics processing unit carries out Dynamic Binarization process to the runway greyscale image data that embedded computer obtains, identify that specifically to use with black line be the runway at edge, by carrying out edge feature calculating to the border of runway, obtain the road conditions such as the steering characteristic of runway, linear feature, cross characteristics, and send differential signal to the motor of vertical balanced car by embedded computer, thus real-time follow-up track.
The attitude angle data that embedded computer calculates by S21, balance control module substitutes into PID controller, is specially:
1) reversible pendulum system is modeled as to vertical balanced car, as shown in Figure 3.
According to stress balance, the restoring force suffered by inverted pendulum is:
F=mg*sinθ-ma*cosθ
Near working point, θ very little (≈ 0), therefore near working point, doing linearization process to above-mentioned equation, then above-mentioned equation turns to:
F=mgθ-mk
1θ
Consider the factors such as air resistance, then must add a damping force, this damping force direction should be consistent with inverted pendulum angular velocity direction, then after considering damping force factor, restoring force is:
F=mgθ-mk
1θ-mk
2θ′
Suppose that power of motor is enough large, then motor input voltage and Driving Torque power are approximated to linear relationship:
F=k
3*u
Associating above formula obtains
u=k
1*θ+k
2*θ′
Therefore show that the relation controlled between Motor torque and angle is approximated to PD control planning.
2) equation of motion is set up to system.
If system gravity and system bottom distance are L, a (t) is system motion acceleration, x (t) is disturbance acceleration, then the equation of motion of system is:
Near working point, because θ is very little, therefore near working point, linearization process is done to the above-mentioned equation of motion:
During system balancing, a (t)==0;
Now:
System transter is:
Obviously now system has two limits, and one of them limit is at the right-half plane of s plane, and now system is unstable;
After additional proportion differential controls, system transter becomes:
Two limits of system are:
Make two limits all be positioned at the Left half-plane of s plane, then must k
1> g, k
2> 0;
The parameter using PD controller to make system stability can be drawn accordingly.
3) for improving stable state accuracy, adding integration control, adopting PID controller to control to this system.
Described PID controller is by following formulae discovery:
Wherein, K
pfor controller proportional gain factor, K
ifor controller integral coefficient, K
dfor controller differential coefficient, e is error;
Use during Embedded computer system and make discretize:
Wherein, e is the numerical value that attitude angle departs from balance angle, and u is the dutycycle directly outputting to motor, e
kand e
k-1represent the deviation in k and k-1 moment respectively.
S22, graphics processing unit carry out Dynamic Binarization process to the runway greyscale image data that embedded computer obtains, and identify that specifically to use with black line be the runway at edge, are specially:
1) view data owing to collecting has certain noise, uses median filtering algorithm to carry out filtering as shown in Figure 4 to signal; Median filtering method is a kind of nonlinear smoothing technology, the gray-scale value of each pixel is set to the intermediate value of all pixel gray-scale values in this some neighborhood window by it, its principle is that the Mesophyticum of each point value in a neighborhood of this point of value of any in digital picture or Serial No. is replaced, allow the actual value that the pixel value of surrounding is close, thus eliminate isolated noise spot.
2) for adapting to different illumination conditions, binary-state threshold should be made variable to the binary conversion treatment of image, threshold variable Dynamic Binarization Algorithm adopts Bernsen algorithm.
Bernsen arthmetic statement is as follows:
Wherein, f (i, j) is for image is at the gray-scale value at pixel (i, j) place, and T (i, j) is the binary-state threshold of each pixel (i, j) in image;
Carry out binaryzation to pixel (i, j) each in image with b (i, the j) pointwise of binaryzation function, b (i, j) function is as follows:
Bernsen binaryzation process flow diagram as shown in Figure 5; Bernsen Binarization methods is a kind of local binarization method of classics, and specific algorithm is as shown in above formula (1).
Runway image effect through binaryzation contrasts as shown in Figure 6, Figure 7; As can see from Figure 7, the image after binaryzation, its runway edge, by having a strong rising edge, namely identifies runway edge by the saltus step of this rising edge of embedded computer identification.
3) runway curvature radius calculation.
If the runway edge identified is f (i, j), then image radius-of-curvature is on centerline:
If curvature and the linear change of differential, then curvature is as follows to left and right motor PWM differential computing formula:
PWM
Difference=K
Diff*k
Wherein, K
difffor differential gain.
In sum, automated navigation system of the present invention adopts camera to carry out the navigation of plane formula, can effectively predict front road conditions, carries out more effective PREDICTIVE CONTROL, improves control accuracy; In addition, have benefited from the sampling rate of IMU sensor and the processing speed of embedded computer, control accuracy also significantly improves.
Embodiment 2:
The present embodiment is an application example, the automated navigation system of above-described embodiment 1 is applied in vertical balanced car.
As shown in Figure 8, described vertical balanced car comprises car body 1, left wheel 2, right wheel 3, motor (not shown) and automated navigation system, described left wheel 2 and right wheel 3 are arranged on the both sides, bottom of car body 1, and described driven by motor left wheel 2 and right wheel 3 move; Wherein, described IMU sensor 4 and embedded computer 5 are arranged in car body 1, and described camera sensing device 6 is arranged on car body 1 top, and described embedded computer 5 is connected with motor.
The above; be only patent preferred embodiment of the present invention; but the protection domain of patent of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the scope disclosed in patent of the present invention; be equal to according to the technical scheme of patent of the present invention and patent of invention design thereof and replaced or change, all belonged to the protection domain of patent of the present invention.
Claims (10)
1. based on the automated navigation system that camera detects, it is characterized in that: described system comprises vertical balanced data acquisition module, camera data acquisition module and signal transacting and control module, described vertical balanced data acquisition module, camera data acquisition module are connected with signal transacting and control module respectively; Wherein:
Described vertical balanced data acquisition module, for the current pose angular data of data acquisition vertical balanced car gathered by IMU sensor;
Described camera data acquisition module, for gathering the greyscale image data of runway by camera sensing device;
Described signal transacting and control module, for being collected by embedded computer, the greyscale image data of Storage and Processing runway, the current pose angular data of vertical balanced car, the current vehicle speed of vertical balanced car and differential data, and according to the current pose angular data of vertical balanced car, balance is carried out to vertical balanced car and controls.
2. the automated navigation system detected based on camera according to claim 1, is characterized in that: described signal transacting and control module comprise:
Balance control module, for according to the current pose angular data obtained, carries out balance to vertical balanced car and controls;
Graphics processing unit, for carrying out computing to the runway greyscale image data gathered.
3. the automated navigation system detected based on camera according to claim 1 and 2, it is characterized in that: described IMU sensor is made up of L3G4200 gyroscope and MMA8451 accelerometer, and described gyroscope is connected with embedded computer by iic bus with accelerometer.
4. the automated navigation system detected based on camera according to claim 1 and 2, be is characterized in that: described camera sensing device adopts imageing sensor OV7620, and is connected with embedded computer by DMA passage.
5. the automated navigation system detected based on camera according to claim 1 and 2, is characterized in that: described embedded computer adopts Freescale company Kinetis MK60DN512 Series MCU to form.
6., based on the control method of automated navigation system described in claim 3, it is characterized in that described method comprises:
In S1, IMU sensor, the data of gyroscope and accelerometer input embedded computer by iic bus, embedded computer is by the inverse trigonometric function computing to accelerometer data, in conjunction with the integration data of gyro data, carry out first-order low-pass ripple, calculate the current pose angular data of vertical balanced car; Meanwhile, the data input embedded computer of camera sensing device, obtains the greyscale image data of runway;
S2, in embedded computer, the attitude angle data that calculated by embedded computer of balance control module substitutes into PID controller, and the balance that the motor rotation controlling vertical balanced car realizes vertical balanced car controls; Simultaneously, graphics processing unit carries out Dynamic Binarization process to the runway greyscale image data that embedded computer obtains, identify that specifically to use with black line be the runway at edge, by carrying out edge feature calculating to the border of runway, obtain the road conditions of runway, and send differential signal to the motor of vertical balanced car by embedded computer, thus real-time follow-up track.
7. the control method of automated navigation system according to claim 6, is characterized in that: embedded computer resolving attitude angle data described in step S1, specific as follows:
Static attitude angle is resolved by following formulae discovery, and the attitude angle calculated is roll angle, the angle of pitch two attitudes:
Wherein, a
x, a
y, a
zfor orthogonal 3-axis acceleration data,
for the static angle of pitch, ρ
ofor static roll angle, a is set
yorthogonal with motor shaft, then effectively static attitude angular data is
angle;
Add gyro data ω and do dynamic data combining, get ω
xparallel with motor shaft, then the dynamic angle of pitch after merging is:
Wherein, Confidence
gyrofor gyrostatic degree of confidence, Confidence
accefor the degree of confidence of accelerometer.
8. the control method of automated navigation system according to claim 6, is characterized in that: PID controller described in step S2 is by following formulae discovery:
Wherein, K
pfor controller proportional gain factor, K
ifor controller integral coefficient, K
dfor controller differential coefficient, e is error;
Use during Embedded computer system and make discretize:
Wherein, e is the numerical value that attitude angle departs from balance angle, and u is the dutycycle directly outputting to motor, e
kand e
k-1represent the deviation in k and k-1 moment respectively.
9. the control method of automated navigation system according to claim 6, is characterized in that: Dynamic Binarization described in step S2 adopts Bernsen algorithm, and this Bemsen arthmetic statement is as follows:
Wherein, f (i, j) is for image is at the gray-scale value at pixel (i, j) place, and T (i, j) is the binary-state threshold of each pixel (i, j) in image;
Carry out binaryzation to pixel (i, j) each in image with b (i, the j) pointwise of binaryzation function, b (i, j) function is as follows:
Image after binaryzation, its runway edge, by having a strong rising edge, namely identifies runway edge by the saltus step of this rising edge of embedded computer identification.
10. vertical balanced car, comprise car body, left wheel, right wheel and motor, described left wheel and right wheel are arranged on the both sides, bottom of car body, and described driven by motor left wheel and right wheel movement, is characterized in that: also comprise automated navigation system according to claim 1; Wherein, described IMU sensor and embedded computer are arranged in car body, and described camera sensing device is arranged on car body top, and described embedded computer is connected with motor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510308759.0A CN104932505B (en) | 2015-06-08 | 2015-06-08 | Automated navigation system, control method and vertical balanced car based on camera detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510308759.0A CN104932505B (en) | 2015-06-08 | 2015-06-08 | Automated navigation system, control method and vertical balanced car based on camera detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104932505A true CN104932505A (en) | 2015-09-23 |
CN104932505B CN104932505B (en) | 2018-04-13 |
Family
ID=54119709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510308759.0A Active CN104932505B (en) | 2015-06-08 | 2015-06-08 | Automated navigation system, control method and vertical balanced car based on camera detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104932505B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105759823A (en) * | 2016-04-27 | 2016-07-13 | 长江大学 | Track-information-based control system and method for two-wheel self-balancing dolly |
CN106020202A (en) * | 2016-07-15 | 2016-10-12 | 东南大学 | Fuzzy PID control method based on Kalman filtering |
CN106092112A (en) * | 2016-06-08 | 2016-11-09 | 尚艳燕 | The air navigation aid of a kind of electrodynamic balance car, guider and electrodynamic balance car |
WO2017166548A1 (en) * | 2016-03-29 | 2017-10-05 | 北京小米移动软件有限公司 | Method and device for controlling stopping of balance car |
CN107340298A (en) * | 2017-06-29 | 2017-11-10 | 广西师范大学 | Balance car system monitoring method based on camera pavement detection |
WO2018036010A1 (en) * | 2016-08-23 | 2018-03-01 | 北京小米移动软件有限公司 | Method and apparatus for controlling balancing vehicle |
CN108360344A (en) * | 2018-02-11 | 2018-08-03 | 云南通衢工程检测有限公司 | Highway technology condition detecting system |
CN108360345A (en) * | 2018-02-11 | 2018-08-03 | 云南通衢工程检测有限公司 | Mobile highway technology status detection device |
CN108445889A (en) * | 2018-05-15 | 2018-08-24 | 深圳市沃特沃德股份有限公司 | A kind of method and its system cleaned based on intelligent sound auxiliary sweeper |
CN108536139A (en) * | 2017-03-06 | 2018-09-14 | 通用汽车环球科技运作有限责任公司 | Soft tracking is kept |
CN110001840A (en) * | 2019-03-12 | 2019-07-12 | 浙江工业大学 | A kind of double-wheel self-balancing vehicle motion control method under various road conditions of view-based access control model sensor |
CN110284426A (en) * | 2019-06-25 | 2019-09-27 | 衡橡科技股份有限公司 | A kind of bridge inspection vehicle frequency-changing control system and its control method |
CN110554706A (en) * | 2019-09-25 | 2019-12-10 | 江苏理工学院 | visual navigation self-balancing vehicle and balancing method |
CN113256739A (en) * | 2021-06-28 | 2021-08-13 | 所托(杭州)汽车智能设备有限公司 | Self-calibration method and device for vehicle-mounted BSD camera and storage medium |
CN114442479A (en) * | 2021-12-31 | 2022-05-06 | 深圳市优必选科技股份有限公司 | Balance car control method and device, balance car and computer readable storage medium |
WO2023197535A1 (en) * | 2022-04-13 | 2023-10-19 | 中国矿业大学 | Slope and curve passage method for unmanned rail electric locomotive in deep limited space |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102874356A (en) * | 2012-10-30 | 2013-01-16 | 王野 | Two-wheel self-balance vehicle control system and two-wheel self-balance vehicle |
CN102890890A (en) * | 2012-10-24 | 2013-01-23 | 长安大学 | Upright self-balancing intelligent vehicle |
CN103512584A (en) * | 2012-06-26 | 2014-01-15 | 北京赛佰特科技有限公司 | Navigation attitude information output method, device and strapdown navigation attitude reference system |
CN103529850A (en) * | 2013-10-28 | 2014-01-22 | 华南理工大学广州学院 | Control method of two-wheeled self-balance vehicle |
CN103676650A (en) * | 2013-11-29 | 2014-03-26 | 上海交通大学 | Method for PID (proportion integration differentiation) optimization control with dead zone for two-wheeled self-balancing intelligent vehicle |
CN103776442A (en) * | 2014-01-17 | 2014-05-07 | 中国人民解放军海军工程大学 | Regional wireless positioning and micro-serial inertial navigation integrated system and positioning method thereof |
CN103792946A (en) * | 2014-02-14 | 2014-05-14 | 上海创绘机器人科技有限公司 | Signal processing method for motion type inverted pendulum system control and intelligent self-balancing vehicle signal control system |
-
2015
- 2015-06-08 CN CN201510308759.0A patent/CN104932505B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103512584A (en) * | 2012-06-26 | 2014-01-15 | 北京赛佰特科技有限公司 | Navigation attitude information output method, device and strapdown navigation attitude reference system |
CN102890890A (en) * | 2012-10-24 | 2013-01-23 | 长安大学 | Upright self-balancing intelligent vehicle |
CN102874356A (en) * | 2012-10-30 | 2013-01-16 | 王野 | Two-wheel self-balance vehicle control system and two-wheel self-balance vehicle |
CN103529850A (en) * | 2013-10-28 | 2014-01-22 | 华南理工大学广州学院 | Control method of two-wheeled self-balance vehicle |
CN103676650A (en) * | 2013-11-29 | 2014-03-26 | 上海交通大学 | Method for PID (proportion integration differentiation) optimization control with dead zone for two-wheeled self-balancing intelligent vehicle |
CN103776442A (en) * | 2014-01-17 | 2014-05-07 | 中国人民解放军海军工程大学 | Regional wireless positioning and micro-serial inertial navigation integrated system and positioning method thereof |
CN103792946A (en) * | 2014-02-14 | 2014-05-14 | 上海创绘机器人科技有限公司 | Signal processing method for motion type inverted pendulum system control and intelligent self-balancing vehicle signal control system |
Non-Patent Citations (2)
Title |
---|
于彦华: "基于视觉导航的两轮自平衡智能模型车的设计与实现", 《中国优秀硕士学位论文全文数据库工程科技辑》 * |
王磊: "硅微航姿***技术研究", 《中国优秀硕士学位论文全文数据库工程科技辑》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017166548A1 (en) * | 2016-03-29 | 2017-10-05 | 北京小米移动软件有限公司 | Method and device for controlling stopping of balance car |
US10429852B2 (en) | 2016-03-29 | 2019-10-01 | Beijing Xiaomi Mobile Software Co., Ltd. | Methods and devices for controlling self-balancing vehicle to park |
CN105759823A (en) * | 2016-04-27 | 2016-07-13 | 长江大学 | Track-information-based control system and method for two-wheel self-balancing dolly |
CN106092112B (en) * | 2016-06-08 | 2018-10-12 | 尚艳燕 | A kind of air navigation aid of electrodynamic balance vehicle, navigation device and electrodynamic balance vehicle |
CN106092112A (en) * | 2016-06-08 | 2016-11-09 | 尚艳燕 | The air navigation aid of a kind of electrodynamic balance car, guider and electrodynamic balance car |
CN106020202A (en) * | 2016-07-15 | 2016-10-12 | 东南大学 | Fuzzy PID control method based on Kalman filtering |
WO2018036010A1 (en) * | 2016-08-23 | 2018-03-01 | 北京小米移动软件有限公司 | Method and apparatus for controlling balancing vehicle |
US10671078B2 (en) | 2016-08-23 | 2020-06-02 | Beijing Xiomi Mobile Software Co., Ltd. | Method, apparatus and medium for controlling self balancing scooter |
CN108536139A (en) * | 2017-03-06 | 2018-09-14 | 通用汽车环球科技运作有限责任公司 | Soft tracking is kept |
CN108536139B (en) * | 2017-03-06 | 2021-08-17 | 通用汽车环球科技运作有限责任公司 | System and method for driving a vehicle |
CN107340298B (en) * | 2017-06-29 | 2020-01-31 | 广西师范大学 | Balance car system measurement and control method based on camera road surface detection |
CN107340298A (en) * | 2017-06-29 | 2017-11-10 | 广西师范大学 | Balance car system monitoring method based on camera pavement detection |
CN108360344A (en) * | 2018-02-11 | 2018-08-03 | 云南通衢工程检测有限公司 | Highway technology condition detecting system |
CN108360345A (en) * | 2018-02-11 | 2018-08-03 | 云南通衢工程检测有限公司 | Mobile highway technology status detection device |
CN108445889A (en) * | 2018-05-15 | 2018-08-24 | 深圳市沃特沃德股份有限公司 | A kind of method and its system cleaned based on intelligent sound auxiliary sweeper |
CN110001840A (en) * | 2019-03-12 | 2019-07-12 | 浙江工业大学 | A kind of double-wheel self-balancing vehicle motion control method under various road conditions of view-based access control model sensor |
CN110001840B (en) * | 2019-03-12 | 2021-01-01 | 浙江工业大学 | Two-wheeled self-balancing vehicle motion control method based on visual sensor under various road conditions |
CN110284426B (en) * | 2019-06-25 | 2021-07-09 | 衡橡科技股份有限公司 | Bridge inspection vehicle frequency conversion control system and control method thereof |
CN110284426A (en) * | 2019-06-25 | 2019-09-27 | 衡橡科技股份有限公司 | A kind of bridge inspection vehicle frequency-changing control system and its control method |
CN110554706A (en) * | 2019-09-25 | 2019-12-10 | 江苏理工学院 | visual navigation self-balancing vehicle and balancing method |
CN113256739A (en) * | 2021-06-28 | 2021-08-13 | 所托(杭州)汽车智能设备有限公司 | Self-calibration method and device for vehicle-mounted BSD camera and storage medium |
CN114442479A (en) * | 2021-12-31 | 2022-05-06 | 深圳市优必选科技股份有限公司 | Balance car control method and device, balance car and computer readable storage medium |
WO2023197535A1 (en) * | 2022-04-13 | 2023-10-19 | 中国矿业大学 | Slope and curve passage method for unmanned rail electric locomotive in deep limited space |
Also Published As
Publication number | Publication date |
---|---|
CN104932505B (en) | 2018-04-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104932505A (en) | Automatic navigation system based on camera detection, control method of system and vertical balance car | |
JP6668375B2 (en) | Steering control method and system for autonomous vehicle using proportional, integral and derivative (PID) controller | |
CN104061899B (en) | A kind of vehicle side inclination angle based on Kalman filtering and angle of pitch method of estimation | |
JP6653381B2 (en) | Map update method and system based on control feedback of autonomous vehicle | |
RU2692097C1 (en) | Device and method for setting a position for stopping a vehicle | |
WO2018072362A1 (en) | Real-time vehicle trajectory prediction method and prediction system | |
Xia et al. | Integrated inertial-LiDAR-based map matching localization for varying environments | |
CN103121447B (en) | A kind of bend preventing side sliding and side turning autonomous cruise speed system and method | |
JP6786511B2 (en) | Methods and systems for tracking the speed of autonomous vehicles | |
CN104198765B (en) | The coordinate system conversion method of vehicle acceleration of motion detection | |
WO2018214227A1 (en) | Unmanned vehicle real-time posture measurement method | |
CN107063305B (en) | Method for correcting downhill suspended rear wheel odometer error by using inertial navigation and pressure sensors | |
CN109195860A (en) | The lane curb of automatic driving vehicle is assisted from road inspection and Lane Keeping System | |
Iagnemma et al. | Classification-based wheel slip detection and detector fusion for mobile robots on outdoor terrain | |
Reina et al. | Slip-based terrain estimation with a skid-steer vehicle | |
KR20170055161A (en) | Apparatus and method for automatic steering control in vehicle | |
CN105182971A (en) | Obstacle avoidance method for service robot in indoor environment | |
CN102818556A (en) | Vehicle road gradient detection method and device thereof | |
CN113822593B (en) | Security situation assessment method and device, storage medium and electronic equipment | |
Karaduman et al. | Deep learning based traffic direction sign detection and determining driving style | |
JP2008089517A (en) | Azimuth discrimination device, azimuth discrimination method, and azimuth discrimination program | |
CN112433531A (en) | Trajectory tracking method and device for automatic driving vehicle and computer equipment | |
CN105785964B (en) | A kind of vehicle closed test method | |
CN112985516B (en) | Underwater crawler belt equipment state sensing system based on artificial lateral line | |
CN106556405A (en) | A kind of lane detection method based on intelligent mobile phone sensor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |