CN108674185A - A kind of unmanned agricultural vehicle field chance barrier method for control speed - Google Patents
A kind of unmanned agricultural vehicle field chance barrier method for control speed Download PDFInfo
- Publication number
- CN108674185A CN108674185A CN201810082768.6A CN201810082768A CN108674185A CN 108674185 A CN108674185 A CN 108674185A CN 201810082768 A CN201810082768 A CN 201810082768A CN 108674185 A CN108674185 A CN 108674185A
- Authority
- CN
- China
- Prior art keywords
- barrier
- agricultural vehicle
- unmanned agricultural
- speed
- unmanned
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K31/00—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator
- B60K31/02—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator including electrically actuated servomechanism including an electric control system or a servomechanism in which the vehicle velocity affecting element is actuated electrically
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K31/00—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator
- B60K31/0008—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator including means for detecting potential obstacles in vehicle path
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
- B60R21/0134—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over responsive to imminent contact with an obstacle, e.g. using radar systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K31/00—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator
- B60K31/0008—Vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator including means for detecting potential obstacles in vehicle path
- B60K2031/0016—Identification of obstacles; Selection of a target vehicle
Abstract
The invention discloses a kind of unmanned agricultural vehicle fields to meet barrier method for control speed, including step once:Obtain obstacle information and input current vehicle speed, establish space-time Raster Data Model, the occupancys grid for obtaining in space-time Raster Data Model barrier, the unmanned agricultural vehicle of acquisition and barrier collision distance, collision distance and obstacle information are input to cloud reasoning device, cloud reasoning device adjusts the travel speed of unmanned agricultural vehicle according to above-mentioned quantitative parameter, after the travel speed adjustment of unmanned agricultural vehicle, recalculates the barrier after adjusting and further adjusted with unmanned agricultural vehicle and to unmanned agricultural vehicle.The information qualitative parameter of unmanned agricultural vehicle and barrier is converted to quantitative parameter by the present invention, is input to cloud reasoning device, and cloud reasoning device adjusts the control speed of unmanned agricultural vehicle according to above-mentioned quantitative parameter, to avoiding obstacles, realizes unmanned operation.
Description
Technical field
The present invention relates to agricultural machinery automatic job fields, and in particular to a kind of unmanned agricultural vehicle field chance barrier speed control
Method processed.
Background technology
With the continuous development of electronic information technology, the development of agricultural vehicle intellectually and automatically is carried forward vigorously.It is right
In the unmanned agricultural vehicle (tractor or agricultural machinery) of not driver, their intellectually and automatically degree requires more
Height, in unstructured, uncertain, complicated agriculture production environment, safe avoidance be unmanned agricultural vehicle critical function it
One.
In farm work generally there is specific job task and work route in view of agricultural vehicle and operating speed compared with
Low, the present invention proposes that the method for control speed after barrier is met in a kind of unmanned agricultural vehicle farm work.
Invention content
To solve deficiency in the prior art, the present invention provides unmanned agricultural vehicle field and meets barrier method for control speed, solution
Determined unmanned agricultural vehicle in farm work can active avoiding obstacles the technical issues of.
In order to realize that above-mentioned target, the present invention adopt the following technical scheme that:
A kind of unmanned agricultural vehicle field chance barrier method for control speed, using following steps:
S1:It obtains obstacle information and inputs current vehicle speed:The obstacle information includes the movement velocity of barrier, fortune
The initial position of dynamic direction and barrier;
S2:Establish space-time Raster Data Model:Specific practice is:The unmanned agricultural vehicle of zero moment and barrier are indicated with X/Y plane
Position, using the longitudinal axis perpendicular to X/Y plane as time shaft TIME, then unmanned agricultural vehicle and barrier be in X/Y plane and
In the rectangular parallelepiped space that time shaft TIME is formed, the rectangular parallelepiped space is cut by several grids with plane TIME=t;
S3:The occupancy grid of barrier is obtained in space-time Raster Data Model:Specific practice is:Unmanned agricultural vehicle is defined
For a bit, barrier is defined as the border circular areas that radius is r, the value of the r is determined by the danger level of barrier, at this time obstacle
The movement of object is defined as a cylinder in space-time Raster Data Model, and the moving line of unmanned agricultural vehicle is in space-time Raster Data Model
On be then defined as a space line, then the collision of unmanned agricultural vehicle and barrier is changed into space line in the rectangular parallelepiped space
The problem of intersecting with cylinder;
S4:Obtain the collision distance of unmanned agricultural vehicle and barrier:When detecting that barrier occurs, start to capture barrier
Hinder object information, it is assumed that between the adjacent obstacle information of capture twice, obstacle information does not change, then barrier is in space-time grid
It is denoted as several coordinates on lattice model, barrier moving line in the time of obstacle information is intended using autoregression algorithm
It closes, and the space cylinder equation derived obstructed paths prediction curve, establish barrier, by the space cylinder equation of barrier
It solves to obtain collision distance L* in conjunction with the moving line of the unmanned agricultural vehicle in S3;
S5:Collision distance L* and obstacle information are input to cloud reasoning device;Specific practice is:By collision distance L*, barrier
Hinder the danger level of object and unmanned agricultural vehicle speed to be converted into quantitative parameter and is input to cloud reasoning device;
S6:Cloud reasoning device adjusts unmanned agriculture according to collision distance L*, the danger level of barrier and unmanned agricultural vehicle speed
The travel speed of industry vehicle;
S7:After the travel speed adjustment of unmanned agricultural vehicle, the barrier after adjusting and unmanned agricultural are recalculated
The distance between vehicle L ' indicates barrier far from unmanned agricultural vehicle, unmanned agricultural vehicle when distance L ' is greater than or equal to zero
It can restore normally travel speed, when distance L ' is less than zero, when indicating that barrier is had the tendency that close to unmanned agricultural vehicle, then
Keep the speed after regulation and control constant, until barrier is separate or generates new prediction of collision point.
Specifically, barrier method for control speed, the cloud reasoning device in the S5 are met in a kind of unmanned agricultural vehicle field above-mentioned
Using double condition more rules processors, double condition more rules processors include former piece cloud and consequent cloud.
Specifically, barrier method for control speed, the decision ginseng of the former piece cloud are met in a kind of unmanned agricultural vehicle field above-mentioned
Number is the danger level of collision distance L* and barrier, and the decision parameters of the consequent cloud are unmanned agricultural vehicle speed.
Specifically, barrier method for control speed, the danger level of the barrier are met in a kind of unmanned agricultural vehicle field above-mentioned
Qualitativing concept be followed successively by from low to high:It is low, relatively low, general, higher, high, the quantitative concept of the danger level of barrier from as low as
Height is followed successively by:[0,1]、(1,3]、(3,5]、(5,7]、(7,10].
Specifically, barrier method for control speed is met in a kind of unmanned agricultural vehicle field above-mentioned, the collision distance L*'s determines
Property concept is followed successively by from low to high:Closely, more closely, generally, farther out, far, the quantitative concept of collision distance L* is followed successively by from low to high:
[0,2]、(2,5]、(5,10]、(10,20]、(20,30]m。
Specifically, barrier method for control speed, the unmanned agricultural vehicle speed are met in a kind of unmanned agricultural vehicle field above-mentioned
The quantitative concept of degree is followed successively by from low to high:Zero, relatively slow, general, very fast, fast, quantifying for the unmanned agricultural vehicle speed is general
Thought be followed successively by from low to high [0,10], (10,20], (20,40], (40,70], (70,100] cm/s.
Specifically, barrier method for control speed is met in a kind of unmanned agricultural vehicle field above-mentioned, the specific practice of the S4 is:
In t0Moment, barrier occur, and after time t', capture n group obstacle informations, it is assumed that adjacent to capture barrier letter twice
Between breath, obstacle information does not change, then barrier is in t0It is denoted as (x in the space-time Raster Data Model at+t' momentr1,yr1)、
(xr2,yr2)、……、(xrn,yrn), barrier moving line in time t' is fitted using autoregression algorithm, then barrier
Path prediction curve it is as follows:
In formula:b0, b1..., bmFor unknown parameter, ε is the stochastic variable of zero-mean;
If current unmanned agricultural vehicle movement velocity is va, current location is (x0,y0), barrier translational speed vb, when
Anteposition is set to (xr0,yr0), barrier risk factors assessment scale radius is r, then forecasting-obstacle driving trace equation is:
In formula:T is time, xrIt is barrier in the abscissa of space-time Raster Data Model, vbFor barrier translational speed;
Formula 2 is further simplified as:
Then Obstacles cylinder equation is:
(x-f(t))2+(y-g(t))2≤r2 (4)
In formula:X, y be barrier in the coordinate of space-time Raster Data Model, t is the time;R is barrier risk factors assessment scale radius;
If unmanned agricultural vehicle equation of motion in a certain operating environment is as follows:
In formula:P, a is correction factor, vaFor the speed of the unmanned agricultural vehicle at a certain moment;
If the moving line of unmanned agricultural vehicle is:
Y=kx+b (6)
In formula:K is working path equation coefficient under current space-time, and b is constant;
Simultaneous equations (4), (5), (6) and restrictive condition, you can obtain prediction of collision equation:
s.t.t≥0,xm≥x≥0,ym≥y≥0 (7)
Position of collision can must be predicted by solving equation, acquire collision distance L*.
In formula:L* is collision distance, and t is time, xm, ymTo be established grid map boundary.
Specifically, barrier method for control speed is met in a kind of unmanned agricultural vehicle field above-mentioned, the specific practice of the S7 is:
If t0Moment working truck coordinate is (x0,y0), obstacle article coordinate is (xr0,yr0), t ' rear vehicle predicted positions are (x1,y1), barrier
It is (x to hinder object predicted positionr1,yr1), then t0Moment vehicle and obstacle distance, then t0Moment unmanned agricultural vehicle and barrier are straight
Linear distance is:
Define t0Moment with after t ' air line distance of unmanned agricultural vehicle and barrier variation be L ';
Then:
By formula (10) it is found that working as L ' >=0, barrier is moved to far from unmanned agricultural vehicle direction, and unmanned agricultural vehicle can
Restore normally travel speed;Conversely, then barrier has the tendency that moving close to unmanned agricultural vehicle, unmanned agricultural vehicle keeps adjusting
Speed after control is constant, until barrier is separate or generates new prediction of collision point.
The advantageous effect that the present invention is reached:
The effect of people is not just for supervision, by the perception of people, knowledge and the speed control for judging the unmanned agricultural vehicle of involvement
In, make unmanned agricultural vehicle when carrying out path planning with automatic obstacle avoiding, rationally adjusts travel speed;It is raw for dynamic agricultural
Environment is produced, effective prediction of collision model is established, using prediction position of collision as one of reference index of speed control.
The present invention will be converted to quantitative parameter with the relevant qualitative parameter of the information of unmanned agricultural vehicle and barrier, input
To cloud reasoning device, cloud reasoning device adjusts the control speed of unmanned agricultural vehicle according to above-mentioned quantitative parameter, to avoiding obstacles,
Realize the unmanned operation of agricultural vehicle.
Description of the drawings
Fig. 1 is inventive algorithm basic procedure;
Fig. 2 is that space-time of the present invention occupies grid map;
Fig. 3 is parameter cloud scale map of the present invention;
Fig. 4 is double condition processor figures of the invention;
Fig. 5 is speed rule processor figure of the present invention;
Fig. 6 is the unmanned agricultural vehicle strategy of speed control flow chart of the present invention.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
Generally there is in view of unmanned agricultural vehicle in farm work specific job task and work route and operation speed
Spend relatively low, the present invention proposes that the method for control speed after barrier is met in a kind of unmanned agricultural vehicle farm work.Fig. 1 is the basic of algorithm
Flow, first disturbance of analysis object information, obstacle information include the initial of the movement velocity of barrier, the direction of motion and barrier
Then position carries out prediction of collision according to obstacle information, then is collided to speed cloud reasoning device input barrier danger level, prediction
Position and unmanned agricultural vehicle speed;Final output speed the reasoning results.
The prediction of collision of barrier is one of the Primary Reference index of unmanned agricultural vehicle rate controlling strategy when meeting barrier.Obstacle
The space-time of object occupies common environmental modeling method when grid map is path planning, it can be by barrier, especially movement barrier
Hinder object, the seizure condition in current environment shows in such a way that 2.5 tie up.It is using current time as zero moment, to distant behaviour
Make agricultural machinery ambient enviroment to be modeled, the position of the unmanned agricultural vehicle of zero moment and barrier indicated with X/Y plane, with perpendicular to
The longitudinal axis of X/Y plane can infinitely extend as time shaft TIME, time shaft TIME, then unmanned agricultural vehicle and barrier are in XY
In the rectangular parallelepiped space that plane and time shaft TIME are formed, the rectangular parallelepiped space is cut by several grid with plane TIME=t
Lattice, the size of each grid are related with the range of environmental modeling and grid number.If it is full that space-time occupies grid map point P (x, y, t)
Sufficient T (P)=1, then it represents that in t moment, grid (x, y) is occupied by barrier, on the contrary then be denoted as T (P)=0.With TIME=t0It is flat
This cuboid is cut in face, then it represents that for by time t0Afterwards, in current environment barrier occupancy grid map.All moment
Projection of the grid map to X/Y plane then forms the static description to different conditions barrier in current environment.
In grid map, moving obstacle can be considered as to particle, and ignore the uncertainty of moving obstacle movement, used
Dangerous amplifying method is to consider uncertain factor, i.e., according to the danger level of barrier, forms a risk factors assessment scale by the center of circle of particle, put
The danger zone of big moving obstacle.
As shown in Figure 2.Zero moment, unmanned agricultural vehicle is in position (x0, y0, 0), and along working path direction straight-line travelling.
A certain moving obstacle is located at (xr,yr, 0), and a risk factors assessment scale is formed according to the danger level of barrier, risk factors assessment scale radius is
r.The movement of barrier at this time occupies grid graph into a cylinder in space-time.Finally, unmanned agricultural vehicle and barrier touch
The problem of hitting is converted into the intersection problems of space line and cylinder.
The road environment of farm work is complicated, is not suitable for the prediction technique using road as prior information.The present invention is in vacation
If on the basis of original state method, the path according to barrier movement and its trend, using the curvilinear regression algorithm pair of fitting of a polynomial
Moving obstacle carries out path prediction.Work as t0Moment, moving obstacle occur, it is assumed that barrier motion state does not change at this time
Become.After time t', sensor captures n group obstacle informations, it is assumed that between the adjacent obstacle information of capture twice, obstacle
Object information does not change, in t0It is denoted as (x in the grid map at+t' momentr1,yr1)、(xr2,yr2)、……、(xrn,yrn).It uses
Autoregression algorithm is fitted barrier moving line in time t', and path prediction curve is as follows:
Wherein, b0, b1..., bmFor unknown parameter, ε is the stochastic variable of zero-mean.
If current unmanned agricultural vehicle movement velocity is va, current location is (x0,y0), barrier translational speed vb, when
Anteposition is set to (xr0,yr0), barrier risk factors assessment scale radius is r, then forecasting-obstacle driving trace equation is:
In formula:T is time, xrIt is barrier in the abscissa of space-time Raster Data Model, vbFor barrier translational speed;
For ease of expression, enable
Then cylinder equation in space is:
(x-f(t))2+(y-g(t))2≤r2 (4)
In formula:X, y be barrier in the coordinate of space-time Raster Data Model, t is the time;R is barrier risk factors assessment scale radius.
If unmanned agricultural vehicle equation of motion in a certain operating environment is as follows:
In formula:P, a is correction factor, vaFor the speed of the unmanned agricultural vehicle at a certain moment.
If the moving line of unmanned agricultural vehicle is:
Y=kx+b (6)
In formula:K is working path equation coefficient under current space-time, and b is constant.
Simultaneous equations (4), (5), (6) and restrictive condition, you can obtain prediction of collision equation:
s.t.t≥0,xm≥x≥0,ym≥y≥0 (7)
Position of collision can must be predicted by solving equation, acquire collision distance L*.
After obtaining collision distance L* and barrier status information, as important references condition entry to cloud reasoning device
In.
It is cloud models theory that cloud reasoning device, which builds basis,.Cloud models theory can it is expected Ex, entropy by 3 numerical characteristics
En, super entropy He, i.e. (Ex, En, He), experience and the knowledge of people are expressed whereby in a manner of fuzzy mathematics.For example, apart from early work
For qualitativing concept, representated by domain be 0~2m, then it is (1,0.33,0.5) to calculate its numerical characteristic.
In conjunction with expertise and common sense, the present invention is by the degree of danger of the prediction collision distance and barrier itself of barrier
As the index that speed rule thruster is formulated, by collision distance and obstacle information (movement velocity, the direction of motion of barrier
And the initial position of barrier) qualitativing concept be converted into quantitative parameter input, realize the output of unmanned agricultural vehicle speed control.
The foundation of cloud scale and speed control generator is vital part in control strategy, and host computer will assist remote
Operator, disturbance in judgement object information is held to calculate and give speed-control scheme within the extremely short time.Cloud model passes through 3 numbers
Word feature, by uncertain concept by being indicated for the discrete dot pattern of the longitudinal axis using metrics range as horizontal axis, degree of membership,
As shown in figure 3, the discrete dot pattern conforms generally to normal distribution.
In cloud model express people's knowledge typical inference rule be " If a and b and c and ..., then d " this
Form.For example, a certain inference rule is that " If a5and b3, then d4 ", are construed to:If the distance of prediction position of collision is
Remote, and degree of danger is in general, then the control of its operating speed is faster.The rule be experience based on human expert with
The knowledge base that knowledge is formed.
As shown in figure 4, the present invention is using double condition more rules processors, the processor is by former piece cloud CGAWith consequent cloud CGB
Two parts form, input:Numerical characteristic (the Ex of collision distance and danger level qualitativing conceptA1i, EnA1i, HeA1i)、(ExA2j,
EnA2j, HeA2j), i/j corresponds to the danger level of different collision distance/barriers respectively;The number of consequent speed qualitativing concept is special
Levy (ExBk, EnBk, HeBk), k corresponds to different speed class.Output:Meet the speed quantitative values X of degree of certainty yB。X1、X2For reality
When distance and danger level encourage, to active processor.
Rule Generator process flow:
(1) according to the Processing Algorithm of qualitative output, for the collision distance X of input of a certain moment1, barrier danger level
X2, calculate all cloud generator CGAIntensity of activation, determine its position on cloud scale.After activation, CGADegree of certainty y1 is exported,
It is optimal rules to select the corresponding rule of maximum y1 values.
(2) y1 after determining is as condition activation output plane CGBOn cloud scale, calculate XB。
(3) for quantitative collision distance X1, barrier danger level X2It carries out N wheels to judge, i.e., n times is carried out to same input
Processing, obtains qualitative variable sampling point set [drop (XB, y2)].Using these water dusts as input, backward cloud generator CG is imported-1, final speed cloud numerical characteristic Ex, En, He are restored, and draw cloud atlas (as shown in Figure 3).
(4) it is exported according to speed cloud numerical characteristic, realizes velocity estimated.
For example, in certain experiment, gait of march of the unmanned agricultural machinery when carrying out operation is 1m/s.To be sensed in experiment
The maximum distance 30m of the accurate perception information of device is boundary, and expert assesses distance parameter and is divided into [0,2], (2,5], (5,10], (10,
20], (20,30] five groups of m, as shown in table 1.
Table 1 is apart from cloud parameter calibration
Likewise, the judgement of the danger level of barrier also assesses discussion jointly by several experts according to reality and experience.Barrier
The key of the risk assessment of object is hindered to be broadly divided into three parts:(1) whether barrier can threaten personal safety;(2) barrier is
It is no to cause greater loss to property;(3) whether barrier moves, and is, increases danger coefficient.Based on above description, expert couple
The danger level of barrier carries out assessment and cloud under certain operating environment, is divided into [0,1], and (1,3], (3,5], (5,7], (7,10] five
A grade, corresponding danger level is low, this relatively low, general, higher, high five concepts.
2 danger level cloud parameter calibration of table
The danger level of collision distance and barrier as decision parameters, be unmanned agricultural vehicle speed control it is main according to
According to.Therefore, the danger level parameter of collision distance and barrier is former piece cloud, and unmanned agricultural vehicle speed control parameter is consequent
Cloud.Speed when the unmanned agricultural vehicle operation that the present invention tests is 1m/s, and speed control domain delimited by magnitude of cm/s and is
[0,100] is equally divided into five grades.Table 3 is that speed class divides and speed cloud parameter calibration.
3 speed cloud parameter calibration of table
Finally, unmanned agricultural vehicle speed inference rule is as shown in table 4:
4 speed inference rule of table
By inference rule table it is found that the rule processor totally 25 rule, that is, form 25 Normal Cloud Generators, wherein
I, the equal value of j, k [1,2,3,4,5], correspond to respectively collision distance, the danger level of barrier and unmanned agricultural vehicle speed by
Low to high five qualitative grades.Strictly all rules build unmanned agricultural vehicle speed rule processor jointly, as shown in Figure 5.
Cloud generator is accomplished that being input to unmanned agricultural vehicle speed from obstacle information exports this process, for quiet
It, can be according to barrier danger level when there is collision generation position on the working path of unmanned agricultural vehicle for state barrier
And position of collision distance is directly realized by speed control.But to dynamic barrier, work as t0Moment unmanned agricultural vehicle is travelled with speed v
When, if after there is the prediction point of impingement and carrying out speed regulation, in t0In the grid map that+t ' moment establishes, the prediction point of impingement may
It can disappear, the decision of the next step of speed control model reply at this time provides foundation.
If t0Moment working truck coordinate is (x0,y0), obstacle article coordinate is (xr0,yr0), t ' rear vehicle predicted positions are
(x1,y1), forecasting-obstacle position is (xr1,yr1), then t0Moment vehicle and obstacle distance, then t0Moment unmanned agricultural vehicle
It is with barrier air line distance:
Define t0Moment with after t ' air line distance of unmanned agricultural vehicle and barrier variation be L ':
By formula (10) it is found that working as L ' >=0, barrier is moved to far from unmanned agricultural vehicle direction, otherwise barrier is to lean on
The trend movement of nearly unmanned agricultural vehicle.When dynamic barrier is far from unmanned agricultural vehicle, unmanned agricultural vehicle can restore just
Normal travel speed;When barrier has the tendency that close to unmanned agricultural vehicle, keep the speed after regulation and control constant, until barrier
Prediction of collision point separate or that generation is new.
For ease of analysis, to the different seizure conditions of barrier are described respectively in grid map.When clear in grid
In the presence of and when the grid nonanticipating position of collision, remember T=0;When there are remember T=1 when static-obstacle thing in grid;T=2 indicate without
When driving with present speed, the prediction point of impingement that can be collided in the grid positions, T=3 indicates certain grid to people's agricultural vehicle
Currently occupied by moving obstacle.QAIndicate the prediction position of collision solved according to prediction model, SminIndicate unmanned agricultural
Vehicle between nearest prediction of collision point at a distance from.Control method of the present invention is as shown in Figure 6.
Therefore, the strategy of speed control in dynamic environment is as follows:Work as t0When barrier occurs in moment, if unmanned agricultural vehicle
The distance between barrier is more than the safety value of setting, then judges whether the barrier is moving obstacle, hinders if movement
Hinder object, then whether the movement of disturbance in judgement object can generate threat to operation.If unmanned agricultural vehicle is touched with barrier in the presence of prediction
Position is hit, then by cloud generator output speed control result, if being not present, keeps current vehicle speed constant.After time t ', if barrier
Hinder object still close to unmanned agricultural vehicle, but collisionless position exists, keep present speed constant, until barrier is far from operation
Normally travel is restored in region.
It the above is only the preferred embodiment of the present invention, it is noted that those skilled in the art are come
It says, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations are also answered
It is considered as protection scope of the present invention.
Claims (8)
1. barrier method for control speed is met in a kind of unmanned agricultural vehicle field, it is characterised in that:Using following steps:
S1:It obtains obstacle information and inputs current vehicle speed:The obstacle information includes the movement velocity of barrier, movement side
To and barrier initial position;
S2:Establish space-time Raster Data Model:Specific practice is:The position of the unmanned agricultural vehicle of zero moment and barrier is indicated with X/Y plane
It sets, using the longitudinal axis perpendicular to X/Y plane as time shaft TIME, then unmanned agricultural vehicle and barrier are in X/Y plane and time
In the rectangular parallelepiped space that axis TIME is formed, the rectangular parallelepiped space is cut by several grids with plane TIME=t;
S3:The occupancy grid of barrier is obtained in space-time Raster Data Model:Specific practice is:Unmanned agricultural vehicle is defined as one
Barrier is defined as the border circular areas that radius is r by point, the value of the r determines by the danger level of barrier, at this time barrier
Movement is defined as a cylinder in space-time Raster Data Model, and the moving line of unmanned agricultural vehicle in space-time Raster Data Model then
It is defined as a space line, then the collision of unmanned agricultural vehicle and barrier is changed into space line and column in the rectangular parallelepiped space
The problem of body intersects;
S4:Obtain the collision distance of unmanned agricultural vehicle and barrier:When detecting that barrier occurs, start to capture barrier
Information, it is assumed that between the adjacent obstacle information of capture twice, obstacle information does not change, then barrier is in space-time grid mould
It is denoted as several coordinates in type, barrier moving line in the time of obstacle information is fitted using autoregression algorithm,
And the space cylinder equation derived obstructed paths prediction curve, establish barrier, by the space cylinder equation knot of barrier
The moving line for closing the unmanned agricultural vehicle in S3 solves to obtain collision distance L*;
S5:Collision distance L* and obstacle information are input to cloud reasoning device;Specific practice is:By collision distance L*, barrier
Danger level and unmanned agricultural vehicle speed be converted into quantitative parameter and be input to cloud reasoning device;
S6:Cloud reasoning device adjusts unmanned agriculture vehicle according to collision distance L*, the danger level of barrier and unmanned agricultural vehicle speed
Travel speed;
S7:After the travel speed adjustment of unmanned agricultural vehicle, the barrier after adjusting and unmanned agricultural vehicle are recalculated
The distance between L ', when distance L ' be greater than or equal to zero when, indicate barrier far from unmanned agricultural vehicle, unmanned agricultural vehicle can
Restore normally travel speed, when distance L ' is less than zero, when indicating that barrier is had the tendency that close to unmanned agricultural vehicle, then keeps
Speed after regulation and control is constant, until barrier is separate or generates new prediction of collision point.
2. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1, it is characterized in that:The S5
In cloud reasoning device using double condition more rules processors, double condition more rules processors include former piece cloud and consequent cloud.
3. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 2, it is characterized in that:Before described
The decision parameters of part cloud are the danger levels of collision distance L* and barrier, and the decision parameters of the consequent cloud are unmanned agricultural vehicles
Speed.
4. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1 or 3, it is characterized in that:Institute
The qualitativing concept for stating the danger level of barrier is followed successively by from low to high:It is low, relatively low, general, higher, high, the danger level of barrier
Quantitative concept be followed successively by from low to high:[0,1]、(1,3]、(3,5]、(5,7]、(7,10].
5. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1 or 3, it is characterized in that:Institute
The qualitativing concept for stating collision distance L* is followed successively by from low to high:Closely, more closely, generally, farther out, far, collision distance L*'s is quantitative general
Thought is followed successively by from low to high:[0,2]、(2,5]、(5,10]、(10,20]、(20,30]m.
6. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1 or 3, it is characterized in that:Institute
The quantitative concept for stating unmanned agricultural vehicle speed is followed successively by from low to high:Zero, relatively slow, general, very fast, fast, the unmanned agricultural
The quantitative concept of car speed be followed successively by from low to high [0,10], (10,20], (20,40], (40,70], (70,100] cm/s.
7. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1, it is characterized in that:The S4
Specific practice be:In t0Moment, barrier occur, and after time t', capture n group obstacle informations, it is assumed that adjacent two
Between secondary capture obstacle information, obstacle information does not change, then barrier is in t0In the space-time Raster Data Model at+t' moment
It is denoted as (xr1,yr1)、(xr2,yr2)、……、(xrn,yrn), barrier moving line in time t' is carried out using autoregression algorithm
Fitting, then the path prediction curve of barrier is as follows:
In formula:b0, b1..., bmFor unknown parameter, ε is the stochastic variable of zero-mean;
If current unmanned agricultural vehicle movement velocity is va, current location is (x0,y0), barrier translational speed vb, present bit
It is set to (xr0,yr0), barrier risk factors assessment scale radius is r, then forecasting-obstacle driving trace equation is:
In formula:T is time, xrIt is barrier in the abscissa of space-time Raster Data Model, vbFor barrier translational speed;Formula 2 is further
It is reduced to:
Then Obstacles cylinder equation is:
(x-f(t))2+(y-g(t))2≤r2 (4)
In formula:X, y be barrier in the coordinate of space-time Raster Data Model, t is the time;R is barrier risk factors assessment scale radius.If unmanned agriculture
Industry vehicle equation of motion in a certain operating environment is as follows:
In formula:P, a is correction factor, vaFor the speed of the unmanned agricultural vehicle at a certain moment;
If the moving line of unmanned agricultural vehicle is:
Y=kx+b (6)
In formula:K is working path equation coefficient under current space-time, and b is constant;
Simultaneous equations (4), (5), (6) and restrictive condition, you can obtain prediction of collision equation:
s.t.t≥0,xm≥x≥0,ym≥y≥0 (7)
Position of collision can must be predicted by solving equation, acquire collision distance L*.
In formula:L* is collision distance, and t is time, xm, ymTo be established grid map boundary.
8. barrier method for control speed is met in a kind of unmanned agricultural vehicle field according to claim 1, it is characterized in that:The S7
Specific practice be:If t0Moment working truck coordinate is (x0,y0), obstacle article coordinate is (xr0,yr0), t ' rear vehicle prediction bits
It is set to (x1,y1), forecasting-obstacle position is (xr1,yr1), then t0Moment vehicle and obstacle distance, then t0Moment unmanned agricultural
Vehicle is with barrier air line distance:
Define t0Moment with after t ' air line distance of unmanned agricultural vehicle and barrier variation be L ';
Then:
By formula (10) it is found that working as L ' >=0, barrier is moved to far from unmanned agricultural vehicle direction, and unmanned agricultural vehicle can restore
Normally travel speed;Conversely, then barrier has the tendency that moving close to unmanned agricultural vehicle, after unmanned agricultural vehicle keeps regulation and control
Speed it is constant, until barrier is separate or generates new prediction of collision point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810082768.6A CN108674185B (en) | 2018-01-29 | 2018-01-29 | Method for controlling obstacle encountering speed of unmanned agricultural vehicle in field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810082768.6A CN108674185B (en) | 2018-01-29 | 2018-01-29 | Method for controlling obstacle encountering speed of unmanned agricultural vehicle in field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108674185A true CN108674185A (en) | 2018-10-19 |
CN108674185B CN108674185B (en) | 2021-01-01 |
Family
ID=63800104
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810082768.6A Active CN108674185B (en) | 2018-01-29 | 2018-01-29 | Method for controlling obstacle encountering speed of unmanned agricultural vehicle in field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108674185B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109887321A (en) * | 2019-03-28 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | The safe method of discrimination of unmanned vehicle lane change, device and storage medium |
CN110209157A (en) * | 2019-04-09 | 2019-09-06 | 丰疆智能科技股份有限公司 | The barrier avoidance system and its method of automatic harvester |
CN112012269A (en) * | 2019-05-29 | 2020-12-01 | 纳博特斯克有限公司 | Operation assistance system and method, maintenance assistance method, and construction machine |
US11574483B2 (en) | 2019-12-24 | 2023-02-07 | Yandex Self Driving Group Llc | Methods and systems for computer-based determining of presence of objects |
US11753037B2 (en) | 2019-11-06 | 2023-09-12 | Yandex Self Driving Group Llc | Method and processor for controlling in-lane movement of autonomous vehicle |
CN117274941A (en) * | 2023-11-22 | 2023-12-22 | 安徽蔚来智驾科技有限公司 | Occupancy grid prediction method and device, intelligent equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201380816Y (en) * | 2008-12-29 | 2010-01-13 | 广东铁将军防盗设备有限公司 | Automatic navigation automobile, and automobile obstacle-avoidance warning system and corresponding circuit thereof |
CN103978488A (en) * | 2014-05-14 | 2014-08-13 | 常州信息职业技术学院 | Transfer robot based on cloud model control system |
US20170066445A1 (en) * | 2015-09-09 | 2017-03-09 | Denso Corporation | Vehicle control apparatus |
CN106989748A (en) * | 2017-05-16 | 2017-07-28 | 南京农业大学 | A kind of Agriculture Mobile Robot man-computer cooperation paths planning method based on cloud model |
CN107529041A (en) * | 2017-09-30 | 2017-12-29 | 江西洪都航空工业集团有限责任公司 | A kind of long-distance monitoring method for unmanned agricultural vehicle |
-
2018
- 2018-01-29 CN CN201810082768.6A patent/CN108674185B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201380816Y (en) * | 2008-12-29 | 2010-01-13 | 广东铁将军防盗设备有限公司 | Automatic navigation automobile, and automobile obstacle-avoidance warning system and corresponding circuit thereof |
CN103978488A (en) * | 2014-05-14 | 2014-08-13 | 常州信息职业技术学院 | Transfer robot based on cloud model control system |
US20170066445A1 (en) * | 2015-09-09 | 2017-03-09 | Denso Corporation | Vehicle control apparatus |
CN106989748A (en) * | 2017-05-16 | 2017-07-28 | 南京农业大学 | A kind of Agriculture Mobile Robot man-computer cooperation paths planning method based on cloud model |
CN107529041A (en) * | 2017-09-30 | 2017-12-29 | 江西洪都航空工业集团有限责任公司 | A kind of long-distance monitoring method for unmanned agricultural vehicle |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109887321A (en) * | 2019-03-28 | 2019-06-14 | 百度在线网络技术(北京)有限公司 | The safe method of discrimination of unmanned vehicle lane change, device and storage medium |
CN109887321B (en) * | 2019-03-28 | 2021-06-11 | 百度在线网络技术(北京)有限公司 | Unmanned vehicle lane change safety judgment method and device and storage medium |
CN110209157A (en) * | 2019-04-09 | 2019-09-06 | 丰疆智能科技股份有限公司 | The barrier avoidance system and its method of automatic harvester |
CN112012269A (en) * | 2019-05-29 | 2020-12-01 | 纳博特斯克有限公司 | Operation assistance system and method, maintenance assistance method, and construction machine |
US11753037B2 (en) | 2019-11-06 | 2023-09-12 | Yandex Self Driving Group Llc | Method and processor for controlling in-lane movement of autonomous vehicle |
US11574483B2 (en) | 2019-12-24 | 2023-02-07 | Yandex Self Driving Group Llc | Methods and systems for computer-based determining of presence of objects |
CN117274941A (en) * | 2023-11-22 | 2023-12-22 | 安徽蔚来智驾科技有限公司 | Occupancy grid prediction method and device, intelligent equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108674185B (en) | 2021-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108674185A (en) | A kind of unmanned agricultural vehicle field chance barrier method for control speed | |
Zhou et al. | Multiobjective optimization of lane-changing strategy for intelligent vehicles in complex driving environments | |
US8510034B2 (en) | Perception model for trajectory following autonomous and human augmented steering control | |
US20080195569A1 (en) | Human perception model for speed control performance | |
CN110466516B (en) | Curve road automatic vehicle lane change track planning method based on nonlinear programming | |
US8498796B2 (en) | Perception model for trajectory following autonomous and human augmented speed control | |
US7769512B2 (en) | Vehicle steering control method and performance | |
CN110502032A (en) | A kind of unmanned plane cluster formation flight method of Behavior-based control control | |
Wang et al. | Self-learning cruise control using kernel-based least squares policy iteration | |
CN111708370B (en) | Multi-robot collaborative path planning method and system based on artificial potential field | |
Huq et al. | Mobile robot navigation using motor schema and fuzzy context dependent behavior modulation | |
CN107168324A (en) | A kind of robot path planning method based on ANFIS fuzzy neural networks | |
Novi et al. | Real-time control for at-limit handling driving on a predefined path | |
US20120158247A1 (en) | Perception Model For Trajectory Following Autonomous And Human Augmented Steering Control | |
CN104501816A (en) | Multi-unmanned aerial vehicle coordination and collision avoidance guide planning method | |
CN103324196A (en) | Multi-robot path planning and coordination collision prevention method based on fuzzy logic | |
CN112284393A (en) | Global path planning method and system for intelligent mobile robot | |
CN114967676A (en) | Model prediction control trajectory tracking control system and method based on reinforcement learning | |
Al Dabooni et al. | Heuristic dynamic programming for mobile robot path planning based on Dyna approach | |
Hunaini et al. | Optimization of automatic steering control on a vehiclewith a steer-by-wire system using particle swarm optimization | |
Wu et al. | Trajectory prediction based on planning method considering collision risk | |
Hartmann et al. | Model-based reinforcement learning for time-optimal velocity control | |
Van Koevering et al. | Provable probabilistic safety and feasibility-assured control for autonomous vehicles using exponential control barrier functions | |
Hamad et al. | Path Planning of Mobile Robot Based on Modification of Vector Field Histogram using Neuro-Fuzzy Algorithm. | |
Chen et al. | RHONN-modeling-based predictive safety assessment and torque vectoring for holistic stabilization of electrified vehicles |
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 |