CN109634277B - Unmanned operation system and operation method for grain harvester - Google Patents
Unmanned operation system and operation method for grain harvester Download PDFInfo
- Publication number
- CN109634277B CN109634277B CN201811531486.6A CN201811531486A CN109634277B CN 109634277 B CN109634277 B CN 109634277B CN 201811531486 A CN201811531486 A CN 201811531486A CN 109634277 B CN109634277 B CN 109634277B
- Authority
- CN
- China
- Prior art keywords
- grain
- dimensional depth
- harvester
- depth sensor
- stubble
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003306 harvesting Methods 0.000 claims abstract description 34
- 238000004804 winding Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims description 31
- 238000000691 measurement method Methods 0.000 claims description 10
- 239000010902 straw Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001124569 Lycaenidae Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D45/00—Harvesting of standing crops
Abstract
The invention provides an unmanned operation system and an unmanned operation method for a grain harvester, and relates to the field of agricultural equipment and navigation. For the return operation path scheme, three-dimensional depth sensors are symmetrically arranged on two sides of the harvester body, and for the winding operation path scheme, the three-dimensional depth sensors are arranged on one side of the harvester body. The three-dimensional depth sensor simultaneously obtains the information of a stubble cutting surface with a certain length and a stubble cutting near scene area, and automatically moves forward along the stubble cutting surface to harvest the grains. The height of the ear head area and the grain height change value are obtained through calculation in the stubble-cutting scenic spot, the judgment of the feeding amount and the lodging is realized, the advancing speed and the header height of the grain harvester are automatically adjusted, and the unmanned harvesting operation with self-adaption of the feeding amount and the lodging is realized. The system has simple structure, good stability and real-time performance, and good adaptability to different fields, grains and the like.
Description
Technical Field
The invention relates to the field of agricultural equipment and navigation, in particular to a grain harvester unmanned operation system and an operation method based on three-dimensional depth vision.
Background
In recent years, agricultural machinery navigation and auxiliary driving technologies are rapidly developed, and meanwhile, unmanned agricultural machinery research also begins to be paid attention to in order to liberate labor force and improve operation quality; the grain harvester is one of the most important agricultural machines, the autonomous driving of the grain harvester is the key point of research and development, and the current autonomous driving technology of the grain harvester still has the following defects:
(1) satellite positioning based on Beidou and GPS usually needs complex system composition such as a navigation base station, a mobile station, an antenna, a board card and the like, only has space coordinate information of a machine body, cannot meet the requirement of realizing unmanned autonomous operation, and has limited applicability and practical value for small and medium-sized fields;
(2) the visual navigation is mainly based on a CCD camera, the light change in the field is large, redundant information is more, the color difference between a target and a background is not prominent, and the effective extraction of crop stubble cutting, ridges and the like is difficult to realize;
(3) the laser radar can only detect two-dimensional depth information, and is convenient for judging whether obstacles exist in navigation, so that the judgment of crops, field heads and the like is difficult to realize.
Three-dimensional depth vision has been applied more recently, and Sharon Nissimov and others apply three-dimensional depth to detect and navigate greenhouse obstacles (Obstacle detection in a greenhouse environment using the Kinect sensor, Computers and Electronics in Agriculture,2015,113:104 and 115.), but it is used for Obstacle avoidance walking, and field grain harvesting requires precise crop stubble discrimination, header adjustment and harvest implementation.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a grain harvester unmanned operation system and method based on three-dimensional depth vision, which applies the three-dimensional depth vision technology to the autonomous driving of the grain harvester to realize the accurate judgment of crop stubbles and the adjustment of a header.
The invention adopts the following specific technical scheme:
a three-dimensional depth sensor is arranged on a harvester body, and the vertical distance D between the three-dimensional depth sensor and a stubble cutting surface is obtained during harvesting operation0And the minimum effective depth detection value D of the three-dimensional depth sensor1Making the vertical viewing surface of the three-dimensional depth sensor form an included angle alpha with the longitudinal center line of the harvester body, wherein alpha is the horizontal viewing angle of the three-dimensional depth sensor1/2 of (1); height H of three-dimensional depth sensor from ground1Is in the value range of [ H ]]≤H1≤1.2[H]Wherein [ H ]]Maximum plant height of grain suitable for grain harvester [ H](ii) a The horizontal viewing surface of the three-dimensional depth sensor inclines downwards by an angle beta along the ground, and the angle beta is 90-theta0/2, where θ0Is the angular range of the vertical field of view of the three-dimensional depth sensor; a light shielding plate is arranged above the three-dimensional depth sensor, the light shielding plate is parallel to the horizontal viewing plane of the three-dimensional depth sensor, and the extending length L of the light shielding plate is B · tan (theta)0/2) wherein B isAnd the vertical distance from the center of the lens of the three-dimensional depth sensor to the light shielding plate.
According to the scheme, for the return operation path scheme of the grain harvester, three-dimensional depth sensors are symmetrically arranged on two sides of a harvester body; for the winding work path solution, a three-dimensional depth sensor is mounted on only one side of the harvester body.
An unmanned operation method of a grain harvester comprises a distant view and close view combined stubble cutting multi-information detection method, a spike head area measurement method, a lodging judgment method and an unmanned operation process of the grain harvester.
Further, the method for detecting the stubble cutting multi-information of the distant view and the near view combination specifically comprises the following steps: the three-dimensional depth sensor has an effective depth detection range of [ D1,D2]The method includes the steps that information of a stubble cutting surface with a certain length is obtained, a transverse ridge is detected in advance, and the grain harvester is guided to accurately move to finish grain harvesting; within the field of view of the three-dimensional depth sensor, starting from the rear edge line of the horizontal field of viewThe information of the cutting surface in the angle is used as a cutting near scene area, and the detection and measurement of the head area of the spike are completed in the cutting near scene area; wherein
Further, the ear head area measuring method specifically comprises the following steps: extracting the boundary line of the ear area and the straw area along the vertical direction in the infrared reflection intensity diagram, detecting the ear area, and detecting the depth of the upper boundary line and the lower boundary line of the ear areaCalculating the height H of the ear head region (15)2Wherein i is 1, 2, 3, 4 ┄ ┄.
Further, the lodging judgment method specifically comprises the following steps: in the stubble cutting plane, the depth from the upper and lower boundary lines of the grains (5) Obtaining the height H of the grain (5)3When height H3Is above a grain height threshold [ Delta H ]]Judging that a lodging region appears in the stubble cutting surface; when the height H is3Is at a grain height threshold [. DELTA.H ]]When the current value is within the range, the lodging region is judged to be ended, wherein j is 1, 2, 3 and 4 ┄ ┄.
Further, for the reentry work path approach, the grain harvester unmanned work comprises the steps of:
step one, the grain harvester enters a field, so that the outer side of the header is aligned to the longitudinal boundary surface of grains in the field;
starting an unmanned operation mode, taking a longitudinal boundary surface detected by a three-dimensional depth sensor at the outer side as a forward old stubble cutting surface, calling a stubble cutting multi-information detection method of a distant view and a near view combination, and acquiring information of the stubble cutting surface and a stubble cutting near view area by the three-dimensional depth sensor;
step three, the grain harvester automatically performs initial adjustment on the header according to the transverse deviation and the course angle deviation of the header relative to the forward old stubble surface, and then controls the harvester to automatically advance along the forward old stubble surface through the transverse deviation and the course angle deviation so as to harvest grains;
step four, calling a spike head region measuring method, and measuring the height H of the spike head region2Judging the feeding amount, and automatically adjusting the advancing speed of the grain harvester according to the feeding amount;
step five, calling a lodging judgment method, judging whether a lodging area of grains exists in front according to a grain height change threshold value [ Delta H ], finishing the judgment of the appearance and the end position of the lodging area, further automatically adjusting the height of the header, and finishing the harvesting of the grains in the lodging area;
step six, when the three-dimensional depth sensor is in [ D ]1,D2]The transverse ridge is detected in advance and the header arrivesTransverse ridges are used for completing one-time harvesting operation according to the forward operation pose and generating a forward new stubble cutting surface;
step seven, the grain harvester automatically turns around for 180 degrees, the three-dimensional depth sensor at the other side detects a forward new stubble cutting surface, the harvester sequentially calls a distant and close view combined stubble multi-information detection method, a spike head region measurement method and a lodging judgment method along the forward new stubble cutting surface, and grain harvesting operation is completed according to turning-back operation poses in the step two to the step five;
and step eight, repeating the steps until the harvesting operation of the grains is finished.
Further, for the winding work path scheme, the unmanned work of the grain harvester comprises the steps one to six and the step eight, and the step seven is replaced by the step seven':
seventhly, the grain harvester circles along the transverse ridge, the three-dimensional depth sensor on the outer side detects the reverse stubble cutting surface of the circle, the distant and near view combined stubble multi-information detection method, the spike head area measurement method and the lodging judgment method are sequentially called along the reverse stubble cutting surface of the circle, and grain harvesting operation is completed according to the operation pose of the circle in the second step to the fifth step.
The invention has the beneficial effects that:
the invention realizes synchronous acquisition of stubble cutting surfaces, field heads, feeding amount and lodging information and unmanned harvesting operation of self-adaption of the feeding amount and lodging by real-time far and near scene combined detection based on the synchronous depth-infrared intensity characteristic and the vehicle body arrangement of the three-dimensional depth sensor, has simple system structure, good stability and real-time performance and good adaptability to different fields, grains and the like.
Drawings
In order to more clearly illustrate the embodiment of the present invention or the technical solutions in the prior art, the drawings used in the description of the prior art will be briefly introduced below.
FIG. 1 is a schematic top view of a grain harvester operating in the field in an example of the invention;
FIG. 2 is a schematic side view of a grain harvester according to an embodiment of the present invention in field operation;
FIG. 3 is a schematic view of the relationship change between the stubble and the header and the configuration of a dual three-dimensional depth sensor in the turning operation according to the embodiment of the present invention;
FIG. 4 is a schematic view of the height measurement principle of the three-dimensional depth sensor in the example of the present invention;
FIG. 5 is a schematic top view of a three-dimensional depth sensor arrangement in an example of the present invention;
FIG. 6 is a schematic diagram of a three-dimensional depth sensor arrangement in an example of the present invention at a head-up level;
FIG. 7 is a schematic diagram of the detection of the ear tip region and lodging in an embodiment of the invention.
In the figure: 1. the harvester comprises a harvester body, 2 cutting tables, 3 three-dimensional depth sensors, 4 forward old cutting surfaces, 4 'forward new cutting surfaces, 4' winding reverse cutting surfaces, 5 grains, 6 lodging regions, 7 horizontal view field rear side lines, 8 horizontal view field front side lines, 9 horizontal ridges, 10 shading plates, 11 sun, 12 vertical view field upper side lines, 13 ground, 14 vertical view field lower side lines, 15 ear head regions, 16 straw regions, 4 straw regions and a plurality of cutting blades, wherein the cutting blades are arranged on the harvester body, the cutting tables are arranged on the two sides of the harvester body, and the cutting blades are arranged on the two sides of the harvester bodyLCutting of stubble surface, S1The acquired area, S2Non-harvested area, a forward working attitude, a' reentry working attitude, a ". circle working attitude, 4CNear-scene areas for cutting stubbles.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1 and 2, the grain harvester is composed of a harvester body 1 and a header 2; referring to fig. 1 and 3, when the grain 5 is harvested by the grain harvester, the harvested area S is a harvested area S1And an unharvested region S2Between which a stubble cutting surface 4 is formedL(ii) a When the grain 5 is harvested, the left side of the header 2 is aligned with the forward old stubble cutting surface 4 to advance according to the width of the header 2 to harvest the grain 5, and the grain 5 is harvested by the header 2 to form a forward new stubble cutting surface 4'; the forward direction of the grain harvester entering the field to start harvesting is taken as the forward direction, and when the grain harvester enters the field to start harvesting, the longitudinal boundary surface of the grain 5 in the field in the forward direction of the harvesting operation is taken as the forward old stubble cutting surface 4.
As shown in fig. 3, grain harvesters typically have two field harvest path options:
(1) folding work path plan: the grain harvester carries out forward operation according to a forward operation pose A, and the left side of the header 2 is aligned with the forward old stubble cutting surface 4; the grain harvester turns around for 180 degrees after reaching the field head, the grain harvester advances according to the turn-back operation pose A ', the right side of the cutting table 2 is aligned with the forward new stubble cutting surface 4', and the cutting webs before and after turn-back are connected;
(2) winding operation path scheme: the grain harvester carries out forward operation according to a forward operation pose A, and the left side of the header 2 is aligned with the forward old stubble cutting surface 4; the grain harvester circles along the field head after reaching the field head, the grain harvester moves forward according to the circle operation pose A ', and the left side of the cutting table 2 is aligned with the circle reverse stubble cutting surface 4'.
In the case of the loop work path, when the grain harvester performs the first loop work, the longitudinal boundary surface of the grain 5 in the field, which is the reverse to the harvester work, is defined as the loop reverse stubble cutting surface 4 ″.
The three-dimensional depth sensor 3 obtains three-dimensional depth information of an object in a view field through active emission and diffuse reflection receiving of an infrared light sourceAnd synchronizing infrared reflection intensity informationWhereinIs a horizontal angular coordinate, theta is a vertical angular coordinate,as a coordinate pointThe depth value of the object of (1),as a coordinate pointThe infrared reflection intensity of the object of (1); the effective depth detection range of the three-dimensional depth sensor 3 is [ D ]1,D2]The field range of the three-dimensional depth sensor 3 is: angular extent of horizontal field of viewAngular extent of vertical field of view theta0The three-dimensional depth sensor 3 of the present embodiment is a RealSense D435 type depth sensor, and has an angular range of a horizontal field of viewAnd the angular extent theta of the vertical field of view091.2 deg. and 65.5 deg., respectively.
As shown in fig. 4, the three-dimensional depth sensor 3 can quickly realize height measurement of a vertical object according to the acquired depth information:
in the formula (1), EF is the height of the vertical object observed by the three-dimensional depth sensor 3, and DEAnd DFThe depth distance values of the highest point and the lowest point of the observed object are respectively, and epsilon is the relative visual angle occupied by the observed object in the vertical direction.
As shown in FIG. 5, in order to realize the unmanned operation of the grain harvester, the three-dimensional depth sensor 3 is installed on the harvester body 1, and during the harvesting operation, the three-dimensional depth sensor 3 and the stubble cutting surface 4LPerpendicular distance D between0And a minimum effective depth detection threshold D of the three-dimensional depth sensor 31Making the vertical viewing surface of the three-dimensional depth sensor 3 form an included angle alpha with the longitudinal center line of the harvester body, wherein alpha is the horizontal viewing angle of the three-dimensional depth sensor 31/2 so as to lead the horizontal field of viewThe line 8 is parallel to the longitudinal center line of the harvester body; the three-dimensional depth sensor 3 of the present embodiment is a RealSense D435 type depth sensor, and the minimum effective depth detection threshold D1Is 200 mm.
As shown in FIG. 6, the height H of the three-dimensional depth sensor 3 from the ground 13 is set1Not less than the maximum plant height [ H ] of the applicable grain 5 of the grain harvester]And is not higher than the maximum plant height [ H ] of the grain 5 suitable for the harvester]1.2 times of that of [ H ]]≤H1≤1.2[H](ii) a The horizontal viewing surface of the three-dimensional depth sensor 3 is inclined downwards along the ground 13 by an angle beta, wherein beta is 90-theta0A vertical view lower edge line 14 of the three-dimensional depth sensor 3 is perpendicular to the ground surface 13, a light shielding plate 10 is mounted above the three-dimensional depth sensor 3, the light shielding plate 10 is parallel to a horizontal view surface of the three-dimensional depth sensor 3, and the light shielding plate 10 has a protrusion length L, L being B · tan (θ)0/2) such that the vertical field of view upper edge line 12 of the three-dimensional depth sensor 3 is parallel to the ground 13; where B is the vertical distance from the lens center of the three-dimensional depth sensor 3 to the light shielding plate 10. The installation requirements of the three-dimensional depth sensor 3 in the horizontal and vertical directions ensure that the three-dimensional depth sensor 3 effectively obtains the stubble cutting surface 4LAnd when information and transverse ridge 9 information are obtained, redundant information caused by overlarge view field is effectively reduced, direct irradiation of the light rays of the sun 11 to the lens of the three-dimensional depth sensor 3 is avoided, and the precision and stability of depth detection under field conditions are improved.
The three-dimensional depth sensor 3 is installed in the direction shown in fig. 5 and 6, so that the orientations of the vertical viewing surface and the horizontal viewing surface of the three-dimensional depth sensor 3 are changed, but the vertical viewing surface is still perpendicular to the ground, and therefore ∈ in equation (1) is the relative angle of view that the object to be observed occupies in the vertical field of view of the three-dimensional depth sensor 3.
As shown in fig. 3, for the turning-back operation path scheme, the left side of the header 2 is aligned with the old forward stubble surface 4 during forward operation of the grain harvester, the right side of the header 2 is aligned with the new forward stubble surface 4' during turning-back operation, and the three-dimensional depth sensors 3 are symmetrically arranged on the left side and the right side of the harvester body 1 according to the installation requirements of the horizontal direction and the vertical direction, so that the requirement of unmanned operation of the grain harvester based on three-dimensional depth vision is met(ii) a For the circle operation path scheme, the grain harvester is aligned to the stubble cutting surface 4 at the left side of the cutting table 2 in the forward operation pose A and the circle operation pose A ″LOnly one three-dimensional depth sensor 3 is symmetrically arranged on the left side of the harvester body 1 according to the installation requirements of the horizontal direction and the vertical direction, and the unmanned operation requirement of the grain harvester based on three-dimensional depth vision is met.
The grain harvester unmanned operation method based on the three-dimensional depth vision comprises a distant view and near view combined stubble multi-information detection method, a spike head region measurement method, a lodging judgment method and a grain harvester unmanned operation process, wherein the distant view and near view combined stubble multi-information detection method, the spike head region measurement method and the lodging judgment method are stored in a controller.
As shown in fig. 5 and 7, the method for detecting multiple stubble cutting information in a distant view and a near view comprises: the three-dimensional depth sensor 3 has an effective depth detection range [ D1,D2]A stubble cutting surface 4 with a certain length is obtained insideLAnd detecting the transverse ridges 9 in advance to guide the grain harvester to accurately move to finish the harvesting of the grains 5; within the field of view of the three-dimensional depth sensor 3, starting from the horizontal field of view rear edge line 7 Cutting surface 4 obtained in angleLThe information part is used as a cutting near scene area 4CIn the near-to-crop area 4CThe detection and measurement of the spike head area 15 are completed; whereinAs the three-dimensional depth sensor 3 of the present embodiment, a RealSense D435 type depth sensor is used, and the maximum detection length that can be obtained is 10 m.
As shown in fig. 6, the spike-head region measurement method is: on the stubble cutting surface 4LInner stubble-cutting near-field 4CSince the ear head region 15 is dense in material and has many reflection data points, the infrared reflection intensity of the ear head region 15Is obviously higher than the straw area 16 according to the infrared reflection intensityThe extraction of the boundary line between the ear area 15 and the straw area 16 along the vertical direction is realized in the infrared reflection intensity diagram, the detection of the ear area 15 is realized, and the detection is carried out according to the depths of the upper and lower boundary lines of the ear area 15 (i is 1, 2, 3, 4 ┄ ┄), and the height H of the ear region 15 is calculated from the formula (1)2. Wherein H2Corresponding to EF in the formula (1), in the depth coordinate of the boundary line on the ear head regionCorresponds to D in the formula (1)EIn the depth coordinate of the lower boundary of the ear-head regionCorresponds to D in the formula (1)F,θiCorresponds to ε in the formula (1).
The lodging judgment method comprises the following steps: on the stubble cutting surface 4LInner, according to the depth of the upper and lower boundary lines of grain 5 (j-1, 2, 3, 4 ┄ ┄), and the height H of grain 5 is calculated from formula (1)3. Wherein H3Corresponding to EF in the formula (1), in the depth coordinate of the upper boundary line of the grain 5Corresponds to D in the formula (1)EIn the depth coordinate of the lower boundary line of grain 5Corresponds to D in the formula (1)F,θjCorresponding to epsilon in formula (1); when the height H of the grain 53Is greater than a grain height variation threshold [ Delta H ]]In this case, it is judged that there is a lodging region 6 of grain 5 in front, and a larger Δ H indicates a more serious lodging of grain 5. The grain height variation threshold [ Delta H ] is set in the controller in advance]Height H of grain 53Is greater than a grain height variation threshold [ Delta H ]]Then, it is judged that the cutting surface 4 isLA lodging region 6 is formed inside; when the height H of the grains 5 is equal to3Is at a grain height variation threshold [ Delta H ]]When the range is within the range, it is judged that the lodging region 6 is ended.
For the reentry operation path scheme, the unmanned operation process of the grain harvester comprises the following steps:
step (1): an operator operates the grain harvester to enter a field, the operator adjusts the grain harvester to enable the left side of the header 2 to be approximately aligned with the longitudinal boundary surface of grains 5 in the field, and the unmanned operation mode is started;
step (2): the left three-dimensional depth sensor 3 detects the longitudinal boundary surface of the grains 5 in the field, the longitudinal boundary surface of the grains 5 in the field is regarded as a forward old stubble cutting surface 4, the controller calls a stubble cutting multi-information detection method of a distant view and close view combination, and the three-dimensional depth sensor 3 simultaneously obtains the stubble cutting surfaces 4 with certain lengthLAnd a stubble-cutting near scene area 4CThe information of (a);
and (3): the grain harvester firstly automatically performs initial adjustment on the header 2 according to the transverse deviation and the course angle deviation of the header 2 relative to the forward old stubble surface 4, and then controls the grain harvester to automatically advance along the forward old stubble surface 4 through the transverse deviation and the course angle deviation of the header 2 relative to the forward old stubble surface 4 so as to perform harvesting operation of grains 5;
and (4): the controller calls a spike head region measuring method to measure the spike head region in the stubble cutting near scene region 4CThe height H of the ear tip region 15 is obtained by internal calculation2According to the height H of the fringe head region 152The feeding quantity is judged, and then the advancing speed of the grain harvester is automatically adjusted according to the feeding quantity, so that the blockage of the header 2 is avoidedThe harvesting operation efficiency is improved while the plug is plugged;
and (5): the controller calls a lodging judgment method to cut the stubble surface 4LInternal height H of grain 53And according to a grain height variation threshold [ Delta H ]]Judging whether a lodging area 6 of grains 5 exists in front, finishing the judgment of the appearance and the end position of the lodging area 6, and further automatically adjusting the height of the header 2 so as to finish the harvesting of the grains 5 in the lodging area 6;
and (6): when the three-dimensional depth sensor 3 is in the effective depth detection range [ D ]1,D2]A transverse ridge 9 is detected in advance, the header 2 of the grain harvester reaches the transverse ridge 9, one-time harvesting operation according to the forward operation pose A is completed, and a forward new stubble cutting surface 4' is generated;
and (7): the controller controls the grain harvester to automatically complete 180-degree turning, the three-dimensional depth sensor 3 on the right side detects the forward new stubble cutting surface 4 ', and sequentially calls a distant and close view combined stubble cutting multi-information detection method, a spike head area measurement method and a lodging judgment method along the forward new stubble cutting surface 4 ', and the grain 5 harvesting operation is completed according to the turning operation pose A ' in the steps (2), (3), (4) and (5);
and (8): and the process is repeated until the harvesting operation of the grains 5 is finished.
For the scheme of the winding operation path, the step (7) is replaced by the step (7') in the unmanned operation process of the grain harvester:
step (7'): the controller controls the grain harvester to wind along the transverse ridge 9, the three-dimensional depth sensor 3 on the left side detects the reverse stubble cutting surface 4 of the wind, and the multi-information stubble cutting detection method, the spike head region measurement method and the lodging judgment method which are combined in a distant view and a near view are called in sequence along the reverse stubble cutting surface 4 'of the wind, and the grain 5 harvesting operation is completed according to the operation pose A' of the wind in the steps (2), (3), (4) and (5).
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The utility model provides a grain harvester unmanned operation system which characterized in that: the three-dimensional depth sensor (3) is arranged on the harvester body (1), and the three-dimensional depth sensor (3) and the stubble cutting surface (4) are arranged during harvesting operationL) Vertical distance D of0With the minimum effective depth detection value D of the three-dimensional depth sensor (3)1The vertical viewing surface of the three-dimensional depth sensor (3) forms an included angle alpha with the longitudinal center line of the harvester body, and the alpha is the horizontal viewing angle of the three-dimensional depth sensor (3)1/2 of (1); height H of three-dimensional depth sensor (3) from ground (13)1Is in the value range of [ H ]]≤H1≤1.2[H]Wherein [ H ]]The maximum plant height of the applicable grain (5) of the grain harvester; the horizontal viewing surface of the three-dimensional depth sensor (3) is inclined downwards by an angle beta along the ground (13), and the angle beta is 90-theta0/2, where θ0Is the angular range of the vertical field of view of the three-dimensional depth sensor (3); a light screen (10) is arranged above the three-dimensional depth sensor (3), the light screen (10) is parallel to the horizontal viewing plane of the three-dimensional depth sensor (3), and the extending length L of the light screen (10) is B-tan (theta)0And/2), wherein B is the vertical distance from the lens center of the three-dimensional depth sensor (3) to the light shielding plate (10).
2. The grain harvester unmanned aerial vehicle system of claim 1, wherein: for the return operation path scheme of the grain harvester, three-dimensional depth sensors (3) are symmetrically arranged on two sides of a harvester body (1); for the winding operation path scheme, a three-dimensional depth sensor (3) is arranged on one side of the harvester body (1).
3. A method of operating the grain harvester unmanned operating system of claim 1, wherein: the method comprises a distant view and perspective view combined stubble cutting multi-information detection method, a spike head region measuring method, a lodging judgment method and a grain harvester unmanned operation process.
4. The method of claim 3, wherein the method comprises: the method for detecting the stubble cutting multi-information of the distant view and the near view combination specifically comprises the following steps: the three-dimensional depth sensor (3) has an effective depth detection range [ D1,D2]A stubble cutting surface (4) with a certain length is obtained insideL) Information and a transverse ridge (9) are detected in advance, and the grain harvester is guided to accurately move to finish the harvesting of the grains (5); within the field of view of the three-dimensional depth sensor (3), starting from the horizontal field of view rear edge line (7)The stubble cutting surface (4) within the angleL) Information as a crop-cutting near scene (4)C) In the near-by area (4)C) Detecting and measuring the inner complete spike head area (15); wherein
5. The method of operating the unmanned grain harvester operating system of claim 4, wherein: the ear head area measuring method specifically comprises the following steps: extracting the boundary line of the ear area (15) and the straw area (16) along the vertical direction in the infrared reflection intensity diagram, detecting the ear area (15), and detecting the depth of the upper and lower boundary lines of the ear area (15)Calculating the height H of the ear head region (15)2Wherein i is 1, 2, 3, 4 … ….
6. The method of operating the unmanned grain harvester operating system of claim 5, wherein: what is needed isThe lodging judgment method specifically comprises the following steps: on the stubble cutting surface (4)L) The depth of the upper and lower boundary lines of the grain (5)Obtaining the height H of the grain (5)3When height H3Is above a grain height threshold [ Delta H ]]Then, it is judged that the cutting surface (4) isL) A lodging region (6) is formed; when the height H is3Is at a grain height threshold [. DELTA.H ]]When the current value is within the range, the lodging region (6) is judged to be ended, wherein j is 1, 2, 3 and 4 ┄ ┄.
7. The method of operating the unmanned grain harvester operating system according to any one of claims 3 to 6, wherein: for the reentry path solution, the grain harvester unmanned operation comprises the following steps:
step one, the grain harvester enters a field block, so that the outer side of the cutting table (2) is aligned to the longitudinal boundary surface of grains (5) in the field block;
step two, starting an unmanned operation mode, regarding a longitudinal boundary surface detected by the three-dimensional depth sensor (3) at the outer side as a forward old stubble cutting surface (4), calling a stubble cutting multi-information detection method of a distant and close scene combination, and acquiring the stubble cutting surface (4) by the three-dimensional depth sensor (3)L) And a near-field area (4)C) The information of (a);
step three, the grain harvester automatically performs initial adjustment on the header (2) according to the transverse deviation and the course angle deviation of the header (2) relative to the forward old stubble surface (4), and then controls the grain harvester to automatically advance along the forward old stubble surface (4) through the transverse deviation and the course angle deviation so as to harvest grains;
step four, invoking a spike head region measuring method, and measuring the height H of the spike head region (15)2Judging the feeding amount, and automatically adjusting the advancing speed of the grain harvester according to the feeding amount;
step five, calling a lodging judgment method, judging whether a lodging area (6) of the grains (5) exists in front according to a grain height change threshold value [ Delta H ], finishing the judgment of the appearance and the end position of the lodging area (6), further automatically adjusting the height of the header (2), and finishing the harvesting of the grains in the lodging area (6);
step six, when the three-dimensional depth sensor (3) is in [ D ]1,D2]A transverse ridge (9) is detected in advance, the header (2) reaches the transverse ridge (9), one-time harvesting operation is completed according to the forward operation pose (A), and a forward new stubble cutting surface (4') is generated;
seventhly, the grain harvester automatically turns around for 180 degrees, the three-dimensional depth sensor (3) on the other side detects a forward new stubble cutting surface (4 '), the harvester sequentially calls a distant and near view combined stubble cutting multi-information detection method, a spike head area measurement method and a lodging judgment method along the forward new stubble cutting surface (4 '), and the grain (5) harvesting operation is completed according to the turning-back operation pose (A ') in the second step to the fifth step;
and step eight, repeating the steps until the harvesting operation of the grains (5) is finished.
8. The method of claim 7, wherein the method comprises: for the winding work path solution, the grain harvester unmanned work comprises steps one to six and step eight, and step seven' is substituted for step seven:
seventhly ', the grain harvester winds along the transverse ridge (9), the three-dimensional depth sensor (3) on the outer side detects a winding reverse stubble cutting surface (4 "), a distant and near view combined stubble cutting multi-information detection method, a spike head area measurement method and a lodging judgment method are sequentially called along the winding reverse stubble cutting surface (4"), and the grain (5) is harvested according to the winding operation pose (A') in the second step to the fifth step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811531486.6A CN109634277B (en) | 2018-12-14 | 2018-12-14 | Unmanned operation system and operation method for grain harvester |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811531486.6A CN109634277B (en) | 2018-12-14 | 2018-12-14 | Unmanned operation system and operation method for grain harvester |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109634277A CN109634277A (en) | 2019-04-16 |
CN109634277B true CN109634277B (en) | 2021-10-08 |
Family
ID=66073883
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811531486.6A Active CN109634277B (en) | 2018-12-14 | 2018-12-14 | Unmanned operation system and operation method for grain harvester |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109634277B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11758844B2 (en) * | 2020-03-19 | 2023-09-19 | Deere & Company | Forward-looking perception and machine control during crop harvesting operations |
CN113016331B (en) * | 2021-02-26 | 2022-04-26 | 江苏大学 | Wide-narrow row ratoon rice harvesting regulation and control system and method based on binocular vision |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103155758A (en) * | 2013-03-12 | 2013-06-19 | 上海大学 | Laser navigation system of unmanned combine-harvester |
CN105700533A (en) * | 2016-04-22 | 2016-06-22 | 扬州大学 | Agricultural machinery automatic driving control system based on Beidou navigation and method thereof |
CN106919901A (en) * | 2017-01-20 | 2017-07-04 | 江苏大学 | A kind of depth ball transversal method of spherefruit identification in strain |
CN106954426A (en) * | 2017-03-23 | 2017-07-18 | 江苏大学 | A kind of robot based on close shot depth transducer approaches positioning picking method in real time |
CN108021130A (en) * | 2017-11-07 | 2018-05-11 | 北京勇搏科技有限公司 | A kind of unpiloted harvester |
CN108496533A (en) * | 2017-02-27 | 2018-09-07 | 西北农林科技大学 | A kind of unmanned combine harvester Laser navigation system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9696162B2 (en) * | 2015-09-17 | 2017-07-04 | Deere & Company | Mission and path planning using images of crop wind damage |
-
2018
- 2018-12-14 CN CN201811531486.6A patent/CN109634277B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103155758A (en) * | 2013-03-12 | 2013-06-19 | 上海大学 | Laser navigation system of unmanned combine-harvester |
CN105700533A (en) * | 2016-04-22 | 2016-06-22 | 扬州大学 | Agricultural machinery automatic driving control system based on Beidou navigation and method thereof |
CN106919901A (en) * | 2017-01-20 | 2017-07-04 | 江苏大学 | A kind of depth ball transversal method of spherefruit identification in strain |
CN108496533A (en) * | 2017-02-27 | 2018-09-07 | 西北农林科技大学 | A kind of unmanned combine harvester Laser navigation system |
CN106954426A (en) * | 2017-03-23 | 2017-07-18 | 江苏大学 | A kind of robot based on close shot depth transducer approaches positioning picking method in real time |
CN108021130A (en) * | 2017-11-07 | 2018-05-11 | 北京勇搏科技有限公司 | A kind of unpiloted harvester |
Non-Patent Citations (2)
Title |
---|
基于机器视觉的谷物联合收获机行走目标直线检测;吴刚 等;《农业机械学报》;20121031;第43卷;266-270 * |
自然光照下智能叶菜收获机作业参数的获取;伍渊远 等;《浙江农业学报》;20171121;第29卷(第11期);1930-1936 * |
Also Published As
Publication number | Publication date |
---|---|
CN109634277A (en) | 2019-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9603300B2 (en) | Autonomous gardening vehicle with camera | |
US9002566B2 (en) | Visual, GNSS and gyro autosteering control | |
EP3119178B1 (en) | Method and system for navigating an agricultural vehicle on a land area | |
US8712144B2 (en) | System and method for detecting crop rows in an agricultural field | |
AU2006202804B2 (en) | Method and system for vehicular guidance using a crop image | |
AU2006202812B2 (en) | Method and system for vehicular guidance using a crop image | |
US8855405B2 (en) | System and method for detecting and analyzing features in an agricultural field for vehicle guidance | |
KR101651600B1 (en) | Unmanned aerial drone having automatic landing function by stereo camera | |
CN109634277B (en) | Unmanned operation system and operation method for grain harvester | |
WO2022107588A1 (en) | Moving body, control unit, data generation unit, method for controlling moving body motion, and method for generating data | |
US20230288942A1 (en) | Mobile machine, data generation unit, and method of generating data | |
CN108196538A (en) | Field robots autonomous navigation system and method based on three-dimensional point cloud model | |
Rovira-Más et al. | Navigation strategies for a vineyard robot | |
CN115280960A (en) | Combine harvester steering control method based on field vision SLAM | |
Möller | Computer vision–a versatile technology in automation of agricultural machinery | |
CN113273375A (en) | Mower system capable of automatically planning path and automatic mower thereof | |
EP4356706A1 (en) | Method for controlling a vehicle for harvesting agricultural material | |
CN111623706B (en) | Caragana microphylla stubble leveling machine information acquisition method | |
WO2024004574A1 (en) | Work vehicle, control method and computer program | |
CN117873054A (en) | Unmanned method and system for intelligent harvester | |
WO2022107586A1 (en) | Moving body, control unit, and method for controlling operation of moving body | |
WO2024004575A1 (en) | Work vehicle and method for controlling work vehicle | |
WO2023276226A1 (en) | Crop row detection system, agricultural machine equipped with crop row detection system, and crop row detection method | |
WO2023243514A1 (en) | Work vehicle and method for controlling work vehicle | |
WO2023120182A1 (en) | Agricultural machine |
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 |
Effective date of registration: 20231130 Address after: 417700 Shuangfeng County Science and Technology Industrial Park, Loudi City, Hunan Province, 457 Hesen Avenue West Patentee after: Hunan Xiangyuan Jinsui Intelligent Equipment Co.,Ltd. Address before: Zhenjiang City, Jiangsu Province, 212013 Jingkou District Road No. 301 Patentee before: JIANGSU University |
|
TR01 | Transfer of patent right |