CN108759829B - Local obstacle avoidance path planning method for intelligent forklift - Google Patents
Local obstacle avoidance path planning method for intelligent forklift Download PDFInfo
- Publication number
- CN108759829B CN108759829B CN201810263821.2A CN201810263821A CN108759829B CN 108759829 B CN108759829 B CN 108759829B CN 201810263821 A CN201810263821 A CN 201810263821A CN 108759829 B CN108759829 B CN 108759829B
- Authority
- CN
- China
- Prior art keywords
- point
- points
- path
- obstacle avoidance
- forklift
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
Abstract
The invention discloses a local obstacle avoidance path planning method for an intelligent forklift, which comprises the following steps: establishing an environment global coordinate system according to the navigation type laser scanning sensor; and detecting the surrounding environment information by using a ranging type laser scanning sensor. And analyzing and processing the obtained data, and extracting all the characteristic points. And selecting a proper point from the characteristic points as a small target point and a B spline curve control point. And generating a B-spline curve path and executing. The invention can not generate the false image that obstacles are everywhere and no road can be moved, and has high obstacle avoidance driving efficiency; the extraction of the characteristic points is very accurate, a path with strict pose requirements on a start point and a stop point can be quickly planned in a complex environment, and the generated path also meets the vehicle kinematics requirement and the vehicle body size constraint; and the B-spline curve is used for planning the local obstacle avoidance path of the intelligent forklift, so that the planning process is simpler and quicker, the selection of the control point is more exquisite, and the positions and postures of the starting point and the stopping point of the planned path can be ensured to meet the requirements.
Description
Technical Field
The invention relates to the field of intelligent forklifts, in particular to a local obstacle avoidance path planning method for an intelligent forklift.
Background
The system is convenient to control, reduces casualty accidents, reduces enterprise operation cost, and is suitable for national development strategy planning of '2025 made by China', the technology of the forklift varies day by day, and particularly the intellectualization of the forklift; the intelligent forklift does not need manual operation and control in the working process, can independently complete stacking and goods taking, and has a motor industrial vehicle with preliminary artificial intelligence. In the operation process of the intelligent forklift, the intelligent forklift inevitably encounters some unpredictable obstacles, cannot run along an originally planned path due to the influence of the obstacles, and needs to plan a path again to avoid the obstacles to reach a target point. At present, most of researches on local obstacle avoidance path planning of the intelligent forklift at home and abroad include a BUG algorithm, an artificial potential field method, a bionic method, a bubble belt technology, a curvature speed technology, a dynamic window method and the like, and most of obstacle processing modes are modes of surrounding circles or surrounding boxes, so that the mode is easy to generate the false appearance that obstacles exist everywhere and no way can be taken; or the collision is avoided in a mode of bypassing along the boundary of the obstacle, although the mode can successfully avoid the obstacle, the driving efficiency is relatively low, and the requirement of the planned path on the pose constraint is not strict.
The local obstacle avoidance path planning refers to local path planning which is performed by using environmental data obtained by a sensor to successfully reach a target point by avoiding an unknown obstacle in the driving process when the intelligent forklift reaches the target point position.
Accordingly, further improvements and improvements are needed in the art.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for local path planning by utilizing environmental data obtained by a sensor on an intelligent forklift.
The purpose of the invention is realized by the following technical scheme:
a local obstacle avoidance path planning method for an intelligent forklift comprises the following steps:
step S1: establishing an environment global coordinate system according to the navigation type laser scanning sensor; and detecting the surrounding environment information by using a ranging type laser scanning sensor.
Step S2: and analyzing and processing the obtained sensor data, and extracting all characteristic points in the environment.
Step S3: and selecting a proper point from the obtained characteristic points as a small target point and a B spline curve control point.
Step S4: and generating a B-spline curve path and executing.
Step S5: until the final target point is reached, otherwise the above steps S1-S4 are repeated.
As a preferable scheme, the step S1 specifically includes:
the method comprises the steps of asymmetrically pasting reflective labels in the working environment of the intelligent forklift, establishing a Cartesian global coordinate system by utilizing the scanning environment of a navigation type laser scanning sensor, calculating the global coordinate of the current position point of each sensor according to the current global position information and the size parameters of the forklift body obtained by the navigation type laser scanning sensor and the position relation among the sensors, and converting the relative coordinates of surrounding objects obtained by a distance measurement type laser scanning sensor into the global coordinate.
Furthermore, the navigation type laser scanning sensor is arranged in the middle of the top end of the forklift and has equal distance to the four wheels; the positive direction of a cross shaft of a coordinate axis of the sensor is the forward direction of the forklift, and after a global coordinate system is established, the included angle between the positive direction of the cross shaft of the sensor and the positive direction of the cross shaft of the global coordinate system is the direction angle of the forklift body; the distance measurement type laser scanning sensor is arranged in the middle of the front head of the forklift, the scanning range is generally set to be 0-180 degrees according to needs, and the obtained polar coordinate data result needs to be converted by combining the set angular resolution of the sensor and the obtaining sequence of each data.
As a preferable scheme, the step S2 specifically includes:
firstly, marking a first point of obtained data as a characteristic point, selecting a plurality of continuous points on the basis of the characteristic point, making a straight line between the first point and the last point, judging whether the distance between the other points in the middle and the straight line is less than a set threshold value, if so, adding a point in sequence on the basis of the selected point, repeating the steps until the existing point is more than the threshold value, marking the added point as the characteristic point, and starting a new cycle on the basis of the characteristic point until all data are analyzed and processed.
As a preferable scheme, the step S3 specifically includes:
selecting all the required feature points with the distance from the connecting line of the current position point and the final target point smaller than a certain threshold value from all the feature points obtained in the step S2; then, the characteristic points are taken as the circle centers, a certain length value larger than half of the vehicle width is taken as a radius to make a circle, then tangent lines of the circle are respectively made through the current position points, and each circle can obtain two tangent points.
And further, respectively taking the obtained tangent point as the center of a circle and a certain length value larger than half of the car width as a radius to make a circle, judging whether more original data points exist in the circle, if so, rejecting the tangent point, and otherwise, keeping the tangent point.
Further, selecting a point closest to the current position point from the residual tangent points as a small target point, namely a first-to-last control point of the B-spline curve, and selecting a point which is very close to the small target point in the tangent direction of the tangent point and is close to the starting point as a second-to-last control point; simultaneously, taking the current position point of the forklift as a first control point, namely a path starting point; and selecting a point which is very close to the starting point in the current advancing direction of the forklift as a second control point. Finally, the middle point between the second control point and the penultimate control point can be selected as a new control point, or other points between the two control points can be selected as new control points according to requirements.
As a preferable scheme, the step S4 specifically includes:
and (5) realizing the local routing rules by using the control points obtained in the step (S3) in combination with a B-spline curve generation mode, and transmitting the result to a routing algorithm for execution.
Furthermore, as the forklift is driven at a low speed in a local obstacle avoidance process, in order to ensure the continuity of the steering angle and the rotation degree of the wheels in the driving process and reduce the program calculation amount, the B-spline curve is generally selected to be in a 4-order form; and the basis functions of the n-th order B-spline curve are as follows:
And B-spline curve expression:
Wherein n represents the order of the spline curve, m represents the curve formed by smoothly connecting m sections of spline curves, i represents the ith section of B spline curve, and P represents the number of the spline curvesi+kRepresenting the kth control point of the ith segment of the B-spline curve.
Further, the total number of the selected control points must be greater than the order of the selected B-spline curve; and calculating corresponding basis functions through the selected B-spline curve order, and combining the selected control points and the expression of the B-spline curve to obtain the function of each spline curve section of the planned path.
As a preferable scheme, the step S5 specifically includes:
when the target point can reach the final target point directly, namely the target point passes by the obstacle but does not reach the final target point, directly replacing the small target point in the steps, repeating the steps S3 and S4 until the final target point is reached and the pose meets the requirement; otherwise, the above steps S2, S3, S4 are repeated.
Compared with the prior art, the invention also has the following advantages:
(1) the local obstacle avoidance path planning method for the intelligent forklift does not generate the false image that obstacles are arranged everywhere and no road can be moved, does not sink into local traps, and is high in obstacle avoidance driving efficiency.
(2) The method for planning the local obstacle avoidance path of the intelligent forklift provided by the invention has the advantages that the extraction of the characteristic points is very accurate, the path meeting the strict pose requirements on the start point and the stop point can be quickly planned in a complex environment, and the generated path also meets the vehicle kinematics requirements and the vehicle body size constraint.
(3) According to the method for planning the local obstacle avoidance path of the intelligent forklift, the B-spline is used for planning the local obstacle avoidance path of the intelligent forklift, so that the planning process is simpler and quicker, only a proper control point needs to be selected, the selection of the control point is more exquisite, and the starting and stopping positions of the planned path can meet the requirements.
Drawings
Fig. 1 is a schematic view of a use scene of a local obstacle avoidance path planning method for an intelligent forklift provided by the invention;
fig. 2 is a work flow chart of a local obstacle avoidance path planning method for an intelligent forklift provided by the invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described below with reference to the accompanying drawings and examples.
Example 1:
as shown in fig. 1 and 2, the present invention discloses a local path planning method using environmental data obtained by a sensor to successfully reach a target point with strict pose requirements for avoiding an unknown obstacle when an intelligent forklift reaches the target point position. The method mainly comprises the following steps:
(1) establishing an environment global coordinate system according to the navigation type laser scanning sensor; and detecting the surrounding environment information by using a ranging type laser scanning sensor.
(2) And analyzing and processing the obtained sensor data, and extracting all characteristic points in the environment.
(3) And selecting a proper point from the obtained characteristic points as a small target point and a B spline curve control point.
(4) And generating a B-spline curve path and executing.
(5) And repeating the steps until the final target point is reached, otherwise.
The step (1) specifically comprises the following steps: a reflecting label is asymmetrically pasted in the working environment of the intelligent forklift, a Cartesian global coordinate system XOY is established by utilizing the scanning environment of a SICK-NAV 350 navigation type laser scanning sensor, then the global coordinate of the current position point of each sensor is calculated by using the current global position information and the vehicle body size parameters obtained by the SICK-NAV 350 navigation type laser scanning sensor and the position relation among the sensors, and then the relative coordinate of the surrounding object obtained by the SICK-LMS 111 ranging type laser scanning sensor is converted into the global coordinate.
The navigation type laser scanning sensor S is arranged in the middle of the top end of the forklift, the distances from the navigation type laser scanning sensor S to the four wheels are equal, the plane projection position can be shown in figure 1, and a bold polygon in the figure is an obstacle; the positive direction of a cross shaft X of a coordinate axis of the sensor is the advancing direction of the forklift, and after a global coordinate system XOY is established, the included angle between the X direction and the positive direction of the cross shaft X of the global coordinate system is the direction angle of the forklift body; the distance measuring type laser scanning sensor S1 is installed at the middle position of the front head of the forklift, the scanning range is generally set to 0 to 180 degrees as required, and the obtained polar coordinate data result needs to be converted by combining the set angular resolution of the sensor and the obtaining sequence of each data.
The sensor S has global coordinates of (x)s，ys，θs) The global coordinate of the sensor S1 is (x)s1，ys1，θs1) As is apparent from the above description, there are
θs＝θs1；
xs1＝xs+SS1*COSθs；
ys1＝ys+SS1*SINθs；
The step (2) specifically comprises the following steps: firstly, marking a first point of obtained data as a characteristic point, selecting a plurality of continuous points on the basis of the characteristic point, making a straight line between the first point and the last point, judging whether the distance between the other points in the middle and the straight line is less than a set threshold value, if so, adding a point in sequence on the basis of the selected point, repeating the steps until the existing point is more than the threshold value, marking the added point as the characteristic point, and starting a new cycle on the basis of the characteristic point until all data are analyzed and processed.
The step (3) specifically comprises the following steps: selecting all required feature points with the distance from the connecting line of the current position point and the final target point smaller than a certain threshold value from all the feature points obtained in the step (2); then, the characteristic points are taken as the circle centers, a certain length value larger than half of the vehicle width is taken as a radius to make a circle, then tangent lines of the circle are respectively made through the current position points, and each circle can obtain two tangent points.
And further, respectively taking the obtained tangent point as the center of a circle and a certain length value larger than half of the car width as a radius to make a circle, judging whether more original data points exist in the circle, if so, rejecting the tangent point, and otherwise, keeping the tangent point.
Further, selecting a point closest to the current position point from the residual tangent points as a small target point, namely a first-to-last control point of the B-spline curve, and selecting a point which is very close to the small target point in the tangent direction of the tangent point and is close to the starting point as a second-to-last control point; simultaneously, taking the current position point of the forklift as a first control point, namely a path starting point; and selecting a point which is very close to the starting point in the current advancing direction of the forklift as a second control point. Finally, the middle point between the second control point and the penultimate control point can be selected as a new control point, or other points between the two control points can be selected as new control points according to requirements.
The two points Q passing through the plane1(x1,y1) And point Q2(x2,y2) The straight line equation is:
y(x2-x1)-x(y2-y1)+x1y2-x2y1＝0
point Q0(x0,y0) The distance to this line is:
the step (4) specifically comprises the following steps: and (4) realizing local path gauge by using the control points obtained in the step (3) and combining a B-spline curve generation mode, and transmitting the result to a path tracking algorithm for execution.
Furthermore, as the forklift is driven at a low speed in a local obstacle avoidance process, in order to ensure the continuity of the steering angle and the rotation degree of the wheels in the driving process and reduce the program calculation amount, the B-spline curve is generally selected to be in a 4-order form; the corresponding basis functions are as follows:
and B-spline curve expression:
wherein n represents the order of the spline curve, m represents the curve formed by smoothly connecting m sections of spline curves, and i represents the ith section of B spline curveCurve, Pi+kA k-th control point, k-0, 1,2, ·, n, representing the i-th B-spline curve; u is an element of [0,1 ]]i＝1,2,···,m。
Further, the total number of the selected control points must be greater than the order of the selected B-spline curve; and calculating corresponding basis functions through the selected B-spline curve order, and combining the selected control points and the expression of the B-spline curve to obtain the function of each spline curve section of the planned path.
The step (5) specifically comprises: when the target point P can reach the final target point, namely the target point P is bypassed but not reached, directly replacing the small target point in the steps with the final target point, repeating the steps (3) and (4) until the final target point is reached and the pose meets the requirement; otherwise, repeating the steps (2), (3) and (4).
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (8)
1. A local obstacle avoidance path planning method for an intelligent forklift is characterized by comprising the following steps:
step S1: establishing an environment global coordinate system according to the navigation type laser scanning sensor; detecting surrounding environment information by using a ranging type laser scanning sensor;
step S2: analyzing and processing the obtained sensor data, and extracting all characteristic points in the environment;
step S3: selecting proper points from the obtained characteristic points as small target points and B spline curve control points;
the step S3 specifically includes:
selecting all the required feature points with the distance from the connecting line of the current position point and the final target point smaller than a certain threshold value from all the feature points obtained in the step S2; then, taking the characteristic points as circle centers one by one, taking a certain length value larger than half of the vehicle width as a radius to make a circle, and respectively making tangent lines of the circle through the current position point, wherein each circle obtains two tangent points; then, respectively taking the obtained tangent point as the circle center, taking a certain length value larger than half of the vehicle width as a radius to make a circle, judging whether more original data points exist in the circle, if so, rejecting the tangent point, and otherwise, keeping the tangent point;
step S4: generating a B spline curve path and executing;
step S5: until the final target point is reached, otherwise, steps S1 to S4 are sequentially repeated.
2. The method for planning a local obstacle avoidance path of an intelligent forklift according to claim 1, wherein the step S1 specifically includes the following operations:
the method comprises the steps of asymmetrically pasting reflective labels in the working environment of the intelligent forklift, establishing a Cartesian global coordinate system by utilizing the scanning environment of a navigation type laser scanning sensor, calculating the global coordinate of the current position point of each sensor according to the current global position information and the vehicle body size parameters obtained by the navigation type laser scanning sensor and the position relation among the sensors, and converting the relative coordinates of surrounding objects obtained by a distance measurement type laser scanning sensor into the global coordinate.
3. The method for planning the local obstacle avoidance path of the intelligent forklift according to claim 1 or 2, wherein the navigation type laser scanning sensor is installed in the middle of the top end of the forklift, and the distances from the navigation type laser scanning sensor to the four wheels are equal; the positive direction of a cross shaft of a coordinate axis of the sensor is the forward direction of the forklift, and after a global coordinate system is established, the included angle between the positive direction of the cross shaft of the sensor and the positive direction of the cross shaft of the global coordinate system is the direction angle of the forklift body; the distance measurement type laser scanning sensor is arranged in the middle of the front head of the forklift, the scanning range is set to be 0-180 degrees according to needs, and the obtained polar coordinate data result needs to be converted by combining the set angular resolution of the sensor and the obtaining sequence of each data.
4. The method for planning a local obstacle avoidance path of an intelligent forklift according to claim 1, wherein the step S2 specifically includes:
firstly, marking a first point of obtained data as a characteristic point, selecting a plurality of continuous points on the basis of the characteristic point, making a straight line between the first point and the last point, judging whether the distance between the other points in the middle and the straight line is less than a set threshold value, if so, adding a point in sequence on the basis of the selected point, repeating the steps until the existing point is more than the threshold value, marking the added point as the characteristic point, and starting a new cycle on the basis of the characteristic point until all data are analyzed and processed.
5. The method for planning the local obstacle avoidance path of the intelligent forklift according to claim 1 or 4, wherein a point closest to the current position point is selected from the remaining tangent points as a small target point and is set as a first-from-last control point of the B-spline curve, and a point which is close to the small target point in the tangent direction of the tangent point and is close to the starting point is selected as a second-from-last control point; simultaneously, taking the current position point of the forklift as a first control point, namely a path starting point; selecting a point which is very close to the initial point in the current advancing direction of the forklift as a second control point; and finally, selecting a middle point between the second control point and the penultimate control point as a new control point, or selecting other points between the two control points as new control points according to requirements.
6. The method for planning a local obstacle avoidance path of an intelligent forklift according to claim 1, wherein the step S4 specifically includes:
and (4) realizing local path planning by using the control points obtained in the step (S3) in combination with a B-spline curve generation mode, transmitting the result to a path tracking algorithm for execution, and selecting a 4-order form for the B-spline curve.
7. The method for planning the local obstacle avoidance path of the intelligent forklift according to any one of claims 1 and 6, wherein the total number of the selected control points is necessarily greater than the order of the selected B-spline curve; and calculating corresponding basis functions through the selected B-spline curve order, and obtaining the functions of the spline curves of all the sections of the planned path by combining the selected control points and the expressions of the B-spline curve.
8. The method for planning a local obstacle avoidance path of an intelligent forklift according to claim 1, wherein the step S5 specifically includes: when the target point can reach the final target point, namely the target point passes by the obstacle but does not reach the final target point, directly replacing the small target point in the steps, repeating the steps S3 and S4 until the final target point is reached and the pose meets the requirement; otherwise, the above steps S2, S3 and S4 are repeated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810263821.2A CN108759829B (en) | 2018-03-28 | 2018-03-28 | Local obstacle avoidance path planning method for intelligent forklift |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810263821.2A CN108759829B (en) | 2018-03-28 | 2018-03-28 | Local obstacle avoidance path planning method for intelligent forklift |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108759829A CN108759829A (en) | 2018-11-06 |
| CN108759829B true CN108759829B (en) | 2021-05-11 |
Family
ID=63980698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810263821.2A Active CN108759829B (en) | 2018-03-28 | 2018-03-28 | Local obstacle avoidance path planning method for intelligent forklift |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108759829B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109471432B (en) * | 2018-11-08 | 2021-09-28 | 南京农业大学 | Shortest obstacle avoidance path planning method for autonomous navigation agricultural vehicle |
| CN111158365B (en) * | 2019-12-31 | 2023-05-16 | 深圳优地科技有限公司 | Path planning method, device, robot and storage medium |
| CN113050636A (en) * | 2021-03-15 | 2021-06-29 | 广东省农业科学院 | Control method, system and device for autonomous tray picking of forklift |
| CN113985881B (en) * | 2021-10-29 | 2023-07-11 | 温州大学 | Mobile robot path planning method based on bidirectional crawler |
| CN114265412B (en) * | 2021-12-29 | 2023-10-24 | 深圳创维数字技术有限公司 | Vehicle control method, device, equipment and computer readable storage medium |
| CN115077534B (en) * | 2022-08-11 | 2022-11-15 | 合肥井松智能科技股份有限公司 | AGV path planning method based on B spline curve |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0844428A (en) * | 1994-07-27 | 1996-02-16 | Shinko Electric Co Ltd | Unmanned traveling vehicle |
| CN101826122A (en) * | 2010-01-18 | 2010-09-08 | 吉林大学 | Method for avoiding obstacles based on blocking corners in pedestrian simulation |
| CN103048996A (en) * | 2012-12-27 | 2013-04-17 | 深圳先进技术研究院 | Automatic guided vehicle based on laser scanning distance meter, and system and navigation method of automatic guided vehicle |
| CN105159294A (en) * | 2015-09-01 | 2015-12-16 | 深圳力子机器人有限公司 | Design method of fuzzy logic motion controller of forklift |
| CN106054882A (en) * | 2016-06-15 | 2016-10-26 | 深圳市金佰科创发展有限公司 | Robot obstacle avoidance method |
| CN106774329A (en) * | 2016-12-29 | 2017-05-31 | 大连理工大学 | A kind of robot path planning method based on oval tangent line construction |
| CN107031626A (en) * | 2017-03-29 | 2017-08-11 | 华南农业大学 | A kind of fork truck automatic obstacle avoiding system and method |
| CN107065880A (en) * | 2017-05-16 | 2017-08-18 | 南京农业大学 | Remote operating agricultural vehicle man-computer cooperation paths planning method based on dynamic guiding point |
| CN107643764A (en) * | 2017-10-20 | 2018-01-30 | 中国人民解放军海军航空工程学院 | A kind of unmanned vehicle barrier-avoiding method based on bispin Lyapunov vector fields |
-
2018
- 2018-03-28 CN CN201810263821.2A patent/CN108759829B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0844428A (en) * | 1994-07-27 | 1996-02-16 | Shinko Electric Co Ltd | Unmanned traveling vehicle |
| CN101826122A (en) * | 2010-01-18 | 2010-09-08 | 吉林大学 | Method for avoiding obstacles based on blocking corners in pedestrian simulation |
| CN103048996A (en) * | 2012-12-27 | 2013-04-17 | 深圳先进技术研究院 | Automatic guided vehicle based on laser scanning distance meter, and system and navigation method of automatic guided vehicle |
| CN105159294A (en) * | 2015-09-01 | 2015-12-16 | 深圳力子机器人有限公司 | Design method of fuzzy logic motion controller of forklift |
| CN106054882A (en) * | 2016-06-15 | 2016-10-26 | 深圳市金佰科创发展有限公司 | Robot obstacle avoidance method |
| CN106774329A (en) * | 2016-12-29 | 2017-05-31 | 大连理工大学 | A kind of robot path planning method based on oval tangent line construction |
| CN107031626A (en) * | 2017-03-29 | 2017-08-11 | 华南农业大学 | A kind of fork truck automatic obstacle avoiding system and method |
| CN107065880A (en) * | 2017-05-16 | 2017-08-18 | 南京农业大学 | Remote operating agricultural vehicle man-computer cooperation paths planning method based on dynamic guiding point |
| CN107643764A (en) * | 2017-10-20 | 2018-01-30 | 中国人民解放军海军航空工程学院 | A kind of unmanned vehicle barrier-avoiding method based on bispin Lyapunov vector fields |
Non-Patent Citations (1)
| Title |
|---|
| 机器人躲避多静态障碍物的路径规划模型;李彦刚;《自动化与仪器仪表》;20130401(第2期);第160-163页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108759829A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108415413B (en) | Intelligent forklift local obstacle avoidance path planning method based on circular useful domain | |
| CN108759829B (en) | Local obstacle avoidance path planning method for intelligent forklift | |
| CN112673234B (en) | Path planning method and path planning device | |
| CN105764773B (en) | method for controlling a vehicle | |
| CN107239076B (en) | AGV laser SLAM method based on virtual scanning and distance measurement matching | |
| CN110243380B (en) | Map matching method based on multi-sensor data and angle feature recognition | |
| CN113306549B (en) | Automatic parking trajectory planning algorithm | |
| CN106708059B (en) | Mobile robot real-time motion planning method based on channel selection | |
| Zheng et al. | RRT based path planning for autonomous parking of vehicle | |
| CN110361013B (en) | Path planning system and method for vehicle model | |
| CN110696819B (en) | Automatic parking path planning method and system | |
| CN113721637B (en) | Intelligent vehicle dynamic obstacle avoidance path continuous planning method and system and storage medium | |
| CN112141091B (en) | Secondary parking method and system for solving parking space deviation and positioning deviation and vehicle | |
| CN114200945B (en) | Safety control method of mobile robot | |
| CN113895463B (en) | Path planning method suitable for turning around of automatic driving vehicle | |
| CN112212887B (en) | Automatic parking positioning parameter calibration method based on Ackerman steering model | |
| JP5493342B2 (en) | Object position detection device | |
| CN106203341B (en) | A kind of Lane detection method and device of unmanned vehicle | |
| Han et al. | Robust ego-motion estimation and map matching technique for autonomous vehicle localization with high definition digital map | |
| WO2024000616A1 (en) | Traveling path boundary determination method and device, vehicle, storage medium, and terminal | |
| CN113525509A (en) | Steering control method and device for articulated vehicle | |
| CN113341999A (en) | Forklift path planning method and device based on optimized D-x algorithm | |
| Eraqi et al. | Static free space detection with laser scanner using occupancy grid maps | |
| CN116189150A (en) | Monocular 3D target detection method, device, equipment and medium based on fusion output | |
| CN114383598B (en) | Tunnel construction operation car and automatic driving system thereof |
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 |