CN111811517A - Dynamic local path planning method and system - Google Patents
Dynamic local path planning method and system Download PDFInfo
- Publication number
- CN111811517A CN111811517A CN202010681054.4A CN202010681054A CN111811517A CN 111811517 A CN111811517 A CN 111811517A CN 202010681054 A CN202010681054 A CN 202010681054A CN 111811517 A CN111811517 A CN 111811517A
- Authority
- CN
- China
- Prior art keywords
- path
- section
- clockwise
- planned
- order
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000014509 gene expression Effects 0.000 claims abstract description 22
- 238000009499 grossing Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
Abstract
The invention relates to a dynamic local path planning method, which comprises the following steps: acquiring an initial pose and an end pose of a moving body, updating a cost map in real time, judging a planned path to be a route of several orders, and representing the planned path through a mathematical expression; discretizing the planned path represented by the mathematical expression to obtain discrete path points, converting the discrete path points into grid coordinates, judging whether the planned path is an infeasible area or not according to the grid coordinates, if so, discarding the planned path, and otherwise, taking the planned path as a possible path; and evaluating all possible paths through an evaluation function, and selecting one path with the highest score for smoothing. The invention also relates to a dynamic local path planning system. The invention ensures that the curvature of the planned path is continuous, the curve is smooth and the movement characteristics of movable equipment such as a robot or an AGV are met.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a dynamic local path planning method and a dynamic local path planning system.
Background
Path planning refers to a robot or an AGV that searches for an optimal or suboptimal path from a start state to a target state according to some performance indexes (e.g., distance, time, etc.). It is classified into 2 types according to the degree of grasp on environmental information: (1) global path planning, also known as static or offline planning, based on environmental prior complete information; (2) local path planning, also known as dynamic or online path planning, based on sensor information. In an application scene of automatic parking, general local path planning methods such as a dynamic window algorithm and a fuzzy logic algorithm cannot consider the posture of an automobile at the end of a planned path, and only can achieve the effect of dynamic obstacle avoidance, while a dubin algorithm and a threads-sheet algorithm can consider the problem of the end pose, but can only plan the path under the condition of no obstacle. For another example, in a logistics storage yard, when a tray with a known pose is required to be inserted, the existing algorithm cannot dynamically avoid the barrier on the basis of considering the pose of the tail end.
The current relatively mature algorithm is an A-x algorithm, the map format of the A-x algorithm is a rasterized cost map, but the A-x algorithm is fixedly in an 8-neighborhood expansion mode when nodes are selected, at most 8 motion directions can be selected around the A-x algorithm, the motion angle is limited to be integral multiple of pi/4, the robot steering is not facilitated, more redundant nodes are generated, the redundant nodes are not optimized, and the final path turning points are more and unsmooth.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a dynamic local path planning method and a dynamic local path planning system, so that the curvature of a planned path is continuous, the curve is smooth and the movement characteristics of movable equipment such as a robot or an AGV are met.
The technical scheme adopted by the invention for solving the technical problems is as follows: a dynamic local path planning method is provided, which comprises the following steps:
(1) acquiring an initial pose and an end pose of a moving body, updating a cost map in real time, judging a planned path to be a route of several orders, and representing the planned path through a mathematical expression;
(2) discretizing the planned path represented by the mathematical expression to obtain discrete path points, converting the discrete path points into grid coordinates, judging whether the planned path is an infeasible area or not according to the grid coordinates, if so, discarding the planned path, and otherwise, taking the planned path as a possible path;
(3) and evaluating all possible paths through an evaluation function, and selecting one path with the highest score for smoothing.
Judging that the planned path is a route of several orders in the step (1), and before representing the planned path through a mathematical expression, converting a global map in an original coordinate system into a global map in a set coordinate system by taking the position of the end pose as an origin and the attitude direction as a Y axis in a (x) conversion mode1,y1)=([x·cos(θ)+y·sin(θ)+X],[y·cos(θ)-x·sin(θ)+Y]) Wherein, (X, Y) is coordinates under the original coordinate system, theta is an included angle between an X axis of the original coordinate system and an X axis of the set coordinate system, and (X, Y) is a difference value between an original point of the original coordinate system and the original point of the set coordinate system.
When the planned path is judged to be a route of several orders in the step (1), the definition, constraint conditions and corresponding actions of each order need to be analyzed, wherein the first-order analysis is as follows:
first order path definition: the moving body can reach the terminal position through a section of direction change from the current pose;
first order path constraints:
(a)d1>Rminand d2 > RminWherein d1 and d2 are respectively the motiles to (R)min0) and (-R)min0) distance, RminIs the minimum turning radius; if the constraint condition (a) is not satisfied, performing third-order analysis, and if the constraint condition (b) is satisfied, verifying the constraint condition (b);
(b)l-shaped path orAn R-type path, where O is the origin and the coordinates are (0, 0); ccIs the upper circle center on the X axis and has the coordinate of (X)c,0),xc∈(-∞,-Rmin)∪(RminInfinity); v is the pose of the moving body and the coordinate is (x)v,yv,θv) Wherein x isv∈(-∞,-Rmin)∪(Rmin,∞),yv>0,θv∈[0,2π](ii) a Beta isAndangle of beta ∈ [0, pi ]]R type represents clockwise, L type represents counterclockwise; and (c) jumping out of the analysis of the order if the constraint condition (b) is met, and otherwise entering into second-order analysis.
The second order analysis is as follows:
second order path definition: the moving body can not reach a target point through first-order analysis, and the pose of the moving body at the next moment can be analyzed through the first-order analysis by adjusting the pose once;
second order path constraint conditions:
(A)d1>Rminand d2 > RminWherein d1 and d2 are respectively the motiles to (R)min0) and (-R)min0) distance, RminIs the minimum turning radius; if the constraint condition (A) is not satisfied, performing third-order analysis, and if the constraint condition (B) is satisfied, verifying the constraint condition (B);
(B)C1C2=R1+R2or C1C2=|R1-R2L, wherein C1Is a radius R1Has a center of a circle with coordinates of (R)1,0),R1>Rmin(ii) a With point V as a straight line, passing point V as a perpendicular to the straight line, C2Is represented by R on the vertical line2Is the center of a radius and has the coordinate of (x)c2,yc2);
(C)θ1Is composed ofAndangle of (a) of2Is composed ofAndRR-type indicates that the first path is clockwise and the second path is clockwise; LR type indicates the first stage path is counterclockwise and the second stage path is clockwise; RL type indicates the first path is clockwise and the second path is counterclockwise; LL type indicates that the first leg of the path is counterclockwise and the second leg of the path is counterclockwise.
The third order analysis is as follows:
third order path definition: if the path is a third-order path, which indicates that the position of the moving body does not meet the constraint condition at this time, d1 < RminOr d2 < RminThen, an arc needs to be found to be tangent to the second-order route and meet the constraint condition of the third-order route;
third order path constraint conditions:wherein, theta3The angle of the third section of circular arc rotation is shown, the RRR type represents that the first section of path is clockwise, the second section of path is clockwise and the third section of path is clockwise; the LRR type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is clockwise; the RLR type indicates that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is clockwise; the LLR type indicates that the first section of path is anticlockwise, the second section of path is anticlockwise and the third section of path is clockwise; RRL type indicates that the first section of path is clockwise, the second section of path is clockwise, and the third section of path is reverseA hour hand; the LRL type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is anticlockwise; the RLL type represents that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is anticlockwise; the LLL type indicates that the first path is counterclockwise, the second path is counterclockwise, and the third path is counterclockwise.
In the step (2), the discrete path points are converted into grid coordinates through a mapping relation, wherein the mapping relation is as follows: grid number of ith point:and (3) obtaining grid coordinates according to the grid serial number:wherein INT denotes rounding, GsizeDenotes the minimum grid width, xmaxCost map x-axis width, (x)i,yi) The coordinates of the ith point,% represents the remainder operator.
The step (2) of judging whether the planned path is an infeasible area according to the grid coordinates specifically comprises the following steps: traversing all the grid coordinates converted by the discrete path points, comparing the cost value of the grid coordinates with a threshold value, and if the grid coordinates larger than the threshold value exist, indicating that the path is an infeasible area.
The scoring criteria of the evaluation function in the step (3) comprise a planning arc radius ratio and a distance of a nearest obstacle, wherein the closer the planning arc radius ratio is to 1, the higher the score is, and the farther the distance of the nearest obstacle is, the higher the score is; and normalizing the two scoring standards during evaluation, then adding the two scoring standards, and selecting the path with the highest score for smoothing.
The technical scheme adopted by the invention for solving the technical problems is as follows: the control module is used for receiving the planning path data and controlling the robot to accurately walk; the obstacle avoidance module is used for receiving external information through an external sensor and outputting the position of an obstacle; the operation module is used for planning an optimal path by adopting the dynamic local path planning method.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: the method judges that the planned path is a route of several orders, expresses the planned path by using a mathematical expression, converts the planned path into a grid position in a cost map by using a discretized mathematical expression, thereby abandoning the path with obstacles, finally evaluates possible paths, and selects one path for smoothing, so that the finally planned path has continuous curvature and smooth curve and accords with the motion characteristics of movable equipment such as a robot or an AGV.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of example 1 of the present invention;
FIG. 3 is a schematic view of example 1 of the present invention;
FIG. 4 is a flowchart of example 2 of the present invention;
FIG. 5 is a schematic view of example 2 of the present invention;
FIG. 6 is a flowchart of example 3 of the present invention;
FIG. 7 is a schematic view of example 3 of the present invention;
fig. 8 is a system block diagram of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to a dynamic local path planning method, as shown in fig. 1, comprising the following steps:
(1) the method comprises the steps of obtaining the starting pose and the ending pose of a moving body, updating a cost map in real time, judging a planned path to be a route of several orders, and representing the planned path through a mathematical expression.
In the embodiment, the initial pose is obtained by self real-time positioning, and the positioning mode can include but is not limited to laser positioning, visual positioning, inertial navigation positioning and the like; the real-time positioning table comprises a timestamp in the pose information transmitted each time, and each timestamp corresponds to a different pose; the information of the starting pose includes: 1. the position of the moving body in the global map; 2. the posture of the moving body is defined as that the moving body is regarded as a rigid body, and the direction of the rigid body is regarded as posture information; 3. a time stamp.
The obtaining mode of the termination pose in this embodiment includes, but is not limited to, the following modes: through human measurement input, UWB positioning acquisition, bluetooth positioning acquisition, and the like. The information of the termination pose includes: 1. the position in the global map at which the moving body stopped; 2. the pose of the moving body in the global map when it stops.
The cost map in the embodiment is a superimposed obstacle map, an expansion map and the like on the original static map; the obstacle map updates the cost value of the map by using the obstacle information dynamically recorded by the sensor through a Bayesian formula; the expansion map is expanded on the two layers of superposed maps, namely the cost value of the grids around the obstacle is increased, so that the case of the robot can be prevented from colliding with the obstacle. Wherein the cost value is the probability that the grid has an obstacle.
In this embodiment, the step of the path is defined as the adjustment times of the direction, and if the direction is not adjusted, the planned path is a first-order path. According to the dubin algorithm, the moving body can plan a planned path consisting of two curves and a straight line, and therefore, the maximum spatial order is a three-order path.
Judging a planned path to be a route of several orders, and before representing the planned path through a mathematical expression, converting a global map under an original coordinate system into a global map under a set coordinate system with a position of a termination pose as an origin and a posture direction as a Y axis in a (x) conversion mode1,y1)=([x·cos(θ)+y·sin(θ)+X],[y·cos(θ)-x·sin(θ)+Y]) Wherein, (X, Y) is coordinates under the original coordinate system, theta is an included angle between an X axis of the original coordinate system and an X axis of the set coordinate system, and (X, Y) is a difference value between an original point of the original coordinate system and the original point of the set coordinate system.
(2) Discretizing the planned path represented by the mathematical expression to obtain discrete path points, converting the discrete path points into grid coordinates, judging whether the planned path is an infeasible area or not according to the grid coordinates, if so, discarding the planned path, and otherwise, taking the planned path as a possible path;
(3) and evaluating all possible paths through an evaluation function, and selecting one path with the highest score for smoothing. In this embodiment, the scoring criteria of the evaluation function include a planned arc radius ratio and a distance dist of the nearest obstacleobstacle. For the planned circular arc radius ratio, in order to make the mechanical wear of the moving body smaller, the planned path is as smooth as possible, and the curvature of the circular arc is related to the turning radius, so that the closer the ratio of the turning radii of the two circular arcs is to 1, the smaller the curvature of the path is, the higher the score is. Distance dist for nearest obstacleobstacleThe farther the planned path is from the obstacle, the better, the farther away from the obstacle the higher the score.
The invention is further illustrated by the following examples.
Example 1:
the embodiment provides a path planning method and system for automatic insertion of irregular goods by a forklift, and further hardware of the system mainly comprises the following steps: a fork truck, a computer, a camera. It should be noted that the obstacle avoidance module includes, but is not limited to, a vision sensor.
As shown in fig. 2, the dynamic local path planning method specifically includes the following steps:
the method comprises the following steps: and obtaining an initial pose, a final pose and a real-time new cost map, judging the planned route to be a route of several orders, and representing the route by using a mathematical expression.
When the planned route is judged to be a route of several orders, first-order path analysis is firstly carried out:
I. determining the order of a path
1.1 first judging whether d1 and d2 meet the constraint condition d1 > RminAnd d2 > Rmin;
In this embodiment, d1 ═ xv+Rmin)2+yv 2,d2=(xv+Rmin)2+yv 2As shown in FIG. 3, d1 and d2 respectively indicate the current position of the forklift truck (R)min0) and (-R)minDistance of (0), (x)v,yv) Position coordinates, R, of the AGV fork truck at the present locationminIs the minimum turning radius. In this example d1 > Rmin,d2>RminAnd therefore the constraint is satisfied.
1.2 judging the constraint conditionsL-shaped path orAn R-type path, where O is the origin and the coordinates are (0, 0); ccIs the upper circle center on the X axis and has the coordinate of (X)c,0),xc∈(-∞,-Rmin)∪(RminInfinity); v is the pose of the moving body and the coordinate is (x)v,yv,θv) Wherein x isv∈(-∞,-Rmin)∪(Rmin,∞),yv>0,θv∈[0,2π](ii) a Beta isAndangle of beta ∈ [0, pi ]]The R-shape represents clockwise, and the L-shape represents counterclockwise.
The judging steps are as follows: according to OCc=CcV is calculated to obtain xcFor L-shaped paths, xc> 0, for R-type path, xcIs less than 0. Determining constraint conditions In this embodiment, the constraint condition is satisfiedAt this time, the planned path is determined to be a first-order path.
II representing the planned path by a mathematical expression
The planned path may be represented by various mathematical expressions, such as an equation, or polar coordinates. The expression of the present embodiment is:
and step two, discretizing the path, converting the path into grid coordinates, and judging an infeasible area.
1. Discretized paths
Sampling gamma at a sampling interval of sigma to obtain discrete path points
2. Conversion to grid coordinates
wherein INT denotes rounding, GsizeDenotes the minimum grid width, xmaxCost map x-axis width, (x)i,yi) Is composed of
The coordinates of the ith point,% represents the remainder operator.
3. Determining infeasible regions
Each grid region stores occupancy information indicating whether the current grid has an obstacle, i.e., a cost value. Therefore, after the grid coordinates are obtained, the cost values of all the grid coordinates are traversed, if the cost values exceed the threshold value, it is indicated that an obstacle exists on the path, the planned path is abandoned, and the selection is carried out again. Otherwise, the path is generated.
And step three, the first-order path has strict requirements on the initial posture of the AGV, so that only one planning path is output. In the whole operation process, the operation module detects whether the obstacle avoidance module outputs obstacle information in real time. And if so, stopping suddenly, returning to the step one, and otherwise, not acting.
If the obstacle information is received after the path is output, the following steps are carried out:
1. obstacle avoidance module outputs two-dimensional coordinates (x)obstacle,yobstacle);
2. Converting the two-dimensional coordinates into grid coordinates;
3. associating the obstacle grid coordinates with the mapped (x)N,yN) And comparing whether the grid coordinates of the obstacle are positioned on the planned path, and if so, abandoning the path and planning again.
Example 2:
the embodiment provides a path planning method and a system for backing and warehousing, and further hardware of the system mainly comprises the following steps: one automobile, one industrial personal computer and several laser radars.
As shown in fig. 4, the dynamic local path planning method specifically includes the following steps:
the method comprises the following steps: and obtaining an initial pose, a final pose and a real-time new cost map, judging the planned route to be a route of several orders, and representing the route by using a mathematical expression.
When the planned route is judged to be a route of several orders, first-order path analysis is firstly carried out:
I. determining the order of a path
1.1 first judging whether d1 and d2 meet the constraint condition d1 > RminAnd d2 > Rmin;
This implementationIn an example, d1 ═ xv+Rmin)2+yv 2,d2=(xv+Rmin)2+yv 2As shown in FIG. 5, d1 and d2 respectively indicate the current position of the automobile (R)min0) and (-R)minDistance of (0), (x)v,yv) As coordinates of the current position of the vehicle, RminIs the minimum turning radius. In this example d1 > Rmin,d2>Rmin。
1.2 judging the constraint conditionsL-shaped path orAn R-shaped path, as shown in FIG. 5, with O as the origin and coordinates of (0, 0); c1Is the upper circle center on the X axis and has the coordinate of (X)c1,0),xc∈(-∞,-Rmin)∪(RminInfinity); v is the pose of the moving body and the coordinate is (x)v,yv,θv) Wherein x isv∈(-∞,-Rmin)∪(Rmin,∞),yv>0,θv∈[0,2π](ii) a Beta isAndangle of beta ∈ [0, pi ]]The R-shape represents clockwise, and the L-shape represents counterclockwise.
The judging steps are as follows: according to OC1=C1V is calculated to obtain xcFor L-shaped paths, xc1> 0, for R-type path, xc1Is less than 0. Determining constraint conditions In this embodiment, the constraint condition is not satisfied
1.3 second order Path analysis
The moving body can not reach the target point through the first-order analysis, and the pose of the moving body at the next moment can be subjected to the first-order analysis by adjusting the pose once, namely, the tail end of a section of circular arc can be planned to be tangent to the first-order circular arc.
1.3.1 judging constraint Condition C1C2=R1+R2(exo) or C1C2=|R1-R2[ endo ] wherein C1Is a radius R1Has a center of a circle with coordinates of (R)1,0),R1>Rmin(ii) a With point V as a straight line, passing point V as a perpendicular to the straight line, C2Is represented by R on the vertical line2Is the center of a radius and has the coordinate of (x)c2,yc2)。
The judging steps are as follows: the radius is selected by spacing d on the perpendicular to the X axis and the vector (X, y, theta)xThe sampling range is the constraint condition until C1C2=R1+R2(exo) or C1C2=|R1-R2L (| (endo)).
Center C1(xc1,yc1) Is (R)10) or (-R)10); center C2(xc2,yc2) Is (x)m+r2*cos(θ-90°),ym+r2Sin (θ -90 °)); circle C1And circle C2Tangent point isAt the end of the traversal, the result is a set of second order paths.
1.3.2 judging the constraint conditionsWherein, thetavFor the attitude of the vehicle, theta1Is composed ofAndangle of (2)θ2Is composed ofAndangle of (2)RR type means that the first section of path is clockwise, and the second section of path is clockwise; LR type indicates the first stage path is counterclockwise and the second stage path is clockwise; RL type indicates the first path is clockwise and the second path is counterclockwise; LL type indicates that the first leg of the path is counterclockwise and the second leg of the path is counterclockwise.
Calculate theta1And theta2And introducing constraint conditions, and screening out a set to be optimized.
II. Representing paths in mathematical form
Center C in this embodiment1The expression of the arc of (1) is:center C2The expression of the arc of (1) is:
and step two, discretizing the path, converting the path into grid coordinates, and judging an infeasible area.
1. Discretized paths
And sampling gamma at a sampling interval of sigma to obtain discrete path points.
2. Conversion to grid coordinates
wherein INT denotes rounding, GsizeDenotes the minimum grid width, xmaxCost map x-axis width, (x)i,yi) The coordinates of the ith point,% represents the remainder operator.
3. Determining infeasible regions
Each grid region stores occupancy information indicating whether the current grid has an obstacle, i.e., a cost value. Therefore, after the grid coordinates are obtained, the cost values of all the grid coordinates are traversed, if the cost values exceed the threshold value, it is indicated that an obstacle exists on the path, the planned path is abandoned, and the selection is carried out again. Otherwise, the path is generated.
And step three, evaluating all possible paths, and smoothing one path with the highest score.
1.1 normalization:
Normal(i)=Normal_ratio(i)+Normal_distobstacle(i)
The number of current paths, Normal _ ratio, is the normalized ratio score of the radius of the planning arc, Normal _ distobstacleAnd selecting a path with the highest score for the normalized nearest barrier distance score.
1.2 smoothing
The specific way of smoothing the planned path is as follows: establishing a multi-target function, solving an extreme value of the target function by adopting a conjugate gradient descent method to obtain a smoother path, and generating a series of nodes X by an algorithmi=(xi,yi) I is [0, N ]]Composition is carried out; let Δ Xi=Xi-Xi-1Representing a vector consisting of two nodes; o isiIndicating the location of the closest obstacle point to the node. The established objective function is:wherein, Wob,WsAnd WkThe weights are obtained by multiple tests.
The first term of the objective function constrains the safe distance between the node and the obstacle, dmaxThe minimum safe distance between a node and an obstacle point when the node is smooth is the length of a vehicle axle, and the value is | Xi-0|>dmaxThe first term has an effect, otherwise the gradient is 0; the second term smoothes the path; the third item restrains the curvature of any node, and the curvature numerical value must be less than kmaxMaximum curvature kmaxDetermined by kinematic constraints of the vehicle, when kiIs less than or equal to kmaxThe gradient of the third term takes the value 0.
Gradient of each item of the objective function isAnd (3) solving an extreme value of the objective function by using a conjugate gradient descent method to obtain a smoother path.
And after a second-order path is obtained, whether the obstacle avoidance module outputs obstacle information is detected in real time. And if so, stopping suddenly, returning to the step one, and otherwise, not acting.
If the obstacle information is received after the path is output, the following steps are carried out:
1. obstacle avoidance module outputs two-dimensional coordinates (x)obstacle,yobstacle);
2. Converting the two-dimensional coordinates into grid coordinates;
3. associating the obstacle grid coordinates with the mapped (x)N,yN) And comparing whether the grid coordinates of the obstacle are positioned on the planned path, and if so, abandoning the path and planning again.
Example 3:
this embodiment provides an embodiment of a third order path.
If the path is a third-order path, which indicates that the position of the moving body does not meet the constraint condition at this time, d1 < RminOr d2 < RminAnd then an arc needs to be found to be tangent to the second-order route and meet the constraint condition of the third-order route.
Third order path constraint conditions:wherein, theta3The angle of the third section of circular arc rotation is shown, the RRR type represents that the first section of path is clockwise, the second section of path is clockwise and the third section of path is clockwise; the LRR type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is clockwise; the RLR type indicates that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is clockwise; the LLR type indicates that the first section of path is anticlockwise, the second section of path is anticlockwise and the third section of path is clockwise; the RRL type indicates that the first section of path is clockwise, the second section of path is clockwise and the third section of path is anticlockwise; the LRL type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is anticlockwise; the RLL type represents that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is anticlockwise; the LLL type indicates that the first path is counterclockwise, the second path is counterclockwise, and the third path is counterclockwise.
As shown in fig. 6, the dynamic local path planning method specifically includes the following steps:
the method comprises the following steps: and obtaining an initial pose, a final pose and a real-time new cost map, judging the planned route to be a route of several orders, and representing the route by using a mathematical expression.
I. Determining the order of a path
1.1 first judging whether d1 and d2 meet the constraint condition d1 > RminAnd d2 > Rmin。
In this embodiment, d1 ═ xv+Rmin)2+yv 2,d2=(xv+Rmin)2+yv 2As shown in fig. 7, d1 and d2 respectively represent the current position of the robot to (R)min0) and (-R)minDistance of (0), (x)v,yv) Is the current position coordinate of the robot, RminIs the minimum turning radius. In this embodiment, the initial pose of the robot does not satisfy the constraint condition, and the third-order path planning includes the following steps:
a. establishing a coordinate system, taking the current coordinate M of the robot as an original point, taking the vector direction as the positive direction of a y axis, taking an x axis as a y-axis perpendicular line, and taking the x axis as a right direction, and converting the matrix into H with the original coordinate system;
b. selecting a point A (x) on a first-order path under the coordinate systema,ya,θa) The point A satisfies the constraint condition, and A' (x) is obtained by converting A into the original coordinate systema',ya',θa') judging whether A' meets the constraint condition;
c. if yes, M->A discrete path points, through H-1After the transformation to the original coordinate system, the second-order path planning as in example 2 is performed with a' as the new starting point. If not, the proper point A is selected again.
As shown in fig. 8, the present embodiment further provides a dynamic local path planning system, which includes an obstacle avoidance module, an operation module, and a control module. The control module is used for receiving planning path data and controlling the robot to accurately walk; the obstacle avoidance module is used for receiving external information through an external sensor and outputting the position of an obstacle; the operation module is used for planning the optimal path by adopting the dynamic local path planning method
The obstacle avoidance module has the functions of image construction and obstacle detection, and external sensors used by the module include but are not limited to laser radar, ultrasonic sensors, vision sensors and the like.
The operation module comprises functions of updating raster map data, planning path operation and basic logic operation, the control module comprises a function of fusing data of the operation module and outputting a control signal, and implementation equipment of the two modules comprises but is not limited to a personal computer, an industrial personal computer and a server.
The operation module obtains an initial pose, a termination pose and a real-time new cost map, analyzes the path order and calculates a path mathematical expression; then, the infeasible area can be evaluated, the path needs to be discretized and converted into a grid coordinate, and information whether the grid is occupied or not is stored in grid information; the calculated path is a set of feasible routes, so the operation module needs to evaluate all the possible paths, and the path with the highest smooth processing score. The obstacle avoidance module is also used for detecting external obstacle information in real time, if an obstacle exists, the operation module transmits an emergency stop signal to the control module and replans a route, otherwise, the control module outputs control information to follow the generated route.
Claims (9)
1. A dynamic local path planning method is characterized by comprising the following steps:
(1) acquiring an initial pose and an end pose of a moving body, updating a cost map in real time, judging a planned path to be a route of several orders, and representing the planned path through a mathematical expression;
(2) discretizing the planned path represented by the mathematical expression to obtain discrete path points, converting the discrete path points into grid coordinates, judging whether the planned path is an infeasible area or not according to the grid coordinates, if so, discarding the planned path, and otherwise, taking the planned path as a possible path;
(3) and evaluating all possible paths through an evaluation function, and selecting one path with the highest score for smoothing.
2. The dynamic local path planning method according to claim 1, wherein the planned path is determined to be a route of several orders in step (1), and before the planned path is represented by a mathematical expression, a global map in an original coordinate system needs to be converted into a global map in a set coordinate system with a position of the end pose as an origin and a posture direction as a Y-axis, and the conversion mode is (x)1,y1)=([x·cos(θ)+y·sin(θ)+X],[y·cos(θ)-x·sin(θ)+Y]) Wherein, (X, Y) is coordinates under the original coordinate system, theta is an included angle between an X axis of the original coordinate system and an X axis of the set coordinate system, and (X, Y) is a difference value between an original point of the original coordinate system and the original point of the set coordinate system.
3. The dynamic local path planning method according to claim 1, wherein the step (1) of determining the planned path as a route of several orders requires analysis of definitions, constraints and corresponding actions of each order, wherein,
the first order analysis was as follows:
first order path definition: the moving body can reach the terminal position through a section of direction change from the current pose;
first order path constraints:
(a)d1>Rminand d2 > RminWherein d1 and d2 are respectively the motiles to (R)min0) and (-R)min0) distance, RminIs the minimum turning radius; if the constraint condition (a) is not satisfied, performing third-order analysis, and if the constraint condition (b) is satisfied, verifying the constraint condition (b);
(b)l-shaped path orAn R-type path, where O is the origin and the coordinates are (0, 0); ccIs the upper circle center on the X axis and has the coordinate of (X)c,0),xc∈(-∞,-Rmin)∪(RminInfinity); v is the pose of the moving body and the coordinate is (x)v,yv,θv) Wherein x isv∈(-∞,-Rmin)∪(Rmin,∞),yv>0,θv∈[0,2π](ii) a Beta isAndangle of beta ∈ [0, pi ]]R type represents clockwise, L type represents counterclockwise; and (c) jumping out of the analysis of the order if the constraint condition (b) is met, and otherwise entering into second-order analysis.
4. A dynamic local path planning method according to claim 3, wherein the second order analysis is as follows:
second order path definition: the moving body can not reach a target point through first-order analysis, and the pose of the moving body at the next moment can be analyzed through the first-order analysis by adjusting the pose once;
second order path constraint conditions:
(A)d1>Rminand d2 > RminWherein d1 and d2 are respectively the motiles to (R)min0) and (-R)min0) distance, RminIs the minimum turning radius; if the constraint condition (A) is not satisfied, performing third-order analysis, and if the constraint condition (B) is satisfied, verifying the constraint condition (B);
(B)C1C2=R1+R2or C1C2=|R1-R2L, wherein C1Is a radius R1Has a center of a circle with coordinates of (R)1,0),R1>Rmin(ii) a With point V as a straight line, passing point V as a perpendicular to the straight line, C2Is represented by R on the vertical line2Is the center of a radius and has the coordinate of (x)c2,yc2);
(C)θ1Is composed ofAndangle of (a) of2Is composed ofAndRR-type indicates that the first path is clockwise and the second path is clockwise; LR type indicates the first stage path is counterclockwise and the second stage path is clockwise; RL type indicates the first path is clockwise and the second path is counterclockwise; LL type indicates that the first leg of the path is counterclockwise and the second leg of the path is counterclockwise.
5. The dynamic local path planning method according to claim 4, wherein the third order analysis is as follows:
third order path definition: if the path is a third-order path, which indicates that the position of the moving body does not meet the constraint condition at this time, d1 < RminOr d2 < RminThen, an arc needs to be found to be tangent to the second-order route and meet the constraint condition of the third-order route;
third order path constraint conditions:wherein, theta3The angle of the third section of circular arc rotation is shown, the RRR type represents that the first section of path is clockwise, the second section of path is clockwise and the third section of path is clockwise; the LRR type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is clockwise; the RLR type indicates that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is clockwise; LLR type means that the first segment path is counterclockwiseThe second section of path is anticlockwise, and the third section of path is clockwise; the RRL type indicates that the first section of path is clockwise, the second section of path is clockwise and the third section of path is anticlockwise; the LRL type indicates that the first section of path is anticlockwise, the second section of path is clockwise and the third section of path is anticlockwise; the RLL type represents that the first section of path is clockwise, the second section of path is anticlockwise and the third section of path is anticlockwise; the LLL type indicates that the first path is counterclockwise, the second path is counterclockwise, and the third path is counterclockwise.
6. The dynamic local path planning method according to claim 1, wherein in the step (2), the discrete path points are converted into grid coordinates through a mapping relationship, wherein the mapping relationship is as follows: grid number of ith point:and (3) obtaining grid coordinates according to the grid serial number:wherein INT denotes rounding, GsizeDenotes the minimum grid width, xmaxCost map x-axis width, (x)i,yi) The coordinates of the ith point,% represents the remainder operator.
7. The dynamic local path planning method according to claim 1, wherein the step (2) of determining whether the planned path is an infeasible area according to the grid coordinates specifically comprises: traversing all the grid coordinates converted by the discrete path points, comparing the cost value of the grid coordinates with a threshold value, and if the grid coordinates larger than the threshold value exist, indicating that the path is an infeasible area.
8. The dynamic local path planning method according to claim 1, wherein the scoring criteria of the evaluation function in step (3) include a planned arc radius ratio and a distance of a nearest obstacle, wherein the closer the planned arc radius ratio is to 1, the higher the score is, the further the distance of the nearest obstacle is, the higher the score is; and normalizing the two scoring standards during evaluation, then adding the two scoring standards, and selecting the path with the highest score for smoothing.
9. A dynamic local path planning system comprises a control module, an obstacle avoidance module and an operation module, and is characterized in that the control module is used for receiving planned path data and controlling a robot to accurately walk; the obstacle avoidance module is used for receiving external information through an external sensor and outputting the position of an obstacle; the calculation module is used for planning an optimal path by using the dynamic local path planner according to any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010681054.4A CN111811517A (en) | 2020-07-15 | 2020-07-15 | Dynamic local path planning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010681054.4A CN111811517A (en) | 2020-07-15 | 2020-07-15 | Dynamic local path planning method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111811517A true CN111811517A (en) | 2020-10-23 |
Family
ID=72865127
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010681054.4A Pending CN111811517A (en) | 2020-07-15 | 2020-07-15 | Dynamic local path planning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111811517A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112286194A (en) * | 2020-10-29 | 2021-01-29 | 广东杜尼智能机器人工程技术研究中心有限公司 | Cost map area division method |
CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
CN112698649A (en) * | 2020-12-15 | 2021-04-23 | 深圳众为兴技术股份有限公司 | Pose path smooth transition planning method, computer readable storage medium and device |
CN112747763A (en) * | 2020-12-30 | 2021-05-04 | 深兰人工智能(深圳)有限公司 | Local path planning method and device, electronic equipment and storage medium |
CN112937557A (en) * | 2021-03-09 | 2021-06-11 | 东风汽车集团股份有限公司 | Curvature control-based passenger-riding parking path planning method and system |
CN112964271A (en) * | 2021-03-15 | 2021-06-15 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
CN112965495A (en) * | 2021-02-10 | 2021-06-15 | 苏州清乐智能科技有限公司 | Disinfection robot and autonomous navigation method thereof |
CN113485369A (en) * | 2021-08-03 | 2021-10-08 | 浙江大学 | Indoor mobile robot path planning and path optimization method for improving A-x algorithm |
CN113758484A (en) * | 2020-11-30 | 2021-12-07 | 北京京东乾石科技有限公司 | Path planning method and device |
CN113778097A (en) * | 2021-09-15 | 2021-12-10 | 龙岩学院 | Intelligent warehouse logistics robot path planning method for improving A-STAR algorithm through L-shaped path trend |
CN114089774A (en) * | 2022-01-14 | 2022-02-25 | 中国科学院微电子研究所 | AGV path planning method and device in storage environment |
CN114995398A (en) * | 2022-05-16 | 2022-09-02 | 中国第一汽车股份有限公司 | Path generation method, path generation device, storage medium, processor and electronic device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060149465A1 (en) * | 2004-12-30 | 2006-07-06 | Samsung Electronics Co., Ltd. | Method and apparatus for moving in minimum cost path using grid map |
CN106353722A (en) * | 2016-11-03 | 2017-01-25 | 中国科学院上海微系统与信息技术研究所 | RSSI (received signal strength indicator) distance measuring method based on cost-reference particle filter |
CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
CN108519773A (en) * | 2018-03-07 | 2018-09-11 | 西安交通大学 | The paths planning method of automatic driving vehicle under a kind of structured environment |
CN109425352A (en) * | 2017-08-25 | 2019-03-05 | 科沃斯机器人股份有限公司 | Self-movement robot paths planning method |
CN110696818A (en) * | 2019-10-12 | 2020-01-17 | 深圳市布谷鸟科技有限公司 | Automatic parking method and system based on optimal path |
CN110728014A (en) * | 2018-06-27 | 2020-01-24 | 百度(美国)有限责任公司 | Reference line smoothing method using segmented spiral curves with weighted geometric cost |
WO2020021126A1 (en) * | 2018-07-27 | 2020-01-30 | Embotech Ag | Method for steering a vehicle and apparatus therefor |
CN110823240A (en) * | 2019-11-19 | 2020-02-21 | 齐鲁工业大学 | Following robot path planning method and system with course constraint |
-
2020
- 2020-07-15 CN CN202010681054.4A patent/CN111811517A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060149465A1 (en) * | 2004-12-30 | 2006-07-06 | Samsung Electronics Co., Ltd. | Method and apparatus for moving in minimum cost path using grid map |
CN106353722A (en) * | 2016-11-03 | 2017-01-25 | 中国科学院上海微系统与信息技术研究所 | RSSI (received signal strength indicator) distance measuring method based on cost-reference particle filter |
CN109425352A (en) * | 2017-08-25 | 2019-03-05 | 科沃斯机器人股份有限公司 | Self-movement robot paths planning method |
CN108519773A (en) * | 2018-03-07 | 2018-09-11 | 西安交通大学 | The paths planning method of automatic driving vehicle under a kind of structured environment |
CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
CN110728014A (en) * | 2018-06-27 | 2020-01-24 | 百度(美国)有限责任公司 | Reference line smoothing method using segmented spiral curves with weighted geometric cost |
WO2020021126A1 (en) * | 2018-07-27 | 2020-01-30 | Embotech Ag | Method for steering a vehicle and apparatus therefor |
CN110696818A (en) * | 2019-10-12 | 2020-01-17 | 深圳市布谷鸟科技有限公司 | Automatic parking method and system based on optimal path |
CN110823240A (en) * | 2019-11-19 | 2020-02-21 | 齐鲁工业大学 | Following robot path planning method and system with course constraint |
Non-Patent Citations (1)
Title |
---|
封声飞 第: "自适应蚁群算法的移动机器人路径规划", 计算机工程与应用, vol. 55, no. 17 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112286194A (en) * | 2020-10-29 | 2021-01-29 | 广东杜尼智能机器人工程技术研究中心有限公司 | Cost map area division method |
CN112286194B (en) * | 2020-10-29 | 2022-05-17 | 广东杜尼智能机器人工程技术研究中心有限公司 | Cost map area division method |
CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
CN112378408B (en) * | 2020-11-26 | 2023-07-25 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
CN113758484A (en) * | 2020-11-30 | 2021-12-07 | 北京京东乾石科技有限公司 | Path planning method and device |
CN112698649A (en) * | 2020-12-15 | 2021-04-23 | 深圳众为兴技术股份有限公司 | Pose path smooth transition planning method, computer readable storage medium and device |
CN112747763A (en) * | 2020-12-30 | 2021-05-04 | 深兰人工智能(深圳)有限公司 | Local path planning method and device, electronic equipment and storage medium |
CN112747763B (en) * | 2020-12-30 | 2024-04-09 | 深兰人工智能(深圳)有限公司 | Local path planning method, device, electronic equipment and storage medium |
CN112965495A (en) * | 2021-02-10 | 2021-06-15 | 苏州清乐智能科技有限公司 | Disinfection robot and autonomous navigation method thereof |
CN112965495B (en) * | 2021-02-10 | 2022-12-06 | 苏州清乐智能科技有限公司 | Disinfection robot and autonomous navigation method thereof |
CN112937557A (en) * | 2021-03-09 | 2021-06-11 | 东风汽车集团股份有限公司 | Curvature control-based passenger-riding parking path planning method and system |
CN112964271B (en) * | 2021-03-15 | 2023-03-31 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
CN112964271A (en) * | 2021-03-15 | 2021-06-15 | 西安交通大学 | Multi-scene-oriented automatic driving planning method and system |
CN113485369A (en) * | 2021-08-03 | 2021-10-08 | 浙江大学 | Indoor mobile robot path planning and path optimization method for improving A-x algorithm |
CN113778097A (en) * | 2021-09-15 | 2021-12-10 | 龙岩学院 | Intelligent warehouse logistics robot path planning method for improving A-STAR algorithm through L-shaped path trend |
CN113778097B (en) * | 2021-09-15 | 2023-05-19 | 龙岩学院 | Intelligent warehouse logistics robot path planning method based on L-shaped path trend improved A-STAR algorithm |
CN114089774B (en) * | 2022-01-14 | 2022-04-12 | 中国科学院微电子研究所 | AGV path planning method and device in storage environment |
CN114089774A (en) * | 2022-01-14 | 2022-02-25 | 中国科学院微电子研究所 | AGV path planning method and device in storage environment |
CN114995398A (en) * | 2022-05-16 | 2022-09-02 | 中国第一汽车股份有限公司 | Path generation method, path generation device, storage medium, processor and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111811517A (en) | Dynamic local path planning method and system | |
Alonso-Mora et al. | Cooperative collision avoidance for nonholonomic robots | |
Paden et al. | A survey of motion planning and control techniques for self-driving urban vehicles | |
US20200379461A1 (en) | Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout | |
Amditis et al. | A situation-adaptive lane-keeping support system: Overview of the safelane approach | |
US11487296B2 (en) | Method and system for deterministic trajectory selection based on uncertainty estimation for an autonomous agent | |
WO2018181974A1 (en) | Determination device, determination method, and program | |
CN108153310B (en) | Mobile robot real-time motion planning method based on human behavior simulation | |
US20210117787A1 (en) | Method for determining a quality grade of data sets of sensors | |
US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
US11604469B2 (en) | Route determining device, robot, and route determining method | |
Artunedo et al. | Motion planning approach considering localization uncertainty | |
Chen et al. | Robot navigation with map-based deep reinforcement learning | |
Garrote et al. | Mobile robot localization with reinforcement learning map update decision aided by an absolute indoor positioning system | |
Kanchwala et al. | Development of an intelligent transport system for EV | |
Tsogas et al. | Using digital maps to enhance lane keeping support systems | |
Bis et al. | Velocity occupancy space: autonomous navigation in an uncertain, dynamic environment | |
Lienke et al. | An ad-hoc sampling-based planner for on-road automated driving | |
Kuhnt et al. | Lane-precise localization of intelligent vehicles using the surrounding object constellation | |
EP4148599A1 (en) | Systems and methods for providing and using confidence estimations for semantic labeling | |
Song et al. | Real-time localization measure and perception detection using multi-sensor fusion for Automated Guided Vehicles | |
Wei et al. | Multi-sensor environmental perception and adaptive cruise control of intelligent vehicles using kalman filter | |
Guan et al. | TNES: terrain traversability mapping, navigation and excavation system for autonomous excavators on worksite | |
Rexin et al. | Fusion of object tracking and dynamic occupancy grid map | |
Zeghmi et al. | A Kalman-particle hybrid filter for improved localization of AGV in indoor environment |
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 |