AU2021105318A4 - Calculation method applied to movement path of intelligent robot - Google Patents
Calculation method applied to movement path of intelligent robot Download PDFInfo
- Publication number
- AU2021105318A4 AU2021105318A4 AU2021105318A AU2021105318A AU2021105318A4 AU 2021105318 A4 AU2021105318 A4 AU 2021105318A4 AU 2021105318 A AU2021105318 A AU 2021105318A AU 2021105318 A AU2021105318 A AU 2021105318A AU 2021105318 A4 AU2021105318 A4 AU 2021105318A4
- Authority
- AU
- Australia
- Prior art keywords
- algorithm
- calculation method
- ros
- intelligent robot
- movement path
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 48
- 238000004364 calculation method Methods 0.000 title claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 119
- 238000004088 simulation Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 238000013461 design Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000009471 action Effects 0.000 claims abstract description 10
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims abstract description 9
- 230000006399 behavior Effects 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 21
- 230000000694 effects Effects 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 4
- 230000018109 developmental process Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 claims description 3
- 230000033772 system development Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 description 5
- 150000002500 ions Chemical class 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 238000004659 sterilization and disinfection Methods 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000001954 sterilising effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 210000000349 chromosome Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 210000003855 cell nucleus Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention discloses a calculation method applied to a movement path
of an intelligent robot, including the following steps: S, selecting tool software;
selecting ROS as a system; taking matrix experiment software as a design and
simulation tool; and determining a communication solution of the matrix experiment
software and the ROS; S2, analyzing exhibition of two achievements of the ROS
system; S3, determining a final algorithm by comparing with an existing path
movement algorithm; obtaining a final calculation method by virtue of analysis of
partial existing algorithms: avoiding local optimum: setting a coefficient to enable an
intelligent agent to have certain probability to take an optimum behavior and to have
certain probability to immediately take all available actions; and bringing all taken
paths into a memory vault to avoid small-range cycles; S4, determining a position
algorithm; and measuring arrival time between a to-be-positioned node MS (x, y) and
a signal of a transmitting terminal (xi, yi) according to a TOA principle. An
application range of a 1 plasma air sterilizer with the intelligent robot as a carrier is
widened in the market.
1/4
Selecting tool software; selecting ROS as a system;
taking matrix experiment software as a design and
simulation tool; and determining a communication
solution of the matrix experiment software and the
ROS
Analyzing exhibitionof two achievements of the
ROS system, wherein the two achievements
respectively include achievements of a real robot
and a simulated robot
Determining a final algorithm by comparing with an
existing path movement algorithm; and obtaining a
final calculation method by virtue of analysis of a
Dijkstra algorithm, a Q-Learning algorithm, a
Bidirectional RRT / RRT Connect algorithm, an
RRT algorithm, a Fuzzy algorithm, a GA algorithm,
a potential algorithm and a PRM algorithm
Determining a position algorithm: measuring arrival
time between a to-be-positioned node MS (x, y)
and a signal of a transmitting terminal (xi, yi)
according to a TOA principle; and then converting
the arrival time into a distance so as to perform
positioning
FIG. 1
Description
1/4
Selecting tool software; selecting ROS as a system; taking matrix experiment software as a design and simulation tool; and determining a communication solution of the matrix experiment software and the ROS
Analyzing exhibitionof two achievements of the ROS system, wherein the two achievements respectively include achievements of a real robot and a simulated robot
Determining a final algorithm by comparing with an existing path movement algorithm; and obtaining a final calculation method by virtue of analysis of a Dijkstra algorithm, a Q-Learning algorithm, a Bidirectional RRT / RRT Connect algorithm, an RRT algorithm, a Fuzzy algorithm, a GA algorithm, a potential algorithm and a PRM algorithm
Determining a position algorithm: measuring arrival time between a to-be-positioned node MS (x, y) and a signal of a transmitting terminal (xi, yi) according to a TOA principle; and then converting the arrival time into a distance so as to perform positioning
FIG. 1
The present invention belongs to the technical field of robot movement paths,
and particularly relates to a calculation method applied to a movement path of an
intelligent robot.
A plasma air sterilizer has the international advanced level, and instantaneously
excites giga-level negative and positive ions by utilizing a (sPC) super ion generator.
It may realize efficient sterilization, is excellent in plasma sterilization and
disinfection effects and short in action time, and has the effects far beyond
high-intensity ultraviolet rays. Plasma is a fourth form after solid, liquid and gas. SPC
super ion cloud releases giga-level negative and positive ions. Lots of energy is
produced by virtue of annihilation of the negative and positive ions, so as to destroy
bacterial envelope and kill cell nucleus.
Most of the existing plasma air sterilizers are fixed or manually pushed, and are
short of intelligent movement functions. Therefore, a calculation method applied to a
movement path of an intelligent robot is urgently needed. The calculation method is
combined with plasma air sterilization so that the plasma air sterilizer is used as a
carrier to widen the application range of the novel plasma air sterilizer in the market
and expand the application range of the robot movement.
To achieve the above purpose, the present invention provides the following
technical solutions:
A calculation method applied to a movement path of an intelligent robot includes
the following steps:
Si, selecting tool software; selecting ROS as a system; taking matrix experiment
software as a design and simulation tool; and determining a communication solution
of the matrix experiment software and the ROS;
S2, analyzing exhibition of two achievements of the ROS system, wherein the
two achievements respectively include achievements of a real robot and a simulated
robot; a cycle navigation effect of the real robot is as follows: navigation points must
be given in rviz by using CycleGoal; then a cycle index is given and navigation is
initiated by using NavPanel; the Enter key needs to be pressed down (can be pressed
once only) after the cycle index is input during use of the NavPanel; the Enter key
needs to be pressed down (can be pressed once only) while initiating navigation; an
autonomous wall patrol mapping effect is as follows: a range needing to be explored
is marked by four points of Publish Point after startup, and then a final point is clicked
in a place with the map to make an exploration tree feasible; after the five points are
clicked, independent exploration needs to be started by 2D Nav Goal; a cycle
navigation effect of the simulated robot includes an avdemo effect as follows:
different from the previous real robot, if a complete Nav needs to be completed during
simulation, multiple navdemos are needed; and an exhibition effect picture of one
demo is provided;
S3, determining a final algorithm by comparing with an existing path movement
algorithm; obtaining a final calculation method by virtue of analysis of a Dijkstra
algorithm, a Q-Learning algorithm, a Bidirectional RRT / RRT Connect algorithm, an
RRT algorithm, a Fuzzy algorithm, a GA algorithm, a potential algorithm and a PRM
algorithm: avoiding local optimum: setting a coefficient to enable an intelligent agent
to have certain probability to take an optimum behavior and to have certain
probability to immediately take all available actions; and bringing all taken paths into
a memory vault to avoid small-range cycles;
increasing tilt movement: setting a reward value of the tilt movement as 42/ 2;
and taking an approximate value of 0.707, so as to avoid a condition that the robot
does not directly move left by two spaces but moves towards the upper left and then towards the lower left; S4, determining a position algorithm: measuring arrival time between a to-be-positioned node MS (x, y) and a signal of a transmitting terminal (xi, yi) according to a TOA principle; then converting the arrival time into a distance so as to perform positioning, wherein distances from three base stations to the MS are respectively rl, r2 and r3; and drawing three circles by taking the respective base stations as the centers of circles and taking the measured distance as a radius, wherein an intersection of the three circles is the location of the MS. When the three base stations are LOS base stations, an estimated position of the MS may be generally calculated according to a least squares (LS) algorithm.
Preferably, the ROS is a distributed process (i.e., "node") framework; the
processes are encapsulated in program packages and function packages that are easily
shared and published; the ROS may support a combination system similar to a code
repository, wherein the system may realize cooperation and release of the project;
development and realization of one project may be subjected to completely
independent decision-making (not limited by the ROS) from a file system to a user
interface; and all the projects may be integrated by a master tool of the ROS.
Preferably, with the adoption of MATLAB (Matrix Laboratory), the matrix
experiment software includes a numerical analysis unit, a numerical and symbolic
computation unit, an engineering and scientific mapping unit, a design and simulation
unit of a control system, a digital image processing unit, a digital signal processing
unit, and a finance and financial engineering unit.
Preferably, the MATLAB includes a plurality of module sets and toolboxes; and
users directly learn, use and evaluate different methods by using the toolboxes without
writing codes. Fields of the MATLAB include data acquisition, database interface,
probability statistics, spline fitting, optimization algorithms, partial differential
equation solution, neural networks, wavelet analysis, signal processing, image
processing, system identification, control system design, LMI control, robust control,
model prediction, fuzzy logic, analytical finance, map tools, nonlinear control design, real-time rapid prototype and semi-physical simulation, embedded system development, fixed-point simulation, DSP and communication and power system simulation.
Preferably, simulated robot demonstration includes steps:
cbh: opening major function packages including functions of mapping, navigation and independent exploration;
navpanel (under CBHcyclenav): rviz plug-in, used for receiving single
navigation points; setting cycle indexes; and publishing multiple navigation points
and cycle indexes;
nav_tool (under CBHcyclenav): rviz tool, publishing single navigation points;
cyclenav(under CBHcyclenav): receiving multiple navigation points and cycle
indexes to realize a multipoint cycle navigation function;
depthimageto-laserscan: converting depth camera data into laser data;
pointcloudtolaserscan: converting point cloud data into laser data;
rrt_exploration: rapidly-exploring random number autonomous wall patrol
mapping algorithm.
Preferably, the rapidly-exploring random number autonomous wall patrol
mapping algorithm is as follows: global and local random exploring trees are made
according to map data; a maker is displayed on rviz; paths of the exploring trees are
published onto a filter; these data are filtered by the filter; data conforming to map
boundary characteristics are published onto an assigner; and movebase navigation is
conducted herein by the assigner.
Preferably, the movement path of the intelligent robot may be further positioned
by a sensing control module; the sensing control module includes an infrared
transmitting unit and an infrared receiving unit; the infrared transmitting unit adopts
an oscillating circuit; an oscillation frequency of the oscillating circuit is adjusted to
be close to a frequency f; an infrared transmitting tube is driven, so that the infrared
transmitting unit transmits infrared light having the frequency f approximately; the
infrared receiving unit receives a signal through an infrared receiving tube; the received signal is amplified by an amplification circuit composed of single operational amplifiers; and the amplified signal is applied to the oscillating circuit for decoding.
Preferably, the infrared transmitting unit and the infrared receiving unit are
cascaded through a master control system.
Preferably, a control circuit of the master control system includes a master
control chip U4; and the master control chip U4 includes third address terminals
CO-C8, three data terminals RAO-RA2, one switch control terminal Power and one
reset control terminal.
Preferably, the third address terminals CO-C8 are respectively matched with
second address terminals BO-B8 of a decoder U3; the data terminals RAO-RA2 are
respectively connected with decoding output terminals DBO-DB2 of the decoder U3
correspondingly; and finally, a corresponding control signal is respectively output to
the switch control terminal and the reset control terminal according to the received
address code and data code.
The present invention has technical effects and advantages as follows: in the
calculation method applied to the movement path of the intelligent robot, after
exhibition of two achievements of the ROS system is analyzed by taking the ROS as
the system and selecting the MATLAB as the design and simulation tool, the final
path movement calculation method is obtained by analyzing the Dijkstra algorithm,
the Q-Learning algorithm, the Bidirectional RRT / RRT Connect algorithm, the RRT
algorithm, the Fuzzy algorithm, the GA algorithm, the potential algorithm and the
PRM algorithm, thereby avoiding the local optimum and increasing the tilt movement.
Meanwhile, the position algorithm is determined, so that maximum values of vectors
in multiple fields are achieved.
Fig. 1 is an algorithm flow chart of a calculation method applied to a movement
path of an intelligent robot in the present invention;
Fig. 2 is a Q-Leaming algorithm flow chart of a calculation method applied to a movement path of an intelligent robot in the present invention;
Fig. 3 is a Dijkstra algorithm flow chart of a calculation method applied to a
movement path of an intelligent robot in the present invention; and
Fig. 4 is a GA algorithm flow chart of a calculation method applied to a
movement path of an intelligent robot in the present invention.
To make purposes, technical solutions and advantages of the present invention
clearer, the present invention will be further described below in detail in combination
with specific embodiments. It should be understood that, the specific embodiments
described herein are merely used for explaining the present invention, rather than
limiting the present invention. Based on embodiments in the present invention, all
other embodiments obtained by those ordinary skilled in the art without making
creative labor belong to the protection scope of the present invention.
A calculation method applied to a movement path of an intelligent robot includes
the following steps:
Si, selecting tool software; selecting ROS as a system; taking matrix experiment
software as a design and simulation tool; and determining a communication solution
of the matrix experiment software and the ROS;
S2, analyzing exhibition of two achievements of the ROS system, wherein the
two achievements respectively include achievements of a real robot and a simulated
robot; a cycle navigation effect of the real robot is as follows: navigation points must
be given in rviz by using CycleGoal; then a cycle index is given and navigation is
initiated by using NavPanel; the Enter key needs to be pressed down (can be pressed
once only) after the cycle index is input during use of the NavPanel; the Enter key
needs to be pressed down (can be pressed once only) while initiating navigation; an
autonomous wall patrol mapping effect is as follows: a range needing to be explored
is marked by four points of Publish Point after startup, and then a final point is clicked
in a place with the map to make an exploration tree feasible; after the five points are clicked, independent exploration needs to be started by 2D Nav Goal; a cycle navigation effect of the simulated robot includes an av demo effect as follows: different from the previous real robot, if a complete Nav needs to be completed during simulation, multiple navdemos are needed; and an exhibition effect picture of one demo is provided;
S3, determining a final algorithm by comparing with an existing path movement
algorithm; obtaining a final calculation method by virtue of analysis of a Dijkstra
algorithm, a Q-Learning algorithm, a Bidirectional RRT / RRT Connect algorithm, an
RRT algorithm, a Fuzzy algorithm, a GA algorithm, a potential algorithm and a PRM
algorithm: avoiding local optimum: setting a coefficient to enable an intelligent agent
to have certain probability to take an optimum behavior and to have certain
probability to immediately take all available actions; and bringing all taken paths into
a memory vault to avoid small-range cycles;
increasing tilt movement: setting a reward value of the tilt movement as J2/ 2;
and taking an approximate value of 0.707, so as to avoid a condition that the robot
does not directly move left by two spaces but moves towards the upper left and then
towards the lower left;
S4, determining a position algorithm: measuring arrival time between a
to-be-positioned node MS (x, y) and a signal of a transmitting terminal (xi, yi)
according to a TOA principle; then converting the arrival time into a distance so as to
perform positioning, wherein distances from three base stations to the MS are
respectively rl, r2 and r3; and drawing three circles by taking the respective base
stations as the centers of circles and taking the measured distance as a radius, wherein
an intersection of the three circles is the location of the MS. When the three base
stations are LOS base stations, an estimated position of the MS may be generally
calculated according to a least squares (LS) algorithm.
Specifically, the ROS is a distributed process (i.e., "node") framework; the
processes are encapsulated in program packages and function packages that are easily
shared and published; the ROS may support a combination system similar to a code repository, wherein the system may realize cooperation and release of the project; development and realization of one project may be subjected to completely independent decision-making (not limited by the ROS) from a file system to a user interface; and all the projects may be integrated by a master tool of the ROS.
Specifically, with the adoption of MATLAB (Matrix Laboratory), the matrix
experiment software includes a numerical analysis unit, a numerical and symbolic
computation unit, an engineering and scientific mapping unit, a design and simulation
unit of a control system, a digital image processing unit, a digital signal processing
unit, and a finance and financial engineering unit.
Specifically, the MATLAB includes a plurality of module sets and toolboxes; and
users directly learn, use and evaluate different methods by using the toolboxes without
writing codes. Fields of the MATLAB include data acquisition, database interface,
probability statistics, spline fitting, optimization algorithms, partial differential
equation solution, neural networks, wavelet analysis, signal processing, image
processing, system identification, control system design, LMI control, robust control,
model prediction, fuzzy logic, analytical finance, map tools, nonlinear control design,
real-time rapid prototype and semi-physical simulation, embedded system
development, fixed-point simulation, DSP and communication and power system
simulation.
Specifically, simulated robot demonstration includes steps:
cbh: opening major function packages including functions of mapping,
navigation and independent exploration;
navpanel (under CBHcyclenav): rviz plug-in, used for receiving single
navigation points; setting cycle indexes; and publishing multiple navigation points
and cycle indexes;
nav_tool (under CBHcyclenav): rviz tool, publishing single navigation points;
cyclenav(under CBHcyclenav): receiving multiple navigation points and cycle
indexes to realize a multipoint cycle navigation function;
depthimageto-laserscan: converting depth camera data into laser data; pointcloudtolaserscan: converting point cloud data into laser data; rrtexploration: rapidly-exploring random number autonomous wall patrol mapping algorithm. Specifically, the rapidly-exploring random number autonomous wall patrol mapping algorithm is as follows: global and local random exploring trees are made according to map data; a maker is displayed on rviz; paths of the exploring trees are published onto a filter; these data are filtered by the filter; data conforming to map boundary characteristics are published onto an assigner; and movebase navigation is conducted herein by the assigner. Specifically, the movement path of the intelligent robot may be further positioned by a sensing control module; the sensing control module includes an infrared transmitting unit and an infrared receiving unit; the infrared transmitting unit adopts an oscillating circuit; an oscillation frequency of the oscillating circuit is adjusted to be close to a frequency f; an infrared transmitting tube is driven, so that the infrared transmitting unit transmits infrared light having the frequency f approximately; the infrared receiving unit receives a signal through an infrared receiving tube; the received signal is amplified by an amplification circuit composed of single operational amplifiers; and the amplified signal is applied to the oscillating circuit for decoding. Specifically, the infrared transmitting unit and the infrared receiving unit are cascaded through a master control system. Specifically, a control circuit of the master control system includes a master control chip U4; and the master control chip U4 includes third address terminals CO-C8, three data terminals RA-RA2, one switch control terminal Power and one reset control terminal. Specifically, the third address terminals CO-C8 are respectively matched with second address terminals B-B8 of a decoder U3; the data terminals RA-RA2 are respectively connected with decoding output terminals DBO-DB2 of the decoder U3 correspondingly; and finally, a corresponding control signal is respectively output to the switch control terminal and the reset control terminal according to the received address code and data code. Specifically, the Q-Leaming algorithm is a value-based algorithm in reinforcement learning algorithms. Q, i.e., Q (s,a), is an expectation that benefits may be obtained with an action a (aEA) in a state s (sES) at a certain moment. Corresponding reward r will be fed back by the environment according to actions of agent. Therefore, a main idea of the algorithm is to form a Q-table from State and Action to store the value Q; and then, the action through which the maximum benefit can be obtained is selected according to the value Q. The Q-Learning algorithm has major advantages as follows: offline learning can be conducted by using a temporal difference method TD (fused with Monte Carlo and dynamic planning); and an optimum strategy may be solved for a markoff process by using an equation bellman. Q(s,a)<-Q(s,a)+a[r+ymaxa'Q(s',a')-Q(s,a)] In the equation, a is a learning rate; and y is an incentive decay coefficient. The equation is a formula of Q-Learning update. The maximum value Q(s',a') in the next state s' is multiplied by the decay y; the product is added to a true reward value; and the sum serves as Q true. Q(s,a) in the previous Q table serves as estimated Q. Specifically, the Dijkstra algorithm is a greedy strategy. An array dis is declared for saving a minimum distance from a source point to each vertex and saving a vertex set T in which the minimum distance is found. At initial time, a path weight of an origin s is assigned as 0, a directly reachable edge of the vertex s is set as (s, m), then dis[m] is set as w(s, m). Meanwhile, the path length of all other unreachable vertexes is set infinite; and the set T only includes s at the initial time. Then, a minimum value is selected from the array dis, thus the value is the shortest path from the origin s to the vertex that corresponds to the value; the point is further added into the T; then it shall be known whether the newly added vertex may reach the other vertexes and whether a path that reaches the other points via the vertex is shorter than a directly reachable path of the origin. If so, values of these vertexes in the dis are replaced.
Later, the minimum value is found in the dis; and the above actions are repeated until all the vertexes of the map are included in the T.
The Dijkstra algorithm includes the following steps:
(1) at initial time, S only includes the origins; U includes other vertexes except
for the s; a distance of the vertexes in the U is "a distance from the origin s to the
vertexes" [for example, the distance of the vertexes v in the U is a length of (s, v); the
s and v are non-adjacent; and the distance of the v is o];
(2) selecting a "vertex k with the minimum distance" from the U; adding the
vertex k into the S; and removing the vertex k from the U;
(3) updating the distance from each vertex in the U to the origin s, wherein the
reason why the distance of the vertexes in the U is updated is that k is the vertex
through which the shortest path in the previous step; then distances of other vertexes
may be updated by utilizing the k; for example, the distance of (s, v) may be greater
than the distance of (s,k)+(k,v);
(4) repeating the steps (2) and (3) until all the vertexes are traversed.
The RRT algorithm is an effective planning method in a multi-dimensional space.
The RRT algorithm is as follows: a rapidly-exploring random tree is generated by
taking an initial point as a root node in a manner of increasing leaf nodes by virtue of
random sampling; when the leaf nodes in the random tree include target points or
enter a target area, a path from the initial point to the target point can be found in the
random tree. During initialization, the random tree T only includes one node, i.e., a
root node qinit. Firstly, a sampling point qrand is randomly selected by a Sample
function from a state space; then a node qnearest nearest to the qrand is selected by
Nearest sample from the random tree; and finally, a novel node qnew is obtained by
extending a certain distance from the qnearest to the qrand by an Extend function. If
the qnew collides with an obstacle, the Extend function returns null; and growth is
abandoned, otherwise the qnew is added into the random tree. The above steps are
repeated until the distance between the qnearest and the target point qgaol is smaller
than a threshold value, which indicates that the random tree reaches the target point
and algorithm return is successful. To make the algorithm controllable, an upper limit of run time or an upper limit of search times may be set. If the target point cannot be reached in limited times, algorithm return is unsuccessful. To increase a speed of reaching the target point from the random tree, a simple improvement method is as follows: whether the qrand is the target point or the random point is determined according to random probability during growth of the random tree each time. A parameter Prob is set in the Sample function; a random value p from 0 to 1.0 is obtained each time; when 0<p<Prob, the random tree grows towards the target point; and when Prob<p<1.0, the random tree grows towards one random direction.
Compared with original RRT, the Bidirectional RRT / RRT Connect algorithm is
as follows: a second tree is built in a target point area for extension. During each
iteration, starting steps are the same as those in the original RRT algorithm and
include operations of sampling random points and performing extension. Then, after a
new node qnew of the first tree is extended, the new target point serves as an
extension direction of the second tree. Meanwhile, the second tree has a slightly
different extension manner. Firstly, q'new is obtained by extension in the first step; if
there is no collision, the second step is continuously extended in the same direction
until extension is unsuccessful or q'new=qnew means that the second tree is
connected with the first tree. Certainly, balance of the two trees must be considered
during each iteration, i.e., the number of nodes of the two trees. The tree with a
"smaller" exchange order is extended. Such a bidirectional RRT technology has
excellent search features, significantly increases the search rate and search efficiency
compared with the original RRT algorithm, and is widely applied. Firstly, compared
with the previous algorithm, the Connect algorithm has a larger extended step length,
so that the tree grows faster; secondly, the two trees are alternatively exchanged
towards each other, instead of a random extension manner, and particularly when a
starting position and a target position are located in a constraint area, the two trees
may be rapidly extended towards each other to get away from the respective
constraint area. Due to the enlightening extension, extension of the tree is greedy and
clear, so that the double-tree RRT algorithm is more effective compared with a single-tree RRT algorithm.
The Fuzzy algorithm is to associate clustering with data points through a member
level. The member level shows association intensity between the data points and
certain clustering. The member level is used as a basis to determine one or more
clusters to which the data points belong. The Fuzzy algorithm includes the following
calculation steps:
(1) performing uniform distribution initialization on a membership matrix by
using a value of (0, 1) to meet constraint:
us= 1,Ys=L1,2,-,m
(2) calculating c clustering centers, wherein j=1,......,c; and an expression is as
follows:
' =
(3) calculating a cost function, wherein the change of the cost function and a cost
function value in the previous iteration is smaller than a certain threshold value, the
algorithm is stopped;
(4) calculating a novel membership matrix; and returning to the step 2.
1.
The GA algorithm is an algorithm which is in combination with adaptive
probability optimization based on biological genetics and evolution mechanisms, and
includes the following specific calculation steps:
(1) determining a value range of a fitness function; and determining precision
and chromosome coding lengths;
(2) initializing: coding chromosome; and determining a population quantity,
cross and mutation probability;
(3) population initialization: randomly generating a first-generation population;
(4) evaluating the population by utilizing the fitness function; judging whether a
stop condition is met; if so, stopping, and outputting an optimal solution; otherwise
continuously operating; and
(5) performing selection, cross and mutation operations on the population to
obtain the next-generation population; and returning to the step 4.
The potential algorithm is as follows: a motion of the robot in an environment is
regarded as a motion of the robot in a virtual artificial stress field; an obstacle
generates repulsion to the robot; the target point generates attraction to the robot; and
resultant force of the attraction and the repulsion serves as accelerating force of the
robot to control a motion direction of the robot and calculate a position of the robot.
A potential field is manually established; the obstacle is set as the repulsion; the
target is set as the attraction; vector addition of the force is conducted; and finally, a
direction of the resultant force is calculated.
Attraction field:
Repulsion field: I 1 1
0,1 p(qqQ) > pO
{ 10, -
~P(q q~t) > PO P(q'qQZbh) P0
Total field:
U(q)=U ,(q)+ U,(q)
F(q)= -VU(q)
The PRM algorithm is a PRM method based on a random sampling technology,
and may effectively solve a path planning problem in "higher dimensional space" and
"complicated constraint".
A path between two points in a given map is searched by a path random map
(PRM) method. The PRM includes the following path planning steps:
learning phase: randomly setting points (with the number self-defined) in a free
space of the given map; and forming a path network map.
a) A construction step
b) An expansion step
Query phase:
A path from a starting point to an ending point is queried.
a) Local path planning
b) Distance calculation
c) Collision check.
To sum up, in the calculation method applied to the movement path of the
intelligent robot, after exhibition of two achievements of the ROS system is analyzed
by taking the ROS as the system and selecting the MATLAB as the design and
simulation tool, the final path movement calculation method is obtained by analyzing
the Dijkstra algorithm, the Q-Learning algorithm, the Bidirectional RRT / RRT
Connect algorithm, the RRT algorithm, the Fuzzy algorithm, the GA algorithm, the
potential algorithm and the PRM algorithm, thereby avoiding the local optimum and
increasing the tilt movement. Meanwhile, the position algorithm is determined, so that
maximum values of vectors in multiple fields are achieved.
Finally, it shall be indicated that, the above only describes preferred
embodiments of the present invention, rather than limits the present invention.
Although the present invention is described in detail with reference to the above
embodiments, technical solutions recorded in the above embodiments may be still
modified by those skilled in the art, or partial technical features may be equivalently
replaced. Any modifications, equivalent replacements and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims (10)
- CLAIMS 1. A calculation method applied to a movement path of an intelligent robot,comprising the following steps:Si, selecting tool software; selecting ROS as a system; taking matrix experimentsoftware as a design and simulation tool; and determining a communication solutionof the matrix experiment software and the ROS;S2, analyzing exhibition of two achievements of the ROS system, wherein thetwo achievements respectively comprise achievements of a real robot and a simulatedrobot; a cycle navigation effect of the real robot is as follows: navigation points aregiven in rviz by using CycleGoal; then a cycle index is given and navigation isinitiated by using NavPanel; an autonomous wall patrol mapping effect is as follows:a range to be explored is marked by four points of Publish Point after startup, and thena final point is clicked in a place with the map to make an exploration tree feasible;after the five points are clicked, independent exploration is started by 2D Nav Goal;S3, determining a final algorithm by comparing with an existing path movementalgorithm; obtaining a final calculation method by virtue of analysis of a Dijkstraalgorithm, a Q-Leaming algorithm, a Bidirectional RRT / RRT Connect algorithm, anRRT algorithm, a Fuzzy algorithm, a GA algorithm, a potential algorithm and a PRMalgorithm: avoiding local optimum: setting a coefficient to enable an intelligent agentto have certain probability to take an optimum behavior and to have certainprobability to immediately take all available actions; and bringing all taken paths intoa memory vault to avoid small-range cycles;increasing tilt movement: setting a reward value of the tilt movement as J2/ 2;and taking an approximate value of 0.707;S4, determining a position algorithm: measuring arrival time between ato-be-positioned node MS (x, y) and a signal of a transmitting terminal (xi, yi)according to a TOA principle; then converting the arrival time into a distance toperform positioning, wherein distances from three base stations to the MS arerespectively rl, r2 and r3; and drawing three circles by taking the respective basestations as the centers of circles and taking the measured distance as a radius, wherein an intersection of the three circles is the location of the MS; and when the three base stations are LOS base stations, an estimated position of the MS is calculated according to a least squares (LS) algorithm.
- 2. The calculation method applied to the movement path of the intelligent robot according to claim 1, wherein the ROS is a distributed process framework encapsulated in program packages and function packages that are easily shared and published; the ROS supports a combination system of a code repository which realizes cooperation and release of the project; development and realization of one project are subjected to completely independent decision-making from a file system to a user interface; and all the projects are integrated by a master tool of the ROS.
- 3. The calculation method applied to the movement path of the intelligent robot according to claim 1, wherein with the adoption of MATLAB (Matrix Laboratory), the matrix experiment software comprises a numerical analysis unit, a numerical and symbolic computation unit, an engineering and scientific mapping unit, a design and simulation unit of a control system, a digital image processing unit, a digital signal processing unit, and a finance and financial engineering unit.
- 4. The calculation method applied to the movement path of the intelligent robot according to claim 3, wherein the MATLAB comprises a plurality of module sets and toolboxes; and users directly learn, use and evaluate different methods by using the toolboxes; and fields of the MATLAB comprise data acquisition, database interface, probability statistics, spline fitting, optimization algorithms, partial differential equation solution, neural networks, wavelet analysis, signal processing, image processing, system identification, control system design, LMI control, robust control, model prediction, fuzzy logic, analytical finance, map tools, nonlinear control design, real-time rapid prototype and semi-physical simulation, embedded system development, fixed-point simulation, DSP and communication and power system simulation.
- 5. The calculation method applied to the movement path of the intelligent robot according to claim 1, wherein simulated robot demonstration comprises steps: cbh: opening function packages comprising mapping, navigation and independentexploration; navpanel (under CBHcyclenav): rviz plug-in, used for receiving single navigation points; setting cycle indexes; and publishing multiple navigation points and cycle indexes; nav_tool (under CBHcyclenav): rviz tool, publishing single navigation points; cyclenav(under CBHcyclenav): receiving multiple navigation points and cycle indexes to realize a multipoint cycle navigation function; depthimageto-laserscan: converting depth camera data into laser data; pointcloudtolaserscan: converting point cloud data into laser data; rrt_exploration: rapidly-exploring random number autonomous wall patrol mapping algorithm.
- 6. The calculation method applied to the movement path of the intelligent robot according to claim 5, wherein the rapidly-exploring random number autonomous wall patrol mapping algorithm is as follows: global and local random exploring trees are made according to map data; a maker is displayed on rviz; paths of the exploring trees are published onto a filter; these data are filtered by the filter; data conforming to map boundary characteristics are published onto an assigner; and movebase navigation is conducted herein by the assigner.
- 7. The calculation method applied to the movement path of the intelligent robot according to claim 1, wherein the movement path of the intelligent robot is positioned by a sensing control module; the sensing control module comprises an infrared transmitting unit and an infrared receiving unit; the infrared transmitting unit adopts an oscillating circuit; an oscillation frequency of the oscillating circuit is adjusted to be a set frequency f; an infrared transmitting tube is driven, so that the infrared transmitting unit transmits infrared light having the frequency f approximately; the infrared receiving unit receives a signal through an infrared receiving tube; the received signal is amplified by an amplification circuit composed of single operational amplifiers; and the amplified signal is applied to the oscillating circuit for decoding.
- 8. The calculation method applied to the movement path of the intelligent robot according to claim 7, wherein the infrared transmitting unit and the infrared receiving unit are cascaded through a master control system.
- 9. The calculation method applied to the movement path of the intelligent robot according to claim 8, wherein a control circuit of the master control system comprises a master control chip U4; and the master control chip U4 comprises third address terminals CO-C8, three data terminals RAO-RA2, one switch control terminal Power and one reset control terminal.
- 10. The calculation method applied to the movement path of the intelligent robot according to claim 9, wherein the third address terminals C-C8 are respectively matched with second address terminals B-B8 of a decoder U3; the data terminals RA-RA2 are respectively connected with decoding output terminals DBO-DB2 of the decoder U3 correspondingly; and finally, a corresponding control signal is respectively output to the switch control terminal and the reset control terminal according to the received address code and data code.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110097551.4 | 2021-01-25 | ||
| CN202110097551.4A CN112925318A (en) | 2021-01-25 | 2021-01-25 | Calculation method applied to intelligent robot moving path |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021105318A4 true AU2021105318A4 (en) | 2021-10-07 |
Family
ID=76167210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021105318A Active AU2021105318A4 (en) | 2021-01-25 | 2021-08-11 | Calculation method applied to movement path of intelligent robot |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112925318A (en) |
| AU (1) | AU2021105318A4 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673836B (en) * | 2021-07-29 | 2023-08-18 | 清华大学深圳国际研究生院 | Reinforced learning-based shared bus line-attaching scheduling method |
| CN113485363B (en) * | 2021-08-02 | 2024-02-20 | 安徽理工大学 | Coal mine underground robot multi-step long path planning method based on membrane calculation and RRT |
| CN113759806B (en) * | 2021-09-28 | 2023-06-30 | 广西科技师范学院 | Control system of writing robot |
| CN114186859B (en) * | 2021-12-13 | 2022-05-31 | 哈尔滨工业大学 | Multi-machine cooperative multi-target task allocation method in complex unknown environment |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221865A (en) * | 2010-04-15 | 2011-10-19 | 鸿富锦精密工业（深圳）有限公司 | Infrared control system |
| CN106444769B (en) * | 2016-10-31 | 2019-05-21 | 湖南大学 | A kind of optimum path planning method of indoor mobile robot increment type environmental information sampling |
| CN107272673A (en) * | 2017-05-18 | 2017-10-20 | 中山大学 | SLAM rear ends track optimizing method based on pose chain model |
| WO2019182521A1 (en) * | 2018-03-22 | 2019-09-26 | Infinium Robotics Pte Ltd | Autonomous taking off, positioning and landing of unmanned aerial vehicles (uav) on a mobile platform |
| CN109579848B (en) * | 2018-12-27 | 2020-03-10 | 武汉大学 | Intermediate planning method for robot under global path |
| CN110032211A (en) * | 2019-04-24 | 2019-07-19 | 西南交通大学 | Multi-rotor unmanned aerial vehicle automatic obstacle-avoiding method |
| CN110244715B (en) * | 2019-05-23 | 2022-09-30 | 西安理工大学 | Multi-mobile-robot high-precision cooperative tracking method based on ultra wide band technology |
| CN110455294A (en) * | 2019-08-28 | 2019-11-15 | 北京工业大学 | Implementation method based on the multithreading distribution SLAM system under ROS environment |
| CN111694364A (en) * | 2020-06-30 | 2020-09-22 | 山东交通学院 | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning |
| CN112230665A (en) * | 2020-10-29 | 2021-01-15 | 广西科技大学 | ROS robot global path optimization method based on ACO |
| CN112857390A (en) * | 2021-01-14 | 2021-05-28 | 江苏智派战线智能科技有限公司 | Calculation method applied to intelligent robot moving path |
-
2021
- 2021-01-25 CN CN202110097551.4A patent/CN112925318A/en active Pending
- 2021-08-11 AU AU2021105318A patent/AU2021105318A4/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112925318A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2021105318A4 (en) | Calculation method applied to movement path of intelligent robot | |
| Dianati et al. | An introduction to genetic algorithms and evolution strategies | |
| WO2017215044A1 (en) | Automatic path planning method for mobile robot and mobile robot | |
| Chen et al. | Patrol robot path planning in nuclear power plant using an interval multi-objective particle swarm optimization algorithm | |
| CN105426992B (en) | Mobile robot traveler optimization method | |
| CN113283095A (en) | Evolutionary digital twin watershed construction method | |
| CN107943045A (en) | A kind of method for planning path for mobile robot based on ant colony genetic fusion algorithm | |
| Williams et al. | Data association by loopy belief propagation | |
| CN111426323B (en) | Routing planning method and device for inspection robot | |
| CN112857390A (en) | Calculation method applied to intelligent robot moving path | |
| Pathak et al. | Traveling salesman problem using bee colony with SPV | |
| Wang et al. | A scheme library-based ant colony optimization with 2-opt local search for dynamic traveling salesman problem | |
| Tu et al. | Improved RRT global path planning algorithm based on Bridge Test | |
| Zhao | Optimal path planning for robot based on ant colony algorithm | |
| Liao | Research on PAGV path planning based on artificial immune ant colony fusion algorithm | |
| Liang et al. | Optimization of robot path planning parameters based on genetic algorithm | |
| CN113535828B (en) | Aggregation query method, system, equipment and storage medium of time sequence data | |
| Hu et al. | An experience aggregative reinforcement learning with multi-attribute decision-making for obstacle avoidance of wheeled mobile robot | |
| Huo | Multi-objective vehicle path planning based on DQN | |
| Zhang et al. | Study on straightness error evaluation of spatial lines based on a hybrid ant colony algorithm | |
| CN116358521A (en) | Map construction method applied to dangerous gas leakage scene | |
| Huang et al. | Global path planning for mobile robot based on improved ant colony algorithms | |
| Dong et al. | Robot obstacle avoidance based on an improved ant colony algorithm | |
| Soylu et al. | A hybrid genetic-ant colony algorithm for travelling salesman problem | |
| Han et al. | Design of autonomous navigation algorithm for security inspection robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) |