CN116242383A - Unmanned vehicle path planning method based on reinforced Harris eagle algorithm - Google Patents
Unmanned vehicle path planning method based on reinforced Harris eagle algorithm Download PDFInfo
- Publication number
- CN116242383A CN116242383A CN202310246117.7A CN202310246117A CN116242383A CN 116242383 A CN116242383 A CN 116242383A CN 202310246117 A CN202310246117 A CN 202310246117A CN 116242383 A CN116242383 A CN 116242383A
- Authority
- CN
- China
- Prior art keywords
- harris eagle
- individual
- eagle
- algorithm
- harris
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G01C21/26—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an unmanned vehicle path planning method based on an enhanced Harris eagle algorithm, and belongs to the technical field of unmanned path planning. Constructing a grid map based on environment information, and determining a starting point position and an end point position of a path; setting initial parameters of a Harris eagle algorithm; executing a Harris eagle algorithm exploration stage and a development stage, and updating the individual position of the Harris eagle; performing differential evolution on the updated Harris eagle individual positions, determining the individual positions of the current generation of optimal Harris eagle according to the fitness function values before and after the differential evolution, and performing linear optimization on the paths; judging whether the iteration times reach the maximum iteration times or not, and outputting the current optimal individual position. The nonlinear control strategy is used in the development stage of the algorithm, the differential evolution algorithm is adopted to locally disturb the searched individual optimal position, the searching capacity of the algorithm is enhanced, and the linear path optimization strategy is adopted to enable the obtained optimal path to be smoother.
Description
Technical Field
The invention relates to the technical field of unmanned path planning, in particular to an unmanned vehicle path planning method based on an enhanced Harris eagle algorithm.
Background
With the development of the integration of technologies such as vehicle and the internet of things, artificial intelligence, information communication and the like, unmanned vehicles are widely applied to the fields of intelligent transportation, logistics distribution and the like. Path planning is a key technology of an unmanned vehicle system, and directly affects the running speed, energy consumption, running time and the like of the unmanned vehicle. The unmanned vehicle path planning is to set an initial position and a target end position under a constraint condition and search an effective path which can avoid all obstacles and safely reach a target point. The unmanned vehicle path planning method mainly comprises a dynamic planning method, a branch delimitation method, an A algorithm, an artificial potential field method (APF), a dynamic window method (DWA), an intelligent optimization method and the like.
At present, a plurality of intelligent optimization algorithms are used for path planning of unmanned vehicles, such as genetic algorithm, ant colony algorithm, firework algorithm, sparrow algorithm and the like. For the intelligent optimization algorithm, the problem of easy sinking into local optimum exists, and the convergence speed of the algorithm is slower in a complex environment.
Therefore, how to provide a new intelligent optimization algorithm for unmanned vehicle path planning is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an unmanned vehicle path planning method based on an enhanced Harisk algorithm, and a planned path with short distance and short optimizing time can be obtained by optimizing the enhanced Harisk algorithm.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an unmanned vehicle path planning method based on an enhanced Harris eagle algorithm comprises the following steps:
s1, constructing a grid map based on environmental information, determining a start position and an end position of a path on the grid map, and creating a fitness function;
s2, setting initial parameters of a Harris eagle algorithm, wherein the initial parameters comprise the maximum iteration times;
s3, executing an exploration phase and a development phase according to the escaping energy of the hunting, and updating the position of the Harris eagle individual;
s4, performing differential evolution on the updated Harris eagle individual position, and determining the current optimal Harris eagle individual position according to the fitness function values before and after the differential evolution;
s5, judging whether the iteration times reach the maximum iteration times, if the current iteration times are smaller than the maximum iteration times, repeating the steps S3-S4, otherwise, stopping algorithm iteration, and outputting the current optimal Harris eagle individual position.
Preferably, creating the fitness function specifically includes:
constructing an fitness function according to the distance of the planned path and the smoothness of the planned path:
Fitness＝f length +f smooth
wherein Fitness expresses the function value of the utility function, f length And f smooth The distance of the planned path and the smoothness of the planned path are expressed separately.
Preferably, the specific calculation formula of the distance of the planned path is:
wherein x is i 、y i Respectively, the current node P in the grid map i Is the abscissa and ordinate of (2); x is x i+1 、y i+1 Respectively the next node P in the grid map i+1 And the abscissa and ordinate of (c).
Preferably, the calculation formula of the smoothness of the planned path is:
wherein P is i-1 、P i 、P i+1 The last node, the current node and the next node in the grid map respectively.
Preferably, step S3 specifically includes:
the hunting energy is defined as E,
when the I E I is not less than 1, executing an exploration phase;
when |E| <1, a development stage is executed, and a Hunting mode of the Harish eagle is determined according to a random number r between the escape energy E of the hunting object and [0,1], and the individual position is updated:
when the E is more than or equal to 0.5 and less than or equal to 1 and r is more than or equal to 0.5, hunting is performed in a soft surrounding mode, and the individual position is updated;
when the I E I is less than 0.5 and r is more than or equal to 0.5, hunting is performed in a hard surrounding mode, and the individual position is updated;
when the E is more than or equal to 0.5 and less than 1 and r is less than 0.5, hunting is performed by adopting a nonlinear control strategy progressive rapid diving soft surrounding mode, and the individual position is updated;
and when the I E I is less than 0.5 and r is less than 0.5, hunting is performed by adopting a nonlinear control strategy progressive rapid dive hard surrounding mode, and the individual position is updated.
Preferably, hunting is performed by adopting a nonlinear control strategy progressive rapid dive soft surrounding mode, and the individual position is updated, and the method specifically comprises the following steps:
the nonlinear control parameter w is introduced:
wherein T represents the current iteration number, T max Representing a maximum number of iterations;
optimizing a progressive rapid dive soft surrounding mode according to the nonlinear control parameter w:
Y 1 ＝ωX rabbit (t)-E|JX rabbit (t)-X(t)|
Z 1 ＝ωY 1 +S×LF(D)
wherein Y is 1 And Z 1 Respectively represent intermediate process position vectors, X rabbit (t) represents the current optimal individual, E represents the energy of the hunting escape, J represents the jump distance during the hunting, and X (t) represents the current generation population position vector; d represents the number of dimensions, S is a D-dimensional random vector, LF represents the Levy flight function, and X (t+1) represents the next generation population location vector.
Preferably, hunting is performed by adopting a nonlinear control strategy progressive rapid dive hard surrounding mode, and the individual position is updated, and the method specifically comprises the following steps:
the nonlinear control parameter w is introduced:
wherein T represents the current iteration number, T max Representing a maximum number of iterations;
optimizing a progressive rapid dive hard enclosure mode according to the nonlinear control parameter w:
Y 2 ＝ωX rabbit (t)-E|JX rabbit (t)-X m (t)|
Z 2 ＝ωY 2 +S×LF(D)
wherein Y is 2 And Z 2 Respectively represent intermediate process position vectors, X rabbit (t) represents the current optimal individual, E represents the energy of the hunting escape, J represents the distance of jump during the hunting, X m (t) represents the current generation populationIs a mean position vector of (2); d represents the number of dimensions, S is a D-dimensional random vector, LF represents the Levy flight function, and X (t+1) represents the next generation population location vector.
S41, performing mutation operation on the updated individual positions, wherein the mutation operation is specifically as follows:
X EV (t+1)＝X i (t)+F(X r1 (t)-X r2 (t))
wherein X is EV (t+1) represents the individual position vector after the mutation operation, X i (t) is the optimal individual position vector of the current generation population after Harris eagle optimization, F represents a scaling factor, X r1 (t)、X r2 (t) randomly selecting individual position vectors in the current generation population after Harris eagle optimization;
s42, performing cross operation based on the individual position vectors after the mutation operation, wherein the cross operation is specifically as follows:
wherein X is CR (t+1) represents the Harris eagle individual position vector after the cross operation, X i (t) is an optimal individual position vector in the current generation population after Harris eagle optimization, and CR represents a crossing factor;
s43, selecting:
comparing the crossed Harris eagle individual position vector with the Harris eagle individual position vector before crossing, and determining whether to adopt a new individual according to the size of the fitness function value, wherein the specific formula is as follows:
wherein X is DE (t+1) means the Harris eagle individual position vector after the selection operation, fitness (X) CR (t+1)) means an adaptation function value obtained by substituting the Harris eagle individual position vector after the cross operation into an adaptation function; x is X i (t) is the most optimized Harris eagle in the current generation populationOptimal individual location vector, fitness (X i (t)) means an adaptation function value obtained by substituting the harris eagle individual position vector before the crossover operation into the adaptation function.
Compared with the prior art, the unmanned vehicle path planning method based on the reinforced Harris eagle algorithm has the following beneficial effects:
(1) The invention combines the Harris hawk algorithm with the differential evolution algorithm, enhances the global searching capability of the algorithm, and avoids the problem that the unmanned vehicle path planning algorithm is in local stagnation in the searching process.
(2) The invention uses the linear path strategy for planning the unmanned vehicle path, and can change the folding lines at the corners of the path into smooth straight lines, so that the obtained path is smooth, and the distance of the path is shortened.
(3) According to the invention, by adding the nonlinear control parameters, the nonlinear control strategy is used for the gradual rapid dive hard wrapping and the gradual rapid dive hard wrapping, so that the development stage and the exploration stage of the Harisk algorithm are balanced, the convergence speed of the intelligent algorithm in the unmanned vehicle path planning process is improved, and the overall efficiency of the unmanned vehicle path planning is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the steps of the method provided by the present invention;
FIG. 2 is a flowchart of a detailed method provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a linear path strategy according to an embodiment of the present invention;
fig. 4 is an iteration convergence curve of the enhanced harris eagle optimization algorithm, the harris eagle optimization algorithm and the ant colony optimization algorithm provided by the embodiment of the invention;
fig. 5 is a schematic diagram of a path planning result of an enhanced harris eagle optimization algorithm, a harris eagle optimization algorithm and an ant colony optimization algorithm provided by the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses an unmanned vehicle path planning method based on an enhanced Harris eagle algorithm, which comprises the following steps:
step 1: according to the environment information, carrying out map modeling on the environment by utilizing a grid map, determining a starting point position and an end point target position, and constructing an fitness function by utilizing a path distance and path smoothness;
in one embodiment, the start point of the path is positioned at the lower left of the grid, the end point is positioned at the upper right of the grid, and one node coordinate of the path is P i (x i ,y i ) The number of nodes of the path is m, and the length of the path can be expressed as:
wherein x is i 、y i Respectively the current nodes P i Is the abscissa and ordinate of (2); x is x i+1 、y i+1 Respectively the next node P i+1 And the abscissa and ordinate of (c).
In this embodiment, the smoothness of the path may be expressed as:
wherein P is i-1 、P i 、P i+1 The node is a last node, a current node and a next node.
The fitness function is expressed as:
Fitness＝f length +f smooth (3)
step 2: initializing algorithm parameters, setting the maximum iteration times of the algorithm and the number of Harris eagle populations, randomly generating Harris eagle population individuals in a solution space, calculating the fitness function value of the Harris eagle population individuals, and selecting the Harris eagle individual position with the minimum fitness function value as an optimal position;
step 3: updating parameters E and J, and executing step 4 when the escape energy factor E is more than or equal to 1; executing the step 5 when E is less than 1; the escape distance J is specifically constituted by:
J＝2(1-r 5 )
where r5 is a random number randomly generated between 0 and 1, and parameters E and J are updated with each iteration.
The Harris eagle algorithm is in an exploration stage, the Harris eagles inhabit at some places randomly, the individual positions of the Harris eagles are updated through sharp eye tracking and hunting, and the fitness function value of the individual positions of the Harris eagles is calculated;
the Harris eagle algorithm is in a development stage, randomly generates a parameter r between [0,1], and executes corresponding steps according to the magnitudes of E and r values.
Step 3.1 is executed when specific I E I is more than or equal to 0.5 and r is more than or equal to 0.5;
executing the step 3.2 when the I E I is less than 0.5 and r is more than or equal to 0.5;
executing the step 3.3 when the E is more than or equal to 0.5 and r is less than 0.5;
executing the step 3.4 when E is less than 0.5 and r is less than 0.5;
step 3.1: the hunting object has enough energy to try to escape from the surrounding ring through random jump, but finally cannot escape, the harris eagle uses a soft surrounding mode to carry out hunting, the individual position of the harris eagle is updated, the fitness function value of the harris eagle individual is calculated, and the position is updated by applying a linear path strategy;
step 3.2: the hunting method comprises the steps that a hunting object does not have enough energy to get rid of, and has no chance of escaping, the harris eagle carries out hunting in a hard surrounding mode, the individual position of the harris eagle is calculated, the fitness function value of the harris eagle individual is calculated, and the position is updated by applying a linear path strategy;
step 3.3: the prey has the opportunity to escape from the enclosure and the escape energy is enough, so that the harris eagle needs to form a more intelligent soft enclosure before attack, the individual position of the harris eagle is updated by using a nonlinear control strategy to gradually and rapidly dive the soft enclosure, the fitness function value of the harris eagle individual is calculated, and the position is updated by applying a linear path strategy;
step 3.4: the hunting articles have the opportunity to escape, but the escape energy is insufficient, so the harris eagle forms a hard surrounding ring before the attack, the average distance between the hard surrounding ring and the hunting articles is reduced, the hard surrounding ring which is gradually and rapidly dived by using a nonlinear control strategy is used for updating the position of the harris eagle individual, the fitness function value of the harris eagle individual is calculated, and the position is updated by adopting a linear path strategy;
step 4: carrying out differential evolution on the individual position after the updating through the Harris eagle search, judging whether to update the optimal position of the Harris eagle according to the fitness function value before and after the differential evolution, if the fitness function value of the differential evolution is smaller than the fitness function value before updating, reserving the Harris eagle individual position after the differential evolution, otherwise, discarding the Harris eagle individual position after the differential evolution;
step 5: and (3) judging whether the current iteration number reaches the maximum iteration number, returning to the step (3) to continue searching if the current iteration number is smaller than the maximum iteration number, otherwise, stopping algorithm iteration, and outputting the individual position of the optimal harris eagle.
After the Haris eagle individual position is updated in the technical scheme, a linear path strategy is applied by calculating the fitness function of the Haris eagle individual position, three points are sequentially selected from a starting point on the path, whether an obstacle exists between the starting point and the updated position is judged, and if the obstacle does not exist, the position of an intermediate node is deleted so as to generate a smoother path, so that the linearization of the path is realized.
The invention takes the length of the path and the smoothness of the path as a fitness function, the smoothness of the path mainly refers to the sum of included angles of each section of path so as to realize a shorter path and a smooth path, and in addition, a linear path strategy is adopted to better realize the smoothness of the path, thereby playing a good role in the safe running of the unmanned vehicle.
The steps in the present invention will be described in detail
Harris eagle exploration stage
When |E| is not less than 1, the exploration phase is executed. The harris eagles inhabit at random in some places, hunting is performed by sharp eye tracking and hunting, and with two opportunities equal strategy. Represented as
Wherein X (t) is the position of the t-th Harris eagle, X (t+1) is the position of the t+1-th Harris eagle, X rand (t) randomly selecting the position of Harris eagle in the t generation, X rabbit (t) is the position of the prey, xm (t) is the average position of the current Harris eagle population, q, r 1 、r 2 、r 3 、r 4 Are all [0,1]]UB and LB are the upper and lower bounds of the solution space, respectively, and N is the total number of populations.
Harris eagle exploration to development stage conversion
Escaping energy factor E to control the conversion of the Harisk algorithm exploration and development stage is expressed as
E＝2E 0 (1-t/T max )
Wherein E is 0 For initial escape energy, is [ -1,1]Random numbers of (a); t is the current iteration number, tmax is the maximum iteration number
Harris eagle development stage
1) Soft enclosure
When the E is more than or equal to 0.5 and less than or equal to 1 and r is more than or equal to 0.5, hunting is performed by adopting a soft surrounding mode. The harris eagle individual position is updated as follows:
X(t+1)＝ΔX(t)-E|JX rabbit (t)-X(t)|
ΔX(t)＝X rabbit (t)-X(t)
J＝2(1-r 5 )
wherein DeltaX (t) is the difference between the optimal individual position of the harris eagle and the current individual position of the harris eagle, r 5 Is [0,1]And the random numbers are uniformly distributed, and J is the jumping distance in the escape process of the rabbits.
2) Hard enclosure
When the I E I is less than 0.5 and r is more than or equal to 0.5, hunting is performed in a hard surrounding mode, and the position of the Harris eagle individual is updated;
X(t+1)＝X rabbit (t)-E|ΔX(t)|
3) Non-linear controlled progressive rapid dive soft wrap
When 0.5 is less than or equal to |E| <1 and r is less than 0.5, the prey has enough escape energy and has the opportunity to escape. The harris eagle adopts a nonlinear control strategy progressive rapid diving soft surrounding mode to carry out hunting, and the individual position of the harris eagle is updated as follows:
Y 1 ＝ωX rabbit (t)-E|JX rabbit (t)-X(t)|
Z 1 ＝ωY 1 +S×LF(D)
wherein ω is a nonlinear control parameter, t represents the current iteration number, and Tmax represents the maximum iteration number; y is Y 1 ,Z 1 The method is characterized in that the method comprises the steps of respectively obtaining an intermediate process position vector, wherein D is the dimension of a solution problem, S is a D-dimensional random vector, LF is a Levy flight function, and the method is expressed as follows:
where μ, ν are random numbers obeying a positive too distribution, σ represents the standard deviation, Γ (β) is the standard gamma function.
The individual position update strategy of harris eagle at this stage is finally as follows:
nonlinear control progressive rapid dive hard wrap
When |E| < 0.5 and r < 0.5, the prey has the opportunity to escape, but the escape energy is insufficient, so that the harris eagle forms a hard surrounding ring before the attack, the average distance between the harris eagle and the prey is reduced, and the individual position of the harris eagle is updated as follows:
Y 2 ＝ωX rabbit (t)-E|JX rabbit (t)-X m (t)|
Z 2 ＝ωY 2 +S×LF(D)
wherein Y is 2 ,Z 2 Intermediate process position vectors, respectively.
Differential evolution
The differential evolution is a simulated biological evolution algorithm, which comprises the following steps of mutation, crossover and selection which are sequentially carried out: after each iteration is finished, the current optimal position vector is mutated and crossed to obtain a new position vector, the fitness function value is calculated, and if the new fitness function value is smaller than the fitness function value of the optimal position vector, the current optimal position is replaced.
The mutation operation is to select the optimal Harris eagle individual position in the current population to perform mutation, so as to enlarge the search range, and the specific formula is as follows:
X EV (t+1)＝X i (t)+F(X r1 (t)-X r2 (t))
wherein X is EV (t+1) represents the position of the mutated Harris eagle individual, X i (t) is the optimal individual position in the current generation population after being optimized by the Harris eagle algorithm, F represents a scaling factor and X r1 (t)、X r2 And (t) randomly selecting the individual position of the hawk after the hawk algorithm optimization of the current generation.
The crossover operation is to determine whether a new individual is generated by generating a random number and comparing the random number with the comparison crossover factor, and is specifically represented by the following formula:
wherein X is CR (t+1) represents the individual position of Harris eagle after crossing, X i (t) the optimal individual position in the current generation population after Harris eagle optimization, wherein CR represents a crossing factor;
the selection operation is to compare the crossed Harris eagle individual position with the Harris eagle individual position before crossing, and determine whether to adopt crossed updated individual position according to the fitness function value, wherein the specific formula is as follows:
X DE (t+1) means the individual position of Harris eagle after the selection operation, fitness (X) CR (t+1)) means that the crossed Harris eagle individual position vector is substituted into the fitness function, and the fitness function value is calculated; x is X i (t) is the optimal individual position in the current generation population after Harris eagle optimization, fitness (X) i (t)) means that the individual positions of harris eagles before crossing are substituted into the fitness function, the fitness function value is calculated, and the two calculated fitness function values are compared, so that the corresponding individual position with the smallest value is selected and retained.
(4) Linear path strategy
The linear path strategy means that path planning is implemented as linearly as possible, which can produce a high quality path, reducing computation run time. The process of the linear path strategy has two phases: obstacle detection and path connection. This process is shown in fig. 3 and is specifically described below.
Step 1: sequentially generating three points from the starting point of the path;
step 2: calculating a coordinate range between the first and third points and determining whether an obstacle is located within the range;
step 3: if no obstacle is found within this range, the second point is removed from the path. Otherwise, the process terminates and linearization of the path continues.
In a particular embodiment
The present invention uses a grid map to construct a simulation environment. The grid deck represents a two-dimensional environment on which the moving area is divided into grid cells with binary information, black grids representing obstacles and white grids representing unmanned vehicles feasible areas. In order to verify the effectiveness of the algorithm, the MATLAB programming solution example is used and analyzed and verified according to the ant colony algorithm, the Harris eagle algorithm and the reinforced Harris eagle algorithm respectively, and the simulation environment is as follows: and adopting MATLAB2018 programming language, and configuring a 16G memory and a CPU 3GHz main frequency computer under the Wi window 10 operating environment.
In this embodiment, the initial parameters are set as follows: the population number is 20, the maximum iteration number is 100, the logarithmic spiral shape constant b is 1, the scaling factor F is 0.7, and the crossover factor CR is 0.8.
Referring to fig. 4, iterative convergence curves of the harris eagle optimization algorithm, the harris eagle optimization algorithm and the ant colony optimization algorithm are enhanced, wherein the abscissa in the iterative convergence curves is the iterative times, and the ordinate is the path optimal distance of path planning. From the graph, the convergence speed of the enhanced hawk optimization algorithm is superior to that of the hawk optimization algorithm, and the convergence accuracy is superior to that of the hawk optimization algorithm and the ant colony algorithm.
Referring to fig. 5, three optimization algorithms compare the path planning results of the unmanned vehicle, and each algorithm is independently executed 20 times to select the optimal result because the intelligent optimization algorithm has certain randomness. Through the search iteration of the algorithm, the improved harris eagle optimization algorithm, the harris eagle optimization algorithm and the ant colony optimization algorithm obtain optimal path lengths of 29.41, 31.64 and 32.38 respectively, and the running time of the algorithm is 0.96 seconds, 0.43 seconds and 3.17 seconds respectively. Compared with the ant colony optimization algorithm, the path length of the reinforced Harris hawk optimization algorithm and the algorithm execution time have better performance; compared with the Harris hawk optimization algorithm, the improved Harris hawk optimization algorithm realizes shorter path planning, but the execution time of the algorithm is increased, which mainly means that the Harris hawk optimization algorithm falls into local optimum in the path planning process, the execution time of the algorithm is small, in addition, the performance of the improved Harris hawk optimization algorithm is optimized by adopting various strategies, and the execution time of the algorithm is increased. Therefore, the improved Harris eagle optimization algorithm has better performance in unmanned vehicle path planning.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An unmanned vehicle path planning method based on an enhanced Harris eagle algorithm is characterized by comprising the following steps:
s1, constructing a grid map based on environmental information, determining a start position and an end position of a path on the grid map, and creating a fitness function;
s2, setting initial parameters of a Harris eagle algorithm, wherein the initial parameters comprise the maximum iteration times;
s3, executing an exploration phase and a development phase according to the escaping energy of the hunting, and updating the position of the Harris eagle individual;
s4, performing differential evolution on the updated Harris eagle individual position, and determining the current optimal Harris eagle individual position according to the fitness function values before and after the differential evolution;
s5, judging whether the iteration times reach the maximum iteration times, if the current iteration times are smaller than the maximum iteration times, repeating the steps S3-S4, otherwise, stopping algorithm iteration, and outputting the current optimal Harris eagle individual position.
2. The unmanned vehicle path planning method based on the enhanced haustilago algorithm of claim 1, wherein creating the fitness function specifically comprises:
constructing an fitness function according to the distance of the planned path and the smoothness of the planned path:
Fitness＝f length +f smooth
wherein Fitness expresses the function value of the utility function, f length And f smooth The distance of the planned path and the smoothness of the planned path are expressed separately.
3. The unmanned vehicle path planning method based on the enhanced haustilago algorithm according to claim 2, wherein the distance f of the planned path length The specific calculation formula is as follows:
wherein x is i 、y i Respectively, the current node P in the grid map i Is the abscissa and ordinate of (2); x is x i+1 、y i+1 Respectively the next node P in the grid map i+1 And the abscissa and ordinate of (c).
4. The unmanned vehicle path planning method based on the enhanced haustilago algorithm according to claim 2, wherein the smoothness f of the planned path smooth The calculation formula of (2) is as follows:
wherein P is i-1 、P i 、P i+1 The last node, the current node and the next node in the grid map respectively.
5. The unmanned vehicle path planning method according to claim 1, wherein the step S3 specifically comprises:
the hunting energy is defined as E,
when the I E I is not less than 1, executing an exploration phase;
when |E| <1, a development stage is executed, a Hunting mode of the Harist eagle is determined according to a random number r between the escape energy E of the prey and [0,1], and the individual position of the Harist eagle is updated:
when E is less than or equal to 0.5 and less than or equal to 1 and r is more than or equal to 0.5, hunting is performed in a soft surrounding mode, and the Harris eagle individual position is updated;
when the I E I is less than 0.5 and r is more than or equal to 0.5, hunting is performed in a hard surrounding mode, and the individual position of the harris eagle is updated;
when E is more than or equal to 0.5 and less than or equal to 1 and r is less than 0.5, hunting is performed by adopting a nonlinear control strategy progressive rapid diving soft surrounding mode, and the individual position of the Harris eagle is updated;
and when the I E I is less than 0.5 and r is less than 0.5, hunting is performed by adopting a nonlinear control strategy progressive rapid dive hard surrounding mode, and the Haris eagle individual position is updated.
6. The unmanned vehicle path planning method based on the enhanced hawk algorithm according to claim 5, wherein hunting is performed by adopting a nonlinear control strategy progressive rapid dive soft surrounding mode, and the hawk individual position is updated, and the method specifically comprises:
the nonlinear control parameter w is introduced:
wherein T represents the current iteration number, T max Representing a maximum number of iterations;
optimizing a progressive rapid dive soft surrounding mode according to the nonlinear control parameter w:
Y 1 ＝ωX rabbit (t)-E|JX rabbit (t)-X(t)|
Z 1 ＝ωY 1 +S×LF(D)
wherein Y is 1 And Z 1 Respectively represent intermediate process position vectors, X rabbit (t) represents the current optimal Harris eagle individual, E represents the escaping energy of the prey, J represents the jumping distance in the escaping process of the prey, X (t) represents the current generation of population position vector, D represents the number of dimensions, S is a D-dimensional random vector, LF represents the Levy flight function, and X (t+1) represents the next generation of population position vector.
7. The unmanned vehicle path planning method based on the enhanced hawk algorithm according to claim 5, wherein hunting is performed in a nonlinear control strategy progressive rapid dive hard surrounding manner, and the hawk individual position is updated, specifically comprising:
the nonlinear control parameter w is introduced:
wherein T represents the current iteration number, T max Representing a maximum number of iterations;
optimizing a progressive rapid dive hard enclosure mode according to the nonlinear control parameter w:
Y 2 ＝ωX rabbit (t)-E|JX rabbit (t)-X m (t)|
Z 2 ＝ωY 2 +S×LF(D)
wherein Y is 2 And Z 2 Respectively represent intermediate process position vectors, X rabbit (t) represents the current optimal Harris eagle individual, E represents the hunting energy, J represents the jump distance during hunting, X m (t) represents an average position vector of the current generation population; d represents the number of dimensions, S is a D-dimensional random vector, LF represents the Levy flight function, and X (t+1) represents the next generation population location vector.
8. The unmanned vehicle path planning method according to claim 1, wherein the step S4 specifically comprises:
s41, performing mutation operation on the updated individual positions, wherein the mutation operation is specifically as follows:
X EV (t+1)＝X i (t)+F(X r1 (t)-X r2 (t))
wherein X is EV (t+1) represents the individual position vector after the mutation operation, X i (t) is the optimal individual position vector of the current generation population after Harris eagle optimization, F represents a scaling factor, X r1 (t)、X r2 (t) randomly selecting individual position vectors in the current generation population after Harris eagle optimization;
s42, performing cross operation based on the individual position vectors after the mutation operation, wherein the cross operation is specifically as follows:
wherein X is CR (t+1) represents the Harris eagle individual position vector after the cross operation, X i (t) is an optimal individual position vector in the current generation population after Harris eagle optimization, and CR represents a crossing factor;
s43, selecting:
comparing the crossed Harris eagle individual position vector with the Harris eagle individual position vector before crossing, and determining whether to adopt a new individual according to the size of the fitness function value, wherein the specific formula is as follows:
wherein X is DE (t+1) means the Harris eagle individual position vector after the selection operation, fitness (X) CR (t+1)) means an adaptation function value obtained by substituting the Harris eagle individual position vector after the cross operation into an adaptation function; x is X i (t) is the optimal individual position vector of the current generation population after Harris eagle optimization, fitness (X) i (t)) means an adaptation function value obtained by substituting the harris eagle individual position vector before the crossover operation into the adaptation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310246117.7A CN116242383B (en) | 2023-03-15 | 2023-03-15 | Unmanned vehicle path planning method based on reinforced Harris eagle algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310246117.7A CN116242383B (en) | 2023-03-15 | 2023-03-15 | Unmanned vehicle path planning method based on reinforced Harris eagle algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116242383A true CN116242383A (en) | 2023-06-09 |
| CN116242383B CN116242383B (en) | 2023-09-15 |
Family
ID=86624080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310246117.7A Active CN116242383B (en) | 2023-03-15 | 2023-03-15 | Unmanned vehicle path planning method based on reinforced Harris eagle algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116242383B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116519003A (en) * | 2023-06-28 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN116822884A (en) * | 2023-06-30 | 2023-09-29 | 上海海事大学 | Multi-crown block cooperative scheduling method in flexible manufacturing system |
| CN117021977A (en) * | 2023-10-10 | 2023-11-10 | 中国人民解放军陆军装甲兵学院 | Method for generating driving force integrated control strategy of multi-wheel independent electric drive vehicle |
| CN117349623A (en) * | 2023-10-25 | 2024-01-05 | 广西财经学院 | System-level fault diagnosis method based on double-population Harris eagle algorithm |
| CN117419739A (en) * | 2023-11-06 | 2024-01-19 | 大唐贵州发耳发电有限公司 | Path planning optimization method for coal conveying system inspection robot |
| CN116822884B (en) * | 2023-06-30 | 2024-05-31 | 上海海事大学 | Multi-crown block cooperative scheduling method in flexible manufacturing system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109540163A (en) * | 2018-11-20 | 2019-03-29 | 太原科技大学 | A kind of obstacle-avoiding route planning algorithm combined based on differential evolution and fuzzy control |
| CN112577507A (en) * | 2020-11-04 | 2021-03-30 | 杭州电子科技大学 | Electric vehicle path planning method based on Harris eagle optimization algorithm |
| CN113485451A (en) * | 2021-08-19 | 2021-10-08 | 金陵科技学院 | Robot multi-target path planning based on improved mayflies optimization algorithm |
| CN113791613A (en) * | 2021-08-19 | 2021-12-14 | 金陵科技学院 | Improved slime optimization algorithm and robot multi-target path planning based on algorithm |
| WO2021248797A1 (en) * | 2020-06-08 | 2021-12-16 | 苏州艾吉威机器人有限公司 | B-spline curve-based path planning method and system, and motion control method and system |
| CN114117876A (en) * | 2021-11-24 | 2022-03-01 | 大连大学 | Feature selection method based on improved Harris eagle algorithm |
| CN114995384A (en) * | 2022-04-27 | 2022-09-02 | 广东碧桂园职业学院 | Improved HHO algorithm AGV path planning fusing neural network |
| US20220379893A1 (en) * | 2020-05-21 | 2022-12-01 | Southeast University | Intelligent vehicle platoon lane change performance evaluation method |
| CN115510978A (en) * | 2022-09-28 | 2022-12-23 | 华能国际电力股份有限公司 | Industrial control system intrusion detection method and device and electronic equipment |
| CN115519542A (en) * | 2022-09-23 | 2022-12-27 | 五邑大学 | Multi-machine cooperation welding track planning method and device based on Harris eagle algorithm |
-
2023
- 2023-03-15 CN CN202310246117.7A patent/CN116242383B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109540163A (en) * | 2018-11-20 | 2019-03-29 | 太原科技大学 | A kind of obstacle-avoiding route planning algorithm combined based on differential evolution and fuzzy control |
| US20220379893A1 (en) * | 2020-05-21 | 2022-12-01 | Southeast University | Intelligent vehicle platoon lane change performance evaluation method |
| WO2021248797A1 (en) * | 2020-06-08 | 2021-12-16 | 苏州艾吉威机器人有限公司 | B-spline curve-based path planning method and system, and motion control method and system |
| CN112577507A (en) * | 2020-11-04 | 2021-03-30 | 杭州电子科技大学 | Electric vehicle path planning method based on Harris eagle optimization algorithm |
| CN113485451A (en) * | 2021-08-19 | 2021-10-08 | 金陵科技学院 | Robot multi-target path planning based on improved mayflies optimization algorithm |
| CN113791613A (en) * | 2021-08-19 | 2021-12-14 | 金陵科技学院 | Improved slime optimization algorithm and robot multi-target path planning based on algorithm |
| CN114117876A (en) * | 2021-11-24 | 2022-03-01 | 大连大学 | Feature selection method based on improved Harris eagle algorithm |
| CN114995384A (en) * | 2022-04-27 | 2022-09-02 | 广东碧桂园职业学院 | Improved HHO algorithm AGV path planning fusing neural network |
| CN115519542A (en) * | 2022-09-23 | 2022-12-27 | 五邑大学 | Multi-machine cooperation welding track planning method and device based on Harris eagle algorithm |
| CN115510978A (en) * | 2022-09-28 | 2022-12-23 | 华能国际电力股份有限公司 | Industrial control system intrusion detection method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 林笑笑: "基于改进哈里斯鹰算法的物流机器人任务分配和路径规划研究", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 2, pages 140 - 595 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116519003A (en) * | 2023-06-28 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN116519003B (en) * | 2023-06-28 | 2023-09-01 | 广汽埃安新能源汽车股份有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN116822884A (en) * | 2023-06-30 | 2023-09-29 | 上海海事大学 | Multi-crown block cooperative scheduling method in flexible manufacturing system |
| CN116822884B (en) * | 2023-06-30 | 2024-05-31 | 上海海事大学 | Multi-crown block cooperative scheduling method in flexible manufacturing system |
| CN117021977A (en) * | 2023-10-10 | 2023-11-10 | 中国人民解放军陆军装甲兵学院 | Method for generating driving force integrated control strategy of multi-wheel independent electric drive vehicle |
| CN117021977B (en) * | 2023-10-10 | 2024-01-09 | 中国人民解放军陆军装甲兵学院 | Method for generating driving force integrated control strategy of multi-wheel independent electric drive vehicle |
| CN117349623A (en) * | 2023-10-25 | 2024-01-05 | 广西财经学院 | System-level fault diagnosis method based on double-population Harris eagle algorithm |
| CN117349623B (en) * | 2023-10-25 | 2024-04-19 | 广西财经学院 | System-level fault diagnosis method based on double-population Harris eagle algorithm |
| CN117419739A (en) * | 2023-11-06 | 2024-01-19 | 大唐贵州发耳发电有限公司 | Path planning optimization method for coal conveying system inspection robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116242383B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116242383B (en) | Unmanned vehicle path planning method based on reinforced Harris eagle algorithm | |
| Abdel-Basset et al. | A novel whale optimization algorithm integrated with Nelder–Mead simplex for multi-objective optimization problems | |
| Haaswijk et al. | Deep learning for logic optimization algorithms | |
| CN102819264B (en) | Path planning Q-learning initial method of mobile robot | |
| CN110347151B (en) | Robot path planning method fused with Bezier optimization genetic algorithm | |
| CN109945881A (en) | A kind of method for planning path for mobile robot of ant group algorithm | |
| CN109597425B (en) | Unmanned aerial vehicle navigation and obstacle avoidance method based on reinforcement learning | |
| CN111159489B (en) | Searching method | |
| Liu et al. | An improved heuristic mechanism ant colony optimization algorithm for solving path planning | |
| CN111709511A (en) | Harris eagle optimization algorithm based on random unscented Sigma point variation | |
| CN112577507A (en) | Electric vehicle path planning method based on Harris eagle optimization algorithm | |
| Ajibade et al. | A hybrid chaotic particle swarm optimization with differential evolution for feature selection | |
| CN114611801A (en) | Traveler problem solving method based on improved whale optimization algorithm | |
| CN111370074B (en) | Method and device for generating molecular sequence and computing equipment | |
| CN116859903A (en) | Robot smooth path planning method based on improved Harris eagle optimization algorithm | |
| CN114995460A (en) | Robot path planning method based on self-adaptive improved ant colony algorithm | |
| CN114742231A (en) | Multi-objective reinforcement learning method and device based on pareto optimization | |
| Gao et al. | An adaptive framework to select the coordinate systems for evolutionary algorithms | |
| Chen et al. | A Spark-based Ant Lion algorithm for parameters optimization of random forest in credit classification | |
| CN116933948A (en) | Prediction method and system based on improved seagull algorithm and back propagation neural network | |
| CN116518977A (en) | Unmanned aerial vehicle path planning method, system and equipment | |
| Cui et al. | Multi-strategy adaptable ant colony optimization algorithm and its application in robot path planning | |
| CN115655279A (en) | Marine unmanned rescue airship path planning method based on improved whale algorithm | |
| CN115933669A (en) | Mobile robot path planning method based on improved butterfly optimization algorithm | |
| Jiang et al. | A parallel based evolutionary algorithm with primary-auxiliary knowledge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |