CN111694364A - Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning - Google Patents
Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning Download PDFInfo
- Publication number
- CN111694364A CN111694364A CN202010619230.1A CN202010619230A CN111694364A CN 111694364 A CN111694364 A CN 111694364A CN 202010619230 A CN202010619230 A CN 202010619230A CN 111694364 A CN111694364 A CN 111694364A
- Authority
- CN
- China
- Prior art keywords
- path
- intelligent vehicle
- node
- ant colony
- path planning
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000003016 pheromone Substances 0.000 claims description 36
- 241000257303 Hymenoptera Species 0.000 claims description 24
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000009499 grossing Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000009125 negative feedback regulation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, 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
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
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 invention discloses a hybrid algorithm based on an improved ant colony algorithm and a dynamic window method, which is applied to intelligent vehicle path planning. According to the algorithm provided by the invention, on the premise of a known obstacle, after an initial point and a target point are specified by using a Matlab simulation platform and an ROS-based intelligent vehicle platform, the global path planning of the intelligent vehicle is completed, meanwhile, an unknown obstacle is arranged on a grid map, a local moving target point is planned, and the local target point is tracked in real time, so that the local real-time obstacle avoidance of the intelligent vehicle is completed. The intelligent vehicle path planning method based on the improved ant colony algorithm and the dynamic window method provided by the invention has the advantages that the turning angle of the path is smoothed, the path planning efficiency is improved, the real-time obstacle avoidance of the intelligent vehicle is realized, and the robustness and the accuracy are good.
Description
Technical Field
The invention relates to a hybrid algorithm based on an improved ant colony algorithm and a dynamic window method and applied to intelligent vehicle path planning, and belongs to the field of intelligent vehicle path planning.
Background
With the rapid development of computer science technology, the research of intelligent vehicles has been one of the research hotspots of intelligent vehicle traffic systems, wherein path planning is an important technology in the intelligent vehicle research field and aims to find a collision-free path from a starting point to a target point in an obstacle environment.
At present, scholars at home and abroad have developed several algorithms for solving the path planning problem, such as a global path planning algorithm: finding an optimal path from a starting point to a target point from an environment by a Voronoi diagram, a Dijkstra algorithm, a genetic algorithm, an ant colony algorithm and the like, wherein the ant colony algorithm is an intelligent optimization algorithm, and has good robustness and global optimization performance; the local path planning method comprises the following steps: the method comprises the steps of obtaining real-time environment information by utilizing an artificial potential field method, a fuzzy logic method, a dynamic window method and the like through utilizing a vehicle-mounted sensor, and planning a collision-free local path, wherein the dynamic window method can plan the path in real time according to the environment information, has good obstacle avoidance capability, and can well meet the autonomous navigation capability of the intelligent vehicle. Therefore, the improved ant colony algorithm can solve the problems of low convergence speed and local optimum when global path planning is carried out, the dynamic window method can improve the obstacle avoidance capability of the intelligent vehicle on unknown obstacles by combining global path information, smooth the turning angle of the path, improve the path planning efficiency and realize the automatic feedback control of the intelligent vehicle.
Therefore, those skilled in the art are dedicated to developing an improved ant colony algorithm and dynamic window method combined hybrid algorithm applied to intelligent vehicle path planning, planning a local obstacle avoidance optimal path on the basis of combining a global optimal path, and providing flexibility and accuracy capable of achieving local obstacle avoidance for path planning of an intelligent vehicle.
Disclosure of Invention
Aiming at the characteristics of low adaptive environment performance and high control difficulty coefficient of the traditional control detection device, the invention greatly enhances the environment adaptive capacity of the robot through the design of the triangular crawler belt and the design of four-motor drive, and enhances the accuracy of control through the negative feedback regulation signal output design.
In view of the above defects in the prior art, the technical problem to be solved by the invention is to solve the problems that the intelligent vehicle has many times of convergence iteration, is easy to fall into local optimum, cannot realize obstacle avoidance on local obstacles in real time and the like in path planning, improve the robustness and accuracy of an algorithm, and realize automatic feedback control of the intelligent vehicle.
In order to achieve the above object, the present invention provides a hybrid algorithm based on an improved ant colony algorithm and a dynamic window method for intelligent vehicle path planning, which is characterized by comprising the following steps:
the method comprises the following steps: acquiring environmental information by using a vehicle-mounted sensor, realizing self positioning of a vehicle, and constructing a grid map;
step two: the global path planning of the intelligent vehicle is completed by using an improved ant colony algorithm; firstly, setting initialization parameters, the number M of ants, the iteration times K, pheromone heuristic factors a and expectation heuristic factors w, and placing M ants at initial positions; secondly, according to ant state transition probability
Selecting a path, putting nodes which are walked by the ants into a tabu table, and judging the next path selection of the ants:
wherein all (i) represents a set of transfer nodes that ants k except the tabu table allow selection next at node i; t isig(t) represents the pheromone content of ants from node i to node g at time t, Nig(t) represents the heuristic function of ants from node i to node g at time t; secondly, introducing a heuristic function N according to the square of the sum of the distance from the current node to the next node and the distance from the current node to the target nodeig(t), the searching speed of the ant colony is accelerated, and the selection guiding effect of the ant colony on the next node is increased:
Νig(t)＝1/(σ·lig+(1-σ)·liE)2
where σ represents the weighted proportion between the distances of two nodes, and σ ∈ [0,1]Determined by the real-time environment,/igRepresents the distance, l, between the current node i and the next node giERepresenting the distance between the current node i and the target point E; then, an improvement is made in the pheromone update: determining the maximum value T of the concentration of pheromones between two pointsmaxAnd a minimum value Tmin：
Wherein DsFor the optimal path length after a certain iteration, n is the number of cycles of each time, after an ant finishes each cycle, pheromone information on the path is changed, in order to obtain the optimal path, the pheromone on the whole path needs to be adjusted, and meanwhile, in order to prevent an ant colony from carrying out path planning by using the pheromone on the local optimal path, the pheromone concentration increment of the ant between two points also needs to be updated, so that each ant can find a feasible path:
Τig(t+1)＝(1-λ)·Τig(t)+△Τig(t)
wherein λDenotes the pheromone volatility coefficient, λ ∈ [0,1]；ΔTig(t) represents pheromone increment of ants between the node i and the node g at the moment t;
the pheromone increment of the b-th ant between the node i and the node g at the moment t is represented; r issThe optimal solution found so far;
step three: and smoothing the global path by adopting a cubic B-spline curve, wherein the mathematical expression mode of the cubic B-spline curve is as follows:
wherein P isi(i-0, 1, 2, …, n) is the coordinates of (n +1) control points of the curve, Fi,k(t) is a k-th order B-spline basis function:
step four: acquiring unknown obstacle information aiming at a vehicle-mounted sensor, and obtaining a maximum speed V according to initial parametersmAnd the linear acceleration v and the angular acceleration omega make a path evaluation by combining the global path planning information by using a dynamic window method, and select a local optimal path:
where goal (v, ω) represents the angle between the vector pointing to the target and the vector connecting the starting point and the current position, d (v, ω) represents the perpendicular distance of the static obstacle from the track currently pointing to the target, d (v, ω)m,ωm) Mu, β, phi and lambda are expressed as weighting coefficients, and meanwhile, a pre-aiming tracking method is used for tracking a local moving target point to obtain an optimal local path planning path, and the planned path trajectory is as follows:
(x-xo)2+(y-yo)2＝R2
wherein the coordinates of the intelligent vehicle are (x, y), the vehicle-mounted sensor measures the coordinates (x) of the circle center of the path track determined by the outgoing mobile target pointo，yo)；
Step five: and judging whether the local moving target point is the final target point, if so, ending, otherwise, returning to the step one until the final target point is reached.
Further, the parameter values in the second step are respectively as follows: the ant number M is 50, the iteration number K is 100, the pheromone heuristic factor a is 1, and the expectation heuristic factor w is 7.
Further, the initial position of the ant in the second step is positioned at the lower right of the grid map.
Furthermore, the cubic B spline curve in the third step is used for smoothing the peak at the turning position of the global path, so that the intelligent vehicle can smoothly and safely pass through the turning position, and the geometric constraint characteristic of the intelligent vehicle is met.
Further, the parameter values in the fourth step are respectively: maximum velocity Vm1m/s and 0.2m/s2Angular acceleration ω 0.9rad/s2The smart car heading weight coefficient μ is 0.02, the obstacle weight coefficient β is 0.10, and the speed weight coefficient Φ is 0.1.
Furthermore, the dynamic window method in the fourth step can complete speed limitation, acceleration limitation and safety distance limitation on obstacles of the intelligent vehicle, and ensure that the intelligent vehicle can avoid the obstacles in real time in the planning process.
The invention also provides a hybrid algorithm based on the improved ant colony algorithm and the dynamic window method, which is applied to the intelligent vehicle path planning and consists of the hybrid algorithm based on the improved ant colony algorithm and the dynamic window method for the intelligent vehicle path planning.
The invention has the beneficial effects that:
(1) aiming at the problems that the traditional ant colony algorithm is long in search time and easy to fall into local stagnation, the heuristic function and the pheromone updating strategy are improved, the turning angle of the path is smoothed by utilizing a cubic B spline curve, the convergence speed is accelerated, and the stability is good.
(2) Aiming at the problem of local obstacles in path planning, a local optimal path is obtained by combining global path planning information and adopting a dynamic window method, and tracking of local target points is realized by utilizing a preview tracking method according to feedback control parameters, so that real-time obstacle avoidance is realized, and robustness is good.
(3) The dynamic window method fused with the global path planning algorithm provided by the invention can realize local real-time obstacle avoidance, improve the path planning efficiency, realize automatic feedback control of the intelligent vehicle and have good robustness and accuracy.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a flow chart of a hybrid algorithm of the present invention based on the improved ant colony algorithm and the dynamic windowing method;
FIG. 2 is a flow chart of the smoothing of a cubic B-spline curve in accordance with the present invention;
FIG. 3 is an optimal path for a basic ant colony algorithm;
FIG. 4 is an optimal path for a prior art ant colony algorithm;
FIG. 5 is an optimal path for improving the ant colony algorithm in the present invention;
FIG. 6 is an iterative convergence trend graph of three ant colony algorithms;
FIG. 7 is a schematic diagram of preview tracking of the dynamic windowing method of the present invention;
FIG. 8 is a path planning result of the hybrid algorithm of the present invention in an unknown obstacle environment I;
FIG. 9 is a path planning result of the hybrid algorithm of the present invention in unknown obstacle environment II;
FIG. 10 is a closed SLAM grid map of a real vehicle test constructed by the hybrid algorithm of the present invention;
FIG. 11 is the result of the hybrid algorithm of the present invention running on a SLAM grid map;
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
The hybrid algorithm based on the improved ant colony algorithm and the dynamic window method, which is applied to the intelligent vehicle path planning, can realize real-time obstacle avoidance of the intelligent vehicle, smooth the turning angle of the path, improve the path planning efficiency and realize automatic feedback control of the intelligent vehicle. The flow chart of the hybrid algorithm based on the improved ant colony algorithm and the dynamic window method provided by the invention is shown in fig. 1, and the specific steps are as follows:
(1) acquiring environmental information by using a vehicle-mounted sensor, realizing self positioning of a vehicle, and constructing a grid map;
(2) the global path planning of the intelligent vehicle is completed by using an improved ant colony algorithm; setting initialization parameters, the number M of ants, the iteration times K, pheromone elicitation factors a and expectation elicitation factors w, and placing M ants at initial positions; secondly, according to ant state transition probability
Selecting a path, putting nodes which are walked by the ants into a tabu table, and judging the next path selection of the ants, wherein the formula (1) is as follows:
wherein all (i) represents a set of transfer nodes that ants k except the tabu table allow selection next at node i; t isig(t) represents the pheromone content of ants from node i to node g at time t, Nig(t) represents the heuristic function of ants from node i to node g at time t;
in the specific embodiment, in order to accelerate the search speed of the ant colony, the selection guiding function of the ant colony on the next node is increased, and the current node is selected according to the current nodeIntroducing a heuristic function N to the square of the sum of the distance from the next node and the distance from the current node to the targetig(t) is represented by the formula (2):
Νig(t)＝1/(σ·lig+(1-σ)·liE)2(2)
where σ represents the weighted proportion between the distances of two nodes, and σ ∈ [0,1]Determined by the real-time environment,/igRepresents the distance, l, between the current node i and the next node giERepresenting the distance between the current node i and the target node E;
in the embodiment, in order to shorten the ant search time, reduce the probability of selecting the walking route, and avoid too low or too much accumulation after the pheromone concentration is volatilized, the maximum value T of the pheromone concentration between two points needs to be determinedmaxAnd a minimum value TminAs shown in formula (3):
wherein DsFor the optimal path length after a certain iteration, n is the cycle number of each time;
in a specific embodiment, after the ant finishes each cycle, the pheromone information on the path changes, and in order to obtain the optimal path, the pheromone on the whole path needs to be adjusted, as shown in formula (4):
Τig(t+1)＝(1-λ)·Τig(t)+△Τig(t) (4)
in a specific embodiment, in order to prevent an ant colony from performing path planning by using pheromones on a local optimal path and ensure that each ant can find a feasible path, an improvement needs to be made on pheromone updating, that is, the pheromone concentration increment of an ant between two points is updated, as shown in formula (5):
wherein λ represents the pheromone volatility coefficient, λ ∈ [0,1]；ΔTig(t) representsthe pheromone increment of ants between the node i and the node g at the moment t;
the pheromone increment of the b-th ant between the node i and the node g at the moment t is represented; r issThe optimal solution found so far;
(3) and smoothing the global path by adopting a B-spline curve, wherein the mathematical expression mode of the B-spline curve is shown as the formula (6):
wherein P isi(i-0, 1, 2, …, n) is the coordinates of (n +1) control points of the curve, Fi,k(t) is a k-th order B-spline basis function as shown in equation (7):
in a specific embodiment, in order to ensure that the smart car smoothly and safely passes through a turn and meet the geometric constraint characteristic of the smart car, a basis function when K is 3 is selected, as shown in equation (8):
in a specific embodiment, the mathematical expression of the cubic B-spline curve is as shown in equation (9):
(4) acquiring unknown obstacle information aiming at a vehicle-mounted sensor, and obtaining a maximum speed V according to initial parametersmThe linear acceleration v and the angular acceleration omega make a path evaluation by combining a dynamic window method with global path planning information, and a local optimal path is selected;
in a specific embodiment, the comprehensive evaluation function of the local optimal path is shown as formula (10):
where goal (v, ω) represents the angle between the vector pointing to the target and the vector connecting the starting point and the current position, d (v, ω) represents the perpendicular distance of the static obstacle from the track currently pointing to the target, d (v, ω)m,ωm) Indicating the vertical distance, v, of the unknown obstacle from the current target trajectorye(v, omega) represents the velocity magnitude evaluation function of the current pointing target track, and mu, β, phi and lambda are represented as weighting coefficients;
in a specific embodiment, a preview tracking method is used to track a local moving target point to obtain an optimal local path planning path, and a planned path trajectory is as shown in formula (11):
(x-xo)2+(y-yo)2＝R2(11)
wherein the coordinates of the intelligent vehicle are (x, y), the vehicle-mounted sensor measures the coordinates (x) of the circle center of the path track determined by the outgoing mobile target pointo，yo)；
(5) And judging whether the local moving target point is the final target point, if so, ending, otherwise, returning to 1) until the final target point is reached.
In a specific embodiment, a cubic B-spline curve is used for smoothing a global path planned by an improved ant colony algorithm, the smoothing flow is as shown in fig. 2, initial parameters of the cubic B-spline curve are firstly set, then an optimal global path node of the improved ant colony algorithm is output, and then the output node is used as a control point of the spline curve, so that the smooth cubic B-spline curve is output, the turning angle of the path is smoothed, and the safety of an intelligent vehicle in the driving process is improved.
In a specific embodiment, by comparing the ant colony algorithm optimal path diagrams of fig. 3, fig. 4, and fig. 5, it can be found that the basic ant colony algorithm, the existing ant colony algorithm, and the ant colony algorithm in the present invention can find the optimal feasible path in the process of performing global path planning search operation, but the ant colony algorithm in the present invention smoothes the turning angle of the path after the cubic B-spline curve smoothing processing, and accelerates the convergence iteration speed.
In a specific embodiment, from the convergence trend graphs of the three ant colony algorithms in fig. 6, it can be seen that the 3 ant colony algorithms have fluctuation changes at the initial stage and gradually tend to be stable at the later stage, and the optimal path length of the basic ant colony algorithm is 29.1842, which tends to converge and generate local optimality for multiple times; the optimal path length of the existing ant colony algorithm is 29.1848; the shortest path obtained by the improved ant colony algorithm provided by the invention is 28.0416, the convergence speed is better, and the smooth safe passing performance of the intelligent vehicle is improved.
In a specific embodiment, because the dynamic window method can plan an optimal track, that is, the control input speed and angle of the intelligent vehicle can be directly obtained, the local moving target point is tracked by using the pre-aiming tracking method shown in fig. 7, the local target point is regarded as the pre-aiming point according to the local target point position updated by the vehicle-mounted sensor in the motion process of the intelligent vehicle, and the distance between the center point of the intelligent vehicle and the pre-aiming point is L; the vertical distance between the intelligent vehicle and the local moving target point is Ms(ii) a When M issNot equal to 0 and L not equal to 0, always has MsLess than or equal to L, and the included angle formed between the motion direction of the intelligent vehicle and the motion direction of the local moving target point is a preview angle phi1The boresight deviation angle is theta1And the invention provides that when the pre-aiming point is at the left front of the moving direction of the intelligent vehicle, theta1And if so, calculating a pre-aiming deviation angle according to the control speed and the angle fed back by the intelligent vehicle in real time, and planning the next operation state of the intelligent vehicle.
In a specific embodiment, a starting point S, a target point T and an unknown obstacle in a grid map are set, a simulation experiment with two different obstacle positions as shown in fig. 8 and 9 is completed by applying the hybrid algorithm of the present invention, it can be seen from the figure that the improved ant colony algorithm of the present invention sets a global optimal path first, the dynamic window algorithm detects the obstacle position according to the vehicle-mounted sensor, and a local target point is set on the global path. If no obstacle is detected, the intelligent vehicle walks according to the global optimal path as much as possible, and if an unknown obstacle is detected, the dynamic window method sets a local target point by combining an evaluation function of global path information and tracks the local target point until the target point is reached. When the obstacle avoidance of the local obstacle is carried out, the dynamic window method can ensure that the intelligent vehicle cannot collide with the obstacle, the direction of real-time tracking of the local target point is consistent with the direction of the target point, the path planning efficiency of the intelligent vehicle is improved, the automatic feedback control and the local real-time obstacle avoidance of the intelligent vehicle are realized, and the purpose of designing a hybrid algorithm is achieved.
In a specific embodiment, the algorithm is verified and analyzed on an intelligent real vehicle platform based on the ROS, before an experiment, a closed SLAM grid map is constructed by calling a Gmapping function package in the ROS, as shown in FIG. 10, wherein black pixels represent obstacles; verifying the robustness and accuracy of the algorithm according to the constructed SLAM grid map, firstly completing the global path planning of the intelligent vehicle according to the known environment, as shown by a thick line in FIG. 11, and then setting an unknown obstacle on the global path; finally, local obstacle avoidance is completed by a dynamic window method, such as a black line part in the graph 11; as can be seen from fig. 11, if there is no local obstacle, the smart car will travel according to the global optimal path; when an unknown obstacle appears, the intelligent vehicle cannot collide with the obstacle in the driving process and always drives along the target direction of the global optimal path, the path planning efficiency is improved, and the driving stability of the vehicle is improved.
The invention is not limited to the embodiments described above, and all technical solutions obtained by equivalent substitution methods fall within the scope of the invention claimed.
Claims (7)
1. A hybrid algorithm based on an improved ant colony algorithm and a dynamic window method and applied to intelligent vehicle path planning is characterized by comprising the following steps:
the method comprises the following steps: acquiring environmental information by using a vehicle-mounted sensor, realizing self positioning of a vehicle, and constructing a grid map;
step two: the global path planning of the intelligent vehicle is completed by using an improved ant colony algorithm; first, setting initialization parameter, ant numberMeasuring M, iteration times K, pheromone elicitation factors a and expectation elicitation factors w, and placing M ants at initial positions; secondly, according to ant state transition probability
Selecting a path, putting nodes which are walked by the ants into a tabu table, and judging the next path selection of the ants:
wherein all (i) represents a set of transfer nodes that ants k except the tabu table allow selection next at node i; t isig(t) represents the pheromone content of ants from node i to node g at time t, Nig(t) represents the heuristic function of ants from node i to node g at time t; secondly, introducing a heuristic function N according to the square of the sum of the distance from the current node to the next node and the distance from the current node to the target nodeig(t), the searching speed of the ant colony is accelerated, and the selection guiding effect of the ant colony on the next node is increased:
Νig(t)＝1/(σ·lig+(1-σ)·liE)2
where σ represents the weighted proportion between the distances of two nodes, and σ ∈ [0,1]Determined by the real-time environment,/igRepresents the distance, l, between the current node i and the next node giERepresenting the distance between the current node i and the target point E; then, an improvement is made in the pheromone update: determining the maximum value T of the concentration of pheromones between two pointsmaxAnd a minimum value Tmin：
Wherein DsFor the optimal path length after a certain iteration, n is the number of cycles of each time, after the ants finish each cycle, the pheromone information on the path is changed, and in order to obtain the optimal path, the pheromone on the whole path needs to be carried outAdjusting, and meanwhile, in order to prevent the ant colony from performing path planning by using pheromones on the local optimal path, the pheromone concentration increment of the ant between two points also needs to be updated, so that each ant can find a feasible path:
wherein λ represents the pheromone volatility coefficient, λ ∈ [0,1]；
The pheromone increment of the b-th ant between the node i to the node g at the time t is represented; r issThe optimal solution found so far;
step three: and smoothing the global path by adopting a cubic B-spline curve, wherein the mathematical expression mode of the cubic B-spline curve is as follows:
wherein P isi(i-0, 1, 2, …, n) is the coordinates of (n +1) control points of the curve, Fi,k(t) is a k-th-order B-spline basis function at time t:
step four: acquiring unknown obstacle information aiming at a vehicle-mounted sensor, and obtaining a maximum speed V according to initial parametersmAnd the linear acceleration v and the angular acceleration omega make a path evaluation by combining the global path planning information by using a dynamic window method, and select a local optimal path:
where goal (v, ω) represents the angle between the vector pointing to the target and the vector connecting the starting point and the current position, d (v, ω) represents the perpendicular distance of the static obstacle from the track currently pointing to the target, d (v, ω)m,ωm) Indicating the vertical distance, v, of the unknown obstacle from the current target trajectoryeAnd (v, omega) represents the evaluation function of the velocity of the current pointing target track, mu, β, phi and lambda represent weighting coefficients, and meanwhile, a pre-aiming tracking method is used for tracking the local moving target point to obtain an optimal local path planning path, wherein the planned path track is as follows:
(x-xo)2+(y-yo)2＝R2
wherein the coordinates of the intelligent vehicle are (x, y), the vehicle-mounted sensor measures the coordinates (x) of the circle center of the path track determined by the outgoing mobile target pointo，yo)；
Step five: and judging whether the local moving target point is the final target point, if so, ending, otherwise, returning to the step one until the final target point is reached.
2. The hybrid algorithm based on the improved ant colony algorithm and the dynamic window method applied to the intelligent vehicle path planning as claimed in claim 1, wherein the parameter values in the second step are respectively as follows: the ant number M is 50, the iteration number K is 100, the pheromone heuristic factor a is 1, and the expectation heuristic factor w is 7.
3. The hybrid algorithm based on the improved ant colony algorithm and the dynamic window method applied to the intelligent vehicle path planning as claimed in claim 1, wherein the initial position of the ant in the second step is located at the lower right of the grid map.
4. The hybrid algorithm applied to intelligent vehicle path planning and based on the improved ant colony algorithm and the dynamic window method as claimed in claim 1, wherein the heuristic function in the second step is an improved heuristic function, and the ant state transition probability ensures that ants always search towards the shortest path, thereby increasing the search speed of the ant colony.
5. The hybrid algorithm based on the improved ant colony algorithm and the dynamic window method applied to the intelligent vehicle path planning in claim 1, wherein the parameter values in the fourth step are respectively: maximum velocity Vm1m/s and 0.2m/s2Angular acceleration ω 0.9rad/s2The smart car heading weight coefficient μ is 0.02, the obstacle weight coefficient β is 0.10, and the speed weight coefficient Φ is 0.1.
6. The hybrid algorithm applied to intelligent vehicle path planning and based on the improved ant colony algorithm and the dynamic window method as claimed in claim 1, wherein the dynamic window method in step four can complete speed limitation, acceleration limitation and safety distance limitation on obstacles of the intelligent vehicle, so as to ensure that the intelligent vehicle can avoid obstacles in real time in the planning process.
7. A hybrid algorithm based on an improved ant colony algorithm and a dynamic window method and applied to intelligent vehicle path planning is characterized by comprising the hybrid algorithm based on the improved ant colony algorithm and the dynamic window method and used for the intelligent vehicle path planning as set forth in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010619230.1A CN111694364A (en) | 2020-06-30 | 2020-06-30 | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010619230.1A CN111694364A (en) | 2020-06-30 | 2020-06-30 | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111694364A true CN111694364A (en) | 2020-09-22 |
Family
ID=72484904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010619230.1A Withdrawn CN111694364A (en) | 2020-06-30 | 2020-06-30 | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111694364A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183710A (en) * | 2020-10-22 | 2021-01-05 | 中国联合网络通信集团有限公司 | Method and device for determining path |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
| CN112486185A (en) * | 2020-12-11 | 2021-03-12 | 东南大学 | Path planning method based on ant colony and VO algorithm in unknown environment |
| CN112631294A (en) * | 2020-12-16 | 2021-04-09 | 上海应用技术大学 | Intelligent path planning method for mobile robot |
| 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 |
| CN112925318A (en) * | 2021-01-25 | 2021-06-08 | 西南交通大学 | Calculation method applied to intelligent robot moving path |
| CN113238554A (en) * | 2021-05-08 | 2021-08-10 | 武汉科技大学 | Indoor navigation method and system based on SLAM technology integrating laser and vision |
| CN113341991A (en) * | 2021-06-18 | 2021-09-03 | 重庆大学 | Path optimization method based on dynamic window and redundant node filtering |
| CN113359718A (en) * | 2021-05-26 | 2021-09-07 | 西安理工大学 | Method and equipment for fusing global path planning and local path planning of mobile robot |
| CN113433936A (en) * | 2021-06-02 | 2021-09-24 | 北京迈格威科技有限公司 | Mobile equipment obstacle-avoiding method and device, mobile equipment and storage medium |
| CN113985888A (en) * | 2021-11-08 | 2022-01-28 | 合肥工业大学 | Forklift path planning method and system based on improved ant colony algorithm |
| CN114035586A (en) * | 2021-11-22 | 2022-02-11 | 江苏科技大学 | Workshop AGV trolley path planning method for improving ant colony algorithm and dynamic window |
| CN114313878A (en) * | 2021-11-19 | 2022-04-12 | 江苏科技大学 | Kinematics modeling strategy and path planning method for material transmission platform |
| CN114415686A (en) * | 2022-01-21 | 2022-04-29 | 中国农业银行股份有限公司 | Path determining method and device |
| CN114543815A (en) * | 2022-04-25 | 2022-05-27 | 汕头大学 | Multi-agent navigation control method, equipment and medium based on gene regulation network |
-
2020
- 2020-06-30 CN CN202010619230.1A patent/CN111694364A/en not_active Withdrawn
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183710B (en) * | 2020-10-22 | 2023-11-24 | 中国联合网络通信集团有限公司 | Method and device for determining path |
| CN112183710A (en) * | 2020-10-22 | 2021-01-05 | 中国联合网络通信集团有限公司 | Method and device for determining path |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
| CN112486185A (en) * | 2020-12-11 | 2021-03-12 | 东南大学 | Path planning method based on ant colony and VO algorithm in unknown environment |
| CN112631294A (en) * | 2020-12-16 | 2021-04-09 | 上海应用技术大学 | Intelligent path planning method for mobile robot |
| CN112631294B (en) * | 2020-12-16 | 2022-06-28 | 上海应用技术大学 | Intelligent path planning method for mobile robot |
| 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 |
| CN112925318A (en) * | 2021-01-25 | 2021-06-08 | 西南交通大学 | Calculation method applied to intelligent robot moving path |
| CN113238554A (en) * | 2021-05-08 | 2021-08-10 | 武汉科技大学 | Indoor navigation method and system based on SLAM technology integrating laser and vision |
| CN113359718A (en) * | 2021-05-26 | 2021-09-07 | 西安理工大学 | Method and equipment for fusing global path planning and local path planning of mobile robot |
| CN113359718B (en) * | 2021-05-26 | 2022-11-22 | 西安理工大学 | Method and equipment for fusing global path planning and local path planning of mobile robot |
| CN113433936A (en) * | 2021-06-02 | 2021-09-24 | 北京迈格威科技有限公司 | Mobile equipment obstacle-avoiding method and device, mobile equipment and storage medium |
| CN113341991A (en) * | 2021-06-18 | 2021-09-03 | 重庆大学 | Path optimization method based on dynamic window and redundant node filtering |
| CN113985888B (en) * | 2021-11-08 | 2022-09-16 | 合肥工业大学 | Forklift path planning method and system based on improved ant colony algorithm |
| CN113985888A (en) * | 2021-11-08 | 2022-01-28 | 合肥工业大学 | Forklift path planning method and system based on improved ant colony algorithm |
| CN114313878A (en) * | 2021-11-19 | 2022-04-12 | 江苏科技大学 | Kinematics modeling strategy and path planning method for material transmission platform |
| CN114313878B (en) * | 2021-11-19 | 2024-04-19 | 江苏科技大学 | Kinematic modeling and path planning method for material transmission platform |
| CN114035586A (en) * | 2021-11-22 | 2022-02-11 | 江苏科技大学 | Workshop AGV trolley path planning method for improving ant colony algorithm and dynamic window |
| CN114035586B (en) * | 2021-11-22 | 2024-03-29 | 江苏科技大学 | Workshop AGV trolley path planning method for improving ant colony algorithm and dynamic window |
| CN114415686A (en) * | 2022-01-21 | 2022-04-29 | 中国农业银行股份有限公司 | Path determining method and device |
| CN114415686B (en) * | 2022-01-21 | 2024-04-19 | 中国农业银行股份有限公司 | Path determination method and device |
| CN114543815A (en) * | 2022-04-25 | 2022-05-27 | 汕头大学 | Multi-agent navigation control method, equipment and medium based on gene regulation network |
| CN114543815B (en) * | 2022-04-25 | 2022-07-19 | 汕头大学 | Multi-agent navigation control method, equipment and medium based on gene regulation network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111694364A (en) | Hybrid algorithm based on improved ant colony algorithm and dynamic window method and applied to intelligent vehicle path planning | |
| WO2020056875A1 (en) | Parking strategy based on deep reinforcement learning | |
| WO2021175313A1 (en) | Automatic driving control method and device, vehicle, and storage medium | |
| CN110928295B (en) | Robot path planning method integrating artificial potential field and logarithmic ant colony algorithm | |
| CN110989576B (en) | Target following and dynamic obstacle avoidance control method for differential slip steering vehicle | |
| CN112356830A (en) | Intelligent parking method based on model reinforcement learning | |
| CN112925315A (en) | Crawler path planning method based on improved ant colony algorithm and A-star algorithm | |
| CN113359718A (en) | Method and equipment for fusing global path planning and local path planning of mobile robot | |
| CN111123953B (en) | Particle-based mobile robot group under artificial intelligence big data and control method thereof | |
| Chen et al. | Path planning for autonomous vehicle based on a two-layered planning model in complex environment | |
| Che et al. | Research on improved ACO algorithm-based multi-robot odor source localization | |
| CN116795120A (en) | Mobile robot hybrid path planning method with improved A-algorithm and dynamic window method | |
| CN116804879A (en) | Robot path planning framework method for improving dung beetle algorithm and fusing DWA algorithm | |
| Hamad et al. | Path Planning of Mobile Robot Based on Modification of Vector Field Histogram using Neuro-Fuzzy Algorithm. | |
| Fu et al. | Collision-free and kinematically feasible path planning along a reference path for autonomous vehicle | |
| Li et al. | Research on the agricultural machinery path tracking method based on deep reinforcement learning | |
| Yan et al. | Study on the local path planning for intelligent vehicles based on an improved VFH method | |
| Xiao et al. | Multiobjective path optimization of an indoor AGV based on an improved ACO-DWA | |
| Smit et al. | Informed sampling-based trajectory planner for automated driving in dynamic urban environments | |
| CN113959446B (en) | Autonomous logistics transportation navigation method for robot based on neural network | |
| He et al. | Intelligent navigation of indoor robot based on improved DDPG algorithm | |
| CN115690343A (en) | Robot laser radar scanning and mapping method based on visual following | |
| Zhang et al. | 2D map building and path planning based on LiDAR | |
| Wang et al. | Experience mixed the modified artificial potential field method | |
| Meng et al. | A navigation framework for mobile robots with 3D LiDAR and monocular camera |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200922 |