CN113110431A - Real-time planning method for field test path of unmanned target vehicle - Google Patents
Real-time planning method for field test path of unmanned target vehicle Download PDFInfo
- Publication number
- CN113110431A CN113110431A CN202110363973.1A CN202110363973A CN113110431A CN 113110431 A CN113110431 A CN 113110431A CN 202110363973 A CN202110363973 A CN 202110363973A CN 113110431 A CN113110431 A CN 113110431A
- Authority
- CN
- China
- Prior art keywords
- path
- information
- target vehicle
- unmanned
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 239000003016 pheromone Substances 0.000 claims description 60
- 241000257303 Hymenoptera Species 0.000 claims description 23
- 230000001788 irregular Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 239000002245 particle Substances 0.000 claims description 17
- 230000003068 static effect Effects 0.000 claims description 7
- 230000004888 barrier function Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008020 evaporation Effects 0.000 claims description 3
- 238000001704 evaporation Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims 1
- 230000008447 perception Effects 0.000 abstract description 3
- 230000008685 targeting Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 7
- 230000002431 foraging effect Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002028 premature Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- 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
-
- 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
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a real-time planning method for field test paths of an unmanned target vehicle, which comprises the following steps: collecting GPS/BDS data information of the unmanned target vehicle, and constructing a grid environment model according to the information in the global map; carrying out global path planning based on an improved ant colony algorithm; the unmanned target vehicle runs along an expected path, receives real-time video signals transmitted from various sensors, and judges whether local path planning is needed or not; a local path planning strategy; and sending the generated real-time local path to an unmanned targeting vehicle control layer. The invention improves the efficiency of field path planning of the unmanned drone vehicle, and ensures that the unmanned drone vehicle can efficiently and reasonably plan a safe path in an unknown field environment by utilizing the environment perception information, thereby ensuring the global optimality and local real-time performance of field path planning.
Description
Technical Field
The invention relates to the technical field of unmanned driving, in particular to a real-time planning method for a field test path of an unmanned target vehicle.
Background
With the progress of science and technology, unmanned technology is increasingly researched, and attention is paid to the unmanned automobile, wherein the unmanned automobile senses road environment through a vehicle-mounted sensing system, defines a starting point and a target point of the automobile according to a specific road environment model, conducts azimuth guidance and controls the automobile to reach a preset destination. The unmanned automobile integrates advanced technologies of precise positioning, environment perception, path decision planning and the like into a traditional vehicle carrier. However, for the current unmanned technology, path planning is a vital technology of the unmanned technology, and the problem to be solved is 'how to go to the place'. The path planning is a key link of the unmanned technology, is the basis for realizing informatization, intellectualization and automation of the unmanned vehicle, and respectively depends on global planning based on an environment model and local path planning based on external information obtained by a sensor.
Path planning can be divided into global path planning based on prior complete information and local path planning based on sensor information according to the degree of confidence in the environmental information. The global planning belongs to static planning, the local path planning belongs to dynamic planning, all environment information needs to be mastered in the global path planning, and the path planning is carried out according to all the information of the environment map; the local path planning only needs to acquire environmental information in real time by a sensor, know the environmental map information and then determine the position of the map and the local obstacle distribution condition of the map, so that the optimal path of a certain sub-target node from the current node can be selected.
The road environment is increasingly complex and changeable, and for an unknown open field area, the traditional path planning algorithm cannot well meet the requirements, and the automatic planning of the path cannot be realized.
Disclosure of Invention
The invention aims to provide a real-time planning method for a field test path of an unmanned target vehicle.
The technical scheme for realizing the purpose of the invention is as follows: a real-time planning method for field test paths of unmanned target vehicles comprises the following steps:
s1, collecting GPS/BDS data information of the unmanned target vehicle, acquiring state position information of the vehicle, taking the position of the unmanned target vehicle as a starting point and a target point as an end point, and loading global map information;
s2, constructing a grid environment model based on the selected starting point and target point information and the global map information, and performing global path planning by adopting an improved ant colony algorithm to generate a global path;
s3, the unmanned target vehicle runs along the expected path and receives real-time signals transmitted from various sensors, environmental information around the unmanned target vehicle, including road information and obstacle information, is obtained according to the signals, analysis and judgment are carried out according to the obtained sensor information to judge whether local path planning is needed, and if the local path planning is needed, the step S4 is carried out; if the local path planning is not needed, go to step S5;
s4, local real-time path planning strategy: when the unmanned target vehicle runs along an expected path, continuously sensing obstacle information in a limited range by using a sensor carried by the unmanned target vehicle, representing the obstacle information in a grid model, taking the real-time position of the current unmanned target vehicle as reference, taking a point closest to the adjacent side of the top point of the grid model of the obstacle as a feasible point, and observing whether the obstacle grid has a part overlapped with the expected path or not by taking the feasible point as a starting point after the unmanned target vehicle runs to the feasible point, and if so, performing local path planning based on an improved ant colony algorithm; if not, go to step S5;
s5, sending the generated expected path to an unmanned drone vehicle chassis controller; if the local path is generated, updating the path information and sending the updated path information to the chassis controller; if no local path is generated, the drone vehicle continues to travel along the desired path.
Further, the global map information in step S1 includes obstacle information, where the obstacle is a static obstacle and is obstacle information that can be obtained from the original global map information; the obstacle information in step S4 is the obstacle information that cannot be acquired in the map or a static obstacle newly added in the course of the unmanned drone vehicle traveling in the open air.
Further, the global path planning process in step S2 is as follows:
s201, acquiring barrier information in a global map and information of an unmanned target vehicle, including speed, direction and position information, by adopting a GPS/BDS system, a millimeter wave radar and a laser radar;
s202, acquiring current position information of a simulated target vehicle as a starting point according to a GPS/BDS, selecting a target point, loading global map information to acquire vehicle driving range information, carrying out environment modeling, carrying out grid division on a driving area by adopting a grid granularity of 1 x 1, uniformly expressing irregular obstacles in an environment by adopting grid particles, and filling the irregular obstacles when the grid particles are not filled in the irregular obstacles;
s203, adopting an improved ant colony algorithm to carry out global path planning to obtain an expected path;
and S204, smoothing the generated global path by adopting a cubic B-spline curve.
Further, the improved ant colony algorithm model is as follows:
allowk is an ant k with access point set;
at the initial moment, n-1 elements exist in allowk, namely, a plurality of points except the current position point of the ant are collected, and the elements in allowk are less and empty at last when the ant walks every step;
the formula for the heuristic function is:
in the above formula, didRepresents the distance between node i and its neighboring point d, ddjRepresents the distance from the node d to the target point j, lambda is the weight coefficient of the distance between the nodes, and lambda belongs to [0,1 ]]。
Further, the pheromone updating strategy in the global path planning based on the improved ant colony algorithm is as follows:
when all ants complete one iteration, the calculation method of the pheromone quantity between the nodes on each path is as follows:
cij(t+1)＝(1-ρ)*cij(t)+Δcij
Wherein Q is a constant representing intensity of pheromone increment, and after one iteration, stacking and sorting path lengths of all ant iterations, and L0<L1<L2<…, the shorter the path, the smaller the rank k, the optimal path L0When k is 0; ω represents the weight of the ant iteration path ordered as k, ω ═ max-k, where max represents the weight of the optimal path;
in the updated pheromone strategy, pheromones with different weights are updated on each path through sequencing of ant iteration paths after one iteration, pheromones on the optimal path are continuously superposed through iteration, so that more ants are attracted to move to the optimal path, if the path with the length of L' is sequenced into r in all paths after the ant iteration for one time, the path weight is max-r, and the pheromones among the nodes of each path are updated into
When the maximum iteration number N is reachedmaxAnd calculating the search path length of each ant to find out the optimal path.
Further, the local path planning analysis method in step S3 is as follows:
judging whether the safe driving of the unmanned target vehicle along the expected path is influenced or not according to the information obtained by various sensors;
comparing the grid number of the driving path of the unmanned target vehicle with the grid number of the obstacle detected by the sensor:
if the grid number of the driving path of the unmanned target vehicle is intersected with the grid number of the obstacle detected by the sensor, judging that local path planning is needed;
and if the grid number of the driving path of the unmanned target vehicle is not intersected with the grid number of the obstacle detected by the sensor, judging that the local path planning is not needed.
Further, the method for performing local path planning in step S4 includes:
s401: obtaining obstacle information through various sensors, dividing an obstacle area by adopting 1 × 1 grid particles, uniformly expressing irregular obstacles in the environment by adopting the grid particles, and filling the irregular obstacles when the grid particles are not filled;
s402: observing whether the obstacle grids overlap with the expected path, if so, generating a local path to avoid collision, and if not, performing step S5;
s403: acquiring the position information of the peak of the barrier grid, selecting the peak closest to the current unmanned target vehicle, taking the peak as a new starting point after the unmanned target vehicle drives along the expected path, and performing local path planning based on an improved ant colony algorithm;
s404: and smoothing the generated path by adopting a cubic B-spline curve.
Further, the method for sending the path planning information to the chassis controller in step S5 specifically includes:
step S501: sending the generated global expected path to a chassis controller, and enabling the unmanned target vehicle to run according to the global expected path;
step S502: if the local path is generated, updating the path information and sending the updated path information to the chassis controller; if no local path is generated, the drone vehicle continues to travel along the desired path.
An electronic device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the unmanned target vehicle field test path real-time planning method.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the above-mentioned method for real-time planning of field test paths of unmanned vehicles.
Compared with the prior art, the invention has the beneficial effects that:
(1) aiming at the problems that the traditional ant colony algorithm is easy to cause, such as low convergence speed, easy to fall into the local optimal solution and the like, the invention improves the ant colony algorithm, accelerates the convergence speed and relieves the condition of easy to fall into the local optimal solution;
(2) the invention provides a new pheromone updating strategy, which can improve the concentration of pheromones on the optimal path, but can not cause the premature convergence of the algorithm to fall into the local optimal solution because the concentration of the pheromones on the optimal path is too prominent;
(3) the unmanned target vehicle path planning aims at the field environment, and compared with the urban environment, the field environment has the characteristic of unknown property, and the unmanned target vehicle can run in the field unknown environment after the prior information is obtained;
(4) and (3) local path planning strategy: the information fusion of various sensors is used for local path planning, and the obstacle avoidance problem of the obstacles in the local path is decided in real time based on environment perception, so that the safety and the reliability of the unmanned target vehicle path planning are improved;
(5) the path is smoothed by utilizing the cubic B-spline curve, and the stability is good.
Drawings
Fig. 1 is a schematic flow chart of a real-time planning method for field test paths of an unmanned target vehicle.
Fig. 2 is a schematic flow chart of the improved ant colony algorithm provided by the invention.
Fig. 3 is a grid diagram for modeling an environment of a driving range of an unmanned drone vehicle in an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
As shown in fig. 1, the method for real-time planning of field test path of unmanned target vehicle in the embodiment of the present invention includes the following steps:
step 1, positioning, comprising the following specific steps:
s101, acquiring current position information of the unmanned target vehicle according to a GPS/BDS system, and taking the current position of the unmanned target vehicle as a starting point;
step S102, loading global map information according to a starting point and a target point, wherein the map comprises all known static obstacles;
the global map information comprises obstacle information, wherein the obstacles are static obstacles and can be acquired from the original global map information.
step 201, acquiring current position information of a simulated target vehicle as a starting point according to a GPS/BDS, selecting a target point, loading global map information to acquire vehicle driving range information, performing environment modeling, performing grid division on a driving area by adopting a grid granularity of 1 x 1, uniformly expressing irregular obstacles in an environment by adopting grid particles, and filling the irregular obstacles when the grid particles are not filled in the irregular obstacles; as shown in fig. 3, where the non-obstacle grid is a feasible grid. The unmanned vehicles can move along the direction of the adjacent sides in the current grid, and the free grids which can be selected by the unmanned vehicles include 25,44,64,65 and 46 by taking the grid 45 in fig. 3 as an example. Setting S, T in the grid as the starting point and the end point of the unmanned vehicle respectively, and constructing an obstacle matrix for representing the specific position of the obstacle:
the driving environment of the unmanned vehicle can be described by using the obstacle matrix.
Step 202, planning a global path, specifically comprising the following steps:
by improving and optimizing heuristic functions of node state transition probability and updating pheromones in the traditional ant colony algorithm, a colony optimization algorithm is provided, and the shortest global path from the trip point to the end point is generated, wherein the improved ant colony algorithm model is as follows:
at the initial moment, n-1 elements exist in allowk, namely, a plurality of points except the current position point of the ant are gathered, and the elements in allowk are less and empty at last when the ant walks every step.
cid(t) the pheromone concentration on the path from the point i to the next adjacent point d;
a is a pheromone importance factor;
b is a heuristic function factor;
cij(t) pheromone concentration on the path from point i to point j;
d is a set of optional nodes adjacent to the position node i, nij(t) is a heuristic function representing the expectation of ants to transfer from point i to point j, nid(t) represents the heuristic function between an ant and the neighboring point d.
The formula for the heuristic function is:
in the above formula, didRepresenting the distance between a node i and its neighbor d, ddjIs the distance from node d to target point j, λ is the weighting coefficient of the distance between nodes, λ ∈ [0,1 ∈ >]The randomness and the purpose of the operation of the algorithm are represented, and the possibility of finding the optimal path is increased.
The aim of modifying the heuristic function is to strengthen the selection guiding effect of the ant colony on the target node and the next node, so that the search time of the ant colony is reduced, the randomness of the ant colony selecting node is ensured to be increased, the local optimization is avoided, and the efficiency of path planning is improved.
An ant colony algorithm-based pheromone updating strategy in global path planning comprises the following steps:
during the process of searching for food source from nest, ant releases a chemical substance called pheromone on the path, so that ant can exchange information through the substance during foraging. During the foraging process of the ants, pheromones with certain concentration are remained on the routes passed by the ants, other ants can sense the concentration of the pheromones remained on the routes during the foraging process, the moving trend of the ants tends to the position with higher pheromone concentration, accordingly, the directions are appointed for the next action of the ants, and meanwhile, the pheromone concentration is reduced along with the foraging of the ants.
When all ants complete one iteration, the calculation method of the pheromone quantity between the nodes on each path is as follows:
cij(t+1)＝(1-ρ)*cij(t)+Δcij
Wherein Q is a constant representing intensity of pheromone increment, and after one iteration, stacking and sorting path lengths of all ant iterations, and L0<L1<L2<…, the shorter the path, the smaller the rank k, the optimal path L0When k is 0.ω represents the weight of the ant iteration path ordered as k, ω ═ max-k, where max represents the weight of the optimal path.
In the updated pheromone strategy, pheromones with different weights are updated on each path by sequencing ant iteration paths after one iteration, so that the condition that the pheromones are in place can be improvedAnd the intensity on the front optimal path is continuously superposed by iteration for one time, so that more ants are attracted to move to the optimal path, if the path with the length of L' is ordered to be r in all paths after the ants are iterated for one time, the weight of the path is max-r, and the pheromones among all path nodes are updated to be
And when the path sequencing is larger, the relative weight is reduced, so that the concentration of pheromones is weakened, and the phenomenon that the algorithm is converged too early and falls into the local optimal solution is effectively prevented. When a bad path has a negative weight (when k is>max), the pheromone concentration on the path is reduced, so that the time for searching the optimal path is reduced, the efficiency of path search is improved, the pheromone concentration on the optimal path can be improved by the pheromone updating strategy, but the premature convergence of the algorithm is not trapped in the local optimal solution because the pheromone concentration on the optimal path is too prominent.
When the maximum iteration number N is reachedmaxAnd outputting the length of each search path to find out the optimal path.
And smoothing the generated global path by adopting a cubic B-spline curve:
because the path searched by the improved ant colony algorithm is not smooth, if the unmanned vehicle can actually drive, the global path needs to be smoothed, and the path turning times are less and smooth.
Step S3, the unmanned target vehicle drives along the expected path and analyzes the current road condition, and the specific implementation steps are as follows:
s301, driving the unmanned target vehicle along a desired path;
step S302, analyzing the field road condition:
the method for analyzing the environmental information around the unmanned target vehicle obtained by various sensors comprises the following steps: detecting surrounding obstacle information including pits of a road surface, information such as road sections and road barriers which are difficult to drive and the like according to a sensor carried by the sensor; whether the safe running of the unmanned target vehicle along the expected path is influenced or not is judged according to the information obtained by various sensors
And S303, dividing the obstacle area by using 1-by-1 grid particles, uniformly representing irregular obstacles in the environment by using the grid particles, filling the irregular obstacles when the grid particles are not filled with the irregular obstacles, uniformly representing the irregular obstacles in the environment by using the grid particles, and filling the irregular obstacles when the grid particles are not filled with the irregular obstacles. As shown in fig. 3, grid numbers are used to indicate specific locations of the drone vehicle and the obstacle.
Step S4, local path planning and analyzing, which comprises the following steps:
and step S401, judging whether safe driving of the unmanned target vehicle along the expected path is influenced or not through information obtained by various sensors.
Step S402, comparing the grid number of the driving path of the unmanned target vehicle with the grid number of the obstacle detected by the sensor
Firstly, if the grid number of the driving path of the unmanned target vehicle intersects with the grid number of the obstacle detected by the sensor, judging that local path planning is needed
And secondly, if the grid number of the driving path of the unmanned target vehicle is not intersected with the grid number of the obstacle detected by the sensor, judging that the local path planning is not needed.
Step S403, if affected, proceeds to step S5, and if not, proceeds to step S6.
Step S5, local path planning, which comprises the following steps:
step S501, collecting the position information of the vertexes of the barrier grids, selecting the vertex closest to the current unmanned drone vehicle, taking the vertex as a new starting point after the unmanned drone vehicle drives along the expected path, and performing local path planning based on an improved ant colony algorithm, wherein the improved ant colony algorithm is the same as the step S2.
And step S502, smoothing the generated path by adopting a cubic B-spline curve.
And step S6, the path planning information is sent to the chassis controller, and the vehicle runs along the expected path.
The present invention also provides an electronic device comprising: the system comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the unmanned target vehicle field test path real-time planning method.
Furthermore, the invention also provides a computer readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the method for real-time planning of the field test path of the unmanned target vehicle.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A real-time planning method for field test paths of unmanned target vehicles is characterized by comprising the following steps:
s1, collecting GPS/BDS data information of the unmanned target vehicle, acquiring state position information of the vehicle, taking the position of the unmanned target vehicle as a starting point and a target point as an end point, and loading global map information;
s2, constructing a grid environment model based on the selected starting point and target point information and the global map information, and performing global path planning by adopting an improved ant colony algorithm to generate a global path;
s3, the unmanned target vehicle runs along the expected path and receives real-time signals transmitted from various sensors, environmental information around the unmanned target vehicle, including road information and obstacle information, is obtained according to the signals, analysis and judgment are carried out according to the obtained sensor information to judge whether local path planning is needed, and if the local path planning is needed, the step S4 is carried out; if the local path planning is not needed, go to step S5;
s4, local real-time path planning strategy: when the unmanned target vehicle runs along an expected path, continuously sensing obstacle information in a limited range by using a sensor carried by the unmanned target vehicle, representing the obstacle information in a grid model, taking the real-time position of the current unmanned target vehicle as reference, taking a point closest to the adjacent side of the top point of the grid model of the obstacle as a feasible point, and observing whether the obstacle grid has a part overlapped with the expected path or not by taking the feasible point as a starting point after the unmanned target vehicle runs to the feasible point, and if so, performing local path planning based on an improved ant colony algorithm; if not, go to step S5;
s5, sending the generated expected path to an unmanned drone vehicle chassis controller; if the local path is generated, updating the path information and sending the updated path information to the chassis controller; if no local path is generated, the drone vehicle continues to travel along the desired path.
2. The method for real-time planning of field path of unmanned drone vehicle of claim 1, wherein the global map information in step S1 includes obstacle information, wherein the obstacle is a static obstacle and is the obstacle information that can be obtained on the original global map information; the obstacle information in step S4 is the obstacle information that cannot be acquired in the map or a static obstacle newly added in the course of the unmanned drone vehicle traveling in the open air.
3. The method for real-time planning of field trial path of unmanned target vehicle as claimed in claim 1, wherein the global path planning process in step S2 is as follows:
s201, acquiring barrier information and unmanned target vehicle self information in a global map by adopting a GPS/BDS system, a millimeter wave radar and a laser radar, wherein the unmanned target vehicle self information comprises speed, direction and position information;
s202, acquiring current position information of a simulated target vehicle as a starting point according to a GPS/BDS, selecting a target point, loading global map information to acquire vehicle driving range information, carrying out environment modeling, carrying out grid division on a driving area by adopting a grid granularity of 1 x 1, uniformly expressing irregular obstacles in an environment by adopting grid particles, and filling the irregular obstacles when the grid particles are not filled in the irregular obstacles;
s203, adopting an improved ant colony algorithm to carry out global path planning to obtain an expected path;
and S204, smoothing the generated global path by adopting a cubic B-spline curve.
4. The method for real-time planning of field trial paths of unmanned target vehicles according to claim 3, wherein the improved ant colony algorithm model is as follows:
allowk is an ant k with access point set;
at the initial moment, n-1 elements exist in allowk, namely, a plurality of points except the current position point of the ant are collected, and the elements in allowk are less and empty at last when the ant walks every step;
the formula for the heuristic function is:
in the above formula, didRepresents nodes i toThe distance between adjacent points d thereof, ddjRepresents the distance from the node d to the target point j, lambda is the weight coefficient of the distance between the nodes, and lambda belongs to [0,1 ]]。
5. The method for planning the field trial path of the unmanned target vehicle in real time according to claim 4, wherein the pheromone updating strategy in the global path planning based on the improved ant colony algorithm is as follows:
when all ants complete one iteration, the calculation method of the pheromone quantity between the nodes on each path is as follows:
cij(t+1)＝(1-ρ)*cij(t)+Δcij
Wherein Q is a constant representing intensity of pheromone increment, and after one iteration, stacking and sorting path lengths of all ant iterations, and L0<L1<L2<…, the shorter the path, the smaller the rank k, the optimal path L0When k is 0; ω represents the weight of the ant iteration path ordered as k, ω ═ max-k, where max represents the weight of the optimal path;
in the updated pheromone strategy, all paths are sequenced through sequencing ant iteration paths after one iterationAnd updating pheromones with different row weights, wherein the pheromones on the optimal path are continuously superposed through iteration so as to attract more ants to move to the optimal path, if the path with the length of L' is ordered to be r in all paths after the ants iterate once, the path weight is max-r, and the pheromones among all path nodes are updated to be pheromones
When the maximum iteration number N is reachedmaxAnd calculating the search path length of each ant to find out the optimal path.
6. The method for real-time planning of field trial path of unmanned target vehicle as claimed in claim 1, wherein the local path planning analysis method in step S3 is as follows:
judging whether the safe driving of the unmanned target vehicle along the expected path is influenced or not according to the information obtained by various sensors;
comparing the grid number of the driving path of the unmanned target vehicle with the grid number of the obstacle detected by the sensor:
if the grid number of the driving path of the unmanned target vehicle is intersected with the grid number of the obstacle detected by the sensor, judging that local path planning is needed;
and if the grid number of the driving path of the unmanned target vehicle is not intersected with the grid number of the obstacle detected by the sensor, judging that the local path planning is not needed.
7. The method for real-time planning of field trial path of unmanned target vehicle as claimed in claim 1, wherein the method for local path planning in step S4 is:
s401: obtaining obstacle information through various sensors, dividing an obstacle area by adopting 1 × 1 grid particles, uniformly expressing irregular obstacles in the environment by adopting the grid particles, and filling the irregular obstacles when the grid particles are not filled;
s402: observing whether the obstacle grids overlap with the expected path, if so, generating a local path to avoid collision, and if not, performing step S5;
s403: acquiring the position information of the peak of the barrier grid, selecting the peak closest to the current unmanned target vehicle, taking the peak as a new starting point after the unmanned target vehicle drives along the expected path, and performing local path planning based on an improved ant colony algorithm;
s404: and smoothing the generated path by adopting a cubic B-spline curve.
8. The method for real-time path planning in field experiments of unmanned target vehicles according to claim 1, wherein the method for sending the path planning information to the chassis controller in step S5 specifically comprises:
step S501: sending the generated global expected path to a chassis controller, and enabling the unmanned target vehicle to run according to the global expected path;
step S502: if the local path is generated, updating the path information and sending the updated path information to the chassis controller; if no local path is generated, the drone vehicle continues to travel along the desired path.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the method for real-time path planning for field trials of unmanned vehicles as claimed in any of claims 1-8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for real-time planning of a field trial path of an unmanned target vehicle according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110363973.1A CN113110431A (en) | 2021-04-03 | 2021-04-03 | Real-time planning method for field test path of unmanned target vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110363973.1A CN113110431A (en) | 2021-04-03 | 2021-04-03 | Real-time planning method for field test path of unmanned target vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113110431A true CN113110431A (en) | 2021-07-13 |
Family
ID=76713647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110363973.1A Pending CN113110431A (en) | 2021-04-03 | 2021-04-03 | Real-time planning method for field test path of unmanned target vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113110431A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113985896A (en) * | 2021-12-03 | 2022-01-28 | 中国重汽集团济南动力有限公司 | Obstacle avoidance path planning method for automatic driving vehicle, vehicle and readable storage medium |
| CN115309163A (en) * | 2022-08-26 | 2022-11-08 | 南京理工大学 | Local path planning method based on improved direction evaluation function DWA algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110375761A (en) * | 2019-08-07 | 2019-10-25 | 天津大学 | Automatic driving vehicle paths planning method based on enhancing ant colony optimization algorithm |
| CN110609557A (en) * | 2019-10-09 | 2019-12-24 | 中国人民解放军陆军装甲兵学院 | Unmanned vehicle mixed path planning algorithm |
| CN111784079A (en) * | 2020-07-28 | 2020-10-16 | 上海海事大学 | Unmanned aerial vehicle path planning method based on artificial potential field and ant colony algorithm |
-
2021
- 2021-04-03 CN CN202110363973.1A patent/CN113110431A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109282815A (en) * | 2018-09-13 | 2019-01-29 | 天津西青区瑞博生物科技有限公司 | Method for planning path for mobile robot based on ant group algorithm under a kind of dynamic environment |
| CN110333714A (en) * | 2019-04-09 | 2019-10-15 | 武汉理工大学 | A kind of pilotless automobile paths planning method and device |
| CN110375761A (en) * | 2019-08-07 | 2019-10-25 | 天津大学 | Automatic driving vehicle paths planning method based on enhancing ant colony optimization algorithm |
| CN110609557A (en) * | 2019-10-09 | 2019-12-24 | 中国人民解放军陆军装甲兵学院 | Unmanned vehicle mixed path planning algorithm |
| CN111784079A (en) * | 2020-07-28 | 2020-10-16 | 上海海事大学 | Unmanned aerial vehicle path planning method based on artificial potential field and ant colony algorithm |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113985896A (en) * | 2021-12-03 | 2022-01-28 | 中国重汽集团济南动力有限公司 | Obstacle avoidance path planning method for automatic driving vehicle, vehicle and readable storage medium |
| CN113985896B (en) * | 2021-12-03 | 2023-12-08 | 中国重汽集团济南动力有限公司 | Automatic driving vehicle obstacle avoidance path planning method, vehicle and readable storage medium |
| CN115309163A (en) * | 2022-08-26 | 2022-11-08 | 南京理工大学 | Local path planning method based on improved direction evaluation function DWA algorithm |
| CN115309163B (en) * | 2022-08-26 | 2024-01-26 | 南京理工大学 | Local path planning method based on improved direction evaluation function DWA algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112650229B (en) | Mobile robot path planning method based on improved ant colony algorithm | |
| CN112925315A (en) | Crawler path planning method based on improved ant colony algorithm and A-star algorithm | |
| CN113110431A (en) | Real-time planning method for field test path of unmanned target vehicle | |
| Wang et al. | Off-road path planning based on improved ant colony algorithm | |
| CN114964261A (en) | Mobile robot path planning method based on improved ant colony algorithm | |
| Ming et al. | A survey of path planning algorithms for autonomous vehicles | |
| CN112484732A (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| CN115355922A (en) | Travel path planning method and system based on improved ant colony algorithm | |
| Bai et al. | Design and Simulation of a Collision-free Path Planning Algorithm for Mobile Robots Based on Improved Ant Colony Optimization. | |
| CN114625137A (en) | AGV-based intelligent parking path planning method and system | |
| CN115237157A (en) | Road network constraint-based air-to-ground unmanned cluster multi-task point path planning method | |
| CN114815801A (en) | Adaptive environment path planning method based on strategy-value network and MCTS | |
| Li et al. | Comparison of biological swarm intelligence algorithms for AUVs for three-dimensional path planning in ocean currents’ conditions | |
| CN112799420A (en) | Real-time track planning method based on multi-sensor unmanned aerial vehicle | |
| CN117371895A (en) | Multi-ground unmanned vehicle path planning method, system and medium in unknown environment | |
| CN116858267A (en) | Path planning method for tobacco industry finished product warehouse flat warehouse inventory robot | |
| Mejri et al. | Energy efficient path planning for low speed autonomous electric vehicle | |
| Chen et al. | GVD-Exploration: An Efficient Autonomous Robot Exploration Framework Based on Fast Generalized Voronoi Diagram Extraction | |
| Zhang et al. | A multi-goal global dynamic path planning method for indoor mobile robot | |
| Zhongjing et al. | Bayesian network based Ant Colony Optimization algorithm for USV path planning in a dynamic environment | |
| Roque-Claros et al. | UAV Path Planning Model Leveraging Machine Learning and Swarm Intelligence for Smart Agriculture | |
| CN118276604B (en) | Multi-unmanned aerial vehicle track planning method and system based on bean-lilac cluster mechanism | |
| Yu | The Impact of Path Planning Model Based on Improved Ant Colony Optimization Algorithm on Green Traffic Management. | |
| Zhao et al. | An improved ant colony algorithm based on Q-Learning for route planning of autonomous vehicle | |
| Yu et al. | Deadlock avoidance based on connectivity detection and dynamic backtracking for path planning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210713 |
|
| RJ01 | Rejection of invention patent application after publication |