CN109900289B - Path planning method and device based on closed-loop control - Google Patents
Path planning method and device based on closed-loop control Download PDFInfo
- Publication number
- CN109900289B CN109900289B CN201910201621.9A CN201910201621A CN109900289B CN 109900289 B CN109900289 B CN 109900289B CN 201910201621 A CN201910201621 A CN 201910201621A CN 109900289 B CN109900289 B CN 109900289B
- Authority
- CN
- China
- Prior art keywords
- circle
- vehicle
- distance
- point
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention provides a path planning method based on closed-loop control, which comprises the following steps: acquiring a reference path; determining a first distance when a first obstacle exists in a circle with the diameter of the distance between the starting point and the first end point; setting a first father circle and a first end circle by taking the starting point and the first distance as radii respectively; determining a second parent circle from the child circles of the first parent circle; when the coincidence degree of the mth father circle and the first end circle is larger than a preset first threshold value, generating a first list and a second list; at the current moment, acquiring a first parameter of the vehicle, and calculating a second parameter at the next moment so as to determine a first track set; processing the first track set according to the first list and the second list; and evaluating the tracks in the processed first track set to determine a first target track, calculating the acceleration and the steering angle of the first target track, and generating a target path when the distance difference between the end point and the end point of the nth target track is smaller than a preset second threshold value. Thereby reducing the control difficulty of the bottom layer control.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a path planning method and device based on closed-loop control.
Background
With the development of artificial intelligence technology and modern manufacturing industry, the automatic driving technology has gradually advanced into the daily life of people, and the travel mode of people is changed profoundly. The unmanned technology can be briefly divided into perception, prediction, positioning, decision, planning and control. The main task of the path planning method is to plan a path which is convenient to be executed by the controller and has no collision according to the current vehicle information and the reasonable exploration environment space. The motion planning sets information such as speed, steering angle and the like of the path points on the basis of path planning, so that the path point information is more perfect.
For the path planning algorithm, besides ensuring algorithm completeness and real-time performance in a complex environment, whether the generated track is friendly to a control module is also an important judgment standard. If the track generation cannot be adapted to the vehicle model, the design of the controller is also required to be high while the control accuracy is not guaranteed.
The current path planning algorithm including motion planning is generally based on a random sampling method, an optimization method and the like.
The random sampling algorithm is a classic tree search algorithm, and the most notable algorithm is a fast expanding random tree (RRT) algorithm. The RRT algorithm expands a tree structure from a starting point to the outside, and the expanding direction of the tree structure is determined by randomly sampling points in a planning space. The method is probabilistic and suboptimal. The random sampling algorithm has the problems of path mutation and the like, and a path which accords with vehicle dynamics needs to be generated through subsequent optimization.
The optimization-based method performs path optimization by minimizing a cost function in the path generation process. The cost function typically includes obstacle distance limits, vehicle acceleration, steering wheel speed limits, terrain limits, and the like. Meanwhile, the planning of the vehicle motion signal is added in the optimization item, and the optimal path of the vehicle is approached by different methods.
The random sampling-based method has certain uncertainty inevitably existing in the path, and the randomness of the sampling points causes the fluctuation characteristic of the original path, so most random sampling-based methods need further optimization of the path, which greatly increases the time consumption of the algorithm and can not meet the real-time path planning requirement of unmanned vehicles.
The optimization-based method needs a large amount of computing resources and is difficult to compute in parallel, meanwhile, the design of the optimization items and the selection of the optimization method have high requirements, due to the complexity of the optimization method, the optimization-based planning algorithm has no determined computing time, and the optimization-based method lacks global knowledge and sometimes falls into local optimization.
In the above path planning method, the control module, i.e., the control difficulty of the bottom controller, is not considered.
Disclosure of Invention
The embodiment of the invention aims to provide a path planning method and a path planning device based on closed-loop control, which are used for solving the problem that the control difficulty of a bottom controller is not considered in path planning in the existing calculation.
In order to solve the above problem, in a first aspect, the present invention provides a path planning method based on closed-loop control, where the method includes:
acquiring a reference path of a vehicle, wherein the reference path comprises a starting point and an end point;
taking a first end point on the reference path; the first end point is located between the start point and the end point;
judging whether an obstacle exists in a circle with the distance between the starting point and the first end point as the diameter;
when a first obstacle exists, determining a first distance between the starting point and the first obstacle; the first obstacle is the obstacle closest to the starting point in the obstacles; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle;
setting a first father circle by taking the starting point as a circle center and the first distance as a radius;
setting a first end point circle by taking the first end point as a circle center and the first distance as a radius;
determining the distance between each of a plurality of circles on the circumference and the nearest barrier to the circle by taking the point on the circumference of the first father circle as the center of the circle, and generating a child distance set;
calculating the geometric distance between each of a plurality of centers of circles on the circumference and the first end point, and generating a geometric distance set;
calculating a set of heuristic values of the sub-circles corresponding to the circle centers according to the sub-distance set and the geometric distance set; the radius of the sub-circle is the difference between the distance between the circle center and the nearest barrier and the safety distance of the vehicle;
determining a child circle corresponding to the minimum heuristic value in the heuristic value set as a second parent circle;
when the coincidence degree of the mth father circle and the first end circle is larger than a preset first threshold value, generating a first list and a second list; the first list comprises circle center positions and radiuses of the first father circle to the mth father circle; the second list includes positions and radii from a sub-circle centered on the circumference of the first parent circle to a center of a sub-circle centered on the circumference of the mth parent circle; m is an integer greater than 2;
at the current moment, acquiring a first parameter of the vehicle;
calculating a second parameter of the vehicle at the next moment according to the first parameter at the current moment and the dynamic model of the vehicle;
calculating a first track set of the vehicle from the current moment to the next moment according to the first parameter and the second parameter;
processing the first track set according to the first list and the second list to generate a processed first track set;
evaluating the tracks in the first track set after processing through a heuristic value function;
determining a first target track from the processed first track set according to an evaluation result;
determining the position of a preview point on the first target track; calculating a pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point;
calculating the steering angle of a preview point according to the preview distance and a dynamic model of the vehicle;
calculating the acceleration of the vehicle at the pre-aiming point according to the expected speed of the pre-aiming point and the current speed of the vehicle;
sending the steering angle and the acceleration of the preview point of the first target track to a bottom controller, so that the bottom controller controls the vehicle at the preview point according to the steering angle and the acceleration of the preview point;
when the distance difference between the end point of the nth target track and the end point is smaller than a preset second threshold value, processing the first target track to the nth target track to generate a target path; n is an integer greater than 2.
In a possible implementation manner, the first parameter includes an x coordinate, a y coordinate, an orientation, a vehicle speed, and a steering wheel angle of the vehicle at a current time, and the calculating a second parameter of the vehicle at a next time according to the first parameter at the current time and a dynamic model of the vehicle specifically includes:
calculating a second parameter of the vehicle at the next time by the following formula:
x t+Δt ＝x t +vcosθcosβΔt
y t+Δt ＝y t +vsinθcosβΔt
θ t+Δt ＝θ t +vsinβΔt/l
v t+Δt ＝v t +aΔt
β t+Δt ＝β t +ωΔt
wherein x is t For the x coordinate, y coordinate of the vehicle at the current moment t Is the y-coordinate, theta, of the vehicle at the current time t Is the orientation of the vehicle at the present moment, v t Speed of the vehicle at the present moment, beta t The steering wheel angle of the vehicle at the current moment; x is a radical of a fluorine atom t+Δt Is the x coordinate, y of the vehicle at the next moment t+Δt Is the y-coordinate, θ, of the vehicle at the next instant t+Δt Is the orientation of the vehicle at the next moment, v t+Δt Is the speed of the vehicle at the next moment, β t+Δt The steering wheel angle for the vehicle at the next moment; and l is the vehicle wheel base.
In a possible implementation manner, the processing the first track set according to the second list to generate a processed first track set specifically includes:
and deleting the tracks of the first track outside the sub-circle in a centralized manner according to the position and the radius from the sub-circle taking the circumference of the first father circle as the center of the circle to the center of the sub-circle taking the circumference of the mth father circle as the center of the circle.
In a possible implementation manner, the evaluating, by using a heuristic function, the processed tracks in the first track set specifically includes:
calculating a heuristic value of each track in the processed first track set through f = g + h;
when the heuristic value of the track is minimum, determining the track as a first target track;
wherein f is a heuristic value of each trajectory, and g is a distance from the starting point to a position where the vehicle is located at the next moment; h comprises a circle center guide item and an end point guide item.
In one possible implementation, the formula h = l next +l 1 +l 2 ...l dist H is calculated;
wherein l next A circle center guide item which represents the distance from the position of the vehicle at the next moment to the nearest circle center, l 1 +l 2 ...l dist The vehicle navigation system is an end point guide item and represents the distance from the circle center closest to the position of the vehicle at the next moment to the next circle center, the distance from the next circle center to the next circle center, \ 823030, and the sum of the distances from the last circle center to the end point.
In a possible implementation manner, before generating the first list and the second list when the coincidence degree of the mth parent circle and the end circle is greater than a preset first threshold, the method further includes:
and when the heuristic values of all the sub-circles of a certain parent circle are equal, returning to the parent circle at the upper level of the parent circle, and deleting the position and the radius of the center of the parent circle from the first list.
In a possible implementation manner, the calculating, according to the preview distance and a dynamic model of the vehicle, a steering angle of a preview point specifically includes:
using formulas
Calculating a steering angle;
wherein, delta is a steering angle, L is a vehicle wheel base in a vehicle dynamic model, L is a vehicle rear wheel base, and L 0 And eta is the pre-aiming distance, and eta is the included angle of the vehicle relative to the direction of the pre-aiming point.
In one possible implementation, a formula is utilized
Calculating a pre-aiming distance; where v is the current speed of the vehicle.
In a possible implementation manner, the calculating the acceleration of the vehicle at the preview point according to the desired speed of the preview point and the current speed of the vehicle specifically includes:
using a formula
Calculating the acceleration of the vehicle;
where α is the acceleration, ki and Kp are empirical constants, and ν is the current speed of the vehicle.
In a second aspect, the present invention provides a vehicle control apparatus based on path planning, the apparatus comprising:
an acquisition unit configured to acquire a reference route of a vehicle, the reference route including a start point and an end point;
the setting unit is used for taking a first end point on the reference path; the first end point is located between the start point and the end point;
a determination unit configured to determine whether or not an obstacle exists in a circle having a diameter equal to a distance between the start point and the first end point;
a determining unit configured to determine, when a first obstacle exists, a first distance between the starting point and the first obstacle; the first obstacle is the obstacle closest to the starting point in the obstacles; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle;
the setting unit is further configured to set a first father circle by taking the starting point as a circle center and the first distance as a radius;
the setting unit is further configured to set a first end point circle by taking the first end point as a circle center and the first distance as a radius;
the determining unit is further configured to determine, with a point on the circumference of the first parent circle as a center, a distance between each of a plurality of circles on the circumference and an obstacle closest thereto, and generate a sub-distance set;
a calculation unit, configured to calculate a geometric distance between each of a plurality of centers of circles on the circumference and the first end point, and generate a set of geometric distances;
the calculation unit is further configured to calculate a set of heuristic values of sub-circles corresponding to the plurality of circle centers according to the set of sub-distances and the set of geometric distances; the radius of the sub-circle is the difference of the distance between the circle center and the nearest barrier minus the safety distance of the vehicle;
the determining unit is further configured to determine a child circle corresponding to a minimum heuristic value in the heuristic value set as a second parent circle;
a generating unit, configured to generate a first list and a second list when a coincidence degree of the mth parent circle and the first end circle is greater than a preset first threshold; the first list comprises circle center positions and radii of the first father circle to the mth father circle; the second list includes positions and radii from a sub-circle centered on the circumference of the first parent circle to a center of a sub-circle centered on the circumference of the mth parent circle; m is an integer greater than 2;
the obtaining unit is further used for obtaining a first parameter of the vehicle at the current moment;
the calculating unit is further used for calculating a second parameter of the vehicle at the next moment according to the first parameter of the current moment and the dynamic model of the vehicle;
the calculation unit is further used for calculating a first track set of the vehicle from the current moment to the next moment according to the first parameter and the second parameter;
the processing unit is used for processing the first track set according to the first list and the second list to generate a processed first track set;
the evaluation unit is used for evaluating the processed tracks in the first track set through a heuristic value function;
the determining unit is further used for determining a first target track from the processed first track set according to the evaluation result;
the determining unit is further used for determining the position of a pre-aiming point on the first target track; the calculation unit is further used for calculating the pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point;
the calculation unit is further used for calculating the steering angle of the preview point according to the preview distance and a dynamic model of the vehicle;
the calculation unit is further used for calculating the acceleration of the vehicle at the preview point according to the expected speed of the preview point and the current speed of the vehicle;
the transmitting unit is used for transmitting the steering angle and the acceleration of the pre-aiming point of the first target track to a bottom layer controller so that the bottom layer controller controls a vehicle at the pre-aiming point according to the steering angle and the acceleration of the pre-aiming point;
the processing unit is further used for processing the first target track to the nth target track to generate a target path when the difference between the distance between the end point of the nth target track and the end point is smaller than a preset second threshold; n is an integer greater than 2.
In a third aspect, the invention provides an apparatus comprising a memory for storing a program and a processor for performing the method of any of the first aspects.
In a fourth aspect, the invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first aspects.
In a fifth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of any one of the first aspects.
By applying the path planning method and device based on closed-loop control provided by the invention, the following technical effects are achieved:
1. a series of exploration circles are generated, which correspond to a fast space exploration that fills the available space. The heuristic track searching direction is guided by utilizing the exploration circles, so that the barrier and the end point are considered in the heuristic searching process, the space utilization rate is also considered, and the reasonability of the unmanned vehicle planning path is greatly enhanced.
2. The process of generating the path samples the acceleration of the vehicle and the rotating speed of the steering wheel, and the generated path contains information such as the coordinate, the orientation, the speed, the steering wheel angle and the like of the vehicle, so that the generated path is continuous in the coordinate and the orientation and continuous in the speed and the steering wheel angle, the generated path is more reasonable, the control difficulty of the unmanned vehicle control module is reduced, and the real-time performance is improved.
3. Horizontal and longitudinal control is considered in path planning, the real-time performance of planning is guaranteed, and the control difficulty of the bottom controller is reduced.
Drawings
Fig. 1 is a schematic flow chart of a path planning method based on closed-loop control according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a spatial search according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of heuristic track search according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating control parameters provided in accordance with an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a path planning apparatus based on closed-loop control according to a second embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 is a schematic flowchart of a path planning method based on closed-loop control according to an embodiment of the present invention. The method is applied to the field of automatic driving, the execution subject of the method is a calculation processing unit of a vehicle, the calculation processing unit can be a vehicle control unit, and as shown in fig. 1, the method comprises the following steps:
The reference path refers to a global path planned in an off-line or real-time manner by the vehicle, and the path does not consider the temporary obstacles on the road. The reference path is used for guiding a planning target of a path planning algorithm, and the vehicle can return to the set road while avoiding obstacles.
The reference path can be acquired by a method that firstly, a starting point of a journey and an end point of the journey sent by a server are received; then, calling an environment map file according to the starting point and the end point of the journey; and finally, generating a reference path according to the starting point of the travel, the end point of the travel and the environment map file.
The server may receive a start point or an end point of a trip transmitted by the user terminal, and the environment map file may be stored in the server, for example, the vehicle may transmit a request message including a current location of the vehicle to the server, and the server may transmit the environment map file including the current location, the start point, and the end point of the vehicle to the vehicle according to the current location of the vehicle. The vehicle may have an environment map file stored therein.
And the vehicle acquires a starting point and an end point of the journey from the server, and then carries out path planning according to the environment map file to generate a reference path.
Wherein, before step 101, obstacle information and a vehicle dynamics model need to be acquired.
The obstacle information is mainly obtained through the upstream nodes (such as perception, prediction and the like) to obtain the position and speed information of the obstacles, and the information is uniformly stored and sequenced according to the relative distance from the vehicle.
The vehicle dynamics model mainly includes intrinsic parameters of the vehicle, such as length and width, vehicle wheel base, minimum turning radius, acceleration limit value, safety distance, etc., which are generally defined in a configuration file.
Specifically, since the length of the reference path is generally long, in order to increase the processing speed, the reference path may be divided, for example, a point is taken on the reference path and is referred to as a first end point, and for example, a circle is made with the starting point of the reference path as a point and the diameter D as a diameter, and an intersection of the circle and the reference path may be referred to as a first end point. D is a preset length.
Specifically, since the obstacle information has been acquired before step 101 and the positions of the obstacles have also been sorted, it is possible to determine whether or not an obstacle exists in a circle having a start point and a first end point as two points on the circle, based on the result of sorting the obstacles.
And when no obstacle exists, continuously judging whether the obstacle exists in a circle taking the first end point as one point on the circle and taking the second end point as another point on the circle.
The second endpoint may be determined according to the above-described method for determining the first endpoint.
104, when a first obstacle exists, determining a first distance between a starting point and the first obstacle; the first barrier is the barrier closest to the starting point in the barriers; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle.
Specifically, the safety distance of the vehicle is already included in the vehicle dynamics model. When a plurality of obstacles are searched in a circle with a starting point and a first end point as two points on the circle, the obstacle closest to the starting point is used as a first obstacle, and the distance between the starting point and the first obstacle is calculated according to the position of the first obstacle and the position of the starting point.
Subsequently, the first distance may be calculated from the distance of the starting point from the first obstacle.
Wherein, the formula R = L can be used obs -d safety L obs Calculating a first distance, wherein R is the first distance, L obs Is the distance from the starting point to the first obstacle, d safety Is the safe distance of the vehicle.
And 105, setting a first father circle by taking the starting point as a circle center and the first distance as a radius.
And 106, setting a first endpoint circle by taking the first endpoint as a circle center and the first distance as a radius.
Specifically, referring to fig. 2, a first parent circle is generated by taking the starting point as the center of a circle and the first distance as the radius, referring to the leftmost dark circle of fig. 2, and an end point circle is generated by taking the first end point as the center of a circle and the first distance as the radius, referring to the rightmost dark circle of fig. 2.
And step 107, taking a point on the circumference of the first parent circle as a circle center, determining the distance between each of a plurality of circles on the circumference and the nearest obstacle, and generating a sub-distance set.
Specifically, on the circumference of the first parent circle, the obstacle is searched by taking a point on the circumference as the center of the circle, for example, on the circumference of the first parent circle, the positions of the centers of the circle are R1, R2 and R3, the obstacle is searched, the positions are A1, A2 and A3, the distances between R1 and A1, between R2 and A2, and between R3 and A3 are calculated, and the generated sub-distance set is { | R1-A1|, | R2-A2|, | R3-A3| }.
Of course, the location information here may be latitude and longitude information, and for ease of understanding, only the sub-distance set is simply illustrated here. The specific calculation process is not detailed.
And step 108, calculating the geometric distance between each of the circles on the circumference and the first end point, and generating a geometric distance set.
Where geometric distances include, but are not limited to, euler distances, manhattan distances, and durbin distances.
The calculation of each specific geometric distance belongs to the prior art, and is not described in the present application.
Specifically, by the formula f = d end -R calculating heuristic values of a plurality of sub-circles corresponding to the center of the circle;
wherein d is end The geometric distance from the center of the circle to the first end point is shown, and R is the radius of the sub-circle.
And step 110, determining the child circle corresponding to the minimum heuristic value in the heuristic value set as a second parent circle.
Specifically, through the above calculation, assuming that the heuristic value of R2 is the smallest among the sub-circles corresponding to R1, R2, and R3, R2 can be regarded as the second parent circle.
Subsequently, steps 107 to 110 may be repeated until the mth parent circle is searched. Wherein m is an integer greater than 2.
Specifically, the overlapping ratio here may be an overlapping area of two circles. When the overlapping area of the mth parent circle and the first end circle is greater than a preset first threshold, it may be determined that the search from the start point to the first end point ends.
Subsequently, steps 102 to 111 may be continued until the reference path is searched. This process may be referred to as spatial exploration.
At the current time, a first parameter of the vehicle is obtained, step 112.
Specifically, the steering wheel angle and the acceleration under the current state are sampled within the current maximum steering wheel angle and the current maximum driving acceleration range of the vehicle. I.e. vehicle speed (calculated from acceleration) and steering wheel angle in the following first parameters. .
The first parameters comprise an x coordinate, a y coordinate, a direction, a vehicle speed and a steering wheel angle of the vehicle at the current moment. The second parameters include the vehicle's x-coordinate, y-coordinate, heading, vehicle speed, steering wheel angle at the next time.
And 113, calculating a second parameter of the vehicle at the next moment according to the first parameter at the current moment and the vehicle dynamic model.
Wherein, step 113 specifically includes: calculating a second parameter of the vehicle at the next time by the following formula:
x t+Δt ＝x t +vcosθcosβΔt
y t+Δt ＝y t +vsinθcosβΔt
θ t+Δt ＝θ t +vsinβΔt/l
v t+Δt ＝v t +aΔt
β t+Δt ＝β t +ωΔt
wherein x is t The x coordinate and y coordinate of the vehicle at the current moment t Is the y-coordinate, theta, of the vehicle at the current time t Is the orientation of the vehicle at the present moment, v t Speed of the vehicle at the present moment, beta t The steering wheel angle of the vehicle at the current moment; x is the number of t+Δt Is the x coordinate, y of the vehicle at the next moment t+Δt Is the y-coordinate, theta, of the vehicle at the next instant t+Δt Is the orientation of the vehicle at the next moment, v t+Δt Is the speed of the vehicle at the next moment, beta t+Δt The steering wheel angle of the vehicle at the next moment, l being the vehicle axisDistance. The vehicle wheel base belongs to one of the parameters in the vehicle dynamic model, so when the parameter of the next moment is calculated, the dynamic model parameter of the vehicle is considered, and the vehicle dynamic constraint is met.
And step 114, calculating a first track set of the vehicle from the current time to the next time according to the first parameter and the second parameter.
Specifically, the trajectory of the vehicle from the current time to the next time may be calculated through a model to obtain a first trajectory set, see fig. 3, where a first circle from the left in fig. 3 is a first parent circle, a second circle is a child circle of the first parent circle (where the first parent circle is called the second parent circle when the heuristic value of the child circle of the first parent circle is minimum), a third circle is a child circle of the second parent circle (where the second parent circle is called the third parent circle when the heuristic value of the child circle of the second parent circle is minimum), and the first trajectory set from the current time to the next time includes a dashed line 11, a dashed line 12, a dashed line 13, a solid line 14, and a dashed line 15.
When the vehicle travels to the next time, the second set of trajectories between the next time to the next time includes dashed line 21, dashed line 22, solid line 23, dashed line 24, dashed line 25. The method for determining the second track set from the next time to the next time is the same as the method for calculating the first track set from the current time to the next time, and is not repeated here.
And step 115, processing the first track set according to the first list and the second list to generate a processed first track set.
Specifically, the tracks of the first track set outside the sub-circle are deleted according to the positions and the radii of the first parent circle to the mth parent circle, and the positions and the radii of the centers of the sub-circle from the circumference of the first parent circle to the sub-circle from the circumference of the mth parent circle.
With continued reference to fig. 3, in fig. 3, from the left, of the broken lines and the solid lines between the first circle and the second circle, the broken lines 11 and 15 are beyond the range of the first circle and the second circle, and therefore, the broken lines 11 and 15 in the first trajectory set are deleted, and the processed first trajectory set includes the broken line 12, the broken line 13, and the solid line 14.
In the second set of tracks, the dashed lines 24 and 25 are beyond the second and third circles, and therefore, the dashed lines 24 and 25 in the second set of tracks are deleted and the processed second set of tracks includes 21, 22 and 23.
And step 116, evaluating the tracks in the processed first track set through a heuristic function.
Specifically, calculating a heuristic value of each track in the processed first track set through f = g + h;
and when the heuristic value of the track is minimum, determining the track as a first target track.
Wherein f is a heuristic value of each trajectory, and g is a distance from the starting point to a position where the vehicle is located at the next moment; h comprises a circle center guide item and an end point guide item;
by the formula h = l next +l 1 +l 2 ...l dist H is calculated;
wherein l next A circle center guide item which represents the distance from the position of the vehicle at the next moment to the nearest circle center, l 1 +l 2 ...l dist The vehicle navigation system is an end point guide item and represents the distance from the circle center closest to the position of the vehicle at the next moment to the next circle center, the distance from the next circle center to the next circle center, \ 823030, and the sum of the distances from the last circle center to the end point.
After the first target trajectory is calculated, the next time is taken as a start time and the next time is taken as an end time, and the steps 112 to 117 are repeated to determine a second target trajectory. This process may be referred to as heuristic track searching.
For example, in fig. 3, it is calculated that the heuristic value of 14 is the smallest in the first trajectory set, and the heuristic value of 23 is the smallest in the second trajectory set, so that 14 can be determined as the first target trajectory and 23 can be determined as the second target trajectory.
The location of the preview point is determined on the first target track, step 118.
Specifically, in order to ensure that the track meets the control requirements and reduce the lower-layer control difficulty, the control of the vehicle can be realized by calculating the steering angle and the acceleration of the preview point.
The pre-aiming point is the position which the controller considers that the vehicle needs to track and arrive at present, and the pre-aiming distance is the distance from the vehicle to the pre-aiming point at present. The pre-aiming distance is mainly used for ensuring the robustness of track tracking in control and preventing the tracking effect from shaking due to a local path.
And step 119, calculating the pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point.
Wherein can be based on
Calculating a pre-aiming distance; where v is the current speed of the vehicle.
Specifically, in the target path, a plurality of waypoints are included, each waypoint including a desired speed for the waypoint.
FIG. 4 is a schematic diagram of control parameters provided in an embodiment of the invention, and referring to FIG. 4, it can be seen that the pre-aiming distance L 0 。
And step 120, calculating the steering angle of the preview point according to the preview distance and the dynamic model of the vehicle.
Specifically, using the formula
Calculating a steering angle;
wherein, delta is a steering angle, L is a vehicle wheel base in a vehicle dynamic model, L is a vehicle rear wheel base, namely the distance between a vehicle turning center point and a rear axle center point, and L is 0 And eta is the pre-aiming distance, and eta is the included angle of the vehicle relative to the direction of the pre-aiming point. A schematic of which is shown in figure 4. Through this angle of turning to, can guarantee the horizontal control accuracy of planning the route.
And step 121, calculating the acceleration of the vehicle at the preview point according to the expected speed of the preview point and the current speed of the vehicle.
In particular, the desired velocity of the home point on the first target trajectory is already included in the first target trajectory as it is planned.
Can utilize formulas
Calculating the acceleration of the vehicle at the pre-aiming point;
wherein, alpha is acceleration, ki and Kp are proportional and integral control quantity, are empirical constants, and are set according to the debugging effect and the empirical value; ν is the current speed of the vehicle. By this acceleration, the control accuracy of the longitudinal speed of the planned path can be ensured.
It is understood that Ki and Kp may be controlled by other control methods, which are exemplified and not limited, and may be controlled by proportional control, proportional differential control, etc.
And step 122, sending the steering angle and the acceleration of the preview point of the first target track to a bottom controller, so that the bottom controller controls the vehicle at the preview point according to the steering angle and the acceleration of the preview point.
Specifically, path planning and control are completely separated, the path planning is performed by the vehicle control unit, and the control is performed by the underlying controller. The path planning only outputs a track containing the expected speed, and how to track the track is completely determined by the control module. According to the method and the device, the recommended values of the bottom output control quantity, namely the acceleration a and the steering angle, are provided for the reference of the bottom controller, so that the control precision of the bottom controller can be improved.
And continuing to execute the steps 112 to 122, so that the steering angle and the acceleration of the sighting point on each target track can be calculated, and then the steering angle and the acceleration of the sighting point on each target track are sent to the underlying controller, so that the control accuracy of the underlying controller is improved.
And 123, processing the first target track to the nth target track to generate a target path when the difference between the distances between the end point and the end point of the nth target track is smaller than a preset second threshold.
Continuing to take fig. 3 as an example, in fig. 3, after calculation, the first target track is determined to be 14, the second target track is determined to be 23, 14 and 23 are spliced, and if other nth target tracks exist subsequently, the splicing is continued to obtain the target track. Wherein n is an integer greater than 2.
Specifically, step 118 includes: splicing the first target track to the nth target track to generate an original target path;
and when the original target path does not meet the vehicle kinematic constraint, performing smoothing processing to generate a target path.
The vehicle dynamics model comprises a minimum turning radius, when a plurality of target tracks are spliced, the curvature of the spliced part is calculated, the curvature is compared with the reciprocal of the minimum turning radius of the vehicle, when the curvature is not more than the reciprocal of the minimum turning radius, the curvature meets the requirement, and when the curvature is more than the reciprocal of the minimum turning radius, the smoothing processing is carried out. By way of example and not limitation, the smoothing may be performed according to a mean filtering manner.
Further, before step 111, the method further includes:
and when the heuristic values of all the child circles of a certain parent circle are equal, returning to the parent circle at the upper level of the parent circle, and deleting the position and the radius of the center of the parent circle from the first list.
Therefore, the path planning method based on the closed-loop control provided by the invention has the following advantages:
1. a series of search circles are generated, which correspond to a fast space search that fills the available space. The heuristic track searching direction is guided by utilizing the exploration circles, so that the barrier and the end point are considered in the heuristic searching process, the space utilization rate is also considered, and the reasonability of the unmanned vehicle planning path is greatly enhanced.
2. The process of generating the path samples the acceleration of the vehicle and the rotating speed of the steering wheel, and the generated path contains information such as coordinates, orientation, speed, steering wheel rotation angle and the like of the vehicle, so that the generated path is continuous in coordinates and orientation and continuous in speed and steering wheel rotation angle, the generated path is more reasonable, the control difficulty of the unmanned vehicle control module is reduced, and the real-time performance is improved.
3. Horizontal and longitudinal control is considered in path planning, and the control difficulty of the bottom controller is reduced.
The embodiment of the invention provides a path planning device based on closed-loop control. Fig. 5 is a schematic structural diagram of a path planning apparatus based on closed-loop control according to a second embodiment of the present invention. As shown in fig. 5, the path planning apparatus includes: an acquisition unit 501, a setting unit 502, a judgment unit 503, a determination unit 504, a calculation unit 505, a generation unit 506, a processing unit 507, an evaluation unit 508, and a transmission unit 509.
The acquisition unit 501 is configured to acquire a reference route of a vehicle, where the reference route includes a start point and an end point;
the setting unit 502 is configured to take a first end point on the reference path; the first end point is positioned between the starting point and the end point;
the judgment unit 503 is configured to judge whether an obstacle exists in a circle having a diameter equal to a distance between the start point and the first end point;
the determining unit 504 is configured to determine, when a first obstacle exists, a first distance between the starting point and the first obstacle; the first barrier is the barrier which is closest to the starting point in the barriers; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle;
the setting unit 502 is further configured to set a first father circle by taking the starting point as a center of a circle and taking the first distance as a radius;
the setting unit 502 is further configured to set a first endpoint circle by taking the first endpoint as a circle center and the first distance as a radius;
the determining unit 504 is further configured to determine, with a point on the circumference of the first parent circle as a center, a distance between each of a plurality of circles on the circumference and the nearest obstacle to the center, and generate a sub-distance set;
the calculating unit 505 is configured to calculate a geometric distance between each of a plurality of centers of circles on the circumference and the first end point, and generate a set of geometric distances;
the calculating unit 505 is further configured to calculate a set of heuristic values of sub-circles corresponding to the plurality of circle centers according to the set of sub-distances and the set of geometric distances; the radius of the sub-circle is the difference of the distance between the circle center and the nearest barrier minus the safety distance of the vehicle;
the determining unit 504 is further configured to determine a child circle corresponding to the minimum heuristic value in the heuristic value set as a second parent circle;
the generating unit 506 is configured to generate a first list and a second list when the overlap ratio of the mth parent circle and the first end circle is greater than a preset first threshold; the first list comprises circle center positions and radiuses of the first father circle to the mth father circle; the second list includes positions and radii of centers of sub-circles having the circumference of the first parent circle as the center of a circle to the center of a circle in the sub-circle having the circumference of the mth parent circle as the center of a circle; m is an integer greater than 2;
the obtaining unit 501 is further configured to obtain a first parameter of the vehicle at the starting point at the current time;
the calculating unit 505 is further configured to calculate a second parameter of the vehicle at a next time according to the first parameter at the current time and the dynamic model of the vehicle;
the calculating unit 505 is further configured to calculate a first trajectory set of the vehicle from the current time to the next time according to the first parameter and the second parameter;
the processing unit 507 is configured to process the first trajectory set according to the first list and the second list, and generate a processed first trajectory set;
the evaluation unit 508 is configured to evaluate the tracks in the processed first track set through a heuristic value function;
the determining unit 504 is further configured to determine a first target trajectory from the processed first trajectory set according to the evaluation result;
the determining unit is further used for determining the position of a pre-aiming point on the first target track;
the calculating unit 505 is further configured to calculate a pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point;
the calculation unit 505 is further configured to calculate a steering angle of the preview point according to the preview distance and a dynamic model of the vehicle;
the calculating unit 505 is further configured to calculate an acceleration of the vehicle at the pre-aiming point according to the expected speed of the waypoint on the first target trajectory and the current speed of the vehicle;
the sending unit 509 is configured to send the steering angle and the acceleration of the home point of the first target trajectory to the underlying controller, so that the underlying controller controls the vehicle at the home point according to the steering angle and the acceleration of the home point.
The processing unit 507 is further configured to, when a difference between distances from an end point to an end point of the nth target track is smaller than a preset second threshold, process the first target track to the nth target track to generate a target path; n is an integer greater than 2.
The specific functions of each module in fig. 5 are the same as those described in the first embodiment, and are not described again here. It is understood that the technical effect of the second embodiment is also the same as that of the first embodiment, and is not described herein again.
The third embodiment of the invention provides equipment, which comprises a memory and a processor, wherein the memory is used for storing programs, and the memory can be connected with the processor through a bus. The memory may be a non-volatile memory, such as a hard disk drive and a flash memory, in which a software program and a device driver are stored. The software program is capable of performing various functions of the above-described methods provided by embodiments of the present invention; the device drivers may be network and interface drivers. The processor is used for executing a software program, and the software program can realize the method provided by the first embodiment of the invention when being executed.
A fourth embodiment of the present invention provides a computer program product including instructions, which, when the computer program product runs on a computer, causes the computer to execute the method provided in the first embodiment of the present invention.
Fifth embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the method provided in the first embodiment of the present invention.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above embodiments are only examples of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for path planning based on closed-loop control, the method comprising:
acquiring a reference path of a vehicle, wherein the reference path comprises a starting point and an end point;
taking a first end point on the reference path; the first end point is located between the start point and the end point;
judging whether an obstacle exists in a circle with the diameter of the distance between the starting point and the first end point;
when a first obstacle exists, determining a first distance between the starting point and the first obstacle; the first barrier is the barrier which is closest to the starting point in the barriers; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle;
setting a first father circle by taking the starting point as a circle center and the first distance as a radius;
setting a first end point circle by taking the first end point as a circle center and the first distance as a radius;
determining the distance between each of a plurality of circles on the circumference and the nearest barrier to the circle by taking the point on the circumference of the first father circle as the center of the circle, and generating a child distance set;
calculating the geometric distance between each of a plurality of centers of circles on the circumference and the first end point, and generating a geometric distance set;
calculating a set of heuristic values of the sub-circles corresponding to the circle centers according to the sub-distance set and the geometric distance set; the radius of the sub-circle is the difference of the distance between the circle center and the nearest barrier minus the safety distance of the vehicle;
determining a child circle corresponding to the minimum heuristic value in the heuristic value set as a second parent circle;
when the coincidence degree of the mth father circle and the first end circle is larger than a preset first threshold value, generating a first list and a second list; the first list comprises circle center positions and radii of the first father circle to the mth father circle; the second list includes positions and radii from a sub-circle centered on the circumference of the first parent circle to a center of a sub-circle centered on the circumference of the mth parent circle; m is an integer greater than 2;
at the current moment, acquiring a first parameter of the vehicle;
calculating a second parameter of the vehicle at the next moment according to the first parameter at the current moment and the dynamic model of the vehicle;
calculating a first track set of the vehicle from the current moment to the next moment according to the first parameter and the second parameter;
processing the first track set according to the first list and the second list to generate a processed first track set;
evaluating the tracks in the first track set after processing through a heuristic value function;
determining a first target track from the processed first track set according to an evaluation result;
determining the position of a pre-aiming point on the first target track;
calculating a pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point;
calculating the steering angle of a preview point according to the preview distance and a dynamic model of the vehicle;
calculating the acceleration of the vehicle at the preview point according to the expected speed of the preview point and the current speed of the vehicle;
sending the steering angle and the acceleration of the preview point of the first target track to a bottom controller, so that the bottom controller controls the vehicle at the preview point according to the steering angle and the acceleration of the preview point;
when the distance difference between the end point of the nth target track and the end point is smaller than a preset second threshold value, processing the first target track to the nth target track to generate a target path; n is an integer greater than 2.
2. The method according to claim 1, wherein the first parameters comprise an x-coordinate, a y-coordinate, an orientation, a vehicle speed, a steering wheel angle of the vehicle at a current time, and wherein calculating a second parameter of the vehicle at a next time based on the first parameters at the current time and a dynamic model of the vehicle comprises:
calculating a second parameter of the vehicle at the next time by the following formula:
x t+Δt ＝x t +v t ·cosθ t ·cosβ t ·Δt
y t+Δt ＝y t +v t ·sinθ t ·cosβ t ·Δt
θ t+Δt ＝θ t +v t ·sinβ t ·Δt/l
v t+Δt ＝v t +a·Δt
β t+Δt ＝β t +ω·Δt
wherein x is t The x coordinate and y coordinate of the vehicle at the current moment t Is the y-coordinate, theta, of the vehicle at the current time t Is the orientation of the vehicle at the present moment, v t Speed of the vehicle at the present moment, beta t The steering wheel angle of the vehicle at the current moment; x is a radical of a fluorine atom t+Δt Is the x coordinate, y of the vehicle at the next moment t+Δt Is the y-coordinate, theta, of the vehicle at the next instant t+Δt Is the orientation of the vehicle at the next moment, v t+Δt Is the speed of the vehicle at the next moment, beta t+Δt The steering wheel angle for the vehicle at the next moment; and l is the vehicle wheel base.
3. The method according to claim 1, wherein the processing the first trajectory set according to the second list to generate a processed first trajectory set specifically includes:
and deleting the tracks of the first track outside the sub-circle in a centralized manner according to the position and the radius from the sub-circle taking the circumference of the first father circle as the center of the circle to the center of the sub-circle taking the circumference of the mth father circle as the center of the circle.
4. The method according to claim 1, wherein the evaluating the processed trajectories in the first trajectory set by a heuristic function specifically comprises:
calculating a heuristic value of each track in the processed first track set through f = g + h;
when the heuristic value of the track is minimum, determining the track as a first target track;
wherein f is a heuristic value of each trajectory, and g is a distance from the starting point to a position where the vehicle is located at the next moment; h comprises a circle center guide item and an end point guide item.
5. Method according to claim 4, characterized in that, by the formula h = l next +l 1 +l 2 ...l dist H is calculated;
wherein l next As a circle center guide item, representDistance from the vehicle's position at the next moment to the nearest center of circle, l 1 +l 2 ...l dist The vehicle navigation system is an end point guide item and represents the distance from the circle center closest to the position of the vehicle at the next moment to the next circle center, the distance from the next circle center to the next circle center, \ 823030, and the sum of the distances from the last circle center to the end point.
6. The method according to claim 1, wherein before generating the first list and the second list when the coincidence degree of the mth parent circle and the end circle is greater than a preset first threshold, the method further comprises:
and when the heuristic values of all the sub-circles of a certain parent circle are equal, returning to the parent circle at the upper level of the parent circle, and deleting the position and the radius of the center of the parent circle from the first list.
7. The method according to claim 1, wherein said calculating a steering angle of a preview point based on said preview distance and a dynamic model of the vehicle comprises in particular:
using formulas
Calculating a steering angle;
wherein, delta is a steering angle, L is a vehicle wheel base in a vehicle dynamic model, L is the vehicle wheel base, and L is 0 And eta is the pre-aiming distance, and is the included angle of the vehicle relative to the direction of the pre-aiming point.
8. The method of claim 7, wherein a formula is utilized
Calculating a pre-aiming distance; where v is the current speed of the vehicle.
9. The method of claim 1, wherein calculating the acceleration of the vehicle at the preview point based on the desired velocity of the preview point and the current velocity of the vehicle specifically comprises:
using formulas
Calculating the acceleration of the vehicle;
wherein α is acceleration, K i And K p As an empirical constant, ν is the current speed of the vehicle.
10. A path planning apparatus based on closed-loop control, the apparatus comprising:
an acquisition unit configured to acquire a reference path of a vehicle, the reference path including a start point and an end point;
the setting unit is used for taking a first end point on the reference path; the first end point is located between the start point and the end point;
a determination unit configured to determine whether or not an obstacle exists in a circle having a diameter equal to a distance between the start point and the first end point;
a determining unit configured to determine, when a first obstacle exists, a first distance between the starting point and the first obstacle; the first barrier is the barrier which is closest to the starting point in the barriers; the first distance is the difference of the distance between the starting point and the first obstacle minus the safety distance of the vehicle;
the setting unit is further configured to set a first father circle by taking the starting point as a circle center and the first distance as a radius;
the setting unit is further used for setting a first end point circle by taking the first end point as a circle center and the first distance as a radius;
the determining unit is further configured to determine, with a point on the circumference of the first parent circle as a center, a distance between each of a plurality of circles on the circumference and a nearest obstacle to the center, and generate a child distance set;
a calculation unit, configured to calculate a geometric distance between each of a plurality of centers of circles on the circumference and the first end point, and generate a geometric distance set;
the calculation unit is further configured to calculate a set of heuristic values of sub-circles corresponding to the plurality of circle centers according to the set of sub-distances and the set of geometric distances; the radius of the sub-circle is the difference of the distance between the circle center and the nearest barrier minus the safety distance of the vehicle;
the determining unit is further configured to determine a child circle corresponding to a minimum heuristic value in the heuristic value set as a second parent circle;
the generating unit is used for generating a first list and a second list when the coincidence degree of the mth father circle and the first end circle is larger than a preset first threshold; the first list comprises circle center positions and radiuses of the first father circle to the mth father circle; the second list includes positions and radii from a sub-circle centered on the circumference of the first parent circle to a center of a sub-circle centered on the circumference of the mth parent circle; m is an integer greater than 2;
the obtaining unit is further used for obtaining a first parameter of the vehicle at the current moment;
the calculation unit is further used for calculating a second parameter of the vehicle at the next moment according to the first parameter at the current moment and the dynamic model of the vehicle;
the calculation unit is further used for calculating a first track set of the vehicle from the current moment to the next moment according to the first parameter and the second parameter;
the processing unit is used for processing the first track set according to the first list and the second list to generate a processed first track set;
the evaluation unit is used for evaluating the processed tracks in the first track set through a heuristic value function;
the determining unit is further used for determining a first target track from the processed first track set according to the evaluation result;
the determining unit is further used for determining the position of a pre-aiming point on the first target track; the calculation unit is further used for calculating the pre-aiming distance according to the current speed of the vehicle and the position of the pre-aiming point;
the calculation unit is also used for calculating the steering angle of the preview point according to the preview distance and a dynamic model of the vehicle;
the calculation unit is also used for calculating the acceleration of the vehicle at the pre-aiming point according to the expected speed of the pre-aiming point and the current speed of the vehicle;
the transmitting unit is used for transmitting the steering angle and the acceleration of the pre-aiming point of the first target track to the underlying controller so that the underlying controller controls the vehicle at the pre-aiming point according to the steering angle and the acceleration of the pre-aiming point;
the processing unit is further used for processing the first target track to the nth target track to generate a target path when the difference between the distance between the end point of the nth target track and the end point is smaller than a preset second threshold; n is an integer greater than 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201621.9A CN109900289B (en) | 2019-03-18 | 2019-03-18 | Path planning method and device based on closed-loop control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201621.9A CN109900289B (en) | 2019-03-18 | 2019-03-18 | Path planning method and device based on closed-loop control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109900289A CN109900289A (en) | 2019-06-18 |
| CN109900289B true CN109900289B (en) | 2023-02-10 |
Family
ID=66952681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910201621.9A Active CN109900289B (en) | 2019-03-18 | 2019-03-18 | Path planning method and device based on closed-loop control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109900289B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113805578A (en) * | 2021-02-25 | 2021-12-17 | 京东鲲鹏(江苏)科技有限公司 | Unmanned vehicle path optimization method and related equipment |
| CN112880700B (en) * | 2021-02-26 | 2024-04-16 | 北京智行者科技股份有限公司 | Local path planning method and device for in-situ steering vehicle |
| CN113009918B (en) * | 2021-03-09 | 2023-12-05 | 京东鲲鹏(江苏)科技有限公司 | Path planning method, device, system and readable storage medium |
| CN113034504B (en) * | 2021-04-25 | 2022-06-03 | 重庆大学 | Plane feature fusion method in SLAM mapping process |
| CN114184203B (en) * | 2021-11-08 | 2023-12-19 | 重庆兰德适普信息科技有限公司 | Path planning method, electronic equipment and mobile device |
| CN114265412B (en) * | 2021-12-29 | 2023-10-24 | 深圳创维数字技术有限公司 | Vehicle control method, device, equipment and computer readable storage medium |
| CN114536328B (en) * | 2022-01-26 | 2024-02-06 | 中国科学院合肥物质科学研究院 | Mechanical arm motion planning method based on improved RRT algorithm |
| CN114924575B (en) * | 2022-07-21 | 2022-09-23 | 北京建筑大学 | Mobile robot path planning method and device, electronic equipment and storage medium |
| CN117311369B (en) * | 2023-11-29 | 2024-02-09 | 江苏伊凡诺尔智能科技有限公司 | Multi-scene intelligent robot inspection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101358855A (en) * | 2008-09-23 | 2009-02-04 | 光庭导航数据（武汉）有限公司 | Navigation head based on layering bidirectional heuristic route planning method |
| CN105717929A (en) * | 2016-04-29 | 2016-06-29 | 中国人民解放军国防科学技术大学 | Planning method for mixed path of mobile robot under multi-resolution barrier environment |
| CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
| CN106970648A (en) * | 2017-04-19 | 2017-07-21 | 北京航空航天大学 | Unmanned plane multi-goal path plans combined method for searching under the environment of city low latitude |
| WO2018227387A1 (en) * | 2017-06-13 | 2018-12-20 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for route planning |
| CN109269518A (en) * | 2018-08-31 | 2019-01-25 | 北京航空航天大学 | A kind of movable fixture confined space path generating method based on intelligent body |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106740868B (en) * | 2016-12-30 | 2019-03-29 | 东软集团股份有限公司 | A kind of method, apparatus and equipment of speed planning |
-
2019
- 2019-03-18 CN CN201910201621.9A patent/CN109900289B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101358855A (en) * | 2008-09-23 | 2009-02-04 | 光庭导航数据（武汉）有限公司 | Navigation head based on layering bidirectional heuristic route planning method |
| CN105717929A (en) * | 2016-04-29 | 2016-06-29 | 中国人民解放军国防科学技术大学 | Planning method for mixed path of mobile robot under multi-resolution barrier environment |
| CN106275066A (en) * | 2016-08-30 | 2017-01-04 | 北京智行者科技有限公司 | The rotating direction control method of a kind of intelligent vehicle and device |
| CN106970648A (en) * | 2017-04-19 | 2017-07-21 | 北京航空航天大学 | Unmanned plane multi-goal path plans combined method for searching under the environment of city low latitude |
| WO2018227387A1 (en) * | 2017-06-13 | 2018-12-20 | Beijing Didi Infinity Technology And Development Co., Ltd. | Methods and systems for route planning |
| CN109269518A (en) * | 2018-08-31 | 2019-01-25 | 北京航空航天大学 | A kind of movable fixture confined space path generating method based on intelligent body |
Non-Patent Citations (1)
| Title |
|---|
| 局部网格生成中初始探索圆半径的搜索算法;樊祥阔等;《计算力学学报》;20080430;第25卷(第2期);第188-193页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109900289A (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109900289B (en) | Path planning method and device based on closed-loop control | |
| CN109916421B (en) | Path planning method and device | |
| US10948919B2 (en) | Dynamic programming and gradient descent based decision and planning for autonomous driving vehicles | |
| US10754339B2 (en) | Dynamic programming and quadratic programming based decision and planning for autonomous driving vehicles | |
| US10800408B2 (en) | Determining driving paths for autonomous driving that avoid moving obstacles | |
| US10754341B2 (en) | Systems and methods for accelerated curve projection | |
| US10775801B2 (en) | Determining speeds along a path for autonomous driving vehicles | |
| US10823575B2 (en) | Reference line smoothing method using piecewise spiral curves with weighted geometry costs | |
| CN109955853B (en) | Method, system and storage medium for operating an autonomous vehicle | |
| US20190235516A1 (en) | Path and speed optimization fallback mechanism for autonomous vehicles | |
| EP3327530B1 (en) | Method for determining command delays of autonomous vehicles | |
| US11199847B2 (en) | Curvature corrected path sampling system for autonomous driving vehicles | |
| US11055540B2 (en) | Method for determining anchor boxes for training neural network object detection models for autonomous driving | |
| CN109489675A (en) | The path planning based on cost for automatic driving vehicle | |
| US11099017B2 (en) | Determining driving paths for autonomous driving vehicles based on offset points | |
| US11586209B2 (en) | Differential dynamic programming (DDP) based planning architecture for autonomous driving vehicles | |
| US11467584B2 (en) | Multi-layer grid based open space planner | |
| CN108340915A (en) | Controller of vehicle | |
| US20200310446A1 (en) | Soft-boundary based path optimization for complex scenes for autonomous driving vehicles | |
| US10753753B2 (en) | Vehicle route navigation | |
| JP6507841B2 (en) | Preceding vehicle estimation device and program | |
| JP2023523350A (en) | Vehicle-based data processing method, data processing apparatus, computer apparatus, and computer program | |
| Park et al. | Path generation algorithm based on crash point prediction for lane changing of autonomous vehicles | |
| WO2023129890A1 (en) | Integrated trajectory forecasting, error estimation, and vehicle handling when detecting an observed scenario | |
| CN115583254A (en) | Path planning method, device and equipment and automatic driving vehicle |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant before: Beijing Idriverplus Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |