CN110954122B - Automatic driving track generation method under high-speed scene - Google Patents
Automatic driving track generation method under high-speed scene Download PDFInfo
- Publication number
- CN110954122B CN110954122B CN201911249603.4A CN201911249603A CN110954122B CN 110954122 B CN110954122 B CN 110954122B CN 201911249603 A CN201911249603 A CN 201911249603A CN 110954122 B CN110954122 B CN 110954122B
- Authority
- CN
- China
- Prior art keywords
- point
- vehicle
- end point
- track
- sampling
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Abstract
The invention relates to an automatic driving track generation method in a high-speed scene, which comprises the following steps: constructing a two-dimensional coordinate system; acquiring original road data and original vehicle state data; obtaining optimal path data; obtaining a plurality of sampling points; generating a candidate track; calculating cost values among all sampling points; screening out and outputting the optimal path data; and obtaining a target track, and outputting the target track to a control system for execution. The invention adopts a three-order Bezier curve, so that the unmanned vehicle can reach a target point along a smooth track when changing lanes, and the curvature of the curve is continuous; aiming at a high-speed automatic driving scene, a Dijkstra algorithm is correspondingly improved, on the basis of finding a shortest path, the calculated amount is greatly reduced, the real-time requirement under a high-speed state is met, and the result is continuous; constraining the vehicle motion through a Cost function model to obtain an optimal solution; the road and motion model is established after the constraint in the actual motion of the vehicle is considered, and the practical application requirements are better met.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to an automatic driving track generation method in a high-speed scene.
Background
The unmanned vehicle decision planning system serves as a vehicle center brain, outputs driving behavior instructions through a decision layer after receiving environment perception information, and then performs trajectory planning. The trajectory plan generates a series of trajectory curves from the current state to the next target state. The trajectory needs to meet the motion and dynamic constraints of the vehicle to avoid collisions with obstacles in a real urban environment.
Currently, mainstream trajectory generation methods are classified into two categories: the first type is a method based on curve interpolation, such as straight lines and circle segments, polynomial curves, clothoids, spline curves, etc., which directly generates a target trajectory mainly by determining parameters. The method has the advantages of intuition, simplicity and easy imagination, but has obvious defects:
1. the straight line and the circular arc section are simple to realize and low in calculation amount, but have discontinuous curvature and are connected with node segments;
2. the polynomial curve has the advantages of low calculation amount and continuous curvature, but the curvature needs more than four orders continuously, and the determination of key parameters is difficult;
3. the clothoid is suitable for local planning, but integration causes time consumption, curvature is continuous but not smooth, and track points are relied on;
4. spline curves also have the advantage of low computation, curvature continuity, but the result may not be an optimal solution.
The second category is a search method based on sampling, such as an improved Dijkstra algorithm, an a-x algorithm, an artificial potential field method and the like, to solve the problem of trajectory planning. This class of methods solves the 4 drawbacks of the previous class of methods, but inevitably brings about some additional drawbacks:
1. although the improved Dijkstra algorithm is suitable for finding the shortest path in a structured environment, the improved Dijkstra algorithm does not meet the real-time requirement due to large calculated amount when used alone, and the result is discontinuous;
2. the advantage of the a-algorithm is heuristic and can obtain the global optimal trajectory faster, however, the search step size is difficult to determine, and the efficiency is low in a complex and wide planning environment.
Currently, there are also a few researches on the improved technologies of the above two types of track generation methods, for example, the application publication No. CN109101017A entitled method for planning a track-finding route of an unmanned vehicle and an invention application of a terminal, which disclose the following steps: the method comprises the following steps: acquiring coordinates of all target tracing points to form a target tracing point set; step two: acquiring the current position of the unmanned vehicle, and adding the current position of the unmanned vehicle into the target tracing point set; step three: and taking the current position of the unmanned vehicle as a tracing starting point, and automatically planning a tracing route which meets the preset requirement and passes through all tracing points in the tracing point set. The method seems to solve the problems, but the theoretical basis is that the unmanned vehicle is simplified into one point to establish a road and motion model, so that the defect that vehicle posture information is ignored, and meanwhile, the behavior instruction of a decision planning layer is not taken into consideration is caused, so that the unmanned vehicle based on the trajectory planning method of the method has simple functions, and meanwhile, the vehicle cannot be effectively controlled under complex working conditions.
Disclosure of Invention
Aiming at the problems, the invention provides an automatic driving track generation method under a high-speed scene, so that an unmanned vehicle can reach a target point along a smooth track when changing lanes, and the curvature of a curve is continuous; on the basis of finding the shortest path in a structured environment, the calculation amount is greatly reduced, the real-time requirement in a high-speed state is met, and the result is continuous; obtaining an optimal solution; the road and motion model is established after the constraint in the actual motion of the vehicle is considered, and the practical application requirements are better met.
In order to achieve the purpose of the invention, the technical scheme provided by the invention is as follows:
the automatic driving track generation method under the high-speed scene comprises an improved Dijkstra algorithm and is characterized in that: the method comprises the following steps:
s100, constructing a two-dimensional coordinate system, and expressing the position of the vehicle in the two-dimensional coordinate system by (x, y); marking the current position of the vehicle as a start point, and marking the target position of the vehicle as an end point;
s200, acquiring original road data and original vehicle state data;
s300, processing according to the original road data and the original vehicle state data to obtain optimal path data; the method specifically comprises the following steps:
s310, selecting a corresponding sampling template from a plurality of preset sampling templates according to original road data and original vehicle state data, and then importing the original road data and the original vehicle state data into the sampling templates to obtain a plurality of sampling points; packing all sampling points into a sampling point set;
s320, generating a plurality of candidate tracks according to the sampling point set and the sampling template; the candidate tracks are composed of sampling points;
s330, calculating cost values among all sampling points one by one; the cost value is calculated as follows:
Cost(pi,pj)＝K1×Dist(pi,pj)+K2×Head(pi,pj)
among them, Cost (p)i,pj) Representing two nodes piAnd pj(x) cost function of (x)i,yi) And (x)j,yj) Are respectively a node piAnd pjCoordinate of (d), Dist (p)i,pj) Representing a node piAnd pjDistance between, Head (p)i,pj) Representing a node piAnd pjAngle difference between, K1Is Dist (p)i,pj) Corresponding weight coefficient, K2Is Head (p)i,pj) A corresponding weight coefficient; wherein Dist (p)i,pj) Calculated as follows:
Head(pi,pj) Calculated as follows:
Head(pi,pj)＝θij
wherein, thetaijIs a node piAnd pjThe angular difference between;
s340, screening out and outputting optimal path data by adopting an improved Dijkstra algorithm;
s400, processing according to the optimal path data to obtain a target track, and outputting the target track to a control system;
the target track comprises an optimal smooth curve, an expected track course angle of the end point, an expected curvature of the end point and an expected speed of the end point; the method specifically comprises the following steps:
s410, performing third-order Bezier curve fitting on the optimal path data to obtain and output an optimal smooth curve; s420, calculating and outputting an expected track course angle of the end point;
s430, calculating and outputting the expected curvature of the end point;
s500, the vehicle-mounted ECU receives the target track, controls the steering mechanism, the accelerating mechanism and the decelerating mechanism to move along the optimal smooth curve, verifies the posture of the vehicle by using the expected curvature of the end point when the controlled vehicle enters the end point, adjusts the speed direction of the vehicle to be the expected track course angle of the end point by the steering mechanism, adjusts the speed of the vehicle to be the expected speed of the end point by the accelerating mechanism and the decelerating mechanism, and then keeps the controlled vehicle to move at a constant speed.
Preferably, the method for constructing the two-dimensional coordinate system comprises the following steps:
s110, selecting a road center line as an x axis;
s120, selecting a projection point of the start point on the x axis as an origin;
s130, taking a straight line which passes through the origin and is vertical to the x axis as a y axis;
and S140, taking the component directions of the current vehicle on the x axis and the y axis as positive directions.
Preferably, each candidate trajectory in S320 contains the same number of sampling points; different candidate tracks have no same sampling point except for the start point and the end point; the x values of the sampling points on each candidate trajectory form an arithmetic progression.
Preferably, the method for screening the optimal path data in S340 includes the following steps:
s341, marking the cost value of the start point as 0, and then selecting the sampling point with the smallest cost value from the sampling points with the smallest x value of the distance between each candidate track and the origin point as the current selected point; recording the selected point into the optimal path data, and connecting the origin point with the selected point in the direction from the origin point to the selected point;
s342, setting the selected midpoint as the current starting point, and then selecting the smallest cost value from the sampling points of which the x value of each candidate track from the current starting point is greater than 0 and the smallest cost value as the selected midpoint; recording the selected point into the optimal path data, and connecting the departure point with the selected point in a direction from the departure point to the selected point;
s343, comparing the coordinate of the selected point with the coordinate of the end point, and according to the comparison result, performing the following operations:
if the coordinates of the selected midpoint and the end point are the same, finishing screening and outputting optimal path data;
or the like, or, alternatively,
and if the coordinates of the selected point and the end point are different, repeating S342 to S343.
Preferably, the third-order Bezier curve described in S410 is calculated as follows:
where T (t) represents a time-stamped trajectory profile function, PkT is a control point and represents a time proportionality coefficient, and the value range is [0,1 ]]N is the order of the curve, Bk,n(t) is a bernstein basis function; the Bernstein basis function is calculated as:
where i denotes the ith control point for the progressive calculation.
Preferably, the first and second electrodes are formed of a metal,
the expected track heading angle of the end point in the step S420 is calculated according to the following formula:
wherein x (t) and y (t) are coordinates of the end point on the x-axis and the y-axis respectively;
the expected curvature of the end point in S430 is calculated as follows:
compared with the prior art, the invention has the following advantages:
1. according to the invention, a three-order Bezier curve is adopted as the driving track of the unmanned vehicle, and the track is divided into three stages to be subjected to Bezier smoothing treatment, so that the unmanned vehicle can reach a target point along the smooth track when changing lanes, and the curvature of the curve is continuous.
2. Aiming at a high-speed automatic driving scene, the Dijkstra algorithm is correspondingly improved, the calculated amount is greatly reduced on the basis of keeping the advantage that the Dijkstra algorithm finds the shortest path in a structured environment, the real-time requirement in a high-speed state is met, and the result is continuous.
3. And the vehicle motion is constrained through a Cost function model, and an optimal solution can be obtained on the premise of determining the number of sampling points.
4. The road and motion model is established after the constraint in the actual motion of the vehicle is considered, and the practical application requirements are better met.
Drawings
Fig. 1 is a schematic diagram of lane changing operation required by the unmanned vehicle in the embodiment of the invention.
FIG. 2 is a schematic diagram of candidate trajectory generation according to an embodiment of the present invention.
FIG. 3 is a node diagram of a cost function according to an embodiment of the present invention.
FIG. 4 is a flowchart illustrating steps for generating optimal path data according to an embodiment of the present invention.
FIG. 5 is a trace diagram of a third order Bezier curve according to an embodiment of the present invention.
FIG. 6 is a course angle variation curve of the unmanned vehicle in the embodiment of the present invention.
Fig. 7 is a graph showing the change of curvature in the movement of the unmanned vehicle according to the embodiment of the present invention.
Wherein, 1-unmanned vehicle, 2-static vehicle.
Detailed Description
The present invention is further illustrated by the following examples, which are intended to be purely exemplary and are not intended to limit the scope of the invention, as various equivalent modifications of the invention will occur to those skilled in the art upon reading the present disclosure and fall within the scope of the appended claims.
As shown in FIG. 1, the driving road of the vehicle is a double lane, and the lane width is 3.5 meters. The unmanned vehicle 1 has a size of 7000mm 2200mm 4000mm, and a stationary vehicle 2 is found in front of the high-speed radar, and a lane change operation as indicated by an arrow in the figure is required to avoid rear-end collision.
The invention relates to an automatic driving track generation method under a high-speed scene, which comprises an improved Dijkstra algorithm and comprises the following steps:
s10, the driverless vehicle 1 obtains an HD map of the lane.
S100, constructing a two-dimensional coordinate system, and expressing the position of the unmanned vehicle 1 in the two-dimensional coordinate system by (x, y); the current position of the unmanned vehicle 1 is marked as a start point, and the target position of the unmanned vehicle 1 is marked as an end point.
The construction method of the two-dimensional coordinate system comprises the following steps:
and S110, selecting the road center line as an x axis.
And S120, selecting a projection point of the start point on the x axis as an origin.
S130, taking a straight line which passes through the origin and is vertical to the x axis as the y axis.
And S140, taking the component directions of the current advancing direction of the unmanned vehicle 1 on the x axis and the y axis as positive directions.
And S200, acquiring original road data and original vehicle state data.
S300, processing according to the original road data and the original vehicle state data to obtain optimal path data; the method specifically comprises the following steps:
s310, selecting a corresponding sampling template from a plurality of preset sampling templates according to original road data and original vehicle state data, and then importing the original road data and the original vehicle state data into the sampling templates to obtain a plurality of sampling points; and packing all the sampling points into a sampling point set.
S320, as shown in the figure 2, generating a plurality of candidate tracks according to the sampling point set and the sampling template; the candidate tracks are composed of sampling points; in S320, each candidate track has the same number of sampling points; different candidate tracks have no same sampling point except for the start point and the end point; the x values of the sampling points on each candidate trajectory form an arithmetic progression.
S330, calculating cost values among all sampling points one by one; in consideration of the steering ability of the unmanned vehicle 1, when randomly distributing the sampling points, it is necessary to consider not only the shortest euclidean distance distribution Dist (p)i,pj) And smoothness of the trajectory, i.e., Head corner Head (p)i,pj) As small as possible. As shown in FIG. 3, the invention selects a more reasonable Cost function Cost model. The cost value is calculated by the following equation (1):
Cost(pi,pj)＝K1×Dist(pi,pj)+K2×Head(pi,pj) (1)
among them, Cost (p)i,pj) Representing two nodes piAnd pj(x) cost function of (x)i,yi) And (x)j,yj) Are respectively a node piAnd pjCoordinate of (d), Dist (p)i,pj) Representing a node piAnd pjDistance between, Head (p)i,pj) Representing a node piAnd pjAngle difference between, K1Is Dist (p)i,pj) Corresponding weight coefficient, K2Is Head (p)i,pj) A corresponding weight coefficient; wherein Dist (p)i,pj) Calculating according to the formula (2):
Head(pi,pj) Calculating according to the formula (3):
Head(pi,pj)＝θij (3)
wherein, thetaijIs a node piAnd pjThe angular difference between them.
S340, screening out and outputting optimal path data by adopting an improved Dijkstra algorithm; as shown in fig. 4, the method for screening out the optimal path data includes the following steps:
s341, marking the cost value of the start point as 0, and then selecting the sampling point with the smallest cost value from the sampling points with the smallest x value of the distance between each candidate track and the origin point as the current selected point; and recording the selected point into the optimal path data, and connecting the origin point with the selected point in the direction from the origin point to the selected point.
S342, setting the selected midpoint as the current starting point, and then selecting the smallest cost value from the sampling points of which the x value of each candidate track from the current starting point is greater than 0 and the smallest cost value as the selected midpoint; and recording the selected point into the optimal path data, and connecting the departure point with the selected point in the direction from the departure point to the selected point.
S343, comparing the coordinate of the selected point with the coordinate of the end point, and according to the comparison result, performing the following operations:
if the coordinates of the selected center point and the end point are the same, finishing the screening and outputting the optimal path data.
Or the like, or, alternatively,
and if the coordinates of the selected point and the end point are different, repeating S342 to S343.
The curvature of each point (x, y) on the optimal path is calculated as equation (4):
k(t)＝(x'(t)y”(t)-x”(t)y'(t))/(x'(t)2+y'(t)2)3/2 (4)
and S400, processing to obtain a target track according to the optimal path data, and outputting to a control system.
The target track comprises an optimal smooth curve, an expected track course angle of the end point, an expected curvature of the end point and an expected speed of the end point; the method specifically comprises the following steps:
s410, performing third-order Bezier curve fitting on the optimal path data to obtain and output an optimal smooth curve; the method can ensure that the relation between the input control point and the generated curve is simple and clear, the key parameters are easy to determine, and the shape and the sequence of the curve are easy to change. Wherein, the third-order Bezier curve is calculated according to the formula (5):
where T (t) represents a time-stamped trajectory profile function, PkT is a control point and represents a time proportionality coefficient, and the value range is [0,1 ]]N is the order of the curve, Bk,n(t) is a bernstein basis function; the bernstein basis function is calculated as equation (6):
where i denotes the ith control point for the progressive calculation.
Considering that changing the direction in situ may damage the tires of the drone vehicle 1, it is necessary for the drone vehicle 1 to travel along a smooth trajectory. At the same time, when changing lanes or turning, the planned trajectory must comply with traffic regulations, i.e. travel along appropriate road sections. On the basis, sampling planning is carried out on the track points of the unmanned vehicle 1. The third order Bezier curve determined by the four control points can be calculated as in equation (7):
wherein, as shown in FIG. 5, in the third-order Bezier curve, the point P0In the representation of the current drone vehicle 1
Position of the heart coordinate, point P1And P2Indicating the coordinate position of the control point in the middle of the curve, point P3Indicating the position of the center coordinates of the target point of the drone vehicle 1.
S420, calculating and outputting an expected track course angle of the end point; wherein, the expected track course angle of the end point is calculated according to the formula (8):
wherein x (t) and y (t) are coordinates of the end point on the x-axis and the y-axis, respectively. As shown in fig. 6, the direction of travel of the final drone vehicle 1 is parallel to the x-axis, and θ (t) is 0.
S430, calculating and outputting the expected curvature of the end point; wherein the expected curvature of the end point is calculated according to equation (9):
as shown in fig. 7, the drone vehicle 1 finally travels in a straight line, with k (t) being 0.
S500, the vehicle-mounted ECU receives the target track, controls the steering mechanism, the accelerating mechanism and the decelerating mechanism to move along the optimal smooth curve, verifies the posture of the unmanned vehicle 1 by using the expected curvature of the end point when the controlled unmanned vehicle 1 enters the end point, adjusts the speed direction of the unmanned vehicle 1 to be the expected track course angle of the end point by the steering mechanism, adjusts the speed of the unmanned vehicle 1 to be the expected speed of the end point by the accelerating mechanism and the decelerating mechanism, and then keeps the controlled unmanned vehicle 1 to move at a constant speed.
The above embodiments are only used for illustrating the design idea and features of the present invention, and the purpose of the present invention is to enable those skilled in the art to understand the content of the present invention and implement the present invention accordingly, and the protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes and modifications made in accordance with the principles and concepts disclosed herein are intended to be included within the scope of the present invention.
Claims (6)
1. An automatic driving track generation method under a high-speed scene comprises an improved Dijkstra algorithm and is characterized in that: the method comprises the following steps:
s100, constructing a two-dimensional coordinate system, and expressing the position of the vehicle in the two-dimensional coordinate system by (x, y); marking the current position of the vehicle as a start point, and marking the target position of the vehicle as an end point;
s200, acquiring original road data and original vehicle state data;
s300, processing according to the original road data and the original vehicle state data to obtain optimal path data; the method specifically comprises the following steps:
s310, selecting a corresponding sampling template from a plurality of preset sampling templates according to original road data and original vehicle state data, and then importing the original road data and the original vehicle state data into the sampling templates to obtain a plurality of sampling points; packing all sampling points into a sampling point set;
s320, generating a plurality of candidate tracks according to the sampling point set and the sampling template; the candidate tracks are composed of sampling points;
s330, calculating cost values among all sampling points one by one; the cost value is calculated as follows:
Cost(pi,pj)＝K1×Dist(pi,pj)+K2×Head(pi,pj)
among them, Cost (p)i,pj) Representing two nodes piAnd pj(x) cost function of (x)i,yi) And (x)j,yj) Are respectively a node piAnd pjCoordinate of (d), Dist (p)i,pj) Representing a node piAnd pjDistance between, Head (p)i,pj) Representing a node piAnd pjAngle difference between, K1Is Dist (p)i,pj) Corresponding weight coefficient, K2Is Head (p)i,pj) A corresponding weight coefficient; wherein Dist (p)i,pj) Calculated as follows:
Head(pi,pj) Calculated as follows:
Head(pi,pj)＝θij
wherein，θijIs a node piAnd pjThe angular difference between;
s340, screening out and outputting optimal path data by adopting an improved Dijkstra algorithm;
s400, processing according to the optimal path data to obtain a target track, and outputting the target track to a control system;
the target track comprises an optimal smooth curve, an expected track course angle of the end point, an expected curvature of the end point and an expected speed of the end point; the method specifically comprises the following steps:
s410, performing third-order Bezier curve fitting on the optimal path data to obtain and output an optimal smooth curve;
s420, calculating and outputting an expected track course angle of the end point;
s430, calculating and outputting the expected curvature of the end point;
s500, the vehicle-mounted ECU receives the target track, controls the steering mechanism, the accelerating mechanism and the decelerating mechanism to move along the optimal smooth curve, verifies the posture of the vehicle by using the expected curvature of the end point when the controlled vehicle enters the end point, adjusts the speed direction of the vehicle to be the expected track course angle of the end point by the steering mechanism, adjusts the speed of the vehicle to be the expected speed of the end point by the accelerating mechanism and the decelerating mechanism, and then keeps the controlled vehicle to move at a constant speed.
2. The automatic driving trajectory generation method in a high-speed scene according to claim 1, characterized in that: the construction method of the two-dimensional coordinate system comprises the following steps:
s110, selecting a road center line as an x axis;
s120, selecting a projection point of the start point on the x axis as an origin;
s130, taking a straight line which passes through the origin and is vertical to the x axis as a y axis;
and S140, taking the component directions of the current vehicle on the x axis and the y axis as positive directions.
3. The automatic driving trajectory generation method in a high-speed scene according to claim 2, characterized in that: in S320, each candidate track has the same number of sampling points; different candidate tracks have no same sampling point except for the start point and the end point; the x values of the sampling points on each candidate trajectory form an arithmetic progression.
4. The automatic driving trajectory generation method in a high-speed scene according to claim 3, characterized in that: the method for screening the optimal path data in the step S340 includes the following steps:
s341, marking the cost value of the start point as 0, and then selecting the sampling point with the smallest cost value from the sampling points with the smallest x value of the distance between each candidate track and the origin point as the current selected point; recording the selected point into the optimal path data, and connecting the origin point with the selected point in the direction from the origin point to the selected point;
s342, setting the selected midpoint as the current starting point, and then selecting the smallest cost value from the sampling points of which the x value of each candidate track from the current starting point is greater than 0 and the smallest cost value as the selected midpoint; recording the selected point into the optimal path data, and connecting the departure point with the selected point in a direction from the departure point to the selected point;
s343, comparing the coordinate of the selected point with the coordinate of the end point, and according to the comparison result, performing the following operations:
if the coordinates of the selected midpoint and the end point are the same, finishing screening and outputting optimal path data;
or the like, or, alternatively,
and if the coordinates of the selected point and the end point are different, repeating S342 to S343.
5. The automatic driving trajectory generation method in a high-speed scene according to claim 4, wherein: the third-order Bezier curve described in S410 is calculated as follows:
where T (t) denotes a time-stamped trackTrace curve function, PkT is a control point and represents a time proportionality coefficient, and the value range is [0,1 ]]N is the order of the curve, Bk,n(t) is a bernstein basis function; the Bernstein basis function is calculated as:
where i denotes the ith control point for the progressive calculation.
6. The automatic driving trajectory generation method in a high-speed scene according to claim 5, characterized in that:
the expected track heading angle of the end point in the step S420 is calculated according to the following formula:
wherein x (t) and y (t) are coordinates of the end point on the x-axis and the y-axis respectively;
the expected curvature of the end point in S430 is calculated as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249603.4A CN110954122B (en) | 2019-12-09 | 2019-12-09 | Automatic driving track generation method under high-speed scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249603.4A CN110954122B (en) | 2019-12-09 | 2019-12-09 | Automatic driving track generation method under high-speed scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110954122A CN110954122A (en) | 2020-04-03 |
| CN110954122B true CN110954122B (en) | 2021-07-06 |
Family
ID=69980372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911249603.4A Active CN110954122B (en) | 2019-12-09 | 2019-12-09 | Automatic driving track generation method under high-speed scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110954122B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523719B (en) * | 2020-04-16 | 2024-03-15 | 东南大学 | Hybrid path planning method based on kinematic constraint of articulated vehicle |
| CN111487971B (en) * | 2020-04-23 | 2023-04-28 | 重庆长安汽车股份有限公司 | Automatic driving transverse control method and system for vehicle |
| CN113701746A (en) * | 2020-05-21 | 2021-11-26 | 华为技术有限公司 | Target orientation determination method and device |
| CN113759888A (en) * | 2020-06-08 | 2021-12-07 | 北京京东乾石科技有限公司 | Method, device and equipment for smoothing leader line and storage medium |
| CN111737389B (en) * | 2020-06-12 | 2023-07-25 | 北京百度网讯科技有限公司 | Curve optimization method, device, equipment and medium |
| CN111998864B (en) * | 2020-08-11 | 2023-11-07 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
| CN114184198B (en) * | 2020-09-14 | 2024-03-01 | 广州汽车集团股份有限公司 | Real-time path generation method and device and automobile |
| CN112146667B (en) * | 2020-09-29 | 2022-10-14 | 广州小鹏自动驾驶科技有限公司 | Method and device for generating vehicle transition track |
| CN112240770A (en) * | 2020-10-15 | 2021-01-19 | 浙江欣奕华智能科技有限公司 | Method, device and terminal for generating robot motion trail |
| CN114264307A (en) * | 2021-12-15 | 2022-04-01 | 广州小鹏自动驾驶科技有限公司 | Route generation method, apparatus, vehicle and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828968A (en) * | 1995-10-31 | 1998-10-27 | Honda Giken Kogyo Kabushiki Kaisha | Method of controlling automatically driven motor vehicle |
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN108153245A (en) * | 2017-12-26 | 2018-06-12 | 深圳市汇川技术股份有限公司 | Smooth trajectory forwarding method and system |
| CN108646667A (en) * | 2018-03-05 | 2018-10-12 | 北京华航唯实机器人科技股份有限公司 | Orbit generation method and device, terminal |
| CN109101017A (en) * | 2018-07-27 | 2018-12-28 | 江苏盛海智能科技有限公司 | A kind of unmanned vehicle tracks route planning method and terminal |
| CN110244710A (en) * | 2019-05-16 | 2019-09-17 | 深圳前海达闼云端智能科技有限公司 | Automatic Track Finding method, apparatus, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9513623B2 (en) * | 2014-01-21 | 2016-12-06 | Mitsubishi Electric Research Laboratories, Inc. | Method for generating trajectory for numerical control process |
-
2019
- 2019-12-09 CN CN201911249603.4A patent/CN110954122B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828968A (en) * | 1995-10-31 | 1998-10-27 | Honda Giken Kogyo Kabushiki Kaisha | Method of controlling automatically driven motor vehicle |
| CN105651295A (en) * | 2016-01-15 | 2016-06-08 | 武汉光庭信息技术股份有限公司 | Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve |
| CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
| CN108153245A (en) * | 2017-12-26 | 2018-06-12 | 深圳市汇川技术股份有限公司 | Smooth trajectory forwarding method and system |
| CN108646667A (en) * | 2018-03-05 | 2018-10-12 | 北京华航唯实机器人科技股份有限公司 | Orbit generation method and device, terminal |
| CN109101017A (en) * | 2018-07-27 | 2018-12-28 | 江苏盛海智能科技有限公司 | A kind of unmanned vehicle tracks route planning method and terminal |
| CN110244710A (en) * | 2019-05-16 | 2019-09-17 | 深圳前海达闼云端智能科技有限公司 | Automatic Track Finding method, apparatus, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| "On-line Planning of Nonholonomic Trajectories in Crowded and Geometrically Unknown Environments";Yanbo Li 等;《2009 IEEE International Conference on Robotics and Automation》;20090331;正文第3230-3235页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110954122A (en) | 2020-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110954122B (en) | Automatic driving track generation method under high-speed scene | |
| CN112068545B (en) | Method and system for planning running track of unmanned vehicle at crossroad and storage medium | |
| CN112964271B (en) | Multi-scene-oriented automatic driving planning method and system | |
| CN107702716B (en) | Unmanned driving path planning method, system and device | |
| CN111426330B (en) | Path generation method and device, unmanned transportation system and storage medium | |
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| CN111006667B (en) | Automatic driving track generation system under high-speed scene | |
| CN109213153B (en) | Automatic vehicle driving method and electronic equipment | |
| Zheng et al. | RRT based path planning for autonomous parking of vehicle | |
| CN111060108B (en) | Path planning method and device and engineering vehicle | |
| CN113721637B (en) | Intelligent vehicle dynamic obstacle avoidance path continuous planning method and system and storage medium | |
| CN111830979A (en) | Trajectory optimization method and device | |
| CN111896004A (en) | Narrow passage vehicle track planning method and system | |
| CN114906173B (en) | Automatic driving decision method based on two-point pre-aiming driver model | |
| CN116185014A (en) | Intelligent vehicle global optimal track planning method and system based on dynamic planning | |
| CN112683290A (en) | Vehicle track planning method, electronic equipment and computer readable storage medium | |
| Bonab et al. | Optimization-based path planning for an autonomous vehicle in a racing track | |
| CN113515111B (en) | Vehicle obstacle avoidance path planning method and device | |
| Park et al. | Path generation algorithm based on crash point prediction for lane changing of autonomous vehicles | |
| CN114187781B (en) | Distributed multi-vehicle cooperative behavior decision method and system | |
| CN114404985A (en) | Path planning method and device for virtual role, electronic device and storage medium | |
| CN111857112A (en) | Automobile local path planning method and electronic equipment | |
| CN117622227B (en) | Vehicle lane changing obstacle avoidance control method and device | |
| CN113050657B (en) | Waypoint processing method and system for automatic driving tracking | |
| Bajić et al. | Trajectory planning for autonomous vehicle using digital map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |