CN110703763A - Unmanned vehicle path tracking and obstacle avoidance method - Google Patents
Unmanned vehicle path tracking and obstacle avoidance method Download PDFInfo
- Publication number
- CN110703763A CN110703763A CN201911069856.3A CN201911069856A CN110703763A CN 110703763 A CN110703763 A CN 110703763A CN 201911069856 A CN201911069856 A CN 201911069856A CN 110703763 A CN110703763 A CN 110703763A
- Authority
- CN
- China
- Prior art keywords
- unmanned vehicle
- current
- control
- front wheel
- predicted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000004888 barrier function Effects 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims description 39
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 19
- 230000001133 acceleration Effects 0.000 claims description 9
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 230000000694 effects Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the field of unmanned vehicle control, in particular to an unmanned vehicle path tracking and obstacle avoidance method, which comprises the following steps: determining each controlled quantity combination of the course speed and the steering angle of the front wheel of the unmanned vehicle according to the running control parameters of the unmanned vehicle; correspondingly generating a predicted track for each control quantity combination by combining an Ackerman steering kinematics model; selecting a predicted track for enabling the unmanned vehicle to safely run from the predicted tracks according to the barrier information fed back by the sensor on the unmanned vehicle to form a safe predicted track set; selecting an optimal predicted track in the safe predicted track set; the control quantity combination corresponding to the optimal predicted track is the optimal control quantity combination, and the control instruction corresponding to the optimal control quantity combination is sent to the unmanned vehicle; judging whether the unmanned vehicle reaches a target point: if so, sending a stop control instruction to stop the unmanned vehicle; if not, entering the next control period. The invention can realize real-time dynamic obstacle avoidance in the unmanned vehicle path tracking driving process.
Description
Technical Field
The invention relates to the field of unmanned vehicle control, in particular to a method for tracking and avoiding an obstacle of an unmanned vehicle path.
Background
The unmanned vehicle is an intelligent ground moving carrier which is provided with a perfect environment sensing system, can make a decision and plan a path according to environment information provided by the sensing system, and controls the vehicle to reach a destination. The path tracking and obstacle avoidance are control links performed after path planning, and require that a vehicle can drive according to a planned path and avoid collision by bypassing obstacles.
At present, path tracking methods for unmanned vehicles include path tracking based on PID control, path tracking based on pure tracking, path tracking based on model predictive control, and the like. The path tracking method based on PID control calculates the path error of the vehicle according to the target path information and the current vehicle pose information, and adjusts the current pose of the vehicle based on the PID control strategy, so that the vehicle can run stably. The pure tracking-based path tracking method is used for pre-aiming a certain point on a target path according to target path information and current vehicle pose information, calculating that an arc path approaches a pre-aiming point, and dynamically adjusting the advancing direction of a vehicle according to the real-time motion state of the vehicle, so that path tracking control with good stability and high precision can be realized. Although the method can realize stable and accurate path tracking, the requirement of real-time dynamic obstacle avoidance in the driving process of the unmanned vehicle is not considered.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method for tracking the path of the unmanned vehicle and avoiding the obstacle, aiming at the defects of the prior art, and realizing real-time dynamic obstacle avoidance in the driving process of the unmanned vehicle.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method for constructing the unmanned vehicle path tracking and obstacle avoidance comprises the following steps:
for one control cycle of the unmanned vehicle, the following operations are performed:
determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle;
generating a predicted track correspondingly aiming at each control quantity combination (v, delta) by combining an Ackerman steering kinematics model;
selecting a predicted track for enabling the unmanned vehicle to safely run from the predicted tracks according to the barrier information fed back by the sensor on the unmanned vehicle to form a safe predicted track set;
selecting an optimal predicted track in the safe predicted track set;
control quantity group corresponding to optimal predicted trajectoryCombining (v, delta) to the optimum control quantity combination (vbest,δbest) Combining the optimum control quantities (v)best,δbest) Sending the corresponding control instruction to the unmanned vehicle;
judging whether the unmanned vehicle reaches a target point: if so, sending a stop control instruction to stop the unmanned vehicle; if not, entering the next control period.
According to the invention, the course speed v and the steering angle delta of the front wheel of the vehicle are used as control quantities, the predicted track is generated based on the kinematic model of the vehicle, the kinematic constraint of Ackerman steering is met, and the generated predicted track is reasonable and feasible. Therefore, the invention can realize real-time dynamic obstacle avoidance in the unmanned vehicle path tracking driving process.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic flow chart of an embodiment of the present invention;
FIG. 3 is a schematic diagram of generating a trajectory in an embodiment of the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1, the method for tracking and avoiding obstacles on the path of an unmanned vehicle according to the present invention includes:
for one control cycle of the unmanned vehicle, the following operations are performed:
101. determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle;
102. generating a predicted track correspondingly aiming at each control quantity combination (v, delta) by combining an Ackerman steering kinematics model;
103. selecting a predicted track for enabling the unmanned vehicle to safely run from the predicted tracks according to the barrier information fed back by the sensor on the unmanned vehicle to form a safe predicted track set;
104. selecting an optimal predicted track in the safe predicted track set;
105. the control quantity combination (v, delta) corresponding to the optimal predicted track is the optimal control quantity combination (v)best,δbest) Combining the optimum control quantities (v)best,δbest) Sending the corresponding control instruction to the unmanned vehicle;
106. judging whether the unmanned vehicle reaches a target point: if so, sending a stop control instruction to stop the unmanned vehicle; if not, entering the next control period.
In the invention, the whole path tracking and obstacle avoidance process of the unmanned vehicle is divided into a plurality of stages, the whole path tracking and obstacle avoidance process is a control cycle, and the time length of each control cycle is tcontrol. After the flow in one control cycle is completed, the next control cycle is entered.
Further, the running control parameters include: a course speed sampling number n and a front wheel steering angle sampling number m;
the driving control parameters are divided into: default driving control parameters or priority driving control parameters;
the method comprises the following steps of determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle, and the method also comprises the following steps: determining a mode of the unmanned vehicle in the current control period;
the determining of the mode in which the unmanned vehicle is located in the current control period specifically includes:
when the number of the obstacles in front acquired by the sensor on the unmanned vehicle is larger than a preset threshold value, judging that the unmanned vehicle is in a priority mode in the current control period; the driving control parameter is a priority driving control parameter;
when the number of the obstacles in front acquired by the sensor on the unmanned vehicle does not exceed a preset threshold value, judging that the unmanned vehicle is in a default mode in the current control period; the driving control parameter is a default driving control parameter;
the course speed sampling number of the priority running control parameter is greater than that of the default running control parameter;
the number of front wheel steering angle samples of the priority running control parameter is greater than the number of front wheel steering angle samples of the default running control parameter.
The mode in which the unmanned vehicle is in may be different during each control cycle. And judging the mode of the unmanned vehicle in the current period according to the number of the obstacles in the current period. When the number of the obstacles is large, the unmanned vehicle enters a priority mode; when the number of obstacles is small, the unmanned vehicle is in the default mode. The control flow of the unmanned vehicle is the same whether in the default mode or the priority mode, and the difference is that the corresponding running control parameter values are different, namely the values of the default running control parameter and the priority running control parameter are different.
Still further, the running control parameters further include: maximum course velocity vmaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolFront wheel steering angle limit angle deltamaxCurrent front wheel steering angle deltacurrentAnd maximum front wheel steering angular velocity ωmax；
The method for determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle specifically comprises the following steps:
from the maximum course velocity vmaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolAnd a course speed sampling number n, and determining a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period1,v2,v3…vn]；
Limiting angle delta by front wheel steering anglemaxCurrent front wheel steering angle deltacurrentMaximum front wheel steering angular velocity ωmaxControl period tcontrolAnd the number m of steering angle samples of the front wheels is counted, and the steering angle vector delta [ delta ] sampled by the unmanned vehicle in the current period is determined1,δ2,δ3…δm]；
The sampling velocity vector V is ═ V1,v2,v3…vn]Element in (b) and a sampling steering angle vector delta ═ delta1,δ2,δ3…δm]The elements in (b) are combined pairwise to form n × m control quantity combinations (v, δ).
Still further, the maximum course velocity vmaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolAnd a course speed sampling number n, and determining a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period1,v2,v3…vn]The method specifically comprises the following steps:
maximum heading speed v of unmanned vehicle in current cyclemaxDetermining the speed limit value interval [0, v ] of the unmanned vehiclemax]；
By the heading speed v of the unmanned vehicle in the current cyclecurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeAnd a control period tcontrolDetermining the speed dynamic interval [ v ] of the unmanned vehiclecurrent-abraketcontrol，vcurrent+amaxtcontrol]；
The speed limit value interval [0, v ] of the unmanned vehiclemax]And speed dynamic range [ v ]current-abraketcontrol，vcurrent+amaxtcontrol]Obtaining intersection to obtain unmanned vehicle speed search interval [ v ]VMIN，vVMAX]；
According to the sampling number n of the course speed, searching the interval [ v ] in the speedVMIN，vVMAX]Equidistant sampling is carried out on the course speed of the unmanned vehicle, and a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period is obtained1,v2,v3…vn]。
Still further, the limit angle δ is limited by the steering angle of the front wheelsmaxCurrent front wheel steering angle deltacurrentMaximum front wheel steering angular velocity ωmaxControl period tcontrolAnd the number m of samples of the steering angle of the front wheelAnd determining that the steering angle vector delta of the unmanned vehicle is [ delta ] sampled in the current period1,δ2,δ3…δm]The method specifically comprises the following steps:
by the limit angle delta of the steering angle of the front wheels of the unmanned vehiclemaxDetermining the range of angle limit value of unmanned vehicle [ -delta ]max,δmax]；
Steering angle delta of front wheel of unmanned vehicle in current cyclecurrentMaximum front wheel steering angular velocity ωmaxAnd a control period tcontrolDetermining the dynamic range [ delta ] of the steering angle of the front wheel of the unmanned vehiclecurrent-ωmaxtcontrol，δcurrent+ωmaxtcontrol]；
The angle limit value interval of the unmanned vehicle is [ -delta ]max,δmax]And angle dynamic interval [ delta ]current-ωmaxtcontrol，δcurrent+ωmaxtcontrol]Obtaining intersection to obtain the unmanned vehicle angle search interval [ delta ]MIN,δMAX]；
According to the sampling number m of the steering angle of the front wheel, in an angle search interval [ delta ]MIN,δMAX]Equidistant sampling is carried out on the steering angle of the front wheel of the unmanned vehicle, and the sampled steering angle vector delta [ delta ] of the front wheel of the unmanned vehicle in the current period is obtained1,δ2,δ3…δm]。
In the above technical solution, the generating a predicted trajectory for each control quantity combination (v, δ) by combining the ackermann steering kinematics model specifically includes:
measuring geodetic coordinates (x) according to the unmanned vehicle odometer and the positioning systemi,yi) The course angle information theta measured by the sensoriAnd each control quantity combination (v, δ) generating a corresponding predicted trajectory; the calculation formula is as follows:
in the formula (1), xi、yi、θiGeodetic coordinates representing the ith track pointAnd course angle information; x is the number ofi+1、yi+1、θi+1The geodetic coordinates and course angle information of the (i + 1) th track point are represented; l represents the wheelbase of the unmanned vehicle; Δ t represents a time step of the current predicted trajectory calculation;
the calculation formula of the time step Δ t is as follows:
in the formula (2), tpredictIs a prediction period; n ispPredicting the number of track points on the track;
the prediction period tpredictThe calculation formula of (2) is as follows:
in the formula (3), abrakeMaximum braking deceleration, v, for unmanned vehiclescurrentIs the current course speed, t, of the unmanned vehiclesafeTime is safely redundant.
The predicted track is composed of a series of discrete track points, and each track point contains geodetic coordinates and course angle information (x, y, theta) of the unmanned vehicle. When the current speed of the vehicle is high, the period t is predictedpredictThe obstacle avoidance effect under high-speed driving is enhanced along with the extension.
In the above technical solution, the selecting, according to the obstacle information fed back by the sensor on the unmanned vehicle, a predicted trajectory for enabling the unmanned vehicle to safely run from among the predicted trajectories to form a safe predicted trajectory set specifically includes:
calculating the minimum distance between each track point in each predicted track and the current obstacle at the current time according to the obstacle information fed back by the unmanned vehicle sensor;
if the minimum distance between a certain track point in the current predicted track and the current obstacle is smaller than the preset safety distance dsafeJudging that the current predicted track is a dangerous predicted track for causing the collision between the unmanned vehicle and the obstacle;
and eliminating each dangerous prediction track in each prediction track, and forming a safe prediction track set by the remaining prediction tracks.
Preferably, the selecting, according to the obstacle information fed back by the sensor on the unmanned vehicle, a predicted trajectory for enabling the unmanned vehicle to safely run from among the predicted trajectories to form a safe predicted trajectory set, and then further including:
when each predicted track in the current period is judged to be a dangerous predicted track, a braking instruction is sent to the unmanned vehicle; the course speed v corresponding to the braking instruction is zero, and the braking deceleration is the maximum braking deceleration abrake；
And returning to the step of calculating the minimum distance between each track point in each predicted track and the current obstacle at the current time according to the obstacle information fed back by the unmanned vehicle sensor until a safe predicted track set is generated.
In the invention, the unmanned vehicle is in a moving state before reaching the target point and when not meeting the obstacle. In a control period, if all the predicted tracks generated currently are dangerous predicted tracks, the unmanned vehicle is enabled to enter a braking state, namely the heading speed v is zero, and the braking deceleration is the maximum braking deceleration abrake. And then, the minimum distance between each current track point and the current obstacle is calculated in a recycling mode until the predicted track which enables the unmanned vehicle not to collide with the obstacle is found out again after the obstacle leaves, and a safe predicted track set is formed.
In the above technical solution, selecting an optimal predicted trajectory in the safe predicted trajectory set specifically includes:
establishing an evaluation index of each predicted track in the safety predicted track set; the evaluation index includes: the distance from the obstacle, the deviation of the path to be tracked, the distance of a driving target point, the change rate of the front wheel steering angle and the course speed;
obtaining the score of each predicted track in the safety predicted track set according to the evaluation indexes and the preset weight corresponding to each evaluation index;
selecting the predicted track with the lowest score as the optimal predicted track;
the running control parameters further include: the weight of the distance from the obstacle, the weight of the change rate of the front wheel steering angle and the weight of the course speed;
the weight of the distance to the obstacle of the priority running control parameter is greater than the weight of the distance to the obstacle of the default running control parameter;
the weight of the front wheel steering angle change rate of the priority running control parameter is less than the weight of the front wheel steering angle change rate of the default running control parameter;
the weight of the course speed of the priority driving control parameter is less than the weight of the course speed of the default driving control parameter.
Preferably, the calculation formula of the score of each predicted track in the safe predicted track set is as follows:
score(v,δ)＝w1·obst(v,δ)+w2·path(v,δ)+w3·goal(v,δ)+w4·steer(δ)+w5·vel(v) (4)
in the formula (4), scoring functions obst, path, good, steer and vel respectively correspond to five evaluation indexes of the distance from the obstacle, the deviation of the path to be tracked, the distance of a driving target point, the angle change rate of the front wheel and the course speed in sequence; w is a1、w2、w3、w4And w5Respectively the weights of scoring functions obst, path, goal, steer and vel,
in the present invention, the scores of each scoring function are normalized. The smaller the score of a certain scoring function is, the better the performance of the predicted track corresponding to the scoring standard is.
The calculation formula of the scoring function obst (v, δ) of the distance to the obstacle is as follows:
in the formula (5), dcomfortIs the comfortable distance between the unmanned vehicle and the obstacle, dsafeFor tracks of predicted trajectorySafe distance between the locus and the obstacle, dminThe shortest distance between a track point of the predicted track and the obstacle is alpha which is a proportionality coefficient; and selecting proper alpha according to the safety distance and the comfort distance to achieve the ideal normalization effect.
When the shortest distance between the track point of the predicted track and the obstacle is greater than the comfortable distance, the scoring function value is 0, and the influence of the obstacle on the scoring is not counted. When the closest distance between the locus point of the predicted locus and the obstacle is between the safe distance and the comfortable distance, the closer the obstacle is, the higher the value of the scoring function obst (v, δ) is. The value of the scoring function obst (v, δ) is within the interval [0,1 ].
The calculation of the quasi tracking path deviation scoring function path (v, delta) comprises the following steps:
d is defined as the sum of the shortest distances between all track points of each predicted track and the path to be tracked in the safe predicted track setpath；
In the formula (6), npPredicting the number of track points on the track; diThe shortest distance between the track point and the path to be tracked is taken as the shortest distance; dptoleranceTolerating a distance for a path deviation;
calculating D of each predicted track in the set of safe predicted trackspathA value;
selecting each DpathMaximum of the values DpmaxAnd the smallest of Dpmin；
The calculation formula of the scoring function obst (v, δ) is:
the smaller the distance between the predicted track and the path to be tracked is, the better the tracking effect of the predicted track on the path is, and the smaller the value of the scoring function obst (v, delta) is. The value of the scoring function obst (v, δ) is within the interval [0,1 ].
The calculation of the scoring function of the distance to the driving target point, coarse (v, δ), comprises the following steps:
calculating the distance D between the last track point of each predicted track in the safe predicted track set and the target pointgoalA value;
selecting each DgoalMaximum of the values DgmaxAnd the smallest of Dgmin；
The calculation formula of the scoring function, coarse (v, δ), is as follows:
the smaller the distance between the predicted trajectory end point and the target point, the smaller the value of the scoring function, goal (v, δ). The value of the scoring function, coarse (v, δ), is within the interval [0,1 ].
The calculation formula of the scoring function steer (delta) of the front wheel steering angle change rate is as follows:
in formula (9), δmaxThe front wheel steering limit angle value is obtained; deltalastThe control quantity is sent to the front wheel turning angle control quantity of the unmanned vehicle in the previous control period;
the larger the change of the front wheel steering angle control δ of the predicted trajectory from the previous control period, the larger the steering width, and the higher the value of the score function steer (δ). The value of the scoring function steer (δ) is within the interval [0,1 ].
The calculation formula of the scoring function vel (v) of the heading speed is as follows:
in the formula (10), vVMIN、vVMAXThe minimum and maximum values within the speed search interval.
The larger the heading speed v, the smaller the value of the scoring function vel (v). The value of the scoring function vel (v) is within the interval [0,1 ].
The invention adopts the course velocity v and the steering angle delta of the front wheels of the vehicle as control quantities, generates the predicted track based on the kinematic model of the vehicle, accords with the kinematic constraint of Ackerman steering, and is reasonable and feasible. The method takes the distance of an obstacle, the deviation of a path to be tracked, the distance of a driving target point, the change rate of the front wheel angle and the course speed as evaluation indexes of a predicted track, and takes path tracking and obstacle avoidance functions into consideration; the problems of frequent steering and overlarge steering amplitude are reduced, and the driving stability of the vehicle is improved; the vehicle can run at the fastest speed as possible, and the efficiency of path tracking is improved. The evaluation index weight, the sampling number of the control quantity and the prediction period can be adaptively adjusted according to the speed, the obstacle density degree and the distance from a target point, and the obstacle avoidance priority mode is entered in an obstacle dense area, so that the obstacle avoidance effect and the driving safety are improved, and the method has certain environment adaptability.
The following examples are given to illustrate the technical solution of the present invention:
as shown in fig. 1 and 2, the method for tracking and avoiding obstacles on the path of an unmanned vehicle according to the present invention includes:
s1, according to the obstacle environment, the obstacle distance, the current speed of the vehicle and the distance of a target point sensed by the sensor, carrying out adaptive adjustment on the control quantity sampling number, the prediction period and the weight of the evaluation index, namely determining the mode of the unmanned vehicle in the current control period, and then adjusting the driving control parameter value of the unmanned vehicle according to different modes.
Acquiring the number of obstacles in an area in front of a vehicle by a sensor, and entering an obstacle avoidance priority mode when the number of the obstacles is larger than a set threshold value; and when the number of the obstacles does not exceed a set threshold value, entering a default mode.
When entering the obstacle avoidance priority mode from the default mode, the following parameter values are adjusted:
1. the course speed sampling number n and the front wheel steering angle sampling number m are increased, the search precision of a controlled quantity interval is improved, and the obstacle avoidance effect is enhanced.
2. The weight parameters of the obstacle distance evaluation items are increased, the influence of obstacle avoidance requirements on track preference is improved, and the obstacle avoidance effect is enhanced.
3. The weight parameter of the evaluation item of the front wheel steering angle change rate is reduced, so that the vehicle can steer more flexibly and rapidly when avoiding the obstacle, and the obstacle avoiding effect is enhanced.
4. The weight parameter of the course speed evaluation item is reduced, and the safety in obstacle avoidance is improved.
And S2, determining a search interval of the heading speed v and the front wheel steering angle delta and carrying out equidistant sampling.
From the maximum heading speed v of the vehiclemaxDetermining the limit value interval of the heading speed as [0, vmax]. At a known current heading velocity v of the vehiclecurrentUnder the condition of the maximum heading acceleration a of the vehiclemaxAnd maximum braking deceleration abrakeAt control period tcontrolWithin a dynamic range [ v ] of the speed which can be reached by the vehiclecurrent-abraketcontrol,vcurrent+amaxtcontrol]. Dividing the above-mentioned limit value interval [0, vmax]And dynamic range [ v ]current-abraketcontrol,vcurrent+amaxtcontrol]Determining search interval [ v ] of course speed v by solving intersectionVMIN,vVMAX]And according to the parameter course speed sampling number n, carrying out equidistant sampling on the course speed in a search interval to obtain a vector V ═ V [ V ] V [ ]1,v2,v3…vn]. Limiting angle delta according to the steering of the front wheels of the vehiclemaxCurrent front wheel steering angle delta of the vehiclecurrentMaximum front wheel steering angular velocity ωmaxAnd a control period tcontrolDetermining a search interval [ delta ] for the steering angle delta of the front wheelMIN,δMAX]And according to the parameter front wheel steering angle sampling number m, carrying out equidistant sampling on the front wheel steering angle in a search interval to obtain a vector delta ═ delta1,δ2,δ3…δm]。
And S3, calculating the predicted track according to the sampled control quantity combination (v, delta) and the Ackerman steering kinematic model, wherein the generated predicted track consists of a group of discrete track points, and each track point comprises the geodetic coordinates and the course angle information (x, y, theta) of the vehicle.
Obtaining the current geodetic coordinates and course angle information x of the vehicle by the odometer, the positioning system and the sensori、yi、θiThe method for calculating the predicted trajectory according to the control quantity combination (v, delta) obtained by sampling comprises the following steps:
in the formula, xi、yi、θiRepresenting the coordinate and course angle information of the ith track point; x is the number ofi+1、yi+1、θi+1Representing the coordinate and course angle information of the (i + 1) th track point; l represents the wheelbase of the vehicle; Δ t represents a time step of the predicted trajectory calculation.
The time step Δ t is calculated by the following method:
in the formula, tpredictIs a prediction period; n ispThe number of trace points on the trace is predicted.
According to the maximum braking deceleration a of the vehiclebrakeAnd the current heading speed vcurrentPredicting the period tpredictAdaptive changes can be made:
in the formula, tsafeTime is safely redundant; when the current speed of the vehicle is high, the period t is predictedpredictThe obstacle avoidance effect under high-speed driving is enhanced along with the extension.
And S4, performing collision check on each predicted track according to the obstacle information fed back by the sensor, and removing the predicted track colliding with the obstacle.
Defining a safety distance d between the vehicle and the obstaclesafe. And calculating the minimum distance between each track point of the predicted track and the obstacle according to the position information of the obstacle obtained by the sensor. If it is at any placeThe minimum distance between one track point and the barrier is less than the safety distance dsafeIf the trajectory is determined to collide with the obstacle, the predicted trajectory is rejected.
When all predicted tracks are judged to collide with the obstacles and can not generate usable control quantity, immediately sending a braking instruction with zero course speed to the unmanned vehicle, and controlling the unmanned vehicle to brake at the maximum deceleration abrakeAnd (5) braking and stopping. Meanwhile, the position of the obstacle is continuously detected through the sensor, and the minimum distance between each track point of the predicted track and the obstacle is calculated until the obstacle leaves to obtain a feasible obstacle avoidance predicted track.
And S5, scoring each predicted track which is not collided according to five evaluation indexes of the distance of the obstacle, the deviation of the path to be tracked, the distance of the driving target point, the change rate of the front wheel steering angle and the heading speed, and adding the scores of each evaluation index multiplied by the weight of the evaluation index to obtain the total score of each track. And selecting the track with the lowest score as the optimal track.
The total score of the predicted trajectory without collision score is calculated by a five-term scoring function in a weighted manner:
score(v,δ)＝w1·obst(v,δ)+w2·path(v,δ)+w3·goal(v,δ)+w4·steer(δ)+w5·vel(v)
in the formula, the scoring functions obst, path, coarse, steer and vel respectively correspond to five evaluation indexes of the distance from the obstacle, the deviation of the path to be tracked, the distance of a driving target point, the change rate of the front wheel angle and the course speed in sequence. The scores of each scoring function are normalized. w is a1、w2、w3、w4And w5Respectively, the weight parameters of the corresponding scoring functions,
the smaller the score of a certain scoring function is, the better the performance of the predicted track corresponding to the scoring standard is. And after all the predicted tracks are scored, selecting the track with the minimum total score as the optimal track.
The calculation method of the obstacle distance scoring function obst (v, δ) is as follows:
in the formula (d)comfortA comfortable distance between the vehicle and the obstacle, dsafeIs the safe distance between the vehicle and the obstacle; dminThe shortest distance between the track point of the predicted track and the obstacle is obtained; alpha is a proportionality coefficient, and an appropriate alpha is selected according to the safe distance and the comfortable distance to achieve an ideal normalization effect.
When the closest distance between the track point of the predicted track and the obstacle is greater than the comfortable distance, the score function value obst (v, δ) is 0, and the influence of the obstacle on the score is not counted. When the shortest distance between the trajectory point of the predicted trajectory and the obstacle is between the safe distance and the comfortable distance, the closer the distance to the obstacle, the higher the score function obst (v, δ) value. The scoring function obst (v, δ) values are within the interval [0,1 ].
The pseudo-tracking path deviation score function path (v, delta) is calculated as follows:
defining the sum D of the shortest distances between all track points of the predicted track and the path to be trackedpath：
In the formula, npPredicting the number of track points on the track; diThe shortest distance between the track point and the path to be tracked is taken as the shortest distance; dptoleranceDistance is tolerated for path deviation.
Calculating D of all non-collision predicted trackspathValue, selecting the largest one DpmaxAnd the smallest of Dpmin. Calculate scoring function path (v, δ):
the smaller the distance between the predicted track and the path to be tracked is, the better the tracking effect of the predicted track on the path is, and the smaller the scoring function value of the item is. The scoring function path (v, δ) values are within the interval [0,1 ].
The calculation method of the driving target point distance scoring function coarse (v, δ) is as follows:
calculating the distance D between the last track point of all the non-collided predicted tracks and the target pointgoalValue, selecting the largest one DgmaxAnd the smallest of Dgmin. Calculating the scoring function, coarse (v, δ):
the smaller the distance between the predicted trajectory end point and the target point, the smaller the score value of the item. The scoring function, the value of the coarse (v, delta) is within the interval [0,1 ].
The front wheel steering rate of change scoring function steer (δ) is calculated as follows:
in the formula, deltamaxThe front wheel steering limit angle value is obtained; deltalastAnd sending the front wheel steering angle control quantity to the chassis for the previous control period. The larger the change of the front wheel steering angle control amount δ of the predicted trajectory from the previous control period is, the larger the steering width is, and the higher the score function value is. The value of the scoring function steer (delta) is in the interval 0,1]Within.
The calculation method of the heading speed scoring function vel (v) is as follows:
in the formula, vVMIN、vVMAXMinimum and maximum values within the search interval are searched for the heading speed. The larger the heading velocity v, the smaller the score function value. Score function vel (v) value in interval [0,1]Within.
Weight parameter w of course velocity scoring function vel (v)5Self-adaptive adjustment is carried out according to the distance between the vehicle and the obstacle and the distance between the vehicle and the target point:weight parameter w5The distance between the vehicle and the obstacle is reduced along with the reduction of the current distance between the vehicle and the obstacle, so that the safety of obstacle avoidance is improved; when the distance between the vehicle and the target point is less than a certain threshold value, the weight parameter w5And the vehicle descends along with the reduction of the distance between the vehicle and the target point so as to ensure that the vehicle can accurately stop at the target point.
S6, combining the control quantities corresponding to the generated optimal trajectory (v)best,δbest) Sending the information to the unmanned vehicle driving controller and the steering controller to execute the course speed vbestAnd front wheel steering angle deltabestAnd (5) instructions.
And S7, judging whether the vehicle reaches the target point according to the distance between the vehicle and the target point. If the target point is reached, generating a stopping control instruction to stop the vehicle; otherwise with a control period tcontrolS1 to S6 are repeatedly performed for a cycle.
Defining a target point deviation tolerance distance dgtoleranceAnd when the distance between the vehicle and the target point is smaller than the value, the vehicle is considered to reach the target point, and the vehicle stops entering the control cycle to generate the control quantity.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. An unmanned vehicle path tracking and obstacle avoidance method is characterized by comprising the following steps:
for one control cycle of the unmanned vehicle, the following operations are performed:
determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle;
generating a predicted track correspondingly aiming at each control quantity combination (v, delta) by combining an Ackerman steering kinematics model;
selecting a predicted track for enabling the unmanned vehicle to safely run from the predicted tracks according to the barrier information fed back by the sensor on the unmanned vehicle to form a safe predicted track set;
selecting an optimal predicted track in the safe predicted track set;
the control quantity combination (v, delta) corresponding to the optimal predicted track is the optimal control quantity combination (v)best,δbest) Combining the optimum control quantities (v)best,δbest) Sending the corresponding control instruction to the unmanned vehicle;
judging whether the unmanned vehicle reaches a target point: if so, sending a stop control instruction to stop the unmanned vehicle; if not, entering the next control period.
2. The unmanned vehicle path tracking and obstacle avoidance method according to claim 1, wherein the driving control parameters include: a course speed sampling number n and a front wheel steering angle sampling number m;
the driving control parameters are divided into: default driving control parameters or priority driving control parameters;
the method comprises the following steps of determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle, and the method also comprises the following steps: determining a mode of the unmanned vehicle in the current control period;
the determining of the mode in which the unmanned vehicle is located in the current control period specifically includes:
when the number of the obstacles in front acquired by the sensor on the unmanned vehicle is larger than a preset threshold value, judging that the unmanned vehicle is in a priority mode in the current control period; the driving control parameter is a priority driving control parameter;
when the number of the obstacles in front acquired by the sensor on the unmanned vehicle does not exceed a preset threshold value, judging that the unmanned vehicle is in a default mode in the current control period; the driving control parameter is a default driving control parameter;
the course speed sampling number of the priority running control parameter is greater than that of the default running control parameter;
the number of front wheel steering angle samples of the priority running control parameter is greater than the number of front wheel steering angle samples of the default running control parameter.
3. The unmanned vehicle path tracking and obstacle avoidance method according to claim 2, wherein the driving control parameters further comprise: maximum course velocity vmaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolFront wheel steering limit angle deltamaxCurrent front wheel steering angle deltacurrentAnd maximum front wheel steering angular velocity ωmax；
The method for determining each controlled variable combination (v, delta) of the heading speed v and the front wheel steering angle delta of the unmanned vehicle according to the running control parameters of the unmanned vehicle specifically comprises the following steps:
from the maximum course velocity vmaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolAnd a course speed sampling number n, and determining a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period1,v2,v3… vn]；
By a control period tcontrolFront wheel steering limit angle deltamaxCurrent front wheel steering angle deltacurrentMaximum front wheel steering angular velocity ωmaxAnd the number m of steering angle samples of the front wheels is counted, and the steering angle vector delta [ delta ] sampled by the unmanned vehicle in the current period is determined1,δ2,δ3…δm]；
The sampling velocity vector V is ═ V1,v2,v3… vn]Element in (b) and a sampling steering angle vector delta ═ delta1,δ2,δ3…δm]The elements in (b) are combined pairwise to form n × m control quantity combinations (v, δ).
4. The unmanned vehicle path and tracking obstacle avoidance method of claim 3, wherein the maximum heading velocity v ismaxCurrent course velocity vcurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeControl period tcontrolAnd a course speed sampling number n, and determining a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period1,v2,v3… vn]The method specifically comprises the following steps:
maximum heading speed v of unmanned vehicle in current cyclemaxDetermining the speed limit value interval [0, v ] of the unmanned vehiclemax]；
By the heading speed v of the unmanned vehicle in the current cyclecurrentMaximum heading acceleration amaxMaximum braking deceleration abrakeAnd a control period tcontrolDetermining the speed dynamic interval [ v ] of the unmanned vehiclecurrent-abraketcontrol，vcurrent+amaxtcontrol]；
The speed limit value interval [0, v ] of the unmanned vehiclemax]And speed dynamic range [ v ]current-abraketcontrol，vcurrent+amaxtcontrol]Obtaining intersection to obtain unmanned vehicle speed search interval [ v ]VMIN，vVMAX]；
According to the sampling number n of the course speed, searching the interval [ v ] in the speedVMIN，vVMAX]Equidistant sampling is carried out on the course speed of the unmanned vehicle, and a sampling speed vector V ═ V [ V ] of the unmanned vehicle in the current period is obtained1,v2,v3… vn]。
5. The unmanned aerial vehicle path tracking and obstacle avoidance method according to claim 3, wherein the limit angle δ is steered by a front wheelmaxCurrent front wheel steering angle deltacurrentMaximum front wheel steering angular velocity ωmaxControl period tcontrolAnd the sampling number m of the steering angle of the front wheel is obtained, and the front wheel steering angle vector delta [ delta ] sampled by the unmanned vehicle in the current period is determined1,δ2,δ3… δm]The method specifically comprises the following steps:
steering limit angle delta of front wheel of unmanned vehiclemaxDetermining the steering angle of the front wheel of the unmanned vehicleLimit interval [ - δ ]max,δmax]；
Steering angle delta of front wheel of unmanned vehicle in current cyclecurrentMaximum front wheel steering angular velocity ωmaxAnd a control period tcontrolDetermining the dynamic range [ delta ] of the steering angle of the front wheel of the unmanned vehiclecurrent-ωmaxtcontrol，δcurrent+ωmaxtcontrol]；
The steering angle limit value interval of the front wheels of the unmanned vehicle is [ -delta ]max,δmax]And angle dynamic interval [ delta ]current-ωmaxtcontrol，δcurrent+ωmaxtcontrol]Obtaining intersection to obtain the search interval [ delta ] of the steering angle of the front wheels of the unmanned vehicleMIN,δMAX]；
According to the sampling number m of the steering angle of the front wheel, searching an interval [ delta ] in the steering angle of the front wheelMIN,δMAX]Equidistant sampling is carried out on the steering angle of the front wheel of the unmanned vehicle to obtain the sampled steering angle vector delta of the front wheel of the unmanned vehicle in the current period1,δ2,δ3… δm]。
6. The unmanned vehicle path tracking and obstacle avoidance method according to claim 3, wherein the combination of the ackerman steering kinematics model correspondingly generates a predicted trajectory for each control quantity combination (v, δ), specifically comprising:
measuring geodetic coordinates (x) according to the unmanned vehicle odometer and the positioning systemi,yi) The course angle information theta measured by the sensoriAnd each control quantity combination (v, δ) generating a corresponding predicted trajectory; the calculation formula is as follows:
in the formula (1), xi、yi、θiThe geodetic coordinates and course angle information of the ith track point are represented; x is the number ofi+1、yi+1、θi+1Geodetic coordinates representing the (i + 1) th track point andcourse angle information; l represents the wheelbase of the unmanned vehicle; Δ t represents a time step of the current predicted trajectory calculation;
the calculation formula of the time step Δ t is as follows:
in the formula (2), tpredictIs a prediction period; n ispPredicting the number of track points on the track;
the prediction period tpredictThe calculation formula of (2) is as follows:
in the formula (3), abrakeMaximum braking deceleration, v, for unmanned vehiclescurrentIs the current course speed, t, of the unmanned vehiclesafeTime is safely redundant.
7. The unmanned vehicle path tracking and obstacle avoidance method according to claim 1, wherein the selecting of the predicted trajectory for the unmanned vehicle to safely run from among the predicted trajectories according to the obstacle information fed back by the sensor on the unmanned vehicle, to form a safe predicted trajectory set, specifically comprises:
calculating the minimum distance between each track point in each predicted track and the current obstacle at the current time according to the obstacle information fed back by the unmanned vehicle sensor;
if the minimum distance between a certain track point in the current predicted track and the current obstacle is smaller than the preset safety distance dsafeJudging that the current predicted track is a dangerous predicted track for causing the collision between the unmanned vehicle and the obstacle;
and eliminating each dangerous prediction track in each prediction track, and forming a safe prediction track set by the remaining prediction tracks.
8. The unmanned vehicle path tracking and obstacle avoidance method according to claim 7, wherein the predicted trajectory for the unmanned vehicle to safely travel is selected from among the predicted trajectories according to obstacle information fed back by the sensor on the unmanned vehicle to form a safe predicted trajectory set, and then further comprising:
when each predicted track in the current period is judged to be a dangerous predicted track, a braking instruction is sent to the unmanned vehicle; the course speed v corresponding to the braking instruction is zero, and the braking deceleration is the maximum braking deceleration abrake；
And returning to the step of calculating the minimum distance between each track point in each predicted track and the current obstacle at the current time according to the obstacle information fed back by the unmanned vehicle sensor until a safe predicted track set is generated.
9. The unmanned aerial vehicle path tracking and obstacle avoidance method of claim 2, wherein the selecting of the optimal predicted trajectory in the set of safe predicted trajectories specifically comprises:
establishing an evaluation index of each predicted track in the safety predicted track set; the evaluation index includes: the distance from the obstacle, the deviation of the path to be tracked, the distance of a driving target point, the change rate of the front wheel steering angle and the course speed;
obtaining the score of each predicted track in the safety predicted track set according to the evaluation indexes and the preset weight corresponding to each evaluation index;
selecting the predicted track with the lowest score as the optimal predicted track;
the running control parameters further include: the weight of the distance from the obstacle, the weight of the change rate of the front wheel steering angle and the weight of the course speed;
the weight of the distance to the obstacle of the priority running control parameter is greater than the weight of the distance to the obstacle of the default running control parameter;
the weight of the front wheel steering angle change rate of the priority running control parameter is less than the weight of the front wheel steering angle change rate of the default running control parameter;
the weight of the course speed of the priority driving control parameter is less than the weight of the course speed of the default driving control parameter.
10. The unmanned aerial vehicle path tracking and obstacle avoidance method of claim 9, wherein a calculation formula of the score of each predicted track in the set of safe predicted tracks is:
score(v,δ)＝w1·obst(v,δ)+w2·path(v,δ)+w3·goal(v,δ)+w4·steer(δ)+w5·vel(v) (4)
in the formula (4), scoring functions obst, path, good, steer and vel respectively correspond to five evaluation indexes of the distance from the obstacle, the deviation of the path to be tracked, the distance of a driving target point, the angle change rate of the front wheel and the course speed in sequence; w is a1、w2、w3、w4And w5Respectively the weights of scoring functions obst, path, goal, steer and vel,
0≤wi≤1；
the calculation formula of the scoring function obst (v, δ) of the distance to the obstacle is as follows:
in the formula (5), dcomfortIs the comfortable distance between the unmanned vehicle and the obstacle, dsafeTo predict the safe distance between the point of the trajectory and the obstacle, dminThe shortest distance between a track point of the predicted track and the obstacle is alpha which is a proportionality coefficient;
the calculation of the quasi tracking path deviation scoring function path (v, delta) comprises the following steps:
d is defined as the sum of the shortest distances between all track points of each predicted track and the path to be tracked in the safe predicted track setpath；
In the formula (6), npFor predicting trace points on a traceThe number of (2); diThe shortest distance between the track point and the path to be tracked is taken as the shortest distance; dptoleranceTolerating a distance for a path deviation;
calculating D of each predicted track in the set of safe predicted trackspathA value;
selecting each DpathMaximum of the values DpmaxAnd the smallest of Dpmin；
The calculation formula of the scoring function obst (v, δ) is:
the calculation of the scoring function of the distance to the driving target point, coarse (v, δ), comprises the following steps:
calculating the distance D between the last track point of each predicted track in the safe predicted track set and the target pointgoalA value;
selecting each DgoalMaximum of the values DgmaxAnd the smallest of Dgmin；
The calculation formula of the scoring function, coarse (v, δ), is as follows:
the calculation formula of the scoring function steer (delta) of the front wheel steering angle change rate is as follows:
in formula (9), δmaxThe front wheel steering limit angle value is obtained; deltalastThe steering angle control quantity is sent to the front wheel of the unmanned vehicle in the previous control period;
the calculation formula of the heading speed scoring function vel (v) is as follows:
in the formula (10), vVMIN、vVMAXThe minimum and maximum values within the speed search interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911069856.3A CN110703763A (en) | 2019-11-05 | 2019-11-05 | Unmanned vehicle path tracking and obstacle avoidance method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911069856.3A CN110703763A (en) | 2019-11-05 | 2019-11-05 | Unmanned vehicle path tracking and obstacle avoidance method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110703763A true CN110703763A (en) | 2020-01-17 |
Family
ID=69204321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911069856.3A Pending CN110703763A (en) | 2019-11-05 | 2019-11-05 | Unmanned vehicle path tracking and obstacle avoidance method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110703763A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111090286A (en) * | 2020-03-24 | 2020-05-01 | 北京三快在线科技有限公司 | Unmanned vehicle motion state planning method and device |
| CN111238523A (en) * | 2020-04-23 | 2020-06-05 | 北京三快在线科技有限公司 | Method and device for predicting motion trail |
| CN111427358A (en) * | 2020-04-16 | 2020-07-17 | 武汉理工大学 | Navigation track control method and system for ship formation and storage medium |
| CN111506084A (en) * | 2020-05-19 | 2020-08-07 | 安徽江淮汽车集团股份有限公司 | Obstacle avoidance method, apparatus, device and storage medium for unmanned vehicle |
| CN111506081A (en) * | 2020-05-15 | 2020-08-07 | 中南大学 | Robot trajectory tracking method, system and storage medium |
| CN111752271A (en) * | 2020-04-16 | 2020-10-09 | 北京京东乾石科技有限公司 | Trajectory prediction method, apparatus, device and storage medium |
| CN112078570A (en) * | 2020-08-04 | 2020-12-15 | 武汉乐庭软件技术有限公司 | Automobile positioning method based on Ackerman steering model |
| CN112305911A (en) * | 2020-09-11 | 2021-02-02 | 重庆智行者信息科技有限公司 | Feedback prediction control method and device under complex environment and vehicle |
| CN112590804A (en) * | 2020-12-23 | 2021-04-02 | 苏州挚途科技有限公司 | Load trajectory tracking method and device for unmanned vehicle |
| CN112639656A (en) * | 2020-04-24 | 2021-04-09 | 深圳市大疆创新科技有限公司 | Movement control method, mobile device and mobile platform |
| CN112744217A (en) * | 2021-03-10 | 2021-05-04 | 北京车和家信息技术有限公司 | Collision detection method, travel path recommendation device, and storage medium |
| CN113495559A (en) * | 2020-03-18 | 2021-10-12 | 百度（美国）有限责任公司 | Learning-based controller for autonomous driving |
| CN113625702A (en) * | 2020-10-28 | 2021-11-09 | 北京科技大学 | Unmanned vehicle simultaneous path tracking and obstacle avoidance method based on quadratic programming |
| CN113703448A (en) * | 2021-08-19 | 2021-11-26 | 深圳亿嘉和科技研发有限公司 | Ackerman chassis obstacle avoidance control method based on ultrasonic waves |
| CN113753060A (en) * | 2020-10-30 | 2021-12-07 | 北京京东乾石科技有限公司 | Vehicle control method and device, computing equipment and medium |
| CN113778082A (en) * | 2021-08-23 | 2021-12-10 | 北京科技大学 | Unmanned vehicle track tracking control method and system based on self-triggering mechanism |
| CN114312770A (en) * | 2020-10-09 | 2022-04-12 | 郑州宇通客车股份有限公司 | Vehicle, and vehicle driving track prediction method and device |
| CN115525054A (en) * | 2022-09-20 | 2022-12-27 | 武汉理工大学 | Large-scale industrial park unmanned sweeper edge path tracking control method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009064088A (en) * | 2007-09-04 | 2009-03-26 | Toyota Motor Corp | Method and device for acquiring route of traveling object |
| CN108021133A (en) * | 2017-11-29 | 2018-05-11 | 江苏若博机器人科技有限公司 | A kind of Multi-sensor Fusion high speed unmanned vehicle detects obstacle avoidance system |
| US20190176333A1 (en) * | 2017-12-13 | 2019-06-13 | Disney Enterprises, Inc. | Robot navigation in context of obstacle traffic including movement of groups |
| CN110362096A (en) * | 2019-08-13 | 2019-10-22 | 东北大学 | A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality |
-
2019
- 2019-11-05 CN CN201911069856.3A patent/CN110703763A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009064088A (en) * | 2007-09-04 | 2009-03-26 | Toyota Motor Corp | Method and device for acquiring route of traveling object |
| CN108021133A (en) * | 2017-11-29 | 2018-05-11 | 江苏若博机器人科技有限公司 | A kind of Multi-sensor Fusion high speed unmanned vehicle detects obstacle avoidance system |
| US20190176333A1 (en) * | 2017-12-13 | 2019-06-13 | Disney Enterprises, Inc. | Robot navigation in context of obstacle traffic including movement of groups |
| CN110362096A (en) * | 2019-08-13 | 2019-10-22 | 东北大学 | A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality |
Non-Patent Citations (2)
| Title |
|---|
| 姜岩等: "基于运动微分约束的无人车辆纵横向协同规划算法的研究", 《自动化学报》 * |
| 徐保来等: "改进动态窗口法的阿克曼移动机器人局部路径规划器", 《机电工程技术》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113495559A (en) * | 2020-03-18 | 2021-10-12 | 百度（美国）有限责任公司 | Learning-based controller for autonomous driving |
| CN111090286A (en) * | 2020-03-24 | 2020-05-01 | 北京三快在线科技有限公司 | Unmanned vehicle motion state planning method and device |
| CN111427358B (en) * | 2020-04-16 | 2021-07-13 | 武汉理工大学 | Navigation track control method and system for ship formation and storage medium |
| CN111427358A (en) * | 2020-04-16 | 2020-07-17 | 武汉理工大学 | Navigation track control method and system for ship formation and storage medium |
| CN111752271A (en) * | 2020-04-16 | 2020-10-09 | 北京京东乾石科技有限公司 | Trajectory prediction method, apparatus, device and storage medium |
| CN111238523A (en) * | 2020-04-23 | 2020-06-05 | 北京三快在线科技有限公司 | Method and device for predicting motion trail |
| CN111238523B (en) * | 2020-04-23 | 2020-08-07 | 北京三快在线科技有限公司 | Method and device for predicting motion trail |
| CN112639656A (en) * | 2020-04-24 | 2021-04-09 | 深圳市大疆创新科技有限公司 | Movement control method, mobile device and mobile platform |
| CN111506081A (en) * | 2020-05-15 | 2020-08-07 | 中南大学 | Robot trajectory tracking method, system and storage medium |
| CN111506084B (en) * | 2020-05-19 | 2021-09-28 | 安徽江淮汽车集团股份有限公司 | Obstacle avoidance method, apparatus, device and storage medium for unmanned vehicle |
| CN111506084A (en) * | 2020-05-19 | 2020-08-07 | 安徽江淮汽车集团股份有限公司 | Obstacle avoidance method, apparatus, device and storage medium for unmanned vehicle |
| CN112078570A (en) * | 2020-08-04 | 2020-12-15 | 武汉乐庭软件技术有限公司 | Automobile positioning method based on Ackerman steering model |
| CN112305911A (en) * | 2020-09-11 | 2021-02-02 | 重庆智行者信息科技有限公司 | Feedback prediction control method and device under complex environment and vehicle |
| CN114312770A (en) * | 2020-10-09 | 2022-04-12 | 郑州宇通客车股份有限公司 | Vehicle, and vehicle driving track prediction method and device |
| CN114312770B (en) * | 2020-10-09 | 2023-07-07 | 宇通客车股份有限公司 | Vehicle, vehicle running track prediction method and device |
| CN113625702B (en) * | 2020-10-28 | 2023-09-22 | 北京科技大学 | Unmanned vehicle simultaneous path tracking and obstacle avoidance method based on quadratic programming |
| CN113625702A (en) * | 2020-10-28 | 2021-11-09 | 北京科技大学 | Unmanned vehicle simultaneous path tracking and obstacle avoidance method based on quadratic programming |
| CN113753060A (en) * | 2020-10-30 | 2021-12-07 | 北京京东乾石科技有限公司 | Vehicle control method and device, computing equipment and medium |
| CN113753060B (en) * | 2020-10-30 | 2023-05-30 | 北京京东乾石科技有限公司 | Control method, device, computing equipment and medium for vehicle |
| CN112590804A (en) * | 2020-12-23 | 2021-04-02 | 苏州挚途科技有限公司 | Load trajectory tracking method and device for unmanned vehicle |
| CN112744217A (en) * | 2021-03-10 | 2021-05-04 | 北京车和家信息技术有限公司 | Collision detection method, travel path recommendation device, and storage medium |
| CN113703448A (en) * | 2021-08-19 | 2021-11-26 | 深圳亿嘉和科技研发有限公司 | Ackerman chassis obstacle avoidance control method based on ultrasonic waves |
| CN113778082A (en) * | 2021-08-23 | 2021-12-10 | 北京科技大学 | Unmanned vehicle track tracking control method and system based on self-triggering mechanism |
| CN113778082B (en) * | 2021-08-23 | 2023-08-22 | 北京科技大学 | Unmanned vehicle track tracking control method and system based on self-triggering mechanism |
| CN115525054A (en) * | 2022-09-20 | 2022-12-27 | 武汉理工大学 | Large-scale industrial park unmanned sweeper edge path tracking control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110703763A (en) | Unmanned vehicle path tracking and obstacle avoidance method | |
| CN106926844B (en) | A kind of dynamic auto driving lane-change method for planning track based on real time environment information | |
| EP3932761A1 (en) | Vehicle abnormal lane change control method, device and system | |
| CN110187639B (en) | Trajectory planning control method based on parameter decision framework | |
| CN109606363B (en) | Multi-state feedback intelligent automobile extension lane keeping control method | |
| CN110597245A (en) | Automatic driving track-changing planning method based on quadratic planning and neural network | |
| CN109664884B (en) | Extension self-adaptive lane keeping control method under variable vehicle speed | |
| CN107943071A (en) | The formation of unmanned vehicle keeps control method and system | |
| CN110286681A (en) | A kind of dynamic auto driving lane-change method for planning track of variable curvature bend | |
| CN111806467A (en) | Variable speed dynamic track changing planning method based on vehicle driving rule | |
| CN108732921B (en) | Transverse extension preview switching control method for automatic driving automobile | |
| CN108646763A (en) | A kind of autonomous driving trace tracking and controlling method | |
| CN111409641A (en) | Trajectory tracking control method and system based on longitudinal and transverse coordination | |
| CN113276848A (en) | Intelligent driving lane changing and obstacle avoiding track planning and tracking control method and system | |
| CN113104037B (en) | Method and system for determining steering angle of vehicle steering wheel | |
| CN110481562B (en) | Optimal trajectory planning and control method and system for automatic lane changing of automobile | |
| CN113064344B (en) | Trajectory tracking control method for multi-axis unmanned heavy-load vehicle | |
| CN115047766A (en) | Speed planning method based on predictive control model | |
| CN112109732A (en) | Intelligent driving self-adaptive curve pre-aiming method | |
| CN115285145A (en) | Unmanned curve collision avoidance trajectory planning and tracking control method | |
| Peicheng et al. | Intelligent vehicle path tracking control based on improved MPC and hybrid PID | |
| CN109001976B (en) | Double-path cooperative extension transverse control method for automatic driving vehicle | |
| CN107856733A (en) | It is a kind of to hide dynamic barrier control method towards man-machine harmonious automobile | |
| CN107878453A (en) | A kind of automobile emergency collision avoidance integral type control method for hiding dynamic barrier | |
| CN109606362A (en) | It is a kind of that holding control method in feedforward lane is opened up based on road curvature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |
|
| RJ01 | Rejection of invention patent application after publication |