CN114932901A - Self-adaptive speed planning method and device and domain controller - Google Patents
Self-adaptive speed planning method and device and domain controller Download PDFInfo
- Publication number
- CN114932901A CN114932901A CN202210663745.0A CN202210663745A CN114932901A CN 114932901 A CN114932901 A CN 114932901A CN 202210663745 A CN202210663745 A CN 202210663745A CN 114932901 A CN114932901 A CN 114932901A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- speed
- distance
- current
- target
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4041—Position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4042—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
Abstract
The invention discloses a self-adaptive speed planning method, a self-adaptive speed planning device and a domain controller, wherein the method comprises the following steps: judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle; selecting obstacle targets with the closest relative distance from the obstacle targets which are collided as following vehicle targets, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle target is positioned on the planned path of the vehicle; and planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameter of the vehicle and the state parameter of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameter comprises speed, course and position. The technical scheme provided by the invention realizes the accurate obstacle avoidance of the automatic driving of the automobile under the multi-obstacle scene.
Description
Technical Field
The invention relates to the field of intelligent driving, in particular to a self-adaptive speed planning method, a self-adaptive speed planning device and a domain controller.
Background
In the unmanned system, trajectory planning is divided into path planning and speed planning. The speed planning can provide a reference speed and a reference acceleration sequence for the downstream control module, the longitudinal controller calculates the control quantity of an accelerator and a brake based on the speed planning information, and the drive-by-wire chassis executes a control instruction to realize the speed control of the vehicle. Commonly used speed planning algorithms include: 1. determining proper speed and acceleration of the vehicle according to the relative position and relative speed of the vehicle and a vehicle following target right in front of the route; 2. the driving path of the vehicle is predicted, whether the vehicle collides with the vehicle when changing lanes is judged, and if the vehicle collides, the vehicle outputs a control curve for early deceleration according to the relative distance and the relative speed of the vehicle, so as to control the speed and the acceleration of the vehicle (refer to patent document CN 108032858A).
However, the speed planning algorithm is applied in a single scene, and in a real scene, a road congestion situation occurs sometimes, and there are many vehicles on a vehicle running track, for example, the vehicle has an obstacle not only right ahead of a route, but also more than one vehicle beside the vehicle is merged onto the vehicle lane.
Disclosure of Invention
In view of this, the embodiment of the invention provides a self-adaptive speed planning method, a self-adaptive speed planning device and a domain controller, so that the accurate obstacle avoidance of the automatic driving of an automobile in a multi-obstacle scene is realized.
According to a first aspect, an embodiment of the present invention provides an adaptive speed planning method, where the method includes: judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle; selecting an obstacle target with the closest relative distance from obstacle targets which are collided as following targets, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle target is positioned on the planned path of the vehicle; and planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameters of the vehicle and the state parameters of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameters comprise speed, course and position.
Optionally, the method further comprises: when the vehicle runs according to the speed control scheme, judging whether the obstacle target sensed by the vehicle collides with the vehicle on the planned path of the vehicle again within a first preset time; and if the collision obstacle targets exist, returning to the step of selecting the obstacle target with the closest relative distance from the collision obstacle targets as the following vehicle target.
Optionally, the determining whether the obstacle target perceived by the host vehicle collides with the host vehicle on the planned path of the host vehicle includes: predicting the course of the vehicle at each position on the planned path of the vehicle, and predicting an entry point of a current obstacle target into the planned path of the vehicle; predicting the running position and the running speed of the vehicle on the planned path of the vehicle when the current obstacle target cuts into the planned path of the vehicle; determining the cut-in speed of the current obstacle target on the cut-in point based on the course of the vehicle at each position on the planned path of the vehicle; and determining whether the vehicle collides with the current obstacle target by using a collision detection distance, the cut-in speed, the running speed, the vehicle length and the current obstacle target length, wherein the collision detection distance is the distance between the cut-in point and the running position.
Optionally, the planning a speed control scheme based on the relative distance between the host vehicle and the following target, the state parameter of the host vehicle, and the state parameter of the following target includes: calculating the relative speed of the vehicle and the following target based on the current state parameter of the vehicle and the current predicted state parameter of the following target; determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle; performing linear programming calculation by using the relative distance between the vehicle and the following target, the relative speed between the vehicle and the following target, the expected vehicle speed and the current vehicle speed of the vehicle, and outputting a first acceleration control quantity; calculating a vehicle predicted state parameter of the vehicle after a second preset time by using the first acceleration control quantity; taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, taking the state parameter predicted after the following target for a second preset time as the current predicted state parameter of the following target, returning to the step of calculating the relative speed of the vehicle and the following target based on the current state parameter of the vehicle and the current predicted state parameter of the following target, and performing iterative calculation; and generating the speed control scheme based on the vehicle predicted state parameters obtained by each iteration.
Optionally, if the obstacle target perceived by the host vehicle does not collide with the host vehicle on the planned path of the host vehicle, the method further includes: and planning the speed of the vehicle based on the vehicle path speed limit information on the vehicle planned path.
Optionally, the speed planning of the vehicle based on the vehicle path speed limit information on the planned path of the vehicle includes: determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle; calculating a second acceleration control quantity of the vehicle based on the distance between the vehicle and the next speed limit point, the expected vehicle speed and the current vehicle speed of the vehicle; calculating the predicted state parameter of the vehicle after a second preset time by using the second acceleration control quantity; taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, returning to the step of determining the expected vehicle speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle, and performing iterative computation; and generating a constant speed control scheme based on the vehicle predicted state parameters obtained by each iteration so as to control the vehicle to run according to the constant speed control scheme.
Optionally, the determining the desired vehicle speed of the host vehicle based on the current state parameter of the host vehicle and the host vehicle path speed limit information includes: calculating a distance to be traveled and a first deceleration distance based on the current state parameter of the vehicle and the path speed limit information of the vehicle, wherein the distance to be traveled is a distance between the vehicle and a next speed limit point, and the first deceleration distance is a distance required for deceleration when the current vehicle speed of the vehicle is higher than the speed limit value of the next speed limit point; when a first condition or a second condition is met, the expected speed is equal to the speed limit value of the next speed limit point, and when a third condition or a fourth condition is met, the expected speed is equal to the current speed limit value; the first condition is that the speed limit value of the next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is not more than zero; the second condition is that the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is smaller than a preset threshold value; the third condition is that the speed limit value of the next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is greater than zero; and under the fourth condition, the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is not smaller than a preset threshold value.
Optionally, the determining whether the vehicle collides with the current obstacle target by using the collision detection distance, the cut-in speed, the running speed, the vehicle length, and the current obstacle target length includes: when the cut-in speed is greater than or equal to the running speed, judging whether the collision detection distance is not greater than a first safety distance, and if the collision detection distance is not greater than the first safety distance, determining that the vehicle collides with the current obstacle target; when the cut-in speed is smaller than the running speed, judging whether the collision detection distance is not larger than a second safe distance, and if the collision detection distance is not larger than the second safe distance, determining that the vehicle collides with the current obstacle target; the first safe distance is obtained by summing up and calculating a second deceleration distance when the obstacle target decelerates to the running speed, the length of the vehicle, the length of the current obstacle target and a preset safe threshold value; and the second safety distance is obtained by summing the length of the vehicle, the length of the current obstacle target and a preset safety threshold.
According to a second aspect, an embodiment of the present invention provides an adaptive speed planning apparatus, including: the collision detection unit is used for judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle; the vehicle following target unit is used for selecting an obstacle target with the closest relative distance from obstacle targets which can collide as a vehicle following target, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle target is positioned on the planned path of the vehicle; and the speed planning unit is used for planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameter of the vehicle and the state parameter of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameter comprises speed, course and position.
According to a third aspect, an embodiment of the present invention provides a domain controller, including: the sensing processing unit, the decision processing unit, the control processing unit and the communication unit are connected in a communication manner, the decision processing unit stores computer instructions, and the decision processing unit executes the computer instructions to execute the method provided by any optional implementation manner of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions for causing a computer to thereby perform the method described in the first aspect, or any one of the optional implementation manners of the first aspect.
The technical scheme provided by the application has the following advantages:
according to the technical scheme, when a vehicle senses obstacle targets such as nearby vehicles through sensing equipment such as a radar and the like in a multi-obstacle scene, whether the sensed obstacle targets collide with the vehicle in the future is judged, the obstacle targets sensed by the vehicle may be located on a planned path of the vehicle or may cut into the planned path of the vehicle in the future, and then the vehicle selects one closest to the vehicle when the obstacle targets are located on the path of the vehicle as a following target from all the obstacle targets sensed to collide, so that the vehicle performs adaptive speed regulation and control, and under the condition that the following target is not collided, other targets far away from the following target are avoided. Therefore, the success rate of the obstacle avoidance of the vehicle in a multi-obstacle scene is improved.
In addition, in one embodiment, collision detection is also performed continuously while the host vehicle is traveling according to the planned speed control scheme, and it is highly likely that a rear-end collision or rear-end collision will occur or be caused during deceleration of the host vehicle, taking into account other vehicles that are not otherwise colliding. Therefore, once the vehicle judges again that the obstacle target sensed by the vehicle and the vehicle generate a new collision accident on the planned path of the vehicle, the vehicle returns to the step of selecting the following target, reselects the following target and regenerates a new speed control scheme, thereby realizing an accurate and reliable multi-obstacle avoidance function. In one embodiment of the present application, when the speed of the host vehicle is planned regardless of whether a collision occurs or not, the host vehicle path speed limit information of each link on the planned path of the host vehicle is introduced, so that the vehicle speed is maximized without exceeding the host vehicle path speed limit information and without causing a collision, thereby saving the travel time.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are schematic and are not to be understood as limiting the invention in any way, and in which:
FIG. 1 is a schematic diagram illustrating the steps of an adaptive speed planning method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for adaptive speed planning according to an embodiment of the present invention;
FIG. 3 illustrates a multi-obstacle target scenario in accordance with an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an adaptive speed planning apparatus according to an embodiment of the present invention;
fig. 5 shows a schematic structure of a domain controller according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1, in an embodiment, an adaptive speed planning method includes the following steps:
step S101: and judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle.
Step S102: and selecting the obstacle target with the closest relative distance from the obstacle targets which are collided as the following vehicle targets, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle target is positioned on the planned path of the vehicle.
Step S103: and planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameter of the vehicle and the state parameter of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameter comprises speed, course and position.
Specifically, in the embodiment of the present invention, the state parameters of the vehicle and the state parameters of the obstacle target, including but not limited to the speed, the course, and the position of the vehicle and the obstacle target, are obtained in advance through sensing devices such as a positioning radar, a sensing radar, a camera, and a signal collector on the vehicle. The above-mentioned related data are regarded as known in the embodiments of the present invention, and the specific obtaining method can refer to the prior art, and is not described herein again.
Based on this, in the embodiment of the present invention, it is possible to determine whether the host vehicle collides with a nearby obstacle target that is perceived by the host vehicle, based on the data such as the state parameter of the host vehicle, the acquired planned path of the host vehicle, the state parameters of the predicted obstacle targets, and the predicted paths of the obstacle targets (collision manners include, but are not limited to, a host vehicle rear-end collision obstacle target and an obstacle target rear-end collision host vehicle, where the host vehicle travels at a current speed or in a steady acceleration scheme, and a scene that can safely surmount the obstacle target is also a case where the collision does not occur), and if the host vehicle determines that at least one obstacle target collides with the host vehicle, the host vehicle enters the adaptive speed planning process. After the vehicle enters the adaptive speed planning process, the number of vehicles which are collided at present is analyzed, and in an actual application scene, obstacle targets (assumed to be obstacle vehicles) may already run on the planned path of the vehicle, or may be subjected to parallel line from the side, and will cut into the planned path of the vehicle to run in the future. Therefore, in the present embodiment, based on the relative distance between the host vehicle and the obstacle target (the relative distance includes the distance between the host vehicle and the obstacle target that is already currently located on the planned path of the host vehicle, and the distance between the cut-in point of another obstacle target to be cut into the planned path of the host vehicle and the host vehicle in the future), the obstacle target with the closest relative distance is selected as the following target, and then linear programming calculation is performed according to the relative distance between the host vehicle and the following target, the state parameter of the host vehicle, and the state parameter of the following target, so as to realize regulation and control of acceleration and speed, thereby generating a speed control scheme with the fastest speed without colliding with the following target. The intelligent automobile is driven according to the speed control scheme, and under the condition that the automobile does not collide with the automobile following target, other obstacle targets which are far away in relative distance and possibly collide do not collide, so that the stability and the accuracy of automatic obstacle avoidance of the intelligent automobile in a multi-obstacle scene are greatly improved.
Specifically, in an embodiment, the adaptive speed planning method provided in the embodiment of the present invention further includes the following steps:
the method comprises the following steps: when the vehicle runs according to the speed control scheme, whether the obstacle target sensed by the vehicle collides with the vehicle on the planned path of the vehicle is judged again at a first preset time.
Step two: if there is an obstacle target that has collided with, the procedure returns to the step of selecting an obstacle target that is closest in relative distance from the obstacle targets that have collided with as a following target.
Specifically, in the present embodiment, when the host vehicle is traveling in accordance with the planned speed control scheme, it is highly likely that a rear-end collision or rear-end collision will occur or be caused during deceleration of the host vehicle, taking into account other vehicles that are not otherwise colliding. Therefore, the vehicle continuously performs collision detection in the first preset time, once the vehicle judges again that a new collision accident occurs between the obstacle target sensed by the vehicle and the vehicle on the planned path of the vehicle, the vehicle returns to the step of selecting the following target, reselects the following target and regenerates a new speed control scheme. The embodiment iteratively performs collision and rear-end collision detection until an optimal vehicle following target is selected, and then an accurate and reliable multi-obstacle avoiding function is realized. In addition, compared with the traditional speed planning method for finding the global optimum based on the convex optimization theory, the method has the following advantages: the method provided by the embodiment is non-convex optimization, only local optimization needs to be considered in each iteration process, and speed planning is carried out again only when collision is detected again.
Specifically, in an embodiment, the step S101 specifically includes the following steps:
step three: and predicting the course of the vehicle at each position on the planned path of the vehicle, and predicting the entry point of the current obstacle target into the planned path of the vehicle.
Specifically, the host vehicle acquires state parameters of various obstacle targets and other related information from the sensing equipment, including the movement speed v of the obstacle targets obs Heading θ obs Position (x) obs ，y obs ) And the current heading θ of the host vehicle ego The current position (x) of the vehicle ego ，y ego ) Vehicle speed information v ego . Then, the present embodiment establishes an obstacle target predicted trajectory equation based on the above data:
y＝tanθ obs *x+(y obs -tanθ obs *x obs )
thereafter, planned route information of the vehicle planned by the vehicle is acquired from the decision processing unit, and the planned route information includes position coordinates ((x) of each time 0 ，y 0 )，(x 1 ，y 1 )，...，(x n ，y n ) And obtaining the planning path expression of the vehicle through polynomial fitting:
y＝a 0 +a 1 x+a 2 x z +…+a k x k
by combining the obstacle target predicted track equation and the vehicle planned path expression, the course theta 1 of each point of the vehicle on the vehicle planned path and the time t of the obstacle target cutting into the planned path can be calculated in And the location of the entry point (x) in ，y in )，s in 。
Step four: and predicting the running position and the running speed of the vehicle on the planned path of the vehicle when the current obstacle target cuts into the planned path of the vehicle.
Specifically, by using the entry point calculated in the third step, when the current obstacle target is cut into the planned path of the vehicle, the vehicle continues to run at the corresponding running position and running speed on the planned path of the vehicle according to the current speed scheme.
Step five: and determining the cut-in speed of the current obstacle target on the cut-in point based on the course of the vehicle at each position on the planned path of the vehicle.
Specifically, the heading of the vehicle at each position on the planned path of the vehicle is calculated by the third step, so that the cut-in speed of the obstacle target at the cut-in point can be calculated. Wherein the included angle between the obstacle target and the tangential direction of the path when the obstacle target cuts into the planned path of the vehicle is alpha 1 ＝θ obs θ 1, then calculating the obstacle at the point of entry s in Cutting speed v in the direction (i.e. tangential to the cutting point) obs_s Comprises the following steps:
v obs_s ＝v obs *cosα 1
step six: and determining whether the vehicle collides with the current obstacle target by using the collision detection distance, the cut-in speed, the running speed, the vehicle length and the current obstacle target length, wherein the collision detection distance is the distance between the cut-in point and the running position.
Specifically, the cut-in speed of the obstacle target, the running speed of the vehicle, the length of the current obstacle target, and the distance between the obstacle target and the corresponding running position of the vehicle when reaching the cut-in point (collision detection distance) are used for analyzing and judging the safety distance, so that accurate collision detection can be basically realized (in the embodiment, the collision condition includes but is not limited to the rear-end collision obstacle target of the vehicle, the vehicle directly collides with the obstacle target when cutting in, and the obstacle target is cut into the planned path of the vehicle after passing the obstacle target and then rear-end the vehicle). Compared with the collision detection method in the prior art, the algorithm is simpler and more convenient, and the calculation resources are saved.
Specifically, in this embodiment, the step six specifically includes the following steps:
step seven: when the cut-in speed is greater than or equal to the running speed, judging whether the collision detection distance is not greater than a first safety distance, and if the collision detection distance is not greater than the first safety distance, determining that the vehicle collides with the current obstacle target;
step eight: when the cut-in speed is smaller than the running speed, judging whether the collision detection distance is not larger than a second safety distance or not, and if the collision detection distance is not larger than the second safety distance, determining that the vehicle collides with the current obstacle target; the first safety distance is obtained by summing and calculating a second deceleration distance when the obstacle target decelerates to the running speed, the length of the vehicle, the length of the current obstacle target and a preset safety threshold; the second safe distance is obtained by summing the length of the vehicle, the length of the current obstacle target and a preset safe threshold value.
Specifically, the collision detection and determination process in the seventh step and the eighth step is described by the following specific formula:
if v is obs_s ≥v ego_predict When is coming into contact with
When the vehicle collides with the obstacle target or causes the obstacle target to rear-end the vehicle;
if v is obs_s ＜v ego_predict When s is ego_predict -s in ≤k 2 *L EGO +k 3 *L obs When the host vehicle is in the + dis-safe state, the host vehicle can collide with the obstacle target or cause the obstacle target to collide with the host vehicle;
in the formula, k 2 、k 3 、k 4 Is a proportion parameter configured when the algorithm is applied, and dis-safe is a preset safety threshold configured when the algorithm is applied, and can be adjusted according to actual conditions. v. of obs_s Cut-in speed, L, for obstacle target EGO Is the length of the vehicle, L obs Is the length of the obstacle target, v ego_predict When a planned path of the vehicle is cut into the obstacle target, the corresponding running speed of the vehicle is obtained; s ego_predict When a planned path of the vehicle is cut into the obstacle target, the corresponding driving position of the vehicle is determined; s in An incision position for an obstacle target; s ego_predict -s in Namely the distance (collision detection distance) between the obstacle target and the vehicle when the obstacle target cuts into the planned path of the vehicle;
and the second deceleration distance is used for representing a required second deceleration distance when the obstacle target moves faster than the vehicle and the obstacle target decelerates to the vehicle speed and reaches the vehicle speed, and the distance between the obstacle target and the vehicle is zero. Therefore, the algorithm for judging whether the obstacle target collides with the vehicle only needs to simply compare the collision detection distance with the two safety distances, so that the algorithm complexity is reduced and the overall algorithm calculation efficiency is improved on the premise of ensuring the collision detection accuracy.
Specifically, in an embodiment, the step S103 specifically includes the following steps:
step nine: and calculating the relative speed of the vehicle and the following target based on the current state parameter of the vehicle and the current predicted state parameter of the following target.
Step ten: determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle;
step eleven: performing linear programming calculation by using the relative distance between the vehicle and the following target, the relative speed between the vehicle and the following target, the expected vehicle speed and the current vehicle speed of the vehicle, and outputting a first acceleration control quantity;
step twelve: calculating the predicted state parameter of the vehicle after the second preset time by using the first acceleration control quantity;
step thirteen: taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, taking the state parameter predicted later between second presets of the following target as the current predicted state parameter of the following target, returning to the ninth step, and performing iterative computation;
fourteen steps: and generating a speed control scheme based on the vehicle predicted state parameters obtained by each iteration.
Specifically, in this embodiment, after the host vehicle determines the following target, the relative speed between the host vehicle and the following target may be calculated according to the state parameter of the host vehicle acquired in real time by the sensing device and the state parameter of the following target predicted in advance. In addition, in order to meet the dual conditions of no collision and no exceeding of the speed limit of each road section on the planned path of the vehicle, the embodiment of the invention ensures that the vehicle speed of the vehicle is optimal, and the expected vehicle speed of the vehicle is determined based on the current state parameters of the vehicle and the speed limit information of the path of the vehicle. Then, linear programming calculation is performed by using the relative distance between the host vehicle and the following target, the relative speed between the host vehicle and the following target, the expected vehicle speed and the current vehicle speed of the host vehicle, a first acceleration control quantity after a second preset time (for example, the next time) is output, and then the predicted state parameters of the host vehicle after the second preset time, namely the vehicle speed, the position, the course and the like at the next time are calculated by using the first acceleration control quantity. The concrete formula is as follows:
in the formula, x and y represent the direction and position change of the automobile, s represents the distance from the position of the automobile to the starting point of the planned path of the automobile, and T represents second preset time.
The linear programming calculation process related to the eleventh step can be realized by algorithms such as a sliding mode, an interpolation table, a PID and the like, the output result limits the acceleration control amount by using the maximum acceleration constraint of the vehicle and the maximum deceleration constraint of the vehicle, and a specific mathematical operation process of the linear programming calculation is the prior art and is not described herein again. Then, the acceleration control amount and the predicted state parameter at the next time are returned to step nine as input values, and the acceleration control amount and the predicted state parameter at the next time and the next time are iteratively calculated, thereby generating a speed control scheme based on the results of the repeated iterations(s) 0， s 1 ......s t )，(v 0， v 1 ......v t )，(a 0， a 1 ......a t ). The speed planning algorithm of the embodiment has the advantages of simple principle, small calculated amount and easy realization.
It should be noted that, in the embodiment, it is considered that due to hardware of the vehicle, there is usually a response delay, and before calculating the predicted state parameter of the vehicle, the embodiment also inputs the first acceleration control quantity into a first-order inertia link (inertia link-longitudinal kinematics model) to simulate the vehicle response delay, so as to obtain an actual response acceleration of the vehicle, and calculate the predicted state parameter of the vehicle according to the actual response acceleration of the vehicle, thereby further improving accuracy of the vehicle response speed planning result, and improving the success rate of obstacle avoidance. The first-order inertia element model provided by the embodiment is as follows:
in the formula, u represents a first acceleration control amount (similarly, u can also be applied to a second acceleration control amount calculated in the case of no obstacle), a t-1 Acceleration representing the actual response at the previous moment, a t An acceleration representing an actual response at the present time,
can be converted into
Of (1), ts represents an inertia time constant.
Finally, selecting the reference acceleration at the kth moment in the speed planning scheme, and converting the reference acceleration into brake and accelerator control quantities through a pre-calibrated relation table to realize unmanned speed planning and longitudinal control; the embodiment of the invention is based on a real-time control theory, and the reference acceleration at the 1 st moment is the control quantity calculated based on the current real vehicle state; from the 2 nd moment, the control quantity is iterated by an inertia link-longitudinal kinematic model, generally, the real-time control quantity is directly used (namely, the 1 st moment), and the kth reference acceleration control can be used in the actual vehicle debugging process and is used as a means for compensating the response delay of the system.
Specifically, in an embodiment, the adaptive speed planning method provided in the embodiment of the present invention further includes the following steps:
a fifteenth step: and if the obstacle target perceived by the vehicle does not collide with the vehicle on the planned path of the vehicle, performing speed planning on the vehicle based on the speed limit information on the planned path of the vehicle.
Specifically, in this embodiment, when the obstacle target perceived by the vehicle does not collide with the vehicle, the vehicle enters a constant speed planning process, and the constant speed planning process performs linear planning calculation only based on the speed limit information on the planned path of the vehicle without considering the collision situation, so that the optimal vehicle speed is achieved without exceeding the speed limit value of each road segment. The specific planning steps are as follows:
1. determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle;
2. calculating a second acceleration control quantity of the vehicle based on the distance between the vehicle and the next speed limit point, the expected vehicle speed and the current vehicle speed of the vehicle;
3. calculating the predicted state parameter of the vehicle after a second preset time by using the second acceleration control quantity;
4. taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, returning to the step 1, and performing iterative computation;
5. and generating a constant speed control scheme based on the vehicle predicted state parameters obtained by each iteration so as to control the vehicle to run according to the constant speed control scheme.
Specifically, the specific steps for generating the constant speed control scheme are similar to the steps for generating the speed control scheme in the adaptive speed planning process, and the difference is that the linear planning calculation process of the constant speed control scheme does not need to consider an obstacle target and does not need to introduce parameters such as relative speed. The description of other steps refers to the description related to the above step nine to step fourteen, and is not repeated here.
It should be noted that, in the constant speed control scheme, the response delay caused by the hardware factors of the vehicle is also considered, so that a first-order inertia element model is introduced to adjust the second acceleration control quantity. Further, while the vehicle is traveling according to the constant speed control plan, the vehicle is similarly subjected to collision detection for the first preset time, and when an obstacle target that can collide is found, the process returns to step S102 described above, and adaptive speed planning is performed.
Specifically, in an embodiment, the step ten and the step 1 specifically include the following steps:
sixthly, the steps are as follows: calculating a distance to be traveled and a first deceleration distance based on the current state parameter of the vehicle and the path speed limit information of the vehicle, wherein the distance to be traveled is a distance between the vehicle and a next speed limit point, and the first deceleration distance is a distance required for deceleration when the current vehicle speed of the vehicle is higher than the speed limit value of the next speed limit point;
seventeen steps: when the first condition or the second condition is satisfied, the expected vehicle speed is equal to the speed limit value of the next speed limit point, and when the third condition or the fourth condition is satisfied, the expected vehicle speed is equal to the current speed limit value. The method comprises the following steps that the speed limit value of a next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is not more than zero under the first condition; the second condition is that the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is smaller than a preset threshold value; the third condition is that the speed limit value of the next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is greater than zero; and in the fourth condition, the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is not smaller than the preset threshold value.
Specifically, in the present embodiment, the summary of the expected vehicle speed generated based on the speed limit information of each segment of the planned path of the host vehicle is:
if the next speed-limiting point is slower than the current speed of the vehicle, calculating a first deceleration distance required by decelerating from the current vehicle speed to the speed-limiting value based on the current deceleration according to the speed-limiting value, and judging: if the distance from the vehicle to the next speed limit point to be driven is just equal to or less than the first deceleration distance, changing the expected speed of constant-speed cruising into the next speed limit value, and starting deceleration to ensure that the vehicle is decelerated in place when reaching the speed limit point; on the contrary, when the speed of the next speed limit point is higher than the current speed, the speed limit point is reached and the acceleration is started, so that the condition that the acceleration exceeds the current road section speed limit in advance is avoided.
The expression for calculating the desired vehicle speed is as follows:
dis＝s hext_limit -s now
dis need ＝k*(v next_limit 2 -v ego 2 )/(2*a min )
where dis is the distance to be traveled, s next_limit Is the position of the next speed limit point, s now Is the current position of the vehicle, dis need Is the first deceleration distance, v ego Is the current speed v of the vehicle next_limit Is the speed limit value of the next speed limit point, a min Is a maximum deceleration constraint.
In the formula, v des In order to achieve the desired speed of the vehicle,
is the current speed limit value, k 1 The speed limit position adjustment value is used for measuring the difference between the distance to be traveled and the first deceleration distance and is usually 0, but in actual application, the formula is not accurate, so that k is adjusted according to actual conditions in debugging 1 The value, for example, changed to 1 means that deceleration is started 1m ahead on the basis of the first deceleration distance.
Specifically, as shown in fig. 2 and fig. 3, in an embodiment of a practical application scenario, the above steps are further explained as follows:
the planned path of the vehicle, the vehicle speed, the heading and the position at each moment are all known, and the vehicle can sense nearby obstacle targets through a sensing device, wherein the obstacle targets include but are not limited to vehicles, pedestrians and roadblocks. The vehicle can predict the speed, the course and the position of the obstacle target at each moment through the decision processing unit.
Based on the above, the vehicle continuously detects the obstacle target in the first preset time in the driving process, if the obstacle target is not detected, a constant speed planning process is executed, the vehicle calculates the expected vehicle speed of the vehicle at each moment according to the method of the above step fifteen by combining the speed limit information of each road section on the vehicle path, then the speed planning of the vehicle is carried out under the condition that the expected vehicle speed is not exceeded, and a first-order inertia link model is introduced in the calculation process of the speed planning, so that the inaccuracy of the output acceleration control quantity caused by the response delay of the vehicle hardware is avoided. If the obstacle targets nearby appear, firstly judging whether the vehicle collides with each obstacle target, if so, entering an adaptive speed planning process, selecting the obstacle target with the closest relative distance from the obstacle targets by the vehicle, calculating the relative speed by taking the obstacle target as a following vehicle target, then performing linear planning calculation by using the relative distance, the relative speed, the expected vehicle speed and state parameters of the vehicle and the obstacle targets to obtain an optimal speed running curve which is not collided and not overspeed, namely a speed planning scheme, wherein the vehicle continuously performs collision detection during the running process of the vehicle according to the speed planning scheme so as to prevent the original non-collided obstacle target from generating new collision during the speed reduction process of the vehicle, and once the vehicle detects the new collision target, re-selecting the following vehicle target from the new collision targets, and performing speed planning, and outputting an optimal speed control scheme in the repeated iteration process.
The embodiment of the invention applies a self-adaptive control method to the field of unmanned speed planning, provides a speed planning method based on self-adaptive control, and can realize the functions of starting, following, stopping and cruise control at constant speed. Compared with the traditional speed planning method based on the convex optimization theory, the technical scheme provided by the embodiment of the invention has the advantages of no complex solving operation and low computing resource occupation; based on a real-time control theory, no solution failure problem exists; the speed planning result does not need secondary smoothing processing; planning and controlling integrated design, and simplifying algorithm structure. On the basis of introducing the barrier prediction information, path planning information and global speed limit information are introduced to serve as speed planning prior information to further improve the practicability of speed planning. The problem of response constraint of a controller and vehicle instruction execution delay is considered, the embodiment of the invention establishes an inertia link-longitudinal kinematics model to simulate vehicle real-time response feedback, outputs a control quantity in a prediction period and generates a next-time state quantity through the inertia link-longitudinal kinematics model feedback, and then iteratively predicts the future state parameters of the vehicle, so that more accurate basis can be provided for collision detection, and the controller is prevented from responding mistakenly and affecting the control effect; in the embodiment, the optimal car following target is selected through iterative collision detection, and the problem that the obstacle target car can collide with the car after passing the obstacle target which is about to enter the driving track is considered.
As shown in fig. 4, the present embodiment further provides an adaptive speed planning apparatus, which includes:
the collision detection unit 101 is configured to determine whether the obstacle target perceived by the host vehicle collides with the host vehicle on the planned path of the host vehicle. For details, refer to the related description of step S101 in the above method embodiment, and details are not repeated herein.
And a following target unit 102, configured to select, as a following target, an obstacle target closest to a relative distance from the current position of the host vehicle when each obstacle target is located on the planned path of the host vehicle, from among the obstacle targets that may collide with each other. For details, refer to the related description of step S102 in the above method embodiment, and details are not repeated herein.
The speed planning unit 103 is configured to plan a speed control scheme based on a relative distance between the host vehicle and the following target, a state parameter of the host vehicle, and a state parameter of the following target, so as to control the host vehicle to travel according to the speed control scheme, where the state parameter includes a speed, a heading, and a position. For details, refer to the related description of step S103 in the above method embodiment, and no further description is provided here.
The adaptive speed planning apparatus provided in the embodiment of the present invention is configured to execute the adaptive speed planning method provided in the above embodiment, and the implementation manner and the principle thereof are the same, and details are referred to the related description of the above method embodiment and are not described again.
Fig. 5 shows a domain controller according to an embodiment of the present invention, where the domain controller includes at least a sensing processing unit 901, a decision processing unit 902, a control processing unit 903, and a communication unit 904, where the sensing processing unit 901, the decision processing unit 902, the control processing unit 903, and the communication unit 904 may be communicatively connected to each other through a bus or in another manner, and fig. 5 illustrates a bus manner as an example.
In this embodiment, the sensing processing unit 901 and the decision processing unit 902 respectively include independent processors, and the sensing processing unit 901 and the decision processing unit 902 may respectively include independent memories, or may use a shared memory.
In the embodiment of the present invention, the sensing processing unit 901 is mainly applied to an engineering machinery scene, and mainly functions as: the image data acquired from the camera is subjected to sensing fusion processing to obtain the environmental information of the environment where the current engineering machinery is located, and then the environmental information is sent to the control processing unit 903 or the decision processing unit 902 according to the data type of the environmental information signal.
The decision processing unit 902 is mainly used for making a driving or operating strategy after information fusion such as surrounding environment, operating scene, vehicle state and the like, and finally sending a control command. The communication unit 904 is mainly used for communicating with the cloud server, uploading the relevant state and information of the device to the cloud service, and requesting the cloud server to assist in computing processing. The control processing unit 903 is mainly used for conversion of communication protocols between signals.
Those skilled in the art will appreciate that all or part of the processes in the methods of the embodiments described above can be implemented by a computer program to instruct related hardware, the implemented program can be stored in a computer readable storage medium and executed by the decision processing unit 902, and the program can include the processes of the embodiments of the methods described above when executed. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
Since the calculation task of the decision processing unit 902 is relatively heavy, especially relating to processing of artificial intelligence, neural network and data training, in this embodiment, the decision processing process may also be completed by using the computing resources in the cloud. In other words, the location of the storage medium storing the program instructions/modules corresponding to the method in the foregoing method embodiment includes the domain controller and the cloud server, and the cloud server receives the relevant image data sent by the domain controller, and then by running the executable program stored in the storage medium of the cloud server, the method for extracting the scene image feature in the foregoing method embodiment is implemented. In this embodiment, the cloud service may be a central server or an edge server.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (11)
1. An adaptive velocity planning method, the method comprising:
judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle;
selecting an obstacle target with the closest relative distance from obstacle targets which are collided as following targets, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle target is positioned on the planned path of the vehicle;
and planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameters of the vehicle and the state parameters of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameters comprise speed, course and position.
2. The method of claim 1, further comprising:
when the vehicle runs according to the speed control scheme, judging whether the obstacle target sensed by the vehicle collides with the vehicle on the planned path of the vehicle again within a first preset time;
and if the collision obstacle targets exist, returning to the step of selecting the obstacle target with the closest relative distance from the collision obstacle targets as the following target.
3. The method of claim 1, wherein determining whether the obstacle target perceived by the host vehicle and the host vehicle will collide with each other on the planned path of the host vehicle comprises:
predicting the course of the vehicle at each position on the planned path of the vehicle, and predicting an entry point of a current obstacle target into the planned path of the vehicle;
predicting the running position and the running speed of the vehicle on the planned path of the vehicle when the current obstacle target cuts into the planned path of the vehicle;
determining the cut-in speed of the current obstacle target on the cut-in point based on the course of the vehicle at each position on the planned path of the vehicle;
and determining whether the vehicle collides with the current obstacle target by using a collision detection distance, the cut-in speed, the running speed, the vehicle length and the current obstacle target length, wherein the collision detection distance is the distance between the cut-in point and the running position.
4. The method of claim 1, wherein the planning a speed control scheme based on the relative distance of the host vehicle to the following target, the state parameter of the host vehicle, and the state parameter of the following target comprises:
calculating the relative speed of the vehicle and the following target based on the current state parameter of the vehicle and the current predicted state parameter of the following target;
determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle;
performing linear programming calculation by using the relative distance between the vehicle and the following target, the relative speed between the vehicle and the following target, the expected vehicle speed and the current vehicle speed of the vehicle, and outputting a first acceleration control quantity;
calculating a vehicle predicted state parameter of the vehicle after a second preset time by using the first acceleration control quantity;
taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, taking the state parameter predicted after the following target for a second preset time as the current predicted state parameter of the following target, returning to the step of calculating the relative speed of the vehicle and the following target based on the current state parameter of the vehicle and the current predicted state parameter of the following target, and performing iterative calculation;
and generating the speed control scheme based on the predicted state parameters of the vehicle obtained by each iteration.
5. The method of claim 1, wherein if no collision between the obstacle target perceived by the host vehicle and the host vehicle occurs on the planned path of the host vehicle, the method further comprises:
and planning the speed of the vehicle based on the vehicle path speed limit information on the vehicle planned path.
6. The method of claim 5, wherein the speed planning of the host vehicle based on the speed limit information of the host vehicle path on the planned path of the host vehicle comprises:
determining the expected speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle;
calculating a second acceleration control quantity of the vehicle based on the distance between the vehicle and the next speed limit point, the expected vehicle speed and the current vehicle speed of the vehicle;
calculating the predicted state parameter of the vehicle after a second preset time by using the second acceleration control quantity;
taking the predicted state parameter of the vehicle as the current state parameter of the vehicle, returning to the step of determining the expected vehicle speed of the vehicle based on the current state parameter of the vehicle and the path speed limit information of the vehicle, and performing iterative computation;
and generating a constant speed control scheme based on the vehicle predicted state parameters obtained by each iteration so as to control the vehicle to run according to the constant speed control scheme.
7. The method of claim 4 or 6, wherein determining the desired vehicle speed of the host vehicle based on the current state parameters of the host vehicle and the host vehicle path speed limit information comprises:
calculating a distance to be traveled and a first deceleration distance based on the current state parameter of the vehicle and the path speed limit information of the vehicle, wherein the distance to be traveled is a distance between the vehicle and a next speed limit point, and the first deceleration distance is a distance required for deceleration when the current vehicle speed of the vehicle is higher than the speed limit value of the next speed limit point;
when a first condition or a second condition is met, the expected speed is equal to the speed limit value of the next speed limit point, and when a third condition or a fourth condition is met, the expected speed is equal to the current speed limit value;
the first condition is that the speed limit value of the next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is not more than zero; the second condition is that the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is smaller than a preset threshold value; the third condition is that the speed limit value of the next speed limit point is not less than the current speed of the vehicle, and the distance to be traveled is greater than zero; and under the fourth condition, the speed limit value of the next speed limit point is smaller than the current speed of the vehicle, and the difference between the distance to be traveled and the first deceleration distance is not smaller than a preset threshold value.
8. The method of claim 3, wherein determining whether the host vehicle will collide with the current obstacle target using the collision detection distance, the cut-in speed, the travel speed, the host vehicle length, and the current obstacle target length comprises:
when the cut-in speed is greater than or equal to the running speed, judging whether the collision detection distance is not greater than a first safety distance, and if the collision detection distance is not greater than the first safety distance, determining that the vehicle collides with the current obstacle target;
when the cut-in speed is smaller than the running speed, judging whether the collision detection distance is not larger than a second safe distance, and if the collision detection distance is not larger than the second safe distance, determining that the vehicle collides with the current obstacle target;
the first safety distance is obtained by summing a second deceleration distance when the obstacle target decelerates to the running speed, the length of the vehicle, the length of the current obstacle target and a preset safety threshold; and the second safety distance is obtained by summing the length of the vehicle, the length of the current obstacle target and a preset safety threshold.
9. An adaptive velocity planning apparatus, the apparatus comprising:
the collision detection unit is used for judging whether the obstacle target perceived by the vehicle collides with the vehicle on the planned path of the vehicle;
the following target unit is used for selecting an obstacle target with the closest relative distance from obstacle targets which can collide as a following target, wherein the relative distance is the distance between each obstacle target and the current position of the vehicle when the obstacle targets are positioned on the planned path of the vehicle;
and the speed planning unit is used for planning a speed control scheme based on the relative distance between the vehicle and the vehicle following target, the state parameter of the vehicle and the state parameter of the vehicle following target so as to control the vehicle to run according to the speed control scheme, wherein the state parameter comprises speed, course and position.
10. A domain controller, comprising:
a perception processing unit, a decision processing unit, a control processing unit and a communication unit, wherein the perception processing unit, the decision processing unit, the control processing unit and the communication unit are connected with each other in a communication manner, the decision processing unit stores computer instructions, and the decision processing unit executes the computer instructions so as to execute the method according to any one of claims 1-8.
11. A computer-readable storage medium having stored thereon computer instructions for causing a computer to thereby perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210663745.0A CN114932901A (en) | 2022-06-10 | 2022-06-10 | Self-adaptive speed planning method and device and domain controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210663745.0A CN114932901A (en) | 2022-06-10 | 2022-06-10 | Self-adaptive speed planning method and device and domain controller |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114932901A true CN114932901A (en) | 2022-08-23 |
Family
ID=82866758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210663745.0A Pending CN114932901A (en) | 2022-06-10 | 2022-06-10 | Self-adaptive speed planning method and device and domain controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114932901A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115520225A (en) * | 2022-11-25 | 2022-12-27 | 小米汽车科技有限公司 | Vehicle obstacle avoidance method, device, medium and vehicle |
| CN115848371A (en) * | 2023-02-13 | 2023-03-28 | 智道网联科技(北京)有限公司 | ACC system control method, device, electronic equipment and storage medium |
| CN116061933A (en) * | 2023-03-31 | 2023-05-05 | 深圳海星智驾科技有限公司 | Vehicle speed planning method and device based on speed limiting information and domain controller |
-
2022
- 2022-06-10 CN CN202210663745.0A patent/CN114932901A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115520225A (en) * | 2022-11-25 | 2022-12-27 | 小米汽车科技有限公司 | Vehicle obstacle avoidance method, device, medium and vehicle |
| CN115520225B (en) * | 2022-11-25 | 2023-03-14 | 小米汽车科技有限公司 | Vehicle obstacle avoidance method, device, medium and vehicle |
| CN115848371A (en) * | 2023-02-13 | 2023-03-28 | 智道网联科技(北京)有限公司 | ACC system control method, device, electronic equipment and storage medium |
| CN116061933A (en) * | 2023-03-31 | 2023-05-05 | 深圳海星智驾科技有限公司 | Vehicle speed planning method and device based on speed limiting information and domain controller |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7466002B2 (en) | DATA PROCESSING METHOD, DATA PROCESSING APPARATUS, COMPUTER DEVICE, AND COMPUTER PROGRAM | |
| CN107848531B (en) | Vehicle control device, vehicle control method, and medium storing vehicle control program | |
| CN114932901A (en) | Self-adaptive speed planning method and device and domain controller | |
| JP2020119517A (en) | Method for assisting driver, driver assistance system, and vehicle having such driver assistance system | |
| US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
| RU2723010C1 (en) | Method for generating target vehicle speed and device for generating target vehicle speed for vehicle with driving assistance | |
| CN110816526A (en) | Acceleration control method and device for automatically driving vehicle to avoid threat and storage medium | |
| JP2021020580A (en) | Vehicle control device, vehicle control method, and program | |
| US11548503B2 (en) | Vehicle control system | |
| CN113165670A (en) | Intelligent driving method, device, storage medium and computer program | |
| US11840227B2 (en) | Vehicle control device, vehicle control method, and storage medium | |
| US20230148202A1 (en) | Vehicle control system | |
| CN113703436A (en) | Parallel barrier buffer system for path planning | |
| CN113348121A (en) | Method and control unit for operating an adaptive speed regulator | |
| JP2020111302A (en) | Vehicle driving support system and method | |
| EP4045370A1 (en) | Adaptive cruise control | |
| EP3857327B1 (en) | Implementation of dynamic cost function of self-driving vehicles | |
| EP3925844B1 (en) | Relative speed based speed planning for buffer area | |
| JP7125969B2 (en) | VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD, AND PROGRAM | |
| CN114763135A (en) | Vehicle running control method and device, electronic equipment and storage medium | |
| JP6599817B2 (en) | Arithmetic apparatus, arithmetic method and program | |
| EP4151490B1 (en) | Safety guaranteed control when planning with uncertainty | |
| JP2020067699A (en) | Driving support method and driving support device | |
| CN115848371B (en) | ACC system control method and device, electronic equipment and storage medium | |
| CN115520225B (en) | Vehicle obstacle avoidance method, device, medium and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |