CN117227714A - Control method and system for turning avoidance of automatic driving vehicle - Google Patents
Control method and system for turning avoidance of automatic driving vehicle Download PDFInfo
- Publication number
- CN117227714A CN117227714A CN202311515348.XA CN202311515348A CN117227714A CN 117227714 A CN117227714 A CN 117227714A CN 202311515348 A CN202311515348 A CN 202311515348A CN 117227714 A CN117227714 A CN 117227714A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- avoidance
- automatic driving
- turning
- 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 60
- 230000004888 barrier function Effects 0.000 claims abstract description 11
- 230000002452 interceptive effect Effects 0.000 claims description 56
- 230000033001 locomotion Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000000547 structure data Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides a method and a system for controlling turning avoidance of an automatic driving vehicle, and relates to the technical field of automatic driving control, wherein the method for controlling turning avoidance of the automatic driving vehicle comprises the following steps: acquiring turning information of an automatic driving vehicle, barrier information and signal lamp information within a set range, wherein the turning information comprises a turning path and a running speed of the automatic driving vehicle, the barrier comprises pedestrians and interference vehicles on a road to be turned, the barrier information comprises positions, running speeds and running directions of the pedestrians, positions, running speeds and running directions of the interference vehicles, and the signal lamp information comprises a steering lamp state and a road traffic lamp state of the interference vehicles; establishing a track model; calculating collision positions and collision time of the automatic driving vehicle, pedestrians and the interference vehicles according to the track model; calculating the avoiding speed of the automatic driving vehicle according to the collision position and the collision time; controlling the autonomous vehicle to turn at the avoidance speed.
Description
Technical Field
The application relates to the technical field of automatic driving control, in particular to a method and a system for controlling turning avoidance of an automatic driving vehicle.
Background
With the continuous progress of science and technology, the automatic driving vehicle is more and more concerned in various aspects, and the automatic driving vehicle is a product of the integration of technical development of automobile electronics, intelligent control, the Internet and the like. The principle is that an automatic driving system utilizes a sensing and positioning system to acquire the azimuth of the vehicle and the external environment information, the information is analyzed by a computing system, a decision is made, and a control execution system is used for realizing acceleration, deceleration or steering of the vehicle, so that the automatic driving is completed under the condition of no need of intervention of a driver.
The normal driving state of an autonomous vehicle generally includes three types, namely, lane keeping (Keep Lane, KL), lane Changing (CL), and turning (Turn), and currently, for Lane keeping, an image acquisition device (e.g., a camera) generally acquires Lane information to determine whether the vehicle is in a specified Lane, and if a Lane departure (including a left-right departure) occurs, a related control device may give an alarm signal and a deviation correction instruction. For lane changing, a sensor (for example, a vision sensor, a millimeter wave radar sensor, a laser radar sensor, etc.) is generally used for monitoring the surrounding environment of the vehicle, and corresponding perception data is provided for a lane changing algorithm of the vehicle so as to ensure that lane changing can be performed safely and accurately.
However, in the case of turning, the turning is generally performed at a lane intersection, and in this case, not only the lane changing operation is involved, but also the interfering vehicle and the pedestrian need to be avoided, and at present, no effective relevant judgment method is available, so that the relevant interfering vehicle and the pedestrian can be effectively and reasonably avoided.
Disclosure of Invention
In order to solve the technical problems in the related art, the application provides a method and a system for controlling the turning avoidance of an automatic driving vehicle.
In order to achieve the above purpose, the technical scheme adopted by the application comprises the following steps:
according to a first aspect of the present application, there is provided a method for controlling turn avoidance of an automatically driven vehicle, applied to turn avoidance of an automatically driven vehicle at a multi-lane junction, comprising:
acquiring turning information of an automatic driving vehicle, barrier information and signal lamp information within a set range, wherein the turning information comprises a turning path and a running speed of the automatic driving vehicle, the barrier comprises pedestrians and interference vehicles on a road to be turned, the barrier information comprises positions, running speeds and running directions of the pedestrians, positions, running speeds and running directions of the interference vehicles, and the signal lamp information comprises a steering lamp state and a road traffic lamp state of the interference vehicles;
establishing a track model;
calculating collision positions and collision time of the automatic driving vehicle, pedestrians and the interference vehicles according to the track model;
calculating the avoiding speed of the automatic driving vehicle according to the collision position and the collision time;
controlling the autonomous vehicle to turn at the avoidance speed.
Optionally, when the autonomous vehicle turns right from the first lane into the second lane;
the acquired obstacle information includes: a position of an interfering vehicle waiting on a straight-going lane within a second lane, a position of an interfering vehicle turning left from a first lane into a second lane in the same direction as the autonomous vehicle, a traveling speed and a traveling direction, and a position, a traveling speed and a traveling direction of a pedestrian on a second lane into which the autonomous vehicle intends to merge;
the acquired signal lamp information comprises the following components: traffic light information on the first lane and the second lane, and a turn light status of the interfering vehicle.
Optionally, the acquired obstacle information further includes: the position, the travel speed and the travel direction of the interfering vehicle on the second lane, which is in the same direction as the autonomous vehicle, are merged from the second lane.
Optionally, the autonomous vehicle is merging from the first lane to the second lane while turning left;
the acquired obstacle information includes: a position of an interfering vehicle waiting on a straight-going lane within a second lane, a position of an interfering vehicle turning right from a first lane into a second lane in the same direction as the autonomous vehicle, a traveling speed and a traveling direction, and a position, a traveling speed and a traveling direction of a pedestrian on a second lane into which the autonomous vehicle intends to merge;
the acquired signal lamp information comprises the following components: traffic light information on the first lane and the second lane, and a turn light status of the interfering vehicle.
Optionally, the acquired obstacle information further includes: in the first lane, the position, the travel speed and the travel direction of the straight-going interfering vehicle traveling opposite the autonomous vehicle, and/or,
the position, the running speed and the running direction of the interfering vehicle which is led into the first lane from the second lane are changed to the right.
Optionally, the establishing the trajectory model includes:
establishing a target vehicle-road model by combining road information;
the obstacle information is imported into a vehicle-road model, and the vehicle-obstacle-road model is built;
and respectively calculating the motion trail of the automatic driving vehicle, the motion trail of the interference vehicle and the motion trail of the pedestrian to generate a trail model.
Optionally, the calculating process of the avoidance speed includes:
setting a vehicle-person safety distance threshold, calculating the collision position and collision time of an automatic driving vehicle and a pedestrian, taking the current position of the automatic driving vehicle as a starting point, taking the collision position of the automatic driving vehicle and the pedestrian as an end point, marking the vehicle-person safety distance threshold on the starting point-end point path by taking the collision position as the center, so as to obtain a vehicle-person avoidance range, calculating the vehicle-person avoidance time from the current position of the pedestrian to the passing vehicle-person avoidance range, and calculating the first avoidance speed of the automatic driving vehicle according to the vehicle-person avoidance time and the length of the starting point-end point path; and/or the number of the groups of groups,
setting a vehicle-vehicle safety distance threshold, calculating the collision position and the collision time of the automatic driving vehicle and the interference vehicle, taking the current position of the automatic driving vehicle as a starting point, taking the collision position of the automatic driving vehicle and the interference vehicle as an ending point, marking the vehicle-vehicle safety distance threshold on the starting point-ending point path by taking the collision position as a center to obtain a vehicle-vehicle avoidance range, calculating the vehicle-vehicle avoidance time from the current position of the interference vehicle to the passing vehicle-vehicle avoidance range, and calculating the second avoidance speed of the automatic driving vehicle according to the vehicle-vehicle avoidance time and the length of the starting point-ending point path.
According to a second aspect of the present application, there is provided an automatic driving vehicle turning avoidance control system, which is applied to the automatic driving vehicle turning avoidance control method according to any one of the first aspect of the present application, the automatic driving vehicle turning avoidance control system comprising:
the acquisition module is used for acquiring turning information of the automatic driving vehicle, barrier information and signal lamp information within a set range;
the calculation module is used for calculating the avoiding speed and outputting the avoiding speed to the vehicle control device.
According to a third aspect of the present application, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor being capable of implementing the method for controlling the avoidance of a turn of an autonomous vehicle according to any one of the first aspect of the present application when executing the computer program.
According to a fourth aspect of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is capable of implementing the automatic driving vehicle turning avoidance control method according to any one of the first aspect of the present application.
The beneficial effects are that:
1. through the above technical solution, in one aspect, the turning avoidance control method of the present application is based on the turning information of the autonomous vehicle itself, that is, the turning avoidance control method of the present application can be effectively adapted to the kinematic parameters (for example, turning radius) of the autonomous vehicle, so as to be adapted to the autonomous vehicle with any kinematic parameters. On the other hand, the path avoidance method is simple in path avoidance calculation, few in related parameters and capable of effectively avoiding the problem of path planning delay. In still another aspect, the turning control avoidance method of the present application not only considers an interfering vehicle, but also uses a pedestrian that may collide as another constraint, and can be effectively applied to an application scenario in which a pedestrian that is passing by exists on a lane where the vehicle is to turn. Therefore, the control method for avoiding the turning of the automatic driving vehicle can not only effectively avoid the collision of the automatic driving vehicle with the possibly collided interference vehicle or the pedestrian, but also meet the requirement that the automatic driving vehicle smoothly and safely completes the turning action.
2. Other benefits or advantages of the application will be described in detail with reference to specific structures in the detailed description.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art. Furthermore, it should be understood that the scale of each component in the drawings in this specification is not represented by the scale of actual material selection, but is merely a schematic diagram of structures or positions, in which:
FIG. 1 is a flow chart illustrating steps of an autonomous vehicle turn avoidance control method according to an exemplary embodiment of the present application;
FIG. 2 is a schematic illustration of an avoidance process for an autonomous vehicle turning in a right turn provided by an exemplary embodiment of the present application;
fig. 3 is a schematic diagram of an avoidance process of an automatic driving vehicle turning in a left turn according to an exemplary embodiment of the present application.
The reference numerals in the drawings indicate:
100-first lane; 200-second lane; 1-automatically driving a vehicle; 21-an interfering vehicle; 22-pedestrians.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Furthermore, references to the terms "comprising" and "having" and any variations thereof in the description of the present application are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the following, some related terms and techniques involved in the embodiments of the present application are explained.
1) MLP (Multilayer Perceptron, multi-layer perceptron), a deep learning model based on a feed-forward neural network (FeedforwardNeural Network), is composed of multiple neuron layers, where each neuron layer is fully connected to the previous layer. The multi-layer perceptron can be used for solving various machine learning problems such as classification, regression, clustering and the like.
2. GNN (Graph Neural Network ) is a class of deep learning models used to process graph structure data. Entities in the graph structure data are represented in the form of nodes, and relationships between the entities are represented in the form of edges. The goal of GNNs is to learn useful representations from graph structure data and use these representations for various tasks such as node classification, graph classification, link prediction, etc.
In order to facilitate the technical solution of the present application to be more clearly and accurately understood by the relevant technicians, the following description is made in more detail in the related art.
In the related art, for a vehicle lane-changing obstacle avoidance motion model, for example, the bulletin number is: CN110893849B (a method and a device for controlling obstacle avoidance and lane change of an autopilot) is a chinese patent document, which determines whether collision occurs by obtaining the relative speed and distance between an obstacle and the autopilot, so as to determine whether an obstacle avoidance lane change is required, and when the obstacle avoidance lane change is required, calculates a lane change pre-aiming distance, thereby leading to a safe lane change. However, this method cannot smoothly complete the turning action when applied to the turning situation, in the event of a collision. Other technologies related to vehicle turning lane change control methods generally focus on the selection of a turning path (for example, CN103646298B, an automatic driving method and system), or on a more optimal path algorithm (for example, CN110286671B, an automatic driving vehicle path generation method based on a turning curve).
That is, the related art basically uses path avoidance as a core to meet the safety of turning or lane changing, but, in the first place, for an autonomous vehicle, the path planning of the turning process is limited by the kinematic parameters of the vehicle, and it may not be possible to accurately turn or avoid according to the planned path. Secondly, the existing calculation process of path avoidance is complex, more parameters are involved, and in the turning process, the problem of path planning hysteresis easily occurs, so that avoidance failure or poor avoidance effect is caused. Third, at an intersection where a vehicle is allowed to turn, for example, an intersection where the vehicle is allowed to turn left, there may occur a phenomenon that a pedestrian who is passing on a lane where the vehicle is to turn, and the influence of the pedestrian who is to travel on the lane where the vehicle is to turn is not generally taken into consideration in the conventional path avoidance.
In view of this, there is a need for a solution that can be applied to turning control so as to be able to achieve smooth turning control while avoiding a collision with a vehicle or a pedestrian that may be involved in a collision.
The technical idea of the application is as follows: according to the acquired turning information of the automatic driving vehicle, obstacle information and signal lamp information in a set range, the time of a position where collision is likely to occur is calculated in advance, and the avoiding speed of the automatic driving vehicle is calculated according to the collision time and the position, so that the situation that the automatic driving vehicle is interfered with the vehicle and pedestrians is avoided, and turning actions can be completed.
The technical scheme of the application is described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1 to 3, according to a first aspect of the present application, there is provided a method for controlling turn avoidance of an automatically driven vehicle, applied to turn avoidance of an automatically driven vehicle at a multi-lane junction, including the steps of:
step S1: the turning information of the autonomous vehicle 1, which includes the turning path and the traveling speed of the autonomous vehicle 1, the obstacle including the pedestrian 22 and the interfering vehicle 21 on the road to be steered, the traveling speed and the traveling direction of the pedestrian 22, the position, the traveling speed and the traveling direction of the interfering vehicle 21, and the signal lamp information including the turn signal lamp state and the road traffic light state of the interfering vehicle 21 are acquired.
In this embodiment, the turning information of the autonomous vehicle 1 itself may be directly acquired by a controller of the autonomous vehicle 1 itself or a related control unit, and the obstacle information and the signal lamp information may be acquired by related sensors (for example, a vision sensor, a millimeter wave radar sensor, a laser radar sensor, etc.) or image acquisition devices (for example, cameras).
Step S2: and establishing a track model.
In this embodiment, the trajectory model may be generated based on the autonomous vehicle 1, with road information as a boundary constraint, in combination with acquired turning information of the autonomous vehicle 1, obstacle information within a set range, and traffic light information. The trajectory model may include a polyline sub-model, which may be implemented by a multi-layer perceptron (MLP, multilayer Perceptron) structure, and a global graph model, which may be implemented using a graph neural network (GNN, graph Neural Network).
Step S3: the collision position and the collision time of the autonomous vehicle 1 with the pedestrian 22, the interfering vehicle 21 are calculated from the trajectory model.
In this embodiment, the collision position and the collision time at which the autonomous vehicle 1 collides with the pedestrian 22 or the interfering vehicle 21 can be calculated from the obtained trajectory model, and for example, the position change, the speed, and the traveling direction of the interfering vehicle 21 can be estimated by the position change of the CELL point reflected by the obstacle (the interfering vehicle 21) by the laser radar, and also the position change, the traveling speed, and the traveling direction of the pedestrian 22 can be estimated by this method. The future movement track of the obstacle is obtained, so that the future movement track of the obstacle and the movement track of the automatic driving vehicle 1 can be fused in the same track model, and further, the future collision parameters (namely the collision position and the collision time) can be conveniently obtained.
Step S4: the collision speed of the autonomous vehicle 1 is calculated from the collision position and the collision time.
In this embodiment, after the collision position and time are obtained, the autonomous vehicle 1 can be enabled to avoid the interfering vehicle 21 and the pedestrian 22 during the turn by controlling the speed of the autonomous vehicle 1 (typically a speed lower than that of a normal turn, and may even be zero). In this way, collision with the interfering vehicle 21 or the pedestrian 22 can be effectively avoided, which is beneficial to improving the safety of the automatic driving vehicle 1 in turning, and the danger possibly occurring due to missing information acquisition can be effectively avoided due to the reduction of the turning speed, so that the safety of the automatic driving vehicle 1 in turning can be further effectively improved.
Step S5: the autonomous vehicle 1 is controlled to turn at the avoidance speed.
With the above-described technical solution, in one aspect, the turning avoidance control method of the present application is based on the turning information of the autonomous vehicle 1 itself, that is, the turning avoidance control method of the present application can be effectively adapted to the kinematic parameters (for example, turning radius) of the autonomous vehicle 1, so as to be able to be adapted to the autonomous vehicle 1 of any kinematic parameters. On the other hand, the path avoidance method is simple in path avoidance calculation, few in related parameters and capable of effectively avoiding the problem of path planning delay. In still another aspect, the turning control avoidance method of the present application not only considers the interfering vehicle 21, but also takes the pedestrian 22 that may collide as another constraint, and can be effectively applied to an application scenario in which the pedestrian 22 that is passing on the lane where the vehicle is to turn is present. Thus, the steering avoidance control method of the autonomous vehicle 1 of the present application can not only effectively avoid collision with the interfering vehicle 21 or the pedestrian 22 that may collide, but also satisfy the need for smooth and safe completion of the steering operation of the autonomous vehicle 1.
In addition, it is understood that the turning avoidance control method of the present application may be applied to intersections such as a cross, an X-shape, a T-shape, a Y-shape, etc., and the present application is not particularly limited thereto.
In one embodiment of the present application, as shown in fig. 2, when the autonomous vehicle 1 turns right from the first lane 100 into the second lane 200; the acquired obstacle information may include: the position of the interfering vehicle 21 waiting on the straight-going lane within the second lane 200, the position, traveling speed, and traveling direction of the interfering vehicle 21 turning left from the first lane 100 into the second lane 200 in the same direction as the autonomous vehicle 1, and the position, traveling speed, and traveling direction of the pedestrian 22 on the second lane 200 into which the autonomous vehicle 1 is to be incorporated; the acquired signal lamp information comprises the following components: traffic light information on the first lane 100 and the second lane 200 interferes with the turn light status of the vehicle 21.
In this way, in one aspect, the trajectory model established by the present application can include the interfering vehicle 21 stopped in the second lane 200 waiting for traffic, the interfering vehicle 21 turning left from the first lane 100 into the second lane 200 in the same direction as the autonomous vehicle 1, and the pedestrian 22 on the second lane 200 into which the autonomous vehicle 1 intends to turn to merge, by obtaining the above-described obstacle information, so as to accurately calculate the collision probability, thereby effectively ensuring the safety of the autonomous vehicle 1 of the present application in turning. On the other hand, by obtaining the signal lamp information, the lane environment information (traffic permission information and traffic prohibition information) of the established track model can be perfected so as to meet the real-time traffic operation regulations, and meanwhile, the information acquisition frequency and the operation frequency of traffic prohibition lanes can be reduced to a certain extent so as to improve the operation efficiency. In addition, the collected state of the steering lamp of the interference vehicle 21 can be used as auxiliary verification information for predicting the motion trail of the interference vehicle 21, so that accuracy of a trail model is improved.
Under prevailing traffic regulations, there may be a situation where the second lane 200 remains allowed to pass during the right turn of the autonomous vehicle 1 from the first lane 100 to the second lane 200, at which time there may be a phenomenon in which the autonomous vehicle 1 merges into the same lane at the side or the side rear thereof with the intervention vehicle 21.
In view of this, as shown in fig. 2, in one embodiment of the present application, the acquired obstacle information of the present application may further include: the position, the travel speed, and the travel direction of the interfering vehicle 21 on the second lane 200 that is in the same direction as the autonomous vehicle 1 are merged straight from the second lane 200.
In this way, by obtaining the information of the interfering vehicle 21, the track model established by the application can include the interfering vehicle 21 which is directly converged on the second lane 200 in the same direction as the automatic driving vehicle 1 from the second lane 200, so that the problem that the interfering vehicle 21 collides with the automatic driving vehicle 1 is avoided, and the safety of the automatic driving vehicle 1 in turning is further improved.
In one embodiment of the present application, as shown in fig. 3, when the autonomous vehicle 1 turns left from the first lane 100 into the second lane 200; the acquired obstacle information may include: the position of the interfering vehicle 21 waiting on the straight-going lane within the second lane 200, the position, traveling speed, and traveling direction of the interfering vehicle 21 turning right from the first lane 100 into the second lane 200 in the same direction as the autonomous vehicle 1, and the position, traveling speed, and traveling direction of the pedestrian 22 on the second lane 200 into which the autonomous vehicle 1 is to enter; the acquired signal lamp information may include: traffic light information on the first lane 100 and the second lane 200 interferes with the turn light status of the vehicle 21.
In this way, in one aspect, the trajectory model established by the present application can include the interfering vehicle 21 stopped in the second lane 200 waiting for traffic, the interfering vehicle 21 turning right from the first lane 100 into the second lane 200 in the same direction as the autonomous vehicle 1, and the pedestrian 22 on the second lane 200 into which the autonomous vehicle 1 intends to turn to merge, by obtaining the above-described obstacle information, so as to accurately calculate the collision probability, thereby effectively ensuring the safety of the autonomous vehicle 1 of the present application in turning. On the other hand, by obtaining the signal lamp information, the lane environment information (traffic permission information and traffic prohibition information) of the established track model can be perfected so as to meet the real-time traffic operation regulations, and meanwhile, the information acquisition frequency and the operation frequency of traffic prohibition lanes can be reduced to a certain extent so as to improve the operation efficiency. In addition, the collected state of the steering lamp of the interference vehicle 21 can be used as auxiliary verification information for predicting the motion trail of the interference vehicle 21, so that accuracy of a trail model is improved.
Under prevailing traffic regulations, there may be a case where the first lane 100 is still allowed to pass and the second lane 200 is allowed to turn right while the autonomous vehicle 1 is turning left from the first lane 100 to the second lane 200, and at this time, there may be a phenomenon where the interfering vehicle 21 turns right to merge into the same lane on the side or behind the autonomous vehicle 1, and a collision between a straight vehicle traveling opposite to the autonomous vehicle 1 and the autonomous vehicle 1 occurs during turning.
In view of this, in one embodiment of the present application, as shown in fig. 3, the acquired obstacle information of the present application may further include: on the first lane 100, the position, the traveling speed, and the traveling direction of the interfering vehicle 21 traveling straight in opposition to the autonomous vehicle 1, and/or the position, the traveling speed, and the traveling direction of the interfering vehicle 21 merging into the first lane 100 from the second lane 200 are turned right.
In this way, by obtaining the information of the interfering vehicle 21, the track model established by the present application can include the interfering vehicle 21 traveling straight in the opposite direction to the autonomous vehicle 1 and the interfering vehicle 21 turning right from the second lane 200 and converging into the first lane 100, so as to avoid the problem that the interfering vehicle 21 collides with the autonomous vehicle 1, which is beneficial to further improving the safety of the autonomous vehicle 1 in turning.
In one embodiment of the present application, the creating a trajectory model of the present application may include: establishing a target vehicle-road model by combining road information; the obstacle information is imported into a vehicle-road model, and the vehicle-obstacle-road model is built; the motion locus of the autonomous vehicle 1, the motion locus of the interfering vehicle 21, and the motion locus of the pedestrian 22 are calculated, respectively, to generate a locus model. Thus, by the above steps, the vehicle-obstacle-road model including the autonomous vehicle 1 and the obstacle can be effectively and accurately established, and the trajectory model can be rapidly and accurately generated.
In one embodiment of the present application, the calculation process of the avoidance speed of the present application may include:
setting a vehicle-person safety distance threshold, calculating the collision position and collision time of the automatic driving vehicle 1 and the pedestrian 22, taking the current position of the automatic driving vehicle 1 as a starting point, taking the collision position of the automatic driving vehicle 1 and the pedestrian 22 as an ending point, marking the vehicle-person safety distance threshold on the starting point-ending point path by taking the collision position as a center, obtaining a vehicle-person avoidance range, calculating the vehicle-person avoidance time of the pedestrian 22 from the current position of the pedestrian 22 to the passing vehicle-person avoidance range, and calculating the first avoidance speed of the automatic driving vehicle 1 according to the vehicle-person avoidance time and the length of the starting point-ending point path.
It will be appreciated that in this embodiment, the vehicle-person avoidance range may be a circular area centered on the collision position, or may be a rectangular area centered on the collision position, where the radius of the circular vehicle-person avoidance range may be set according to the physical dimensions of different autonomous vehicles 1 and the safe distance between pedestrians 22, and the present application is not limited specifically to the values thereof; the side length of the rectangular vehicle-person avoidance range may be set according to the physical dimensions of the different autonomous vehicles 1 and the safety distance between the pedestrians 22, and the numerical value thereof is not particularly limited by the present application.
In another embodiment of the present application, the calculation process of the avoidance speed of the present application may further include:
setting a vehicle-vehicle safety distance threshold, calculating the collision position and the collision time of the autonomous vehicle 1 and the interference vehicle 21, taking the current position of the autonomous vehicle 1 as a starting point, taking the collision position of the autonomous vehicle 1 and the interference vehicle 21 as an ending point, marking the vehicle-vehicle safety distance threshold on the starting point-ending point path by taking the collision position as a center, obtaining a vehicle-vehicle avoidance range, calculating the vehicle-vehicle avoidance time of the interference vehicle 21 from the current position of the interference vehicle 21 to the passing vehicle-vehicle avoidance range, and calculating the second avoidance speed of the autonomous vehicle 1 according to the vehicle-vehicle avoidance time and the length of the starting point-ending point path.
It will be appreciated that in this embodiment, the vehicle-to-vehicle avoidance range may be a circular area centered on the collision position, or may be a rectangular area centered on the collision position, where the radius of the circular vehicle-to-person avoidance range may be set according to the safe distance between the physical dimensions of different autonomous vehicles 1 and the physical dimensions of the interfering vehicle 21, and the present application is not limited in its numerical value; the side length of the rectangular vehicle-person avoidance range may be set according to the safety distance between the physical dimensions of the different autonomous vehicles 1 and the physical dimensions of the interfering vehicle 21, and the numerical value thereof is not particularly limited by the present application.
According to a second aspect of the present application, there is provided a turning avoidance control system of an automatically driven vehicle 1, which is applied to the turning avoidance control method of the automatically driven vehicle 1 of any one of the first aspects of the present application, the turning avoidance control system of the automatically driven vehicle 1 comprising:
an acquisition module for acquiring turning information of the autonomous vehicle 1, obstacle information within a set range, and signal lamp information;
the calculation module is used for calculating the avoiding speed and outputting the avoiding speed to the vehicle control device.
Through the technical scheme, the steering avoidance control system of the automatic driving vehicle 1 can be suitable for the automatic driving vehicle 1 with any kinematic parameter, and can also effectively avoid the problem of path planning lag. In addition, the system of the present application can also satisfy the need for smooth and safe completion of the turning action of the autonomous vehicle 1 on the basis of effectively avoiding the collision with the interfering vehicle 21 or the pedestrian 22, which may be involved in the collision.
According to the embodiment of the application, the function modules or the function units of the steering avoidance control system of the automatic driving vehicle can be divided according to the method example, for example, each function module or each function unit can be divided corresponding to each function, and two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware, or in software functional modules or functional units. The division of the modules or units in the embodiment of the present application is schematic, which is merely a logic function division, and other division manners may be implemented in practice.
According to a third aspect of the present application, there is also provided a computer-readable storage medium having instructions stored therein that, when executed on a terminal, cause the terminal to perform the steps of the method for controlling turn avoidance of an autonomous vehicle as in any of the first aspects of the present application.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access Memory (Random Access Memory, RAM), a Read-Only Memory (ROM), an erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), a register, a hard disk, an optical fiber, a portable compact disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (ApplicationSpecific Integrated Circuit, ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
According to a fourth aspect of the present application, there is also provided an electronic device comprising a processor and a communication interface, the communication interface being coupled to the processor, the processor being adapted to run a computer program or instructions to implement the steps of the method for controlling turn avoidance of an autonomous vehicle as in any of the first aspects of the present application.
The above-described processors may be implemented or executed with the various illustrative logical blocks, modules, and circuits described in connection with the present disclosure. The processor may be a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor may also be a combination that performs the function of a computation, e.g., a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, etc.
In the several embodiments provided herein, it should be understood that the disclosed systems, modules, and methods may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, indirect coupling or communication connection of devices or units, electrical, mechanical, or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The present application is not limited to the above embodiments, and any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (10)
1. The control method for avoiding the turning of the automatic driving vehicle is characterized by being applied to avoiding the turning of the automatic driving vehicle at a multi-lane junction and comprising the following steps:
acquiring turning information of an automatic driving vehicle, barrier information and signal lamp information within a set range, wherein the turning information comprises a turning path and a running speed of the automatic driving vehicle, the barrier comprises pedestrians and interference vehicles on a road to be turned, the barrier information comprises positions, running speeds and running directions of the pedestrians, positions, running speeds and running directions of the interference vehicles, and the signal lamp information comprises a steering lamp state and a road traffic lamp state of the interference vehicles;
establishing a track model;
calculating collision positions and collision time of the automatic driving vehicle, pedestrians and the interference vehicles according to the track model;
calculating the avoiding speed of the automatic driving vehicle according to the collision position and the collision time;
controlling the autonomous vehicle to turn at the avoidance speed.
2. The method for controlling cornering avoidance of an autonomous vehicle according to claim 1, characterized in that,
when the autonomous vehicle turns right from the first lane to the second lane;
the acquired obstacle information includes: a position of an interfering vehicle waiting on a straight-going lane within a second lane, a position of an interfering vehicle turning left from a first lane into a second lane in the same direction as the autonomous vehicle, a traveling speed and a traveling direction, and a position, a traveling speed and a traveling direction of a pedestrian on a second lane into which the autonomous vehicle intends to merge;
the acquired signal lamp information comprises the following components: traffic light information on the first lane and the second lane, and a turn light status of the interfering vehicle.
3. The method for controlling cornering avoidance of an autonomous vehicle according to claim 2, characterized in that,
the acquired obstacle information further includes: the position, the travel speed and the travel direction of the interfering vehicle on the second lane, which is in the same direction as the autonomous vehicle, are merged from the second lane.
4. The method for controlling cornering avoidance of an autonomous vehicle according to claim 1, characterized in that,
when the autonomous vehicle turns left from the first lane to merge into the second lane;
the acquired obstacle information includes: a position of an interfering vehicle waiting on a straight-going lane within a second lane, a position of an interfering vehicle turning right from a first lane into a second lane in the same direction as the autonomous vehicle, a traveling speed and a traveling direction, and a position, a traveling speed and a traveling direction of a pedestrian on a second lane into which the autonomous vehicle intends to merge;
the acquired signal lamp information comprises the following components: traffic light information on the first lane and the second lane, and a turn light status of the interfering vehicle.
5. The method for controlling cornering avoidance of an autonomous vehicle according to claim 4, characterized in that,
the acquired obstacle information further includes: in the first lane, the position, the travel speed and the travel direction of the straight-going interfering vehicle traveling opposite the autonomous vehicle, and/or,
the position, the running speed and the running direction of the interfering vehicle which is led into the first lane from the second lane are changed to the right.
6. The automated driving vehicle turn avoidance control method of any of claims 1-5, wherein the establishing a trajectory model comprises:
establishing a target vehicle-road model by combining road information;
the obstacle information is imported into a vehicle-road model, and the vehicle-obstacle-road model is built;
and respectively calculating the motion trail of the automatic driving vehicle, the motion trail of the interference vehicle and the motion trail of the pedestrian to generate a trail model.
7. The method for controlling cornering avoidance of an autonomous vehicle according to claim 6, characterized in that,
the calculation process of the avoidance speed comprises the following steps:
setting a vehicle-person safety distance threshold, calculating the collision position and collision time of an automatic driving vehicle and a pedestrian, taking the current position of the automatic driving vehicle as a starting point, taking the collision position of the automatic driving vehicle and the pedestrian as an end point, marking the vehicle-person safety distance threshold on the starting point-end point path by taking the collision position as the center, so as to obtain a vehicle-person avoidance range, calculating the vehicle-person avoidance time from the current position of the pedestrian to the passing vehicle-person avoidance range, and calculating the first avoidance speed of the automatic driving vehicle according to the vehicle-person avoidance time and the length of the starting point-end point path; and/or the number of the groups of groups,
setting a vehicle-vehicle safety distance threshold, calculating the collision position and the collision time of the automatic driving vehicle and the interference vehicle, taking the current position of the automatic driving vehicle as a starting point, taking the collision position of the automatic driving vehicle and the interference vehicle as an ending point, marking the vehicle-vehicle safety distance threshold on the starting point-ending point path by taking the collision position as a center to obtain a vehicle-vehicle avoidance range, calculating the vehicle-vehicle avoidance time from the current position of the interference vehicle to the passing vehicle-vehicle avoidance range, and calculating the second avoidance speed of the automatic driving vehicle according to the vehicle-vehicle avoidance time and the length of the starting point-ending point path.
8. An automated driving vehicle turning avoidance control system, characterized by being applied to the automated driving vehicle turning avoidance control method according to any one of claims 1 to 7, the automated driving vehicle turning avoidance control system comprising:
the acquisition module is used for acquiring turning information of the automatic driving vehicle, barrier information and signal lamp information within a set range;
the calculation module is used for calculating the avoiding speed and outputting the avoiding speed to the vehicle control device.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is capable of implementing the method of controlling turn avoidance of an autonomous vehicle as claimed in any of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, is capable of implementing the automated driving vehicle turn avoidance control method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311515348.XA CN117227714A (en) | 2023-11-15 | 2023-11-15 | Control method and system for turning avoidance of automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311515348.XA CN117227714A (en) | 2023-11-15 | 2023-11-15 | Control method and system for turning avoidance of automatic driving vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117227714A true CN117227714A (en) | 2023-12-15 |
Family
ID=89084696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311515348.XA Pending CN117227714A (en) | 2023-11-15 | 2023-11-15 | Control method and system for turning avoidance of automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117227714A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118004275A (en) * | 2024-04-08 | 2024-05-10 | 无锡车联天下信息技术有限公司 | Transverse control method and structure for vehicles moving straight at intersection |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109557925A (en) * | 2018-12-29 | 2019-04-02 | 北京智行者科技有限公司 | Automatic driving vehicle barrier preventing collision method and device |
| CN109801508A (en) * | 2019-02-26 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | The motion profile prediction technique and device of barrier at crossing |
| JP2020097276A (en) * | 2018-12-17 | 2020-06-25 | 本田技研工業株式会社 | Travel trajectory determining device and automatic driving device |
| US20200307573A1 (en) * | 2019-03-28 | 2020-10-01 | Honda Motor Co., Ltd. | Vehicle control system |
| US20210284195A1 (en) * | 2020-03-13 | 2021-09-16 | Baidu Usa Llc | Obstacle prediction system for autonomous driving vehicles |
| CN214565289U (en) * | 2021-09-17 | 2021-11-02 | 成都西谌科技有限公司 | On-vehicle 4G intelligent terminal |
| CN113650608A (en) * | 2021-09-14 | 2021-11-16 | 广州小鹏自动驾驶科技有限公司 | Obstacle avoidance method and device based on automatic driving |
| KR20220019251A (en) * | 2020-07-02 | 2022-02-16 | 현대모비스 주식회사 | Apparatus and method for autonomous driving |
| CN115257815A (en) * | 2022-08-25 | 2022-11-01 | 北斗星通智联科技有限责任公司 | Planning method and device for automatically driving automobile to turn right and terminal equipment |
| CN116198542A (en) * | 2023-03-08 | 2023-06-02 | 酷哇科技有限公司 | Automatic driving unprotected left turning method and system |
-
2023
- 2023-11-15 CN CN202311515348.XA patent/CN117227714A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020097276A (en) * | 2018-12-17 | 2020-06-25 | 本田技研工業株式会社 | Travel trajectory determining device and automatic driving device |
| CN109557925A (en) * | 2018-12-29 | 2019-04-02 | 北京智行者科技有限公司 | Automatic driving vehicle barrier preventing collision method and device |
| CN109801508A (en) * | 2019-02-26 | 2019-05-24 | 百度在线网络技术（北京）有限公司 | The motion profile prediction technique and device of barrier at crossing |
| US20200307573A1 (en) * | 2019-03-28 | 2020-10-01 | Honda Motor Co., Ltd. | Vehicle control system |
| US20210284195A1 (en) * | 2020-03-13 | 2021-09-16 | Baidu Usa Llc | Obstacle prediction system for autonomous driving vehicles |
| KR20220019251A (en) * | 2020-07-02 | 2022-02-16 | 현대모비스 주식회사 | Apparatus and method for autonomous driving |
| CN113650608A (en) * | 2021-09-14 | 2021-11-16 | 广州小鹏自动驾驶科技有限公司 | Obstacle avoidance method and device based on automatic driving |
| CN214565289U (en) * | 2021-09-17 | 2021-11-02 | 成都西谌科技有限公司 | On-vehicle 4G intelligent terminal |
| CN115257815A (en) * | 2022-08-25 | 2022-11-01 | 北斗星通智联科技有限责任公司 | Planning method and device for automatically driving automobile to turn right and terminal equipment |
| CN116198542A (en) * | 2023-03-08 | 2023-06-02 | 酷哇科技有限公司 | Automatic driving unprotected left turning method and system |
Non-Patent Citations (1)
| Title |
|---|
| 王斌;: "智能汽车避障风险评估及轨迹规划", 汽车技术, no. 06 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118004275A (en) * | 2024-04-08 | 2024-05-10 | 无锡车联天下信息技术有限公司 | Transverse control method and structure for vehicles moving straight at intersection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108986540B (en) | Vehicle control system and method, and driving assistance server | |
| US11932284B2 (en) | Trajectory setting device and trajectory setting method | |
| JP6725568B2 (en) | Vehicle control device, vehicle, vehicle control method, and program | |
| CN113056749B (en) | Future object trajectory prediction for autonomous machine applications | |
| CN110248861B (en) | Guiding a vehicle using a machine learning model during vehicle maneuvers | |
| US11574089B2 (en) | Synthetic scenario generator based on attributes | |
| US11049398B2 (en) | Surrounding environment recognizing apparatus | |
| US11568100B2 (en) | Synthetic scenario simulator based on events | |
| US10037036B2 (en) | Method and arrangement for determining safe vehicle trajectories | |
| CN113267199B (en) | Method and device for planning driving track | |
| CN112193244B (en) | Automatic driving vehicle motion planning method based on linear constraint | |
| CN112601686A (en) | System and method for navigation with safe distance | |
| RU2760046C1 (en) | Driving assistance and driving assistance device | |
| CN110352450A (en) | Driving assistance method and drive assistance device | |
| US11615702B2 (en) | Determining vehicle path | |
| JP2019144691A (en) | Vehicle control device | |
| CN117227714A (en) | Control method and system for turning avoidance of automatic driving vehicle | |
| WO2020264276A1 (en) | Synthetic scenario generator based on attributes | |
| US11429843B2 (en) | Vehicle operation labeling | |
| JP6796679B2 (en) | Vehicle control system and method, and driving support server | |
| JP7388208B2 (en) | Vehicle control device | |
| CN113753038A (en) | Trajectory prediction method and apparatus, electronic device and storage medium | |
| WO2021048583A1 (en) | Action deciding method of traveling support device, and traveling support device | |
| CN113715846B (en) | Lane borrowing control method and device, storage medium and vehicle | |
| JP7470584B2 (en) | Driving support method and driving support device |
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 |