CN117022262A

CN117022262A - Unmanned vehicle speed planning control method and device, electronic equipment and storage medium

Info

Publication number: CN117022262A
Application number: CN202310970656.5A
Authority: CN
Inventors: 李国峰; 吕强; 苗乾坤
Original assignee: Neolithic Zhongyan Shanghai Technology Co ltd
Current assignee: Neolithic Zhongyan Shanghai Technology Co ltd
Priority date: 2023-08-02
Filing date: 2023-08-02
Publication date: 2023-11-10

Abstract

The application provides a unmanned vehicle speed planning control method, a device, electronic equipment and a storage medium. The method is applied to an unmanned vehicle, unmanned equipment or automatic driving equipment and comprises the following steps: dividing a detection area around the unmanned vehicle according to the running state information and the road environment information in the running process of the unmanned vehicle; acquiring identification information of obstacles around the unmanned aerial vehicle, and classifying the obstacles around the unmanned aerial vehicle by using a predetermined classification method; judging whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, performing speed planning control on the unmanned vehicle by using a first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, the speed planning control is carried out on the unmanned vehicle by using a second speed planning method. The application improves the success rate of speed planning and the parallelism and safety of the whole vehicle operation.

Description

Unmanned vehicle speed planning control method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of unmanned technologies, and in particular, to a method and apparatus for controlling unmanned vehicle speed, an electronic device, and a storage medium.

Background

The speed planning control is to add speed related information based on one or more path curves given by the local path planning, so as to meet the operation limit of the feedback control and meet the output result of the behavior decision. It is mainly considered to avoid dynamic obstacles. The existing speed planning method comprises the following steps: the velocity, spline interpolation, function fitting, target time point method, dynamic programming algorithm, etc. are generated by specifying linear acceleration, with dynamic programming algorithm being most common.

The inputs to the dynamic programming algorithm include environmental information such as reference paths, obstructions, and the like. The calculation process mainly comprises the steps of obstacle prediction and processing, S-T diagram generation, S-T diagram sampling and searching, speed smoothing and the like. However, current speed planning control schemes still have some problems. Although the dynamic programming algorithm can successfully perform speed programming, the effect is good in the case of only motor vehicles on the structured road. This is because the safety distance between motor vehicles is relatively large and the running behavior is standardized. However, in a mixed traffic flow scene of a motor vehicle, a bicycle, a pedestrian and the like, the types of obstacles are various, the safety distance between the vehicle and the vehicle is small, and irregular behaviors such as short-distance overtaking and following exist. Under these complex conditions, the existing obstacle prediction processing method easily causes failure of speed planning control, and further may cause a series of comfort and safety problems such as sudden braking, rear-end collision, collision and the like.

Disclosure of Invention

In view of the above, the embodiments of the present application provide a method, an apparatus, an electronic device, and a storage medium for controlling speed planning of an unmanned vehicle, so as to solve the problem in the prior art that speed planning control is easily failed in a mixed traffic flow scene, thereby causing a series of comfort and safety problems.

In a first aspect of the embodiment of the present application, there is provided a method for controlling speed planning of an unmanned vehicle, including: acquiring driving state information and road environment information in the driving process of the unmanned vehicle, and dividing a detection area around the unmanned vehicle according to the driving state information and the road environment information; classifying the obstacles around the unmanned vehicle by using a predetermined classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the category of the obstacles; judging whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, performing speed planning control on the unmanned vehicle by using a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, the speed planning control is carried out on the unmanned vehicle by utilizing a preset second speed planning method.

In a second aspect of the embodiment of the present application, there is provided an unmanned vehicle speed planning control device, including: the division module is configured to collect driving state information and road environment information in the driving process of the unmanned vehicle and divide a detection area around the unmanned vehicle according to the driving state information and the road environment information; the classification module is configured to classify the obstacles around the unmanned vehicle by utilizing a preset classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the category of the obstacles; the speed planning control module is configured to judge whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, the speed planning control is carried out on the unmanned vehicle by utilizing a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, the speed planning control is carried out on the unmanned vehicle by utilizing a preset second speed planning method.

In a third aspect of the embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.

In a fourth aspect of the embodiments of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.

The above at least one technical scheme adopted by the embodiment of the application can achieve the following beneficial effects:

acquiring driving state information and road environment information in the driving process of the unmanned vehicle, and dividing a detection area around the unmanned vehicle according to the driving state information and the road environment information; classifying the obstacles around the unmanned vehicle by using a predetermined classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the category of the obstacles; judging whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, performing speed planning control on the unmanned vehicle by using a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, the speed planning control is carried out on the unmanned vehicle by utilizing a preset second speed planning method. The application improves the success rate of speed planning and the parallelism and safety of the whole vehicle operation.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of prior art obstacle prediction and handling;

FIG. 2 is an S-T diagram of a normal running motor vehicle in the same direction in a prior art scenario;

FIG. 3 is a schematic diagram of a predicted processing result of an obstacle in the prior art;

FIG. 4 is a S-T diagram generated when an obstacle is relatively close to an unmanned vehicle in a prior art scenario;

fig. 5 is a schematic flow chart of a method for controlling speed planning of an unmanned vehicle according to an embodiment of the present application;

FIG. 6 is a schematic illustration of an embodiment of the present application dividing a detection zone around an unmanned vehicle;

fig. 7 is a schematic view of a possible positional relationship of an obstacle with a front collision detection area;

fig. 8 is a schematic view of a possible positional relationship between an obstacle and a side collision detection area;

fig. 9 is a schematic structural diagram of an unmanned vehicle speed planning control device according to an embodiment of the present application;

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

Unmanned vehicles, also called autonomous vehicles, unmanned vehicles or wheeled mobile robots, are the new technology products of integration and intellectualization integrating multiple elements such as environment perception, path planning, state identification, vehicle control and the like. The unmanned vehicle automatic driving system mainly comprises a sensor drive system, a sensing system, a fusion system, a decision system, a motion planning system, a control system and the like. In unmanned vehicle driving, the main function of speed planning control is to ensure that the vehicle generates the vehicle speed adapting to the current driving environment according to the current environment perception and the vehicle state under the constraint conditions of the driving comfort, the safety, the efficiency and the like.

The speed planning control is that after a local path planning gives one or a plurality of selected path curves, information related to the speed is added on the basis of the local path so as to meet the operation limit of feedback control and meet the output result of behavior decision. I.e. mainly considering the avoidance of dynamic obstacles. The existing speed planning method comprises the following steps: the velocity, spline interpolation, function fitting, target time point method, dynamic programming algorithm, etc. are generated by specifying linear acceleration. The more common method is a dynamic programming algorithm.

The dynamic planning algorithm needs to input environmental information such as a reference path, an obstacle and the like, and the calculation process of the dynamic planning algorithm mainly comprises the steps of obstacle prediction and processing, S-T diagram generation, S-T diagram sampling and searching and speed smoothing.

Wherein, the obstacle prediction and treatment means that when the movement obstacle appears in the environment, the movement obstacle occupies the planned path at some future time. If the target automobile is still traveling at a constant speed at the current speed, it is possible that the target automobile collides with the movement obstacle at a future time. It is therefore necessary to calculate range information of t and s for predicting that an obstacle may collide with the planned trajectory of the unmanned vehicle.

The S-T map is generated by using the obstacle prediction information, and a certain path Δs occupied by the obstacle on the path S at a certain time Δt is marked in the S-T map.

The S-T diagram sampling and searching is to discretize the S-T diagram, and then search in the S-T searching space to generate a path from the starting point to the target point for each S-T candidate target point.

The speed smoothing is the smoothing of the tortuous and discrete paths obtained in the S-T graph sampling and searching, and meets the requirements of smoothness, comfort, control and the like of the unmanned vehicle while avoiding dynamic obstacles.

Based on the above description, it can be found that the prediction of the obstacle and the planned trajectory of the unmanned vehicle are the data bases required by the whole speed planning calculation; the success of the speed planning solution by using a dynamic planning algorithm depends on the input of the obstacle to a great extent. On structured roads with only motor vehicles, the obstacle is other motor vehicles; the speed planning method based on the dynamic planning algorithm is high in success rate because the safety distance between motor vehicles is relatively large and the running behavior is standard; however, in a mixed traffic flow scene such as a motor vehicle, a bicycle, a pedestrian and the like, the types of the obstacles are more, the safety distance between the obstacles and an unmanned vehicle is small, and the obstacles have nonstandard behaviors such as short-distance overtaking and following, so that the speed planning failure is extremely easy to be caused by using the processing method for predicting the obstacles, and a series of problems affecting the comfort and the safety of the vehicle such as sudden braking, rear-end collision and the like are further caused.

The following first describes a specific implementation procedure of a speed planning method based on a dynamic planning algorithm in the prior art with reference to the accompanying drawings. As shown in fig. 1 to 4, fig. 1 is a schematic diagram of predicting and processing an obstacle in the prior art, fig. 2 is an S-T diagram of a motor vehicle running normally in the same direction in a prior art scene, fig. 3 is a schematic diagram of a result of predicting and processing an obstacle in the prior art, and fig. 4 is an S-T diagram generated when the obstacle is relatively close to an unmanned vehicle in the prior art scene.

As illustrated in fig. 1, this is a prior art process of handling obstacle prediction. It calculates a time-path map (S-T map) of the obstacle obs by taking into account the predicted trajectory prediction of the obstacle obs and the planned path of the unmanned vehicle ego. For a motor vehicle that is co-directional and traveling normally, its S-T diagram is shown in fig. 2, which can be handled by a conventional speed planning method. However, in the case of an actual mixed traffic flow, particularly in a scene of traveling on a secondary road, the obstacle in the same direction may be a non-motor vehicle such as an electric bicycle, in addition to a motor vehicle. When the traveling speed of the unmanned vehicle is low, the result of the prediction processing of these obstacles is shown in fig. 3. At this time, the obstacle obs is relatively close to the unmanned vehicle ego, and the S-T diagram is shown in FIG. 4. As can be seen from fig. 4, the solution space for the velocity planning is very small or even absent, and if the velocity planning is continued by using the dynamic planning at this time, the planning may fail.

Based on the above prior art, it can be seen that in a mixed traffic flow scenario, the speed planning is performed by simply relying on dynamic planning, so that the success rate of the planning cannot be ensured, but a series of problems such as sudden braking, rear-end collision, collision and the like may be caused. Therefore, the dynamic programming algorithm in the prior art has high success rate for speed programming of the same-direction motor vehicle, but has lower success rate when the same-direction non-motor vehicle has irregular behaviors, so that a series of comfort and safety problems such as sudden braking, rear-end collision and the like are easily caused. In the application, in the process of predicting and processing the obstacle, a detection area with a certain range is divided at the periphery of the vehicle body according to the running state of the unmanned vehicle, and different speed planning control methods are selected for the obstacle meeting different conditions by combining two factors of the type of the obstacle and whether the obstacle is in the detection area, so that the success rate of speed planning is ensured, and the comfort and the safety of the vehicle are improved while the obstacle of different types is stably processed.

The following describes a method and apparatus for controlling speed planning of an unmanned vehicle according to embodiments of the present application in detail with reference to the accompanying drawings and specific embodiments.

Fig. 5 is a flow chart of a method for controlling speed planning of an unmanned vehicle according to an embodiment of the present application. The unmanned vehicle speed planning control method of fig. 5 may be performed by a control unit of the unmanned vehicle system. As shown in fig. 5, the unmanned vehicle speed planning control method specifically may include:

s501, acquiring running state information and road environment information in the running process of the unmanned vehicle, and dividing a detection area around the unmanned vehicle according to the running state information and the road environment information;

s502, classifying the obstacles around the unmanned vehicle by using a predetermined classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the types of the obstacles;

s503, judging whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, performing speed planning control on the unmanned vehicle by using a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, the speed planning control is carried out on the unmanned vehicle by utilizing a preset second speed planning method.

In some embodiments, dividing the detection area around the unmanned vehicle according to the driving state information and the road environment information includes: and dividing a front collision detection area and a side collision detection area on the front side and the two sides of the unmanned vehicle respectively according to the running state information and the road environment information of the unmanned vehicle, and superposing the front collision detection area and the side collision detection area to form a complete detection area.

Specifically, before dividing a detection area around the unmanned vehicle, first, driving state information and external road environment information during the driving process of the unmanned vehicle are collected in real time by using various sensors installed on the unmanned vehicle, for example: in practical applications, the vehicle speed sensor and the vision sensor may be utilized to obtain the driving state information of the unmanned vehicle, where the driving state information includes, but is not limited to, vehicle speed information, vehicle front turning information, and the like; in addition, real-time road environment information may be obtained using data information returned by various sensors (e.g., lidar), where the road environment information includes, but is not limited to, the width of the road ahead, whether the road is curved, whether the road ahead is straight or curved, and the like.

After the running state information and the road environment information of the unmanned vehicle are acquired in real time, a detection area is dynamically divided around the unmanned vehicle according to the running state of the unmanned vehicle and the change of the surrounding environment. The following describes the dividing process and principle of the detection area with reference to the drawings, fig. 6 is a schematic diagram of dividing the detection area around the unmanned vehicle according to the embodiment of the present application, fig. 7 is a schematic diagram of a possible positional relationship between the obstacle and the front collision detection area, and fig. 8 is a schematic diagram of a possible positional relationship between the obstacle and the side collision detection area. As shown in fig. 6 to 8, the dividing process of the detection area may specifically include:

in the embodiment of the application, a detection area can be divided around the unmanned vehicle according to the running state information of the unmanned vehicle and the surrounding road environment information. Specifically, a front collision detection area and a side collision detection area may be divided in front of and on both sides of the unmanned vehicle, respectively, based on these information, and then the two areas are superimposed, thereby forming one complete detection area.

In one example, as shown in fig. 6, a detection area check_area (a display area having a gradation in fig. 6) of a specific range is partitioned around the unmanned vehicle based on the running state information of the unmanned vehicle. The size parameter of the detection area is related to the size, the running speed and the road environment of the unmanned vehicle, and the detection area can be formed by overlapping three rectangular areas of front, left and right. Although a rectangular region is selected in the embodiment of the present application, the shape of the region is not limited to a rectangle in practical application.

Taking a rectangular area as an example, one front collision detection area check_area_front is partitioned in front of the unmanned vehicle, and side collision detection areas check_ar ea_side are partitioned on the left and right sides of the unmanned vehicle. An obstacle may exist at any position in the detection areas check_area_front and check_area_side, for example, a possible positional relationship between the obstacle obs and the detection area is shown with reference to fig. 7 and 8.

In some embodiments, the method further comprises: the shape and size of the front collision detection area and the side collision detection area change following the change of the traveling state information and the road environment information of the unmanned vehicle, wherein the default shape of the front collision detection area and the side collision detection area is rectangular.

Specifically, the embodiment of the application divides the detection areas in front of the vehicle and at two sides of the vehicle according to the running state information of the vehicle and the surrounding road environment information. The shape and size of these detection areas may vary depending on the driving state (such as speed) of the unmanned vehicle and the road environment (such as whether there is an intersection or curve on the road ahead). For example, if the vehicle speed is high, or there is an intersection in front, it may be necessary to enlarge the detection area in front. Conversely, if the vehicle is traveling on a straight road and the speed is slow, the forward detection zone may be relatively small.

The detection area of the embodiment of the present application is divided into a front collision detection area (check_area_front) and a side collision detection area (check_area_side), and finally, the front collision detection area and the side collision detection area are respectively corresponding rectangular areas (three gray rectangular areas as shown in fig. 6) are overlapped to form a complete detection area. In practical application, the shape and size of the three rectangular areas can be dynamically adjusted according to the size, the running speed and the road environment of the unmanned vehicle.

In some embodiments, classifying the obstacle around the unmanned vehicle using a predetermined classification method according to the identification information of the obstacle around the unmanned vehicle by the sensing module includes: acquiring identification information obtained by detecting and identifying obstacles around the unmanned vehicle by a perception module of the unmanned vehicle, wherein the identification information comprises the type of the obstacle and the size of the obstacle; the obstacles around the unmanned vehicle are classified according to the type of the obstacle and the size of the obstacle, wherein the categories of the obstacle include a risk-free obstacle category and a risk-free obstacle category.

Specifically, according to the embodiment of the application, the surrounding obstacles are classified by using a preset classification method according to the identification information of the surrounding obstacles by the perception module of the unmanned vehicle. Firstly, acquiring identification information obtained by detecting and identifying obstacles around an unmanned vehicle by a perception module, wherein the identification information at least comprises type information and size (such as cross-sectional area) of the obstacles; then, the obstacles around the unmanned vehicle are classified according to the type and size of the obstacle. In this process, the obstacles are mainly divided into two main categories, namely, a risk-free obstacle category and a risk-obstacle category.

In one example, during a specific classification, since the participating objects in the mixed traffic flow are very complex, including trucks, buses, passenger cars, tricycles, motorcycles, electric vehicles, pedestrians, and balance cars, etc., when the traveling speed of the unmanned vehicle is around 20km/h, these types of obstacles may overtake the unmanned vehicle, thereby affecting its speed planning. Therefore, when the speed planning is performed, the reasonable classification of the obstacle by combining the result of the sensing module is particularly important.

In an embodiment of the present application, the types of obstacles are classified into the following two categories according to whether the obstacles may produce irregular traffic behavior: the risk-free obstacle obs_safe (i.e., risk-free obstacle class) and the risk-free obstacle obs_potential_risk (i.e., risk-free obstacle class). The classification method can evaluate the influence of the obstacle on the speed planning of the unmanned vehicle more accurately, so that the driving safety and efficiency of the unmanned vehicle in the mixed traffic flow are improved.

In some embodiments, classifying the obstacle around the drone according to the type of obstacle and the size of the obstacle includes: judging whether the obstacle belongs to a motor vehicle or a non-motor vehicle according to the type of the obstacle, and classifying the obstacle into a risk obstacle type when the obstacle is judged to belong to the non-motor vehicle or the size of the obstacle is smaller than a preset condition; otherwise, the obstacles are classified into risk-free obstacle categories.

In particular, embodiments of the present application may classify obstacles around an unmanned vehicle according to the type and size (e.g., cross-sectional area) of the obstacle. In the classification process of the obstacle type, firstly judging whether the obstacle belongs to a motor vehicle or a non-motor vehicle according to the obstacle type; then, when it is determined that the obstacle belongs to the non-motor vehicle, or the cross-sectional area of the obstacle is smaller than a preset condition (such as a preset cross-sectional area threshold), classifying the obstacle into a risk obstacle category, namely obs_potential_task; otherwise, this obstacle would be classified into a risk-free obstacle class, namely obs_safe.

Further, in a specific judging process, the judging standard of the obs_potential_risk is based on the type and the cross-sectional area of the obstacle, however, the dividing standard of the obstacle type in the embodiment of the application is not limited to the type and the cross-sectional area of the obstacle, and any mode capable of distinguishing the type of the obstacle is suitable for the technical scheme of the application, and the application is not limited thereto.

In one example, for example: obstacle types may be classified as non-motor vehicle obstacles, or as obstacles having a cross-sectional size (i.e., cross-sectional area) of less than 4 square meters (i.e., risk obstacle categories). Correspondingly, the obstacle types may be classified as being motor vehicle obstacles, or as being greater than 4 square meters in cross-sectional size (i.e., cross-sectional area) into obs_safe (i.e., risk-free obstacle categories).

The embodiment of the application further selects a proper speed planning method for the obstacles meeting different preset conditions according to whether the obstacles and the types of the obstacles exist in the detection area, and realizes speed planning control for different types of the obstacles in the detection area. The obstacle classification method provided by the embodiment of the application can evaluate the obstacles in the mixed traffic flow more accurately, thereby being beneficial to more accurately planning the speed and improving the driving safety and efficiency of the unmanned vehicle in a complex traffic environment.

In some embodiments, the speed planning control of the unmanned vehicle using a predetermined first speed planning method according to a relative speed and a relative distance between the unmanned vehicle and an obstacle in the detection area includes:

determining a speed limit value of the unmanned vehicle according to the relation between the relative speed and a preset safety speed threshold value and the relation between the relative distance and a preset safety distance threshold value;

generating a first S-T diagram by using the speed limit value, the time domain and the distance domain, and marking a first forbidden area in the first S-T diagram;

discretizing the first S-T diagram, searching a path from a starting point to a target point in an S-T search space by utilizing a search algorithm for each target point, and bypassing a first forbidden region by the path from the starting point to the target point;

And carrying out speed smoothing processing on the path from the starting point to the target point to obtain a speed planning path after the speed smoothing processing.

Specifically, firstly determining a speed limit value of the unmanned vehicle, and then using the speed limit value as the slope of a straight line in a first S-T diagram, and generating the first S-T diagram by using the speed limit value, a time domain and a distance domain, wherein S represents distance and T represents time. The information acquired in the obstacle prediction stage is converted into a graphical representation when the first S-T diagram is generated. If the predicted moving obstacle is likely to occupy a certain distance deltas within a certain time period deltat, this part is marked in the first S-T diagram, denoted as a forbidden area.

Further, discretizing the first S-T diagram to obtain a grid diagram. A search algorithm (such as the a-algorithm or Dijkstra algorithm) is then used to find a path from the start point to the target point. This path is avoided from the first forbidden region in the S-T diagram to prevent collision with the predicted obstacle.

Further, after the processing of the S-T diagram sampling and searching steps, the obtained path may be tortuous and discrete, which does not meet the actual driving requirement. Therefore, a speed smoothing process, such as spline interpolation, is required, so that the generated speed plan more meets the requirements of smoothness, comfort and control of the unmanned vehicle, and a final speed planning path is obtained.

In some embodiments, determining the speed limit value of the unmanned vehicle based on the relationship between the relative speed and the preset safe speed threshold and the relationship between the relative distance and the preset safe distance threshold comprises:

subtracting the speed of the obstacle in the detection area from the speed of the unmanned vehicle to obtain a relative speed, and comparing the relative speed with a preset safety speed threshold;

when the relative speed is greater than the safety speed threshold, executing unmanned vehicle speed planning control of the next cycle period;

otherwise, subtracting the position of the obstacle in the detection area from the position of the unmanned vehicle to obtain a relative distance, and comparing the relative distance with a preset safety distance threshold;

when the relative distance is greater than the safety distance threshold, executing unmanned vehicle speed planning control of the next cycle period; otherwise, determining the speed limit value of the unmanned vehicle.

In particular, the present application employs a variety of methods to achieve speed planning control. For example, a speed planning method based on a time interval or a safe distance (i.e., a first speed planning method) is employed. The speed planning method can be used for keeping a safe distance or safe collision time through slow braking or speed limiting under the condition that the distance between the unmanned vehicle and the obstacle is relatively close. Embodiments of such methods include forward and lateral collision time and safety distance calculations, with common calculation parameters including Time To Collision (TTC) and following distance (THW). In practical application, besides the mode of calculating the relative speed and the relative distance to control the unmanned vehicle to perform slow braking and speed limiting, the relative included angle (namely the included angle in the speed direction) between the obstacle and the unmanned vehicle can be calculated to control the unmanned vehicle to perform slow braking and speed limiting so as to keep the safe distance or safe collision time between the unmanned vehicle and the obstacle, thereby realizing more accurate speed planning control.

In one example, for example: in the front collision detection area (check_area_front) shown in fig. 7, assuming that the obs1, obs2, obs3, and obs4 are all potential risk obstacles (obs_potential_ris k), then the obs1, obs2 are processed by a second speed planning method (i.e., a speed planning method based on a dynamic planning algorithm); while obs3 and obs4 are processed using the first speed planning method (i.e., a speed planning method based on time intervals or safe distances). Similarly, in the side collision detection area (check_area_side) shown in fig. 8, assuming that the obs1, obs2, obs3, and obs4 are all potentially risky obstacles (obs_potential_task), then the obs4 is determined to be processed by the second speed planning method; and the first speed planning method is adopted for processing the obs1, the obs2 and the obs 3. Therefore, the embodiment of the application realizes the selection switching logic of the speed planning method according to whether the obstacle exists in the detection area and the type of the obstacle.

In the case of dealing with potentially risky obstacles, the selection of different speed planning methods depends mainly on the relative speed and relative distance between the drone and the obstacle. When the relative speed exceeds a preset safe speed threshold value or the relative distance exceeds a preset safe distance threshold value, the unmanned vehicle speed planning control of the next cycle period is selected to be continuously executed. In contrast, if both conditions are not met, the embodiment of the application selects to perform slow brake speed limiting control on the unmanned vehicle so as to maintain the safe distance or safe collision time between the unmanned vehicle and the obstacle in the detection area, namely, the speed planning control is performed on the unmanned vehicle by adopting the first speed planning method (the speed planning method based on the time interval or the safe distance).

In some embodiments, speed planning control of the drone with a predetermined second speed planning method includes:

predicting the future state of the obstacle in the detection area by using the current state of the obstacle in the detection area and a prediction model, and calculating the range information of the time and the distance of collision between the obstacle and the expected path of the unmanned vehicle based on the future state;

generating a second S-T diagram according to the range information of time and distance, and marking a second forbidden area in the second S-T diagram, wherein the second forbidden area is used for representing the path distance occupied by the obstacle on the expected path of the unmanned vehicle in a specific time period;

discretizing the second S-T diagram, and searching a path from the starting point to the target point in an S-T search space by utilizing a search algorithm for each target point, wherein the path from the starting point to the target point bypasses a second forbidden area;

In particular, dynamic planning (Dynamic Programming, DP) is an optimization algorithm for solving optimization problems with specific structures, typically involving decomposition of the problem and recursive solving of sub-problems. It is applicable to many different problems including speed planning problems for autonomous vehicles. When the speed planning control is performed on the unmanned vehicle based on the dynamic planning algorithm, the dynamic planning algorithm can comprise the following steps:

1) Obstacle prediction and treatment: this step involves the perception and understanding of the environment. Based on data collected by various sensors (e.g., radar, lidar, cameras, etc.), the future state of the moving obstacle may be predicted. This is based on the current state of the obstacle (e.g., position, velocity, direction, etc.) and some predictive model (e.g., constant velocity model, constant acceleration model, etc.). Once the future state of the obstacle is predicted, the time and distance range over which the obstacle may collide with the intended path of the drone may be calculated.

2) S-T diagram generation: the S-T plot is a time-distance plot, where S represents distance and T represents time. The information acquired in the obstacle prediction stage is converted into a graphical representation when the second S-T diagram is generated. If the predicted moving obstacle is likely to occupy a certain distance deltas within a certain time period deltat, this part is marked in the second S-T diagram, denoted as a forbidden area.

3) S-T graph sampling and searching: in this step, the second S-T diagram is first discretized to obtain a grid diagram. A search algorithm (such as the a-algorithm or Dijkstra algorithm) is then used to find a path from the start point to the target point. This path is avoided from the second forbidden region in the second S-T diagram to prevent collision with the predicted obstacle.

4) And (3) speed smoothing: the path obtained by the S-T diagram sampling and searching step may be tortuous and discrete, not meeting the actual driving needs. Therefore, a speed smoothing process, such as spline interpolation, is needed, so that the generated speed plan more meets the requirements of smoothness, comfort and control of the unmanned vehicle.

The above is the basic process of unmanned vehicle speed planning control based on the dynamic planning algorithm in the embodiment of the application. The key point of the dynamic programming algorithm is to effectively search and select the solution of the sub-problem, thereby obtaining a globally optimal solution.

According to the technical scheme provided by the embodiment of the application, the surrounding area of the unmanned vehicle is divided into the front collision detection area and the side collision detection area by comprehensively considering the running state and the road environment information of the unmanned vehicle, so that the complete detection area is formed. Meanwhile, according to the identification information of the obstacles around the unmanned vehicle by the sensing module, the obstacles around the unmanned vehicle are classified by a preset classification method, wherein the classification method comprises a risk-free obstacle class and a risk-free obstacle class. This classification takes into account not only the type of obstacle but also the cross-sectional area of the obstacle.

In addition, the speed planning control is carried out on the unmanned vehicle according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area. When the relative speed or the relative distance exceeds a preset safety threshold, the unmanned vehicle executes the speed planning control of the next cycle according to the original plan. When both conditions are not met, the unmanned vehicle will perform a slow-braking speed-limiting control to maintain a safe distance or safe collision time between the unmanned vehicle and the obstacle in the detection area.

Therefore, the application can effectively cope with the scene of mixed traffic flow, especially the overtaking scene of obstacles such as electric vehicles at a short distance, improves the success rate of speed planning, and avoids the problems of sudden braking, rear-end collision and the like possibly caused by the traditional S-T diagram and dynamic planning method, thereby improving the running smoothness and safety of the whole vehicle. In general, the application realizes safe and effective speed planning control of the unmanned vehicle in a complex mixed traffic environment by dynamically dividing the detection area, adjusting the type of the obstacle in time and selecting a proper speed planning method according to the type of the obstacle in the detection area.

The following are examples of the apparatus of the present application that may be used to perform the method embodiments of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method of the present application.

Fig. 9 is a schematic structural diagram of an unmanned vehicle speed planning control device according to an embodiment of the present application. As shown in fig. 9, the unmanned vehicle speed planning control device includes:

the dividing module 901 is configured to collect driving state information and road environment information in the driving process of the unmanned vehicle, and divide a detection area around the unmanned vehicle according to the driving state information and the road environment information;

a classification module 902 configured to classify the obstacle around the unmanned vehicle by using a predetermined classification method according to the identification information of the obstacle around the unmanned vehicle by the sensing module, so as to determine a class of the obstacle;

the speed planning control module 903 is configured to determine whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, perform speed planning control on the unmanned vehicle according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area by using a predetermined first speed planning method; otherwise, the speed planning control is carried out on the unmanned vehicle by utilizing a preset second speed planning method.

In some embodiments, the dividing module 901 of fig. 9 divides the front collision detection area and the side collision detection area respectively in front of and on both sides of the unmanned vehicle according to the driving state information of the unmanned vehicle and the road environment information, and superimposes the front collision detection area and the side collision detection area to form a complete detection area.

In some embodiments, the shape and size of the front collision detection region and the side collision detection region in the division module 901 of fig. 9 change following the change of the driving state information of the unmanned vehicle and the road environment information, wherein the default shape of the front collision detection region and the side collision detection region is rectangular.

In some embodiments, the classification module 902 of fig. 9 obtains identification information obtained by detecting and identifying an obstacle around the unmanned vehicle by the perception module of the unmanned vehicle, where the identification information includes a type of the obstacle and a size of the obstacle; the obstacles around the unmanned vehicle are classified according to the type of the obstacle and the size of the obstacle, wherein the categories of the obstacle include a risk-free obstacle category and a risk-free obstacle category.

In some embodiments, classification module 902 of fig. 9 determines whether an obstacle belongs to a motor vehicle or a non-motor vehicle based on the type of obstacle, and classifies the obstacle as a risky obstacle class when it is determined that the obstacle belongs to the non-motor vehicle or the size of the obstacle is less than a preset condition; otherwise, the obstacles are classified into risk-free obstacle categories.

In some embodiments, the speed planning control module 903 of fig. 9 determines the speed limit value of the drone vehicle based on the relationship between the relative speed and the preset safe speed threshold, and the relationship between the relative distance and the preset safe distance threshold; generating a first S-T diagram by using the speed limit value, the time domain and the distance domain, and marking a first forbidden area in the first S-T diagram; discretizing the first S-T diagram, searching a path from a starting point to a target point in an S-T search space by utilizing a search algorithm for each target point, and bypassing a first forbidden region by the path from the starting point to the target point; and carrying out speed smoothing processing on the path from the starting point to the target point to obtain a speed planning path after the speed smoothing processing.

In some embodiments, the speed planning control module 903 of fig. 9 subtracts the speed of the obstacle in the detection area from the speed of the drone to obtain a relative speed, and compares the relative speed to a preset safety speed threshold; when the relative speed is greater than the safety speed threshold, executing unmanned vehicle speed planning control of the next cycle period; otherwise, subtracting the position of the obstacle in the detection area from the position of the unmanned vehicle to obtain a relative distance, and comparing the relative distance with a preset safety distance threshold; when the relative distance is greater than the safety distance threshold, executing unmanned vehicle speed planning control of the next cycle period; otherwise, determining the speed limit value of the unmanned vehicle.

In some embodiments, the speed planning control module 903 of fig. 9 predicts a future state of an obstacle within the detection area using a current state of the obstacle within the detection area and a prediction model, calculates range information of a time and a distance at which the obstacle collides with an expected path of the drone based on the future state; generating a second S-T diagram according to the range information of time and distance, and marking a second forbidden area in the second S-T diagram, wherein the second forbidden area is used for representing the path distance occupied by the obstacle on the expected path of the unmanned vehicle in a specific time period; discretizing the second S-T diagram, and searching a path from the starting point to the target point in an S-T search space by utilizing a search algorithm for each target point, wherein the path from the starting point to the target point bypasses a second forbidden area; and carrying out speed smoothing processing on the path from the starting point to the target point to obtain a speed planning path after the speed smoothing processing.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.

Fig. 10 is a schematic structural diagram of an electronic device 10 according to an embodiment of the present application. As shown in fig. 10, the electronic device 10 of this embodiment includes: a processor 1001, a memory 1002 and a computer program 1003 stored in the memory 1002 and executable on the processor 1001. The steps of the various method embodiments described above are implemented by the processor 1001 when executing the computer program 1003. Alternatively, the processor 1001 implements the functions of the modules/units in the above-described respective device embodiments when executing the computer program 1003.

By way of example, computer program 1003 may be split into one or more modules/units stored in memory 1002 and executed by processor 1001 to accomplish the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions for describing the execution of the computer program 1003 in the electronic device 10.

The electronic device 10 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 10 may include, but is not limited to, a processor 1001 and a memory 1002. It will be appreciated by those skilled in the art that fig. 10 is merely an example of the electronic device 10 and is not intended to limit the electronic device 10, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.

The processor 1001 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 1002 may be an internal storage unit of the electronic device 10, for example, a hard disk or a memory of the electronic device 10. The memory 1002 may also be an external storage device of the electronic device 10, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 10. Further, the memory 1002 may also include both internal and external storage units of the electronic device 10. The memory 1002 is used to store computer programs and other programs and data required by the electronic device. The memory 1002 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment 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, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided by the present application, it should be understood that the disclosed apparatus/computer device and method may be implemented in other manners. For example, the apparatus/computer device embodiments described above are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementations, 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 may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

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 over 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 integrated units may be implemented in hardware or in software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. An unmanned vehicle speed planning control method, comprising:

collecting driving state information and road environment information in the driving process of the unmanned vehicle, and dividing a detection area around the unmanned vehicle according to the driving state information and the road environment information;

classifying the obstacles around the unmanned vehicle by using a predetermined classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the category of the obstacle;

judging whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, performing speed planning control on the unmanned vehicle by using a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, performing speed planning control on the unmanned vehicle by using a preset second speed planning method.

2. The method of claim 1, wherein the dividing the detection area around the unmanned vehicle according to the driving status information and the road environment information comprises:

and dividing a front collision detection area and a side collision detection area respectively at the front and two sides of the unmanned vehicle according to the driving state information and the road environment information of the unmanned vehicle, and superposing the front collision detection area and the side collision detection area to form a complete detection area.

3. The method according to claim 2, wherein the method further comprises:

the shape and size of the front collision detection area and the side collision detection area change following the change in the travel state information and the road environment information of the unmanned vehicle, wherein the default shape of the front collision detection area and the side collision detection area is rectangular.

4. The method according to claim 1, wherein classifying the obstacle around the unmanned vehicle using a predetermined classification method based on the identification information of the obstacle around the unmanned vehicle by the perception module comprises:

Acquiring identification information obtained by detecting and identifying obstacles around the unmanned vehicle by a perception module of the unmanned vehicle, wherein the identification information comprises the type of the obstacle and the size of the obstacle;

and classifying the obstacles around the unmanned vehicle according to the type of the obstacle and the size of the obstacle, wherein the categories of the obstacle comprise a risk-free obstacle category and a risk-free obstacle category.

5. The method of claim 4, wherein classifying the obstacle around the drone according to the type of obstacle and the size of the obstacle comprises:

judging whether the obstacle belongs to a motor vehicle or a non-motor vehicle according to the type of the obstacle, and classifying the obstacle into a risk obstacle type when judging whether the obstacle belongs to the non-motor vehicle or the size of the obstacle is smaller than a preset condition; otherwise, the obstacles are classified into risk-free obstacle categories.

6. The method of claim 1, wherein the speed planning control of the drone with a predetermined first speed planning method based on the relative speed and relative distance between the drone and the obstacle within the detection area comprises:

discretizing the first S-T diagram, and searching a path from a starting point to a target point in an S-T search space by utilizing a search algorithm for each target point, wherein the path from the starting point to the target point bypasses the first forbidden area;

7. The method of claim 6, wherein determining the speed limit value of the drone based on the relationship between the relative speed and a preset safe speed threshold and the relationship between the relative distance and a preset safe distance threshold comprises:

8. The method of claim 1, wherein the speed planning control of the drone with a predetermined second speed planning method comprises:

predicting the future state of the obstacle in the detection area by using the current state of the obstacle in the detection area and a prediction model, and calculating range information of time and distance of collision between the obstacle and an expected path of the unmanned vehicle based on the future state;

generating a second S-T diagram according to the range information of the time and the distance, and marking a second forbidden area in the second S-T diagram, wherein the second forbidden area is used for representing the path distance occupied by an obstacle on the expected path of the unmanned vehicle in a specific time period;

Discretizing the second S-T graph, and searching a path from a starting point to a target point in an S-T search space by using a search algorithm for each target point, wherein the path from the starting point to the target point bypasses the second forbidden area;

9. An unmanned vehicle speed planning control device, characterized by comprising:

the division module is configured to collect driving state information and road environment information in the driving process of the unmanned vehicle, and a detection area is divided around the unmanned vehicle according to the driving state information and the road environment information;

the classification module is configured to classify the obstacles around the unmanned vehicle by utilizing a preset classification method according to the identification information of the obstacles around the unmanned vehicle by the perception module so as to determine the category of the obstacles;

the speed planning control module is configured to judge whether an obstacle exists in the detection area, and when the obstacle exists in the detection area and the type of the obstacle in the detection area is a risk obstacle type, the speed planning control is carried out on the unmanned vehicle by utilizing a preset first speed planning method according to the relative speed and the relative distance between the unmanned vehicle and the obstacle in the detection area; otherwise, performing speed planning control on the unmanned vehicle by using a preset second speed planning method.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any one of claims 1 to 7 when executing the computer program.

11. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 7.