CN114995421A

CN114995421A - Automatic driving obstacle avoidance method, device, electronic device, storage medium, and program product

Info

Publication number: CN114995421A
Application number: CN202210612741.XA
Authority: CN
Inventors: 谭鑫; 谯睿智
Original assignee: Chongqing Changan Automobile Co Ltd
Current assignee: Chongqing Changan Automobile Co Ltd
Priority date: 2022-05-31
Filing date: 2022-05-31
Publication date: 2022-09-02
Anticipated expiration: 2042-05-31
Also published as: CN114995421B

Abstract

The invention provides an automatic driving obstacle avoidance method, an automatic driving obstacle avoidance device, electronic equipment, a storage medium and a program product, wherein the automatic driving obstacle avoidance method comprises the following steps: acquiring navigation information and barrier information; marking a visual area in the navigation information at equal intervals once to obtain a dot matrix diagram comprising a plurality of first nodes; according to the static obstacle position area and the dot matrix diagram, local path planning is carried out to obtain a first planned path, and based on the first planned path, an initial avoidance path which is shortest to a target location is determined; carrying out secondary interval marking according to the dynamic barrier position area to obtain a plurality of second nodes; the mark spacing of the second node is smaller than the mark spacing of the first node; and calculating the shortest avoidance path based on the second node, and determining the optimal path according to the shortest avoidance path and the offset of the initial avoidance path. This scheme can effectively increase driving safety nature and keep away the barrier flexibility.

Description

Automatic driving obstacle avoidance method, device, electronic device, storage medium, and program product

Technical Field

The application relates to the field of automatic driving, in particular to an automatic driving obstacle avoidance method, an automatic driving obstacle avoidance device, electronic equipment, a storage medium and a program product.

Background

The automatic driving vehicle is an intelligent agent with an autonomous decision making capability, and needs to acquire information from an external environment and make a decision according to the information, so that global path planning is performed, and local obstacle avoidance is realized.

At present, obstacle avoidance in automatic driving is a key research problem in the field of automatic driving, and a good obstacle avoidance method can greatly improve the safety of automatic driving and improve the driving efficiency. The problems of poor flexibility, low path planning speed and the like exist in the automatic driving process of the existing vehicle.

Disclosure of Invention

In view of the above-mentioned drawbacks of the prior art, the present invention provides an automatic driving obstacle avoidance method, an automatic driving obstacle avoidance apparatus, an electronic device, a storage medium, and a program product to solve the above-mentioned technical problems.

The automatic driving obstacle avoidance method provided by the invention comprises the following steps:

acquiring navigation information and obstacle information, wherein the obstacle information comprises a static obstacle position area and a dynamic obstacle position area;

marking a visual area in the navigation information at equal intervals once to obtain a dot matrix diagram comprising a plurality of first nodes;

according to the static obstacle position area and the dot matrix diagram, local path planning is carried out to obtain a first planned path, and an initial avoidance path which is the shortest to a target location is determined based on the first planned path, wherein the first planned path comprises a set of avoidance paths from a current position to a reachable first node which avoids the static obstacle position area;

carrying out secondary interval marking according to the dynamic barrier position area to obtain a plurality of second nodes; the mark spacing of the second node is smaller than the mark spacing of the first node;

and calculating the shortest avoidance path based on the second node, and determining the optimal path according to the shortest avoidance path and the offset of the initial avoidance path.

Optionally, the calculating a shortest avoidance path based on the second node includes:

according to the position information of the vehicle in the navigation information, taking a second node where the vehicle is located as a starting point, and randomly selecting an adjacent second node as a next starting point to obtain a second planned path reaching the target location;

forming a path cluster by a plurality of second planning paths;

and comparing the multiple second planned paths in each path cluster with the initial avoidance path respectively to obtain a second planned path with the minimum offset with the initial avoidance path in each path cluster as the shortest avoidance path.

Optionally, the determining an optimal path according to the offset of the shortest avoidance path and the initial avoidance path includes:

acquiring at least two shortest avoidance paths with intersection points to form a path group;

dividing each shortest avoidance path into at least two sub-paths by taking the intersection point of the shortest avoidance path in each path group as a dividing point;

combining sub-paths of different shortest avoidance paths in the same path group by taking the division points as connection points to generate at least two recombination paths leading to a target site;

comparing the recombined path with the initial avoidance path to obtain a recombined path with the minimum offset between the recombined path and the initial avoidance path in each path group as a recombined preferred path;

determining the optimal path based on the recomposed preferred path.

Optionally, said determining the optimal path based on the recomposed preferred path comprises:

acquiring a plurality of recombination preferred paths to form a recombination path cluster;

comparing the recombined preferred paths in each recombined path cluster with the initial avoidance path respectively to obtain a recombined preferred path with the minimum offset between the recombined preferred path and the initial avoidance path in each recombined path cluster as an alternative path;

and sequencing according to the offset between each alternative path and the initial avoidance path, and taking the alternative path with the minimum offset as an optimal path.

Optionally, before performing local path planning according to the static obstacle position area and the dot matrix map, the method further includes:

according to the position information of the vehicle in the navigation information, the vehicle spreads around by taking a first node where the vehicle is located as a center, and the equipment perception range is obtained;

if no static obstacle position area exists in the equipment sensing range, taking the equipment sensing range as a path planning area;

if a static obstacle position area exists in the equipment sensing range, acquiring the static obstacle position area which is farthest away from the vehicle in the equipment sensing range, and generating a distance value between the static obstacle position area and the vehicle;

planning the diameter of a path planning area to be the distance numerical value plus a preset numerical value by taking a first node where the vehicle is located as a circle center;

if the distance value exceeds the equipment sensing range after being added with a preset value, taking the equipment sensing range as a path planning area;

and according to the static obstacle position area and the dot matrix diagram, local path planning is carried out in the path planning area.

Optionally, the performing local path planning according to the static obstacle position area and the dot matrix map includes:

determining a first passing area in the visualization area according to the static obstacle position area;

according to the position information of the vehicle in the navigation information, in the first passing area, a first node where the vehicle is located is used as a starting point, and an adjacent first passable node is randomly selected as a next starting point to obtain a first planned path reaching a target place;

and comparing the avoidance paths in the first planned path to determine the shortest initial avoidance path to the target site.

Optionally, performing secondary distance marking according to the dynamic obstacle position area to obtain a plurality of second nodes, including:

marking the dynamic barrier location area as a no-pass area within the first pass area; periodically updating the no-passing area according to the acquisition period of the dynamic barrier position area;

determining the second passing area according to the first passing area and the no-passing area;

and marking at equal intervals in the second passing area to obtain a plurality of second nodes.

In order to solve the above problems, the present invention further provides an automatic driving obstacle avoidance device, including:

the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring navigation information and barrier information, and the barrier information comprises a static barrier position area and a dynamic barrier position area;

the first marking module is used for marking the visual area in the navigation information at equal intervals for one time to obtain a dot matrix diagram comprising a plurality of first nodes;

the first path planning module is used for carrying out local path planning according to the static obstacle position area and the dot matrix map to obtain a first planned path, and determining an initial avoidance path which is shortest to a target site on the basis of the first planned path, wherein the first planned path comprises a set of avoidance paths from a current position to a reachable first node which avoids the static obstacle position area;

the secondary marking module is used for carrying out secondary distance marking according to the dynamic barrier position area to obtain a plurality of second nodes; the mark spacing of the second node is smaller than the mark spacing of the first node;

and the optimal path confirmation module is used for calculating the shortest avoidance path based on the second node and determining the optimal path according to the shortest avoidance path and the offset of the initial avoidance path.

In order to solve the above problem, the present invention also provides an electronic device, including:

one or more processors;

a storage device to store one or more programs that, when executed by the one or more processors, cause the electronic device to implement the autopilot obstacle avoidance method.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, wherein computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the automatic driving obstacle avoidance method.

The invention has the beneficial effects that:

in the process of confirming the initial avoidance path, only the static obstacle position area is considered, but the dynamic obstacle position area is not considered, because the dynamic obstacle can change the position in real time, if the initial avoidance path is determined according to the dynamic obstacle, not only the calculation processing amount is increased, but also the initial avoidance path can not be used as a fixed and unchangeable reference path to confirm the optimal path.

When the second node is marked, the avoidance consideration of the position area of the dynamic barrier is increased, so that the automatic driving vehicle can avoid not only the static barrier, but also the dynamic barrier, and the driving safety is guaranteed.

According to the scheme, the initial avoidance path and the optimal path are quickly acquired by reducing the calculation processing amount, so that sufficient avoidance response time is provided for the automatic driving vehicle, and the driving safety and the obstacle avoidance flexibility are improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

FIG. 1 is a schematic illustration of an implementation environment shown in an exemplary embodiment of the present application;

FIG. 2 is a flow chart illustrating an autonomous driving obstacle avoidance method according to an exemplary embodiment of the present application;

fig. 3 is a flow chart of step S30 in the embodiment shown in fig. 2 in an exemplary embodiment.

Fig. 4 is a flow chart of step S306 in the embodiment shown in fig. 3 in an exemplary embodiment.

Fig. 5 is a flowchart of step S40 in the embodiment shown in fig. 2 in an exemplary embodiment.

Fig. 6 is a flow chart of step S50 in the embodiment shown in fig. 2 in an exemplary embodiment.

Fig. 7 is a flow chart of step S508 in the embodiment shown in fig. 6 in an exemplary embodiment.

Fig. 8 is a block diagram of an autonomous driving obstacle avoidance apparatus according to an exemplary embodiment of the present application.

FIG. 9 is a block diagram of a second tagging module shown in an exemplary embodiment of the present application.

Fig. 10 is a block diagram of an optimal path validation module shown in an exemplary embodiment of the present application.

FIG. 11 is a block diagram of an optimal path election submodule, shown in an exemplary embodiment of the present application

FIG. 12 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Other advantages and effects of the present invention will become apparent to those skilled in the art from the disclosure herein, wherein the embodiments of the present invention are described in detail with reference to the accompanying drawings and preferred embodiments. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, and are not intended to limit the scope of the present invention.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.

The automatic driving obstacle avoidance method provided by the embodiment of the invention can be applied to an implementation environment shown in fig. 1, wherein network communication is performed between the intelligent terminal 1 and the server 2, and the navigation map software is installed in the intelligent terminal 1, so that the navigation map software can refresh road conditions in minutes, that is, a network request can be made to the server 2 every minute according to the domain name of the intelligent terminal 1, and then the server 2 can return corresponding navigation information to the navigation map software. The navigation information includes vehicle own position information, lane number information, lane width information, a visualization area, and the like.

The intelligent terminal 1 shown in fig. 1 may be any terminal device supporting installation of navigation map software, such as a smart phone, a vehicle-mounted computer, a tablet computer, a notebook computer, and a wearable device, but is not limited thereto. The server 2 shown in fig. 2 is a navigation server, and may be, for example, an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), and a big data and artificial intelligence platform, which is not limited herein. The intelligent terminal 210 may communicate with the server 2 through a wireless network such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), 5G (fifth generation mobile information technology), and the like, which is not limited herein.

Intelligent terminal 1 can install on the vehicle that needs autopilot in this embodiment, acquires through the radar of vehicle self and camera and fuses the perception information, fuses the perception information and includes static obstacle position region and dynamic obstacle position region, according to static obstacle position region and dynamic obstacle position region, carries out route planning to autopilot's vehicle, avoids autopilot vehicle and static obstacle or dynamic obstacle collision, improves autopilot's security.

Referring to fig. 2, fig. 2 is a flowchart illustrating an automatic driving obstacle avoidance method according to an exemplary embodiment of the present application. The method can be applied to the implementation environment shown in fig. 1 and is specifically executed by the intelligent terminal 1 in the implementation environment. It should be understood that the method may be applied to other exemplary implementation environments and is specifically executed by devices in other implementation environments, and the embodiment does not limit the implementation environment to which the method is applied.

As shown in fig. 2, in an exemplary embodiment, the automatic driving obstacle avoidance method at least includes steps S10 to S50, which are described in detail as follows:

step S10, acquiring navigation information and obstacle information, where the obstacle information includes a static obstacle position area and a dynamic obstacle position area.

Specifically, the navigation information includes vehicle own position information, lane number information, lane width information, lane line type, visualization area, and the like. And acquiring the lane line type so as to know whether the operations such as lane change, turning around and the like can be performed. Static obstacles include lane barriers, stationary vehicles on the road, maintenance signs, and the like. Dynamic obstacles include pedestrians, moving vehicles, and the like.

And step S20, marking the visual area in the navigation information at equal intervals once to obtain a dot matrix including a plurality of first nodes.

Specifically, the mark interval may be set as required, in this embodiment, the mark interval is 0.5m, a dot diagram is generated at an interval of 0.5m from the position of the vehicle to the periphery according to the position information of the vehicle, the position of the vehicle is used as an origin, the first node is marked, and finally, a dot diagram covering each lane is formed.

And step S30, performing local path planning according to the static obstacle position area and the dot matrix map to obtain a first planned path, and determining an initial avoidance path with the shortest heading to a target site based on the first planned path, wherein the first planned path comprises a set of avoidance paths from a current position to a reachable first node avoiding the static obstacle position area.

As shown in fig. 3, step S30 includes at least step S301 to step S306.

Step S301, according to the position information of the vehicle in the navigation information, the information is spread around by taking a first node where the vehicle is located as a center, and the equipment perception range is obtained.

Specifically, the device perception range refers to the perception range of radar, a camera, or the like that the vehicle itself has.

Step S302, if no static obstacle position area exists in the equipment sensing range, the equipment sensing range is used as a path planning area.

Specifically, because only the static obstacle position region and the dynamic obstacle position region can be detected within the sensing range, if the path planning region is set outside the sensing range, the static obstacle and the dynamic obstacle cannot be avoided by the partial path planning outside the sensing range.

Step S303, if a static obstacle position area exists in the equipment sensing range, acquiring the static obstacle position area which is farthest away from the vehicle in the equipment sensing range, and generating a distance value between the static obstacle position area and the vehicle.

Specifically, the distance data is acquired so as to bring a static obstacle position area farthest from the vehicle into a routing area, so that obstacle avoidance planning of the static obstacle is realized.

Step S304, with a first node where the vehicle is located as a circle center, the diameter of the path planning area is planned to be the distance value plus a preset value.

Specifically, the preset value may be set according to requirements, and the preset value in this embodiment is, for example, 100 meters.

Step S305, if the distance value exceeds the equipment perception range after being added with a preset value, taking the equipment perception range as a path planning area.

Specifically, since the static obstacle position area and the dynamic obstacle position area cannot be detected beyond the device sensing range, the obstacle avoidance planning cannot be performed, and therefore, the path planning outside the sensing range is not considered in this embodiment.

And S306, performing local path planning in the path planning region according to the static obstacle position region and the dot matrix diagram.

Specifically, the initial obstacle avoidance path is obtained by genetic algorithm calculation such as a dixtar algorithm, a heuristic search algorithm (a star algorithm) and the like. Through the steps S301 to S306, the dynamic adjustment of the path planning region is realized, the path planning region is set in the sensing range, the path planning is not performed in the whole visualization region, the number of planned paths is reduced, and the path planning is conveniently and rapidly completed.

In an embodiment, if the device sensing range is within 500 meters from the vehicle itself, and the static obstacle location area is not detected within the device sensing range, the path planning area is the device sensing range.

In an embodiment, if the device sensing range is within 500 meters from the vehicle itself, and the static obstacle location area farthest from the vehicle itself is located at a position 300 meters from the vehicle within the device sensing range, the distance value generated in step S303 is 300 meters, and the diameter of the path planning area in step S304 should be 400m (the preset value takes 100 meters as an example, the diameter of the path planning area is the distance value plus the preset value).

In an embodiment, if the sensing range of the device is within 500 meters from the vehicle itself, and the static obstacle location area farthest from the vehicle itself is located at a position 450 meters from the vehicle within the sensing range, the distance value generated in step S303 is 450 meters, and the diameter of the path planning area in step S304 should be 550m (the preset value takes 100 meters as an example, the diameter of the path planning area is the distance value plus the preset value). Since the diameter of the current path planning region is larger than the device sensing range, according to step S305, the device sensing range is used as the path planning region.

As shown in fig. 4, step S306 includes at least step S3061 to step S3063.

Step S3061, determining a first traffic area within the visualization area according to the static obstacle location area.

Specifically, the first passing area is an area except for a static obstacle position area in the routing area.

Step S3062, according to the position information of the vehicle in the navigation information, in the first passing area, a first node where the vehicle is located is taken as a starting point, and an adjacent first passable node is randomly selected as a next starting point, so as to obtain a first planned path reaching the target location.

It is worth to be noted that the first planned path is an ideal path, that is, only a static obstacle position area is avoided during planning, and a dynamic obstacle position area is not considered, so that the path planning consideration factor is reduced, and the planning efficiency is accelerated.

Step S3063, comparing the avoidance paths in the first planned path to determine the shortest initial avoidance path to the target location.

As can be seen from steps S3061 to S3063, the number of planned avoidance paths in the first planned path is several, and the initial avoidance path having the shortest distance to the target location in all the paths needs to be calculated quickly, so as to avoid that the initial avoidance path acquisition time is too long. The mark distance of the first node is 0.5m, and the mark distance is longer, so that the required path planning amount is reduced, and the initial avoidance path is quickly obtained.

Step S40, carrying out secondary distance marking according to the dynamic obstacle position area to obtain a plurality of second nodes; the mark pitch of the second node is smaller than the mark pitch of the first node.

As shown in fig. 5, at least step S401 to step S403 are included in step S40.

Step S401, marking the dynamic barrier position area as a no-pass area in the first pass area; and periodically updating the no-passing area according to the acquisition period of the dynamic obstacle position area.

It should be noted that, since the position of the dynamic obstacle object is changed, that is, the no-pass area changes according to the change of the position of the dynamic obstacle object, the no-pass area needs to be periodically (for example, periodically set to 0.02s) updated according to the position area of the dynamic obstacle object, so as to achieve the avoidance of the dynamic obstacle object.

Step S402, determining the second passing area according to the first passing area and the no-passing area.

It is worth explaining that the second passing area not only considers the static obstacle position area but also considers the dynamic obstacle position area in the application, so as to realize real-time obstacle avoidance.

And S403, marking at equal intervals in the second passing area to obtain a plurality of second nodes.

Specifically, the distance between the second node markers may be set according to a requirement, the smaller the distance between the second node markers is, the denser the number of the second nodes is, and when the path is planned while avoiding obstacles, the planned path is more accurate, but the planned path amount increases with the increase of the number of the second nodes when the path is planned, which affects the path planning efficiency. In this embodiment, the pitch of the first node mark is 0.5m, and the pitch of the second node mark is 0.02 m. Assuming that the width of the lane where the vehicle is located is 5m, the vehicle required to be automatically driven runs at the speed of 30m/s, and the total number of lanes is three.

When the first nodes are dotted, the vehicle 0.02s should travel 0.6m, one first node is marked at intervals of 0.5m, only 1 node is marked at 0.6m, a 1-row 30-column dot diagram is formed in three lanes, and the number of the first nodes is 30 in total.

When the second nodes are reached, the vehicle 0.02s should run for 0.6m, one second node is marked every 0.02m, then the marking of 30 second nodes is carried out for 0.6m in total, a 30-row 750-column dot-matrix diagram is formed in three lanes, and the number of the second nodes reaches 22500 in total.

Therefore, the number of the second nodes is far larger than that of the first nodes, and if the optimal path is calculated according to the method for calculating the initial avoidance path, the problems of large calculation workload, low path planning efficiency and the like exist.

And step S50, calculating the shortest avoidance path based on the second node, and determining the optimal path according to the offset of the shortest avoidance path and the initial avoidance path.

As shown in fig. 6, at least step S501 to step S508 are included in step S50.

Step S501, according to the position information of the vehicle in the navigation information, a second node where the vehicle is located is taken as a starting point, and an adjacent second node is randomly selected as a next starting point, so that a second planned path reaching the target location is obtained.

Specifically, one second node is used as a starting point to connect any adjacent second node, the second node is used as a next starting point to connect the adjacent second nodes, and the steps are repeated in a circulating mode until the second node where the target location is located is reached, so that a second planning path is formed.

Step S502, a plurality of second planning paths are combined into a path cluster.

It should be noted that the path cluster in this embodiment does not include all the second planned paths, but a small part of all the second planned paths, and the specific number of the second planned paths in the path cluster may be set according to requirements.

In one embodiment, there are 5 second planned paths in the path cluster, for example.

Step S503, comparing the multiple second planned paths in each path cluster with the initial avoidance path, respectively, to obtain a second planned path with the minimum offset from the initial avoidance path in each path cluster, and using the second planned path as the shortest avoidance path.

As can be seen from step S503, in this embodiment, only one second planned path is finally selected as the shortest avoidance path in each path cluster.

Step S504, at least two shortest avoidance paths with intersection points are obtained to form a path group.

Specifically, the number of the shortest avoidance paths in the path group may be set according to requirements, and is set to 2 in this embodiment as an example.

Step S505 is to divide each shortest avoidance path into at least two sub-paths by using the intersection point of the shortest avoidance path in each path group as a dividing point.

It should be noted that only the shortest avoidance paths with intersecting points can form a path group, otherwise, sub-paths between different shortest avoidance paths cannot be connected by dividing points to form a complete regrouping path.

Step S506, combining the sub-paths of different shortest avoidance paths in the same path group by taking the division points as connection points to generate at least two recombination paths leading to the target site.

It should be noted that the number of the recombination paths between the two shortest avoidance paths may be two, or may constitute more recombination paths, and the number of the recombination paths is specifically determined by the number of the intersection points between the two shortest avoidance paths. For example, if there is only one intersection point in the two shortest paths constituting the path group, there are only two recombination paths, and if there are only two intersection points in the two shortest paths constituting the path group, there are six recombination paths.

Step S507, comparing the regrouped path with the initial avoidance path to obtain a regrouped path with the smallest offset between the regrouped path and the initial avoidance path in each path group, and using the regrouped path as a regrouped preferred path.

Specifically, at least half of the recombination paths will be eliminated, via step S507.

And step S508, determining the optimal path based on the recombined preferred path.

As shown in fig. 7, at least steps S5081 to S5083 are included in step S508.

Step S5081, a plurality of reassembly preferred paths are obtained to form a reassembly path cluster.

In particular, the division of the path cluster is regrouped in order to facilitate further screening of the regrouped preferred paths. The number of the recombination preferred paths in the recombination path cluster can be set according to requirements, for example, the number of the recombination preferred paths in each recombination path cluster is 10.

Step S5082, comparing the recombined preferred paths in each recombined path cluster with the initial avoidance path, to obtain a recombined preferred path with the smallest offset between the recombined preferred path and the initial avoidance path in each recombined path cluster, and using the recombined preferred path as an alternative path.

Specifically, the number of the recombined path clusters can be set according to requirements, and the larger the number of the recombined path clusters is, the smaller the offset between the finally selected optimal path and the initial avoidance path is. In this embodiment, taking the regrouping path cluster as 100 examples, the regrouping preferred path in the 100 regrouping path clusters is compared with the initial avoidance path to obtain 100 candidate paths.

And step 5083, sorting the candidate paths according to the offset between each candidate path and the initial avoidance path, and taking the candidate path with the minimum offset as an optimal path.

As can be seen from steps S501 to S508, the optimal path is obtained without comparing each second planned path with the initial avoidance path, only a part of the second planned paths are compared with the initial avoidance path, and the optimal path is finally selected in a continuous elimination manner. The number of the second planned paths does not need to plan all paths which can lead to the target location, and only the acquisition of the optimal paths is needed, so that the calculation amount of the server side is reduced.

From step S10 to step S50, in the whole optimal path calculation process, only the static obstacle location area is considered when the first planned path is planned, and the dynamic obstacle location area is not considered, because the dynamic obstacle may change in location in real time, and when the optimal path is calculated subsequently, the location of the dynamic obstacle may have changed, and there is no reference value for calculating the optimal path. And when the initial avoidance path is obtained, only the optimal path reaching the target location under the ideal state is considered and no dynamic barrier exists.

And when the optimal path is obtained, the distance between the marks of the second nodes is set to be smaller than the mark distance of the first nodes, at the moment, the number of the second nodes is far larger than the mark number of the first nodes, and if all the second planned paths are compared with the initial avoidance paths at the moment, the calculation workload is large, the path planning efficiency is low, the barriers are not avoided timely, and the trip safety is influenced. Therefore, a mode of comparing the part of the second planning path with the initial avoidance path is selected to reduce the calculation amount. And increasing the number of paths going to the destination point by recombining the paths to select the final optimal path.

As shown in fig. 8, the exemplary autonomous driving obstacle avoidance apparatus includes:

the data acquisition module 10 is configured to acquire navigation information and obstacle information, where the obstacle information includes a static obstacle position area and a dynamic obstacle position area;

the first marking module 20 is configured to mark a visualization area in the navigation information at equal intervals for one time to obtain a bitmap including a plurality of first nodes;

a first path planning module 30, configured to perform local path planning according to the static obstacle location area and the bitmap to obtain a first planned path, and determine, based on the first planned path, an initial avoidance path that is the shortest to a target location, where the first planned path includes a set of avoidance paths from a current location to a reachable first node that avoids the static obstacle location area;

the second marking module 40 is used for marking the secondary distance according to the position area of the dynamic barrier to obtain a plurality of second nodes; the mark distance of the second node is smaller than that of the first node;

and an optimal path confirmation module 50, configured to calculate a shortest avoidance path based on the second node, and determine an optimal path according to offsets of the shortest avoidance path and the initial avoidance path.

In this embodiment, the data acquisition module 10 acquires navigation information and obstacle information, and the first marking module 20 marks a first node in a visualization area to form a bitmap. Through the first path planning module 30, a first planned path is obtained according to the static obstacle position area, and an initial avoidance path which is shortest to the target location is calculated in the first planned path.

The marking of the second node is performed within the passable area by a second marking module 40. The optimal path confirmation module 50 is used to plan a second planned path, and an optimal path is calculated according to the second planned path and the initial avoidance path.

In one embodiment, the first path planning module 30 includes:

and the perception range acquisition unit is used for acquiring the perception range of the equipment by taking a first node where the vehicle is located as a center to diffuse all around according to the position information of the vehicle in the navigation information.

And the dynamic path planning area adjusting unit is used for adjusting the path planning area. And if no static obstacle position area exists in the equipment sensing range, taking the equipment sensing range as a path planning area. And if the static obstacle position area exists in the equipment sensing range, acquiring the static obstacle position area which is farthest away from the vehicle in the equipment sensing range, and generating a distance value between the static obstacle position area and the vehicle. And the diameter planning method is also used for planning the diameter of the path planning area to be the sum of the distance value and a preset value by taking a first node where the vehicle is located as a circle center. And if the distance value exceeds the equipment perception range after being added with a preset value, taking the equipment perception range as a path planning area.

As shown in fig. 9, in one embodiment, the second marking module 40 includes:

a no-pass area identification unit 401, configured to mark the dynamic obstacle location area as a no-pass area in the first pass area; and periodically updating the no-passing area according to the acquisition period of the dynamic obstacle position area.

A second passing area confirming unit 402, configured to determine the second passing area according to the first passing area and the no-passing area.

A second node marking unit 403, configured to mark a distance in the second passing area to obtain a plurality of second nodes.

As shown in fig. 10, in one embodiment, the optimal path confirmation module 50 includes:

and a second path planning submodule 501, configured to randomly select an adjacent second node as a next starting point according to the position information of the vehicle in the navigation information, where the second node is located, so as to obtain a second planned path to the target location.

The path cluster building sub-module 502 is configured to build a path cluster from the plurality of second planned paths.

The shortest avoidance path determining sub-module 503 is configured to compare the multiple second-time planned paths in each path cluster with the initial avoidance path, respectively, to obtain a second-time planned path with a minimum offset from the initial avoidance path in each path cluster, and use the second-time planned path as the shortest avoidance path.

The path group forming sub-module 504 is configured to obtain at least two shortest avoidance paths having intersection points, and form a path group.

And the path division submodule 505 is configured to divide each shortest avoidance path into at least two sub-paths by using an intersection of the shortest avoidance path in each path group as a division point.

The path recombining sub-module 506 is configured to combine sub-paths of different shortest avoidance paths in the same path group with the division point as a connection point, and generate at least two recombined paths leading to the target location.

And a recombined preferred path election module 507, configured to compare the recombined path with the initial avoidance path to obtain a recombined path with the smallest offset between each path group and the initial avoidance path, and use the recombined path as a recombined preferred path.

And an optimal path election sub-module 508, configured to determine the optimal path according to the recombined preferred path.

As shown in fig. 11, in an embodiment, the optimal path election sub-module 508 includes:

the cluster building unit 5081 is configured to obtain a plurality of recombined preferred paths to form a recombined path cluster.

An alternative path election unit 5082, configured to compare the recombined preferred paths in each recombined path cluster with the initial back-off path, respectively, to obtain a recombined preferred path with the smallest offset between the recombined preferred path and the initial back-off path in each recombined path cluster, where the recombined preferred path is used as an alternative path

And an optimal path election unit 5083, configured to sort according to the offset between each candidate path and the initial avoidance path, and use the candidate path with the smallest offset as the optimal path.

It should be noted that the autonomous driving obstacle avoidance apparatus provided in the foregoing embodiment and the autonomous driving obstacle avoidance method provided in the foregoing embodiment belong to the same concept, and specific manners in which each module and unit perform operations have been described in detail in the method embodiment, and are not described herein again. In practical applications, the automatic driving obstacle avoidance device provided in the above embodiment may distribute the above functions to different functional modules according to needs, that is, divide the internal structure of the device into different functional modules to complete all or part of the above described functions, which is not limited herein.

An embodiment of the present application further provides an electronic device, including: one or more processors; a storage device, configured to store one or more programs, which when executed by the one or more processors, cause the electronic device to implement the automatic driving obstacle avoidance method provided in each of the above embodiments.

FIG. 12 illustrates a schematic structural diagram of a computer system suitable for use to implement the electronic device of the embodiments of the subject application. It should be noted that the computer system of the electronic device shown in fig. 12 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 12, the computer system 1200 includes a Central Processing Unit (CPU)1201, which can perform various appropriate actions and processes, such as executing the method described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1202 or a program loaded from a storage section 1208 into a Random Access Memory (RAM) 1203. In the RAM 1203, various programs and data necessary for system operation are also stored. The CPU 1201, ROM 1202, and RAM 1203 are connected to each other by a bus 1204. An Input/Output (I/O) interface 1205 is also connected to bus 1204.

The following components are connected to the I/O interface 1205: an input portion 1206 including a keyboard, a mouse, and the like; an output section 1207 including a Display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1209 performs communication processing via a network such as the internet. A driver 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 1210 as necessary, so that a computer program read out therefrom is mounted into the storage section 1208 as necessary.

In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 1209, and/or installed from the removable medium 1211. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 1201.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, 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. In the present application, a computer-readable signal medium may comprise a propagated data signal with a computer-readable computer program embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

Another aspect of the present application also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the road condition refreshing method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist separately without being incorporated in the electronic device.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the automatic driving obstacle avoidance method provided in the foregoing embodiments.

The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims

1. An automatic driving obstacle avoidance method is characterized by comprising the following steps:

carrying out secondary interval marking according to the dynamic barrier position area to obtain a plurality of second nodes; the mark distance of the second node is smaller than that of the first node;

2. The autonomous driving obstacle avoidance method of claim 1, wherein the calculating a shortest avoidance path based on the second node comprises:

forming a path cluster by the plurality of second planned paths;

3. The automatic driving obstacle avoidance method according to claim 1, wherein the determining an optimal path according to the shortest avoidance path and the offset of the initial avoidance path comprises:

determining the optimal path based on the recomposed preferred path.

4. The autonomous driving obstacle avoidance method of claim 3, wherein said determining the optimal path based on the recomposed preferred path comprises:

5. The automatic driving obstacle avoidance method according to claim 1, wherein before performing the local path planning according to the static obstacle location area and the dot matrix map, the method further comprises:

6. The automatic driving obstacle avoidance method of claim 1, wherein the local path planning according to the static obstacle location area and the dot matrix map comprises:

and comparing the avoidance paths in the first planning path to determine the shortest initial avoidance path to the target site.

7. The automatic driving obstacle avoidance method according to claim 6, wherein secondary distance marking is performed according to the dynamic obstacle position area to obtain a plurality of second nodes, and the method comprises:

8. An autonomous driving obstacle avoidance apparatus, the apparatus comprising:

the first marking module is used for marking the visual area in the navigation information at equal intervals once to obtain a dot matrix diagram comprising a plurality of first nodes;

9. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the autonomous driving obstacle avoidance method of any of claims 1 to 7.

10. A computer-readable storage medium having computer-readable instructions stored thereon, which, when executed by a processor of a computer, cause the computer to perform the automated driving obstacle avoidance method of any one of claims 1 to 7.