CN116879921A

CN116879921A - Laser radar sensing method, device, equipment and medium based on grid

Info

Publication number: CN116879921A
Application number: CN202311028710.0A
Authority: CN
Inventors: 罗海; 陈晨光; 张硕; 钱永强
Original assignee: Shanghai Mooe Robot Technology Co ltd
Current assignee: Shanghai Mooe Robot Technology Co ltd
Priority date: 2023-08-15
Filing date: 2023-08-15
Publication date: 2023-10-13

Abstract

The embodiment of the invention discloses a laser radar sensing method, a laser radar sensing device, laser radar sensing equipment and a laser radar sensing medium based on a grid. Wherein the method comprises the following steps: constructing a grid map according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids; acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determining a point cloud sensing state of the point cloud according to height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state; determining a grid sensing state of a target grid according to the point cloud sensing states of all the point clouds falling into the target grid; and controlling the running of the unmanned vehicle according to the grid perception states of all grids in the grid map. According to the technical scheme, the obstacle and the drop point can be accurately and effectively detected through the laser radar based on the constructed grid map, and the running efficiency and the running safety of the unmanned vehicle are improved.

Description

Laser radar sensing method, device, equipment and medium based on grid

Technical Field

The invention relates to the technical field of radar detection, in particular to a laser radar sensing method, device, equipment and medium based on a grid.

Background

Along with the rapid development of unmanned vehicle intelligent technology, unmanned vehicles are widely used in the fields of express logistics, intelligent storage, industry and the like at present. When the unmanned vehicle encounters an obstacle, a downward step section or a dock with a large height difference, if the unmanned vehicle advances according to a set running speed, the unmanned vehicle can collide, fall and even be damaged, equipment loss is caused, and the running efficiency and the running safety of the unmanned vehicle are affected.

At present, the obstacle and the drop point are determined by the height detection result of laser radar point cloud information, but the mode can bring certain detection errors, so that the running efficiency of the unmanned vehicle is low, and the safe running of the unmanned vehicle is influenced.

Disclosure of Invention

The invention provides a laser radar sensing method, a device, equipment and a medium based on a grid, which can accurately and effectively detect obstacles and drop points through a laser radar based on a constructed grid map, and improve the running efficiency and the running safety of an unmanned vehicle.

According to an aspect of the present invention, there is provided a grid-based lidar sensing method, the method comprising:

Constructing a grid map according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids;

acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determining a point cloud sensing state of the point cloud according to height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state;

determining a grid sensing state of a target grid according to the point cloud sensing states of all the point clouds falling into the target grid;

and controlling the running of the unmanned vehicle according to the grid perception states of all grids in the grid map.

According to another aspect of the present invention, there is provided a grid-based lidar sensing device, comprising:

the grid map construction module is used for constructing a grid map according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids;

the point cloud sensing state determining module is used for acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle and determining the point cloud sensing state of the point cloud according to the height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state;

The grid perception state determining module is used for determining the grid perception state of the target grid according to the point cloud perception states of all the point clouds falling into the target grid;

and the unmanned vehicle running control module is used for controlling the running of the unmanned vehicle according to the grid perception states of all grids in the grid map.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the grid-based lidar sensing method of any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement a grid-based lidar perception method according to any of the embodiments of the present invention when executed.

According to the technical scheme, the grid map is constructed according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids; acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determining a point cloud sensing state of the point cloud according to height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state; determining a grid sensing state of a target grid according to the point cloud sensing states of all the point clouds falling into the target grid; and controlling the running of the unmanned vehicle according to the grid perception states of all grids in the grid map. According to the technical scheme, the obstacle and the drop point can be accurately and effectively detected through the laser radar based on the constructed grid map, and the running efficiency and the running safety of the unmanned vehicle are improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

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

FIG. 1 is a flow chart of a method for grid-based lidar sensing according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for sensing a grid-based lidar according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a laser radar sensing device based on a grid according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device implementing a grid-based lidar sensing method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a method for sensing a laser radar based on a grid, which is applicable to a case of performing laser radar sensing based on a constructed grid map according to an embodiment of the present invention, where the method may be performed by a grid-based laser radar sensing device, and the grid-based laser radar sensing device may be implemented in hardware and/or software, and the grid-based laser radar sensing device may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:

s110, constructing a grid map according to the driving area range of the unmanned vehicle; wherein, the grid map comprises a plurality of grids.

In this embodiment, it is first necessary to construct a grid map according to the driving area range of the unmanned vehicle. Wherein, the grid map comprises a plurality of grids. For example, assuming that the driving area range of the unmanned vehicle may be represented as { min_x, min_y, max_x, max_y }, and the unit size of each grid in the grid map is represented as patch_size, the grid map size is represented as width height, there are: width= (max_x-min_x)/latch_size+1, height= (max_y-min_y)/latch_size+1. After the grid map is constructed, initializing the grid to an unknown state, wherein the unknown state indicates that the grid is not perceived.

S120, acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determining a point cloud sensing state of the point cloud according to the height information of the point cloud information falling into a target grid.

In this embodiment, after the grid map is constructed according to the driving area range of the unmanned vehicle, the radar point cloud information of the current frame can be obtained according to the laser radar deployed on the unmanned vehicle, and which point clouds fall into which grid can be determined based on the radar point cloud information of the current frame. Specifically, each grid in the grid map is numbered in advance with a grid id, where the grid id may be used to uniquely characterize the grid. Assuming that the two-dimensional x-coordinate and y-coordinate of the grid map are denoted as map_x and map_y, respectively, and the x-coordinate and y-coordinate of the point cloud are denoted as point_x and point_y, respectively, where map_x= (point_x-min_x)/patch_size, map_y= (point_y-min_y)/patch_size, there is id=map_x height+map_y. Thus, it can be determined by the grid id which grid the point cloud falls into.

After determining which grid each point cloud falls into, the point cloud perceived state of the point cloud may be determined from the height information of the point cloud information falling into the target grid. The target grid may refer to any one grid in the grid map. The perceived states include a passable state, an obstacle state, and a drop point state. Specifically, the passable state is used for representing a state that the unmanned vehicle can safely pass on the normal ground, the obstacle state is used for representing a state of sensing the obstacle, and the falling point state is used for representing a state of sensing the falling point.

In this embodiment, optionally, determining the point cloud sensing state of the point cloud according to the altitude information of the point cloud information falling in the target grid includes: if the height information of the point cloud information is larger than the sum of the ground height and a preset height error threshold value, determining that the point cloud sensing state of the point cloud is an obstacle state; if the height information of the point cloud information is smaller than the difference between the ground height and the preset height error threshold value, determining that the point cloud sensing state of the point cloud is a falling point state; if the absolute value of the difference between the height information of the point cloud information and the ground height is smaller than the preset height error threshold value, determining that the point cloud sensing state of the point cloud is a passable state.

In this embodiment, the point cloud sensing state of each point cloud in the target grid may be determined according to the relationship between the height information of the point cloud information, the ground height, and the preset height error threshold. The preset height error threshold may be set according to actual requirements, and the embodiment is not specifically limited. For example, assuming that the height information of the point cloud information is point_z, the ground height is ground_z, and the preset height error threshold is delta_z. Wherein the height information of the point cloud information and the ground height are obtained in the same coordinate system (scanning coordinate system of the laser radar). If point_z > group_z+delta_z, determining that the point cloud sensing state of the point cloud is an obstacle state; if point_z is less than group_z-delta_z, determining that the point cloud sensing state of the point cloud is a falling point state; if |point_z-group_z| < delta_z, determining the point cloud sensing state of the point cloud as a passable state.

According to the scheme, through the arrangement, the point cloud sensing state of each point cloud in the target grid can be rapidly and accurately determined according to the relation among the height information of the point cloud information, the ground height and the preset height error threshold.

Furthermore, the sensing range of the certain range of raster data can be obtained according to the actual requirement, for example, the sensing range of a certain distance around the current position of the unmanned vehicle is obtained. For example, the sensing range may be set to a preset distance range in front of the unmanned vehicle, and the preset distance range may be determined according to a sum of a current vehicle speed braking distance and a preset parking safety distance of the unmanned vehicle, and a blind area distance under the laser scanning platform and a preset laser recognition distance. The current vehicle speed braking distance may refer to a buffering distance required by the unmanned vehicle to brake at the current vehicle speed. The preset parking safety distance can be understood as a fault tolerance distance of the braking distance of the current vehicle speed. The preset laser recognition distance can be understood as a fault tolerance distance of a blind area distance under the laser scanning platform, and it should be noted that the preset parking safety distance and the preset laser recognition distance can be set according to actual requirements, which is not specifically limited in this embodiment.

S130, determining the grid perception state of the target grid according to the point cloud perception states of all the point clouds falling into the target grid.

In this embodiment, after determining the point cloud sensing states of the point clouds falling into the target grid, the grid sensing state of the target grid may be determined according to the point cloud sensing states of all the point clouds falling into the target grid. The grid sensing state may refer to a point cloud sensing state corresponding to the grid. For example, in determining the grid sensing state of the target grid, a traversal determination manner may be adopted, or an overall determination manner may be adopted. The traversing determination mode is that for a target grid, once the point cloud sensing state of one of the point clouds is determined; the overall determination mode refers to that for the target grid, after the point cloud sensing states of all the point clouds are determined, the grid sensing state is finally determined.

In this embodiment, optionally, determining the grid sensing state of the target grid according to the point cloud sensing states of all the point clouds falling into the target grid includes: if the type of the point cloud sensing state of all the point clouds in the target grid is one, determining the point cloud sensing state as the grid sensing state of the target grid; if the types of the point cloud sensing states of all the point clouds in the target grid are at least two, determining the grid sensing state of the target grid according to the at least two point cloud sensing states.

In this embodiment, when determining the grid sensing state of the target grid, it is first required to determine whether the types of the point cloud sensing states of all the point clouds in the target grid are the same. If the point cloud sensing states are the same, namely the types of the point cloud sensing states of all the point clouds in the target grid are one, the point cloud sensing states can be directly determined to be the grid sensing states of the target grid; if the point cloud sensing states of all the point clouds in the target grid are different, namely the types of the point cloud sensing states of all the point clouds in the target grid are at least two, determining the grid sensing state of the target grid according to the at least two point cloud sensing states.

In this embodiment, optionally, determining the grid sensing state of the target grid according to at least two point cloud sensing states includes: if the at least two point cloud sensing states are the falling point state and the other state, determining a grid sensing state of the target grid according to the other states; wherein the other states are passable states and/or obstacle states; and if at least two point cloud sensing states are the obstacle state and the passable state, determining that the grid sensing state of the target grid is the obstacle state.

It should be noted that, since the drop point is the lowest point (the drop point height is smaller than the normal ground height), the other states are higher than the drop point, that is, the drop point state has the lowest priority. Therefore, in this embodiment, if the point cloud sensing state is the falling point state or another state, the grid sensing state of the target grid may be determined according to the other state, so as to prevent false detection caused by sensor noise. Wherein the other state is a passable state and/or an obstacle state. The three conditions are that the point cloud sensing state is a falling point state and a passable state (two states in total), the point cloud sensing state is a falling point state and an obstacle state (two states in total), and the point cloud sensing state is a falling point state, a passable state and an obstacle state (three states in total).

The obstacle height is larger than the normal ground height, that is, the obstacle state has the highest priority. Therefore, in the present embodiment, if the point cloud sensing state is the obstacle state and the passable state, it is possible to determine that the grid sensing state of the target grid is the obstacle state, thereby preventing false detection caused by sensor noise.

According to the scheme, through the arrangement, the grid sensing state of the target grid can be accurately determined according to at least two point cloud sensing states, so that false detection caused by sensor noise is prevented, and accuracy of determining the grid sensing state is improved.

And S140, controlling the running of the unmanned vehicle according to the grid perception states of all grids in the grid map.

In this embodiment, after determining the grid sensing states of the target grids, the driving of the unmanned vehicle may be further controlled according to the grid sensing states of all the grids in the grid map. Optionally, controlling the running of the unmanned vehicle according to the grid sensing states of all grids in the grid map includes: modifying the point cloud sensing states of all point clouds in a target grid according to the grid sensing states of the target grid in the grid map; clustering the point clouds according to the point cloud sensing states of all the point clouds in the modified grid map; and controlling the running of the unmanned vehicle according to the point cloud clustering result.

In this embodiment, first, the point cloud sensing states of all the point clouds in the target grid are modified according to the grid sensing states of the target grid in the grid map. Specifically, once the grid sensing state of the target grid is determined, the point cloud sensing states of all the point clouds in the target grid need to be uniformly modified into the grid sensing state. Accordingly, when the point cloud sensing states of all the point clouds in the target grid are modified, a traversal modification mode or an overall modification mode can be adopted. The traversal modification mode is to determine whether to modify the point cloud sensing states of all the point clouds in the target grid once by adopting the traversal determination mode every time the grid sensing states are determined; the overall modification mode is to modify the point cloud sensing states of all the point clouds in the target grid after the grid sensing states are finally determined by adopting the overall determination mode. It should be noted that, if the traversal modification is adopted, after the point cloud sensing states of all the point clouds in the target grid are modified each time, the state update time of the target grid needs to be recorded. The state update time may be a time corresponding to when the pointing cloud sensing state is updated.

After the point cloud sensing states of all the point clouds in the target grid are modified according to the grid sensing states of the target grid in the grid map, clustering processing can be carried out on the point clouds according to the point cloud sensing states of all the point clouds in the modified grid map, and then the running of the unmanned vehicle is controlled according to the point cloud clustering result. Optionally, controlling the unmanned vehicle to run according to the point cloud clustering result includes: determining a path state according to the point cloud clustering result; determining the path length of the unmanned vehicle in a passable state on the current running path according to the path state; if the path length is greater than or equal to the sum of the current vehicle speed braking distance and the preset parking safety distance, controlling the unmanned vehicle to continue running; if the path length is smaller than the sum of the current vehicle speed braking distance and the preset parking safety distance and the path state in front of the passable state path is an obstacle state, controlling the unmanned vehicle to update the driving path; and if the path length is smaller than the sum of the current vehicle speed braking distance and the preset parking safety distance and the path state in front of the passable state path is in a drop point state, controlling the unmanned vehicle to trigger drop-proof warning.

In this embodiment, when controlling the unmanned vehicle to travel according to the point cloud clustering result, the path state is determined according to the point cloud clustering result. When the point cloud sensing states of all the point clouds in the modified grid map are falling point states or obstacle states, if the point cloud clustering result shows that the point cloud clustering area is smaller than the preset area threshold, the point cloud sensing states can be modified into passable states, and therefore the path states are determined to be passable states, and accuracy of determining the path states is improved. The preset area threshold may be set according to an actual application, which is not specifically limited in this embodiment. If the point cloud clustering result shows that the point cloud clustering area is larger than or equal to the preset area threshold, the path state can be directly determined as the point cloud perception state of all the point clouds in the modified grid map.

After determining the path state, a path length that is in a passable state on a current travel path of the unmanned vehicle may be determined according to the path state. The current driving path may refer to a driving path of the unmanned vehicle at the current time. And then comparing the path length with the sum of the current vehicle speed braking distance and the distance of the preset parking safety distance, and controlling the unmanned vehicle to run according to the comparison result. Specifically, if the path length is greater than or equal to the sum of the current vehicle speed braking distance and the preset parking safety distance, the path length which can be passed by the unmanned vehicle in front of the unmanned vehicle is longer, and no passing danger exists in a short time, and the unmanned vehicle can be controlled to continue to run at the moment; if the path length is smaller than the sum of the current vehicle speed braking distance and the preset parking safety distance, the fact that the path length before the unmanned vehicle can pass is short is indicated, and a passing danger exists in the near future, and the path state in front of the path in the passing state needs to be further determined. If the path state in front of the passable state path is an obstacle state, the unmanned vehicle can be controlled to update the running path; if the path state in front of the passable state path is a drop point state, the unmanned vehicle needs to be controlled to trigger the anti-drop warning.

According to the scheme, through the arrangement, the running of the unmanned vehicle can be controlled by adopting different control modes according to the comparison result of the sum of the path length and the distance between the current vehicle speed braking distance and the preset parking safety distance and the path state in front of the path in a passable state, so that the running safety of the unmanned vehicle can be effectively ensured.

According to the technical scheme, the grid map is constructed according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids; acquiring radar point cloud information of a current frame according to a laser radar deployed on an unmanned vehicle, and determining a point cloud sensing state of the point cloud according to height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state; determining a grid sensing state of the target grid according to the point cloud sensing states of all the point clouds falling into the target grid; and controlling the running of the unmanned vehicle according to the grid sensing states of all grids in the grid map. According to the technical scheme, the obstacle and the drop point can be accurately and effectively detected through the laser radar based on the constructed grid map, and the running efficiency and the running safety of the unmanned vehicle are improved.

In this embodiment, optionally, the obstacle states include a first obstacle state and a second obstacle state, wherein the first obstacle state characterizes the obstacle as perceived for the first time in the target grid and the second obstacle state characterizes the obstacle as perceived for the second time in the target grid; accordingly, after determining that the grid perceived state of the target grid is the obstacle state, the method further includes: if the state updating time of the target grid is smaller than the current frame point cloud acquisition time and the historical grid sensing state of the target grid is the obstacle state, determining that the grid sensing state of the target grid is the second obstacle state; otherwise, determining the grid sensing state of the target grid as the first obstacle state.

In this embodiment, after determining that the grid sensing state of the target grid is the obstacle state, the state update time of the target grid may be compared with the current frame point cloud acquisition time, and whether the state update of the target grid occurs in the current frame or in the history frame (i.e., the radar frame before the current frame) may be determined according to the comparison result. Specifically, if the state update time of the target grid is smaller than the current frame point cloud acquisition time, the state update of the target grid is indicated to occur in the history frame; if the state update time of the target grid is equal to the current frame point cloud acquisition time, indicating that the state update of the target grid occurs in the current frame. Further, if the state update time of the target grid is less than the current frame point cloud acquisition time, that is, the state update of the target grid occurs in the history frame, and the history grid sensing state of the target grid is an obstacle state, which indicates that the obstacle is sensed in the history frame, the grid sensing state of the target grid can be determined to be a second obstacle state at this time, and the second obstacle state is used for representing that the obstacle is not sensed for the first time in the target grid; otherwise, it indicates that the obstacle is not perceived in the history frame, at this time, the grid perceived state of the target grid may be determined as the first obstacle state, which is used to characterize that the obstacle is perceived in the target grid for the first time.

It should be noted that, if the absolute value of the difference between the state update time of the target grid and the current frame point cloud acquisition time is greater than the preset time difference, it indicates that the target grid is not updated for a long time, and at this time, the point cloud sensing states of the point clouds in the target grid need to be reset to the initialized state.

By means of the arrangement, the specific obstacle state can be judged according to different time stamps, so that whether the obstacle is perceived in the target grid for the first time or not can be determined.

Example two

Fig. 2 is a flowchart of a grid-based lidar sensing method according to a second embodiment of the present invention, which is optimized based on the foregoing embodiment.

As shown in fig. 2, the method of this embodiment specifically includes the following steps:

s210, constructing a grid map according to the driving area range of the unmanned vehicle; wherein, the grid map comprises a plurality of grids.

S220, acquiring radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determining a point cloud sensing state of the point cloud according to the height information of the point cloud information falling into a target grid.

Wherein the perceived state includes a passable state, an obstacle state, and a drop point state.

S230, if the type of the point cloud sensing state of all the point clouds in the target grid is one type, determining the point cloud sensing state as the grid sensing state of the target grid.

And S240, if the at least two point cloud sensing states are the falling point state and the other state, determining the grid sensing state of the target grid according to the other state.

Wherein the other state is a passable state and/or an obstacle state.

S250, if at least two point cloud sensing states are an obstacle state and a passable state, determining that the grid sensing state of the target grid is the obstacle state.

S260, modifying the point cloud sensing states of all the point clouds in the target grid according to the grid sensing states of the target grid in the grid map.

S270, clustering the point clouds according to the point cloud perception states of all the point clouds in the modified grid map.

S280, controlling the unmanned vehicle to run according to the point cloud clustering result.

According to the technical scheme provided by the embodiment of the invention, the obstacle and the drop point can be accurately and effectively detected by the laser radar based on the constructed grid map, so that the running efficiency and the running safety of the unmanned vehicle are improved.

Example III

Fig. 3 is a schematic structural diagram of a grid-based lidar sensing device according to a third embodiment of the present invention, where the device may perform the grid-based lidar sensing method according to any embodiment of the present invention, and the device has functional modules and beneficial effects corresponding to the performing method. As shown in fig. 3, the apparatus includes:

The grid map construction module 310 is configured to construct a grid map according to the driving area range of the unmanned vehicle; wherein the grid map comprises a plurality of grids;

the point cloud sensing state determining module 320 is configured to obtain radar point cloud information of a current frame according to a laser radar deployed on the unmanned vehicle, and determine a point cloud sensing state of the point cloud according to height information of the point cloud information falling into a target grid; the sensing state comprises a passable state, an obstacle state and a falling point state;

a grid sensing state determining module 330, configured to determine a grid sensing state of a target grid according to point cloud sensing states of all point clouds falling into the target grid;

and the unmanned vehicle running control module 340 is configured to control running of the unmanned vehicle according to grid sensing states of all grids in the grid map.

Optionally, the grid aware status determination module 330 includes:

a first grid sensing state determining unit, configured to determine, if the type of the point cloud sensing states of all the point clouds in the target grid is one, the point cloud sensing state as a grid sensing state of the target grid;

and the second grid perception state determining unit is used for determining the grid perception state of the target grid according to at least two point cloud perception states if the types of the point cloud perception states of all the point clouds in the target grid are at least two.

Optionally, the second grid-aware state determining unit is configured to:

if the at least two point cloud sensing states are a falling point state and other states, determining a grid sensing state of the target grid according to the other states; wherein the other state is a passable state and/or an obstacle state;

and if the at least two point cloud sensing states are the obstacle state and the passable state, determining that the grid sensing state of the target grid is the obstacle state.

Optionally, the obstacle states include a first obstacle state and a second obstacle state, wherein the first obstacle state characterizes the obstacle as perceived first in the target grid, and the second obstacle state characterizes the obstacle as perceived not first in the target grid;

correspondingly, the second grid-aware status determining unit is further configured to:

after determining that the grid sensing state of the target grid is an obstacle state, if the state updating time of the target grid is smaller than the current frame point cloud acquisition time and the historical grid sensing state of the target grid is an obstacle state, determining that the grid sensing state of the target grid is a second obstacle state;

Otherwise, determining the grid sensing state of the target grid as a first obstacle state.

Optionally, the unmanned vehicle driving control module 340 includes:

the point cloud perception state modification unit is used for modifying the point cloud perception states of all the point clouds in the target grid according to the grid perception states of the target grid in the grid map;

the point cloud clustering processing unit is used for clustering the point clouds according to the point cloud sensing states of all the point clouds in the modified grid map;

and the unmanned vehicle running control unit is used for controlling the running of the unmanned vehicle according to the point cloud clustering result.

Optionally, the unmanned vehicle driving control unit is configured to:

determining a path state according to the point cloud clustering result;

determining the path length of the unmanned vehicle in a passable state on the current running path according to the path state;

if the path length is greater than or equal to the sum of the current vehicle speed braking distance and the preset parking safety distance, controlling the unmanned vehicle to continue running;

if the path length is smaller than the sum of the current vehicle speed braking distance and the preset parking safety distance and the path state in front of the passable state path is an obstacle state, controlling the unmanned vehicle to update the driving path;

And if the path length is smaller than the sum of the current vehicle speed braking distance and the preset parking safety distance and the path state in front of the path in the passable state is in a falling point state, controlling the unmanned vehicle to trigger the anti-falling warning.

Optionally, the point cloud sensing state determining module 320 is configured to:

if the height information of the point cloud information is larger than the sum of the ground height and a preset height error threshold value, determining that the point cloud sensing state of the point cloud is an obstacle state;

if the height information of the point cloud information is smaller than the difference between the ground height and the preset height error threshold value, determining that the point cloud sensing state of the point cloud is a falling point state;

and if the absolute value of the difference between the height information of the point cloud information and the ground height is smaller than a preset height error threshold value, determining that the point cloud sensing state of the point cloud is a passable state.

The grid-based laser radar sensing device provided by the embodiment of the invention can execute the grid-based laser radar sensing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 4 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a grid-based lidar perception method.

In some embodiments, the grid-based lidar perception method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the grid-based lidar sensing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the grid-based lidar sensing method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 or 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.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of grid-based lidar perception, the method comprising:

2. The method of claim 1, wherein determining the grid perceived status of the target grid from the point cloud perceived statuses of all point clouds falling within the target grid comprises:

if the type of the point cloud sensing state of all the point clouds in the target grid is one, determining the point cloud sensing state as the grid sensing state of the target grid;

and if the types of the point cloud sensing states of all the point clouds in the target grid are at least two, determining the grid sensing state of the target grid according to the at least two point cloud sensing states.

3. The method of claim 2, wherein determining the grid perceived status of the target grid from at least two point cloud perceived statuses comprises:

4. A method according to claim 2 or 3, wherein the obstacle states comprise a first obstacle state and a second obstacle state, wherein the first obstacle state characterizes the obstacle as perceived first in the target grid and the second obstacle state characterizes the obstacle as perceived not first in the target grid;

accordingly, after determining that the grid perceived state of the target grid is an obstacle state, the method further includes:

if the state updating time of the target grid is smaller than the current frame point cloud acquisition time and the historical grid sensing state of the target grid is an obstacle state, determining that the grid sensing state of the target grid is a second obstacle state;

5. The method of claim 1, wherein controlling travel of the drone vehicle according to grid-aware status of all grids in the grid map comprises:

Modifying the point cloud perception states of all point clouds in a target grid according to the grid perception states of the target grid in the grid map;

clustering the point clouds according to the point cloud sensing states of all the point clouds in the modified grid map;

and controlling the unmanned vehicle to run according to the point cloud clustering result.

6. The method of claim 5, wherein controlling travel of the drone vehicle based on the point cloud clustering results comprises:

determining a path state according to the point cloud clustering result;

7. The method of claim 1, wherein determining a point cloud perceived state of the point cloud from altitude information of the point cloud information falling in the target grid comprises:

8. A grid-based lidar sensing device, the device comprising:

9. An electronic device, the electronic device comprising:

at least one processor; and

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the grid-based lidar sensing method of any of claims 1-7.

10. A computer readable storage medium storing computer instructions for causing a processor to implement the grid-based lidar perception method of any of claims 1-7 when executed.